CN112182174A - Business question-answer knowledge query method and device, computer equipment and storage medium - Google Patents
Business question-answer knowledge query method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112182174A CN112182174A CN202011014031.4A CN202011014031A CN112182174A CN 112182174 A CN112182174 A CN 112182174A CN 202011014031 A CN202011014031 A CN 202011014031A CN 112182174 A CN112182174 A CN 112182174A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- question
- answer
- user data
- data
- 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 55
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012015 optical character recognition Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 17
- 230000004888 barrier function Effects 0.000 abstract description 6
- 238000010276 construction Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 7
- 238000012790 confirmation Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a method and a device for inquiring business question-answer knowledge, computer equipment and a storage medium. The method comprises the following steps: receiving a data query request, and extracting user data carried in the data query request; searching a target service node corresponding to the user data in a preset knowledge graph; determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph; and obtaining question-answer knowledge corresponding to the data query operation according to the knowledge nodes. The information barrier between the question and answer knowledge and the user data is opened, so that the question and answer knowledge can be searched through the preset knowledge map, the question and answer knowledge corresponding to the user data can be synchronously obtained in the process of inquiring and searching the user data, and the speed of processing the service is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for querying knowledge about service question answering, a computer device, and a storage medium.
Background
In daily business, customer service often handles customer's needs according to certain flow, and these needs divide into two parts: user data and knowledge points.
And in a user database related to the user data, the customer service determines the service to be inquired or transacted according to the confidential information provided by the client, such as an identity card number, an equipment number and a bound mobile phone number. The customer service confirms the related content according to the questions put forward by the user, which is related to the service proficiency of the customer service and needs to search answers step by step in the confirmation process.
In the process of serving the user by the customer service, the answer searching process can slow down the speed of processing the service by the customer service.
Disclosure of Invention
In view of the above, it is necessary to provide a service question and answer knowledge query method, device, computer device and storage medium capable of improving the speed of customer service processing service.
A business question-answer knowledge query method comprises the following steps:
receiving a data query request, and extracting user data carried in the data query request;
searching a target service node corresponding to the user data in a preset knowledge graph;
determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph;
and obtaining question-answer knowledge corresponding to the data query operation according to the knowledge nodes.
In one embodiment, before searching for a target service node corresponding to user data in a preset knowledge graph, the method further includes:
acquiring a first knowledge graph constructed based on question and answer knowledge and a second knowledge graph constructed based on user data;
performing data association matching on the question and answer knowledge and the user data, and screening out target question and answer knowledge and target user data which are successfully associated;
determining a knowledge node corresponding to target question-answering data in a first knowledge graph and a service node corresponding to target user data in a second knowledge graph;
and performing node communication on the first knowledge graph and the second knowledge graph according to the knowledge nodes and the service nodes to construct and obtain a preset knowledge graph.
In one embodiment, before obtaining the first knowledge-graph constructed based on the question-answering knowledge and the second knowledge-graph constructed based on the user data, the method further comprises the following steps:
acquiring question and answer knowledge in a knowledge base, and determining knowledge points corresponding to the question and answer knowledge;
identifying the incidence relation among knowledge points according to the storage position relation of the question and answer knowledge in the knowledge base to obtain a knowledge point triple;
and constructing to obtain a first knowledge graph according to the knowledge point triple.
In one embodiment, the obtaining of question and answer knowledge in the knowledge base and the determining of knowledge points corresponding to the question and answer knowledge comprise:
acquiring question-answer knowledge in a text format and question-answer knowledge in an image format in a knowledge base;
carrying out optical character recognition processing on the question-answer knowledge in the image format so as to convert the question-answer knowledge in the image format into question-answer knowledge in a text format;
and determining knowledge points corresponding to the data to be processed according to the knowledge types corresponding to the data to be processed by taking the obtained question-answer knowledge in the text format and the converted question-answer knowledge in the text format as the data to be processed.
In one embodiment, a triple of knowledge points includes a head entity, a relationship, and a tail entity;
according to the knowledge point triple, the step of constructing and obtaining the first knowledge graph comprises the following steps:
and importing the knowledge point triple into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and taking the relation as a node association relation, and constructing to obtain a first knowledge graph.
In one embodiment, before obtaining the first knowledge-graph constructed based on the question-answering knowledge and the second knowledge-graph constructed based on the user data, the method further comprises the following steps:
acquiring a data table from a relational database, wherein the data table is used for storing user data;
obtaining a user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located;
and constructing and obtaining a second knowledge graph according to the user data triple.
In one embodiment, the searching for the target service node corresponding to the user data in the preset knowledge graph includes:
extracting service requirements in the data query request, and searching nodes matched with user data in a preset knowledge graph;
and searching a target service node matched with the service requirement based on the node matched with the user data and the node incidence relation.
A business question-answer knowledge inquiry device comprises:
the request receiving module is used for receiving the data query request and extracting the user data carried in the data query request;
the node searching module is used for searching a target service node corresponding to the user data in a preset knowledge graph;
the node determination module is used for determining a knowledge node associated with the target service node according to the target service node and the association relation between the knowledge node and the service node in the preset knowledge graph;
and the data determining module is used for obtaining question and answer knowledge corresponding to the data query operation according to the knowledge nodes.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
receiving a data query request, and extracting user data carried in the data query request;
searching a target service node corresponding to the user data in a preset knowledge graph;
determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph;
and obtaining question-answer knowledge corresponding to the data query operation according to the knowledge nodes.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
receiving a data query request, and extracting user data carried in the data query request;
searching a target service node corresponding to the user data in a preset knowledge graph;
determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph;
and obtaining question-answer knowledge corresponding to the data query operation according to the knowledge nodes.
The service question-answer knowledge query method, the service question-answer knowledge query device, the computer equipment and the storage medium receive the data query request, extract user data carried in the data query request, associate the data query operation with the preset knowledge map based on a target service node corresponding to the user data in the preset knowledge map, and get through an information barrier between the question-answer knowledge and the user data based on the preset knowledge map comprising the knowledge node and the service node to realize the search of the question-answer knowledge through the preset knowledge map, so that the question-answer knowledge corresponding to the user data can be synchronously obtained in the query search process of the user data, and the service processing speed is improved.
Drawings
FIG. 1 is a diagram of an application environment of a business question and answer knowledge query method in one embodiment;
FIG. 2 is a flow diagram of a business question and answer knowledge query method in one embodiment;
FIG. 3 is a schematic flow chart illustrating construction of a predetermined knowledge graph in the business question-answer knowledge query method according to an embodiment;
FIG. 4 is a schematic flow chart illustrating construction of a first knowledge graph in the business question-answer knowledge query method in one embodiment;
FIG. 5 is a schematic flow chart illustrating construction of a second knowledge graph in the business question-answer knowledge query method in one embodiment;
FIG. 6 is a diagram illustrating a preset knowledge graph in a business question-answer knowledge query method according to an embodiment;
FIG. 7 is a flow diagram of a business question and answer knowledge query method in another embodiment;
FIG. 8 is a block diagram of an embodiment of a business question and answer knowledge query device;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The business question-answer knowledge query method provided by the application can be applied to the application environment shown in figure 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 responds to a data query request sent by a customer service worker through a data query operation triggered by the terminal 102, and extracts user data carried in the data query request; searching a target service node corresponding to the user data in a preset knowledge graph; determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph; and obtaining question and answer knowledge corresponding to the data query operation according to the knowledge nodes, and pushing the question and answer knowledge to the terminal 102 where the customer service staff is located. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for querying knowledge about service question answering is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The data query request refers to a data processing request sent by the terminal to the server, and the server feeds corresponding data back to the terminal through data processing based on the data query request to complete data interaction between the terminal and the server. In an embodiment, the data query request may be a request triggered by a customer service staff through a terminal operation according to a customer service requirement.
The user data refers to data for characterizing the business object, and specifically, the user data may be user identity information, device information, and the like. It can be understood that, in some application scenarios, the user identity information and the device information are associated, for example, the attribution or management object of a certain device is a certain user, and the customer service staff may determine, based on the user identity information, each device managed by the user through the management data in the background, and may also determine, based on the device information, such as a telephone number, the user identity information of the user to which the device information belongs.
For example, in the power industry, when a customer calls for a consultation, the customer service staff is informed of the service to be consulted and the user data corresponding to the service. And the customer service personnel operates and processes the terminal based on the information provided by the client to determine the specific information of the service corresponding to the user data and reply the related consultation problem of the user according to the specific information.
And step 204, searching a target service node corresponding to the user data in the preset knowledge graph.
The preset knowledge graph refers to a pre-constructed knowledge graph stored in the server, and the preset knowledge graph comprises service nodes corresponding to the user data. A knowledge graph is a graph that sets forth relationships between various entities that exist, between relationships, and between entities and attributes of relationships. The entity is the most basic element in the knowledge graph, and different relationships exist among different entities. A knowledge graph may be constructed based on triples, i.e., head entities, relationships, and tail entities. By taking the essence of the knowledge graph, the knowledge graph is also a simple heterogeneous network, the relation in the triples is used for describing the specific relation between the head entity and the tail entity, and the main realization aim is to improve a search engine so as to improve the accuracy of the search result and the search experience of the user.
In the embodiment, the server performs node search in a preset knowledge graph by extracting user data carried in the data query request and taking the user data as a search keyword to obtain a node matched with the user data, and then determines a target service node according to the node matched with the user data and a service requirement by extracting the service requirement in the data query request.
And step 206, determining the knowledge node associated with the target service node according to the target service node and the association relationship between the knowledge node and the service node in the preset knowledge graph.
The preset knowledge graph is formed by fusing a first knowledge graph containing knowledge nodes and a second knowledge graph containing service nodes, and the service nodes and the knowledge nodes are communicated and have an association relation in the preset knowledge graph. And determining the knowledge node associated with the target service node according to the association relationship between the knowledge node and the service node.
And step 208, obtaining question and answer knowledge corresponding to the data query operation according to the knowledge nodes.
The knowledge node corresponds to the question-answer knowledge direction, the question-answer knowledge corresponding to the knowledge node can be obtained based on the determined knowledge node, and the question-answer knowledge is pushed to a sending terminal of data query operation, so that customer service staff of the sending terminal can synchronously obtain the question-answer knowledge corresponding to the service data based on the data query operation.
In an embodiment, the question-answer knowledge includes service-related paraphrases corresponding to the service nodes, and the like. For example, in the prior art, the data related to the user is stored in a user database, and the customer service determines the service to be inquired or transacted according to the confidential information provided by the client, such as an identity card number, an electricity meter number, and a bound mobile phone number; the relevant knowledge points are stored in a knowledge base, and the customer service confirms relevant contents according to questions put forward by a user, which is related to the service proficiency of the customer service and requires the customer service to search answers step by step in the confirmation process. When the customer consultation is asked and answered, customer service staff need to switch among different systems, the service efficiency is seriously influenced, and the service experience of the customer is reduced.
Therefore, the user data in the user database and the question and answer knowledge in the knowledge base are communicated through the fusion of the knowledge base through the knowledge base, so that the customer service staff can obtain corresponding knowledge points while determining the services to be inquired or transacted by the customer, answers do not need to be obtained based on search operation again, and the question and answer efficiency is improved.
The service question-answer knowledge query method receives a data query request, extracts user data carried in the data query request, associates data query operation with a preset knowledge graph based on a target service node corresponding to the user data in the preset knowledge graph, and puts through an information barrier between question-answer knowledge and the user data based on the preset knowledge graph comprising the knowledge node and the service node to realize the search of the question-answer knowledge through the preset knowledge graph, so that the question-answer knowledge corresponding to the user data can be synchronously obtained in the query search process of the user data, and the service processing speed is improved.
In one embodiment, as shown in fig. 3, before searching for a target service node corresponding to user data in a preset knowledge graph, that is, before step 204, a construction process of the preset knowledge graph is further included, specifically including steps 302 to 308.
And 304, performing data association matching on the question and answer knowledge and the user data, and screening out target question and answer knowledge and target user data which are successfully associated.
And 308, performing node communication on the first knowledge graph and the second knowledge graph according to the knowledge nodes and the service nodes to construct a preset knowledge graph.
The first knowledge graph is a knowledge graph which is constructed based on question and answer knowledge and is used for representing the association relation between the knowledge points corresponding to the question and answer knowledge. The second knowledge graph is a knowledge graph which is constructed based on the user data and used for representing the association relation between the corresponding services of the user data.
The knowledge points corresponding to the question and answer knowledge are actually knowledge points related to the business and are used for explaining a specific business. By performing data association matching on the knowledge points corresponding to the question and answer knowledge and the service types corresponding to the user data, the corresponding relation between the question and answer knowledge and the user data can be determined.
Further, the knowledge points corresponding to the question and answer knowledge may be subjected to data association matching with the service types corresponding to the user data in a manner of keyword matching of the knowledge points with the services or calculation of similarity of description information.
Through data association matching, a data group formed by the target question-answer knowledge and the target user data which are successfully associated can be screened out. According to the knowledge node corresponding to the target question-answer data in the first knowledge graph and the service node corresponding to the target user data in the second knowledge graph, the node communication between the first knowledge graph and the second knowledge graph can be achieved, and the first knowledge graph and the second knowledge graph are fused to obtain the preset knowledge graph.
In an embodiment, the same user data may correspond to a plurality of question-answer knowledge, constituting a plurality of data sets. Similarly, when the nodes of the first knowledge graph and the second knowledge graph are associated, the service node corresponding to the user data and each knowledge node corresponding to a plurality of question and answer knowledge can be associated, so that the question and answer knowledge corresponding to the plurality of knowledge nodes can be obtained when the data is inquired, and the customer service staff can select the question and answer knowledge.
In one embodiment, as shown in fig. 4, the first knowledge-graph constructed based on question-answering knowledge and the second knowledge-graph constructed based on user data are obtained, that is, step 302 is preceded by a first knowledge-graph construction process, specifically including steps 402 to 406.
And step 404, identifying the association relation among the knowledge points according to the storage position relation of the question-answer knowledge in the knowledge base to obtain the knowledge point triple.
And 406, constructing to obtain a first knowledge graph according to the knowledge point triple.
Various question and answer knowledge related to the business is stored in the knowledge base, the question and answer knowledge corresponds to the knowledge points, in the embodiment, one knowledge point can correspond to a plurality of question and answer knowledge, and one question and answer knowledge can also correspond to a plurality of knowledge points. The storage position relation in the knowledge base is used for representing the incidence relation between question answering knowledge,
the question-answer knowledge in the knowledge base is generally subordinative knowledge points or information stored in a table form, has a certain relation representation mode, and converts each knowledge point into a knowledge point triple by presetting a conversion script corresponding to a storage mode. The knowledge point triple refers to a data description mode for describing any two knowledge points and the association relationship thereof. Based on the knowledge point triples, the first knowledge graph which takes the knowledge points as nodes and takes the association relationship among the knowledge points as the association relationship among the nodes can be obtained through accurate positioning.
In one embodiment, the obtaining of question and answer knowledge in the knowledge base and the determining of knowledge points corresponding to the question and answer knowledge comprise: and acquiring the question-answer knowledge in the text format and the question-answer knowledge in the image format in the knowledge base. And carrying out optical character recognition processing on the question-answer knowledge in the image format so as to convert the question-answer knowledge in the image format into question-answer knowledge in a text format. And determining knowledge points corresponding to the data to be processed according to the knowledge types corresponding to the data to be processed by taking the obtained question-answer knowledge in the text format and the converted question-answer knowledge in the text format as the data to be processed.
The knowledge base comprises question and answer knowledge in text format and question and answer knowledge in image format, such as answer flow chart and explanatory picture. The question-answering knowledge in the image format can be set at a corresponding knowledge point according to the context by converting an image into a corresponding text in a manner of an OCR (Optical Character Recognition, specifying a process of inspecting characters printed on paper by an electronic device, determining the shape of the characters by detecting dark and light patterns, and translating the shape into computer characters by a Character Recognition method) and the like.
In one embodiment, a triple of knowledge points includes a head entity, a relationship, and a tail entity. According to the knowledge point triple, the step of constructing and obtaining the first knowledge graph comprises the following steps: and importing the knowledge point triple into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and taking the relation as a node association relation, and constructing to obtain a first knowledge graph.
The knowledge point triplets and the user data triplets are triplets including a head entity, a relationship, and a tail entity. Taking the triple of knowledge points as an example, the triple of knowledge points is imported into a preset initial knowledge map by taking a head entity and a tail entity as nodes and taking a relation as a node incidence relation, so as to construct and obtain a first knowledge map. Taking the user data triple as an example, the user data triple is led into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and taking the relation as a node incidence relation, and a second knowledge graph is constructed and obtained.
By predetermining the triples, the incidence relation between every two data can be accurately described, and the corresponding knowledge graph can be conveniently and quickly and accurately constructed.
In one embodiment, as shown in fig. 5, the first knowledge-graph constructed based on question-answering knowledge and the second knowledge-graph constructed based on user data are obtained, that is, step 302 further includes a first knowledge-graph construction process, specifically including steps 502 to 506.
And step 504, obtaining the user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located.
A relational database refers to a database that uses a relational model to organize data, and stores data in rows and columns for a user to understand, and a series of rows and columns of the relational database are called tables, and a set of tables constitutes the database. A user retrieves data in a database by a query, which is an executable code that defines certain areas in the database. The relational model can be simply understood as a two-dimensional table model, and a relational database is a data organization composed of two-dimensional tables and relations between them.
In particular, the data table is used to store user data. And the server obtains the user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located. And constructing and obtaining a second knowledge graph according to the user data triples based on the same manner of the knowledge point triples. The user data are stored on the basis of the relational database, the incidence relation among the user data can be conveniently and quickly determined, the user data triple can be conveniently and quickly constructed, and the construction efficiency of the second knowledge graph is improved.
In the embodiment, as shown in fig. 6, the user data is divided and associated mainly according to three types of entities, i.e., users, devices, and services. The knowledge graph of the knowledge base is divided into service knowledge and document knowledge according to the types of the knowledge, each type has respective three-level nodes, service type-sub service type-subdivision service type, document type-sub document type-document). The customer service is supposed to answer the content in the service, so that the service class of the service corresponding to the user data is associated with the subdivided service class/document of the knowledge base, and the corresponding content can be quickly retrieved.
In one embodiment, as shown in fig. 7, step 204 of finding the corresponding target service node of the user data in the preset knowledge graph includes steps 702 to 704.
In an embodiment, the service requirement in the data query request may be determined based on a user operation of the terminal response, such as a click operation of a customer service person. Based on the service requirement, the service requirement can be determined, in the preset knowledge graph, the node matched with the user data is uniquely determined, for example, the node corresponding to the user name is determined, but the number of other nodes associated with the user data is large, and after the service requirement is determined, a target service node matched with the service requirement can be screened out from the nodes with the association relation based on the other nodes associated with the user data, so that the accurate positioning of the target service node is realized.
It should be understood that, although the steps in the flowcharts are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in each of the flowcharts described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In one embodiment, as shown in fig. 8, there is provided a business question-answer knowledge inquiry apparatus, including: a request receiving module 802, a node lookup module 804, a node determination module 806, and a data determination module 808, wherein:
the request receiving module 802 is configured to receive a data query request and extract user data carried in the data query request.
The node searching module 804 is configured to search a target service node corresponding to the user data in the preset knowledge graph.
The node determining module 806 is configured to determine a knowledge node associated with the target service node according to the target service node and an association relationship between the knowledge node and the service node in the preset knowledge graph.
And the data determining module 808 is configured to obtain question-answer knowledge corresponding to the data query operation according to the knowledge node.
In one embodiment, the service question-answer knowledge query device further comprises a preset knowledge graph construction module, a query module and a query module, wherein the preset knowledge graph construction module is used for acquiring a first knowledge graph constructed based on question-answer knowledge and a second knowledge graph constructed based on user data; performing data association matching on the question and answer knowledge and the user data, and screening out target question and answer knowledge and target user data which are successfully associated; determining a knowledge node corresponding to target question-answering data in a first knowledge graph and a service node corresponding to target user data in a second knowledge graph; and performing node communication on the first knowledge graph and the second knowledge graph according to the knowledge nodes and the service nodes to construct and obtain a preset knowledge graph.
In one embodiment, the service question-answer knowledge query device further comprises a first knowledge graph construction module, which is used for acquiring question-answer knowledge in a knowledge base and determining knowledge points corresponding to the question-answer knowledge; identifying the incidence relation among knowledge points according to the storage position relation of the question and answer knowledge in the knowledge base to obtain a knowledge point triple; and constructing to obtain a first knowledge graph according to the knowledge point triple.
In one embodiment, the first knowledge graph building module is further used for acquiring question and answer knowledge in a text format and question and answer knowledge in an image format in a knowledge base; carrying out optical character recognition processing on the question-answer knowledge in the image format so as to convert the question-answer knowledge in the image format into question-answer knowledge in a text format; and determining knowledge points corresponding to the data to be processed according to the knowledge types corresponding to the data to be processed by taking the obtained question-answer knowledge in the text format and the converted question-answer knowledge in the text format as the data to be processed.
In one embodiment, a triple of knowledge points includes a head entity, a relationship, and a tail entity; the first knowledge graph building module is further used for leading the triple of the knowledge points into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and taking the relation as a node incidence relation, and building the first knowledge graph.
In one embodiment, the service question-answering knowledge inquiry device further comprises a second knowledge graph construction module, which is used for acquiring a data table from a relational database, wherein the data table is used for storing user data; obtaining a user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located; and constructing and obtaining a second knowledge graph according to the user data triple.
In one embodiment, the node searching module is further configured to extract a service requirement in the data query request, and search a node matching the user data in a preset knowledge graph; and searching a target service node matched with the service requirement based on the node matched with the user data and the node incidence relation.
The service question-answer knowledge inquiry device receives the data inquiry request, extracts the user data carried in the data inquiry request, associates the data inquiry operation with the preset knowledge map based on the target service node corresponding to the user data in the preset knowledge map, and puts through an information barrier between the question-answer knowledge and the user data based on the preset knowledge map comprising the knowledge node and the service node so as to search the question-answer knowledge through the preset knowledge map, and can synchronously obtain the question-answer knowledge corresponding to the user data in the inquiry and search process of the user data so as to improve the speed of processing the service.
For the specific limitation of the knowledge query device for service question answering, reference may be made to the above limitation of the knowledge query method for service question answering, and details are not described herein again. All or part of the modules in the service question-answering knowledge inquiry device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing a preset knowledge map and question and answer knowledge. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a business question-answer knowledge query method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
receiving a data query request, and extracting user data carried in the data query request; finding a target service node corresponding to the user data in a preset knowledge graph; determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph; and obtaining question-answer knowledge corresponding to the data query operation according to the knowledge nodes.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a first knowledge graph constructed based on question and answer knowledge and a second knowledge graph constructed based on user data; performing data association matching on the question and answer knowledge and the user data, and screening out target question and answer knowledge and target user data which are successfully associated; determining a knowledge node corresponding to target question-answering data in a first knowledge graph and a service node corresponding to target user data in a second knowledge graph; and performing node communication on the first knowledge graph and the second knowledge graph according to the knowledge nodes and the service nodes to construct and obtain a preset knowledge graph.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring question and answer knowledge in a knowledge base, and determining knowledge points corresponding to the question and answer knowledge; identifying the incidence relation among knowledge points according to the storage position relation of the question and answer knowledge in the knowledge base to obtain a knowledge point triple; and constructing to obtain a first knowledge graph according to the knowledge point triple.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring question-answer knowledge in a text format and question-answer knowledge in an image format in a knowledge base; carrying out optical character recognition processing on the question-answer knowledge in the image format so as to convert the question-answer knowledge in the image format into question-answer knowledge in a text format; and determining knowledge points corresponding to the data to be processed according to the knowledge types corresponding to the data to be processed by taking the obtained question-answer knowledge in the text format and the converted question-answer knowledge in the text format as the data to be processed.
In one embodiment, a triple of knowledge points includes a head entity, a relationship, and a tail entity. The processor, when executing the computer program, further performs the steps of:
and importing the knowledge point triple into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and taking the relation as a node association relation, and constructing to obtain a first knowledge graph.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a data table from a relational database, wherein the data table is used for storing user data; obtaining a user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located; and constructing and obtaining a second knowledge graph according to the user data triple.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
extracting service requirements in the data query request, and searching nodes matched with user data in a preset knowledge graph; and searching a target service node matched with the service requirement based on the node matched with the user data and the node incidence relation.
The computer equipment for realizing the service question and answer knowledge query method receives the data query request, extracts user data carried in the data query request, associates the data query operation with the preset knowledge graph based on a target service node corresponding to the user data in the preset knowledge graph, and puts through an information barrier between question and answer knowledge and the user data based on the preset knowledge graph comprising the knowledge node and the service node to realize the search of the question and answer knowledge through the preset knowledge graph, and can synchronously obtain the question and answer knowledge corresponding to the user data in the query search process of the user data to improve the speed of processing the service.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving a data query request, and extracting user data carried in the data query request; finding a target service node corresponding to the user data in a preset knowledge graph; determining a knowledge node associated with a target service node according to the target service node and an association relation between the knowledge node and the service node in a preset knowledge graph; and obtaining question-answer knowledge corresponding to the data query operation according to the knowledge nodes.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a first knowledge graph constructed based on question and answer knowledge and a second knowledge graph constructed based on user data; performing data association matching on the question and answer knowledge and the user data, and screening out target question and answer knowledge and target user data which are successfully associated; determining a knowledge node corresponding to target question-answering data in a first knowledge graph and a service node corresponding to target user data in a second knowledge graph; and performing node communication on the first knowledge graph and the second knowledge graph according to the knowledge nodes and the service nodes to construct and obtain a preset knowledge graph.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring question and answer knowledge in a knowledge base, and determining knowledge points corresponding to the question and answer knowledge; identifying the incidence relation among knowledge points according to the storage position relation of the question and answer knowledge in the knowledge base to obtain a knowledge point triple; and constructing to obtain a first knowledge graph according to the knowledge point triple.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring question-answer knowledge in a text format and question-answer knowledge in an image format in a knowledge base; carrying out optical character recognition processing on the question-answer knowledge in the image format so as to convert the question-answer knowledge in the image format into question-answer knowledge in a text format; and determining knowledge points corresponding to the data to be processed according to the knowledge types corresponding to the data to be processed by taking the obtained question-answer knowledge in the text format and the converted question-answer knowledge in the text format as the data to be processed.
In one embodiment, a triple of knowledge points includes a head entity, a relationship, and a tail entity. The computer program when executed by the processor further realizes the steps of:
and importing the knowledge point triple into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and taking the relation as a node association relation, and constructing to obtain a first knowledge graph.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a data table from a relational database, wherein the data table is used for storing user data; obtaining a user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located; and constructing and obtaining a second knowledge graph according to the user data triple.
In one embodiment, the computer program when executed by the processor further performs the steps of:
extracting service requirements in the data query request, and searching nodes matched with user data in a preset knowledge graph; and searching a target service node matched with the service requirement based on the node matched with the user data and the node incidence relation.
The computer-readable storage medium for implementing the service question and answer knowledge query method receives the data query request, extracts user data carried in the data query request, associates the data query operation with the preset knowledge graph based on a target service node corresponding to the user data in the preset knowledge graph, and gets through an information barrier between question and answer knowledge and the user data based on the preset knowledge graph comprising the knowledge node and the service node to realize the search of the question and answer knowledge through the preset knowledge graph, so that the question and answer knowledge corresponding to the user data can be synchronously obtained in the query search process of the user data, and the service processing speed is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for querying knowledge of a service question and answer is characterized by comprising the following steps:
receiving a data query request, and extracting user data carried in the data query request;
searching a target service node corresponding to the user data in a preset knowledge graph;
determining a knowledge node associated with the target service node according to the target service node and an association relation between the knowledge node and the service node in the preset knowledge graph;
and obtaining question and answer knowledge corresponding to the data query operation according to the knowledge nodes.
2. The method of claim 1, wherein the searching for the corresponding target service node of the user data in the preset knowledge-graph further comprises:
acquiring a first knowledge graph constructed based on question and answer knowledge and a second knowledge graph constructed based on user data;
performing data association matching on the question and answer knowledge and the user data, and screening out target question and answer knowledge and target user data which are successfully associated;
determining a knowledge node corresponding to the target question-answering data in the first knowledge graph and a service node corresponding to the target user data in the second knowledge graph;
and performing node communication on the first knowledge graph and the second knowledge graph according to the knowledge nodes and the service nodes to construct and obtain the preset knowledge graph.
3. The method of claim 2, wherein obtaining the first knowledge-graph constructed based on question and answer knowledge and the second knowledge-graph constructed based on user data is preceded by:
acquiring question and answer knowledge in a knowledge base, and determining knowledge points corresponding to the question and answer knowledge;
identifying the incidence relation among the knowledge points according to the storage position relation of the question-answer knowledge in the knowledge base to obtain a knowledge point triple;
and constructing and obtaining the first knowledge graph according to the knowledge point triple.
4. The method according to claim 3, wherein the obtaining of question and answer knowledge in a knowledge base and the determining of knowledge points corresponding to the question and answer knowledge comprise:
acquiring question-answer knowledge in a text format and question-answer knowledge in an image format in a knowledge base;
carrying out optical character recognition processing on the question-answer knowledge in the image format so as to convert the question-answer knowledge in the image format into question-answer knowledge in a text format;
and determining knowledge points corresponding to the data to be processed according to the knowledge types corresponding to the data to be processed by taking the obtained question-answer knowledge in the text format and the converted question-answer knowledge in the text format as the data to be processed.
5. The method of claim 3, wherein the triple of knowledge points comprises a head entity, a relationship, and a tail entity;
the constructing and obtaining the first knowledge graph according to the triple of knowledge points comprises:
and importing the knowledge point triple into a preset initial knowledge graph by taking the head entity and the tail entity as nodes and the relation as a node incidence relation, and constructing to obtain the first knowledge graph.
6. The method of claim 2, wherein obtaining the first knowledge-graph constructed based on question and answer knowledge and the second knowledge-graph constructed based on user data is preceded by:
acquiring a data table from a relational database, wherein the data table is used for storing user data;
obtaining a user data triple according to the incidence relation of the data table in the relational database and the data table where the user data is located;
and constructing and obtaining the second knowledge graph according to the user data triple.
7. The method of claim 6, wherein the searching for the target service node corresponding to the user data in the predetermined knowledge-graph comprises:
extracting service requirements in the data query request, and searching nodes matched with the user data in a preset knowledge graph;
and searching a target service node matched with the service requirement based on the node matched with the user data and the node incidence relation.
8. A business question-answering knowledge inquiry apparatus, comprising:
the request receiving module is used for receiving a data query request and extracting user data carried in the data query request;
the node searching module is used for searching a target service node corresponding to the user data in a preset knowledge graph;
a node determination module, configured to determine a knowledge node associated with the target service node according to the target service node and an association relationship between the knowledge node and the service node in the preset knowledge graph;
and the data determining module is used for obtaining question and answer knowledge corresponding to the data query operation according to the knowledge nodes.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011014031.4A CN112182174A (en) | 2020-09-24 | 2020-09-24 | Business question-answer knowledge query method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011014031.4A CN112182174A (en) | 2020-09-24 | 2020-09-24 | Business question-answer knowledge query method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112182174A true CN112182174A (en) | 2021-01-05 |
Family
ID=73955433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011014031.4A Pending CN112182174A (en) | 2020-09-24 | 2020-09-24 | Business question-answer knowledge query method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112182174A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407730A (en) * | 2021-05-28 | 2021-09-17 | 北京小米移动软件有限公司 | Knowledge graph-based question and answer method and device and computer readable storage medium |
| CN113742474A (en) * | 2021-11-08 | 2021-12-03 | 北京博瑞彤芸科技股份有限公司 | Intelligent question and answer method and device based on knowledge graph |
| CN114090752A (en) * | 2021-11-17 | 2022-02-25 | 中国建设银行股份有限公司 | Problem thread mining method, device, computer equipment and medium |
| CN117669713A (en) * | 2024-01-31 | 2024-03-08 | 宁德时代新能源科技股份有限公司 | Battery information processing method, device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543019A (en) * | 2018-11-27 | 2019-03-29 | 苏州思必驰信息科技有限公司 | Dialogue service method and device for vehicle |
| CN110119463A (en) * | 2019-04-04 | 2019-08-13 | 厦门快商通信息咨询有限公司 | Information processing method, device, equipment and storage medium |
| CN110866122A (en) * | 2019-10-10 | 2020-03-06 | 青岛聚好联科技有限公司 | Method and device for mapping entity words based on knowledge graph |
| CN111090739A (en) * | 2019-10-30 | 2020-05-01 | 贝壳技术有限公司 | Information processing method, information processing device, electronic device, and storage medium |
| CN111177400A (en) * | 2019-12-05 | 2020-05-19 | 国网能源研究院有限公司 | Associated display method and device of equipment, service and data based on knowledge graph |
| CN111522927A (en) * | 2020-04-15 | 2020-08-11 | 北京百度网讯科技有限公司 | Entity query method and device based on knowledge graph |
-
2020
- 2020-09-24 CN CN202011014031.4A patent/CN112182174A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543019A (en) * | 2018-11-27 | 2019-03-29 | 苏州思必驰信息科技有限公司 | Dialogue service method and device for vehicle |
| CN110119463A (en) * | 2019-04-04 | 2019-08-13 | 厦门快商通信息咨询有限公司 | Information processing method, device, equipment and storage medium |
| CN110866122A (en) * | 2019-10-10 | 2020-03-06 | 青岛聚好联科技有限公司 | Method and device for mapping entity words based on knowledge graph |
| CN111090739A (en) * | 2019-10-30 | 2020-05-01 | 贝壳技术有限公司 | Information processing method, information processing device, electronic device, and storage medium |
| CN111177400A (en) * | 2019-12-05 | 2020-05-19 | 国网能源研究院有限公司 | Associated display method and device of equipment, service and data based on knowledge graph |
| CN111522927A (en) * | 2020-04-15 | 2020-08-11 | 北京百度网讯科技有限公司 | Entity query method and device based on knowledge graph |
Non-Patent Citations (1)
| Title |
|---|
| 贾李蓉 等: "基于中医药学语言***的知识问答***的设计与构建", 《中华医学图书情报杂志》, vol. 28, no. 5, pages 11 - 14 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407730A (en) * | 2021-05-28 | 2021-09-17 | 北京小米移动软件有限公司 | Knowledge graph-based question and answer method and device and computer readable storage medium |
| CN113407730B (en) * | 2021-05-28 | 2024-03-12 | 北京小米移动软件有限公司 | Knowledge graph-based question-answering method and device and computer-readable storage medium |
| CN113742474A (en) * | 2021-11-08 | 2021-12-03 | 北京博瑞彤芸科技股份有限公司 | Intelligent question and answer method and device based on knowledge graph |
| CN113742474B (en) * | 2021-11-08 | 2022-02-22 | 北京博瑞彤芸科技股份有限公司 | Intelligent question and answer method and device based on knowledge graph |
| CN114090752A (en) * | 2021-11-17 | 2022-02-25 | 中国建设银行股份有限公司 | Problem thread mining method, device, computer equipment and medium |
| CN117669713A (en) * | 2024-01-31 | 2024-03-08 | 宁德时代新能源科技股份有限公司 | Battery information processing method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112182174A (en) | Business question-answer knowledge query method and device, computer equipment and storage medium | |
| CN110428058B (en) | Federal learning model training method, device, terminal equipment and storage medium | |
| CN109873745B (en) | Communication control method, communication control device and storage medium | |
| CN103634371B (en) | A kind of party affair information intelligent mobile client and management method | |
| CN101506769A (en) | Generating search results based on determined relationships between data objects and user connections to identified destinations | |
| CN112559865B (en) | Information processing system, computer-readable storage medium, and electronic device | |
| CN109636582B (en) | Credit information management method, apparatus, device and storage medium | |
| US20190163699A1 (en) | Method and apparatus for information interaction | |
| CN109241384B (en) | Scientific research information visualization method and device | |
| CN111339277A (en) | Question-answer interaction method and device based on machine learning | |
| CN107633022A (en) | Personnel's portrait analysis method, device and storage medium | |
| CN112925898B (en) | Question-answering method and device based on artificial intelligence, server and storage medium | |
| CN111783415B (en) | Template configuration method and device | |
| CN112035638A (en) | Information processing method, device, storage medium and equipment | |
| CN110166522A (en) | Server identification method, device, readable storage medium storing program for executing and computer equipment | |
| CN111563382A (en) | Text information acquisition method and device, storage medium and computer equipment | |
| CN112291423A (en) | Intelligent response processing method and device for communication call, electronic equipment and storage medium | |
| CN105453081A (en) | Answering people-related questions | |
| CN113051389B (en) | Knowledge pushing method and device | |
| CN110134920B (en) | Pictogram compatible display method, device, terminal and computer readable storage medium | |
| CN110990527A (en) | Automatic question answering method and device, storage medium and electronic equipment | |
| CN106485520B (en) | Cross-channel communication control method and server | |
| CN107832342B (en) | Robot chatting method and system | |
| CN110059184B (en) | Operation error collection and analysis method and system | |
| EP3200137A1 (en) | A method, an apparatus, a computer program product for determining metadata for a data item |
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 |