CN108921743B - Confusion method and confusion education robot system based on big data and artificial intelligence - Google Patents
Confusion method and confusion education robot system based on big data and artificial intelligence Download PDFInfo
- Publication number
- CN108921743B CN108921743B CN201810630017.3A CN201810630017A CN108921743B CN 108921743 B CN108921743 B CN 108921743B CN 201810630017 A CN201810630017 A CN 201810630017A CN 108921743 B CN108921743 B CN 108921743B
- Authority
- CN
- China
- Prior art keywords
- statement
- sentence
- knowledge
- data
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013473 artificial intelligence Methods 0.000 title abstract description 9
- 238000005065 mining Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/065—Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A confusion method and a confusion education robot system based on big data and artificial intelligence comprise: and acquiring the problem of the user, analyzing and mining the big knowledge data to obtain a knowledge statement set corresponding to the problem of the user. The method and the system combine the problem of the user puzzlement with the big knowledge data, and the big knowledge data is used for teaching the problem, so that the user can obtain the latest knowledge related to the problem of the user puzzlement from the big knowledge data, the teaching is more targeted, the user can obtain the updated and more comprehensive knowledge, and the teaching effect is improved.
Description
Technical Field
The invention relates to the technical field of information, in particular to a confusion method and a confusion education robot system based on big data and artificial intelligence.
Background
Confucius, Scotta and Berla all adopt an interaction method to guide students to obtain knowledge, rather than directly infusing the knowledge to the students. The teacher also gives way, gives business and confusion. The existing teaching method usually stays in the stage of channel transfer and business, but the channel lacking in solution is a dead channel and dead knowledge, so that the phenomenon of high score and low energy can be created. In the prior art, a teacher often gives lessons according to own lesson preparation data, and the teacher answers the problems of students according to own knowledge.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: if only the textbook knowledge point is scratched completely in the teaching, if the students do not learn with the problem, the cultured students are always in a dead-remembered hard-backed type, the teaching becomes duck-filling type teaching, and the ability of the students to learn the knowledge alive cannot be cultured. In the prior art, the teaching effect is influenced by the personal knowledge of a teacher, and the knowledge and the answering time of the teacher are always limited, so that the aim of learning and teaching with problems cannot be fulfilled.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
Therefore, it is necessary to provide a confusion method and a confusion robot system based on big data and artificial intelligence to solve the disadvantages of narrow knowledge plane, poor pertinence and incapability of teaching with problems in the prior art.
In a first aspect, an embodiment of the present invention provides a method for obfuscation, where the method includes:
a question obtaining step, namely obtaining a question of a user and taking the question as a first statement;
and a sentence generating step of analyzing and mining the knowledge big data to obtain a knowledge sentence set corresponding to the first sentence, and taking the knowledge sentence set as a second sentence set.
Preferably, the generating a statement step comprises:
and outputting the sentences, namely outputting the optimal second sentence selected from the second sentence set to the user.
Preferably, after the step of obtaining the question comprises:
a type judging step, namely judging whether the type of the problem in the problem obtaining step is a theoretical problem or an application problem or an innovation problem: if the problem is a theoretical problem, executing the theoretical stage step; if the problem is the application problem, executing the step of the application stage; if the problem is an innovation problem, executing an innovation stage step;
a theoretical stage step, adding the problem in the problem obtaining step into theoretical problem big data;
an application stage step, adding the problem in the problem acquisition step into application problem big data;
an innovation stage step, namely acquiring a theoretical problem related to the problem in the problem acquisition step from big data of the theoretical problem, taking the theoretical problem as a first statement, executing a statement generation step to obtain a second statement set, and taking the second statement set as a third statement set; acquiring an application problem related to the problem in the problem acquisition step from application problem big data, taking the application problem as a first statement, executing a statement generation step to obtain a second statement set, and taking the second statement set as a fourth statement set; and comprehensively analyzing the third statement set and the fourth statement set to obtain a fifth statement set, and taking the fifth statement set as a second statement set.
Preferably, the step of comprehensively analyzing the third statement set and the fourth statement set in the step of the innovation stage to obtain a fifth statement set includes:
sentence matching, namely matching each third sentence in the third sentence set with each fourth sentence in the fourth sentence set;
selecting each third sentence and each fourth sentence with a larger matching degree, and adding a sentence pair set which is successfully matched;
and combining the sentences, namely combining the two sentences in each sentence pair in the sentence pair set which is successfully matched according to the matched sentence parts to obtain a fifth sentence.
Preferably, the step of generating sentences to analyze and mine the big knowledge data to obtain a knowledge sentence set corresponding to the user's question includes:
acquiring data, namely acquiring knowledge big data related to the first statement through the Internet or a cloud;
a matching calculation step, namely calculating the matching degree of each knowledge data in the knowledge big data and the first statement;
selecting the knowledge data with larger matching degree, and adding the selected knowledge data into the first knowledge data set;
personalized data step, obtaining personalized data of users;
an individual matching step, namely calculating the matching degree of each knowledge data in the first knowledge data set and the user individual data;
and a knowledge selecting step, namely selecting knowledge data with larger matching degree to obtain a second knowledge data set, and taking the second knowledge data set as a knowledge statement set corresponding to the problem of the user.
In a second aspect, an embodiment of the present invention provides a obfuscation system, where the system includes:
the problem obtaining module is used for obtaining a problem of a user and taking the problem as a first statement;
a statement generation module which analyzes and excavates the big knowledge data to obtain a knowledge statement set corresponding to the first statement, and takes the knowledge statement set as a second statement set;
and the output statement module is used for outputting the optimal second statement selected from the second statement set to the user.
Preferably, the system further comprises:
a type judging module, which judges whether the problem type in the problem obtaining module is a theoretical problem or an application problem or an innovation problem: if the problem is a theoretical problem, executing a theoretical stage module; if the problem is the application problem, the application phase module is executed; if the problem is an innovation problem, an innovation stage module is executed;
a theoretical stage module, which adds the problem in the problem acquisition module into the big data of the theoretical problem;
the application phase module is used for adding the problems in the problem acquisition module into the big data of the application problems;
the innovation stage module is used for acquiring the theoretical problem related to the problem in the problem acquisition module from the big data of the theoretical problem, taking the theoretical problem as a first statement, executing the data acquisition module and the statement generation module to obtain a second statement set, and taking the second statement set as a third statement set; acquiring an application problem related to the problem in the problem acquisition module from application problem big data, taking the application problem as a first statement, executing the data acquisition module and the statement generation module to obtain a second statement set, and taking the second statement set as a fourth statement set; and comprehensively analyzing the third statement set and the fourth statement set to obtain a fifth statement set, and taking the fifth statement set as a second statement set.
Preferably, the innovation phase module comprises:
the sentence matching module is used for matching each third sentence in the third sentence set with each fourth sentence in the fourth sentence set;
the sentence selecting module is used for selecting each third sentence and each fourth sentence with larger matching degree and adding a sentence pair set which is successfully matched;
and the sentence combination module is used for combining the two sentences in each sentence pair in the sentence pair set which is successfully matched according to the matched sentence part to obtain a fifth sentence.
Preferably, the statement generating module includes:
the data acquisition module acquires big knowledge data related to the first statement through the Internet or a cloud;
the matching calculation module is used for calculating the matching degree of each knowledge data in the knowledge big data and the first statement;
the data selection module is used for selecting the knowledge data with larger matching degree and adding the knowledge data into the first knowledge data set;
the personalized data module is used for acquiring personalized data of a user;
the individual matching module is used for calculating the matching degree of each knowledge data in the first knowledge data set and the user individual data;
and the knowledge selection module is used for selecting the knowledge data with larger matching degree to obtain a second knowledge data set, and the second knowledge data set is used as a knowledge statement set corresponding to the problem of the user.
In a third aspect, an embodiment of the present invention provides an educational robot system in which the confusion system according to any one of the second aspects is configured.
The embodiment of the invention has the following advantages and beneficial effects:
according to the confusion method and the confusion education robot system based on big data and artificial intelligence, the problems of the user are obtained, the big knowledge data are analyzed and mined, the knowledge statement set corresponding to the problems of the user is obtained, the problems which are puzzled by the user are combined with the big knowledge data, the big knowledge data are utilized to teach the problems, the user can obtain the latest knowledge related to the problems from the big knowledge data, the teaching is more targeted, the user can obtain the updated and more comprehensive knowledge, and the teaching effect is improved.
Drawings
FIG. 1 is a flow chart of a solution method provided in embodiment 1 of the present invention;
FIG. 2 is a flow chart of a obfuscation method provided in embodiment 2 of the present invention;
FIG. 3 is a flow chart of a obfuscation method provided in embodiment 3 of the present invention;
FIG. 4 is a flowchart of the type determining step provided in embodiment 3 of the present invention;
FIG. 5 is a flowchart of the steps of the innovation stage provided by embodiment 4 of the present invention;
FIG. 6 is a flowchart of the step of generating a statement provided by embodiment 5 of the present invention;
FIG. 7 is a schematic block diagram of a obfuscation system provided by embodiment 6 of the present invention;
FIG. 8 is a schematic block diagram of a obfuscation system provided by embodiment 7 of the present invention;
fig. 9 is a schematic block diagram of a type judgment module provided in embodiment 7 of the present invention;
FIG. 10 is a schematic block diagram of an innovation phase module provided by embodiment 8 of the present invention;
fig. 11 is a schematic block diagram of a generate statement module provided in embodiment 9 of the present invention.
Detailed Description
The technical solutions in the examples of the present invention are described in detail below with reference to the embodiments of the present invention.
The embodiment of the invention provides a confusion method and a confusion educational robot system based on big data and artificial intelligence. The big data technology comprises matching and analyzing and mining problem data and knowledge big data, and the artificial intelligence technology comprises matching technology of the problem data and the knowledge big data and analyzing and mining the knowledge big data.
Example 1, a method of delocalization, as illustrated in fig. 1, comprising:
the get question step S100 gets a question of the user as a first sentence. Preferably, the questions of the user are collected through a microphone, and are automatically recognized and translated into characters through voice translation software, and the characters are used as first sentences; or receiving question words input by a user through a touch screen or a keyboard, and taking the words as a first sentence.
And a sentence generating step S300, analyzing and mining the big knowledge data to obtain a knowledge sentence set corresponding to the first sentence, and taking the knowledge sentence set as a second sentence set.
Preferably, the user is a student; the user's question is an academic question or a question about a knowledge point or a question generated during class attendance; the knowledge big data can comprise the contents of articles, patents, courseware, web pages and the like, and can comprise the forms of words, voice, video and the like; the second set of sentences is essentially answers and confusion to the question.
The embodiment obtains the knowledge sentences capable of answering the student questions by searching the big knowledge data in a targeted manner aiming at the student questions, which is beneficial for the student to master the knowledge corresponding to the questioned questions and is beneficial for helping the student to master the questioned knowledge more quickly, and meanwhile, the knowledge corresponding to the answering questions comes from the big knowledge data instead of the personal answer of the teacher, so that the knowledge corresponding to the answering of the questions can be more comprehensive and new, and the knowledge contained in the big knowledge data is more comprehensive and new than the knowledge mastered by the teacher. The user also can be for arbitrary one person, the problem also can be for arbitrary problem, and the second sentence set that obtains through knowledge big data is just right the answer and the solution of problem to make the puzzlement can obtain solving, can "no teacher from oneself", thereby improved the efficiency and the effect of teaching and provide the shortcut for self-study.
Embodiment 2, according to the obfuscation method described in embodiment 1, as shown in fig. 2, after the step S300 of generating a statement, the method includes:
and a sentence outputting step S400, namely, outputting the optimal second sentence selected from the second sentence set to the user. Preferably, each second statement in the second statement set is matched with the first statement to obtain the matching degree of each second statement and the first statement; acquiring a second statement with the maximum matching degree; and expressing and recommending the second sentence with the maximum matching degree to the user in one or more modes of characters, voice and actions.
According to the embodiment, the optimal second sentence is directly recommended to the user, so that the user does not need to manually select a proper second sentence from the plurality of second sentences as the answer to the question, the time of the user is saved, and the speed and the satisfaction degree of the user for obtaining the answer to the question are improved.
Embodiment 3, the obfuscation method according to embodiment 1 or 2, as shown in fig. 3, comprising, after the acquire problem step S100:
as shown in fig. 4, a type determining step S200 determines whether the type of the problem in the problem obtaining step is a theoretical problem, an application problem, or an innovation problem: if it is a theoretical problem, a theoretical stage step S210 is executed; if it is an application problem, execute the application stage step S220; if it is an innovation issue, the step S230 of the innovation stage is executed. Preferably, the innovative questions refer to questions without ready answers, that is, questions from which answers cannot be directly searched from knowledge big data; the theoretical problem refers to a problem corresponding to theoretical knowledge; the application problem refers to a problem corresponding to knowledge application.
A theoretical stage step S210, adding the problem in the problem obtaining step into theoretical problem big data;
an application phase step S220, adding the question in the question acquisition step into application question big data;
an innovation stage step S230 of obtaining a theoretical problem related to the problem in the problem obtaining step S100 from the big data of the theoretical problem, taking the theoretical problem as a first statement, executing a statement generating step S300 to obtain a second statement set, and taking the second statement set as a third statement set; acquiring an application problem related to the problem in the problem acquisition step S100 from application problem big data, taking the application problem as a first statement, executing a statement generation step S300 to obtain a second statement set, and taking the second statement set as a fourth statement set; and comprehensively analyzing the third statement set and the fourth statement set to obtain a fifth statement set, and taking the fifth statement set as a second statement set.
The embodiment obtains different big knowledge data by judging the type of the question so as to obtain different answers, so that the answers aiming at the question are more targeted, and the embodiment is suitable for using corresponding stage steps in theoretical courses, experimental courses and innovation and creation courses in actual teaching; particularly, the knowledge statement set corresponding to the innovation problem can be obtained as an answer in the step of the innovation stage, so that the innovation of the user aiming at the problem can be facilitated, and the innovation capability of the user can be improved.
Embodiment 4 and the obfuscation method according to embodiment 3, as shown in fig. 5, the step of comprehensively analyzing the third statement set and the fourth statement set in the step S230 of the innovation stage to obtain a fifth statement set includes:
sentence matching step S231 matches each third sentence in the third sentence set with each fourth sentence in the fourth sentence set.
And a sentence selecting step S232, selecting each third sentence and each fourth sentence with a larger matching degree, and adding a sentence pair set with a successful matching. Preferably, the matching degrees are sorted from large to small; selecting the first K (K is a preset number) sentence pairs corresponding to the matching degrees; and adding a sentence pair set which is successfully matched.
And a sentence combining step S233, combining two sentences in each sentence pair in the sentence pair set successfully matched according to the matched sentence part, so as to obtain a fifth sentence. Preferably, two sentences in each sentence pair in the sentence pair set with successful matching are obtained; matching to obtain the parts with the same two sentences; replacing one sentence in the left or right part of the same part with another sentence in the left or right part of the same part; and taking another sentence obtained after the replacement as a fifth sentence. For example, the sentence pair is A1BC1, A2BC2, and the resulting fifth sentence is A2BC1, A1BC 2. For another example, the statement pair is AB, BC, and the fifth resulting statement is ABC.
Embodiment 5, according to the obfuscation method described in embodiment 1, as shown in fig. 6, the step of analyzing and mining the big knowledge data in the sentence generating step S300 to obtain a knowledge sentence set corresponding to the user' S question includes:
a data obtaining step S310, obtaining big knowledge data related to the first sentence through the internet or the cloud. Preferably, crawled through a web crawler, or obtained from a search engine such as ***, ***; and inputting the first sentence into a search engine, and taking a set of search results as the knowledge big data.
A matching calculation step S320, calculating a matching degree between each knowledge data in the knowledge big data and the first sentence. Preferably, each search result is matched with the first sentence to obtain a matching degree. Further preferably, the matching degree of each search result is determined as a proportion of the ranking of each search result in all search results to the total number of search results.
And a data selecting step S330, namely selecting the knowledge data with larger matching degree and adding the knowledge data into the first knowledge data set. Preferably, the matching degrees are sorted from large to small; selecting knowledge data corresponding to the first G (G is a preset number) matching degrees; a first set of knowledge data is added.
Personalized data step S340, obtaining personalized data of the user. Preferably, the personalization data comprises a profession or occupation of the user; if the user is a student, acquiring the specialty of the user; if the user is not a student, the occupation of the user is obtained.
An individuation matching step S350, calculating a matching degree between each knowledge data in the first knowledge data set and the user individuation data. Preferably, the user personalized data is segmented to obtain a keyword set, and the proportion of the number of the keywords appearing in each knowledge data in the keyword set in the total number of the keywords in the keyword set is counted to be used as the matching degree of each knowledge data and the user personalized data.
And a knowledge selecting step S360, selecting knowledge data with a larger matching degree to obtain a second knowledge data set, and taking the second knowledge data set as a knowledge statement set corresponding to the problem of the user. Preferably, the matching degrees are sorted from large to small; selecting knowledge data corresponding to the first H matching degrees (H is a preset number); adding a second set of knowledge data.
Embodiment 6, a delocalization system, as shown in fig. 7, the system comprising:
an acquire question module 100 for acquiring a question of a user as a first sentence;
the sentence generating module 300 is used for analyzing and mining the big knowledge data to obtain a knowledge sentence set corresponding to the first sentence, and taking the knowledge sentence set as a second sentence set;
and the output statement module 400 is used for outputting the optimal second statement selected from the second statement set to the user.
The preferred embodiment of example 6 corresponds to and is similar to the preferred embodiments of examples 1 and 2, and is not described again.
Embodiment 7, the obfuscation system according to embodiment 6, as shown in fig. 8, further comprising:
as shown in fig. 9, the type determining module 200 determines whether the type of the problem in the problem obtaining module is a theoretical problem, an application problem, or an innovation problem: is a theoretical problem, the theoretical stage module 210 is executed; if it is an application problem, the application phase module 220 is executed; if it is an innovation issue, then the innovation stage module 230 is executed;
a theoretical stage module 210, which adds the problem in the problem obtaining module to the big data of the theoretical problem;
an application phase module 220, which adds the question in the question acquisition module to the big data of the application question;
an innovation phase module 230, configured to obtain a theoretical problem related to the problem in the problem obtaining module 100 from the big data of the theoretical problem, use the theoretical problem as a first statement, execute the data obtaining module and the statement generating module 300 to obtain a second statement set, and use the second statement set as a third statement set; acquiring an application problem related to the problem in the problem acquisition module 100 from the big application problem data, taking the application problem as a first statement, executing the data acquisition module and the statement generation module 300 to obtain a second statement set, and taking the second statement set as a fourth statement set; and comprehensively analyzing the third statement set and the fourth statement set to obtain a fifth statement set, and taking the fifth statement set as a second statement set.
The preferred embodiment of example 7 corresponds to and is similar to the preferred embodiment of example 3, and is not described again.
Embodiment 8, the obfuscation system according to embodiment 7, as shown in fig. 10, wherein the innovation stage module 230 includes:
the sentence matching module 231 is used for matching each third sentence in the third sentence set with each fourth sentence in the fourth sentence set;
the sentence selecting module 232 selects each third sentence and each fourth sentence with a larger matching degree, and adds a sentence pair set with successful matching;
and the sentence combination module 233 is configured to combine the two sentences in each sentence pair in the sentence pair set successfully matched with each other according to the matched sentence part, so as to obtain a fifth sentence.
The preferred embodiment of example 8 corresponds to and is similar to the preferred embodiment of example 4, and is not described again.
Embodiment 9, the obfuscation system according to embodiment 6, as shown in fig. 11, wherein the sentence generation module 300 includes:
the data acquiring module 310 acquires big knowledge data related to the first sentence through the internet or a cloud;
the matching calculation module 320 is used for calculating the matching degree of each knowledge data in the knowledge big data and the first statement;
the data selecting module 330 selects knowledge data with a relatively high matching degree and adds the selected knowledge data into the first knowledge data set;
the personalized data module 340 acquires personalized data of the user;
the personalized matching module 350 is used for calculating the matching degree of each knowledge data in the first knowledge data set and the personalized data of the user;
the knowledge selecting module 360 selects knowledge data with a large matching degree to obtain a second knowledge data set, and uses the second knowledge data set as a knowledge statement set corresponding to the problem of the user.
The preferred embodiment of example 9 corresponds to and is similar to the preferred embodiment of example 5, and is not described again.
Embodiment 10, an educational robot system in which the confusion systems according to any one of embodiments 6 to 9 are respectively arranged.
The preferred embodiment of example 10 corresponds to and is similar to the preferred embodiments of examples 6-9, and is not described again.
According to the confusion method and the confusion education robot system based on big data and artificial intelligence, the problems of the user are obtained, the big knowledge data are analyzed and mined, the knowledge statement set corresponding to the problems of the user is obtained, the problems which are puzzled by the user are combined with the big knowledge data, the big knowledge data are utilized to teach the problems, the user can obtain the latest knowledge related to the problems from the big knowledge data, the teaching is more targeted, the user can obtain the updated and more comprehensive knowledge, and the teaching effect is improved.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (6)
1. A method of obfuscation, the method comprising:
a question obtaining step, namely obtaining a question of a user and taking the question as a first statement;
a sentence generating step, namely analyzing and mining the big knowledge data to obtain a knowledge sentence set corresponding to the first sentence, and taking the knowledge sentence set as a second sentence set;
after the step of obtaining the question comprises:
a type judging step, namely judging whether the type of the problem in the problem obtaining step is a theoretical problem or an application problem or an innovation problem: if the problem is a theoretical problem, executing the theoretical stage step; if the problem is the application problem, executing the step of the application stage; if the problem is an innovation problem, executing an innovation stage step;
a theoretical stage step, adding the problem in the problem obtaining step into theoretical problem big data;
an application stage step, adding the problem in the problem acquisition step into application problem big data;
an innovation stage step, namely acquiring a theoretical problem related to the problem in the problem acquisition step from big data of the theoretical problem, taking the theoretical problem as a first statement, executing a statement generation step to obtain a second statement set, and taking the second statement set as a third statement set; acquiring an application problem related to the problem in the problem acquisition step from application problem big data, taking the application problem as a first statement, executing a statement generation step to obtain a second statement set, and taking the second statement set as a fourth statement set; comprehensively analyzing the third statement set and the fourth statement set to obtain a fifth statement set, and taking the fifth statement set as a second statement set;
the step of comprehensively analyzing the third statement set and the fourth statement set in the step of the innovation stage to obtain a fifth statement set comprises the following steps:
sentence matching, namely matching each third sentence in the third sentence set with each fourth sentence in the fourth sentence set;
selecting each third sentence and each fourth sentence with a larger matching degree, and adding a sentence pair set which is successfully matched;
and combining the sentences, namely combining the two sentences in each sentence pair in the sentence pair set which is successfully matched according to the matched sentence parts to obtain a fifth sentence.
2. A method according to claim 1, wherein said generating a statement step is followed by:
and outputting the sentences, namely outputting the optimal second sentence selected from the second sentence set to the user.
3. A method according to claim 1, wherein said step of generating sentences and analyzing and mining said big knowledge data to obtain a set of knowledge sentences corresponding to said user's question comprises:
acquiring data, namely acquiring knowledge big data related to the first statement through the Internet or a cloud;
a matching calculation step, namely calculating the matching degree of each knowledge data in the knowledge big data and the first statement;
selecting the knowledge data with larger matching degree, and adding the selected knowledge data into the first knowledge data set;
personalized data step, obtaining personalized data of users;
an individual matching step, namely calculating the matching degree of each knowledge data in the first knowledge data set and the user individual data;
and a knowledge selecting step, namely selecting knowledge data with larger matching degree to obtain a second knowledge data set, and taking the second knowledge data set as a knowledge statement set corresponding to the problem of the user.
4. A delocalization system, characterized in that it comprises:
the problem obtaining module is used for obtaining a problem of a user and taking the problem as a first statement;
the sentence generating module is used for analyzing and mining the big knowledge data to obtain a knowledge sentence set corresponding to the first sentence, and the knowledge sentence set is used as a second sentence set;
the output statement module is used for outputting the optimal second statement selected from the second statement set to a user;
the system further comprises:
a type judging module, which judges whether the problem type in the problem obtaining module is a theoretical problem or an application problem or an innovation problem: if the problem is a theoretical problem, executing a theoretical stage module; if the problem is the application problem, the application phase module is executed; if the problem is an innovation problem, an innovation stage module is executed;
a theoretical stage module, which adds the problem in the problem acquisition module into the big data of the theoretical problem;
the application phase module is used for adding the problems in the problem acquisition module into the big data of the application problems;
the innovation stage module is used for acquiring the theoretical problem related to the problem in the problem acquisition module from the big data of the theoretical problem, taking the theoretical problem as a first statement, executing the data acquisition module and the statement generation module to obtain a second statement set, and taking the second statement set as a third statement set; acquiring an application problem related to the problem in the problem acquisition module from application problem big data, taking the application problem as a first statement, executing the data acquisition module and the statement generation module to obtain a second statement set, and taking the second statement set as a fourth statement set; comprehensively analyzing the third statement set and the fourth statement set to obtain a fifth statement set, and taking the fifth statement set as a second statement set;
the innovation stage module comprises:
the sentence matching module is used for matching each third sentence in the third sentence set with each fourth sentence in the fourth sentence set;
the sentence selecting module is used for selecting each third sentence and each fourth sentence with larger matching degree and adding a sentence pair set which is successfully matched;
and the sentence combination module is used for combining the two sentences in each sentence pair in the sentence pair set which is successfully matched according to the matched sentence part to obtain a fifth sentence.
5. The obfuscation system of claim 4, wherein the generate statement module comprises:
the data acquisition module acquires big knowledge data related to the first statement through the Internet or a cloud;
the matching calculation module is used for calculating the matching degree of each knowledge data in the knowledge big data and the first statement;
the data selection module is used for selecting the knowledge data with larger matching degree and adding the knowledge data into the first knowledge data set;
the personalized data module is used for acquiring personalized data of a user;
the individual matching module is used for calculating the matching degree of each knowledge data in the first knowledge data set and the user individual data;
and the knowledge selection module is used for selecting the knowledge data with larger matching degree to obtain a second knowledge data set, and the second knowledge data set is used as a knowledge statement set corresponding to the problem of the user.
6. An educational robot system characterized in that the educational robot is provided therein with the confusion system as set forth in any one of claims 4 to 5, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810630017.3A CN108921743B (en) | 2018-06-20 | 2018-06-20 | Confusion method and confusion education robot system based on big data and artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810630017.3A CN108921743B (en) | 2018-06-20 | 2018-06-20 | Confusion method and confusion education robot system based on big data and artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108921743A CN108921743A (en) | 2018-11-30 |
| CN108921743B true CN108921743B (en) | 2020-12-22 |
Family
ID=64420536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810630017.3A Active CN108921743B (en) | 2018-06-20 | 2018-06-20 | Confusion method and confusion education robot system based on big data and artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921743B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109862473B (en) * | 2019-03-07 | 2020-10-13 | 上海优谦智能科技有限公司 | Artificial intelligence helps teaching audio amplifier based on under classroom teaching scene |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678568A (en) * | 2013-12-09 | 2014-03-26 | 北京奇虎科技有限公司 | Method, server and system for providing problem solutions |
| CN103810218A (en) * | 2012-11-14 | 2014-05-21 | 北京百度网讯科技有限公司 | Problem cluster-based automatic asking and answering method and device |
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN105912712A (en) * | 2016-04-29 | 2016-08-31 | 华南师范大学 | Big data-based robot conversation control method and system |
| CN106294774A (en) * | 2016-08-11 | 2017-01-04 | 北京光年无限科技有限公司 | User individual data processing method based on dialogue service and device |
| CN106407425A (en) * | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| CN107293172A (en) * | 2017-08-23 | 2017-10-24 | 山东文捷智能动力有限公司 | One kind is learnt by oneself with intelligent expert system, artificial intelligence lecture system and implementation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140006012A1 (en) * | 2012-07-02 | 2014-01-02 | Microsoft Corporation | Learning-Based Processing of Natural Language Questions |
-
2018
- 2018-06-20 CN CN201810630017.3A patent/CN108921743B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810218A (en) * | 2012-11-14 | 2014-05-21 | 北京百度网讯科技有限公司 | Problem cluster-based automatic asking and answering method and device |
| CN103678568A (en) * | 2013-12-09 | 2014-03-26 | 北京奇虎科技有限公司 | Method, server and system for providing problem solutions |
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN105912712A (en) * | 2016-04-29 | 2016-08-31 | 华南师范大学 | Big data-based robot conversation control method and system |
| CN106294774A (en) * | 2016-08-11 | 2017-01-04 | 北京光年无限科技有限公司 | User individual data processing method based on dialogue service and device |
| CN106407425A (en) * | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| CN107293172A (en) * | 2017-08-23 | 2017-10-24 | 山东文捷智能动力有限公司 | One kind is learnt by oneself with intelligent expert system, artificial intelligence lecture system and implementation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108921743A (en) | 2018-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10249207B2 (en) | Educational teaching system and method utilizing interactive avatars with learning manager and authoring manager functions | |
| WO2014127183A2 (en) | Language learning systems and methods | |
| US10083219B2 (en) | Enhanced knowledge delivery and attainment using a question answering system | |
| CN110569364A (en) | online teaching method, device, server and storage medium | |
| US11978130B2 (en) | Semi-automated system and method for assessment of responses | |
| Wu et al. | Development of an inquiry-based learning support system based on an intelligent knowledge exploration approach | |
| Andrei et al. | Designing an American Sign Language avatar for learning computer science concepts for deaf or hard-of-hearing students and deaf interpreters | |
| Liu et al. | A bibliometric analysis of computer-assisted English learning from 2001 to 2020 | |
| Tsortanidou et al. | Unplugged computational thinking at K-6 education: Evidence from a multiple-case study in Spain | |
| Chauncey et al. | A framework and exemplars for ethical and responsible use of AI Chatbot technology to support teaching and learning | |
| CN108921743B (en) | Confusion method and confusion education robot system based on big data and artificial intelligence | |
| CN108920554B (en) | Creative method based on big data and artificial intelligence and creative education robot system | |
| Eslit | Elevating language acquisition through deep learning and meaningful pedagogy in an AI-evolving educational landscape | |
| Stojanova et al. | Application of VARK learning model on “Data Structures and Algorithms” course | |
| Averkieva et al. | Internet technologies in foreign language learning | |
| Drigas et al. | Web 2.0 learning strategies for disabled students | |
| Barria-Pineda et al. | Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions and Challenges. | |
| Middlebrook et al. | Showcase hybridity: A role for blogfolios | |
| CN112287115A (en) | Personalized teaching method, system and device based on knowledge mastery degree graph | |
| Ivanov et al. | Navigating Learning Paths with EDSense: An AI-Powered Learning Platform | |
| Addison et al. | Teaching Users to Work with Research Data: Case Studies in Architecture, History and Social Work | |
| Hall | Beyond teacher transmission and Googling information to more creative language learning | |
| Girotto et al. | A tool for integrating log and video data for exploratory analysis and model generation | |
| Kumar et al. | Distractor Re-ranking for Automatic Quiz Generation | |
| Joshi Kaustubh et al. | Android Based E-Learning Application “Class-E” |
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 |