CN112613611A - Tax knowledge base system based on knowledge graph - Google Patents
Tax knowledge base system based on knowledge graph Download PDFInfo
- Publication number
- CN112613611A CN112613611A CN202011592779.2A CN202011592779A CN112613611A CN 112613611 A CN112613611 A CN 112613611A CN 202011592779 A CN202011592779 A CN 202011592779A CN 112613611 A CN112613611 A CN 112613611A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- module
- tax
- data
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000010276 construction Methods 0.000 claims abstract description 15
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000012423 maintenance Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 39
- 239000013598 vector Substances 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000007639 printing Methods 0.000 claims description 6
- 238000011144 upstream manufacturing Methods 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 3
- 238000009411 base construction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000009193 crawling Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000012916 structural analysis Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/027—Frames
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of tax knowledge bases, and discloses a tax knowledge base system based on a knowledge graph, which comprises a data module, a knowledge module and a test evaluation module, wherein the knowledge module comprises: the system comprises a knowledge acquisition module, a knowledge fusion module, a knowledge calculation module, a knowledge representation module, a knowledge construction module, a knowledge storage module and a knowledge operation and maintenance module. According to the invention, by arranging the knowledge acquisition module, the knowledge fusion module, the knowledge calculation module, the knowledge representation module, the knowledge construction module, the knowledge storage module and the knowledge operation and maintenance module, the problems that the knowledge structure in the tax field is complex and difficult to construct, the knowledge relationship is difficult to sort and construct, the knowledge in the tax field has timeliness, the condition that the knowledge in the tax field fails just after being constructed can exist in the construction of the traditional method, the service knowledge quantity in the tax field is huge, the service knowledge in the tax field is crossed with the knowledge in other industries, the construction of the service knowledge in the tax field needs talents with professional backgrounds, and the like are solved.
Description
Technical Field
The invention relates to the technical field of tax knowledge bases, in particular to a tax knowledge base system based on a knowledge graph.
Background
The tax system is an organic whole consisting of tax institutions which have common tax targets and are mutually associated. From the perspective of organization, a tax authority may be considered a tax system. The functional departments such as the basic collection institution, personnel, tickets, accountants, statistics, plans and the like which belong to the tax authority system form parts of the tax authority system, and the common goal of the departments is to complete tax tasks.
The existing tax knowledge base system has the following problems in the using process:
1. the knowledge structure in the tax field is complex and difficult to construct, and the knowledge relationship is difficult to sort and construct.
2. The tax field knowledge is time-efficient, and the traditional method construction may have the condition of failure just after construction.
3. The business knowledge amount in the tax field is huge.
4. Business knowledge in the tax field is crossed with other industry knowledge.
5. Construction of business knowledge in the tax field requires talents with professional backgrounds. Therefore, a tax knowledge base system based on the knowledge graph is provided.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a tax knowledge base system based on a knowledge graph.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme: a tax knowledge base system based on knowledge graph, a data module, a knowledge module and a test evaluation module, wherein the knowledge module comprises: the system comprises a knowledge acquisition module, a knowledge fusion module, a knowledge calculation module, a knowledge representation module, a knowledge construction module, a knowledge storage module and a knowledge operation and maintenance module;
the data module specifically comprises:
a) the method is used as a knowledge acquisition source and comprises structured data, semi-structured data and unstructured data, wherein the final structure of the data is entity-attribute-value;
b) structured data, related data in a relational database;
i. the tax completion certification is printed;
attributes containing upstream outstanding traffic;
value real name authentication;
c) the semi-structured data is log-related, third-party interface data and other data sources;
i. the semi-structured data may only comprise entity-attribute, entity-value, attribute-value;
ii, data completion is required to be carried out through data integration, a third-party interface, algorithm prediction and other modes;
the unstructured data needs to be completed in ways of entity extraction, attribute extraction, value prediction, value association and the like;
entity extraction, attribute extraction will be introduced in knowledge acquisition.
Preferably, the knowledge acquisition module specifically includes:
a) the knowledge acquisition is used as a key component in the whole engine and mainly completes the functions of information extraction, entity identification, relationship extraction, attribute extraction and the like;
b) the first step of tax concept extraction and knowledge base construction is that how to automatically extract information from heterogeneous data into candidate knowledge units;
c) extracting an entity by adopting a Bi.LSTM.CRE model;
i. data input, namely tax linguistic data, crawling policy, tax report, data and books;
ii, outputting the result of the tax business, the tax policy and the tax rule;
d) relationship extraction, through entity extraction, some tax business entities are obtained, but these entities
The entities are discrete, and in order to obtain semantic information, the entities can be connected together only by extracting the relationships among the entities;
i. the relation extraction adopts four modes of models to carry out Ensemble;
ii, supervised learning method, for known relationship, model is Bi-LSTM;
1) the input is entity corpora;
2) the output is the relationship;
the semi-supervised learning method comprises the steps of adopting BootStraping to extract the relation, setting a plurality of seed corpora and finding out the corresponding relation;
1) business, tax completion certification printing;
2) attribute-contains upstream outstanding traffic;
3) value-real name authentication;
4) find some similar relation data, this seed is equivalent to the template;
adopting syntactic analysis and dependency analysis to obtain a structural analysis result of the sentence, and extracting through the relation phrase;
v. rule extraction method:
1) setting a rule word (relation word), for example, if necessary, completing, and authenticating a real name;
2) and detecting the rule words, performing entity extraction, and extracting the relation obtained by the corresponding service.
Preferably, the knowledge fusion module specifically comprises: the knowledge fusion is a technology for fusing a plurality of related knowledge maps and knowledge bases together.
Preferably, the knowledge calculation module specifically includes:
a) the main function of knowledge calculation is knowledge reasoning, and how one knowledge infers another knowledge, a reasoning mechanism;
b) knowledge statistics, which is used for reasoning calculation through a statistical inference mode;
c) graph computation.
Preferably, the knowledge representation module is specifically:
a) a symbolic representation RDF triple;
subject-subject;
predicate-predicate;
object-object;
examples iv
1) Subject is tax proof printing;
2) setting a starting date;
3) object is start date;
b) VSM representation
i. A representation method based on a space vector model;
modeling the entities into column vectors and relationships into matrixes, and determining the relationships between the entities by performing pictographic transformation on the entity vectors and the shutdown matrixes and finally performing clicking operation on the entities and the tail entities;
a typical approach includes a-tasse model based on the trigonometric rule and norm principle of vectors, a tranh, transr, and transd model that deal with multivariate relations through hyperplane transformation or linear transformation, a-trassparse-model that resolves heterogeneous multivariate relations by adding a sparsity parameter vector.
Preferably, the knowledge construction module specifically comprises:
a) generating a conceptual top-bottom relationship;
b) attribute identification;
c) rule modeling;
d) spatio-temporal modeling.
Preferably, the knowledge storage module specifically includes:
a) knowledge storage, namely storing the knowledge triples and the vectorized representation;
b) storing the triples in a relational database based on the table structure;
c) based on a graph structure, a graph database is based on a directed graph, the theoretical basis of the graph database is graph theory, and nodes, edges and attributes are core concepts of the graph database.
Preferably, the knowledge operation and maintenance module specifically comprises:
a) knowledge collaboration;
b) knowledge validation;
c) correction of knowledge.
Preferably, the test evaluation name module specifically comprises:
a) accuracy evaluation, wherein each time the model is on line, the accuracy rate is obtained, and an evaluation report of test run is referred to;
b) coverage rate evaluation, namely periodically updating the triggering times and the unanswered ratio of all knowledge points in the knowledge base;
c) and performance evaluation, namely periodically evaluating the response and load performance of the current knowledge base.
(III) advantageous effects
Compared with the prior art, the invention provides a tax knowledge base system based on a knowledge graph, which has the following beneficial effects:
the tax knowledge base system based on the knowledge map solves the problems that the tax domain knowledge structure is complex and difficult to construct, knowledge relations are difficult to sort and construct, the tax domain knowledge has timeliness, the traditional method is constructed and the condition that the tax domain knowledge is invalid just after being constructed can exist, the tax domain business knowledge is huge, the tax domain business knowledge and other industry knowledge are crossed, and the tax domain business knowledge construction needs to have the problems of talents with professional backgrounds and the like by arranging the knowledge acquisition module, the knowledge fusion module, the knowledge calculation module, the knowledge representation module, the knowledge construction module, the knowledge storage module and the knowledge operation and maintenance module.
Drawings
FIG. 1 is an overall frame diagram of the present invention;
FIG. 2 is a flow chart of the present invention.
Detailed Description
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 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.
Referring to fig. 1-2, a knowledge-graph-based tax knowledge base system, a data module, a knowledge module and a test evaluation module, the knowledge module includes: the system comprises a knowledge acquisition module, a knowledge fusion module, a knowledge calculation module, a knowledge representation module, a knowledge construction module, a knowledge storage module and a knowledge operation and maintenance module;
the data module specifically comprises:
a) the method is used as a knowledge acquisition source and comprises structured data, semi-structured data and unstructured data, wherein the final structure of the data is entity-attribute-value;
b) structured data, related data in a relational database;
i. the tax completion certification is printed;
attributes containing upstream outstanding traffic;
value real name authentication;
c) the semi-structured data is log-related, third-party interface data and other data sources;
i. the semi-structured data may only comprise entity-attribute, entity-value, attribute-value;
ii, data completion is required to be carried out through data integration, a third-party interface, algorithm prediction and other modes;
the unstructured data needs to be completed in ways of entity extraction, attribute extraction, value prediction, value association and the like;
entity extraction, attribute extraction will be introduced in knowledge acquisition.
The knowledge acquisition module specifically comprises:
a) the knowledge acquisition is used as a key component in the whole engine and mainly completes the functions of information extraction, entity identification, relationship extraction, attribute extraction and the like;
b) the first step of tax concept extraction and knowledge base construction is that how to automatically extract information from heterogeneous data into candidate knowledge units;
c) extracting an entity by adopting a Bi.LSTM.CRE model;
i. data input, namely tax linguistic data, crawling policy, tax report, data and books;
ii, outputting the result of the tax business, the tax policy and the tax rule;
d) relationship extraction, through entity extraction, some tax business entities are obtained, but these entities
The entities are discrete, and in order to obtain semantic information, the entities can be connected together only by extracting the relationships among the entities;
i. the relation extraction adopts four modes of models to carry out Ensemble;
ii, supervised learning method, for known relationship, model is Bi-LSTM;
1) the input is entity corpora;
2) the output is the relationship;
the semi-supervised learning method comprises the steps of adopting BootStraping to extract the relation, setting a plurality of seed corpora and finding out the corresponding relation;
1) business, tax completion certification printing;
2) attribute-contains upstream outstanding traffic;
3) value-real name authentication;
4) find some similar relation data, this seed is equivalent to the template;
adopting syntactic analysis and dependency analysis to obtain a structural analysis result of the sentence, and extracting through the relation phrase;
v. rule extraction method:
1) setting a rule word (relation word), for example, if necessary, completing, and authenticating a real name;
2) and detecting the rule words, performing entity extraction, and extracting the relation obtained by the corresponding service.
The knowledge fusion module specifically comprises: the knowledge fusion is a technology for fusing a plurality of related knowledge maps and knowledge bases together.
The knowledge calculation module specifically comprises:
a) the main function of knowledge calculation is knowledge reasoning, and how one knowledge infers another knowledge, a reasoning mechanism;
b) knowledge statistics, which is used for reasoning calculation through a statistical inference mode;
c) graph computation.
The knowledge representation module is specifically as follows:
a) a symbolic representation RDF triple;
subject-subject;
predicate-predicate;
object-object;
examples iv
1) Subject is tax proof printing;
2) setting a starting date;
3) object is start date;
b) VSM representation
i. A representation method based on a space vector model;
modeling the entities into column vectors and relationships into matrixes, and determining the relationships between the entities by performing pictographic transformation on the entity vectors and the shutdown matrixes and finally performing clicking operation on the entities and the tail entities;
a typical approach includes a-tasse model based on the trigonometric rule and norm principle of vectors, a tranh, transr, and transd model that deal with multivariate relations through hyperplane transformation or linear transformation, a-trassparse-model that resolves heterogeneous multivariate relations by adding a sparsity parameter vector.
The knowledge construction module specifically comprises:
a) generating a conceptual top-bottom relationship;
b) attribute identification;
c) rule modeling;
d) spatio-temporal modeling.
The knowledge storage module specifically comprises:
a) knowledge storage, namely storing the knowledge triples and the vectorized representation;
b) storing the triples in a relational database based on the table structure;
c) based on a graph structure, a graph database is based on a directed graph, the theoretical basis of the graph database is graph theory, and nodes, edges and attributes are core concepts of the graph database.
The knowledge operation and maintenance module specifically comprises:
a) knowledge collaboration;
b) knowledge validation;
c) correction of knowledge.
The test evaluation name module specifically comprises:
a) accuracy evaluation, wherein each time the model is on line, the accuracy rate is obtained, and an evaluation report of test run is referred to;
b) coverage rate evaluation, namely periodically updating the triggering times and the unanswered ratio of all knowledge points in the knowledge base;
c) and performance evaluation, namely periodically evaluating the response and load performance of the current knowledge base.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The utility model provides a tax knowledge base system based on knowledge map, data module, knowledge module and test evaluation module which characterized in that: the knowledge module includes: the system comprises a knowledge acquisition module, a knowledge fusion module, a knowledge calculation module, a knowledge representation module, a knowledge construction module, a knowledge storage module and a knowledge operation and maintenance module;
the data module specifically comprises:
a) the method is used as a knowledge acquisition source and comprises structured data, semi-structured data and unstructured data, wherein the final structure of the data is entity-attribute-value;
b) structured data, related data in a relational database;
i. the tax completion certification is printed;
attributes containing upstream outstanding traffic;
value real name authentication;
c) the semi-structured data is log-related, third-party interface data and other data sources;
i. the semi-structured data may only comprise entity-attribute, entity-value, attribute-value;
ii, data completion is required to be carried out through data integration, a third-party interface, algorithm prediction and other modes;
the unstructured data needs to be completed in ways of entity extraction, attribute extraction, value prediction, value association and the like;
entity extraction, attribute extraction will be introduced in knowledge acquisition.
2. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge acquisition module specifically comprises:
a) the knowledge acquisition is used as a key component in the whole engine and mainly completes the functions of information extraction, entity identification, relationship extraction, attribute extraction and the like;
b) the first step of tax concept extraction and knowledge base construction is that how to automatically extract information from heterogeneous data into candidate knowledge units;
c) extracting an entity by adopting a Bi.LSTM.CRE model;
i. data input, namely tax linguistic data, crawling policy, tax report, data and books;
ii, outputting the result of the tax business, the tax policy and the tax rule;
d) relationship extraction, through entity extraction, some tax business entities are obtained, but these entities
The entities are discrete, and in order to obtain semantic information, the entities can be connected together only by extracting the relationships among the entities;
i. the relation extraction adopts four modes of models to carry out Ensemble;
ii, supervised learning method, for known relationship, model is Bi-LSTM;
1) the input is entity corpora;
2) the output is the relationship;
the semi-supervised learning method comprises the steps of adopting BootStraping to extract the relation, setting a plurality of seed corpora and finding out the corresponding relation;
1) business, tax completion certification printing;
2) attribute-contains upstream outstanding traffic;
3) value-real name authentication;
4) find some similar relation data, this seed is equivalent to the template;
adopting syntactic analysis and dependency analysis to obtain a structural analysis result of the sentence, and extracting through the relation phrase;
v. rule extraction method:
1) setting a rule word (relation word), for example, if necessary, completing, and authenticating a real name;
2) and detecting the rule words, performing entity extraction, and extracting the relation obtained by the corresponding service.
3. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge fusion module specifically comprises: the knowledge fusion is a technology for fusing a plurality of related knowledge maps and knowledge bases together.
4. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge calculation module specifically comprises:
a) the main function of knowledge calculation is knowledge reasoning, and how one knowledge infers another knowledge, a reasoning mechanism;
b) knowledge statistics, which is used for reasoning calculation through a statistical inference mode;
c) graph computation.
5. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge representation module is specifically as follows:
a) a symbolic representation RDF triple;
subject-subject;
predicate-predicate;
object-object;
examples iv
1) Subject is tax proof printing;
2) setting a starting date;
3) object is start date;
b) VSM representation
i. A representation method based on a space vector model;
modeling the entities into column vectors and relationships into matrixes, and determining the relationships between the entities by performing pictographic transformation on the entity vectors and the shutdown matrixes and finally performing clicking operation on the entities and the tail entities;
a typical approach includes a-tasse model based on the trigonometric rule and norm principle of vectors, a tranh, transr, and transd model that deal with multivariate relations through hyperplane transformation or linear transformation, a-trassparse-model that resolves heterogeneous multivariate relations by adding a sparsity parameter vector.
6. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge construction module specifically comprises:
a) generating a conceptual top-bottom relationship;
b) attribute identification;
c) rule modeling;
d) spatio-temporal modeling.
7. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge storage module specifically comprises:
a) knowledge storage, namely storing the knowledge triples and the vectorized representation;
b) storing the triples in a relational database based on the table structure;
c) based on a graph structure, a graph database is based on a directed graph, the theoretical basis of the graph database is graph theory, and nodes, edges and attributes are core concepts of the graph database.
8. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the knowledge operation and maintenance module specifically comprises:
a) knowledge collaboration;
b) knowledge validation;
c) correction of knowledge.
9. The knowledge-graph-based tax knowledge base system according to claim 1, wherein: the test evaluation name module specifically comprises:
a) accuracy evaluation, wherein each time the model is on line, the accuracy rate is obtained, and an evaluation report of test run is referred to;
b) coverage rate evaluation, namely periodically updating the triggering times and the unanswered ratio of all knowledge points in the knowledge base;
c) and performance evaluation, namely periodically evaluating the response and load performance of the current knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011592779.2A CN112613611A (en) | 2020-12-29 | 2020-12-29 | Tax knowledge base system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011592779.2A CN112613611A (en) | 2020-12-29 | 2020-12-29 | Tax knowledge base system based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112613611A true CN112613611A (en) | 2021-04-06 |
Family
ID=75248807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011592779.2A Pending CN112613611A (en) | 2020-12-29 | 2020-12-29 | Tax knowledge base system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613611A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139068A (en) * | 2021-05-10 | 2021-07-20 | 内蒙古工业大学 | Knowledge graph construction method and device, electronic equipment and storage medium |
| CN113849659A (en) * | 2021-08-18 | 2021-12-28 | 国网天津市电力公司 | Construction method of audit system time sequence knowledge graph |
| CN114358287A (en) * | 2021-12-01 | 2022-04-15 | 中国人民解放军国防科技大学 | Bulk transportation demand decomposition method based on atlas clustering |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843897A (en) * | 2016-03-23 | 2016-08-10 | 青岛海尔软件有限公司 | Vertical domain-oriented intelligent question and answer system |
| US10042836B1 (en) * | 2012-04-30 | 2018-08-07 | Intuit Inc. | Semantic knowledge base for tax preparation |
| CN111428053A (en) * | 2020-03-30 | 2020-07-17 | 西安交通大学 | Tax field knowledge graph construction method |
| CN111488465A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Knowledge graph construction method and related device |
| CN111914094A (en) * | 2019-05-10 | 2020-11-10 | 中国人民大学 | Knowledge graph representation learning method based on ternary interaction |
-
2020
- 2020-12-29 CN CN202011592779.2A patent/CN112613611A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10042836B1 (en) * | 2012-04-30 | 2018-08-07 | Intuit Inc. | Semantic knowledge base for tax preparation |
| CN105843897A (en) * | 2016-03-23 | 2016-08-10 | 青岛海尔软件有限公司 | Vertical domain-oriented intelligent question and answer system |
| CN111914094A (en) * | 2019-05-10 | 2020-11-10 | 中国人民大学 | Knowledge graph representation learning method based on ternary interaction |
| CN111428053A (en) * | 2020-03-30 | 2020-07-17 | 西安交通大学 | Tax field knowledge graph construction method |
| CN111488465A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Knowledge graph construction method and related device |
Non-Patent Citations (2)
| Title |
|---|
| WANG, S.等: "Geographic Knowledge Graph (GeoKG): A Formalized Geographic Knowledge Representation", 《ISPRS INT. J. GEO-INF.》, vol. 8, no. 4, 8 April 2019 (2019-04-08), pages 1 - 24 * |
| 蒋秉川等: "多源异构数据的大规模地理知识图谱构建", 《测绘学报》, vol. 47, no. 8, 15 August 2018 (2018-08-15), pages 1051 - 1061 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139068A (en) * | 2021-05-10 | 2021-07-20 | 内蒙古工业大学 | Knowledge graph construction method and device, electronic equipment and storage medium |
| CN113139068B (en) * | 2021-05-10 | 2023-05-09 | 内蒙古工业大学 | Knowledge graph construction method and device, electronic equipment and storage medium |
| CN113849659A (en) * | 2021-08-18 | 2021-12-28 | 国网天津市电力公司 | Construction method of audit system time sequence knowledge graph |
| CN114358287A (en) * | 2021-12-01 | 2022-04-15 | 中国人民解放军国防科技大学 | Bulk transportation demand decomposition method based on atlas clustering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021103492A1 (en) | Risk prediction method and system for business operations | |
| WO2021196520A1 (en) | Tax field-oriented knowledge map construction method and system | |
| CN112559766B (en) | Legal knowledge map construction system | |
| CN112613611A (en) | Tax knowledge base system based on knowledge graph | |
| CN112612902A (en) | Knowledge graph construction method and device for power grid main device | |
| CN111967761B (en) | Knowledge graph-based monitoring and early warning method and device and electronic equipment | |
| CN103440287B (en) | A kind of Web question and answer searching system based on product information structure | |
| CN107679221B (en) | Time-space data acquisition and service combination scheme generation method for disaster reduction task | |
| Jabbar et al. | A methodology of real-time data fusion for localized big data analytics | |
| CN111078780A (en) | AI optimization data management method | |
| CN112036842B (en) | Intelligent matching device for scientific and technological service | |
| CN106407216A (en) | Clue tracing audition system developed on basis of semantic net construction path and construction method of clue tracing audition system | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| CN111061679A (en) | Method and system for rapid configuration of technological innovation policy based on rete and drools rules | |
| Anand et al. | Uncertainty analysis in ontology-based knowledge representation | |
| CN115827797A (en) | Environmental data analysis and integration method and system based on big data | |
| Zhang et al. | A knowledge graph system for the maintenance of coal mine equipment | |
| CN114792145A (en) | Standard digital management maintenance system and method based on knowledge graph | |
| Tang et al. | Automatic schema construction of electrical graph data platform based on multi-source relational data models | |
| CN116842195A (en) | Knowledge graph and large model based automatic generation report generation method | |
| Shi et al. | Human resources balanced allocation method based on deep learning algorithm | |
| CN115827885A (en) | Operation and maintenance knowledge graph construction method and device and electronic equipment | |
| Yerashenia et al. | Semantic data pre-processing for machine learning based bankruptcy prediction computational model | |
| Xu et al. | Research on intelligent campus and visual teaching system based on Internet of things | |
| Zhao | Construction of Multimedia‐Assisted English Teaching Mode in Big Data Network Environment |
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 |