CN116578723A - Information query method and device, processor and electronic equipment - Google Patents
Information query method and device, processor and electronic equipment Download PDFInfo
- Publication number
- CN116578723A CN116578723A CN202310614854.8A CN202310614854A CN116578723A CN 116578723 A CN116578723 A CN 116578723A CN 202310614854 A CN202310614854 A CN 202310614854A CN 116578723 A CN116578723 A CN 116578723A
- Authority
- CN
- China
- Prior art keywords
- query
- template
- target
- information
- knowledge graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000012545 processing Methods 0.000 claims description 49
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 102100038367 Gremlin-1 Human genes 0.000 description 3
- 101001032872 Homo sapiens Gremlin-1 Proteins 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an information query method, an information query device, a processor and electronic equipment, wherein the method is applied to the field of artificial intelligence, and comprises the following steps: receiving query information input by a user; determining a target query template according to the query information; generating a target query statement corresponding to the query information according to the target query template; and acquiring a query result corresponding to the query information from the knowledge graph database according to the target query statement. According to the application, the problem that the working efficiency of the knowledge graph question-answering system is lower due to a higher use threshold of a template configuration method when a query template in the knowledge graph question-answering system is configured to answer a query problem of a user in the related technology is solved.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to an information query method, an information query device, a processor and electronic equipment.
Background
In the prior art, a Knowledge graph question-answering system (knowledges-based Question Answering, KBQA) aims at analyzing and processing the problems proposed by users by utilizing the analysis and processing capacity of a machine learning algorithm, and inquiring and reasoning by utilizing structured Knowledge in a Knowledge base to obtain accurate answers of the problems proposed by the users so as to assist the users in solving different types of problems.
The knowledge graph question-answering system which is adopted more at present is generally a semantic analysis model based on traditional linguistics. The semantic analysis model based on traditional linguistics can achieve higher accuracy in a simple question-answering scene, but with the increase of the complexity of the question-answering scene and the increase of the data volume containing the knowledge graph in the knowledge base, the accuracy of the knowledge graph question-answering system is reduced, meanwhile, a large number of templates and expert rules are required to be maintained by specific personnel, the use threshold of the knowledge graph question-answering system is increased, and the working efficiency of the knowledge graph question-answering system is reduced.
Aiming at the problem that the working efficiency of the knowledge graph question-answering system is lower because of a higher use threshold of a template configuration method when a query template in the knowledge graph question-answering system is configured to answer a query problem of a user in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The application mainly aims to provide an information query method, an information query device, a processor and electronic equipment, so as to solve the problem that the working efficiency of a knowledge graph question-answering system is lower because a template configuration method has a higher use threshold when a query template in the knowledge graph question-answering system is configured to answer a query question of a user in the related technology.
To achieve the above object, according to one aspect of the present application, there is provided an information query method including: receiving query information input by a user; determining a target query template according to the query information, wherein the target query template is a query template for processing the query information; generating a target query statement corresponding to the query information according to the target query template; and acquiring query results corresponding to the query information from a knowledge graph database according to the target query statement, wherein the knowledge graph database stores data of query scenes to which N pieces of query information belong, and N is a positive integer.
Further, before receiving the query information input by the user, the method further comprises: acquiring target data associated with an application scene to which the query information belongs to obtain M target data, wherein M is a positive integer; constructing a pattern structure of the knowledge graph database according to the relation among the M pieces of target data, wherein the pattern structure is a data structure of the target data stored in the knowledge graph database, and at least comprises the following components: entity, relationship, entity attribute, and relationship attribute; processing the M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer; configuring target parameters of the L knowledge maps to obtain the knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
Further, after processing the M target data according to the pattern structure to obtain L knowledge maps, the method further includes: generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs, wherein the first built-in template is used for generating a query result for querying the entity in the knowledge graph database; generating a second built-in template according to the entity attribute of each knowledge graph in the L knowledge graphs, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge graph database; and determining an embedded query template according to the first embedded template and the second embedded template, so as to obtain a query result corresponding to the query information in a knowledge graph database through the embedded query template.
Further, generating, according to the target query template, a target query statement corresponding to the query information includes: if the target query template belongs to a new added template, generating the target query statement according to the query intention of the query information, wherein the new added template represents the query template created by the user; and if the target query template belongs to a reference template, generating the target query statement according to a query scene to which the query information belongs, wherein the reference template represents a query template combined through an existing template.
Further, if the target query template belongs to a new template, generating the target query statement according to the query intention of the query information includes: determining a query intention corresponding to the query information in a preset query intention, wherein the preset query intention represents data stored in the knowledge graph database; determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention; and generating the target query statement according to the query intention and the target constraint condition.
Further, if the target query template belongs to a reference template, generating the target query statement according to a query scene to which the query information belongs includes: determining at least one query template selected by the user in a preset template library according to the scene type of the query scene to obtain a target reference template; and generating the target query statement according to the target reference template and the query information.
Further, after processing the M target data according to the pattern structure to obtain L knowledge maps, the method further includes: obtaining synonyms of elements in the pattern structures of the L knowledge maps; and acquiring a query result of the query information from the knowledge graph database according to the synonyms of the query information.
In order to achieve the above object, according to another aspect of the present application, there is provided an information inquiry apparatus including: the receiving unit is used for receiving query information input by a user; the first determining unit is used for determining a target query template according to the query information, wherein the target query template is a query template for processing the query information; the first generation unit is used for generating a target query statement corresponding to the query information according to the target query template; the first obtaining unit is configured to obtain, according to the target query statement, a query result corresponding to the query information in a knowledge graph database, where the knowledge graph database stores data of query scenarios to which N pieces of query information belong, and N is a positive integer.
Further, the apparatus further comprises: the second acquisition unit is used for acquiring target data associated with an application scene to which the query information belongs before receiving the query information input by a user, so as to obtain M target data, wherein M is a positive integer; the construction unit is configured to construct a schema structure of the knowledge-graph database according to the links between the M pieces of target data, where the schema structure is a data structure of the target data stored in the knowledge-graph database, and the schema structure at least includes: entity, relationship, entity attribute, and relationship attribute; the processing unit is used for processing the M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer; the configuration unit is used for configuring target parameters of the L knowledge maps to obtain the knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
Further, the apparatus further comprises: the second generating unit is used for generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs after processing the M target data according to the mode structure to obtain the L knowledge graphs, wherein the first built-in template is used for generating a query result of querying the entity in the knowledge graph database; the third generation unit is used for generating a second built-in template according to the entity attribute of each knowledge graph in the L knowledge graphs, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge graph database; and the second determining unit is used for determining an embedded query template according to the first embedded template and the second embedded template so as to acquire a query result corresponding to the query information in the knowledge graph database through the embedded query template.
Further, the first generating unit includes: a first generation subunit, configured to generate, if the target query template belongs to a new template, the target query statement according to a query intention of the query information, where the new template represents a query template created by the user; and the second generation subunit is used for generating the target query statement according to the query scene to which the query information belongs if the target query template belongs to the reference template, wherein the reference template represents the query template combined through the existing template.
Further, the first generation subunit includes: the first determining module is used for determining a query intention corresponding to the query information in a preset query intention, wherein the preset query intention represents data stored in the knowledge graph database; the second determining module is used for determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention; the first generation module is used for generating the target query statement according to the query intention and the target constraint condition.
Further, the second generating subunit includes: the third determining module is used for determining at least one query template selected by the user in a preset template library according to the scene type of the query scene to obtain a target reference template; and the second generation module is used for generating the target query statement according to the target reference template and the query information.
Further, the apparatus further comprises: the third acquisition unit is used for acquiring synonyms of elements in the mode structure of the L knowledge-graph after processing the M target data according to the mode structure to obtain the L knowledge-graph; and the fourth acquisition unit is used for acquiring the query result of the query information in the knowledge graph database according to the synonyms of the query information.
In order to achieve the above object, according to one aspect of the present application, there is provided a processor for executing a program, wherein the program executes any one of the information query methods described above.
In order to achieve the above object, according to one aspect of the present application, there is provided an electronic device including one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any one of the information query methods described above.
According to the application, the following steps are adopted: receiving query information input by a user; determining a target query template according to the query information, wherein the target query template is a query template for processing the query information; generating a target query statement corresponding to the query information according to the target query template; according to the target query statement, query results corresponding to the query information are obtained in a knowledge graph database, wherein the knowledge graph database stores data of query scenes to which N pieces of query information belong, and N is a positive integer, so that the problem that the working efficiency of the knowledge graph question-answering system is low due to the fact that a template configuration method has a high use threshold when a query template in the knowledge graph question-answering system is configured to answer query questions of users in the related technology is solved. By acquiring the query information of the clients and constructing the target query template, the query result can be acquired according to the target query template, the difficulty of generating the target query template is reduced, the effect of simply, conveniently and quickly acquiring the query result through the knowledge graph question-answering system is realized, and the effect of improving the working efficiency of the knowledge graph question-answering system is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flowchart of an information query method according to a first embodiment of the present application;
FIG. 2 is a schematic diagram I of an alternative information query method according to the first embodiment of the present application;
FIG. 3 is a schematic diagram II of an alternative information query method according to the first embodiment of the present application;
fig. 4 is a schematic diagram of an information query apparatus according to a second embodiment of the present application;
fig. 5 is a schematic diagram of an information query electronic device according to a fifth embodiment of the present application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, user query information, etc.) and the data (including, but not limited to, data for analysis, stored data, displayed data, queried data, generated data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and are provided with corresponding operation entries for the user to select authorization or rejection.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
The present application will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a method for querying information according to a first embodiment of the present application, as shown in fig. 1, and the method includes the following steps:
step S101, receiving query information input by a user.
In the first embodiment, the query information input by the user may belong to the query information under a plurality of scenes. For example, in a financial scenario, the results of calculation of the returns of a single or multiple financial products, or querying information such as risk levels of the financial products, are used. For another example, in a question-answer scenario of an enterprise architecture, the number of staff of an enterprise staff is queried, or the staff organization structure of a research and development department is queried.
Step S102, determining a target query template according to the query information, wherein the target query template is a query template for processing the query information.
Specifically, if the query information is "risk level of financial product a", determining a query template for querying an entity attribute in the existing template as a target query template, where the entity corresponds to "financial product a" in the query information and the entity attribute corresponds to "risk level" in the query information.
Step S103, generating a target query statement corresponding to the query information according to the target query template.
Specifically, if the query information is "risk level of the financial product a", the target query template is a query template for querying the entity attribute, the "financial product a" is extracted from the query information as the entity to be queried, and the "risk level" is extracted as the entity attribute to be queried. Next, according to the entity "financial product a" and the entity attribute "risk level", a target query sentence "g.V (). Has ('name', 'financial product a'). Values ('risk level')", based on the Gremlin language, represents that the value of the attribute "risk level" is searched for in the node named "financial product a", and the value of the attribute is returned. In the first embodiment, the target query sentence may be generated based on Gremlin language, or may be generated by using other languages according to actual situations. The Gremlin language is a language used for querying and operating a graph database, and supports a plurality of graph database systems, for example, graph database systems such as Apache TinkerPop, neo4j and janus graph.
Step S104, obtaining query results corresponding to the query information from a knowledge graph database according to the target query statement, wherein the knowledge graph database stores data of query scenes to which N pieces of query information belong, and N is a positive integer.
Specifically, if the target query statement is "g.V ()," has ('name', 'financial product a'). Values ('risk level') ", the target query statement is executed in the knowledge graph database, so as to obtain a query result. In the first embodiment, the knowledge-graph database is a graph database for storing a plurality of knowledge-graphs. The knowledge graph database may be used to store data in multiple query scenarios, for example, the knowledge graph database a stores employee organizational chart of the enterprise research and development department and employee organizational chart of the market department. For another example, a knowledge graph database B stores a related information graph of financial products of a financial institution.
In summary, in the information query method provided by the first embodiment of the present application, query information input by a user is received; determining a target query template according to the query information, wherein the target query template is a query template for processing the query information; generating a target query statement corresponding to the query information according to the target query template; according to the target query statement, query results corresponding to query information are obtained in a knowledge graph database, wherein the knowledge graph database stores data of query scenes to which N pieces of query information belong, and N is a positive integer, so that the problem that the working efficiency of the knowledge graph question-answering system is low due to the fact that a higher use threshold exists in a template configuration method when a query template in the knowledge graph question-answering system is configured to answer a query problem of a user in the related art is solved. By acquiring the query information of the clients and constructing the target query template, the query result can be acquired according to the target query template, the difficulty of generating the target query template is reduced, the effect of simply, conveniently and quickly acquiring the query result through the knowledge graph question-answering system is realized, and the effect of improving the working efficiency of the knowledge graph question-answering system is achieved.
Optionally, in the information query method provided in the first embodiment of the present application, before receiving query information input by a user, the method further includes: acquiring target data associated with an application scene to which query information belongs to obtain M target data, wherein M is a positive integer; according to the relation among M pieces of target data, constructing a mode structure of a knowledge graph database, wherein the mode structure is a data structure stored in the knowledge graph database by the target data, and at least comprises the following steps: entity, relationship, entity attribute, and relationship attribute; processing M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer; configuring target parameters of L knowledge maps to obtain a knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
In the first embodiment, in order to construct the knowledge graph database, the target data of the application scenario to which the query information belongs needs to be processed to obtain a plurality of knowledge graphs, and the plurality of knowledge graphs are stored in the graph database to obtain the knowledge graph database. The knowledge graph is a data model based on graph structure, the nodes in the knowledge graph represent entities, the attributes of the nodes in the knowledge graph represent entity attributes, and the edges between two nodes represent the relationship between the two entities.
Specifically, if the query information belongs to a financial scene, the financial product and a product manager can be taken as entities, the characteristics of the financial product such as income information and risk level are taken as entity attributes of the financial product, and the relationship between the product manager and the financial product is taken as relationship and relationship attributes. These entities, relationships, entity attributes and relationship attributes are then converted into schema structures (schemas) of the knowledge graph. After the mode structure of the knowledge graph is constructed, relevant data (namely target data) related to the financial scene is imported into the knowledge graph to obtain a plurality of knowledge graphs in the financial scene. And finally, generating relevant parameters of a plurality of knowledge maps, and writing the relevant parameters into a configuration table of a knowledge map database to obtain the knowledge map database. Table 1 is an example of relevant parameters of the knowledge graph, and table 1 is shown below. Wherein es (Elastic Search) indexes are used to store and manage data in a database, a user can define different mappings (mapping) for each es index, and query the corresponding data using complex query statements for better distributed data storage and management, thereby improving system performance and scalability.
TABLE 1 configuration Table
The method is beneficial to the follow-up method for designing and inquiring and processing the knowledge graph according to the mode structure by constructing the mode structure of the knowledge graph database according to the actual condition of the inquiring scene, the effect of flexibly defining the inquiring method is realized, the target data related to the inquiring scene is written into the knowledge graph database, the inquiring information of the user can be processed by the inquiring method of the graph database, and the effect of improving the inquiring efficiency of the inquiring data of the user is achieved.
Optionally, in the information query method provided in the first embodiment of the present application, after processing M pieces of target data according to a pattern structure to obtain L knowledge maps, the method further includes: generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs, wherein the first built-in template is used for generating a query result for querying the entity in the knowledge graph database; generating a second built-in template according to the entity attribute of each of the L knowledge maps, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge map database; and determining the built-in query template according to the first built-in template and the second built-in template so as to acquire a query result corresponding to the query information in the knowledge graph database through the built-in query template.
In the first embodiment, in order to simply and quickly query in the knowledge-graph database, a first built-in template for querying the entity in the knowledge-graph is constructed, and a second built-in template for querying the attribute of the entity in the knowledge-graph is constructed. Specifically, the content included in the first built-in template may be shown in table 2, where the template name is the first built-in template, and the query content is [ entity_1] (i.e. entity). The second built-in template may include a content as shown in table 3, where the template name is the second built-in template, and the query content is [ entity_property_ontologiy_1 ] of [ entity_1] (i.e. the attribute of the entity).
TABLE 2 first built-in template
| Template name | First built-in template |
| Querying content | Entity: [ entity_1] |
TABLE 3 second built-in template
| Template name | Second built-in template |
| Querying content | Entity attributes: [ entity_1]Is [ entity_property_ontologigy_1 ]] |
By configuring the built-in query template, the query result of the simple problem can be quickly obtained from the knowledge graph database, the use threshold of the knowledge graph question-answering system is reduced, the effect of simple and quick question-answering through the knowledge graph question-answering system is realized, and the effect of improving the working efficiency of the knowledge graph question-answering system is achieved.
Optionally, in the information query method provided in the first embodiment of the present application, generating, according to the target query template, a target query statement corresponding to query information includes: if the target query template belongs to the newly added template, generating a target query statement according to the query intention of the query information, wherein the newly added template represents the query template created by the user; if the target query template belongs to the reference template, generating a target query statement according to a query scene to which query information belongs, wherein the reference template represents a query template combined through the existing template.
In the first embodiment, the new template refers to a query template created by the user in the knowledge-graph question-answering system. For example, the query information is "risk level of the financial product a", and the query content of the query information may be "financial product a" and "risk level". Then, a target query sentence is generated according to the financial product A and the risk level. In addition, the reference template means that the user refers to at least one query template among existing templates as a target query template. For example, if the query information is "risk level of financial product a", the second built-in template may be referred to, and the entity "financial product a" and the entity attribute "risk level" are input in the second built-in template, so as to obtain the target query statement. And generating target query sentences corresponding to the query information through the target query templates, so that the use threshold of the knowledge graph question-answering system is reduced, and the effect of improving the working efficiency of the knowledge graph question-answering system is achieved.
Optionally, in the information query method provided in the first embodiment of the present application, if the target query template belongs to the newly added template, generating the target query statement according to the query intention of the query information includes: determining query intentions corresponding to the query information in preset query intentions, wherein the preset query intentions represent data stored in a knowledge graph database; determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention; and generating a target query statement according to the query intention and the target constraint condition.
In the first embodiment, table 4 is an example of content included in the newly added template. As shown in Table 4, the newly added templates include template names, query intents, query constraints, query statements, and template sources. FIG. 2 is a schematic diagram of a flow of generating a target query statement by adding templates. As shown in fig. 2, first, the query information "risk level of financial product a" input by the user is acquired, and the query information input by the user may be used as the template name of the newly added template. Next, the user can select the entity "financial product a" and the entity attribute "risk level" in the knowledge-graph database through a drop-down box. The entity 'financial product A' and the entity attribute 'risk level' are used as query intents of query information. The user may then select, via a drop down box, that the entity type of the selected entity "financial product A" must be the fund product. The entity type of the entity "financial product a" must be the fund product as a target constraint. The target constraint may be expressed as { "conditionnmap": { "entity_1": { "elementconditionnmap": { "label": [ "foundation product" ] } } }). And finally, generating a target query statement according to the entity 'financial product A', the entity attribute 'risk level' and the target constraint condition.
Table 4 newly added templates
In addition, the new template can also comprise a custom template, namely, a custom query sentence input by a user is received, and the custom query sentence of the user is used as a target query sentence to query in the knowledge graph database.
By acquiring the query information and the query intention of the user, the situation that the user must design the target query sentence by himself to obtain the query result is avoided, the process of creating the target query template by the user is simplified, the use threshold of the target query template is reduced, the effect of reducing the use threshold of the knowledge graph question-answering system is achieved, and the effect of improving the query efficiency of the knowledge graph question-answering system is further achieved.
Optionally, in the information query method provided in the first embodiment of the present application, if the target query template belongs to the reference template, generating the target query statement according to the query scene to which the query information belongs includes: determining at least one query template selected by a user in a preset template library according to the scene type of the query scene to obtain a target reference template; and generating a target query statement according to the target reference template and the query information.
Specifically, if the query information is "all financial products subordinate to the product manager a", a query template of which the query scene belongs to the financial scene is obtained from a preset template library. Next, it is determined that the user selects a query template B for querying neighboring nodes of a single node among query templates belonging to the financial scene, and the query template B is taken as a target reference template. Then, the entity 'product manager A' and the relation 'adjacent to the product manager A' are input in the query template B, and a target query statement is generated. The target reference template selected by the user is determined in the preset template library, and the target reference template is used as the target query template, so that the use threshold of the target query template is reduced, the effect of reducing the use threshold of the knowledge graph question-answering system is achieved, and the effect of improving the query efficiency of the knowledge graph question-answering system is further achieved.
Optionally, in the information query method provided in the first embodiment of the present application, after processing M pieces of target data according to a pattern structure to obtain L knowledge maps, the method further includes: obtaining synonyms of elements in the pattern structures of the L knowledge maps; and obtaining the query result of the query information in the knowledge graph database according to the synonyms of the query information.
Specifically, the knowledge graph a includes an entity "financial product A1", and a synonym of the entity "financial product A1" may be set as "investment product A1", so as to query related information of the financial product A1 "according to the entity" investment product A1 ". The elements in the schema structure may include elements other than entities, such as relationships, entity attributes, and relationship attributes. By setting the synonyms of each element in the pattern structure, the query result of the query information can be obtained according to the synonyms of the query information, the query range of the query information is enlarged, and the query efficiency effect of the knowledge graph question-answering system is achieved.
Alternatively, in the first embodiment, the flow of acquiring the query result by the knowledge-graph question-answering system in the present embodiment may be as shown in fig. 3. Firstly, constructing a mode structure of a knowledge graph database according to a query scene to obtain the knowledge graph database. Next, synonyms for each element of the schema structure are configured in a knowledge-graph database. Then, a target query template for acquiring a query result corresponding to the query information is determined. And finally, generating a target query statement according to the target query template, and acquiring a query result corresponding to the query information in the knowledge graph database.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example two
The second embodiment of the present application also provides an information query apparatus, which needs to be described, where the information query apparatus of the second embodiment of the present application may be used to execute the information query method provided by the first embodiment of the present application. The following describes an information query apparatus provided in the second embodiment of the present application.
Fig. 4 is a schematic diagram of an information query apparatus according to a second embodiment of the present application. As shown in fig. 4, the apparatus includes: a receiving unit 401, a first determining unit 402, a first generating unit 403, and a first acquiring unit 404.
Specifically, the receiving unit 401 is configured to receive query information input by a user.
The first determining unit 402 is configured to determine a target query template according to the query information, where the target query template is a query template for processing the query information.
The first generating unit 403 is configured to generate a target query statement corresponding to the query information according to the target query template.
The first obtaining unit 404 is configured to obtain, according to the target query statement, a query result corresponding to the query information in a knowledge graph database, where the knowledge graph database stores data of a query scenario to which N pieces of query information belong, and N is a positive integer.
In the information query device provided in the second embodiment of the present application, the receiving unit 401 receives query information input by a user; the first determining unit 402 determines a target query template according to the query information, wherein the target query template is a query template for processing the query information; the first generating unit 403 generates a target query statement corresponding to the query information according to the target query template; the first obtaining unit 404 obtains the query result corresponding to the query information in the knowledge graph database according to the target query statement, where the knowledge graph database stores data of query scenarios to which N pieces of query information belong, N is a positive integer, so that the problem that in the related art, when a query question of a user is answered by configuring a query template in the knowledge graph question answering system, the working efficiency of the knowledge graph question answering system is lower because a higher use threshold exists in a template configuration method is solved. By acquiring the query information of the clients and constructing the target query template, the query result can be acquired according to the target query template, the difficulty of generating the target query template is reduced, the effect of simply, conveniently and quickly acquiring the query result through the knowledge graph question-answering system is realized, and the effect of improving the working efficiency of the knowledge graph question-answering system is achieved.
Optionally, in the information query apparatus provided in the second embodiment of the present application, the apparatus further includes: the second acquisition unit is used for acquiring target data associated with an application scene to which the query information belongs before receiving the query information input by a user to obtain M target data, wherein M is a positive integer; the construction unit is used for constructing a pattern structure of the knowledge graph database according to the relation among M pieces of target data, wherein the pattern structure is a data structure of the target data stored in the knowledge graph database, and at least comprises the following components: entity, relationship, entity attribute, and relationship attribute; the processing unit is used for processing the M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer; the configuration unit is used for configuring target parameters of the L knowledge maps to obtain a knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
Optionally, in the information query apparatus provided in the second embodiment of the present application, the apparatus further includes: the second generation unit is used for processing the M target data according to the mode structure to obtain L knowledge graphs, and then generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs, wherein the first built-in template is used for generating a query result for querying the entity in the knowledge graph database; the third generation unit is used for generating a second built-in template according to the entity attribute of each of the L knowledge maps, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge map database; and the second determining unit is used for determining the built-in query template according to the first built-in template and the second built-in template so as to acquire a query result corresponding to the query information in the knowledge graph database through the built-in query template.
Optionally, in the information query apparatus provided in the second embodiment of the present application, the first generating unit 403 includes: the first generation subunit is configured to generate a target query statement according to a query intention of the query information if the target query template belongs to a new added template, where the new added template represents a query template created by a user; and the second generation subunit is used for generating a target query statement according to the query scene to which the query information belongs if the target query template belongs to the reference template, wherein the reference template represents the query template combined by the existing template.
Optionally, in the information query apparatus provided in the second embodiment of the present application, the first generating subunit includes: the first determining module is used for determining query intentions corresponding to the query information in preset query intentions, wherein the preset query intentions represent data stored in the knowledge graph database; the second determining module is used for determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention; the first generation module is used for generating a target query statement according to the query intention and the target constraint condition.
Optionally, in the information query apparatus provided in the second embodiment of the present application, the second generating subunit includes: the third determining module is used for determining at least one query template selected by a user in a preset template library according to the scene type of the query scene to obtain a target reference template; and the second generation module is used for generating a target query statement according to the target reference template and the query information.
Optionally, in the information query apparatus provided in the second embodiment of the present application, the apparatus further includes: the third acquisition unit is used for processing the M target data according to the pattern structure to obtain L knowledge maps and then acquiring synonyms of elements in the pattern structure of the L knowledge maps; and the fourth acquisition unit is used for acquiring the query result of the query information in the knowledge graph database according to the synonyms of the query information.
The information query apparatus includes a processor and a memory, where the receiving unit 401, the first determining unit 402, the first generating unit 403, the first obtaining unit 404, and the like are stored as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the working efficiency of the knowledge graph question-answering system is improved by adjusting kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
A third embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements an information query method.
The fourth embodiment of the invention provides a processor, which is used for running a program, wherein the information query method is executed when the program runs.
As shown in fig. 5, a fifth embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: receiving query information input by a user; determining a target query template according to the query information, wherein the target query template is a query template for processing the query information; generating a target query statement corresponding to the query information according to the target query template; and acquiring query results corresponding to the query information from a knowledge graph database according to the target query statement, wherein the knowledge graph database stores data of query scenes to which the N query information belongs, and N is a positive integer.
The processor also realizes the following steps when executing the program: the method further comprises the following steps before receiving the query information input by the user: acquiring target data associated with an application scene to which query information belongs to obtain M target data, wherein M is a positive integer; according to the relation among M pieces of target data, constructing a mode structure of a knowledge graph database, wherein the mode structure is a data structure stored in the knowledge graph database by the target data, and at least comprises the following steps: entity, relationship, entity attribute, and relationship attribute; processing M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer; configuring target parameters of L knowledge maps to obtain a knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
The processor also realizes the following steps when executing the program: after processing the M target data according to the pattern structure to obtain L knowledge maps, the method further includes: generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs, wherein the first built-in template is used for generating a query result for querying the entity in the knowledge graph database; generating a second built-in template according to the entity attribute of each of the L knowledge maps, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge map database; and determining the built-in query template according to the first built-in template and the second built-in template so as to acquire a query result corresponding to the query information in the knowledge graph database through the built-in query template.
The processor also realizes the following steps when executing the program: generating a target query statement corresponding to the query information according to the target query template comprises: if the target query template belongs to the newly added template, generating a target query statement according to the query intention of the query information, wherein the newly added template represents the query template created by the user; if the target query template belongs to the reference template, generating a target query statement according to a query scene to which query information belongs, wherein the reference template represents a query template combined through the existing template.
The processor also realizes the following steps when executing the program: if the target query template belongs to the newly added template, generating a target query sentence according to the query intention of the query information comprises: determining query intentions corresponding to the query information in preset query intentions, wherein the preset query intentions represent data stored in a knowledge graph database; determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention; and generating a target query statement according to the query intention and the target constraint condition.
The processor also realizes the following steps when executing the program: if the target query template belongs to the reference template, generating a target query sentence according to a query scene to which the query information belongs comprises: determining at least one query template selected by a user in a preset template library according to the scene type of the query scene to obtain a target reference template; and generating a target query statement according to the target reference template and the query information.
The processor also realizes the following steps when executing the program: after processing the M target data according to the pattern structure to obtain L knowledge maps, the method further includes: obtaining synonyms of elements in the pattern structures of the L knowledge maps; and obtaining the query result of the query information in the knowledge graph database according to the synonyms of the query information.
The device herein may be a server, PC, PAD, cell phone, etc.
The application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: receiving query information input by a user; determining a target query template according to the query information, wherein the target query template is a query template for processing the query information; generating a target query statement corresponding to the query information according to the target query template; and acquiring query results corresponding to the query information from a knowledge graph database according to the target query statement, wherein the knowledge graph database stores data of query scenes to which the N query information belongs, and N is a positive integer.
When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: the method further comprises the following steps before receiving the query information input by the user: acquiring target data associated with an application scene to which query information belongs to obtain M target data, wherein M is a positive integer; according to the relation among M pieces of target data, constructing a mode structure of a knowledge graph database, wherein the mode structure is a data structure stored in the knowledge graph database by the target data, and at least comprises the following steps: entity, relationship, entity attribute, and relationship attribute; processing M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer; configuring target parameters of L knowledge maps to obtain a knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: after processing the M target data according to the pattern structure to obtain L knowledge maps, the method further includes: generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs, wherein the first built-in template is used for generating a query result for querying the entity in the knowledge graph database; generating a second built-in template according to the entity attribute of each of the L knowledge maps, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge map database; and determining the built-in query template according to the first built-in template and the second built-in template so as to acquire a query result corresponding to the query information in the knowledge graph database through the built-in query template.
When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: generating a target query statement corresponding to the query information according to the target query template comprises: if the target query template belongs to the newly added template, generating a target query statement according to the query intention of the query information, wherein the newly added template represents the query template created by the user; if the target query template belongs to the reference template, generating a target query statement according to a query scene to which query information belongs, wherein the reference template represents a query template combined through the existing template.
When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: if the target query template belongs to the newly added template, generating a target query sentence according to the query intention of the query information comprises: determining query intentions corresponding to the query information in preset query intentions, wherein the preset query intentions represent data stored in a knowledge graph database; determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention; and generating a target query statement according to the query intention and the target constraint condition.
When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: if the target query template belongs to the reference template, generating a target query sentence according to a query scene to which the query information belongs comprises: determining at least one query template selected by a user in a preset template library according to the scene type of the query scene to obtain a target reference template; and generating a target query statement according to the target reference template and the query information.
When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: after processing the M target data according to the pattern structure to obtain L knowledge maps, the method further includes: obtaining synonyms of elements in the pattern structures of the L knowledge maps; and obtaining the query result of the query information in the knowledge graph database according to the synonyms of the query information.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. An information query method, comprising:
receiving query information input by a user;
determining a target query template according to the query information, wherein the target query template is a query template for processing the query information;
generating a target query statement corresponding to the query information according to the target query template;
Obtaining the query result corresponding to the query information in a knowledge graph database according to the target query statement, wherein the knowledge graph database stores data of query scenes to which N pieces of query information belong,
n is a positive integer.
2. The method of claim 1, wherein prior to receiving the query information entered by the user, the method further comprises:
acquiring target data associated with an application scene to which the query information belongs to obtain M target data, wherein M is a positive integer;
constructing a pattern structure of the knowledge graph database according to the relation among the M pieces of target data, wherein the pattern structure is a data structure of the target data stored in the knowledge graph database, and at least comprises the following components: entity, relationship, entity attribute, and relationship attribute;
processing the M target data according to the mode structure to obtain L knowledge maps, wherein L is a positive integer;
configuring target parameters of the L knowledge maps to obtain the knowledge map database, wherein the target parameters at least comprise the following parameters: scene ID, query statement corresponding to scene ID.
3. The method of claim 2, wherein after processing the M target data according to the pattern structure to obtain L knowledge-maps, the method further comprises:
generating a first built-in template according to the entity of each knowledge graph in the L knowledge graphs, wherein the first built-in template is used for generating a query result for querying the entity in the knowledge graph database;
generating a second built-in template according to the entity attribute of each knowledge graph in the L knowledge graphs, wherein the second built-in template is used for generating a query result for querying the entity attribute in the knowledge graph database;
and determining an embedded query template according to the first embedded template and the second embedded template, so as to obtain a query result corresponding to the query information in a knowledge graph database through the embedded query template.
4. The method of claim 1, wherein generating the target query statement corresponding to the query information in accordance with the target query template comprises:
if the target query template belongs to a new added template, generating the target query statement according to the query intention of the query information, wherein the new added template represents the query template created by the user;
And if the target query template belongs to a reference template, generating the target query statement according to a query scene to which the query information belongs, wherein the reference template represents a query template combined through an existing template.
5. The method of claim 4, wherein if the target query template belongs to a new template, generating the target query statement according to the query intent of the query information comprises:
determining a query intention corresponding to the query information in a preset query intention, wherein the preset query intention represents data stored in the knowledge graph database;
determining a target constraint condition corresponding to the query intention in preset constraint conditions, wherein the preset constraint conditions represent constraint conditions for the query intention;
and generating the target query statement according to the query intention and the target constraint condition.
6. The method of claim 4, wherein if the target query template belongs to a reference template, generating the target query statement according to a query scenario to which the query information belongs comprises:
determining at least one query template selected by the user in a preset template library according to the scene type of the query scene to obtain a target reference template;
And generating the target query statement according to the target reference template and the query information.
7. The method of claim 2, wherein after processing the M target data according to the pattern structure to obtain L knowledge-maps, the method further comprises:
obtaining synonyms of elements in the pattern structures of the L knowledge maps;
and acquiring a query result of the query information from the knowledge graph database according to the synonyms of the query information.
8. An information inquiry apparatus, characterized by comprising:
the receiving unit is used for receiving query information input by a user;
the first determining unit is used for determining a target query template according to the query information, wherein the target query template is a query template for processing the query information;
the first generation unit is used for generating a target query statement corresponding to the query information according to the target query template;
the first obtaining unit is configured to obtain, according to the target query statement, a query result corresponding to the query information in a knowledge graph database, where the knowledge graph database stores data of query scenarios to which N pieces of query information belong, and N is a positive integer.
9. A processor, characterized in that the processor is configured to run a program, wherein the program, when run, performs the information query method of any of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the information query method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310614854.8A CN116578723A (en) | 2023-05-26 | 2023-05-26 | Information query method and device, processor and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310614854.8A CN116578723A (en) | 2023-05-26 | 2023-05-26 | Information query method and device, processor and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116578723A true CN116578723A (en) | 2023-08-11 |
Family
ID=87533926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310614854.8A Pending CN116578723A (en) | 2023-05-26 | 2023-05-26 | Information query method and device, processor and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116578723A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117951281A (en) * | 2024-03-26 | 2024-04-30 | 上海森亿医疗科技有限公司 | Knowledge graph-based database query statement generation method, system and terminal |
-
2023
- 2023-05-26 CN CN202310614854.8A patent/CN116578723A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117951281A (en) * | 2024-03-26 | 2024-04-30 | 上海森亿医疗科技有限公司 | Knowledge graph-based database query statement generation method, system and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107038207B (en) | Data query method, data processing method and device | |
| CN109284363B (en) | Question answering method and device, electronic equipment and storage medium | |
| Hartig et al. | Publishing and consuming provenance metadata on the web of linked data | |
| CN105630881B (en) | A kind of date storage method and querying method of RDF | |
| CN110750649A (en) | Knowledge graph construction and intelligent response method, device, equipment and storage medium | |
| CN113032579B (en) | Metadata blood relationship analysis method and device, electronic equipment and medium | |
| CN109977175B (en) | Data configuration query method and device | |
| CN114201616A (en) | Knowledge graph construction method and system based on multi-source database | |
| CN116578723A (en) | Information query method and device, processor and electronic equipment | |
| Ravat et al. | Efficient querying of multidimensional RDF data with aggregates: Comparing NoSQL, RDF and relational data stores | |
| CN111625638B (en) | Question processing method, device, equipment and readable storage medium | |
| CN114090760B (en) | Data processing method of table question and answer, electronic equipment and readable storage medium | |
| CN115080765A (en) | Aerospace quality knowledge map construction method, system, medium and equipment | |
| CN117668182A (en) | Standard intelligent question-answering method and system integrating knowledge graph and large language model | |
| CN108550019A (en) | A kind of resume selection method and device | |
| CN117033744A (en) | Data query method and device, storage medium and electronic equipment | |
| CN101719162A (en) | Multi-version open geographic information service access method and system based on fragment pattern matching | |
| CN108241624B (en) | Query script generation method and device | |
| Berardi et al. | StdTrip+ K: Design Rationale in the RDB-to-RDF process | |
| Su-Cheng et al. | Mapping of extensible markup language-to-ontology representation for effective data integration | |
| Goonetillake et al. | A hybrid approach towards optimisation of data and knowledge management through cooperation of database and ontology | |
| CN111930778B (en) | Knowledge query method and device | |
| CN118132722A (en) | Training method, training device, training equipment, training medium and training product for form question-answer model | |
| CN111651465B (en) | Knowledge data storage method and device for enterprise cooperation | |
| CN111221846B (en) | Automatic translation method and device for SQL sentences |
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 |