CN109086391B - Method and system for constructing knowledge graph - Google Patents
Method and system for constructing knowledge graph Download PDFInfo
- Publication number
- CN109086391B CN109086391B CN201810842317.8A CN201810842317A CN109086391B CN 109086391 B CN109086391 B CN 109086391B CN 201810842317 A CN201810842317 A CN 201810842317A CN 109086391 B CN109086391 B CN 109086391B
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge
- semi
- knowledge graph
- node
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for constructing a knowledge graph. The method comprises the following steps: acquiring semi-structured data; extracting information from a webpage aiming at a target field, and acquiring vertical field data containing entity nodes and/or node relations; and supplementing the vertical domain data into the semi-structured data to generate a knowledge graph containing the vertical domain data. Compared with the prior art, the method and the system can simply and quickly generate the knowledge graph aiming at the specific vertical field, thereby providing powerful data support for the man-machine interaction of the intelligent robot.
Description
Technical Field
The invention relates to the field of computers, in particular to a method and a system for constructing a knowledge graph.
Background
With the continuous development of artificial intelligence technology, intelligent robots are increasingly applied to the production and life of human beings.
In the interaction process of the intelligent robot and the human, in order to improve the accuracy of response of the intelligent robot to user requirements and improve the user experience of the intelligent robot, the intelligent robot generally calls a related knowledge graph and generates an interaction response according to knowledge information data in the knowledge graph in the interaction process of generating the interaction response. For example, when the user asks about "doing a potato", the intelligent robot calls the relevant knowledge graph to obtain a menu about "potatoes". In the process, the correctness and the completeness of knowledge information data in the knowledge graph directly influence the correctness of the response of the intelligent robot.
At present, the construction of knowledge graphs is based on manually written structured data. However, manual writing is time-consuming and labor-consuming, and relatively deviated knowledge points are easily missed. This results in that the knowledge map which can be put into use at the present stage is not only very deficient, but also has the problem that the accuracy and the comprehensiveness of the knowledge cannot meet the requirements even if the knowledge map is put into use.
Disclosure of Invention
The invention provides a method for constructing a knowledge graph, which comprises the following steps:
acquiring semi-structured data;
extracting information from a webpage aiming at a target field, and acquiring vertical field data containing entity nodes and/or node relations;
and supplementing the vertical domain data into the semi-structured data to generate a knowledge graph containing the vertical domain data.
In one embodiment, information extraction from a web page includes:
text recognition, namely recognizing webpage text;
crawling data, and acquiring data related to the target field based on a text recognition result;
and extracting an entity and extracting a relationship, namely extracting entity nodes and/or node relationships missing from the obtained data.
In one embodiment, the step of crawling data further comprises:
and data cleaning, wherein the data cleaning is non-entity cleaning, and specific words are filtered.
In one embodiment, the entity extraction comprises:
and (3) named entity recognition, wherein the named entity recognition is carried out by utilizing a deep learning method.
In one embodiment, node relationship extraction is performed based on a neural network.
The invention also provides an interaction method, which comprises the following steps:
obtaining and analyzing multi-modal user data, and determining the user interaction intention;
determining a vertical field corresponding to the user interaction intention;
calling a knowledge graph, wherein the knowledge graph comprises vertical domain data corresponding to the vertical domain;
extracting knowledge information data required for responding to the user interaction intention from the knowledge graph;
and generating multi-modal interaction response data aiming at the user interaction intention according to the knowledge information data.
In an embodiment, the method further comprises:
acquiring feedback data of a user aiming at the multi-mode interactive response data;
determining satisfaction of the user with respect to the multi-modal interaction response data from the feedback data;
determining the data accuracy and/or data integrity of the knowledge information data extracted from the knowledge graph according to the satisfaction;
and performing data updating on the knowledge information data extracted from the knowledge graph and/or performing data supplement on the knowledge graph according to the data accuracy and/or the data integrity.
The invention also proposes a storage medium on which a program code implementing the method according to the invention is stored.
The invention also provides a construction system for the knowledge graph, which comprises the following steps:
an infrastructure construction module configured to obtain semi-structured data;
the data extraction module is configured to determine a target field, extract information from a webpage aiming at the target field and acquire vertical field data containing entity nodes and/or node relations;
a knowledge graph generation module configured to supplement the vertical domain data to the semi-structured data, generating a knowledge graph comprising vertical domain data.
The invention also provides an interactive system, which comprises:
an input acquisition module configured to collect user multimodal data;
the interaction analysis module is configured to analyze the user multi-mode data, acquire a user interaction intention and determine a vertical field corresponding to the user interaction intention;
a knowledge graph calling module configured to call a knowledge graph generated by the construction system according to the invention, wherein the knowledge graph comprises vertical domain data corresponding to the vertical domain;
and the interaction response generation module is configured to extract knowledge information data required for responding to the user interaction intention from the knowledge graph, and generate multi-mode interaction response data aiming at the user interaction intention according to the knowledge information data.
Compared with the prior art, the method and the system can simply and quickly generate the knowledge graph aiming at the specific vertical field, thereby providing powerful data support for the man-machine interaction of the intelligent robot.
Additional features and advantages of the invention will be set forth in the description which follows. Also, some of the features and advantages of the invention will be apparent from the description, or may be learned by practice of the invention. The objectives and some of the advantages of the invention may be realized and attained by the process particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow diagram of a method of constructing a knowledge-graph according to an embodiment of the invention;
FIG. 2 is a flow diagram of a portion of a method of constructing a knowledge-graph according to an embodiment of the present invention;
FIG. 3 is a flow diagram of an interaction method according to an embodiment of the invention;
FIG. 4 is a partial flow diagram of an interaction method according to an embodiment of the invention;
FIG. 5 is a block diagram of a system for constructing a knowledge-graph, according to an embodiment of the present invention;
FIG. 6 is a block diagram of a system for building a knowledge-graph, in accordance with an embodiment of the present invention;
fig. 7 is a simplified structural diagram of an interactive system in accordance with an embodiment of the present invention.
Detailed Description
The following detailed description will be provided for the embodiments of the present invention with reference to the accompanying drawings and examples, so that the practitioner of the present invention can fully understand how to apply the technical means to solve the technical problems, achieve the technical effects, and implement the present invention according to the implementation procedures. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
With the continuous development of artificial intelligence technology, intelligent robots are increasingly applied to the production and life of human beings.
In the interaction process of the intelligent robot and the human, in order to improve the accuracy of response of the intelligent robot to user requirements and improve the user experience of the intelligent robot, the intelligent robot generally calls a related knowledge graph and generates an interaction response according to knowledge information data in the knowledge graph in the interaction process of generating the interaction response. For example, when a user asks about "doing a potato", the intelligent robot calls the associated knowledge graph to obtain a menu about "potatoes". In the process, the correctness and the integrity of knowledge information data in the knowledge graph directly influence the correctness of the response of the intelligent robot.
At present, the construction of knowledge graphs is based on manually written structured data. However, manual writing is time-consuming and labor-consuming, and relatively deviated knowledge points are easily missed. This results in that the knowledge map which can be put into use at the present stage is not only very deficient, but also has the problem that the accuracy and the comprehensiveness of the knowledge cannot meet the requirements even if the knowledge map is put into use.
Aiming at the problems, the invention provides a method for constructing a knowledge graph.
In order to ensure the accuracy and comprehensiveness of the knowledge graph in a specific vertical domain, it is required that the knowledge graph contains knowledge data of the corresponding vertical domain as much as possible. In the current technical environment, one important information source with relatively comprehensive knowledge data volume is the web page. Therefore, in the method, the webpage is used as a data source for collecting the knowledge data, so that comprehensive knowledge data aiming at the target knowledge field is obtained.
Furthermore, a complete knowledge map cannot be formed by pure vertical domain knowledge data. In order to simplify the construction process of the knowledge graph as much as possible, in the method, the existing and common data structure is used as a backbone, and the knowledge data in the vertical field is attached to the backbone to form the knowledge graph simply and quickly.
Under the current technical environment, semi-structured data (semi-structured data) is a data type in a database system, and has the following characteristics:
(1) it is a data model suitable for database integration, that is, for describing data contained in two or more databases containing similar data in different schemas.
(2) It is a basic model of markup services for sharing information on the Web.
Compared with the common plain text, the semi-structured data has certain structurality, but has data loss compared with the data of a relational database with a strict theoretical model.
Based on the characteristic analysis of the semi-structured data, in the method, the existing structured data is used as a backbone, knowledge data is collected aiming at a target knowledge field, and the collected knowledge data is filled into the semi-structured data, so that a knowledge graph containing complete vertical field data is obtained. Compared with the prior art, the method and the system can simply and quickly generate the knowledge graph aiming at the specific vertical field, thereby providing powerful data support for the man-machine interaction of the intelligent robot.
The detailed flow of a method according to an embodiment of the invention is described in detail below based on the accompanying drawings, the steps shown in the flow chart of which can be executed in a computer system containing instructions such as a set of computer executable instructions. Although a logical order of steps is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
As shown in fig. 1, in one embodiment, a method comprises:
acquiring semi-structured data (S110);
extracting information from the webpage aiming at the target field, and acquiring vertical field data containing entity nodes and/or node relations (S120);
the vertical domain data acquired in step S120 is supplemented to the semi-structured data acquired in step S110, and a knowledge map including the vertical domain data is generated (S130).
In the method flow of the invention, one of the key points lies in obtaining correct and comprehensive vertical domain data from the webpage. In one embodiment, knowledge information contained in the webpage is determined based on webpage text recognition, and vertical domain knowledge information of a target knowledge domain is screened from the knowledge information contained in the webpage. With the continuous accumulation of the web pages as data sources, the acquired vertical domain knowledge information is also continuously accumulated. As the webpage serving as the data source has a large data volume, the comprehensive vertical domain knowledge information can be ensured to be finally acquired.
Further, semi-structured data is targeted, the missing data of which compared to the complete knowledge graph comprises entity nodes and/or node relationships.
Thus, in one embodiment, the data filling of vertical domain data into semi-structured data is filling of entity nodes and/or node relationships into semi-structured data. Specifically, the vertical domain knowledge information acquired from the web page is converted into specific entity nodes and/or node relationships.
Specifically, as shown in fig. 2, in an embodiment, the extracting information from the web page includes:
text recognition (S210) of recognizing a web page text;
crawling data (S220) for acquiring data related to the target domain based on the text recognition result of step S210;
and (S230) extracting entities and relations, and extracting entity nodes and/or node relations missing semi-structured data from the data acquired in the step S220.
Specifically, in step S230, the extracted result may be a simple entity node, a simple node relationship, or a set of entity nodes and node relationships.
Specifically, in an embodiment, the node relationship of the missing semi-structured data may be a node relationship between entity nodes included in the semi-structured data, a node relationship between entity nodes of the missing semi-structured data, or a node relationship between an entity node of the missing semi-structured data and an entity node included in the semi-structured data.
Further, given the complexity of the information on the network, it may contain redundant information and/or erroneous information. Thus, in one embodiment, the step of crawling the data further comprises a data cleansing step.
In particular, in one embodiment, the data cleansing step performs a re-audit and verification process on the data with the purpose of deleting duplicate information, correcting existing errors, and providing data consistency.
Further, considering that the network information may include sensitive information, in one embodiment, the data cleansing step includes a non-entity cleansing step in which filtering is performed for a specific vocabulary.
Further, in an embodiment, in the entity extraction process, the entity extraction includes a named entity identification step.
Further, in order to ensure the accuracy of named entity identification and avoid missing entity nodes, in an embodiment, a deep learning method is used for named entity identification. Specifically, in one embodiment, a BilSTM + CRF model is used for named entity recognition by using a deep learning method.
Further, in order to ensure that an accurate node relationship is obtained and avoid missing the node relationship, in an embodiment, the node relationship is extracted based on a neural network.
Further, to avoid data redundancy, in an embodiment, when entity extraction and relationship extraction are performed, entity nodes and node relationships existing in the semi-structured data are synchronously compared, so that repeated data is prevented from being filled into the semi-structured data.
Furthermore, based on the method for constructing the knowledge graph provided by the invention, the invention also provides an interaction method. Specifically, as shown in fig. 3, in an embodiment, the method includes:
acquiring user multimodal data (S310);
parsing the user multimodal data to determine a user interaction intention (S320);
determining a vertical field corresponding to the user interaction intention determined in the step S320 (S330);
calling a knowledge graph containing vertical domain data corresponding to the vertical domain determined in step S330 (S340);
extracting knowledge information data required to respond to the user interaction intention determined in step S320 from the knowledge graph called in step S340 (S350);
and generating multi-modal interaction response data for the user interaction intention determined in the step S320 according to the knowledge information data extracted in the step S350 (S360).
Furthermore, in an actual application scenario, theoretically, it cannot be absolutely guaranteed that all knowledge information in a specific vertical field is acquired from a webpage; meanwhile, it cannot be absolutely guaranteed that all knowledge information acquired from the web page is correct. Therefore, it cannot be absolutely guaranteed that the knowledge graph contains all vertical domain data required by the user; meanwhile, it cannot be absolutely guaranteed that all multi-modal interactive responses generated according to vertical domain data in the knowledge graph are completely correct.
Based on the above problems, in an embodiment, a dynamic correction mode is adopted to continuously correct and perfect the knowledge graph. Even if the current knowledge graph has data loss and/or data errors so as to cause unsatisfactory user experience, the data loss and/or data errors of the knowledge graph are less and less inevitably after continuous data correction and perfection, and thus the continuous improvement of the user experience is finally realized.
Specifically, in one embodiment, the web page information is monitored (periodically or aperiodically), new vertical domain knowledge information in the web page information is compared with existing data in the knowledge graph, and when vertical domain knowledge information which is not included in the knowledge graph appears in the web page information, the new vertical domain knowledge information is supplemented to the knowledge graph, so that self-improvement of the knowledge graph is realized.
Further, in an embodiment, when vertical domain knowledge information inconsistent with vertical domain data contained in the knowledge graph appears in the webpage information, the correctness of the webpage information and the vertical domain knowledge information is confirmed, and the correct data is stored in the knowledge graph, so that the self-correction of the knowledge graph is realized.
Further, in one embodiment, whether the current knowledge graph meets the user requirements is determined according to the interactive response of the user, so that the knowledge graph is actively corrected and perfected according to the user requirements.
Specifically, as shown in fig. 4, in an embodiment, the method further includes:
acquiring feedback data of a user for the multi-modal interactive response data (S410);
determining satisfaction of the user with respect to the multi-modal interactive response data according to the feedback data acquired at step S410 (S420);
determining data accuracy and/or data integrity of the intellectual information data extracted from the knowledge-graph according to the satisfaction (S430);
the data of the knowledge information extracted from the knowledge graph is updated according to the data accuracy and/or the data integrity determined in the step S430 and/or the knowledge graph is supplemented (S440).
Further, based on the method of the present invention, the present invention also provides a storage medium, which stores program codes for implementing the method of the present invention.
Furthermore, based on the method, the invention also provides a construction system for the knowledge graph. Specifically, as shown in fig. 5, in an embodiment, the system includes:
an infrastructure construction module 510 configured to obtain semi-structured data;
a data extraction module 520, configured to determine a target domain, extract information from a webpage for the target domain, and obtain vertical domain data including entity nodes and/or node relationships;
a knowledge-graph generation module 530 configured to supplement the vertical domain data into the semi-structured data, generating a knowledge-graph containing the vertical domain data.
Specifically, in an embodiment, as shown in fig. 6, the data extraction module includes:
a text recognizer 610 configured to recognize web page text;
a crawling data unit 620 configured to acquire data related to the target domain based on the text recognition result of the text recognizer 610;
the data extracting unit 630 extracts entity nodes and/or node relationships missing from the data obtained by the crawling data unit 620.
Further, based on the method of the invention, the invention also provides an interactive system. Specifically, in one embodiment, as shown in fig. 7, the system includes:
an input acquisition module 710 configured to collect user multimodal data;
the interaction analysis module 720 is configured to analyze the multi-modal data of the user, obtain the user interaction intention and determine the vertical field corresponding to the user interaction intention;
a knowledge graph calling module 730 configured to call a knowledge graph generated by the construction system proposed by the present invention, the knowledge graph including vertical domain data corresponding to the vertical domain determined by the interaction parsing module 720;
and an interactive response generation module 740 configured to extract knowledge information data required for responding to the user interaction intention from the knowledge map called by the knowledge map calling module 730, and generate multi-modal interactive response data for the user interaction intention according to the knowledge information data.
Further, based on the interaction method and the interaction system, the invention also provides an interaction system based on the virtual human. Specifically, in an embodiment, the system includes an intelligent device and a cloud server, wherein:
the cloud server comprises the interactive system and a plurality of capability interfaces. The interaction system is configured to call a capability interface of the cloud server to acquire and analyze the multi-mode data of the user, and generate and output multi-mode interaction response data. Specifically, each capability interface calls corresponding logic processing in the multi-modal data analysis process.
Specifically, the capability interface of the cloud server comprises a semantic understanding interface, a visual recognition interface, an emotion calculation interface and a cognitive calculation interface.
Specifically, in one embodiment, the following is a description of each interface:
and the semantic understanding interface receives the specific voice instruction forwarded from the communication module of the intelligent device, performs voice recognition on the specific voice instruction and performs natural language processing based on a large amount of linguistic data.
The visual identification interface can detect, identify, track and the like video contents according to a computer visual algorithm, a deep learning algorithm and the like aiming at human bodies, human faces and scenes. Namely, the image is identified according to a preset algorithm, and a quantitative detection result is given. The method has the functions of image preprocessing, feature extraction and decision making. Wherein:
the image preprocessing function may be basic processing of the acquired visual acquisition data, including color space conversion, edge extraction, image transformation, and image thresholding;
the characteristic extraction function can extract characteristic information such as complexion, color, texture, movement, coordinates and the like of a target in the image;
the decision function can be that the feature information is distributed to specific multi-mode output equipment or multi-mode output application needing the feature information according to a certain decision strategy, such as the functions of face detection, person limb identification, motion detection and the like are realized.
And the emotion calculation interface receives the multimodal data forwarded from the communication module and calculates the current emotional state of the user by using emotion calculation logic (which can be emotion recognition technology). The emotion recognition technology is an important component of emotion calculation, the content of emotion recognition research comprises the aspects of facial expression, voice, behavior, text, physiological signal recognition and the like, and the emotional state of a user can be judged through the content. The emotion recognition technology may monitor the emotional state of the user only through the visual emotion recognition technology, or may monitor the emotional state of the user in a manner of combining the visual emotion recognition technology and the voice emotion recognition technology, and is not limited thereto. In this embodiment, it is preferable to monitor the emotion by a combination of both.
The emotion calculation interface collects human facial expression images by using image acquisition equipment during visual emotion recognition, converts the human facial expression images into analyzable data, and then performs expression emotion analysis by using technologies such as image processing and the like. Understanding facial expressions typically requires detecting subtle changes in the expression, such as changes in cheek muscles, mouth, and eyebrow plucking.
And the cognitive computing interface is used for processing the multi-modal data to perform data acquisition, recognition and learning so as to acquire user portrait, knowledge map and the like and reasonably decide multi-modal output data.
It is to be understood that the disclosed embodiments of the invention are not limited to the particular structures, process steps, or materials disclosed herein but are extended to equivalents thereof as would be understood by those ordinarily skilled in the relevant arts. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting.
Reference in the specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Thus, appearances of the phrase "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. Various other embodiments of the method described herein are possible. Various corresponding changes or modifications may be made by those skilled in the art without departing from the spirit of the invention, and these corresponding changes or modifications are intended to fall within the scope of the appended claims.
Claims (8)
1. A method of constructing a knowledge graph, the method comprising:
acquiring semi-structured data, wherein the semi-structured data is a main data structure formed by adopting existing requirement related data and comprises the following characteristics: the data is structural and has data loss;
extracting information from a webpage aiming at a target field, and acquiring vertical field data containing entity nodes and/or node relations;
supplementing the vertical domain data into the semi-structured data to generate a knowledge graph containing vertical domain data;
the process of extracting information from the web page comprises the following steps: text recognition, namely recognizing webpage text;
crawling data, and acquiring data related to the target field based on a text recognition result;
extracting entities and relations, namely extracting entity nodes and/or node relations missing from the obtained data;
extracting node relation based on a neural network;
the extracted results include one or more of the following: a set of simple entity nodes, simple node relationships, and entity nodes and node relationships;
the node relationships for the missing semi-structured data include one or more of the following: the node relationship among entity nodes contained in the semi-structured data, the node relationship among entity nodes missing from the semi-structured data, and the node relationship between the entity nodes missing from the semi-structured data and the contained entity nodes.
2. The method of claim 1, wherein the step of crawling data further comprises:
and data cleaning, wherein the data cleaning is non-entity cleaning, and specific words are filtered.
3. The method of claim 2, wherein the entity extraction comprises:
and (3) named entity recognition, wherein the named entity recognition is carried out by utilizing a deep learning method.
4. An interaction method based on any one of claims 1-3, the method comprising:
obtaining and analyzing multi-modal user data, and determining the user interaction intention;
determining a vertical field corresponding to the user interaction intention;
calling a knowledge graph, wherein the knowledge graph comprises vertical domain data corresponding to the vertical domain;
extracting knowledge information data required for responding to the user interaction intention from the knowledge graph;
and generating multi-modal interaction response data aiming at the user interaction intention according to the knowledge information data.
5. The method of claim 4, further comprising:
acquiring feedback data of a user aiming at the multi-mode interactive response data;
determining satisfaction of the user with respect to the multi-modal interaction response data from the feedback data;
determining the data accuracy and/or data integrity of the knowledge information data extracted from the knowledge graph according to the satisfaction;
and performing data updating on the knowledge information data extracted from the knowledge graph and/or performing data supplement on the knowledge graph according to the data accuracy and/or the data integrity.
6. A storage medium having stored thereon program code for implementing the method according to any one of claims 1-5.
7. A construction system for a knowledge graph, the system comprising:
an infrastructure construction module configured to obtain semi-structured data, wherein the semi-structured data is a backbone data structure formed by existing requirement-related data, and the infrastructure construction module includes the following features: the data is structural and has data loss;
the data extraction module is configured to determine a target field, extract information from a webpage aiming at the target field and acquire vertical field data containing entity nodes and/or node relations;
a knowledge graph generation module configured to supplement the vertical domain data to the semi-structured data, generating a knowledge graph containing vertical domain data;
the data extraction module is configured to perform the following operations:
text recognition, namely recognizing webpage text;
crawling data, and acquiring data related to the target field based on a text recognition result;
extracting entities and relations, namely extracting entity nodes and/or node relations missing from the obtained data;
the data extraction module extracts node relation based on a neural network; the extracted results include one or more of the following: a set of simple entity nodes, simple node relationships, and entity nodes and node relationships;
the node relationships for the missing semi-structured data include one or more of the following: the node relationship among entity nodes contained in the semi-structured data, the node relationship among entity nodes missing from the semi-structured data, and the node relationship between the entity nodes missing from the semi-structured data and the contained entity nodes.
8. An interactive system, characterized in that the system comprises:
an input acquisition module configured to collect user multimodal data;
the interaction analysis module is configured to analyze the user multi-mode data, acquire a user interaction intention and determine a vertical field corresponding to the user interaction intention;
a knowledge-graph calling module configured to call a knowledge-graph generated by the system of claim 7, the knowledge-graph containing vertical domain data corresponding to the vertical domain;
and the interaction response generation module is configured to extract knowledge information data required for responding to the user interaction intention from the knowledge graph, and generate multi-mode interaction response data aiming at the user interaction intention according to the knowledge information data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810842317.8A CN109086391B (en) | 2018-07-27 | 2018-07-27 | Method and system for constructing knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810842317.8A CN109086391B (en) | 2018-07-27 | 2018-07-27 | Method and system for constructing knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109086391A CN109086391A (en) | 2018-12-25 |
| CN109086391B true CN109086391B (en) | 2022-07-01 |
Family
ID=64831028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810842317.8A Active CN109086391B (en) | 2018-07-27 | 2018-07-27 | Method and system for constructing knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086391B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110851612B (en) * | 2019-08-29 | 2023-08-18 | 国家计算机网络与信息安全管理中心 | Mobile application knowledge graph composite completion method and device based on encyclopedia knowledge |
| CN114491085B (en) * | 2022-04-15 | 2022-08-09 | 支付宝(杭州)信息技术有限公司 | Graph data storage method and distributed graph data calculation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956052A (en) * | 2016-04-27 | 2016-09-21 | 青岛海尔软件有限公司 | Building method of knowledge map based on vertical field |
| CN106815293A (en) * | 2016-12-08 | 2017-06-09 | 中国电子科技集团公司第三十二研究所 | System and method for constructing knowledge graph for information analysis |
| CN106960005A (en) * | 2017-02-20 | 2017-07-18 | 北京光年无限科技有限公司 | A kind of output intent and robot for artificial intelligence robot |
| CN107491555A (en) * | 2017-09-01 | 2017-12-19 | 北京纽伦智能科技有限公司 | Knowledge mapping construction method and system |
| CN107665252A (en) * | 2017-09-27 | 2018-02-06 | 深圳证券信息有限公司 | A kind of method and device of creation of knowledge collection of illustrative plates |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090187444A1 (en) * | 2007-05-11 | 2009-07-23 | Yefim Zhuk | Service knowledge map |
-
2018
- 2018-07-27 CN CN201810842317.8A patent/CN109086391B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956052A (en) * | 2016-04-27 | 2016-09-21 | 青岛海尔软件有限公司 | Building method of knowledge map based on vertical field |
| CN106815293A (en) * | 2016-12-08 | 2017-06-09 | 中国电子科技集团公司第三十二研究所 | System and method for constructing knowledge graph for information analysis |
| CN106960005A (en) * | 2017-02-20 | 2017-07-18 | 北京光年无限科技有限公司 | A kind of output intent and robot for artificial intelligence robot |
| CN107491555A (en) * | 2017-09-01 | 2017-12-19 | 北京纽伦智能科技有限公司 | Knowledge mapping construction method and system |
| CN107665252A (en) * | 2017-09-27 | 2018-02-06 | 深圳证券信息有限公司 | A kind of method and device of creation of knowledge collection of illustrative plates |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109086391A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11226673B2 (en) | Affective interaction systems, devices, and methods based on affective computing user interface | |
| CN108665492B (en) | Dance teaching data processing method and system based on virtual human | |
| Zhang et al. | Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot | |
| CN109658928A (en) | A kind of home-services robot cloud multi-modal dialog method, apparatus and system | |
| CN108536681A (en) | Intelligent answer method, apparatus, equipment and storage medium based on sentiment analysis | |
| CN112686048B (en) | Emotion recognition method and device based on fusion of voice, semantics and facial expressions | |
| CN109086860B (en) | Interaction method and system based on virtual human | |
| CN106997243A (en) | Speech scene monitoring method and device based on intelligent robot | |
| CN106502382B (en) | Active interaction method and system for intelligent robot | |
| CN113673244B (en) | Medical text processing method, medical text processing device, computer equipment and storage medium | |
| WO2020224433A1 (en) | Target object attribute prediction method based on machine learning and related device | |
| Morozov | Development of a method for intelligent video monitoring of abnormal behavior of people based on parallel object-oriented logic programming | |
| CN113571184B (en) | Dialogue interactive design method and system for mental health evaluation | |
| CN109086391B (en) | Method and system for constructing knowledge graph | |
| CN112528004A (en) | Voice interaction method, voice interaction device, electronic equipment, medium and computer program product | |
| da Silva et al. | Recognition of affective and grammatical facial expressions: a study for Brazilian sign language | |
| CN112699758A (en) | Sign language translation method and device based on dynamic gesture recognition, computer equipment and storage medium | |
| CN109086351A (en) | A kind of method and user tag system obtaining user tag | |
| CN111524043A (en) | Method and device for automatically generating litigation risk assessment questionnaire | |
| CN112735564A (en) | Mental health state prediction method, mental health state prediction apparatus, mental health state prediction medium, and computer program product | |
| CN111797856B (en) | Modeling method and device, storage medium and electronic equipment | |
| Abdulhamied et al. | Real-time recognition of American sign language using long-short term memory neural network and hand detection | |
| CN111241256A (en) | System for optimizing conversation quality of robot | |
| CN113378826B (en) | Data processing method, device, equipment and storage medium | |
| CN114328864A (en) | Ophthalmic question-answering system based on artificial intelligence and knowledge graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |