CN110929045A - Construction method and system of poetry-semantic knowledge map - Google Patents
Construction method and system of poetry-semantic knowledge map Download PDFInfo
- Publication number
- CN110929045A CN110929045A CN201911239868.6A CN201911239868A CN110929045A CN 110929045 A CN110929045 A CN 110929045A CN 201911239868 A CN201911239868 A CN 201911239868A CN 110929045 A CN110929045 A CN 110929045A
- Authority
- CN
- China
- Prior art keywords
- poetry
- semantic
- knowledge
- question
- knowledge graph
- 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
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
- G06F16/36—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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
Abstract
The embodiment of the invention provides a construction method of a poetry-semantic knowledge graph. The method comprises the following steps: acquiring poetry training data, and determining semantic features and entity features of the poetry training data; modeling the entity characteristics to generate a poetry retrieval database; modeling the semantic features and the entity features to generate a poetry knowledge graph, wherein the poetry knowledge graph is used for associating the semantic features with the entity features; and fusing the preset semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database for modeling to generate a poetry-semantic knowledge graph for poetry knowledge question and answer. The embodiment of the invention also provides a construction system of the poetry-semantic knowledge graph. The embodiment of the invention improves the retrieval efficiency, is quick and efficient, enables the poetry knowledge graph to receive more questions, provides more services, has wider use scenes and more accurate answering content.
Description
Technical Field
The invention relates to the field of knowledge maps, in particular to a construction method and a system of poetry-semantic knowledge maps.
Background
The technology related to poetry question-answer interaction comprises the following steps: crawling poem content; classifying the basic information of poetry; making content association on the labels, contents and the like of poems; some basic objects in the extraction are used as several labels of poetry: such as expressing emotions, themes, etc.; recommending or associating other poems according to the search of one poem; helping the user learn knowledge. And these focus on either the poetry itself or the association in a poetry database.
The knowledge graph is constructed in various forms and fields, such as construction of semantic networks, construction of proprietary fields (medical, health and wellness) and the like, or a recommendation system based on commodity buying and selling. Poetry is often used in knowledge maps as a module in the field of education or literature, and most of the common poetry information such as Baidu encyclopedia is simply presented.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the related art:
when the question answering of poetry is realized, the general poetry question answering technology does not carry out deep knowledge mining on poetry, and is lack of association with a semantic network and a general knowledge map.
The general poetry atlas contains basic information of poetry such as the content, author, emotion, classification, annotation, temperament and the like. These basic information are then stored in a knowledge graph and associated with similar poems. Poems of the same author can be associated, all belong to poems of countryside, the top sentence of the Tang Dynasty and the like.
The association lacks the mining of poetry deep content, a direct association method is adopted during association, semantic information contained in poetry content cannot be extracted, and the retrieval range is fixed and limited. The lack of semantic association manifests as: other poems describing the bed or poems related to the bright moon are difficult to be reiterated in the sentence of 'light before bed' and the moon, a 'thinking home' label is generally marked on 'quiet night thought', and the semantics inside the poems are not further processed. The mining and characterization of poetry content is also lacked when the database is modeled, and semantic information is often ignored.
The common knowledge-graph technology rarely constructs poems as a proprietary domain. In the existing literature, a knowledge graph related to poetry generally relates poetry basic information to other fields. For example, as the general knowledge map is not associated with knowledge in the fields, the super questions are the questions which are difficult to answer for the general knowledge map, or the Chinese peaches in the family of the last year and this day are flourishing for several months, and the questions cannot be answered in the commonly used poetry knowledge map.
Disclosure of Invention
In order to solve the problem that a knowledge graph database in the prior art is difficult to express quickly and efficiently in retrieval efficiency, common poetry knowledge graphs are generally aggregated in poetry in the application direction and lack of connection with the whole semantic network, so that the knowledge graphs are single in application, single in inquiry method, single in service function and single in use scene, and wrong questions may appear in the answered content.
In a first aspect, an embodiment of the present invention provides a method for constructing a poetry-semantic knowledge base, including:
acquiring poetry training data, and determining semantic features and entity features of the poetry training data;
modeling the entity characteristics to generate a poetry retrieval database;
modeling the semantic features and the entity features to generate a poetry knowledge graph, wherein the poetry knowledge graph is used for associating the semantic features and the entity features;
and fusing a preset semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database for modeling to generate a poetry-semantic knowledge graph for poetry knowledge question and answer.
In a second aspect, an embodiment of the present invention provides a poetry question-answer method based on a poetry-semantic knowledge base, where the method includes:
responding to a poetry question of a user, and performing semantic analysis on the poetry question to determine a query statement;
inputting the query statement into a poetry-semantic knowledge map, determining a poetry statement corresponding to the query statement based on a poetry retrieval database, determining question semantics of the query statement based on the poetry knowledge map, performing knowledge acquisition on the question semantics based on a semantic network knowledge map, and determining a reply answer for replying a poetry question dialogue;
and feeding back the reply answer to the user.
In a third aspect, an embodiment of the present invention provides a system for constructing a poetry-semantic knowledge base, including:
the system comprises a characteristic determining program module, a characteristic determining program module and a characteristic determining program module, wherein the characteristic determining program module is used for acquiring poetry training data and determining semantic characteristics and entity characteristics of the poetry training data;
the retrieval database generation program module is used for modeling the entity characteristics to generate a poetry retrieval database;
a poetry knowledge map generation program module for modeling the semantic features and the entity features to generate a poetry knowledge map, wherein the poetry knowledge map is used for associating the semantic features and the entity features;
and the map construction program module is used for fusing a preset semantic network knowledge map, the poetry knowledge map and the poetry retrieval database for modeling to generate a poetry-semantic knowledge map for poetry knowledge question answering.
In a fourth aspect, an embodiment of the present invention provides a poetry question-answering system based on a poetry-semantic knowledge base, including:
the query sentence determination program module is used for responding to a poetry question of a user and performing semantic analysis on the poetry question to determine a query sentence;
a reply answer determining program module, configured to input the query statement to a poetry-semantic knowledge base constructed according to the system of claim 7, determine a poetry statement corresponding to the query statement based on a poetry retrieval database, determine question semantics of the query statement based on the poetry knowledge base, perform knowledge acquisition on the question semantics based on a semantic network knowledge base, and determine a reply answer to a reply poetry question dialog;
and the feedback program module is used for feeding back the reply answer to the user.
In a fifth aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the steps of the poetry-semantic-knowledge-map construction method and the poetry question-answer method based on the poetry-semantic-knowledge-map of any of the embodiments of the present invention.
In a sixth aspect, an embodiment of the present invention provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the method for constructing a poetry-semantic knowledge base and the method for question-answering a poetry based on the poetry-semantic knowledge base of any embodiment of the present invention.
The embodiment of the invention has the beneficial effects that: the combination of the special poetry field and the general semantic network knowledge graph is a successful attempt to combine various knowledge graphs. The retrieval efficiency is improved, and meanwhile, the poetry knowledge graph can receive more questions, provide more services, have wider use scenes and more accurate answer contents.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for constructing a poetry-semantic knowledge base according to an embodiment of the present invention;
FIG. 2 is a relational structure diagram of a construction method of a poetry-semantic knowledge base according to an embodiment of the present invention;
FIG. 3 is a flow chart of a poetry question-answer method based on a poetry-semantic knowledge base according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a construction system of a poetry-semantic knowledge base according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a poetry question-answer system based on a poetry-semantic knowledge base according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 flowchart of a method for constructing a poetry-semantic knowledge base according to an embodiment of the present invention, including the following steps:
s11: acquiring poetry training data, and determining semantic features and entity features of the poetry training data;
s12: modeling the entity characteristics to generate a poetry retrieval database;
s13: modeling the semantic features and the entity features to generate a poetry knowledge graph, wherein the poetry knowledge graph is used for associating the semantic features and the entity features;
s14: and fusing a preset semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database for modeling to generate a poetry-semantic knowledge graph for poetry knowledge question and answer.
For step S11, in order to more deeply mine semantic information inside the poem, a variety of deep neural networks are applied to extract and correlate entity information in the poem. Common elements of a poem are: title, content, author, year, subject, emotion, annotation, temperament and other basic information, and the information is also the most common data presentation of poetry knowledge maps. However, if it is desired to go deep to which persons and things are mentioned in each poem, which word indicates which intent, it is not possible to extract the information with these features and representations without complicated data mining.
As an embodiment, the semantic features include at least: keywords, synonyms, antonyms, negatives, adjectives;
the physical characteristics at least comprise people, places, tissues, events, natural phenomena, animals and plants in poetry. In order to extract more information
For example, the transducer, self-attribute, etc. can be used to extract the content of the poetry by NER (named entity Recognition), etc., so as to obtain more information enriched in the content of the poetry. For example, in Jing Ye Si (thought at night), "Ming Yue Guang before bed", it is suspected that the frost is on the ground. To look at the moon and to look low at the hometown. 'bed' can be extracted on the basic information as a living article, 'frost' as a natural phenomenon, and 'moon' as a celestial body. For example, in "Libai boat going on" from Wanlun on hand, the song is stepped on the bank. The depth of the Taohuatan pool is thousands of feet, which is not as good as the Wanlun Send me situation. "the poem can extract two characters of" Libai "and" Wanlun ", a place of" Taohuatan ", and the like. The extracted semantic features are words such as 'multiply', 'desire', 'smell', 'collapse', 'deep', 'send', etc. The intent of the corresponding entity feature is represented.
For step S12, when querying, the general knowledge graph uses an RDF (Resource description framework) framework to model knowledge, which has the advantages of describing relationships in entities well and has the disadvantage of very slow retrieval speed. The conventional knowledge graph retrieval frames in the market all have the problems of slow query and low concurrency, and particularly can only query an entity basically but cannot query the content and description of the entity, so that the knowledge graph database can only solve part of problems in practical application.
While general recommendation or retrieval type databases can efficiently query documents, they cannot describe the internal association of documents and understand the relationship between documents and entity knowledge.
To address this problem, a database modeling of the determined poetry entity characteristics is performed. For the internal knowledge and entity association related to poetry, for example, the semantic association of the Taohuatan place and the 'deep' is carried out to obtain the relation between the internal entity knowledge in the poetry. The combination of poetry and semantic knowledge is solved by adopting a knowledge map frame. When a poetry retrieval and recommendation type problem is met, a poetry retrieval type database is used for searching poetry contents.
For step S13, by combining semantic features and entity features with a common knowledge graph, the poetry knowledge graph can enrich multiple kinds of knowledge questions and answers to poetry, which is rarely applied in the prior knowledge graph. Through the deep excavation of the internal knowledge of the poem, the semantics and the entities in the poem can be excavated, and the method comprises the following steps: characters, places, organizations, dynasties, time, nature, stars, living things, mathematics, events, etc. And then the characteristics are fused with a common knowledge map, so that very interesting knowledge question answering can be carried out.
Wanlon refers to who ' in the ' not-too-wanlon ' send me situation ', and can answer ' wanlon, character shin, character fenglin, she state \40671; (yellow mountain, ge anhui, tazey, japan). The poems, famous poems, in the order of jing between the elements of the Tang dynasty were Libai friends. "
For another example, when a peach flower blooms in the 'facial peach flower looks red', the answer can be obtained through the extracted 'peach flower': peach blossoms are usually open in spring for 3,4 months.
And for the step S14, fusing and modeling the preset semantic network knowledge graph and the poetry retrieval database determined in the steps S12 and S13. The poetry-semantic knowledge graph fused in the way not only can correlate knowledge entities in poetry, but also can be fused by using the knowledge graph to obtain interesting knowledge question and answer.
Through the implementation mode, the combination of the special poetry field and the general semantic network knowledge graph is a successful attempt to combine multiple knowledge graphs. The retrieval efficiency is improved, and meanwhile, the poetry knowledge graph can receive more questions, provide more services, have wider use scenes and more accurate answer contents.
As an implementation manner, in this embodiment, the modeling by fusing the preset semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database includes:
associating the poetry knowledge graph with the semantic network knowledge graph for acquiring knowledge from the poetry knowledge graph to the semantic network knowledge graph;
and associating the poetry knowledge graph with the poetry retrieval database, and performing poetry query on the poetry knowledge graph from the poetry retrieval database.
In the embodiment, in order to fuse the semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database and embody the relationship between the graph and the database after fusion modeling, as shown in fig. 2, the poetry knowledge graph is connected with the semantic network knowledge graph, and when the poetry knowledge graph receives a problem, knowledge acquisition is carried out on the semantic network knowledge graph to obtain an answer. And when the poetry knowledge graph receives a poetry retrieval problem, the poetry knowledge graph fuses knowledge skip to the poetry retrieval database to acquire corresponding poetry data.
According to the implementation mode, the structural relationship between each knowledge graph and the database is given, and the retrieval efficiency of the poetry-semantic knowledge graph and the accuracy of answering poetry questions are further improved.
Fig. 3 is a flowchart of a poetry question-answer method based on a poetry-semantic knowledge base, which is provided by an embodiment of the present invention, and the method includes the following steps:
s21: responding to a poetry question of a user, and performing semantic analysis on the poetry question to determine a query statement;
s22: inputting the query statement into a poetry-semantic knowledge map constructed according to the method of claim 1, determining a poetry sentence corresponding to the query statement based on a poetry retrieval database, determining question semantics of the query statement based on the poetry knowledge map, performing knowledge acquisition on the question semantics based on a semantic network knowledge map, and determining a reply answer to reply to a poetry question dialogue;
s23: and feeding back the reply answer to the user.
With step S21, for example, the user says "when the flower blooms in the second sentence of the topic city south village" at the time of use by the user. At the moment, the poetry questions are subjected to semantic analysis, the sentences needing to be inquired are determined, firstly, what is the second sentence of 'subject city south village', what flowers are asked by the user is determined, secondly, after what flowers are asked, the time for the semantic questions to bloom is determined.
For step S22, at this time, the query statement is input into the poetry-semantic knowledge base. Determining a poetry sentence corresponding to the query sentence based on a poetry retrieval database, determining the queried poetry sentence ' the face is pink, and determining question semantics of the query sentence based on a poetry knowledge graph, thereby determining that the poetry sentence asked by a user is ' the blossom poetry sentence of peach blossom '. And acquiring knowledge of the question semantics based on a semantic network knowledge graph, and inquiring an answer that the peach blossoms are in 3-4 months.
For step S23, the answer is 'facial peach blossom is red, and the peach blossom in the answer is 3-4 months'.
According to the embodiment, more complex questions can be answered by using the poetry-semantic knowledge graph, the answered answers are more accurate, and the using effect of the user is improved.
As an implementation manner, in this embodiment, after the responding to the poetry question of the user and performing semantic parsing on the poetry question to determine a query statement, the method further includes:
determining the question type of the poetry questioning dialogue based on the query sentence, wherein the question type at least comprises poetry retrieval questions;
and when the question type is a poetry retrieval question, determining an answer poetry sentence corresponding to the query sentence through a poetry retrieval database in a poetry-semantic knowledge map, and replying.
When the user's question is less complex, if the user only asks a query-type question, for example, only asks the next sentence of a poetry sentence, or a certain sentence in a poetry, when a knowledge-graph-type question-answer is not needed. And only using a poem retrieval database to determine answer poems corresponding to the query sentences for answering. The efficiency of answering the user's questions is further improved.
As an embodiment, after the feeding back the reply answer to the user, the method further includes:
sending a plurality of evaluation levels of the reply answer to the user for the user to select, wherein the plurality of evaluation levels at least comprise: the answer is correct and wrong;
and receiving the evaluation level selected by the user, and feeding back to the developer when the answer to any one poem question receives the wrong evaluation level of answers exceeding the preset number for the developer to adjust so as to improve the quality of the answer to be replied.
In the embodiment, for unusual poetry, the entity and semantic features have obvious deviation when poetry is asked and answered. By introducing a labeling and evaluating mechanism, poetry content is fed back, the problem of easy error is intensively solved, and the reply quality can be effectively improved.
Fig. 4 is a schematic structural diagram of a system for constructing a poetry-semantic knowledge base according to an embodiment of the present invention, which can execute the method for constructing a poetry-semantic knowledge base according to any of the embodiments described above and is configured in a terminal.
The construction system of the poetry-semantic knowledge base provided by the embodiment comprises: a feature determination program module 11, a search database generation program module 12, a poetry knowledge map generation program module 13, and a map construction program module 14.
The characteristic determining program module 11 is configured to obtain poetry training data, and determine semantic characteristics and entity characteristics of the poetry training data; the retrieval database generation program module 12 is used for modeling the entity characteristics to generate a poetry retrieval database; the poetry knowledge map generation program module 13 is used for modeling the semantic features and the entity features to generate a poetry knowledge map, and the poetry knowledge map is used for associating the semantic features and the entity features; the map construction program module 14 is configured to fuse a preset semantic network knowledge map, the poetry knowledge map and the poetry retrieval database for modeling, and generate a poetry-semantic knowledge map for poetry knowledge question answering.
The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores computer executable instructions which can execute the construction method of the poetry-semantic knowledge graph in any method embodiment;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
acquiring poetry training data, and determining semantic features and entity features of the poetry training data;
modeling the entity characteristics to generate a poetry retrieval database;
modeling the semantic features and the entity features to generate a poetry knowledge graph, wherein the poetry knowledge graph is used for associating the semantic features and the entity features;
and fusing a preset semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database for modeling to generate a poetry-semantic knowledge graph for poetry knowledge question and answer.
Fig. 5 is a schematic structural diagram of a poetry question-answering system based on a poetry-semantic knowledge base, which is provided by an embodiment of the present invention, and the system can execute the poetry question-answering method based on the poetry-semantic knowledge base described in any embodiment above and is configured in a terminal.
The poetry question-answer system based on the poetry-semantic knowledge base provided by the embodiment comprises: a query statement determination program module 21, a reply answer determination program module 22 and a feedback program module 23.
Wherein, the query sentence determination program module 21 is configured to respond to a poetry question of a user, and perform semantic analysis on the poetry question to determine a query sentence; the answer reply determination program module 22 is configured to input the query statement to a poetry-semantic knowledge base, determine a poetry sentence corresponding to the query statement based on a poetry retrieval database, determine question semantics of the query statement based on the poetry knowledge base, perform knowledge acquisition on the question semantics based on a semantic network knowledge base, and determine a reply answer to a reply poetry question dialogue; the feedback program module 23 is used for feeding back the answer to the user.
The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores computer executable instructions which can execute the poetry question-answer method based on the poetry-semantic knowledge graph in any method embodiment;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
responding to a poetry question of a user, and performing semantic analysis on the poetry question to determine a query statement;
inputting the query statement into a poetry-semantic knowledge map, determining a poetry statement corresponding to the query statement based on a poetry retrieval database, determining question semantics of the query statement based on the poetry knowledge map, performing knowledge acquisition on the question semantics based on a semantic network knowledge map, and determining a reply answer for replying a poetry question dialogue;
and feeding back the reply answer to the user.
As a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the methods in embodiments of the present invention. One or more program instructions are stored in a non-transitory computer readable storage medium, which when executed by a processor, perform a method of constructing a poetry-semantic knowledge base and a poetry question-answering method based on the poetry-semantic knowledge base in any of the above method embodiments.
The non-volatile computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the device, and the like. Further, the non-volatile computer-readable storage medium may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the non-transitory computer readable storage medium optionally includes memory located remotely from the processor, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
An embodiment of the present invention further provides an electronic device, which includes: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the steps of the poetry-semantic-knowledge-map construction method and the poetry question-answer method based on the poetry-semantic-knowledge-map of any of the embodiments of the present invention.
The client of the embodiment of the present application exists in various forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones, multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as tablet computers.
(3) Portable entertainment devices such devices may display and play multimedia content. The devices comprise audio and video players, handheld game consoles, electronic books, intelligent toys and portable vehicle-mounted navigation devices.
(4) Other electronic devices with data processing capabilities.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A construction method of a poetry-semantic knowledge graph comprises the following steps:
acquiring poetry training data, and determining semantic features and entity features of the poetry training data;
modeling the entity characteristics to generate a poetry retrieval database;
modeling the semantic features and the entity features to generate a poetry knowledge graph, wherein the poetry knowledge graph is used for associating the semantic features and the entity features;
and fusing a preset semantic network knowledge graph, the poetry knowledge graph and the poetry retrieval database for modeling to generate a poetry-semantic knowledge graph for poetry knowledge question and answer.
2. The method of claim 1, wherein the fusing the preset semantic web knowledge graph, the poetry knowledge graph, and the poetry retrieval database for modeling comprises:
associating the poetry knowledge graph with the semantic network knowledge graph for acquiring knowledge from the poetry knowledge graph to the semantic network knowledge graph;
and associating the poetry knowledge graph with the poetry retrieval database, and performing poetry query on the poetry knowledge graph from the poetry retrieval database.
3. The method of claim 1, wherein the semantic features include at least: keywords, synonyms, antonyms, negatives, adjectives;
the physical characteristics at least comprise people, places, tissues, events, natural phenomena, animals and plants in poetry.
4. A poetry question-answer method based on a poetry-semantic knowledge domain comprises the following steps:
responding to a poetry question of a user, and performing semantic analysis on the poetry question to determine a query statement;
inputting the query statement into a poetry-semantic knowledge map constructed according to the method of claim 1, determining a poetry sentence corresponding to the query statement based on a poetry retrieval database, determining question semantics of the query statement based on the poetry knowledge map, performing knowledge acquisition on the question semantics based on a semantic network knowledge map, and determining a reply answer to reply to a poetry question dialogue;
and feeding back the reply answer to the user.
5. The method of claim 4, wherein after said semantically parsing said poetry query to determine a query statement in response to a poetry query of a user, said method further comprises:
determining the question type of the poetry questioning dialogue based on the query sentence, wherein the question type at least comprises poetry retrieval questions;
and when the question type is a poetry retrieval question, determining an answer poetry sentence corresponding to the query sentence through a poetry retrieval database in a poetry-semantic knowledge map, and replying.
6. The method of claim 4, wherein after said feeding back the reply answer to the user, the method further comprises:
sending a plurality of evaluation levels of the reply answer to the user for the user to select, wherein the plurality of evaluation levels at least comprise: the answer is correct and wrong;
and receiving the evaluation level selected by the user, and feeding back to the developer when the answer to any one poem question receives the wrong evaluation level of answers exceeding the preset number for the developer to adjust so as to improve the quality of the answer to be replied.
7. A construction system of a poetry-semantic knowledge base, comprising:
the system comprises a characteristic determining program module, a characteristic determining program module and a characteristic determining program module, wherein the characteristic determining program module is used for acquiring poetry training data and determining semantic characteristics and entity characteristics of the poetry training data;
the retrieval database generation program module is used for modeling the entity characteristics to generate a poetry retrieval database;
a poetry knowledge map generation program module for modeling the semantic features and the entity features to generate a poetry knowledge map, wherein the poetry knowledge map is used for associating the semantic features and the entity features;
and the map construction program module is used for fusing a preset semantic network knowledge map, the poetry knowledge map and the poetry retrieval database for modeling to generate a poetry-semantic knowledge map for poetry knowledge question answering.
8. A poetry question-answer system based on a poetry-semantic knowledge base, comprising:
the query sentence determination program module is used for responding to a poetry question of a user and performing semantic analysis on the poetry question to determine a query sentence;
a reply answer determining program module, configured to input the query statement to a poetry-semantic knowledge base constructed according to the system of claim 7, determine a poetry statement corresponding to the query statement based on a poetry retrieval database, determine question semantics of the query statement based on the poetry knowledge base, perform knowledge acquisition on the question semantics based on a semantic network knowledge base, and determine a reply answer to a reply poetry question dialog;
and the feedback program module is used for feeding back the reply answer to the user.
9. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any of claims 1-6.
10. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911239868.6A CN110929045B (en) | 2019-12-06 | 2019-12-06 | Construction method and system of poetry-semantic knowledge map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911239868.6A CN110929045B (en) | 2019-12-06 | 2019-12-06 | Construction method and system of poetry-semantic knowledge map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110929045A true CN110929045A (en) | 2020-03-27 |
| CN110929045B CN110929045B (en) | 2022-07-12 |
Family
ID=69858155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911239868.6A Active CN110929045B (en) | 2019-12-06 | 2019-12-06 | Construction method and system of poetry-semantic knowledge map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929045B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651570A (en) * | 2020-05-13 | 2020-09-11 | 深圳追一科技有限公司 | Text sentence processing method and device, electronic equipment and storage medium |
| CN112101040A (en) * | 2020-08-20 | 2020-12-18 | 淮阴工学院 | Ancient poetry semantic retrieval method based on knowledge graph |
| CN112632386A (en) * | 2020-12-29 | 2021-04-09 | 广州视源电子科技股份有限公司 | Poetry recommendation method, device and equipment and storage medium |
| CN112989068A (en) * | 2021-04-28 | 2021-06-18 | 新疆大学 | Knowledge graph construction method for Tang poetry knowledge and Tang poetry knowledge question-answering system |
| CN113127627A (en) * | 2021-04-23 | 2021-07-16 | 中国石油大学(华东) | Poetry recommendation method based on LDA topic model and poetry knowledge map |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8407253B2 (en) * | 2009-12-09 | 2013-03-26 | Electronics And Telecommunications Research Institute | Apparatus and method for knowledge graph stabilization |
| CN109766453A (en) * | 2019-01-18 | 2019-05-17 | 广东小天才科技有限公司 | A kind of method and system of user's corpus semantic understanding |
| CN109902187A (en) * | 2019-03-21 | 2019-06-18 | 广东小天才科技有限公司 | A kind of construction method and device, terminal device of feature knowledge map |
-
2019
- 2019-12-06 CN CN201911239868.6A patent/CN110929045B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8407253B2 (en) * | 2009-12-09 | 2013-03-26 | Electronics And Telecommunications Research Institute | Apparatus and method for knowledge graph stabilization |
| CN109766453A (en) * | 2019-01-18 | 2019-05-17 | 广东小天才科技有限公司 | A kind of method and system of user's corpus semantic understanding |
| CN109902187A (en) * | 2019-03-21 | 2019-06-18 | 广东小天才科技有限公司 | A kind of construction method and device, terminal device of feature knowledge map |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651570A (en) * | 2020-05-13 | 2020-09-11 | 深圳追一科技有限公司 | Text sentence processing method and device, electronic equipment and storage medium |
| CN112101040A (en) * | 2020-08-20 | 2020-12-18 | 淮阴工学院 | Ancient poetry semantic retrieval method based on knowledge graph |
| CN112101040B (en) * | 2020-08-20 | 2024-03-29 | 淮阴工学院 | Ancient poetry semantic retrieval method based on knowledge graph |
| CN112632386A (en) * | 2020-12-29 | 2021-04-09 | 广州视源电子科技股份有限公司 | Poetry recommendation method, device and equipment and storage medium |
| CN113127627A (en) * | 2021-04-23 | 2021-07-16 | 中国石油大学(华东) | Poetry recommendation method based on LDA topic model and poetry knowledge map |
| CN112989068A (en) * | 2021-04-28 | 2021-06-18 | 新疆大学 | Knowledge graph construction method for Tang poetry knowledge and Tang poetry knowledge question-answering system |
| CN112989068B (en) * | 2021-04-28 | 2022-04-19 | 新疆大学 | Knowledge graph construction method for Tang poetry knowledge and Tang poetry knowledge question-answering system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110929045B (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929045B (en) | Construction method and system of poetry-semantic knowledge map | |
| US10720078B2 (en) | Systems and methods for extracting keywords in language learning | |
| CN108446286B (en) | Method, device and server for generating natural language question answers | |
| CN109940627B (en) | Man-machine interaction method and system for picture book reading robot | |
| CN111400506B (en) | Ancient poetry proposition method and system | |
| CN106126524B (en) | Information pushing method and device | |
| CN105068661A (en) | Man-machine interaction method and system based on artificial intelligence | |
| JP2019504410A (en) | Travel guide generation method and system | |
| CN107133303A (en) | Method and apparatus for output information | |
| CN109299399B (en) | Learning content recommendation method and terminal equipment | |
| CN110569364A (en) | online teaching method, device, server and storage medium | |
| CN108920450A (en) | A kind of knowledge point methods of review and electronic equipment based on electronic equipment | |
| CN111553138B (en) | Auxiliary writing method and device for standardizing content structure document | |
| KR102146433B1 (en) | Method for providing context based language learning service using associative memory | |
| CN114707000A (en) | Knowledge graph-based question-answer library generation method and device, electronic equipment and storage medium | |
| CN116362331A (en) | Knowledge point filling method based on man-machine cooperation construction knowledge graph | |
| CN112800177B (en) | FAQ knowledge base automatic generation method and device based on complex data types | |
| CN114238787B (en) | Answer processing method and device | |
| CN111026834B (en) | Question and answer corpus generation method and system | |
| CN109284364B (en) | Interactive vocabulary updating method and device for voice microphone-connecting interaction | |
| CN109063127A (en) | A kind of searching method, device, server and storage medium | |
| CN109636693A (en) | A kind of exercise purpose recommended method and electronic equipment | |
| Miluț et al. | Iasi City Explorer-Alexa, what can we do today? | |
| Núñez Miniguano | Podcasts for the enhancement of listening skills in second year high school students | |
| Suhartono et al. | Implementation of Voice Recognition Technology on English Learning Application by Self Learning Based on Android Device |
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 | ||
| CB02 | Change of applicant information |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant before: AI SPEECH Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |