CN110502645B - Information query method and device - Google Patents
Information query method and device Download PDFInfo
- Publication number
- CN110502645B CN110502645B CN201910801095.XA CN201910801095A CN110502645B CN 110502645 B CN110502645 B CN 110502645B CN 201910801095 A CN201910801095 A CN 201910801095A CN 110502645 B CN110502645 B CN 110502645B
- Authority
- CN
- China
- Prior art keywords
- data
- query
- information
- structured data
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000013480 data collection Methods 0.000 claims 1
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
-
- 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
Abstract
The invention provides an information query method and device, comprising the following steps: acquiring query information from a terminal; determining at least one keyword in the query information; acquiring a query result corresponding to query information from a knowledge graph according to at least one keyword, wherein the knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model; and sending the query result to the terminal so that the terminal displays the query result. The information query method and the information query device provided by the invention reduce the query time and improve the accuracy of the query result.
Description
Technical Field
The present invention relates to the field of network technology information, and in particular, to an information query method and apparatus.
Background
As the channels for receiving information increase from the development of the media industry, the demand for fragmented queries also increases. Based on the method, the intelligent customer service is more widely applied, so that the query result can be automatically displayed according to the query information input by the user.
At present, the existing intelligent customer service system has low intelligent degree, which results in low quality of service of the intelligent customer service. After receiving the query information input by the user, the intelligent customer service system needs to spend a long time for result query, and the displayed query result is often inconsistent with the query result actually required by the user.
Disclosure of Invention
The invention provides an information query method and device, and aims to solve the problem that an intelligent customer service system in the prior art is long in query time and low in query result accuracy.
A first aspect of the present invention provides an information query method, including:
acquiring query information from a terminal;
determining at least one keyword in the query information;
acquiring a query result corresponding to the query information from a knowledge graph according to the at least one keyword, wherein the knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model;
and sending the query result to the terminal so that the terminal displays the query result.
Optionally, before the obtaining of the query information input by the user, the method further includes:
acquiring a data set corresponding to a knowledge graph to be created, wherein data in the data set comprises at least one entity;
converting unstructured data in the data set into structured data;
creating the knowledge-graph from the structured data.
Optionally, the converting unstructured data in the data set into structured data includes:
determining a knowledge template corresponding to the unstructured data;
and storing the entities in the unstructured data in the knowledge template according to element information in the knowledge template to generate the structured data, wherein the element information comprises the entity types, the attributes of the entities and the relations among the entities.
Optionally, the creating the knowledge-graph according to the structured data includes:
determining type information of the structured data;
determining a map template corresponding to the structured data according to the type information;
if the element information of the map model is the same as the element information of the knowledge template corresponding to the structured data, determining that the structured data is an atom of the map model;
and importing the structured data into the map model to establish the knowledge map.
Optionally, before the importing the structured data into the graph model and establishing the knowledge graph, the method includes:
and processing the entities in the structured data and the entities in the atlas model.
A second aspect of the present invention provides an apparatus for querying information, including:
the first acquisition module is used for acquiring query information from a terminal;
a determining module, configured to determine at least one keyword in the query information;
the result module is used for acquiring a query result corresponding to the query information from a knowledge graph according to the at least one keyword, wherein the knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model;
and the sending module is used for sending the query result to the terminal so that the terminal displays the query result.
Optionally, the method further includes:
the second acquisition module is used for acquiring a data set corresponding to the knowledge graph to be created, wherein data in the data set comprises at least one entity;
the conversion module is used for converting unstructured data in the data set into structured data;
a creation module to create the knowledge-graph from the structured data.
Optionally, the conversion module is specifically configured to determine a knowledge template corresponding to the unstructured data; and storing the entities in the unstructured data in the knowledge template according to element information in the knowledge template to generate the structured data, wherein the element information comprises the entity types, the attributes of the entities and the relations among the entities.
Optionally, the creating module is specifically configured to determine type information of the structured data; determining a map template corresponding to the structured data according to the type information; if the element information of the map model is the same as the element information of the knowledge template corresponding to the structured data, determining that the structured data is an atom of the map model; and importing the structured data into the map model to establish the knowledge map.
Optionally, the creating module is further configured to process the entity in the structured data and the entity in the atlas model.
A third aspect of the present invention provides an electronic apparatus comprising:
a memory for storing program instructions;
a processor for calling and executing the program instructions in the memory to perform the method steps of the first aspect.
A fourth aspect of the present invention provides a storage medium having stored thereon a computer program for executing the method of any one of the first aspects.
According to the information query method and device provided by the invention, the query information from the terminal is obtained, at least one keyword in the query information is determined, the query result corresponding to the query information is obtained from the knowledge graph according to the at least one keyword, and the query result is sent to the terminal, so that the terminal displays the query result. The knowledge graph is built by converting unstructured data to structured data and matching the structured data to a graph model. By the method, the query time can be reduced, and the accuracy of the query result can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the following briefly introduces the drawings needed to be used in the description of the embodiments or the prior art, and obviously, the drawings in the following description are some embodiments of the present invention, and those skilled in the art can obtain other drawings according to the drawings without inventive labor.
Fig. 1 is a schematic view of a scenario of an information query method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of an information query method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another information query method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an information query apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of another information query device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of another information query device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As the channels for receiving information increase from the development of the media industry, the demand for fragmented queries also increases. Based on the method, the intelligent customer service is more widely applied, so that the query result can be automatically displayed according to the query information input by the user. In the prior art, the existing intelligent customer service system has low intelligent degree, which results in low quality of service of the intelligent customer service. After receiving the query information input by the user, the intelligent customer service system needs to spend a long time for result query, and the displayed query result is often inconsistent with the query result actually required by the user.
In view of the above problems, the present invention provides an information query method and apparatus, which perform information query by converting unstructured data into structured data and then establishing a knowledge graph, thereby reducing query time and improving accuracy of query results.
Fig. 1 is a schematic scene diagram of an information query method according to an embodiment of the present application. As shown in fig. 1, a terminal 101 acquires query information input by a user in a query application and transmits the query information to a server 102. The server 102 obtains the keyword from the query information, and obtains a query result corresponding to the query information from the knowledge graph according to the keyword. Subsequently, the server 102 transmits the query result to the terminal 101 so that the terminal 101 can display the query result.
Wherein, the terminal 101: the wireless terminal can be a wireless terminal or a wired terminal, and the wireless terminal can be a device with a wireless transceiving function, can be deployed on land, and comprises indoor or outdoor, handheld or vehicle-mounted; can also be deployed on the water surface (such as a ship and the like); and may also be deployed in the air (e.g., airplanes, balloons, satellites, etc.). The terminal may be a mobile phone (mobile phone), a tablet computer (Pad), a computer with a wireless transceiving function, a Virtual Reality (VR) terminal, an Augmented Reality (AR) terminal, a wireless terminal in industrial control (industrial control), a wireless terminal in self driving (self driving), a wireless terminal in remote medical (remote medical), a wireless terminal in smart grid (smart grid), a wireless terminal in transportation safety (transportation safety), a wireless terminal in smart city (smart city), a wireless terminal in smart home (smart home), and the like, which are not limited herein. It can be understood that, in the embodiment of the present application, a terminal may also be referred to as a User Equipment (UE).
The server 102 may be an application server, and may correspond to an application that performs information query on the terminal 101, for example: and the intelligent customer service server.
It can be understood that the information query method provided by the embodiment of the present application can be applied to any server for performing information query.
It can be understood that the page detection method may be implemented by an information query apparatus provided in the embodiments of the present application, where the information query apparatus may be part or all of a certain device, and may be, for example, the server described above.
The following takes a server integrated or installed with relevant execution codes as an example, and details the technical solution of the embodiment of the present application with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a schematic flowchart of an information query method according to an embodiment of the present application. The embodiment relates to a specific process of how the server determines the query result corresponding to the query information. As shown in fig. 2, the method includes:
s201, acquiring query information from a terminal.
In this step, the user may input query information in the application of the terminal to obtain the query result to be obtained. And the terminal sends the query information input by the user to a server corresponding to the application so that the server determines a query result corresponding to the query information.
The query information may be at least one phrase or a sentence, and the content of the query information is not limited in the embodiments of the present application. For example, if the query information is a word group, the following steps may be performed: weather today, remaining costs, etc. If the query information is a sentence, for example: the flow is a package of 10G per month, and the like.
In an implementation manner, before the terminal sends the query information to the server, the query information may also be preprocessed, and the preprocessing manner is not limited in the embodiment of the present application. For example, when the user inputs the query information, the terminal may preliminarily determine whether the server can provide the query result corresponding to the query information. Specifically, the terminal may perform semantic recognition on the query information, thereby determining whether the query information is within the query range of the application. If the query information is in the query range of the application, the terminal sends the query information to the server, and if the query information is no longer in the query range of the application, the terminal displays prompt information to prompt a user that the query is failed.
S202, determining at least one keyword in the query information.
In this step, after receiving the query information sent by the terminal, the server may extract the keyword from the query information.
One or more keywords may be used, and the number of keywords is not limited in the embodiment of the present application.
It should be noted that, the embodiment of the present application does not limit how to determine the keywords in the query information. In one implementation, the query information may be subjected to a speech analysis, and at least one keyword is extracted from the query information according to semantics determined from the query information.
For example, if the query information is "the cheapest package", it may be determined through the speech analysis that the user wishes to query a package with a relatively low cost, and accordingly, the three keywords "cost", "lowest", "package" may be determined from the query information.
In another possible implementation manner, the query information may be segmented, and then the segmented query information is sequentially compared with preset words to determine whether the preset words or words agreed with the preset words exist in the query information, and if so, the preset words or words are used as the keywords.
For example, if the query message is "cheapest package," it may be split into "cheapest" and "package. After comparing with the preset words, the keywords in the query information can be determined as "lowest" and "package".
In addition, if it is determined that the query information does not include the keyword, in an implementation manner, the server may further send a prompt message to the terminal, so that the terminal prompts the user that the query fails by displaying the prompt message.
S203, acquiring a query result corresponding to the query information from the knowledge graph according to at least one keyword.
The knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model.
In this step, after the server determines at least one keyword from the query information, the keyword may be input into the knowledge graph, so that the knowledge graph inputs the query result corresponding to the query information according to the keyword.
The number of the query results is not limited in the embodiment of the present application.
In the prior art, the data set used to create a knowledge graph may include structured data and unstructured data. The data structure of unstructured data is irregular or incomplete, and data represented by two-dimensional logic of a database is inconvenient due to the fact that a preset data model is not available. Structured data, also referred to as row data, is data logically represented and implemented by a two-dimensional table structure, which strictly follows the data format and length specifications, and may be data in a database. In the process of establishing the knowledge graph, when a data set is extracted based on encyclopedia or vertical site extraction, rule and dictionary-based entity extraction, or a statistical machine learning-based entity, unstructured data can be extracted, and the problem of blindness and complexity exists in establishing the knowledge graph based on the unstructured data, so that the establishing efficiency of the knowledge graph is low.
In order to solve the above problem, in the process of establishing the knowledge graph used in the embodiment of the present application, unstructured data may be converted into structured data, so that the knowledge graph is not established directly by using the unstructured data.
Specifically, the unstructured data is converted into structured data, and the structured data can be generated by storing entities in the unstructured data according to element information in a knowledge template.
In addition, after the unstructured data are converted into structured data, the structured data can be matched with a map model, and therefore the knowledge map is established.
And S204, sending the query result to the terminal so that the terminal displays the query result.
If the number of the query results is one, the server can directly send the query results to the terminal, so that the terminal can display the query results for the user to check.
If there are a plurality of query results, in an implementation manner, the server may further rank the query results, and when the query results are sent to the terminal, the server may also send the rank, so that the terminal displays the query results in order. It should be noted that, the embodiment of the present application does not limit how to sort the query results.
Illustratively, after the server determines a plurality of query results from the knowledge graph, the server may also determine the number of queries corresponding to each query result, and rank the query results according to the number of queries from high to low.
According to the information query method provided by the embodiment of the application, the query information from the terminal is obtained, at least one keyword in the query information is determined, the query result corresponding to the query information is obtained from the knowledge graph according to the at least one keyword, and the query result is sent to the terminal, so that the terminal displays the query result. The knowledge graph is built by converting unstructured data to structured data and matching the structured data to a graph model. By the method, the query time can be reduced, and the accuracy of the query result can be improved.
The following is a detailed description of how the server builds the knowledge graph.
Fig. 3 is a schematic flowchart of another information query method according to an embodiment of the present application. The embodiment relates to a specific process of how the knowledge graph is established by the server. As shown in fig. 3, on the basis of fig. 2, the method includes:
s301, acquiring a data set corresponding to the knowledge graph to be created, wherein data in the data set comprises at least one entity.
The data set corresponding to the to-be-created knowledge graph may include data of a domain in which the to-be-created knowledge graph is located. The data set may include structured data or unstructured data.
In an implementation manner, after a data set corresponding to a knowledge graph to be created is obtained, data in the data set may be monitored, it is determined that the data in the data set includes at least one entity, and if it is determined that some data in the data set does not include an entity, the data is deleted.
S302, converting unstructured data in the data set into structured data.
In this step, a plurality of knowledge templates may be preset, and when the unstructured data in the data set is converted into structured data, the knowledge template corresponding to the unstructured data may be determined first.
The embodiment of the application is not limited to how to determine the knowledge template corresponding to the unstructured data, and in an implementation manner, the knowledge template may correspond to a data type, and the knowledge template corresponding to the data type may be determined according to the data type. In another possible embodiment, the knowledge template may also be determined by the server receiving an indication of the user.
After the knowledge template corresponding to the unstructured data is determined, entities in the unstructured data can be stored in the knowledge template according to element information in the knowledge template to generate structured data.
The element information comprises entity types, attributes of the entities and relationships among the entities.
In an alternative embodiment, when the structured data is generated, the related information of the unstructured data can be also entered in the knowledge template.
And S303, creating a knowledge graph according to the structured data.
The embodiment of the present application does not limit how to create the knowledge graph, and in an alternative implementation, the knowledge graph may be created by a graph template.
For example, the server may first retrieve the structured data and determine the type information of the structured data. Then, the server can determine a map template corresponding to the structured data from the pre-established map templates of the knowledge map according to the type information. And if the element information of the map model is the same as the element information of the knowledge template corresponding to the structured data, determining the structured data as an atom of the map model. And finally, importing the structured data into a map model to establish a knowledge map.
In an alternative embodiment, if the element information of the atlas model is identical to the element information of the knowledge template corresponding to the structured data, it is determined that the matching is successful. In another possible implementation manner, if the semantics of the element information of the atlas model and the semantics of the element information of the knowledge template corresponding to the structured data are the same, the atlas model and the knowledge template may also be considered to be the same, and it is determined that the matching is successful. The embodiment of the application does not limit the standard for determining that the element information is completely the same, and can be set according to specific situations.
In an alternative embodiment, before the structured data is imported into the graph model and the knowledge graph is established, the entity in the structured data and the entity in the graph model can be processed.
S304, acquiring the query information from the terminal.
S305, determining at least one keyword in the query information.
S306, acquiring a query result corresponding to the query information from a knowledge graph according to at least one keyword, wherein the knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model.
S307, sending the query result to the terminal so that the terminal displays the query result.
The technical terms, technical effects, technical features, and alternative embodiments of steps S304-S307 can be understood with reference to steps S201-S204 shown in fig. 2, and repeated content will not be described herein.
According to the information query method provided by the embodiment of the application, the query information from the terminal is obtained, at least one keyword in the query information is determined, the query result corresponding to the query information is obtained from the knowledge graph according to the at least one keyword, and the query result is sent to the terminal, so that the terminal displays the query result. The knowledge graph is built by converting unstructured data to structured data and matching the structured data to a graph model. By the method, the query time can be reduced, and the accuracy of the query result can be improved.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Fig. 4 is a schematic structural diagram of an information query apparatus according to an embodiment of the present application. The information inquiry device can be realized by software, hardware or a combination of the two, and can be the server.
As shown in fig. 4, the information inquiry apparatus includes:
a first obtaining module 41, configured to obtain query information from a terminal;
a determining module 42 for determining at least one keyword in the query information;
a result module 43, configured to obtain a query result corresponding to the query information from a knowledge graph according to the at least one keyword, where the knowledge graph is created by converting unstructured data into structured data and matching the structured data with a graph model;
and the sending module 44 is configured to send the query result to the terminal, so that the terminal displays the query result.
The information query device provided in the embodiment of the present application may perform the actions of the server in the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 5 is a schematic structural diagram of another information query device according to an embodiment of the present application. The information inquiry apparatus may be implemented by software, hardware or a combination of both, and may be the aforementioned server.
As shown in fig. 5, the information inquiry apparatus includes:
a second obtaining module 51, configured to obtain a data set corresponding to a knowledge graph to be created, where data in the data set includes at least one entity;
a conversion module 52, configured to convert unstructured data in the data set into structured data;
a creation module 53 for creating a knowledge graph from the structured data.
A first obtaining module 54, configured to obtain query information from a terminal;
a determining module 55 for determining at least one keyword in the query information;
a result module 56, configured to obtain a query result corresponding to the query information from a knowledge graph according to the at least one keyword, where the knowledge graph is created by converting unstructured data into structured data and matching the structured data with a graph model;
and a sending module 57, configured to send the query result to the terminal, so that the terminal displays the query result.
The conversion module 52 is specifically configured to determine a knowledge template corresponding to the unstructured data; and according to element information in the knowledge template, storing the entities in the unstructured data in the knowledge template to generate structured data, wherein the element information comprises entity types, entity attributes and relationships among the entities.
A creating module 53, specifically configured to determine type information of the structured data; determining a map template corresponding to the structured data according to the type information; if the element information of the map model is the same as the element information of the knowledge template corresponding to the structured data, determining the structured data as an atom of the map model; and importing the structured data into a map model to establish a knowledge map.
And the creating module 53 is further configured to process the entities in the structured data and the entities in the atlas model.
The information query device provided in the embodiment of the present application may perform the actions of the server in the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 6 is a schematic structural diagram of another information query device according to an embodiment of the present application. As shown in fig. 6, the information inquiry apparatus may include: at least one processor 61 and a memory 62. Fig. 6 shows an electronic device as an example of a processor.
And a memory 62 for storing programs. In particular, the program may include program code including computer operating instructions.
The memory 62 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 61 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement the embodiments of the present Application.
Alternatively, in a specific implementation, if the communication interface, the memory 62 and the processor 61 are implemented independently, the communication interface, the memory 62 and the processor 61 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. Buses may be classified as address buses, data buses, control buses, etc., but do not represent only one bus or type of bus.
Alternatively, in a specific implementation, if the communication interface, the memory 62 and the processor 61 are integrated into a chip, the communication interface, the memory 62 and the processor 61 may complete communication through an internal interface.
The present invention also provides a computer-readable storage medium, which may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and in particular, the computer-readable storage medium stores program instructions, and the program instructions are used in the method in the foregoing embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for querying information, comprising:
acquiring query information from a terminal;
determining at least one keyword in the query information;
acquiring a query result corresponding to the query information from a knowledge graph according to the at least one keyword, wherein the knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model;
sending the query result to the terminal so that the terminal displays the query result;
before the acquiring of the query information from the terminal, the method further includes:
acquiring a data set corresponding to a knowledge graph to be created, wherein data in the data set comprises at least one entity;
converting unstructured data in the data set into structured data;
creating the knowledge-graph from the structured data;
the creating the knowledge-graph from the structured data comprises:
determining type information of the structured data;
determining a map template corresponding to the structured data according to the type information;
if the element information of the map model is the same as the element information of the knowledge template corresponding to the structured data, determining that the structured data is an atom of the map model;
and importing the structured data into the map model to establish the knowledge map.
2. The method of claim 1, wherein transforming unstructured data in the data collection into structured data comprises:
determining a knowledge template corresponding to the unstructured data;
and storing the entities in the unstructured data in the knowledge template according to element information in the knowledge template to generate the structured data, wherein the element information comprises the entity types, the attributes of the entities and the relations among the entities.
3. The method of claim 1, wherein prior to said importing said structured data into said graph model, building said knowledge-graph, further comprises:
and processing the entities in the structured data and the entities in the atlas model.
4. An apparatus for querying information, comprising:
the first acquisition module is used for acquiring query information from a terminal;
a determining module, configured to determine at least one keyword in the query information;
the result module is used for acquiring a query result corresponding to the query information from a knowledge graph according to the at least one keyword, wherein the knowledge graph is established by converting unstructured data into structured data and matching the structured data with a graph model;
the sending module is used for sending the query result to the terminal so that the terminal can display the query result;
the second acquisition module is used for acquiring a data set corresponding to the knowledge graph to be created, wherein the data in the data set comprises at least one entity;
the conversion module is used for converting the unstructured data in the data set into structured data;
a creation module to create the knowledge-graph from the structured data;
the creation module is specifically configured to determine type information of the structured data; determining a map template corresponding to the structured data according to the type information; if the element information of the map model is the same as the element information of the knowledge template corresponding to the structured data, determining that the structured data is an atom of the map model; and importing the structured data into the map model to establish the knowledge map.
5. The apparatus according to claim 4, wherein the conversion module is specifically configured to determine a knowledge template corresponding to the unstructured data; and storing the entities in the unstructured data in the knowledge template according to element information in the knowledge template to generate the structured data, wherein the element information comprises the entity types, the attributes of the entities and the relations among the entities.
6. The apparatus of claim 4, wherein the creation module is further configured to process the entities in the structured data with the entities in the atlas model.
7. An electronic device, comprising: a memory and a processor;
the memory for storing executable instructions of the processor;
the processor is configured to perform the method of any of claims 1-3 via execution of the executable instructions.
8. A storage medium having a computer program stored thereon, comprising: the program when executed by a processor implements the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910801095.XA CN110502645B (en) | 2019-08-28 | 2019-08-28 | Information query method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910801095.XA CN110502645B (en) | 2019-08-28 | 2019-08-28 | Information query method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110502645A CN110502645A (en) | 2019-11-26 |
| CN110502645B true CN110502645B (en) | 2022-07-08 |
Family
ID=68589850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910801095.XA Active CN110502645B (en) | 2019-08-28 | 2019-08-28 | Information query method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110502645B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159467B (en) * | 2019-12-31 | 2022-05-10 | 青岛海信智慧家居系统股份有限公司 | Method and equipment for processing information interaction |
| CN111708898A (en) * | 2020-06-13 | 2020-09-25 | 广州华建工智慧科技有限公司 | Intelligent construction information transmission method and system based on knowledge graph |
| CN112182177A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | User problem processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| CN108829858A (en) * | 2018-06-22 | 2018-11-16 | 北京京东金融科技控股有限公司 | Data query method, apparatus and computer readable storage medium |
| CN109145003A (en) * | 2018-08-24 | 2019-01-04 | 蜜小蜂智慧（北京）科技有限公司 | A kind of method and device constructing knowledge mapping |
| CN109885698A (en) * | 2019-02-13 | 2019-06-14 | 北京航空航天大学 | A kind of knowledge mapping construction method and device, electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9037615B2 (en) * | 2010-05-14 | 2015-05-19 | International Business Machines Corporation | Querying and integrating structured and unstructured data |
-
2019
- 2019-08-28 CN CN201910801095.XA patent/CN110502645B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| CN108829858A (en) * | 2018-06-22 | 2018-11-16 | 北京京东金融科技控股有限公司 | Data query method, apparatus and computer readable storage medium |
| CN109145003A (en) * | 2018-08-24 | 2019-01-04 | 蜜小蜂智慧（北京）科技有限公司 | A kind of method and device constructing knowledge mapping |
| CN109885698A (en) * | 2019-02-13 | 2019-06-14 | 北京航空航天大学 | A kind of knowledge mapping construction method and device, electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110502645A (en) | 2019-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10489435B2 (en) | Method, device and equipment for acquiring answer information | |
| JP6647351B2 (en) | Method and apparatus for generating candidate response information | |
| CN110502645B (en) | Information query method and device | |
| CN109508352B (en) | Report data output method, device, equipment and storage medium | |
| US11934394B2 (en) | Data query method supporting natural language, open platform, and user terminal | |
| CN107680588B (en) | Intelligent voice navigation method, device and storage medium | |
| CN107798001B (en) | Webpage processing method, device and equipment | |
| CN107145784B (en) | Vulnerability scanning method and device and computer readable medium | |
| CN108664471B (en) | Character recognition error correction method, device, equipment and computer readable storage medium | |
| CN111694926A (en) | Interactive processing method and device based on scene dynamic configuration and computer equipment | |
| CN110399448B (en) | Chinese place name address searching and matching method, terminal and computer readable storage medium | |
| CN117076719B (en) | Database joint query method, device and equipment based on large language model | |
| US11163765B2 (en) | Non-transitory compuyer-read able storage medium, information output method, and information processing apparatus | |
| CN111488186A (en) | Data processing method and device, electronic equipment and computer storage medium | |
| CN113127125B (en) | Page automatic adaptation method, device, equipment and storage medium | |
| CN112698818A (en) | Point exchange method and device based on activity page and point exchange system | |
| CN110442696B (en) | Query processing method and device | |
| WO2017133171A1 (en) | Information pushing method and device | |
| CN116996601A (en) | Message format conversion method and device, electronic equipment and storage medium | |
| CN107679055B (en) | Information retrieval method, server and readable storage medium | |
| CN116151240A (en) | Relation extraction model training method and device, electronic equipment and storage medium | |
| CN113220949B (en) | Construction method and device of private data identification system | |
| WO2015010386A1 (en) | Document format conversion device and document format conversion method | |
| WO2021135103A1 (en) | Method and apparatus for semantic analysis, computer device, and storage medium | |
| CN110705275A (en) | Theme word extraction method and device, storage medium and electronic equipment |
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 |