CN112612841A - Knowledge extraction construction method, device, equipment and storage medium - Google Patents
Knowledge extraction construction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112612841A CN112612841A CN202011603763.7A CN202011603763A CN112612841A CN 112612841 A CN112612841 A CN 112612841A CN 202011603763 A CN202011603763 A CN 202011603763A CN 112612841 A CN112612841 A CN 112612841A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- extraction
- constructed
- task
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 236
- 238000010276 construction Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000004590 computer program Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge extraction construction method, a knowledge extraction construction device, knowledge extraction equipment and a storage medium, wherein the method comprises the following steps: receiving the uploaded service data, and converting the service data into data of a preset data structure; determining a pre-constructed knowledge extraction task, and adding the business data of a preset data structure into the knowledge extraction task; and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base. According to the method and the device, automatic extraction and construction of knowledge in the business data can be achieved without manual intervention, knowledge perception is effectively improved, a knowledge construction process is simplified, occupied time is shortened, and finally knowledge acquisition cost is effectively reduced.
Description
Technical Field
The present invention relates to the field of text processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for extracting and constructing knowledge.
Background
Related staff in the field of bank customer service need to give correct answers in time in order to face the problems of different customers; however, the related business of the bank is wide, the types of the related business documents are complex, the introduction contents of the documents are too many, and the query is very difficult. At present, the knowledge related to bank customer service staff is usually sorted manually, confirmed in a centralized way and recorded in sequence; the knowledge manager needs to sort out different related elements and knowledge points in advance by combing the issued related business documents, then secondary combing is carried out according to a unified knowledge type structure, and after confirming that the knowledge content is correct with related personnel, the knowledge manager inputs the knowledge into the system by using a knowledge construction mode of manual uploading and batch importing, so that the construction process of the knowledge is completed. Therefore, knowledge acquisition depends on artificial perception when knowledge acquisition is realized in the prior art, the knowledge perception is not enough, the knowledge construction process is complex, the occupied time is long, and the knowledge acquisition cost is high.
Disclosure of Invention
The invention aims to provide a knowledge extraction construction method, a knowledge extraction construction device, knowledge extraction equipment and a storage medium.
In order to achieve the above purpose, the invention provides the following technical scheme:
a knowledge extraction construction method comprises the following steps:
receiving the uploaded service data, and converting the service data into data of a preset data structure;
determining a pre-constructed knowledge extraction task, and adding the business data of a preset data structure into the knowledge extraction task;
and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base.
Preferably, before the knowledge extraction task is executed, the method further includes:
and judging whether the business data of a preset data structure meets the preset requirement for knowledge extraction, if so, executing the step of executing the knowledge extraction task, and otherwise, feeding back the information of the business data needing to be uploaded again.
Preferably, the determining the extraction result of which knowledge needs to be constructed includes:
displaying the extraction result and the service data of a preset data structure;
and determining a selection instruction input by the outside based on the displayed content, and determining an extraction result corresponding to the selection instruction as an extraction result needing knowledge construction.
Preferably, the step of storing the extracted result of the knowledge to be constructed as knowledge in a corresponding knowledge base includes:
and acquiring a knowledge label corresponding to the extraction result of the knowledge to be constructed, and storing the extraction result of the knowledge to be constructed and the corresponding knowledge label into the knowledge base.
Preferably, after determining the extraction result of which knowledge needs to be constructed, the method further includes:
and determining that the extraction results except the extraction result needing knowledge construction are all to-be-fed back results, and feeding back the to-be-fed back results in a list form.
Preferably, after the extraction result of the knowledge to be constructed is stored as knowledge in a corresponding knowledge base, the method further includes:
and pushing the information of the stored business data corresponding knowledge to the knowledge base to all terminals capable of accessing the knowledge base.
Preferably, the knowledge extraction task is constructed, and comprises the following steps:
and receiving a knowledge extraction request, and constructing a task responding to the knowledge extraction request as a knowledge extraction task.
A knowledge extraction building apparatus comprising:
a conversion module to: receiving the uploaded service data, and converting the service data into data of a preset data structure;
an add module to: determining a pre-constructed knowledge extraction task, and adding the business data of a preset data structure into the knowledge extraction task;
an extraction module to: and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base.
A knowledge extraction building apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of the knowledge extraction construction method as described in any one of the above when the computer program is executed.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the knowledge extraction building method as described in any one of the above.
The invention provides a knowledge extraction construction method, a knowledge extraction construction device, knowledge extraction equipment and a storage medium, wherein the method comprises the following steps: receiving the uploaded service data, and converting the service data into data of a preset data structure; determining a pre-constructed knowledge extraction task, and adding the business data of a preset data structure into the knowledge extraction task; and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base. After the uploaded business data are received, the business data are converted into data of a preset data structure in order to facilitate processing of the business data, then the business data are added to corresponding knowledge extraction tasks, the knowledge in the business data is extracted through execution of the knowledge extraction tasks, and storage of the knowledge to a knowledge database is achieved, so that manual intervention is not needed, automatic extraction and construction of the knowledge in the business data can be achieved, further knowledge perception is effectively improved, a knowledge construction flow is simplified, occupied time is reduced, and finally knowledge acquisition cost is effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a first flowchart of a knowledge extraction construction method according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a knowledge extraction construction method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a knowledge extraction construction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart of a knowledge extraction construction method according to an embodiment of the present invention is shown, where the method may include:
s11: and receiving the uploaded service data, and converting the service data into data of a preset data structure.
The execution main body of the knowledge extraction construction method provided by the embodiment of the invention can be a corresponding knowledge extraction construction device; in addition, the method and the device can be applied to extraction and construction of business document knowledge in the banking field, the knowledge extracted from the method and the device can include definitions, specifications and other contents of different businesses, and corresponding business data uploaded by the user in the embodiment of the method and the device can be business documents. According to the embodiment of the application, after the uploaded service data are received on the basis of the data processing interface, the service data are correspondingly processed, and finally data of a data structure meeting the requirements of knowledge extraction and construction are obtained; the data processing interface is used for processing implementation classes of different data types and a unified data structure, the preset data structure can be set according to actual needs, such as a text format, and the service data is converted into data of the preset data structure, so that all text information contained in the service data can be obtained by analyzing the service data and used as information for realizing knowledge extraction subsequently.
S12: and determining a pre-constructed knowledge extraction task, and adding service data of a preset data structure into the knowledge extraction task.
When knowledge extraction is needed, corresponding knowledge extraction tasks can be constructed, such as setting a thread for realizing knowledge extraction, setting other modules for realizing knowledge extraction, and the like; after the uploaded service data are analyzed to obtain data of a preset data structure, the data of the preset data structure can be added into the knowledge extraction task, so that the knowledge in the data of the preset data structure can be extracted through the execution of the knowledge extraction task.
S13: and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base.
And executing the knowledge extraction task can realize the knowledge extraction operation of the added data in the knowledge extraction task, obtain the knowledge contained in the data added to the knowledge extraction task, and further store the knowledge in a corresponding knowledge base, thereby realizing the automatic extraction and construction of the knowledge.
After the uploaded business data are received, the business data are converted into data of a preset data structure in order to facilitate processing of the business data, then the business data are added to corresponding knowledge extraction tasks, the knowledge in the business data is extracted through execution of the knowledge extraction tasks, and storage of the knowledge to a knowledge database is achieved, so that manual intervention is not needed, automatic extraction and construction of the knowledge in the business data can be achieved, further knowledge perception is effectively improved, a knowledge construction flow is simplified, occupied time is reduced, and finally knowledge acquisition cost is effectively reduced.
The knowledge extraction construction method provided by the embodiment of the invention can further comprise the following steps before executing the knowledge extraction task:
and judging whether the service data of the preset data structure meets the preset requirement for knowledge extraction, if so, executing the step of executing the knowledge extraction task, and otherwise, feeding back the information of the service data needing to be uploaded again.
After the business data is converted into the data of the preset data structure, before the knowledge extraction task is executed, whether the business data meets the preset requirement for knowledge extraction can be judged, such as whether a messy code condition exists in the business data or whether the business data is empty or not, and therefore when the messy code condition exists in the business data or the business data is empty or not, the business data is determined not to meet the preset requirement for knowledge extraction, therefore, information of the business data needs to be uploaded again in a feedback mode, otherwise, the business data meets the preset requirement for knowledge extraction, and therefore the knowledge extraction task can be executed on the business data, and therefore, the effectiveness of knowledge extraction and construction based on the business data is further guaranteed through the mode. And judging whether the business data meet the preset requirement for knowledge extraction, namely analyzing the data type of the business data, so as to determine whether the data type of the business data meets the format requirement for knowledge extraction, and realizing subsequent operation based on the data type.
The knowledge extraction construction method provided by the embodiment of the invention determines the extraction result of the knowledge to be constructed, and can comprise the following steps:
displaying the extraction result and the service data of a preset data structure;
and determining a selection instruction input by the outside based on the displayed content, and determining an extraction result corresponding to the selection instruction as an extraction result needing knowledge construction.
After the extraction result is obtained, the extraction result can be stored; and the extraction result list is displayed, and the uploaded business data is displayed at the same time, so that an external user can compare the extraction result list with the uploaded business data, judge whether the extraction result is the knowledge required to be extracted from the business data, namely whether the extraction result meets the requirement called knowledge, if the judgment result is yes, a corresponding selection instruction can be input, and the knowledge extraction construction device can store the extraction results corresponding to the selection instruction as the knowledge, so that the knowledge stored in the knowledge base can be guaranteed to be the knowledge required to be extracted from the business data. When the extraction result is displayed in a list form, a user can set a mark on the extraction result which needs to be used as knowledge, but does not need to set a mark on the extraction result which needs to be used as knowledge, so that the set mark is determined to be a corresponding selection instruction, and the extraction result which is used as knowledge is selected based on the selection instruction.
The knowledge extraction construction method provided by the embodiment of the invention stores the extraction result of knowledge to be constructed as knowledge in a corresponding knowledge base, and can comprise the following steps:
and acquiring a knowledge label corresponding to the extraction result of the knowledge to be constructed, and storing the extraction result of the knowledge to be constructed and the corresponding knowledge label in a knowledge base.
It should be noted that, in the embodiment of the present application, corresponding keywords may be extracted from the extraction result as the knowledge tags of the extraction result, or the knowledge tags of the extraction result input by an external user may also be obtained, and then the knowledge tags and the corresponding extraction result are stored in the knowledge base, so that the division of the knowledge types is realized, the support of multi-scenario application is satisfied, the knowledge can be quickly located when the consumer inquires, and further, the accurate pushing of the knowledge is satisfied. The knowledge tags may be keywords representing the corresponding knowledge or keywords associated with the corresponding knowledge, and if the knowledge is "apple planting method", the corresponding tags may be "apple cultivation", "plant planting", and the like.
The knowledge extraction construction method provided by the embodiment of the invention can further comprise the following steps after the extraction result of the knowledge required to be constructed is determined:
and determining that the extraction results except the extraction result needing knowledge construction are all to-be-fed back results, and feeding back the to-be-fed back results in a list form.
According to the method and the device, after the extraction result of the knowledge is determined to be required to be constructed, other extraction result list pages can be fed back, so that an external user can know the extraction result which cannot be stored in a knowledge base as the knowledge based on the extraction result, and the manual editing or other operations can be conveniently realized.
The knowledge extraction construction method provided by the embodiment of the invention can store the extraction result of the knowledge to be constructed as the knowledge in the corresponding knowledge base, and can further comprise the following steps:
and pushing the information of the knowledge in the knowledge base corresponding to the stored business data to all terminals capable of accessing the knowledge base.
In order to facilitate acquisition of knowledge in the knowledge base by users of different terminals, the embodiment of the application can also push information of stored service data corresponding to the knowledge in the knowledge base to all terminals with access authority to the knowledge base, so that the terminals can conveniently know the new knowledge addition behavior in the knowledge base, and further realize corresponding access and other operations based on the information.
The knowledge extraction construction method provided by the embodiment of the invention is used for constructing a knowledge extraction task, and can comprise the following steps:
and receiving a knowledge extraction request, and constructing a task responding to the knowledge extraction request as a knowledge extraction task.
When the knowledge extraction task is constructed, after a knowledge extraction request input by a user is received, the knowledge extraction task such as a corresponding thread or module is constructed, so that the response to the user request is realized, and the requirements of the user for realizing the knowledge extraction and construction are met.
In a specific application scenario, the knowledge extraction construction method provided in the embodiment of the present application may be divided into multiple stages, which are respectively adding business data, extracting knowledge, and warehousing knowledge, and as shown in fig. 2, the method specifically may include:
firstly, knowledge extraction: and (4) sorting the service data and extracting the knowledge points in the service data.
Step 104 analyzes the data type: if the uploaded data type meets the format requirement of knowledge extraction, extraction can be performed, otherwise, data uploading is returned, and the data type meeting the format needs to be uploaded again.
Step 105 extracts knowledge: and executing a knowledge extraction task.
Step 106 generates a knowledge extraction result: and after the knowledge extraction operation is carried out on the uploaded service data, displaying the extraction result list, and simultaneously displaying the original service data for comparison.
Secondly, knowledge construction: and combing and editing the extraction result, adding a knowledge tag for the extraction result, and adding new knowledge into a warehouse.
Step 201 saves the extraction result: and storing the extraction result obtained by the current knowledge extraction.
Step 202 checks whether the extraction result meets: and checking whether the result of the knowledge extraction of the data conforms to the requirement of becoming knowledge, if so, constructing the knowledge of the extraction result, and otherwise, editing the stored extraction result.
Step 203 determines whether to construct knowledge based on step 202: and judging whether the current extraction result needs to be constructed into knowledge (namely whether the extraction result meets the requirement of becoming the knowledge), if so, adding the knowledge again, otherwise, feeding back a knowledge extraction result list page.
Step 204 adds a knowledge tag: and adding a knowledge tag for the extraction result.
Step 205 adds new knowledge: the extraction result is added as knowledge.
After various documents and data generated on the business are analyzed by means of semantic understanding and a knowledge model, the knowledge is automatically extracted and generated according to the definition, specification and other contents of different businesses possibly appearing in the documents, and the extracted knowledge is labeled, so that the knowledge is conveniently and rapidly positioned and secondarily searched. The method mainly aims at the knowledge extraction results of document data of different business types in the bank field, can generate better performance and is suitable for different knowledge management use scenes, so that the business pertinence is strong; by means of semantic understanding and knowledge models in the natural language understanding technology, different business type data can be suitable for the extraction technology, and the method has a complete knowledge management flow and supports adding labels to knowledge points, so that the functional coverage is complete; the method is beneficial to increasing knowledge maintenance efficiency, improving knowledge management benefits, accelerating demand response speed, enhancing external service competitiveness, improving economic benefits, perfecting knowledge consumption and improving the working efficiency of business personnel, so that the comprehensive benefits are high.
An embodiment of the present invention further provides a knowledge extraction construction apparatus, as shown in fig. 3, which may include:
a conversion module 11 for: receiving the uploaded service data, and converting the service data into data of a preset data structure;
an adding module 12 for: determining a pre-constructed knowledge extraction task, and adding service data of a preset data structure into the knowledge extraction task;
an extraction module 13 for: and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base.
The knowledge extraction construction device provided by the embodiment of the invention can further comprise:
a determination module configured to: before executing the knowledge extraction task, judging whether the service data of the preset data structure meets the preset requirement for knowledge extraction, if so, executing the step of executing the knowledge extraction task, otherwise, feeding back the information of the service data needing to be uploaded again.
In the knowledge extraction and construction device provided in the embodiment of the present invention, the extraction module may further include:
a determination unit configured to: displaying the extraction result and the service data of a preset data structure; and determining a selection instruction input by the outside based on the displayed content, and determining an extraction result corresponding to the selection instruction as an extraction result needing knowledge construction.
In the knowledge extraction construction apparatus provided in the embodiment of the present invention, the extraction module may include:
an acquisition unit configured to: and acquiring a knowledge label corresponding to the extraction result of the knowledge to be constructed, and storing the extraction result of the knowledge to be constructed and the corresponding knowledge label in a knowledge base.
The knowledge extraction construction device provided by the embodiment of the invention can further comprise:
a feedback module to: after the extraction result of the knowledge required to be constructed is determined, the extraction results except the extraction result of the knowledge required to be constructed are determined to be the results to be fed back, and the results to be fed back are fed back in a form of a list.
The knowledge extraction construction device provided by the embodiment of the invention can further comprise:
a push module to: and after the extraction result of the knowledge required to be constructed is stored in a corresponding knowledge base as the knowledge, pushing the information of the knowledge in the knowledge base corresponding to the stored business data to all terminals capable of accessing the knowledge base.
The knowledge extraction construction device provided by the embodiment of the invention can further comprise:
a build module to: and receiving a knowledge extraction request, and constructing a task responding to the knowledge extraction request as a knowledge extraction task.
The embodiment of the invention also provides knowledge extraction construction equipment, which can comprise:
a memory for storing a computer program;
and the processor is used for realizing the steps of the knowledge extraction construction method when executing the computer program.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program can realize the steps of any one of the above knowledge extraction construction methods.
It should be noted that, for the description of the relevant parts in the knowledge extraction construction apparatus, the device and the storage medium provided in the embodiment of the present invention, reference is made to the detailed description of the corresponding parts in the knowledge extraction construction method provided in the embodiment of the present invention, and details are not repeated here. In addition, parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail, so as to avoid redundant description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A knowledge extraction construction method is characterized by comprising the following steps:
receiving the uploaded service data, and converting the service data into data of a preset data structure;
determining a pre-constructed knowledge extraction task, and adding the business data of a preset data structure into the knowledge extraction task;
and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base.
2. The method of claim 1, wherein prior to performing the knowledge extraction task, further comprising:
and judging whether the business data of a preset data structure meets the preset requirement for knowledge extraction, if so, executing the step of executing the knowledge extraction task, and otherwise, feeding back the information of the business data needing to be uploaded again.
3. The method of claim 2, wherein determining the extraction results for which knowledge needs to be constructed comprises:
displaying the extraction result and the service data of a preset data structure;
and determining a selection instruction input by the outside based on the displayed content, and determining an extraction result corresponding to the selection instruction as an extraction result needing knowledge construction.
4. The method of claim 3, wherein storing the extracted results of knowledge required to be constructed as knowledge in a corresponding knowledge base comprises:
and acquiring a knowledge label corresponding to the extraction result of the knowledge to be constructed, and storing the extraction result of the knowledge to be constructed and the corresponding knowledge label into the knowledge base.
5. The method of claim 4, wherein after determining the extraction result for which knowledge needs to be constructed, further comprising:
and determining that the extraction results except the extraction result needing knowledge construction are all to-be-fed back results, and feeding back the to-be-fed back results in a list form.
6. The method according to claim 5, wherein after storing the extracted result of knowledge to be constructed as knowledge in the corresponding knowledge base, further comprising:
and pushing the information of the stored business data corresponding knowledge to the knowledge base to all terminals capable of accessing the knowledge base.
7. The method of claim 6, wherein constructing a knowledge extraction task comprises:
and receiving a knowledge extraction request, and constructing a task responding to the knowledge extraction request as a knowledge extraction task.
8. A knowledge extraction building apparatus, comprising:
a conversion module to: receiving the uploaded service data, and converting the service data into data of a preset data structure;
an add module to: determining a pre-constructed knowledge extraction task, and adding the business data of a preset data structure into the knowledge extraction task;
an extraction module to: and executing the knowledge extraction task to obtain a corresponding extraction result, and storing the extraction result of the knowledge required to be constructed as the knowledge into a corresponding knowledge base.
9. A knowledge extraction building apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the knowledge extraction building method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the steps of the knowledge extraction building method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011603763.7A CN112612841A (en) | 2020-12-29 | 2020-12-29 | Knowledge extraction construction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011603763.7A CN112612841A (en) | 2020-12-29 | 2020-12-29 | Knowledge extraction construction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112612841A true CN112612841A (en) | 2021-04-06 |
Family
ID=75249188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011603763.7A Pending CN112612841A (en) | 2020-12-29 | 2020-12-29 | Knowledge extraction construction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112612841A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750650A (en) * | 2019-09-30 | 2020-02-04 | 中盈优创资讯科技有限公司 | Construction method and device of enterprise knowledge graph |
| CN110929007A (en) * | 2019-11-08 | 2020-03-27 | 国网江苏省电力有限公司电力科学研究院 | Electric power marketing knowledge system platform and application method |
| CN111626568A (en) * | 2020-05-06 | 2020-09-04 | 厦门理工学院 | Knowledge base construction method and device and knowledge search method and system |
| CN111858963A (en) * | 2020-07-28 | 2020-10-30 | 中国银行股份有限公司 | Webpage customer service knowledge extraction method and device |
| CN111966689A (en) * | 2020-08-19 | 2020-11-20 | 中国银行股份有限公司 | Application knowledge base construction method and device |
| CN112035678A (en) * | 2020-09-03 | 2020-12-04 | 中国银行股份有限公司 | Bank business knowledge graph construction method and device |
-
2020
- 2020-12-29 CN CN202011603763.7A patent/CN112612841A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750650A (en) * | 2019-09-30 | 2020-02-04 | 中盈优创资讯科技有限公司 | Construction method and device of enterprise knowledge graph |
| CN110929007A (en) * | 2019-11-08 | 2020-03-27 | 国网江苏省电力有限公司电力科学研究院 | Electric power marketing knowledge system platform and application method |
| CN111626568A (en) * | 2020-05-06 | 2020-09-04 | 厦门理工学院 | Knowledge base construction method and device and knowledge search method and system |
| CN111858963A (en) * | 2020-07-28 | 2020-10-30 | 中国银行股份有限公司 | Webpage customer service knowledge extraction method and device |
| CN111966689A (en) * | 2020-08-19 | 2020-11-20 | 中国银行股份有限公司 | Application knowledge base construction method and device |
| CN112035678A (en) * | 2020-09-03 | 2020-12-04 | 中国银行股份有限公司 | Bank business knowledge graph construction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 杨迪等: "基于人工智能的智能交互系统体系架构", 《电信科学》, vol. 34, no. 12, pages 92 - 101 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109947789B (en) | Method, device, computer equipment and storage medium for processing data of multiple databases | |
| CN107766371B (en) | Text information classification method and device | |
| CN110347953B (en) | Page generation method, page generation device, computer equipment and storage medium | |
| CN109669933B (en) | Transaction data intelligent processing method and device and computer readable storage medium | |
| CN106844307B (en) | System and method for converting Excel into Word based on mark | |
| CN111160045B (en) | Game resource file translation method, device and equipment | |
| CN110515951B (en) | BOM standardization method and system, electronic device and storage medium | |
| CN105975446A (en) | Method and system for displaying word document content by modules in mobile phone terminal | |
| CN109344374B (en) | Report generation method and device based on big data, electronic equipment and storage medium | |
| CN111737443B (en) | Answer text processing method and device and key text determining method | |
| CN111191429A (en) | System and method for automatic filling of data table | |
| CN113010542A (en) | Service data processing method and device, computer equipment and storage medium | |
| CN113434627A (en) | Work order processing method and device and computer readable storage medium | |
| CN112612841A (en) | Knowledge extraction construction method, device, equipment and storage medium | |
| CN114495138A (en) | Intelligent document identification and feature extraction method, device platform and storage medium | |
| CN114115831A (en) | Data processing method, device, equipment and storage medium | |
| CN112508535A (en) | Jbpm-based method and device for improving approval workflow | |
| CN113033169A (en) | Service data processing method and device | |
| CN112561558A (en) | Express time portrait generation method, generation device, equipment and storage medium | |
| CN110276055B (en) | Chart remark information generation method and device, electronic equipment and storage medium | |
| CN111459904B (en) | TPM document automatic management system and method | |
| CN116151804A (en) | Automatic operation ticket generation method, device, equipment and storage medium | |
| CN115065153A (en) | Intelligent power grid regulation and control processing system and method | |
| CN115983545A (en) | Data extraction method, system, equipment and storage medium for bill splitting software | |
| CN117688345A (en) | Data service method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210406 |