CN113515605A - Intelligent robot question-answering method based on artificial intelligence and intelligent robot - Google Patents
Intelligent robot question-answering method based on artificial intelligence and intelligent robot Download PDFInfo
- Publication number
- CN113515605A CN113515605A CN202110550212.7A CN202110550212A CN113515605A CN 113515605 A CN113515605 A CN 113515605A CN 202110550212 A CN202110550212 A CN 202110550212A CN 113515605 A CN113515605 A CN 113515605A
- Authority
- CN
- China
- Prior art keywords
- question
- actual
- initial
- sentence
- standard question
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an intelligent robot question-answering method based on artificial intelligence and an intelligent robot, which are used for acquiring an actual question input by a user, acquiring at least two initial standard questions corresponding to the actual question from a question database according to the actual question, acquiring a characteristic phrase of the actual question corresponding to the actual question by combining a characteristic extraction algorithm and a preset sequence, acquiring a target standard question corresponding to the actual question according to the characteristic phrase of the actual question and the initial standard question characteristic phrases corresponding to the initial standard questions, acquiring a target answer corresponding to the target standard question from the question-answering database according to the target standard question, accurately and reliably acquiring the target standard question corresponding to the actual question input by the user, greatly improving the accuracy and ensuring that the obtained target standard question has higher matching degree with the actual question, and the accuracy of the question and answer result of the intelligent robot is further improved.
Description
Technical Field
The invention relates to an intelligent robot question-answering method based on artificial intelligence and an intelligent robot.
Background
At present, the application of intelligent robots capable of performing question and answer operations is more and more extensive, such as question and answer robots in public places such as markets and hospitals and intelligent customer service robots in various e-commerce platforms. Due to different human language expressions, the following situations often occur: for multiple questions, the questions are synonymous, but are expressed differently. When the intelligent robot carries out data processing, the intelligent robot firstly carries out analysis according to input questions and matches the questions with standard question sentences, and then obtains and outputs corresponding answers from a database according to the standard question sentences. When a standard question is obtained according to an actual question, a keyword mode is usually adopted at present, namely, keywords in the actual question are obtained, and then a corresponding standard question is obtained according to the keywords.
Disclosure of Invention
The invention provides an intelligent robot question-answering method based on artificial intelligence and an intelligent robot, which are used for solving the technical problem of the accuracy of the question-answering mode of the existing intelligent robot.
An intelligent robot question-answering method based on artificial intelligence comprises the following steps:
acquiring an actual question sentence input by a user;
acquiring at least two initial standard question sentences corresponding to the actual question sentences from a question sentence database according to the actual question sentences;
analyzing the actual question sentence according to a preset feature extraction algorithm to obtain feature information in the actual question sentence;
sequencing the characteristic information according to the characteristic information in the actual question sentence and a preset sequence to obtain an actual question sentence characteristic language segment corresponding to the actual question sentence;
acquiring a target standard question corresponding to the actual question according to the actual question feature words and the initial standard question feature words corresponding to the initial standard question;
and acquiring a target answer corresponding to the target standard question from a question-answer database according to the target standard question.
Preferably, the obtaining of the actual question sentence input by the user specifically includes:
acquiring an initial voice signal input by a user;
performing voice recognition on the initial voice signal to obtain at least two candidate initial question sentences;
and displaying each candidate initial question, and acquiring the candidate initial question selected by the user from each candidate initial question to obtain the actual question input by the user.
Preferably, the obtaining, according to the actual question, at least two initial standard questions corresponding to the actual question from a question database specifically includes:
acquiring keywords in the actual question sentence according to the actual question sentence;
acquiring keywords of each standard question in the question database;
comparing the keywords in the actual question sentence with the keywords of each standard question sentence in the question sentence database, and obtaining the similarity between the actual question sentence and each standard question sentence in the question sentence database according to the comparison result, wherein the more the same keywords are, the higher the similarity is;
and determining at least two initial standard question sentences corresponding to the actual question sentences according to the similarity.
Preferably, the process of acquiring the initial standard question sentence characteristic language segment corresponding to the initial standard question sentence includes:
analyzing the initial standard question sentence according to the feature extraction algorithm to obtain feature information in the initial standard question sentence;
and sequencing all the characteristic information in the initial standard question sentence according to all the characteristic information in the initial standard question sentence and the preset sequence to obtain an initial standard question sentence characteristic language segment corresponding to the initial standard question sentence.
Preferably, the obtaining of the target standard question corresponding to the actual question according to the actual question feature words and the initial standard question feature words corresponding to the initial standard question specifically includes:
acquiring the similarity between the actual question and each initial standard question;
determining the candidate sequence of each initial standard question according to the similarity between the actual question and each initial standard question;
determining whether the actual question sentence characteristic language segments are matched with the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences in sequence according to the candidate sequence; and if the initial standard question is matched with the target standard question, taking the current initial standard question as the target standard question.
Preferably, the process of determining whether the actual question sentence characteristic language segment matches the initial standard question sentence characteristic language segment corresponding to each initial standard question sentence includes:
and for any one initial standard question sentence, if the structure of the actual question sentence characteristic language segment is the same as that of the initial standard question sentence characteristic language segment corresponding to the initial standard question sentence, judging that the actual question sentence characteristic language segment is matched with the initial standard question sentence characteristic language segment corresponding to the initial standard question sentence.
Preferably, in the process of sequentially determining whether the actual question sentence characteristic language segment matches with the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences, if not, determining whether the meanings of the characteristic information in the actual question sentence characteristic language segment are corresponding to the meanings of the characteristic information in the initial standard question sentence characteristic language segment of the current initial standard question sentence, if so, taking the current initial standard question sentence as the target standard question sentence,
preferably, after the target answers corresponding to the target standard question are obtained from a question-answer database according to the target standard question, the intelligent robot question-answer method based on artificial intelligence further includes the following steps:
detecting a mobile terminal which is started with Bluetooth in a preset range, and carrying out Bluetooth pairing;
and after the Bluetooth pairing is completed, sending the target answer to the mobile terminal.
An intelligent robot comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the intelligent robot question-answering method based on artificial intelligence.
The technical effects of the invention comprise: the method comprises the steps of firstly determining at least two initial standard question sentences corresponding to actual question sentences according to the actual question sentences input by a user, then analyzing the actual question sentences according to a preset feature extraction algorithm to obtain relevant feature information in the actual question sentences, sequencing all feature information according to all feature information in the actual question sentences and a preset sequence to obtain actual question sentence feature language segments corresponding to the actual question sentences, then combining the actual question sentence feature language segments and the initial standard question sentence feature language segments corresponding to all the initial standard question sentences to obtain target standard question sentences corresponding to the actual question sentences, and finally obtaining target answers corresponding to the target standard question sentences from a question-answer database according to the obtained target standard question sentences. According to the question-answering method of the intelligent robot, the target standard question corresponding to the actual question input by the user can be accurately and reliably acquired, and compared with the traditional mode that the standard question is determined only according to the keywords, the accuracy is greatly improved, so that the matching degree of the acquired target standard question and the actual question is high, and the accuracy of the question-answering result of the intelligent robot is improved.
Drawings
Fig. 1 is a flowchart of an intelligent robot question-answering method based on artificial intelligence provided by the invention.
Detailed Description
The embodiment of the question-answering method of the intelligent robot based on artificial intelligence comprises the following steps:
the embodiment provides an intelligent robot question-answering method based on artificial intelligence, which can be applied to various intelligent robots, intelligent mobile terminals and the like. As shown in fig. 1, the intelligent robot question-answering method based on artificial intelligence includes the following steps:
step 1: acquiring an actual question sentence input by a user:
the intelligent robot obtains the actual question that the user input, and the user can manually input the corresponding text message of actual question, and under the usual condition, intelligent robot is provided with the microphone, receives the speech signal that the user spoken through the microphone, and then, the concrete process of obtaining the actual question of user input includes:
(1) acquiring an initial voice signal input by a user through a microphone;
(2) the speech recognition is carried out on the initial speech signal by adopting the built-in speech recognition algorithm, because the recognition result of the speech recognition algorithm is not absolutely correct, and the speech signal can be recognized as other character information with the same pronunciation or highly similar pronunciation, then at least two candidate initial question sentences can be obtained by carrying out the speech recognition on the initial speech signal by adopting the built-in speech recognition algorithm, and the pronunciation of each candidate initial question sentence is the same or highly similar.
(3) Displaying each candidate initial question on a display screen or a touch screen of the intelligent robot, and after seeing each candidate initial question, selecting a correct candidate initial question from the candidate initial questions, such as: the selection is made by clicking on the corresponding candidate initial question on the touch screen. And determining that the obtained candidate initial question is the actual question input by the user.
Step 2: according to the actual question, at least two initial standard questions corresponding to the actual question are obtained from a question database:
a question database is preset in the intelligent robot and comprises a plurality of standard questions. Typically, intelligent robots have specific applications, such as hospitals, malls, etc. Therefore, in order to improve the identification accuracy, all the currently known standard question sentences related to the application are included in the question sentence database.
As a specific embodiment, a specific implementation procedure for obtaining at least two initial standard question sentences corresponding to actual question sentences from a question sentence database according to the actual question sentences is given as follows:
(1) and acquiring the keywords in the actual question sentence according to the actual question sentence. The keyword extraction process can adopt the existing keyword extraction algorithm to extract. In general, a plurality of keywords can be extracted from an actual question sentence. Correspondingly, the same keyword extraction algorithm is adopted to extract keywords of each standard question in the question database, and keywords of each standard question in the question database are obtained.
(2) And comparing the keywords in the actual question with the keywords of each standard question in the question database, and for any standard question, comparing the keywords in the actual question with the keywords of the standard question and determining the number of the keywords which are the same as those in the standard question in the actual question. It should be understood that when the keywords are compared, the keywords do not need to be compared one by one according to the sequence of the keywords in the question sentence, that is, the comparison does not need to be performed according to the following comparison rule: the first keyword in the actual question is compared with the first keyword in the standard question, the second keyword in the actual question is compared with the second keyword in the standard question, and so on. But simply determines the number of keywords in the actual question that are the same as in the standard question. And determining the similarity between the actual question and the standard question according to the number of the same keywords, wherein the more the same keywords are, the higher the similarity is. And the specific numerical relationship between the number of the same keywords and the similarity is set according to actual needs.
(3) And determining at least two initial standard question sentences corresponding to the actual question sentences according to the similarity. A similarity threshold may be set, and standard question sentences having a similarity greater than or equal to the similarity threshold are obtained from the standard question sentences, and the obtained standard question sentences are the required initial standard question sentences.
As another embodiment, for any one standard question, each character in the actual question may be compared with each character in the standard question one by one, specifically: comparing the first character in the actual question with the first character in the standard question, comparing the second character in the actual question with the second character in the standard question, comparing the third character in the actual question with the third character in the standard question, and so on until the last character in the actual question is compared with the last character in the standard question. And determining the similarity according to the number of the same characters, wherein the similarity is higher according to the more the number of the same characters is.
And step 3: analyzing the actual question sentence according to a preset feature extraction algorithm to obtain feature information in the actual question sentence:
a feature extraction algorithm is preset in the intelligent robot and used for extracting feature information in the text. It should be understood that the feature extraction algorithm is an existing feature extraction algorithm, such as the TF-IDF algorithm. And analyzing the actual question by a feature extraction algorithm to obtain feature information in the actual question. The characteristic information may be related words, words or phrases. The types of the property information may be: background, status, actions, questions, and the like.
In this embodiment, the feature extraction algorithm may include a plurality of feature types and each specific feature information included in each feature type. Then, the actual question is input into the feature extraction algorithm, so that each feature information in the actual question and the feature type to which each feature information belongs can be obtained.
And 4, step 4: sequencing the characteristic information according to the characteristic information in the actual question sentence and a preset sequence to obtain an actual question sentence characteristic language segment corresponding to the actual question sentence:
the preset sequence may be a sequence indicating each feature information in the actual question sentence feature field, that is, a sequence indicating a feature type corresponding to each feature information in the actual question sentence feature field, where the sequence of the feature type corresponding to each feature information in the preset sequence is specifically set according to actual needs. It should be understood that if the order of each feature information obtained after analyzing the actual question is different from the preset order, the order of each feature information needs to be adjusted to the preset order. In addition, in order to meet the requirements of actual question sentences input by different users, the preset sequence includes the sequence of the feature types corresponding to each feature information in the feature sentence field of the actual question sentence, and there is a possibility that the preset sequence also includes the feature types corresponding to the feature information which is not included in the actual question sentence.
Correspondingly, the actual question sentence feature language segment is a sentence obtained by arranging each feature information according to a preset sequence, that is, a sentence obtained by arranging the feature types corresponding to each feature information in the actual question sentence according to the preset sequence. It can be understood that the actual question sentence feature word segment is a word segment obtained by removing each remaining feature information after other irrelevant information in the actual question sentence and sorting according to a preset sequence. For example: if the actual question is: and A + a + B + B + C + C, wherein A, B and C are feature information, a, B and C are irrelevant information, and if the preset sequence is the feature type name corresponding to the feature information B, the feature type name corresponding to the feature information D, the feature type name corresponding to the feature information C, the feature type name corresponding to the feature information E and the feature type name corresponding to the feature information A, the actual question feature words are the feature information B, the feature information C and the feature information A.
And 5: acquiring a target standard question corresponding to the actual question according to the actual question feature words and the initial standard question feature words corresponding to the initial standard question:
the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences can also be obtained according to the obtaining process of the actual question sentence characteristic language segments, which is specifically as follows: analyzing any initial standard statement according to a feature extraction algorithm to obtain feature information in the initial standard statement; and then, sequencing all the characteristic information in the initial standard question according to all the characteristic information in the initial standard question and a preset sequence to obtain an initial standard question characteristic language section corresponding to the initial standard question. And further obtaining the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences. It should be understood that the initial standard question sentence characteristic word segment corresponding to each initial standard question sentence may be obtained by processing after each initial standard question sentence is obtained, or may be obtained by processing after the actual question sentence characteristic word segment is obtained.
And acquiring a target standard question corresponding to the actual question according to the actual question characteristic language segment and the initial standard question characteristic language segments corresponding to the initial standard question. As a specific embodiment, a specific acquisition process of the target standard question is given below:
(1) and acquiring the similarity between the actual question and each initial standard question. It should be understood that the similarity may be obtained according to the similarity obtaining procedure given above.
(2) And determining the candidate sequence of each initial standard question according to the similarity between the actual question and each initial standard question. The higher the similarity is, the earlier the candidate sequence is, and the candidate sequence is the ranking of each initial standard question according to the height of the similarity.
(3) And according to the candidate sequence, sequentially determining whether the actual question sentence characteristic language segments are matched with the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences. Wherein, the matching meaning can be: the actual question feature words have the same structure as the initial standard question feature words (that is, the feature types corresponding to the feature information in the actual question feature words are the same as the feature types corresponding to the feature information in the initial standard question feature words, the sequence of the feature types is also the same, and the specific content of the feature information in the two feature words is also the same), that is, the matching meaning is: the actual question sentence characteristic language segment is completely the same as the initial standard question sentence characteristic language segment. Then, when determining whether the actual question feature word segment matches with the initial standard question feature word segment corresponding to a certain initial standard question, if matching, the current initial standard question (i.e. the certain initial standard question) is taken as the target standard question. Correspondingly, if the two characteristic words are not matched, it may be determined whether the meanings of the respective characteristic information in the actual question sentence characteristic word segment are corresponding to the meanings of the respective characteristic information in the initial standard question sentence characteristic word segment of the current initial standard question sentence, that is, when the actual question sentence characteristic word segment is not completely identical to the current initial standard question sentence characteristic word segment, the process may be returned to the next step, and it is determined whether the meanings of the respective characteristic information in the actual question sentence characteristic word segment are corresponding to the meanings of the respective characteristic information in the initial standard question sentence characteristic word segment of the current initial standard question sentence, for example: although two words are not the same word, it is determined whether the two words are synonyms. And if the initial standard question is the same as the target standard question, taking the current initial standard question as the target standard question. And then determining whether the actual question sentence characteristic language segment is matched with the initial standard question sentence characteristic language segment corresponding to the next initial standard question sentence.
As another embodiment, instead of performing the sorting process of the candidate sequence, whether the actual question sentence feature word segment is matched with the initial standard question sentence feature word segments corresponding to the initial standard question sentences may be directly obtained, and the matched initial standard question sentence feature word segment is found, where the initial standard question sentence corresponding to the initial standard question sentence feature word segment is the required target standard question sentence.
Step 6: according to the target standard question, obtaining a target answer corresponding to the target standard question from a question-answer database:
the intelligent robot is preset with a question-answer database, the question-answer database comprises the corresponding relation between at least two standard question sentences and corresponding answers, and it should be understood that the question-answer database comprises the corresponding relation between enough standard question sentences and corresponding answers.
And acquiring a target answer corresponding to the target standard question from the question-answer database according to the target standard question. Because the target answers corresponding to the target standard question are obtained from the question-answer database according to the target standard question, the method belongs to the conventional question-answer process of the intelligent robot and is not repeated.
After the intelligent robot obtains the target answer, the target answer can be displayed through a touch screen, or a voice signal of the target answer is output through a loudspeaker.
In this embodiment, the intelligent robot is further provided with a bluetooth module. If the user carries the mobile terminal with him, and the bluetooth function of the mobile terminal is turned on. Then, in this embodiment, after obtaining the target answer, the intelligent robot detects a mobile terminal with bluetooth enabled within a preset range with the intelligent robot as a center, and then performs bluetooth pairing with the mobile terminal with bluetooth enabled.
After the Bluetooth pairing is completed, namely after Bluetooth connection with the mobile terminal is established, the intelligent robot sends the target answer to the mobile terminal. Therefore, after the intelligent robot obtains the target answer, the target answer is sent to the mobile terminal of the user, and the intelligent degree is improved.
Intelligent robot embodiment:
the present embodiment provides an intelligent robot, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned intelligent robot question-answering method based on artificial intelligence when executing the computer program. Since the intelligent robot question-answering method based on artificial intelligence has been given in detail above, it is not described in detail.
Claims (9)
1. An intelligent robot question-answering method based on artificial intelligence is characterized by comprising the following steps:
acquiring an actual question sentence input by a user;
acquiring at least two initial standard question sentences corresponding to the actual question sentences from a question sentence database according to the actual question sentences;
analyzing the actual question sentence according to a preset feature extraction algorithm to obtain feature information in the actual question sentence;
sequencing the characteristic information according to the characteristic information in the actual question sentence and a preset sequence to obtain an actual question sentence characteristic language segment corresponding to the actual question sentence;
acquiring a target standard question corresponding to the actual question according to the actual question feature words and the initial standard question feature words corresponding to the initial standard question;
and acquiring a target answer corresponding to the target standard question from a question-answer database according to the target standard question.
2. The intelligent robot question-answering method based on artificial intelligence according to claim 1, wherein the obtaining of the actual question sentence input by the user specifically comprises:
acquiring an initial voice signal input by a user;
performing voice recognition on the initial voice signal to obtain at least two candidate initial question sentences;
and displaying each candidate initial question, and acquiring the candidate initial question selected by the user from each candidate initial question to obtain the actual question input by the user.
3. The intelligent robot question-answering method based on artificial intelligence according to claim 1, wherein the at least two initial standard question sentences corresponding to the actual question sentences are obtained from a question sentence database according to the actual question sentences, specifically:
acquiring keywords in the actual question sentence according to the actual question sentence;
acquiring keywords of each standard question in the question database;
comparing the keywords in the actual question sentence with the keywords of each standard question sentence in the question sentence database, and obtaining the similarity between the actual question sentence and each standard question sentence in the question sentence database according to the comparison result, wherein the more the same keywords are, the higher the similarity is;
and determining at least two initial standard question sentences corresponding to the actual question sentences according to the similarity.
4. The intelligent robot question-answering method based on artificial intelligence according to claim 1, wherein the process of obtaining the initial standard question sentence characteristic language segment corresponding to the initial standard question sentence comprises:
analyzing the initial standard question sentence according to the feature extraction algorithm to obtain feature information in the initial standard question sentence;
and sequencing all the characteristic information in the initial standard question sentence according to all the characteristic information in the initial standard question sentence and the preset sequence to obtain an initial standard question sentence characteristic language segment corresponding to the initial standard question sentence.
5. The question-answering method for the intelligent robot based on the artificial intelligence according to claim 1, wherein the target standard question sentence corresponding to the actual question sentence is obtained according to the actual question sentence characteristic language segment and the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences, which specifically comprises:
acquiring the similarity between the actual question and each initial standard question;
determining the candidate sequence of each initial standard question according to the similarity between the actual question and each initial standard question;
determining whether the actual question sentence characteristic language segments are matched with the initial standard question sentence characteristic language segments corresponding to the initial standard question sentences in sequence according to the candidate sequence; and if the initial standard question is matched with the target standard question, taking the current initial standard question as the target standard question.
6. The intelligent robot question-answering method based on artificial intelligence according to claim 5, wherein the process of judging whether the actual question sentence characteristic language segment matches with the initial standard question sentence characteristic language segment corresponding to each initial standard question sentence comprises:
and for any one initial standard question sentence, if the structure of the actual question sentence characteristic language segment is the same as that of the initial standard question sentence characteristic language segment corresponding to the initial standard question sentence, judging that the actual question sentence characteristic language segment is matched with the initial standard question sentence characteristic language segment corresponding to the initial standard question sentence.
7. The intelligent robot question-answering method based on artificial intelligence according to claim 5, wherein in the process of sequentially determining whether the actual question feature words are matched with the initial standard question feature words corresponding to the initial standard question, if not, determining whether the meanings of the feature information in the actual question feature words are corresponding to the meanings of the feature information in the initial standard question feature words of the current initial standard question, and if so, taking the current initial standard question as the target standard question.
8. The intelligent robot question-answering method based on artificial intelligence according to claim 1, wherein after the target answers corresponding to the target standard question are obtained from a question-answering database according to the target standard question, the intelligent robot question-answering method based on artificial intelligence further comprises the following steps:
detecting a mobile terminal which is started with Bluetooth in a preset range, and carrying out Bluetooth pairing;
and after the Bluetooth pairing is completed, sending the target answer to the mobile terminal.
9. An intelligent robot comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the artificial intelligence based intelligent robot question-answering method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110550212.7A CN113515605B (en) | 2021-05-20 | 2021-05-20 | Intelligent robot question-answering method based on artificial intelligence and intelligent robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110550212.7A CN113515605B (en) | 2021-05-20 | 2021-05-20 | Intelligent robot question-answering method based on artificial intelligence and intelligent robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113515605A true CN113515605A (en) | 2021-10-19 |
| CN113515605B CN113515605B (en) | 2023-12-19 |
Family
ID=78064929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110550212.7A Active CN113515605B (en) | 2021-05-20 | 2021-05-20 | Intelligent robot question-answering method based on artificial intelligence and intelligent robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113515605B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110047178A1 (en) * | 2009-08-24 | 2011-02-24 | Sensology Inc. | System and method for searching and question-answering |
| CN107315766A (en) * | 2017-05-16 | 2017-11-03 | 广东电网有限责任公司江门供电局 | A kind of voice response method and its device for gathering intelligence and artificial question and answer |
| CN108628811A (en) * | 2018-04-10 | 2018-10-09 | 北京京东尚科信息技术有限公司 | The matching process and device of address text |
| CN109035001A (en) * | 2018-06-28 | 2018-12-18 | 招联消费金融有限公司 | Intelligent voice response processing method and system |
| CN110647614A (en) * | 2019-08-01 | 2020-01-03 | 平安科技（深圳）有限公司 | Intelligent question and answer method, device, medium and electronic equipment |
| CN111444321A (en) * | 2019-01-16 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Question answering method, device, electronic equipment and storage medium |
| CN111597313A (en) * | 2020-04-07 | 2020-08-28 | 深圳追一科技有限公司 | Question answering method, device, computer equipment and storage medium |
| CN112052676A (en) * | 2020-08-31 | 2020-12-08 | 国网山东省电力公司荣成市供电公司 | Text content processing method, computer equipment and storage medium |
| CN112052683A (en) * | 2020-09-03 | 2020-12-08 | 平安科技（深圳）有限公司 | Text matching method and device, computer equipment and storage medium |
| CN112287069A (en) * | 2020-10-29 | 2021-01-29 | 平安科技（深圳）有限公司 | Information retrieval method and device based on voice semantics and computer equipment |
-
2021
- 2021-05-20 CN CN202110550212.7A patent/CN113515605B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110047178A1 (en) * | 2009-08-24 | 2011-02-24 | Sensology Inc. | System and method for searching and question-answering |
| CN107315766A (en) * | 2017-05-16 | 2017-11-03 | 广东电网有限责任公司江门供电局 | A kind of voice response method and its device for gathering intelligence and artificial question and answer |
| CN108628811A (en) * | 2018-04-10 | 2018-10-09 | 北京京东尚科信息技术有限公司 | The matching process and device of address text |
| CN109035001A (en) * | 2018-06-28 | 2018-12-18 | 招联消费金融有限公司 | Intelligent voice response processing method and system |
| CN111444321A (en) * | 2019-01-16 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Question answering method, device, electronic equipment and storage medium |
| CN110647614A (en) * | 2019-08-01 | 2020-01-03 | 平安科技（深圳）有限公司 | Intelligent question and answer method, device, medium and electronic equipment |
| CN111597313A (en) * | 2020-04-07 | 2020-08-28 | 深圳追一科技有限公司 | Question answering method, device, computer equipment and storage medium |
| CN112052676A (en) * | 2020-08-31 | 2020-12-08 | 国网山东省电力公司荣成市供电公司 | Text content processing method, computer equipment and storage medium |
| CN112052683A (en) * | 2020-09-03 | 2020-12-08 | 平安科技（深圳）有限公司 | Text matching method and device, computer equipment and storage medium |
| CN112287069A (en) * | 2020-10-29 | 2021-01-29 | 平安科技（深圳）有限公司 | Information retrieval method and device based on voice semantics and computer equipment |
Non-Patent Citations (2)
| Title |
|---|
| 周法国;杨炳儒;: "句子相似度计算新方法及在问答***中的应用", 计算机工程与应用, no. 01 * |
| 唐朝霞;: "多特征融合的中文问答***答案抽取算法", 贵州大学学报(自然科学版), no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113515605B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046133B (en) | Question and answer method, equipment, storage medium and device based on mapping knowledge base | |
| US11062090B2 (en) | Method and apparatus for mining general text content, server, and storage medium | |
| CN108682420B (en) | Audio and video call dialect recognition method and terminal equipment | |
| CN110334179B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| US20220254507A1 (en) | Knowledge graph-based question answering method, computer device, and medium | |
| CN113168836A (en) | Computer system, speech recognition method and program | |
| CN111949802A (en) | Construction method, device and equipment of knowledge graph in medical field and storage medium | |
| CN109522397B (en) | Information processing method and device | |
| WO2020199600A1 (en) | Sentiment polarity analysis method and related device | |
| CN110827803A (en) | Method, device and equipment for constructing dialect pronunciation dictionary and readable storage medium | |
| CN111554276B (en) | Speech recognition method, device, equipment and computer readable storage medium | |
| CN110717021A (en) | Input text and related device for obtaining artificial intelligence interview | |
| CN113220862A (en) | Standard question recognition method and device, computer equipment and storage medium | |
| CN112686051A (en) | Semantic recognition model training method, recognition method, electronic device, and storage medium | |
| CN112231452A (en) | Question-answering method, device, equipment and storage medium based on natural language processing | |
| CN112256827A (en) | Sign language translation method and device, computer equipment and storage medium | |
| CN110110066B (en) | Interactive data processing method and device and computer readable storage medium | |
| CN111444321B (en) | Question answering method, device, electronic equipment and storage medium | |
| CN113901837A (en) | Intention understanding method, device, equipment and storage medium | |
| CN113658690A (en) | Intelligent medical guide method and device, storage medium and electronic equipment | |
| CN110263346B (en) | Semantic analysis method based on small sample learning, electronic equipment and storage medium | |
| CN113515605B (en) | Intelligent robot question-answering method based on artificial intelligence and intelligent robot | |
| CN115019788A (en) | Voice interaction method, system, terminal equipment and storage medium | |
| CN115114404A (en) | Question and answer method and device for intelligent customer service, electronic equipment and computer storage medium | |
| CN112434148A (en) | Intelligent robot response method and device based on artificial intelligence |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231121 Address after: No. 1916, 19th Floor, Building 14, Binjiang Coast Phase III, No. 23 Haidian Island East Road, Meilan District, Haikou City, Hainan Province, 570100 Applicant after: Zhongchen Tianrun Industrial Co.,Ltd. Address before: 450000 No. 33, Zone D, floor 8, building 2, No. 85, Jinshui East Road, Zhengzhou area (Zhengdong), pilot Free Trade Zone, Zhengzhou City, Henan Province Applicant before: Henan GuangYue Network Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |