CN111460119A - Intelligent question and answer method and system for economic knowledge and intelligent equipment - Google Patents
Intelligent question and answer method and system for economic knowledge and intelligent equipment Download PDFInfo
- Publication number
- CN111460119A CN111460119A CN202010230062.7A CN202010230062A CN111460119A CN 111460119 A CN111460119 A CN 111460119A CN 202010230062 A CN202010230062 A CN 202010230062A CN 111460119 A CN111460119 A CN 111460119A
- Authority
- CN
- China
- Prior art keywords
- question
- economic
- information
- index
- data processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 description 12
- 230000004044 response Effects 0.000 description 6
- 102100038367 Gremlin-1 Human genes 0.000 description 3
- 101001032872 Homo sapiens Gremlin-1 Proteins 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 235000006732 Torreya nucifera Nutrition 0.000 description 1
- 244000111306 Torreya nucifera Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides an economic knowledge intelligent question-answering method, a system and intelligent equipment, wherein the method comprises the following steps: receiving question information input by a user; matching a question template corresponding to the question information, wherein the question template is provided with a question type identifier; analyzing the question information through the question template to obtain an analysis result, wherein the analysis result comprises the question type identifier and a keyword in the question information; calling an alternative database according to the question type identifier to generate answer information corresponding to the keyword, wherein the alternative database comprises an economic knowledge graph; and outputting the answer information. According to the method and the device, the answer information is generated by calling the data in the economic knowledge map, the advantage of strong data correlation in the economic knowledge map is utilized, the answer accuracy and comprehensiveness of the economic knowledge question information are improved, and the economic knowledge acquisition efficiency is improved.
Description
Technical Field
The application relates to the technical field of economics, in particular to an economic knowledge intelligent question answering method, system and intelligent equipment.
Background
The economic data retrieval method is an important way for people to acquire economic knowledge. The economic data retrieval method is usually based on an economic index database, index data corresponding to economic indexes are retrieved by using keywords, and important basis is provided for people to obtain economic knowledge and further solve the problem of economics. However, the economic index database can only store the index data of each economic index independently, so that the economic knowledge obtained by people according to the independent index data is scattered, and the economic indexes related to the economic problem are usually complicated and complicated, so that the economic problem is still solved by depending on people to retrieve each index data respectively and then perform data analysis on the retrieved index data, which causes the workload of people for obtaining economic knowledge to be large, and further causes the efficiency of data analysis to be low, which is not beneficial to the solution of the economic problem.
Disclosure of Invention
The application provides an economic knowledge intelligent question-answering method, system and intelligent equipment, which aim to solve the problem that the economic knowledge retrieved by an economic data retrieval method is weak in relevance.
In a first aspect, the present application provides an intelligent question-answering method for economic knowledge, comprising:
receiving question information input by a user;
matching a question template corresponding to the question information, wherein the question template is provided with a question type identifier;
analyzing the question information through the question template to obtain an analysis result, wherein the analysis result comprises the question type identifier and a keyword in the question information;
calling an alternative database according to the question type identifier to generate answer information corresponding to the keyword, wherein the alternative database comprises an economic knowledge graph;
and outputting the answer information.
In a second aspect, the present application provides an economic knowledge intelligent question-answering system, comprising:
the user input module is used for receiving the question information input by the user;
the semantic analysis module is used for matching a problem template corresponding to the problem information and analyzing the problem information according to the problem template to obtain an analysis result, wherein the analysis result comprises a problem type identifier and an analysis result of a keyword;
the data processing module is used for calling an alternative database to generate answer information corresponding to the key words, and the alternative database comprises an economic knowledge map;
and the output module is used for outputting the answer information.
In a third aspect, the present application provides a smart device, comprising:
a display screen for displaying the answer information;
the user input component is used for inputting the economic knowledge problem information by a user;
a processor configured to receive user-entered economic knowledge question information and display the answer information on the display screen.
The economic knowledge intelligent question-answering method, the economic knowledge intelligent question-answering system and the intelligent equipment have the advantages that:
according to the method and the device, the question information input by the user is analyzed through the preset question template to obtain the question type identifier and the key word of the question information, the alternative database is called according to the question type identifier to generate and output the answer information corresponding to the key word, and the answer accuracy and the comprehensiveness of the economic knowledge type question information are improved by utilizing the advantage of strong data correlation in the economic knowledge map.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a schematic flow chart of an intelligent question-answering method for economic knowledge according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a question answering interface provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of an economic knowledge intelligent question-answering system according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all 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 application.
In a first aspect, the present embodiment provides an intelligent economic knowledge question-answering method, referring to fig. 1, which is a schematic flow chart of the intelligent economic knowledge question-answering method provided in the embodiment of the present application, and as shown in fig. 1, the intelligent economic knowledge question-answering method provided in the embodiment of the present application includes the following steps:
step S110: question information input by a user is received.
The problem information input by the user can be voice information or text information, and if the problem information input by the user is the voice information, the voice information can be converted into the text information through a voice recognition technology; and if the question information input by the user is text information, acquiring the text information.
Some Chinese-character and foreign-language words may exist in the problem information input by the user, such as "kaya" and the like, and the Chinese-character and foreign-language words interfere with the identification of the keywords, so that the Chinese-character and foreign-language words in the text information are removed, and the identification accuracy of the keywords is improved. The method comprises the steps of matching characters in text information with a preset tone word library through presetting the tone word library, identifying tone words in the text information, and removing the tone words from the text information.
Step S120: and matching a question template corresponding to the question information, wherein the question template is provided with a question type identifier.
The keyword and the question type identifier in the question information may be obtained by performing semantic parsing on the question information obtained in step S110, the semantic parsing may be based on a template matching method of AIM L, a question template may be preset, the keyword in the question information may be captured using the question template, and the question type identifier may be obtained.
The problem template in the AIM L format provided by the embodiment is as follows:
<category>
< Pattern > how many </pattern > in year >
<template>1％exact_value％<star index＝"3"/>％<star index＝"1"/>％<star index＝"2"/>
</template>
</category>
In the above problem template, the content between < category > and </category > is the content of the problem template, and the content between < pattern > </pattern > is the format of the text information matched with the problem template, wherein, is the fuzzy matching character, which is used to perform fuzzy matching, the problem information that the problem template can be matched with is as follows: what is the total value of the whole market production in the Qingdao city of 2012?
Between < template > and </template > are the output contents of the question template, each separated by "%", which from left to right can be the 0 th element, the 1 st element, the 2 nd element … … nth element.
The problem information is divided into a plurality of problem types based on AIM L, wherein the problem types may include a major problem type and a minor problem type, the major problem type may include an index search type, an index relationship search type, an index comparison type, a general problem type, and a professional problem type, the minor problem type is a subdivided type of the major problem type, and for example, the index search type may be subdivided into an index attribute search type and an index relationship search type, wherein the index attribute is an attribute of an economic index, such as an index value, a brief introduction, a short form, and the like, and correspondingly, the index attribute search type may specifically be an index value search type, a brief introduction search type, a search type for short form, and the like.
In the output content corresponding to the question template, the 0 th element and the 1 st element can be both question type identifiers for distinguishing the question types, wherein the 0 th element is a large-class identifier for distinguishing a plurality of large-class question types, for example, the index search type can be represented by "1", the index relation search type can be represented by "2", the index comparison type can be represented by "3", the general question type can be represented by "4", and the professional question type can be represented by "5".
In the output content corresponding to the question template, the 1 st element is a subclass identifier for distinguishing a plurality of subclass question types, and for example, "exact _ value" may be used to indicate the index value search type.
In the output content corresponding to the problem template, < star index ═ n "/> indicates the data pointed to by the nth" × ", and for example, in the problem template, the values of n are 3, 1, and 2, respectively, and what is the total production value for the whole market of the Qingdao city in 2012? "the data corresponding to the elements after the 1 st element are: the city produces total value, 2012, Qingdao. Of course, the values of n can also adopt other orders, such as 1, 2, 3 or 3, 2, 1, etc.
The problem template corresponding to the problem information can be matched by a fuzzy matching method, and the analysis result is output by using the problem template. The resolution result includes a question type identifier and a keyword in the question information, and may be in the form of a list, such as [ 'major class identifier', 'minor class identifier', 'keyword', …, 'keyword' ].
For example, what is the total value of the city production for the question information "2012 Qingdao City? ", it can be matched to the question template in the above example, and the analysis result is output through the question template as follows: [ '1', 'exact _ value', 'total production from city', '2012', 'Qingdao city' ].
Step S130: and calling an alternative database according to the question type identifier to generate answer information corresponding to the keyword.
The problem information of different problem types can be modularly processed through a plurality of data processing modules, and the data processing modules are preset algorithm modules, such as an index searching module, an index relation searching module, an index comparison module, a professional problem answering module and a general problem answering module.
And matching the corresponding data processing module according to the question type identifier in the analysis result to answer the question information. For example, according to the fact that the large-class identifier is 1, the matching index searching module carries out solution; according to the fact that the large-class identifier is 2, the matching index relation searching module carries out answering; according to the fact that the class identifier is 3, the matching index comparison module answers; matching a professional question answering module to answer according to the fact that the category identifier is 4; and according to the 5 of the large-class identifier, the matching general question answering module answers.
And each data processing module determines the alternative database according to the large-class identifier. For example, the index searching module selects the economic knowledge graph as an alternative database according to the fact that the large-class identifier is 1; the index relation module selects the economic knowledge graph as an alternative database according to the major identifier of 2; the index comparison module selects an economic knowledge graph as an alternative database according to the major identifier of 3; the professional question answering module selects an algorithm library and an economic knowledge map as alternative databases according to the large-class identifier of 4; and the general question answering module selects an answer base as an alternative database according to the 5-class identifier.
All data of the knowledge graph can be stored on a Gremlin-Server, each item of data is provided with a UR L (Uniform Resource L adapter, Uniform Resource locator), data under UR L can be extracted through a data retrieval statement, and the obtained data is in a json string form, wherein the data retrieval statement comprises 3 types of full-attribute retrieval, direct relation retrieval and relational link retrieval.
The data retrieval statement for full-attribute retrieval provided by this embodiment is as follows:
weburl_all＝janusgraph_url+':8182/？gremlin＝g.V().has("Index_Name","'+name+'").valueMap()'
wherein the janussgraph _ url is the Server address of the Gremlin-Server, and the name is the index name.
The data retrieval statement for direct relationship retrieval provided by this embodiment is as follows:
weburl_osrelation＝janusgraph_url+':8182/？gremlin＝g.V().has("Index_Name","'+name+'").bothE().otherV().path().by("Index_Name").by("Edge_Name")'
wherein, janusgraph _ url is the Server address of Gremlin-Server, and name is the index name.
The data retrieval statement for the relational link retrieval provided by this embodiment is as follows:
weburl_relation＝janusgraph_url+':8182/？gremlin＝g.V().has("Index_Name","'+name1+'")repeat(bothE().otherV().simplePath()).until(has("Index_Name","'+name2+'")).path().by("Index_Name").by("Edge_Name")'
wherein, janusgraph _ url is the Server address of Gremlin-Server, and name1 and name2 are index names.
The index searching module, the index relation searching module, the index comparison module and the professional question answering module can retrieve data corresponding to the knowledge map by using the data retrieval sentences, answer the question information according to the retrieved data, the general question answering module answers the question information according to the answering database, and in addition, the professional question answering module answers the question information according to the algorithm database besides the knowledge map.
After each data processing module determines the alternative database, the process of solving the problem information according to the alternative database is as follows:
(1) index searching module
The index search module has a category identifier of 1, and the module functions include full attribute search, specific attribute search and associated index search. The full-attribute search refers to outputting attribute values of all index attributes of a certain economic index, and can be matched with problem information in a format such as 'all information of total production value in whole market' and the like for processing; the designated attribute search refers to outputting the attribute value of the designated index attribute of a certain economic index, and can be matched with the problem information of formats such as 'what the index introduction of the total production value of the whole market' and the like for processing; the related index search refers to outputting other economic indexes related to the economic index, giving the relation between the current economic index and the related economic index, and processing the problem information in a matching format, such as 'what the economic index directly related to the total production value of the whole market is', so that a user can know the related information of the economic index.
The index attributes include: index name, English name, synonym, data source, related formula, index brief introduction, evaluation item, data unit, remark, area list covered by the index, year covered by the index and area data.
When the full-attribute search function and the designated attribute search function in the index search module are used, firstly, executing a full-attribute retrieval statement, extracting a json string containing index attributes corresponding to the keywords from the economic knowledge graph, then extracting attribute values in the json string, and finally placing the attribute values in an output dictionary, wherein the output dictionary is output information of the data processing module; when the relevance index searching function is used, firstly, a direct relation retrieval statement is executed, all economic indexes directly related to the economic indexes corresponding to the keywords and a json string formed by corresponding relations are extracted from the economic knowledge graph, and then the relevance indexes and the corresponding relations in the json string are placed in an output dictionary.
(2) Index relation searching module
The index relation searching module has a class identifier of 2, and has the function of providing a relation link which is formed by taking two specified economic indexes as end points and taking all the relevant indexes and the relevant relations between the two indexes as paths, wherein if the economic index A, the economic index C and the economic index D form an A-C-D link, the economic index B, the economic indexes D and E form a D-E-B link, and the '-' represents the relation between the two economic indexes, the relation link provided when the relation between the economic index A and the economic index B is searched is A-C-D-E-B, so that a user can know the related information between the economic indexes.
The index relation searching module can process the problem information in a matching format, such as 'the relation between the total production value of the whole market and the social employment number'. When the index relation search module is used, firstly, a relation link retrieval statement is executed, a json string of relation link information corresponding to a keyword is extracted from the economic knowledge graph, then the relation link information in the json string is extracted, and finally the relation link information is placed in an output dictionary.
(3) Index comparison module
The index comparison module has the function of giving the numerical values of two indexes needing to be compared and giving the difference value of the two indexes, so that a user can know the difference and the increasing and decreasing trend between the indexes. The question is in the form of 'the total production value of the whole city in Qingdao City in 2010 and 2011 data comparison' and the like.
When the index relation search module is used, firstly, a full-attribute retrieval statement is executed to obtain a json string containing all attribute information of two economic indexes corresponding to a keyword, secondly, data A and data B corresponding to the keyword are extracted from the json string, the two data are placed into an output dictionary, then the two data are subjected to subtraction, and then the difference value is placed into the output dictionary.
(4) Professional question answering module
The function of the professional question answering module is to pertinently solve professional economic questions proposed by users and provide answers with reference values. The module designs an algorithm adaptive to each economic problem in a targeted manner, the algorithm is stored in an algorithm library, and the economic problems proposed by users can be solved professionally by calling the algorithm library. The professional question answering module can be matched with the format for processing the question information such as 'what suggestions are made in the aspect of improving the general public budget income of the Qingdao city', 'how the whole situation of new and old kinetic energy conversion projects of the Qingdao city in 2019' and 'large debt repayment pressure of the Qingdao city government' and the like.
When the professional question answering module is used, in order to meet individual requirements of different questions, an algorithm library can be matched according to keywords in the analysis result, wherein the algorithm library can be arranged in the professional question answering module or can be independently used as an alternative database for the professional question answering module to call.
The method comprises the steps that retrieval sentences are preset in each algorithm library, data in the form of json strings of economic indexes are obtained after the retrieval sentences are retrieved in the algorithm libraries and the knowledge graph spectrums, then information is extracted from the json strings according to problem information, then corresponding answers are obtained through reasoning calculation according to the extracted information by using algorithms in the algorithm libraries, and finally the answers are placed in an output dictionary.
(5) General question answering module
The universal question answering module has the functions of chatting with users and providing answers to questions related to statistical data, can meet various requirements of the users, and improves humanization. The general question answering module can match the question information in the format of 'how many indexes there are together', 'how much the weather is today' and 'what your name is' and the like.
When the general question answering module is used, a question answering template corresponding to the keyword can be searched in an answering library according to the analysis result of the question information, and then preset answers of the question answering template are placed in an output dictionary, wherein the answering library can be arranged in the general question answering module or can be independently used as an alternative database for the general question answering module to call.
Step S140: and outputting the answer information.
After the output dictionary of the data processing module is obtained according to step S130, a question reply interface containing the answer information is generated according to the content of the output dictionary. In order to facilitate the user to know the relevant knowledge of the question information more clearly, the question answering interface can display the answer information and the relevant information of the question information in a visual form, for example, the answer information and the relevant information of the question information can be displayed in one or more forms of comprehensive map network, table, text and the like.
Referring to fig. 2, a schematic diagram of a question answering interface shown in the embodiment of the present application is shown, and as shown in fig. 2, a left page of the question answering interface shows question information "how many total production values are for the whole city of the 2012 Qingdao city? "the content of the answer information includes: the Qingdao city of 2012 GDP 7302.1 billion Yuan. The related information of the question information is also shown below the answer information, including the related information such as brief introduction, evaluation items and the like; the middle page of the question answering interface shows an economic knowledge map with a keyword 'total production value in the question information' as a core, and the relationship among all economic indexes can be shown; the right page of the question reply interface displays relevant data of keywords 'Qingdao city' and 'total production value of city' in the question information, such as a calendar year GDP broken line graph, a GDP calculation formula, and the origin and remark information of the data, wherein the calendar year GDP broken line graph can be used for a user to selectively display GDP of the Qingdao city and GDP of subordinate administrative units of the Qingdao city. Therefore, the embodiment can display the answer information, and can analyze the relevant information of the answer information according to the keywords in the question information, so that the user can obtain richer economic knowledge.
In a second aspect, corresponding to the above-mentioned economic knowledge intelligent question-answering method, the present embodiment further provides an economic knowledge intelligent question-answering system, as shown in fig. 3, which includes a user input module 100, a semantic parsing module 200, an index searching module 301, an index relation searching module 302, an index comparing module 303, a professional question-answering module 304, a general question-answering module 305, and an output module 400.
The user input module 100 may collect the question information using two input modes, a voice input mode and a text information input mode, and accordingly, the user input module 100 is provided with a voice information input module and a text information input module. In the voice input mode, the voice input module can collect voice information input by a user and convert the voice information into text information through a voice recognition technology; in the text input mode, the text information input module may collect text information input by a user. The user input module 100 is further provided with a preprocessing module, which can remove the semantic words in the text information output by the voice information input module and the text information input module, and send the removed text information to the semantic analysis module 200.
The semantic analysis module 200 obtains a problem template through fuzzy matching, analyzes the text information by using the problem template to obtain an analysis result containing a problem type identifier and a keyword, and sends the analysis result to a corresponding data processing module according to the problem type identifier.
The data processing module, such as the index searching module 301, the index relation searching module 302, the index comparing module 303, the professional question answering module 304 and the general question answering module 305, calls the alternative database according to the question type identifier to generate answer information corresponding to the keyword, and sends the answer information to the output module 400; further, the data processing module may also call the alternative database according to the keyword to generate relevant information of the answer information, and send the relevant information and the answer information to the output module 400.
The output module 400 may generate a question response interface according to the response information, and display the response information to the user, or generate a visual question response interface according to the response information and the related information, and display the response information and the related information to the user.
In a third aspect, the present embodiment further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the method for intelligently asking and answering economic knowledge according to the first aspect is implemented.
In a fourth aspect, the present embodiment further provides an intelligent device, which may be a device including a display screen, a user input component, and a processor, such as an intelligent communication terminal, an intelligent television, a computer, and the like. The display screen can be used for displaying the answer information; the user input assembly can comprise one or two of a voice input assembly and a text input assembly, the voice input assembly can be a pickup device, the text input assembly can be a keyboard, a touch screen and other devices, and the user input assembly can be used for inputting economic knowledge problem information by a user; a processor configured to receive the economic knowledge question information input by the user and to display the answer information on the display screen, wherein the method for the processor to derive the answer information is as described in the first aspect.
The intelligent device can be provided with the economic knowledge intelligent question-answering system of the second aspect to realize the above functions.
According to the embodiment, the question information input by the user is analyzed through the preset question template to obtain the question type identifier and the key word of the question information, the alternative database is called according to the question type identifier to generate and output the answer information corresponding to the key word, the advantage of strong data correlation in the economic knowledge map is utilized, the answer accuracy and comprehensiveness of the economic knowledge question information are improved, and the economic knowledge acquisition efficiency is improved. The data processing module is arranged, different data processing modules are selected according to the problem type identifiers to analyze the problem information, various types of problem information can be answered comprehensively and accurately, an important technical means is provided for people to master more and more comprehensive economic knowledge, and an important reference basis is provided for government departments to solve economic problems and make economic decisions.
Since the above embodiments are all described by referring to and combining with other embodiments, the same portions are provided between different embodiments, and the same and similar portions between the various embodiments in this specification may be referred to each other. And will not be described in detail herein.
It is noted that, in this specification, relational terms such as "first" and "second," and the like, are 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 circuit structure, 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 circuit structure, article, or apparatus. Without further limitation, the presence of an element identified by the phrase "comprising an … …" does not exclude the presence of other like elements in a circuit structure, article or device comprising the element.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
The above-described embodiments of the present application do not limit the scope of the present application.
Claims (10)
1. An intelligent economic knowledge question-answering method is characterized by comprising the following steps:
receiving question information input by a user;
matching a question template corresponding to the question information, wherein the question template is provided with a question type identifier;
analyzing the question information through the question template to obtain an analysis result, wherein the analysis result comprises the question type identifier and a keyword in the question information;
calling an alternative database according to the question type identifier to generate answer information corresponding to the keyword, wherein the alternative database comprises an economic knowledge graph;
and outputting the answer information.
2. The economic knowledge intelligent question answering method according to claim 1, wherein the calling of an alternative database according to the question type identifier to generate answer information corresponding to the keyword comprises:
matching a data processing module corresponding to the question type identifier;
and obtaining answer information corresponding to the keyword from an alternative database corresponding to the data processing module through the data processing module.
3. The economic knowledge intelligent question answering method according to claim 2, wherein the obtaining, by the data processing module, answer information corresponding to the keyword from an alternative database corresponding to the data processing module comprises:
detecting a search rule corresponding to the problem type identifier according to the index search module serving as the data processing module, wherein the search rule comprises index attribute search and associated index search;
extracting economic indexes matched with the keywords from an economic knowledge graph according to the corresponding searching of the problem type identifiers and the index attributes, wherein the entity of the economic knowledge graph comprises the economic indexes, the edges of the economic knowledge graph comprise the relations among the economic indexes, and the entity is provided with the index attributes;
generating answer information according to the index attribute of the economic index;
extracting economic indexes associated with the economic indexes matched with the keywords from the economic knowledge graph according to the correspondence between the question type identifiers and the associated index search;
generating answer information according to the associated economic indicators.
4. The economic knowledge intelligent question answering method according to claim 3, wherein the obtaining, by the data processing module, answer information corresponding to the keyword from an alternative database corresponding to the data processing module comprises:
acquiring two economic indexes corresponding to the keywords from the economic knowledge graph according to the index relation searching module serving as the data processing module;
extracting a relation link between the two economic indexes from the economic knowledge graph;
and generating answer information according to the relationship link.
5. The economic knowledge intelligent question answering method according to claim 3, wherein the obtaining, by the data processing module, answer information corresponding to the keyword from an alternative database corresponding to the data processing module comprises:
acquiring two economic indexes corresponding to the keywords from the economic knowledge graph according to the condition that the data processing module is an index comparison module;
extracting data corresponding to the two economic indexes from the economic knowledge graph;
calculating a difference value between the data of the two economic indexes;
and generating answer information according to the values of the two index attributes and the difference value.
6. The economic knowledge intelligent question answering method according to claim 3, wherein the obtaining, by the data processing module, answer information corresponding to the keyword from an alternative database corresponding to the data processing module comprises:
acquiring a preset algorithm corresponding to the keyword from an algorithm library according to the fact that the data processing module is a professional question answering module, wherein the alternative database comprises the algorithm library;
extracting data corresponding to economic indexes from the economic knowledge graph according to the preset algorithm;
and generating answer information according to the preset algorithm and the data corresponding to the economic index.
7. The economic knowledge intelligent question answering method according to claim 3, wherein the obtaining, by the data processing module, answer information corresponding to the keyword from an alternative database corresponding to the data processing module comprises:
acquiring a question and answer template corresponding to the keyword from an answer library according to the fact that the data processing module is a general question and answer module, wherein the alternative database comprises the answer library;
and generating answer information according to the preset answers of the question-answer template.
8. The intelligent economic knowledge question-answering method according to claim 1, wherein the outputting the answer information comprises: and outputting the answer information in a visual form, wherein the visual form comprises any one or more of a map network, a table and characters.
9. An economic knowledge intelligent question-answering system, comprising:
the user input module is used for receiving the question information input by the user;
the semantic analysis module is used for matching a problem template corresponding to the problem information and analyzing the problem information according to the problem template to obtain an analysis result, wherein the analysis result comprises a problem type identifier and an analysis result of a keyword;
the data processing module is used for calling an alternative database to generate answer information corresponding to the key words, and the alternative database comprises an economic knowledge map;
and the output module is used for outputting the answer information.
10. A smart device, the smart device comprising:
a display screen for displaying the answer information;
the user input component is used for inputting the economic knowledge problem information by a user;
a processor configured to receive user-entered economic knowledge question information and display the answer information on the display screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010230062.7A CN111460119B (en) | 2020-03-27 | 2020-03-27 | Intelligent question-answering method and system for economic knowledge and intelligent equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010230062.7A CN111460119B (en) | 2020-03-27 | 2020-03-27 | Intelligent question-answering method and system for economic knowledge and intelligent equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111460119A true CN111460119A (en) | 2020-07-28 |
| CN111460119B CN111460119B (en) | 2024-04-12 |
Family
ID=71681533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010230062.7A Active CN111460119B (en) | 2020-03-27 | 2020-03-27 | Intelligent question-answering method and system for economic knowledge and intelligent equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111460119B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579753A (en) * | 2020-12-17 | 2021-03-30 | 京东数字科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
| CN116823140A (en) * | 2023-04-21 | 2023-09-29 | 华腾建信科技有限公司 | Project problem information reporting method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332025A (en) * | 2011-09-29 | 2012-01-25 | 奇智软件（北京）有限公司 | Intelligent vertical search method and system |
| CN104850539A (en) * | 2015-05-28 | 2015-08-19 | 宁波薄言信息技术有限公司 | Natural language understanding method and travel question-answering system based on same |
| CN106709002A (en) * | 2016-12-23 | 2017-05-24 | 山东体育学院 | Intelligent exercise planning method and device based on natural language interaction |
| CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技（上海）有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
| CN107203565A (en) * | 2016-03-18 | 2017-09-26 | 刘陈伟 | Towards the intelligent recommendation system of fresh food |
| CN108256056A (en) * | 2018-01-12 | 2018-07-06 | 广州杰赛科技股份有限公司 | Intelligent answer method and system |
| CN109033221A (en) * | 2018-06-29 | 2018-12-18 | 上海银赛计算机科技有限公司 | Answer generation method, device and server |
| CN109145102A (en) * | 2018-09-06 | 2019-01-04 | 杭州安恒信息技术股份有限公司 | Intelligent answer method and its knowledge mapping system constituting method, device, equipment |
| CN109804364A (en) * | 2016-10-18 | 2019-05-24 | 浙江核新同花顺网络信息股份有限公司 | Knowledge mapping constructs system and method |
| CN110147436A (en) * | 2019-03-18 | 2019-08-20 | 清华大学 | A kind of mixing automatic question-answering method based on padagogical knowledge map and text |
| CN110209787A (en) * | 2019-05-29 | 2019-09-06 | 袁琦 | A kind of intelligent answer method and system based on pet knowledge mapping |
| CN110727779A (en) * | 2019-10-16 | 2020-01-24 | 信雅达***工程股份有限公司 | Question-answering method and system based on multi-model fusion |
| CN110750656A (en) * | 2019-10-29 | 2020-02-04 | 上海德拓信息技术股份有限公司 | Multimedia detection method based on knowledge graph |
-
2020
- 2020-03-27 CN CN202010230062.7A patent/CN111460119B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332025A (en) * | 2011-09-29 | 2012-01-25 | 奇智软件（北京）有限公司 | Intelligent vertical search method and system |
| CN104850539A (en) * | 2015-05-28 | 2015-08-19 | 宁波薄言信息技术有限公司 | Natural language understanding method and travel question-answering system based on same |
| CN107203565A (en) * | 2016-03-18 | 2017-09-26 | 刘陈伟 | Towards the intelligent recommendation system of fresh food |
| CN109804364A (en) * | 2016-10-18 | 2019-05-24 | 浙江核新同花顺网络信息股份有限公司 | Knowledge mapping constructs system and method |
| CN106709002A (en) * | 2016-12-23 | 2017-05-24 | 山东体育学院 | Intelligent exercise planning method and device based on natural language interaction |
| CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技（上海）有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
| CN108256056A (en) * | 2018-01-12 | 2018-07-06 | 广州杰赛科技股份有限公司 | Intelligent answer method and system |
| CN109033221A (en) * | 2018-06-29 | 2018-12-18 | 上海银赛计算机科技有限公司 | Answer generation method, device and server |
| CN109145102A (en) * | 2018-09-06 | 2019-01-04 | 杭州安恒信息技术股份有限公司 | Intelligent answer method and its knowledge mapping system constituting method, device, equipment |
| CN110147436A (en) * | 2019-03-18 | 2019-08-20 | 清华大学 | A kind of mixing automatic question-answering method based on padagogical knowledge map and text |
| CN110209787A (en) * | 2019-05-29 | 2019-09-06 | 袁琦 | A kind of intelligent answer method and system based on pet knowledge mapping |
| CN110727779A (en) * | 2019-10-16 | 2020-01-24 | 信雅达***工程股份有限公司 | Question-answering method and system based on multi-model fusion |
| CN110750656A (en) * | 2019-10-29 | 2020-02-04 | 上海德拓信息技术股份有限公司 | Multimedia detection method based on knowledge graph |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579753A (en) * | 2020-12-17 | 2021-03-30 | 京东数字科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
| CN112579753B (en) * | 2020-12-17 | 2024-04-12 | 京东科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
| CN116823140A (en) * | 2023-04-21 | 2023-09-29 | 华腾建信科技有限公司 | Project problem information reporting method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111460119B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8325189B2 (en) | Information processing apparatus capable of easily generating graph for comparing of a plurality of commercial products | |
| CN109710935B (en) | Museum navigation and knowledge recommendation method based on cultural relic knowledge graph | |
| CN113505586A (en) | Seat-assisted question-answering method and system integrating semantic classification and knowledge graph | |
| CN111292751B (en) | Semantic analysis method and device, voice interaction method and device, and electronic equipment | |
| CN116756295B (en) | Knowledge base retrieval method, device and storage medium | |
| CN110297880B (en) | Corpus product recommendation method, apparatus, device and storage medium | |
| JP2002132812A (en) | Method and system for answering question and recording medium with recorded question answering program | |
| CN111368093B (en) | Information acquisition method, information acquisition device, electronic equipment and computer readable storage medium | |
| CN114077705A (en) | Method and system for portraying media account on social platform | |
| CN111460119B (en) | Intelligent question-answering method and system for economic knowledge and intelligent equipment | |
| CN114186040A (en) | Operation method of intelligent robot customer service | |
| JP2010211575A (en) | Information evaluation support system | |
| CN112711716A (en) | Knowledge graph-based marine industry news pushing method and system | |
| US20090319514A1 (en) | Method and system for assigning scores | |
| JP2005190284A (en) | Information classification device and method | |
| CN109783612B (en) | Report data positioning method and device, storage medium and terminal | |
| CN117112595A (en) | Information query method and device, electronic equipment and storage medium | |
| CN115982322A (en) | Water conservancy industry design field knowledge graph retrieval method and retrieval system | |
| CN110765107A (en) | Question type identification method and system based on digital coding | |
| CN113779983B (en) | Text data processing method and device, storage medium and electronic device | |
| CN115186063A (en) | Service data processing method, device, equipment and storage medium | |
| CN111949781B (en) | Intelligent interaction method and device based on natural sentence syntactic analysis | |
| JP2014049044A (en) | Content management device, content management system, content management method, program, and storage medium | |
| JP6375367B2 (en) | Objection generation method, objection generation system | |
| JP2000148770A (en) | Device and method for classifying question documents and record medium where program wherein same method is described is recorded |
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 |