CN111026856A - Intelligent interaction method and device and computer readable storage medium - Google Patents
Intelligent interaction method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN111026856A CN111026856A CN201911249451.8A CN201911249451A CN111026856A CN 111026856 A CN111026856 A CN 111026856A CN 201911249451 A CN201911249451 A CN 201911249451A CN 111026856 A CN111026856 A CN 111026856A
- Authority
- CN
- China
- Prior art keywords
- entity
- information
- request information
- question
- specific entity
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000003993 interaction Effects 0.000 title claims abstract description 24
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 10
- 241000158764 Murraya Species 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009193 crawling 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
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent interaction method, an intelligent interaction device and a computer readable storage medium, wherein the intelligent interaction method comprises the following steps: receiving request information of a user or a user terminal; carrying out specific entity identification on the received request information by using a specific entity identification model, and extracting a specific entity; determining an entity type according to the extracted specific entity; generating a problem template according to the determined entity type; and acquiring feedback information corresponding to the request information according to the specific entity and the problem template. The specific entity in the request information is extracted through an artificial intelligence technology, the corresponding problem template is finally generated according to the specific entity, and finally the feedback information corresponding to the request information is obtained according to the specific entity and the problem template.
Description
Technical Field
The present invention relates to the field of human-computer interaction, and in particular, to an intelligent interaction method, apparatus, and computer-readable storage medium.
Background
In the prior art, the most mature scheme of the chat robot is that a large number of question-answer pairs are manually compiled, the questions of the user are matched with the questions configured by the system, corresponding answers are returned, and the construction cost is high.
Disclosure of Invention
The embodiment of the invention provides an intelligent interaction method, an intelligent interaction device and a computer-readable storage medium, which can reduce the construction cost of a chat robot scheme.
One aspect of the present invention provides an intelligent interaction method, including: receiving request information of a user or a user terminal; carrying out specific entity identification on the received request information by using a specific entity identification model, and extracting a specific entity; determining an entity type according to the extracted specific entity; generating a problem template according to the determined entity type; and acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
In one embodiment, the specific entity is a music entity; the entity type comprises at least one of the following types: song title, album and singer.
In an embodiment, the determining the entity type according to the extracted specific entity includes: judging whether the specific entity exists in the type word list or not; and if the specific entity exists in the type word list, determining the entity type according to the specific entity.
In one possible embodiment, after generating the problem template, the method further comprises: judging whether the problem template exists in a template library or not; and if the problem template is judged to exist in the template library, acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
In an implementation manner, the obtaining feedback information corresponding to the request information according to the specific entity and the question template includes: generating a database query statement based on the specific entity and the question template; and taking the generated database query statement as an input of a first question-answer database so as to acquire feedback information corresponding to the request information from the first question-answer database.
In an embodiment, the method further comprises: if the specific entity is determined to be the singer type, similarity matching is carried out on the request information and the question information in the second question-and-answer database one by one; and if the target question information matched with the request information exists in the second question-answer database, using reply information corresponding to the target question information in the second question-answer database as feedback information of the request information.
In an embodiment, the method further comprises: if the target question information matched with the request information does not exist in the second question-answering database, taking the request information as the input of an online search engine so as to obtain a search result corresponding to the request information through the online search engine; and extracting corresponding reply information from the acquired search result as feedback information of the request information.
In an implementation manner, after obtaining the feedback information corresponding to the request information, the method further includes: judging whether the feedback information comprises sensitive words or not; and if the feedback information does not comprise the sensitive words, feeding the feedback information back to the user or the user terminal.
Another aspect of an embodiment of the present invention provides an intelligent interaction apparatus, where the apparatus includes: the receiving module is used for receiving request information of a user or a user terminal; the entity identification module is used for carrying out entity identification on the received request information based on an artificial intelligence entity identification model and extracting entity information; the entity type determining module is used for determining the entity type according to the extracted entity information; the problem template generating module is used for generating a problem template according to the determined entity type; and the feedback module is used for acquiring corresponding feedback information according to the entity information and the problem template.
Another aspect of embodiments of the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform an intelligent interaction method.
In the embodiment of the invention, the specific entity in the request information is extracted through the artificial intelligence technology, the corresponding question template is finally generated according to the specific entity, and the feedback information corresponding to the request information is finally obtained according to the specific entity and the question template.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Fig. 1 is a schematic diagram of an implementation flow of an intelligent interaction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an intelligent interaction device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic diagram of an implementation flow of an intelligent interaction method according to an embodiment of the present invention, as shown in fig. 1.
One aspect of the present invention provides an intelligent interaction method, including:
102, carrying out specific entity identification on the received request information by using a specific entity identification model, and extracting a specific entity;
103, determining an entity type according to the extracted specific entity;
and 105, acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
In this embodiment, first, request information of a user or a user terminal is received, where the request information is text information, and if the user or the user terminal sends voice information, the voice information needs to be converted into text information through a voice-to-text conversion technology.
And then, carrying out specific entity identification on the received request information by using a specific entity identification model to extract a specific entity. The specific entity recognition model can be realized by using a currently universal Bilstm (bidirectional long-and-short memory network) + CRF (conditional random field) model through specific entity recognition training.
When the method is applied to the field of music, the specific entity is a music entity, the music entity can be divided into a song title entity, an album entity and a singer entity, and correspondingly, the entity types comprise a song title type, an album type and a singer type.
When an entity type is determined according to a specific entity, if any one of a singer name entity, an album entity and a singer entity is identified through a specific entity identification model, the entity is classified into the corresponding entity type. For example, the request information content is "how do you feel the murraya septemfasciata", the specific entity "murraya septemata" is identified through the specific entity identification model, the "murraya septemata" is the song name, and the "murraya septemata" is classified as the song name type.
Then generating a problem template according to the determined entity type, and the specific steps are as follows: and replacing a specific entity in the request information by using a wildcard corresponding to the entity type, thereby generating the problem template. When applied in the music field, the wildcard for the song title type may be denoted as < song >, and the wildcard for the album type may be < album >. For example, the question template for the request information "how you feel how Qilixiang" is "how you feel < song >, and so on, and the request information" how still exhibitions "is for the corresponding question template" < album >.
And finally, the acquired specific entity and the problem template acquire feedback information corresponding to the request information and send the feedback information to the user or the user terminal.
Therefore, the specific entity in the request information is extracted through the artificial intelligence technology, the corresponding question template is finally generated according to the specific entity, and the feedback information corresponding to the request information is finally obtained according to the specific entity and the question template.
In one embodiment, the specific entity is a music entity; the entity types include at least one of the following types: song title, album and singer.
In this embodiment, the embodiment of the present invention is mainly applied to the music field, and the specific entity includes a song title, an album, and a singer, and correspondingly, the entity type includes a song title type, an album type, and a singer type.
In one embodiment, determining the entity type according to the extracted specific entity includes:
judging whether a specific entity exists in the type word list or not;
and if the specific entity exists in the type word list, determining the entity type according to the specific entity.
In this embodiment, the number of the type vocabularies may be one or more, and each vocabularies includes a large amount of entity information of the same type as the corresponding vocabularies. For example, the vocabulary in the music field may be a song title vocabulary including commercially available song titles, an album vocabulary including commercially available albums, and a singer vocabulary including commercially available singers.
Thus, the specific process of determining the entity type according to the extracted specific entity is as follows: judging whether the identified specific entity exists in the current type word list one by one according to the plurality of type word lists, if a certain type word list contains the specific entity, determining that the entity type of the specific entity is consistent with the type of the type word list, for example, whether the specific entity obtained by identification is 'Qilixiang' is judged, then judging whether the 'Qilixiang' exists in the song name word list, the album word list and the singer word list in sequence, and if the 'Qilixiang' is contained in the song name word list, determining that the 'Qilixiang' is the song name type.
In one possible embodiment, after generating the problem template, the method further comprises:
judging whether the problem template exists in a template library or not;
and if the problem template is judged to exist in the template library, acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
In this embodiment, a large number of question templates are recorded in the template library, and taking the question template of the song name as an example, the question template of the song name includes "how you feel < song >," < song > how you feel good at ", and so on, so as to cover the questions that the user may possibly ask as much as possible.
Therefore, after the problem template corresponding to the request information is acquired, whether the problem template exists in the template library or not needs to be judged, and if the problem template exists in the template library, feedback information corresponding to the request information is acquired according to the specific entity and the problem template. If the problem template is determined not to exist in the template library, no information is fed back or otherwise processed.
In an implementation manner, obtaining feedback information corresponding to the request information according to the specific entity and the question template includes:
generating a database query statement based on the specific entity and the question template;
and taking the generated database query sentence as an input of the first question-answer database so as to acquire feedback information corresponding to the request information from the first question-answer database.
In this embodiment, a large amount of question template data, specific entity data, and feedback information corresponding to each other are stored in the first question-and-answer database. When the method is applied to the field of music, the feedback information is mainly used for feeding back evaluations of song titles and albums, the main sources are that evaluations of the song titles and the albums are searched from some famous music forums or music software in advance according to the song titles, the albums and corresponding problem templates, the evaluation information is crawled by utilizing the existing crawler technology, and the crawled evaluation information is used as the feedback information.
Therefore, the specific steps of acquiring the feedback information corresponding to the request information according to the specific entity and the problem template are as follows: and setting the obtained specific entity and the obtained question template as fields of a database query statement, finding corresponding feedback information from the first question-answer database according to the two fields of the specific entity and the question template, and sending the feedback information to a user or a user terminal.
In an embodiment, the method further comprises:
if the specific entity is determined to be the singer type, similarity matching is carried out on the request information and the question information in the second question-and-answer database one by one;
and if the target question information matched with the request information exists in the second question-answering database, using the reply information corresponding to the target question information in the second question-answering database as the feedback information of the request information.
In this embodiment, the second question-answering database includes a large amount of question information and corresponding reply information about a specific field, where the question information may be written manually, or the question information about a singer may be obtained from a music website or software according to the name of the singer, and the corresponding reply information is obtained by inputting the question information into the music website and crawling the relevant reply information by using a crawler technology.
Therefore, if the specific entity is determined to be the singer type, the request information is input into the second question-answer database, and the request information and all question information in the second question-answer database are subjected to similarity matching one by one through the conventional similarity algorithm. And then selecting one or more pieces of target question information with the highest similarity from the second question-answer database, extracting reply information corresponding to the selected target question information, and taking the extracted reply information as feedback information.
In an embodiment, the method further comprises:
if the target question information matched with the request information does not exist in the second question-answering database, the request information is used as the input of an online search engine so as to obtain a search result corresponding to the request information through the online search engine;
and extracting corresponding reply information from the acquired search result as feedback information of the request information.
In this embodiment, if the similarity between all the question information in the second question-and-answer database and the request information does not satisfy the requirement, it is determined that there is no target question information matching the request information in the second question-and-answer database, and the request information is input to an online search engine, and then a search result corresponding to the request information is obtained online by using the existing crawler technology, and the search result is used as feedback information of the request information.
If the problem template corresponding to the request problem does not exist in the template library, the required feedback information can be found out through an online searching mode through the request information.
In an implementation manner, after obtaining the feedback information corresponding to the request information, the method further includes:
judging whether the feedback information comprises sensitive words or not;
and if the feedback information does not comprise the sensitive words, feeding the feedback information back to the user or the user terminal.
In this embodiment, after the feedback information is obtained, all vocabularies in the feedback information are identified by using the existing entity identification model, and whether all the vocabularies exist in the vocabulary containing the sensitive vocabularies is determined one by one, and if the sensitive vocabularies exist in the feedback information, the feedback information is stopped being sent to the user or the user terminal; and if the sensitive words do not exist in the feedback information, sending the feedback information to the user or the user terminal.
Fig. 2 is a schematic view of an implementation flow of an intelligent interaction device according to an embodiment of the present invention, as shown in fig. 2.
Based on the above provided intelligent interaction method, an embodiment of the present invention further provides an intelligent interaction apparatus, including:
a receiving module 201, configured to receive request information of a user or a user terminal;
an entity identification module 202, configured to perform entity identification on the received request information based on an artificial intelligence entity identification model, and extract entity information;
an entity type determining module 203, configured to determine an entity type according to the extracted entity information;
a question template generating module 204, configured to generate a question template according to the determined entity type;
and the feedback module 205 is configured to obtain corresponding feedback information according to the entity information and the problem template.
In this embodiment, the receiving module 201 first receives request information of a user or a user terminal, where the request information is text information, and if the user or the user terminal sends voice information, the voice information needs to be converted into text information through a voice-to-text conversion technology.
The entity identification module 202 then performs entity-specific identification on the received request message using an entity-specific identification model to extract a specific entity. The specific entity recognition model can be realized by using a currently universal Bilstm (bidirectional long-and-short memory network) + CRF (conditional random field) model through specific entity recognition training.
When the method is applied to the field of music, the specific entity is a music entity, the music entity can be divided into a song title entity, an album entity and a singer entity, and correspondingly, the entity types comprise a song title type, an album type and a singer type.
When the entity type determination module 203 determines the entity type according to the specific entity, if any one of the singer name entity, the album entity and the singer entity is identified through the specific entity identification model, the entity is classified into the corresponding entity type. For example, the request information content is "how do you feel the murraya septemfasciata", the specific entity "murraya septemata" is identified through the specific entity identification model, the "murraya septemata" is the song name, and the "murraya septemata" is classified as the song name type.
Then, the question template generating module 204 generates a question template according to the determined entity type, and the specific steps are as follows: and replacing a specific entity in the request information by using a wildcard corresponding to the entity type, thereby generating the problem template. When applied in the music field, the wildcard for the song title type may be denoted as < song >, and the wildcard for the album type may be < album >. For example, the question template for the request information "how you feel how Qilixiang" is "how you feel < song >, and so on, and the request information" how still exhibitions "is for the corresponding question template" < album >.
Finally, the feedback module 205 obtains the feedback information corresponding to the request information according to the obtained specific entity and the problem template, and sends the feedback information to the user or the user terminal.
Therefore, the specific entity in the request information is extracted through the artificial intelligence technology, the corresponding question template is finally generated according to the specific entity, and the feedback information corresponding to the request information is finally obtained according to the specific entity and the question template.
Based on the intelligent interaction method provided by the upper level, the embodiment of the invention also provides a computer readable storage medium, wherein the storage medium comprises a group of computer executable instructions, and when the instructions are executed, the computer readable storage medium is used for executing the intelligent interaction method
In an embodiment of the present invention, a computer-readable storage medium includes a set of computer-executable instructions, which when executed, are configured to receive a request for information from a user or a user terminal; carrying out specific entity identification on the received request information by using a specific entity identification model, and extracting a specific entity; determining an entity type according to the extracted specific entity; generating a problem template according to the determined entity type; and acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
The specific entity in the request information is extracted through an artificial intelligence technology, the corresponding problem template is finally generated according to the specific entity, and finally the feedback information corresponding to the request information is obtained according to the specific entity and the problem template.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent interaction method, the method comprising:
receiving request information of a user or a user terminal;
carrying out specific entity identification on the received request information by using a specific entity identification model, and extracting a specific entity;
determining an entity type according to the extracted specific entity;
generating a problem template according to the determined entity type;
and acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
2. The method of claim 1, wherein the specific entity is a music entity; the entity type comprises at least one of the following types: song title, album and singer.
3. The method according to claim 1 or 2, wherein the determining an entity type according to the extracted specific entity comprises:
judging whether the specific entity exists in the type word list or not;
and if the specific entity exists in the type word list, determining the entity type according to the specific entity.
4. The method of claim 1 or 2, wherein after generating the problem template, the method further comprises:
judging whether the problem template exists in a template library or not;
and if the problem template is judged to exist in the template library, acquiring feedback information corresponding to the request information according to the specific entity and the problem template.
5. The method according to claim 1 or 2, wherein the obtaining feedback information corresponding to the request information according to the specific entity and the question template comprises:
generating a database query statement based on the specific entity and the question template;
and taking the generated database query statement as an input of a first question-answer database so as to acquire feedback information corresponding to the request information from the first question-answer database.
6. The method of claim 2, further comprising:
if the specific entity is determined to be the singer type, similarity matching is carried out on the request information and the question information in the second question-and-answer database one by one;
and if the target question information matched with the request information exists in the second question-answer database, using reply information corresponding to the target question information in the second question-answer database as feedback information of the request information.
7. The method of claim 6, further comprising:
if the target question information matched with the request information does not exist in the second question-answering database, taking the request information as the input of an online search engine so as to obtain a search result corresponding to the request information through the online search engine;
and extracting corresponding reply information from the acquired search result as feedback information of the request information.
8. The method according to claim 1 or 2, wherein after acquiring the feedback information corresponding to the request information, the method further comprises:
judging whether the feedback information comprises sensitive words or not;
and if the feedback information does not comprise the sensitive words, feeding the feedback information back to the user or the user terminal.
9. An intelligent interaction device, the device comprising:
the receiving module is used for receiving request information of a user or a user terminal;
the entity identification module is used for carrying out entity identification on the received request information based on an artificial intelligence entity identification model and extracting entity information;
the entity type determining module is used for determining the entity type according to the extracted entity information;
the problem template generating module is used for generating a problem template according to the determined entity type;
and the feedback module is used for acquiring corresponding feedback information according to the entity information and the problem template.
10. A computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform the intelligent interaction method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911249451.8A CN111026856A (en) | 2019-12-09 | 2019-12-09 | Intelligent interaction method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911249451.8A CN111026856A (en) | 2019-12-09 | 2019-12-09 | Intelligent interaction method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111026856A true CN111026856A (en) | 2020-04-17 |
Family
ID=70205266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911249451.8A Pending CN111026856A (en) | 2019-12-09 | 2019-12-09 | Intelligent interaction method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026856A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114630135A (en) * | 2020-12-11 | 2022-06-14 | 北京字跳网络技术有限公司 | Live broadcast interaction method and device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110022635A1 (en) * | 2009-07-26 | 2011-01-27 | Moris Michael | Method and System to Formulate Queries With Minivisuals |
| US20140188935A1 (en) * | 2012-12-31 | 2014-07-03 | Erik N. Vee | Natural-Language Rendering of Structured Search Queries |
| US20150039292A1 (en) * | 2011-07-19 | 2015-02-05 | MaluubaInc. | Method and system of classification in a natural language user interface |
| US20170017716A1 (en) * | 2015-07-13 | 2017-01-19 | International Business Machines Corporation | Generating Probabilistic Annotations for Entities and Relations Using Reasoning and Corpus-Level Evidence |
| CN108345690A (en) * | 2018-03-09 | 2018-07-31 | 广州杰赛科技股份有限公司 | Intelligent answer method and system |
| CN109508420A (en) * | 2018-11-26 | 2019-03-22 | 北京羽扇智信息科技有限公司 | A kind of cleaning method and device of knowledge mapping attribute |
| CN109522393A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
| CN109657037A (en) * | 2018-12-21 | 2019-04-19 | 焦点科技股份有限公司 | A kind of knowledge mapping answering method and system based on entity type and semantic similarity |
| CN109766494A (en) * | 2018-12-25 | 2019-05-17 | 出门问问信息科技有限公司 | Problem answers are to extending method, device, equipment and computer readable storage medium |
| CN110019695A (en) * | 2017-08-07 | 2019-07-16 | 芋头科技（杭州）有限公司 | A kind of automatic chatting response method |
| CN110516054A (en) * | 2019-08-15 | 2019-11-29 | 出门问问(武汉)信息科技有限公司 | A kind of garbage classification answering method, equipment and readable storage medium storing program for executing |
-
2019
- 2019-12-09 CN CN201911249451.8A patent/CN111026856A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110022635A1 (en) * | 2009-07-26 | 2011-01-27 | Moris Michael | Method and System to Formulate Queries With Minivisuals |
| US20150039292A1 (en) * | 2011-07-19 | 2015-02-05 | MaluubaInc. | Method and system of classification in a natural language user interface |
| US20140188935A1 (en) * | 2012-12-31 | 2014-07-03 | Erik N. Vee | Natural-Language Rendering of Structured Search Queries |
| US20170017716A1 (en) * | 2015-07-13 | 2017-01-19 | International Business Machines Corporation | Generating Probabilistic Annotations for Entities and Relations Using Reasoning and Corpus-Level Evidence |
| CN110019695A (en) * | 2017-08-07 | 2019-07-16 | 芋头科技（杭州）有限公司 | A kind of automatic chatting response method |
| CN108345690A (en) * | 2018-03-09 | 2018-07-31 | 广州杰赛科技股份有限公司 | Intelligent answer method and system |
| CN109522393A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
| CN109508420A (en) * | 2018-11-26 | 2019-03-22 | 北京羽扇智信息科技有限公司 | A kind of cleaning method and device of knowledge mapping attribute |
| CN109657037A (en) * | 2018-12-21 | 2019-04-19 | 焦点科技股份有限公司 | A kind of knowledge mapping answering method and system based on entity type and semantic similarity |
| CN109766494A (en) * | 2018-12-25 | 2019-05-17 | 出门问问信息科技有限公司 | Problem answers are to extending method, device, equipment and computer readable storage medium |
| CN110516054A (en) * | 2019-08-15 | 2019-11-29 | 出门问问(武汉)信息科技有限公司 | A kind of garbage classification answering method, equipment and readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 李和瀚;孟小峰;邹磊;: "面向ScholarSpace知识库的关键词查询方法" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114630135A (en) * | 2020-12-11 | 2022-06-14 | 北京字跳网络技术有限公司 | Live broadcast interaction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN108959559B (en) | Question and answer pair generation method and device | |
| US8335787B2 (en) | Topic word generation method and system | |
| JP2013541793A (en) | Multi-mode search query input method | |
| CN111291210B (en) | Image material library generation method, image material recommendation method and related devices | |
| CN111475623A (en) | Case information semantic retrieval method and device based on knowledge graph | |
| CN105956053B (en) | A kind of searching method and device based on the network information | |
| CN112214593A (en) | Question and answer processing method and device, electronic equipment and storage medium | |
| CN105653547B (en) | Method and device for extracting text keywords | |
| CN113900954B (en) | Test case recommendation method and device using knowledge graph | |
| CN112749328A (en) | Searching method and device and computer equipment | |
| CN111737523B (en) | Video tag, generation method of search content and server | |
| CN111026856A (en) | Intelligent interaction method and device and computer readable storage medium | |
| CN110750632B (en) | Improved Chinese ALICE intelligent question-answering method and system | |
| CN112417174A (en) | Data processing method and device | |
| CN115774996B (en) | Intelligent interview topdressing problem generation method and device and electronic equipment | |
| CN111639160A (en) | Domain identification method, interaction method, electronic device and storage medium | |
| CN112541091A (en) | Image searching method, device, server and storage medium | |
| CN113742474B (en) | Intelligent question and answer method and device based on knowledge graph | |
| JP6521931B2 (en) | Model generation device, click log correct likelihood calculation device, document search device, method, and program | |
| CN114281942A (en) | Question and answer processing method, related equipment and readable storage medium | |
| CN114242047A (en) | Voice processing method and device, electronic equipment and storage medium | |
| Nghiem et al. | Which one is better: presentation-based or content-based math search? | |
| CN113468306A (en) | Voice conversation method, device, electronic equipment and storage medium | |
| CN113704623A (en) | Data recommendation method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |