CN115048513B - Knowledge base construction system based on natural language recognition customer service robot - Google Patents
Knowledge base construction system based on natural language recognition customer service robot Download PDFInfo
- Publication number
- CN115048513B CN115048513B CN202210612464.2A CN202210612464A CN115048513B CN 115048513 B CN115048513 B CN 115048513B CN 202210612464 A CN202210612464 A CN 202210612464A CN 115048513 B CN115048513 B CN 115048513B
- Authority
- CN
- China
- Prior art keywords
- module
- knowledge
- language
- unit
- processing
- 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
- 238000009411 base construction Methods 0.000 title claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 95
- 238000006243 chemical reaction Methods 0.000 claims abstract description 35
- 238000012790 confirmation Methods 0.000 claims abstract description 33
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 21
- 238000010276 construction Methods 0.000 claims abstract description 19
- 230000001502 supplementing effect Effects 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims description 14
- 230000009469 supplementation Effects 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013500 data storage Methods 0.000 abstract description 2
- 238000000034 method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Security & Cryptography (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge base construction system based on a natural language recognition customer service robot, which comprises a preset knowledge input unit, a knowledge base construction system, a recognition authority unit, a natural language conversion construction unit, a scene knowledge construction unit, a incomplete language supplementing unit, a knowledge compensation system and a knowledge feedback unit, wherein the output end of the preset knowledge input unit is electrically connected with the input end of the knowledge base construction system, and the preset knowledge input unit is in bidirectional connection with the recognition authority unit, and the invention has the beneficial effects that: by adding the identification authority unit, the key confirmation and cloud information confirmation processing are needed when the internal data is changed and added, the safety of internal data storage is improved, and by adding the natural language conversion establishing unit, the voice conversion processing is carried out on different natural languages, so that the method is suitable for people with various natural languages.
Description
Technical Field
The invention relates to the technical field of natural language identification customer service robots, in particular to a knowledge base construction system based on a natural language identification customer service robot.
Background
The knowledge base is a knowledge-based intelligent system, and in the use of a natural language recognition customer service robot, the knowledge base construction needs to be carried out on the robot, but the conventional knowledge base construction system does not have scene pairing during question answering, cannot better communicate with a user, and does not have intelligent recognition compensation processing on incomplete sentences during processing of questions.
Disclosure of Invention
The invention aims to provide a knowledge base construction system based on a natural language recognition customer service robot, which aims to solve the problems that the conventional knowledge base construction system proposed in the background art does not have scene pairing during question answering, cannot better communicate with a user, and does not have intelligent recognition compensation processing on incomplete sentences during processing of questions.
In order to achieve the above purpose, the present invention provides the following technical solutions: the knowledge base construction system based on the natural language recognition customer service robot comprises a preset knowledge input unit, a knowledge base construction system, a recognition authority unit, a natural language conversion construction unit, a scenario knowledge construction unit, a incomplete language supplementation unit, a knowledge compensation system and a knowledge feedback unit, wherein the output end of the preset knowledge input unit is electrically connected with the input end of the knowledge base construction system, the preset knowledge input unit is in bidirectional connection with the recognition authority unit, the knowledge base construction system is in bidirectional connection with the natural language conversion construction unit, the knowledge base construction system is in bidirectional connection with the scenario knowledge construction unit, the output end of the knowledge base construction system is electrically connected with the input end of the incomplete language supplementation unit, the incomplete language supplementation unit is in bidirectional connection with the knowledge compensation system, the output end of the knowledge compensation system is electrically connected with the input end of the knowledge feedback unit, and the output end of the knowledge feedback unit is electrically connected with the input end of the preset knowledge input unit;
The preset knowledge input unit is used for inputting natural language required by the customer service robot prepared in advance into a knowledge base for establishment;
the knowledge base construction system is used for carrying out differential classification on knowledge data and storing the classified knowledge data;
The identification authority unit is used for performing authority verification processing when a preset knowledge input unit is operated, and is also used for performing encryption processing in the knowledge base construction system;
the natural language conversion building unit is used for classifying and distinguishing the recognized languages and also used for carrying out language conversion processing on the distinguished texts;
the scene knowledge construction unit is used for carrying out proper scene matching and carrying out question reply processing when the response processing is established;
The incomplete language supplementing unit is used for carrying out incomplete supplementing complete processing on the language when the language is incomplete;
the knowledge compensation system is used for carrying out AI identification on the collected languages and carrying out back-questioning processing on the languages which are not successfully identified;
the knowledge feedback unit is used for feeding back the knowledge data which is newly obtained after the incomplete language supplementing unit and the knowledge compensation system are processed.
As a preferred embodiment of the present invention: the knowledge base construction system comprises a language collection module, a knowledge classification module, a cloud storage module and a weight setting unit, wherein the output end of the language collection module is electrically connected with the input end of the knowledge classification module, the output end of the knowledge classification module is electrically connected with the input end of the cloud storage module, and the cloud storage module is in bidirectional connection with the weight setting unit;
The language collection module is used for receiving and processing knowledge data and simultaneously receiving and processing data when an external problem is sent out;
The knowledge classification module is used for classifying the received knowledge data into knowledge categories;
the cloud storage module is used for storing the collected knowledge data through a cloud;
The weight setting unit is used for performing feature arrangement on the received knowledge data and performing storage processing.
As a preferred embodiment of the present invention: the weight setting unit comprises a receiving time ordering module and a feature extraction module, wherein the output end of the receiving time ordering module is electrically connected with the input end of the feature extraction module, the receiving time ordering module is used for carrying out time ordering processing on knowledge data input into the cloud storage module in different time periods, and the feature extraction module is used for carrying out feature language extraction processing on the knowledge data and carrying out rapid classification arrangement processing on extracted feature languages.
As a preferred embodiment of the present invention: the identification authority unit comprises a key confirmation module and a cloud information confirmation module, wherein the output end of the key confirmation module is electrically connected with the input end of the cloud information confirmation module, the key confirmation module is used for carrying out key confirmation processing when knowledge data is input, and the cloud information confirmation module is used for carrying out cloud information face confirmation processing on operators during knowledge input processing.
As a preferred embodiment of the present invention: the natural language conversion building unit comprises a language identification module, a text information conversion module and a text language-to-speech module, wherein the output end of the language identification module is electrically connected with the input end of the text information conversion module, and the output end of the text information conversion module is electrically connected with the input end of the text language-to-speech module;
the language identification module is used for carrying out language type identification processing on the received language data;
the text information conversion module is used for carrying out text information conversion processing after distinguishing the language types;
The text language-to-speech module is used for converting text information into required language-like speech.
As a preferred embodiment of the present invention: the scene knowledge construction unit comprises a knowledge keyword input module, a keyword scene matching module and a language answer matching module, wherein the output end of the knowledge keyword input module is electrically connected with the input end of the keyword scene matching module, and the output end of the keyword scene matching module is electrically connected with the input end of the language answer matching module;
The knowledge keyword input module is used for inputting keywords of knowledge data and correspondingly processing the input keywords and the knowledge data;
the keyword scene pairing module is used for carrying out proper dialogue scene pairing processing on the identified keywords;
The language answer matching module is used for carrying out dialogue answer knowledge data matching processing after the dialogue scene is matched.
As a preferred embodiment of the present invention: the incomplete language supplementing unit comprises an incomplete threshold value confirming module, a knowledge base sentence integral comparison module and a knowledge base word interpretation module, wherein the output end of the incomplete threshold value confirming module is electrically connected with the input end of the knowledge base sentence integral comparison module, and the output end of the knowledge base sentence integral comparison module is electrically connected with the input end of the knowledge base word interpretation module;
The incomplete threshold value confirmation module is used for confirming the loss threshold value of the characters which are identified to be lost in the incomplete language data;
the knowledge base whole sentence comparison module is used for comparing the received incomplete language data with similar sentences in the knowledge base;
the knowledge base single word interpretation module is used for interpreting the word meanings of the received incomplete language data one by one and matching the word meanings.
As a preferred embodiment of the present invention: the knowledge compensation system comprises a language acquisition unit and a repeated question-back unit, wherein the language acquisition unit is in bidirectional connection with the incomplete language supplementing unit, the language acquisition unit is in bidirectional connection with the repeated question-back unit, the output end of the repeated question-back unit is electrically connected with the input end of the knowledge feedback unit, the language acquisition unit is used for carrying out question recognition processing on the collected language data, and the repeated question-back unit is used for carrying out question-back user operation on unidentified language data questions and answers.
As a preferred embodiment of the present invention: the language acquisition unit comprises an AI language identification module, a similar problem expansion module and a problem classification reply module, wherein the output end of the AI language identification module is electrically connected with the input end of the similar problem expansion module, and the output end of the similar problem expansion module is electrically connected with the input end of the problem classification reply module;
The AI language identification module is used for carrying out AI identification allocation processing on the questions raised by the language data;
the similar problem expansion module is used for searching knowledge data similar to the problem and expanding the problem in the knowledge base when the problem proposed by the language data is identified;
The question classification replying module is used for classifying and replying questions presented by the language data.
Compared with the prior art, the invention has the beneficial effects that: the invention realizes that key confirmation and cloud information confirmation processing are needed when internal data are changed and added by adding the identification authority unit, improves the safety of internal data storage, realizes that voice conversion processing is carried out on different types of natural languages by adding the natural language conversion establishing unit, is applicable to crowds with various natural languages, improves the working efficiency, realizes that keyword extraction is carried out on sentences and proper scene matching is carried out by adding the scene knowledge establishing unit, and is suitable for carrying out proper dialogue answer processing with different scenes.
Drawings
FIG. 1 is a block diagram of a system of the present invention;
fig. 2 is a block diagram of a weight setting unit system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides a technical solution: the knowledge base construction system based on the natural language recognition customer service robot comprises a preset knowledge input unit, a knowledge base construction system, a recognition authority unit, a natural language conversion establishment unit, a scenario knowledge construction unit, an incomplete language supplementation unit, a knowledge compensation system and a knowledge feedback unit, wherein the output end of the preset knowledge input unit is electrically connected with the input end of the knowledge base construction system, the preset knowledge input unit is in bidirectional connection with the recognition authority unit, the knowledge base construction system is in bidirectional connection with the natural language conversion establishment unit, the knowledge base construction system is in bidirectional connection with the scenario knowledge construction unit, the output end of the knowledge base construction system is electrically connected with the input end of the incomplete language supplementation unit, the incomplete language supplementation unit is in bidirectional connection with the knowledge compensation system, the output end of the knowledge compensation system is electrically connected with the input end of the knowledge feedback unit, and the output end of the knowledge feedback unit is electrically connected with the input end of the preset knowledge input unit;
the preset knowledge input unit is used for inputting natural language required by the customer service robot prepared in advance into the knowledge base for establishment, and inputting the natural language knowledge base for the customer service robot and initially establishing the knowledge base;
the knowledge base construction system is used for distinguishing and classifying the knowledge data, storing the classified knowledge data, classifying and storing the knowledge data, and matching the corresponding knowledge data faster in use, so that the recognition efficiency is improved;
The identification authority unit is used for performing authority verification processing when the preset knowledge input unit is operated, and is also used for performing encryption processing in the knowledge base construction system, and performing encryption processing to protect the preset knowledge input unit and the knowledge base construction system, so that verification processing is required during operation, and safety is improved;
the natural language conversion building unit is used for classifying and distinguishing the recognized languages, and is also used for carrying out language conversion processing on the distinguished texts, recognizing different natural languages and applying corresponding languages, so that the working efficiency is improved;
the scene knowledge construction unit is used for carrying out proper scene matching and question reply processing when the response processing is established, matching the scenes and improving the question and answer efficiency;
The incomplete language supplementing unit is used for supplementing complete incomplete language processing when incomplete language appears, and intelligently compensating sentences when incomplete sentences are received;
the knowledge compensation system is used for carrying out AI identification on the collected languages and carrying out back-questioning processing on the languages which are not successfully identified;
the knowledge feedback unit is used for feeding back the knowledge data which is newly obtained after the incomplete language supplementing unit and the knowledge compensation system are processed.
The knowledge base construction system comprises a language collection module, a knowledge classification module, a cloud storage module and a weight setting unit, wherein the output end of the language collection module is electrically connected with the input end of the knowledge classification module, the output end of the knowledge classification module is electrically connected with the input end of the cloud storage module, and the cloud storage module is in bidirectional connection with the weight setting unit;
The language collection module is used for receiving and processing knowledge data and simultaneously receiving and processing data when an external problem is sent out;
The knowledge classification module is used for classifying the received knowledge data into knowledge categories;
The cloud storage module is used for storing the collected knowledge data through the cloud, distinguishing the knowledge data types through the knowledge classification module, and storing the knowledge data after distinguishing;
the weight setting unit is used for performing feature arrangement on the received knowledge data and performing storage processing.
The weight setting unit comprises a receiving time ordering module and a feature extraction module, wherein the output end of the receiving time ordering module is electrically connected with the input end of the feature extraction module, the receiving time ordering module is used for carrying out time ordering processing on knowledge data input into the cloud storage module in different time periods, the feature extraction module is used for carrying out feature language extraction processing on the knowledge data, extracting feature languages are subjected to rapid classification arrangement processing, the knowledge data input into the cloud storage module in different time periods are subjected to time ordering processing, the features are extracted, and proper weight distribution is carried out when the knowledge data are emergent feature language data.
The identification authority unit comprises a key confirmation module and a cloud information confirmation module, wherein the output end of the key confirmation module is electrically connected with the input end of the cloud information confirmation module, the key confirmation module is used for carrying out key confirmation processing when knowledge data is input, the cloud information confirmation module is used for carrying out cloud information face confirmation processing on operators during knowledge input processing, the key confirmation module is used for inputting keys and carrying out key verification processing, and after verification processing, the cloud information and user information are matched and confirmed, so that management safety and working stability are improved.
The natural language conversion building unit comprises a language identification module, a text information conversion module and a text language-to-speech module, wherein the output end of the language identification module is electrically connected with the input end of the text information conversion module, and the output end of the text information conversion module is electrically connected with the input end of the text language-to-speech module;
The language identification module is used for carrying out language type identification processing on the received language data;
The text information conversion module is used for carrying out text information conversion processing after distinguishing the language types;
the text-to-speech module is used for converting text information into required language speech, identifying the language when encountering different languages, identifying natural language types, converting human voice language into text information, and converting the text information into matched speech.
The scene knowledge construction unit comprises a knowledge keyword input module, a keyword scene matching module and a language answer matching module, wherein the output end of the knowledge keyword input module is electrically connected with the input end of the keyword scene matching module, and the output end of the keyword scene matching module is electrically connected with the input end of the language answer matching module;
The knowledge keyword input module is used for inputting keywords of knowledge data and correspondingly processing the input keywords and the knowledge data;
The keyword scene pairing module is used for carrying out proper dialogue scene pairing processing on the identified keywords;
The language answer matching module is used for carrying out dialogue answer knowledge data matching processing after matching dialogue scenes, and carrying out scene matching on the language keywords collected by the language collecting module, and carrying out proper answer processing for different scene states after scene matching.
The incomplete language supplementing unit comprises an incomplete threshold value confirming module, a knowledge base sentence whole comparing module and a knowledge base word interpretation module, wherein the output end of the incomplete threshold value confirming module is electrically connected with the input end of the knowledge base sentence whole comparing module, and the output end of the knowledge base sentence whole comparing module is electrically connected with the input end of the knowledge base word interpretation module;
The incomplete threshold value confirmation module is used for confirming the missing threshold value of the characters which are identified to be missing in the incomplete language data;
the knowledge base whole sentence comparison module is used for comparing the received incomplete language data with similar sentences in the knowledge base;
the knowledge base single word interpretation module is used for interpreting word meanings of received incomplete language data one by one and matching the word meanings, so that the repair efficiency of the incomplete language data is improved.
The knowledge compensation system comprises a language acquisition unit and a repeated question-back unit, wherein the language acquisition unit is in bidirectional connection with the incomplete language supplementing unit, the language acquisition unit is in bidirectional connection with the repeated question-back unit, the output end of the repeated question-back unit is electrically connected with the input end of the knowledge feedback unit, the language acquisition unit is used for carrying out question recognition processing on collected language data, and the repeated question-back unit is used for carrying out question-back user operation on unidentified language data questions and answers, so that the accuracy and the working efficiency of question processing are improved.
The system comprises a language acquisition unit, a question classification and response module and a question classification and response module, wherein the language acquisition unit comprises an AI language identification module, a similar question expansion module and a question classification and response module, the output end of the AI language identification module is electrically connected with the input end of the similar question expansion module, and the output end of the similar question expansion module is electrically connected with the input end of the question classification and response module;
The AI language identification module is used for carrying out AI identification distribution processing on the problems presented by the language data, carrying out problem matching on the presented language data problems, and improving the working efficiency;
The similar problem expansion module is used for searching knowledge data similar to the problem and expanded problems in the knowledge base when the problem presented by the language data at the recognition position is identified, expanding the following problems, and matching the following series of problems, so that the matching efficiency of the later-stage answer is improved;
the question classification replying module is used for classifying and replying the questions presented by the language data.
Specifically, when in use, the key confirmation module is used for inputting keys and carrying out key verification processing, cloud information and user information are matched and confirmed after verification processing, knowledge data is input to the knowledge base construction system through the preset knowledge input unit after verification, the knowledge data types are collected and are subjected to distinguishing processing through the knowledge classification module, cloud storage is carried out after distinguishing, the voice of an external consultation customer service robot is collected through the language collection module, knowledge data input into the cloud storage module in different time periods are subjected to time sequencing processing, characteristic language extraction processing is carried out, characteristic language is extracted and is subjected to rapid classifying arrangement processing, languages are identified when different languages are encountered, natural language types are confirmed after identification and are converted into text information, the text information is converted into matched voice processing, communication scene efficiency is improved, all keywords are established through the knowledge keyword input module of the scene knowledge scene construction unit, the keywords collected through the language collection module are matched, appropriate answer processing is carried out on different scene states, when a dialogue is received through the language collection module, when a incomplete sentence is input into the knowledge data in the cloud storage module in different time periods, the dialogue is subjected to the time sequencing processing, the problem is set up, the problem is directly solved by setting a threshold value of a comparison question and is set up, the answer is directly after the question is set up in a threshold value is set, the answer is set up, and the question is directly is compared with a question is set up in a threshold-of a question is set, and is quite poor, and the question is set up, the incomplete language supplementing unit can not recognize the language data and the questions which can not be answered by the repeated question-back unit are input into the preset knowledge input unit through the knowledge feedback unit for memorizing and processing.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The knowledge base construction system based on the natural language recognition customer service robot is characterized by comprising a preset knowledge input unit, a knowledge base construction system, a recognition authority unit, a natural language conversion construction unit, a scenario knowledge construction unit, a incomplete language supplementation unit, a knowledge compensation system and a knowledge feedback unit, wherein the output end of the preset knowledge input unit is electrically connected with the input end of the knowledge base construction system, the preset knowledge input unit is in bidirectional connection with the recognition authority unit, the knowledge base construction system is in bidirectional connection with the natural language conversion construction unit, the knowledge base construction system is in bidirectional connection with the scenario knowledge construction unit, the output end of the knowledge base construction system is electrically connected with the input end of the incomplete language supplementation unit, the output end of the knowledge compensation system is electrically connected with the input end of the knowledge feedback unit, and the output end of the incomplete language supplementation unit is electrically connected with the input end of the knowledge feedback unit;
The preset knowledge input unit is used for inputting natural language required by the customer service robot prepared in advance into a knowledge base for establishment;
the knowledge base construction system is used for carrying out differential classification on knowledge data and storing the classified knowledge data;
The identification authority unit is used for performing authority verification processing when a preset knowledge input unit is operated, and is also used for performing encryption processing in the knowledge base construction system;
the natural language conversion building unit is used for classifying and distinguishing the recognized languages and also used for carrying out language conversion processing on the distinguished texts;
the scene knowledge construction unit is used for carrying out proper scene matching and carrying out question reply processing when the response processing is established;
The incomplete language supplementing unit is used for carrying out incomplete supplementing complete processing on the language when the language is incomplete;
the knowledge compensation system is used for carrying out AI identification on the collected languages and carrying out back-questioning processing on the languages which are not successfully identified;
the knowledge feedback unit is used for feeding back the knowledge data which is newly obtained after the incomplete language supplementing unit and the knowledge compensation system are processed.
2. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 1, wherein: the knowledge base construction system comprises a language collection module, a knowledge classification module, a cloud storage module and a weight setting unit, wherein the output end of the language collection module is electrically connected with the input end of the knowledge classification module, the output end of the knowledge classification module is electrically connected with the input end of the cloud storage module, and the cloud storage module is in bidirectional connection with the weight setting unit;
The language collection module is used for receiving and processing knowledge data and simultaneously receiving and processing data when an external problem is sent out;
The knowledge classification module is used for classifying the received knowledge data into knowledge categories;
the cloud storage module is used for storing the collected knowledge data through a cloud;
The weight setting unit is used for performing feature arrangement on the received knowledge data and performing storage processing.
3. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 2, wherein: the weight setting unit comprises a receiving time ordering module and a feature extraction module, wherein the output end of the receiving time ordering module is electrically connected with the input end of the feature extraction module, the receiving time ordering module is used for carrying out time ordering processing on knowledge data input into the cloud storage module in different time periods, and the feature extraction module is used for carrying out feature language extraction processing on the knowledge data and carrying out rapid classification arrangement processing on extracted feature languages.
4. A knowledge base construction system based on a natural language recognition customer service robot according to claim 3, wherein: the identification authority unit comprises a key confirmation module and a cloud information confirmation module, wherein the output end of the key confirmation module is electrically connected with the input end of the cloud information confirmation module, the key confirmation module is used for carrying out key confirmation processing when knowledge data is input, and the cloud information confirmation module is used for carrying out cloud information face confirmation processing on operators during knowledge input processing.
5. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 4, wherein: the natural language conversion building unit comprises a language identification module, a text information conversion module and a text language-to-speech module, wherein the output end of the language identification module is electrically connected with the input end of the text information conversion module, and the output end of the text information conversion module is electrically connected with the input end of the text language-to-speech module;
the language identification module is used for carrying out language type identification processing on the received language data;
the text information conversion module is used for carrying out text information conversion processing after distinguishing the language types;
The text language-to-speech module is used for converting text information into required language-like speech.
6. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 5, wherein: the scene knowledge construction unit comprises a knowledge keyword input module, a keyword scene matching module and a language answer matching module, wherein the output end of the knowledge keyword input module is electrically connected with the input end of the keyword scene matching module, and the output end of the keyword scene matching module is electrically connected with the input end of the language answer matching module;
The knowledge keyword input module is used for inputting keywords of knowledge data and correspondingly processing the input keywords and the knowledge data;
the keyword scene pairing module is used for carrying out proper dialogue scene pairing processing on the identified keywords;
The language answer matching module is used for carrying out dialogue answer knowledge data matching processing after the dialogue scene is matched.
7. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 6, wherein: the incomplete language supplementing unit comprises an incomplete threshold value confirming module, a knowledge base sentence integral comparison module and a knowledge base word interpretation module, wherein the output end of the incomplete threshold value confirming module is electrically connected with the input end of the knowledge base sentence integral comparison module, and the output end of the knowledge base sentence integral comparison module is electrically connected with the input end of the knowledge base word interpretation module;
The incomplete threshold value confirmation module is used for confirming the loss threshold value of the characters which are identified to be lost in the incomplete language data;
the knowledge base whole sentence comparison module is used for comparing the received incomplete language data with similar sentences in the knowledge base;
the knowledge base single word interpretation module is used for interpreting the word meanings of the received incomplete language data one by one and matching the word meanings.
8. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 7, wherein: the knowledge compensation system comprises a language acquisition unit and a repeated question-back unit, wherein the language acquisition unit is in bidirectional connection with the incomplete language supplementing unit, the language acquisition unit is in bidirectional connection with the repeated question-back unit, the output end of the repeated question-back unit is electrically connected with the input end of the knowledge feedback unit, the language acquisition unit is used for carrying out question recognition processing on the collected language data, and the repeated question-back unit is used for carrying out question-back user operation on unidentified language data questions and answers.
9. The knowledge base construction system based on natural language identification customer service robot as claimed in claim 8, wherein: the language acquisition unit comprises an AI language identification module, a similar problem expansion module and a problem classification reply module, wherein the output end of the AI language identification module is electrically connected with the input end of the similar problem expansion module, and the output end of the similar problem expansion module is electrically connected with the input end of the problem classification reply module;
The AI language identification module is used for carrying out AI identification allocation processing on the questions raised by the language data;
the similar problem expansion module is used for searching knowledge data similar to the problem and expanding the problem in the knowledge base when the problem proposed by the language data is identified;
The question classification replying module is used for classifying and replying questions presented by the language data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210612464.2A CN115048513B (en) | 2022-05-31 | 2022-05-31 | Knowledge base construction system based on natural language recognition customer service robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210612464.2A CN115048513B (en) | 2022-05-31 | 2022-05-31 | Knowledge base construction system based on natural language recognition customer service robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115048513A CN115048513A (en) | 2022-09-13 |
| CN115048513B true CN115048513B (en) | 2024-05-17 |
Family
ID=83158962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210612464.2A Active CN115048513B (en) | 2022-05-31 | 2022-05-31 | Knowledge base construction system based on natural language recognition customer service robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115048513B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054042A (en) * | 2010-12-30 | 2011-05-11 | 百度在线网络技术（北京）有限公司 | Service method and site for exchanging knowledge information and question and answer exchange platform |
| CN106934068A (en) * | 2017-04-10 | 2017-07-07 | 江苏东方金钰智能机器人有限公司 | The method that robot is based on the semantic understanding of environmental context |
| CN112036906A (en) * | 2020-07-31 | 2020-12-04 | 苏宁金融科技(南京)有限公司 | Data processing method, device and equipment |
| CN112052317A (en) * | 2020-08-19 | 2020-12-08 | 杭州古珀医疗科技有限公司 | Medical knowledge base intelligent retrieval system and method based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10127274B2 (en) * | 2016-02-08 | 2018-11-13 | Taiger Spain Sl | System and method for querying questions and answers |
-
2022
- 2022-05-31 CN CN202210612464.2A patent/CN115048513B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054042A (en) * | 2010-12-30 | 2011-05-11 | 百度在线网络技术（北京）有限公司 | Service method and site for exchanging knowledge information and question and answer exchange platform |
| CN106934068A (en) * | 2017-04-10 | 2017-07-07 | 江苏东方金钰智能机器人有限公司 | The method that robot is based on the semantic understanding of environmental context |
| CN112036906A (en) * | 2020-07-31 | 2020-12-04 | 苏宁金融科技(南京)有限公司 | Data processing method, device and equipment |
| CN112052317A (en) * | 2020-08-19 | 2020-12-08 | 杭州古珀医疗科技有限公司 | Medical knowledge base intelligent retrieval system and method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 基于多级检索的自动问答系统研究;蔡刚山;叶俊;周曼丽;;科学技术与工程;20070228(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115048513A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110457689B (en) | Semantic processing method and related device | |
| CN108595696A (en) | A kind of human-computer interaction intelligent answering method and system based on cloud platform | |
| CN105895101A (en) | Speech processing equipment and processing method for power intelligent auxiliary service system | |
| CN109460459B (en) | Log learning-based dialogue system automatic optimization method | |
| CN108984778A (en) | A kind of intelligent interaction automatically request-answering system and self-teaching method | |
| CN109408555B (en) | Data type identification method and device and data storage method and device | |
| CN109147768A (en) | A kind of audio recognition method and system based on deep learning | |
| CN105261356A (en) | Voice recognition system and method | |
| CN110516057B (en) | Petition question answering method and device | |
| CN115292461B (en) | Man-machine interaction learning method and system based on voice recognition | |
| CN112632244A (en) | Man-machine conversation optimization method and device, computer equipment and storage medium | |
| CN110196897B (en) | Case identification method based on question and answer template | |
| CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
| CN110321414B (en) | Artificial intelligence consultation service method and system based on deep learning | |
| CN113705192B (en) | Text processing method, device and storage medium | |
| CN115048513B (en) | Knowledge base construction system based on natural language recognition customer service robot | |
| CN112182019B (en) | Semantic parsing search method for power grid statistics professional index feature extraction | |
| TWI751504B (en) | Dialogue system and method for human-machine cooperation | |
| CN116911869A (en) | Intelligent customer service system based on artificial intelligence and method thereof | |
| CN112579666A (en) | Intelligent question-answering system and method and related equipment | |
| CN110688473A (en) | Method for robot to dynamically acquire information | |
| CN112382276A (en) | Power grid material information acquisition method and device based on voice semantic recognition | |
| CN112417113A (en) | Intelligent question-answering method and system based on voice recognition technology | |
| CN113053416A (en) | Speech emotion recognition system based on knowledge graph | |
| CN112652303A (en) | Local engine voice recognition and interaction method |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230627 Address after: Floor 1, No. 50, section 4, Renmin South Road, Wuhou District, Chengdu, Sichuan 610000 Applicant after: Marketing service center of State Grid Sichuan Electric Power Co. Applicant after: Kong Deshi Applicant after: Zhang Liyan Applicant after: Li Bo Address before: 88-4-1, Guanghe 2nd Street, High-tech Zone, Chengdu, Sichuan 610000 Applicant before: Kong Deshi Applicant before: Zhang Liyan Applicant before: Li Bo |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231218 Address after: Floor 1, No. 50, section 4, Renmin South Road, Wuhou District, Chengdu, Sichuan 610000 Applicant after: Marketing service center of State Grid Sichuan Electric Power Co. Address before: Floor 1, No. 50, section 4, Renmin South Road, Wuhou District, Chengdu, Sichuan 610000 Applicant before: Marketing service center of State Grid Sichuan Electric Power Co. Applicant before: Kong Deshi Applicant before: Zhang Liyan Applicant before: Li Bo |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |