CN113627148A - Automatic association method and device for knowledge in knowledge base - Google Patents
Automatic association method and device for knowledge in knowledge base Download PDFInfo
- Publication number
- CN113627148A CN113627148A CN202110546194.5A CN202110546194A CN113627148A CN 113627148 A CN113627148 A CN 113627148A CN 202110546194 A CN202110546194 A CN 202110546194A CN 113627148 A CN113627148 A CN 113627148A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- target
- information
- association
- dimensions
- 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 36
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims description 51
- 238000013459 approach Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 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
- 238000005457 optimization Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000000750 progressive effect 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
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for automatically associating knowledge in a knowledge base. Therefore, the association degree of each knowledge in the knowledge base can be analyzed through the pre-trained relation analysis model, and therefore when the user searches for the related knowledge, the knowledge which is more in line with the user expectation can be provided for the user.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an automatic association method and device for knowledge in a knowledge base.
Background
The knowledge base is a massive knowledge management tool platform, and has the main functions of storing and managing knowledge and providing the capability of knowledge retrieval. Currently, knowledge in the knowledge base is independent of each other, and when a user searches, the potential needs of the user cannot be found.
In the prior art, in order to solve the problems, the association between the knowledge is artificially established in a manual mode, the processing efficiency of the manual association mode is low, and the manual association mode is subjective and difficult to find the implicit association information between the knowledge.
Disclosure of Invention
In view of this, embodiments of the present invention provide an automatic association method and apparatus for knowledge in a knowledge base, where through a pre-trained relationship analysis model, the association degree between knowledge in the knowledge base can be analyzed, so as to not only achieve the purpose of intelligent knowledge association, but also reflect the association degree between knowledge in the established association relationship, so that when a user searches for relevant knowledge, the user can be provided with knowledge more meeting the user's expectations, and when performing knowledge association, information of multiple dimensions is considered, and the association relationship possibly existing between knowledge is considered more comprehensively, so that the established association relationship between knowledge is more accurate.
The embodiment of the invention discloses an automatic association method of knowledge in a knowledge base, which comprises the following steps:
acquiring information of a plurality of target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
extracting a first target feature from information of a plurality of target dimensions of each piece of knowledge;
inputting the first target characteristics into a preset relation analysis model to obtain a correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and establishing the association relation among the knowledge in the knowledge base according to the association coefficient of the knowledge.
Optionally, the attribute knowledge includes:
knowledge title, creator, creation time, catalog, tag, knowledge source.
Optionally, the content information of the knowledge includes:
keyword similarity information and text similarity information of knowledge.
Optionally, the training process of the association model includes:
acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge;
and inputting second characteristics of the historical data of a plurality of target dimensions of the plurality of pieces of knowledge into the association model to be trained as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the association model to be trained on the training samples approaches to the preset association coefficient of the plurality of pieces of knowledge.
Optionally, the obtaining a second target feature of the historical data of the multiple target dimensions of the multiple pieces of knowledge includes:
acquiring preset historical data of multiple dimensions from account information of a user;
acquiring a second target feature from the historical data of each dimension;
determining a weight of each second target feature that is a history of dimensions;
and screening out the second target characteristics of the target dimension from the plurality of dimensions according to the weight of the second target characteristics of the historical data of each dimension.
The embodiment of the invention discloses an automatic association device for knowledge in a knowledge base, which comprises:
the acquisition unit is used for acquiring information of a plurality of target dimensions of each piece of knowledge in the knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
the characteristic extraction unit is used for extracting first target characteristics from information of a plurality of target dimensions of each piece of knowledge;
the correlation coefficient calculation unit is used for inputting the first target characteristic into a preset relation analysis model to obtain the correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and the relation construction unit is used for establishing the incidence relation among the knowledge in the knowledge base according to the incidence coefficient of the knowledge.
Optionally, the attribute knowledge includes:
knowledge title, creator, creation time, catalog, tag, knowledge source.
Optionally, the content information of the knowledge includes:
keyword similarity information and text similarity information of knowledge.
Optionally, the method further includes:
an association model training unit:
acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge;
and inputting second characteristics of the historical data of a plurality of target dimensions of the plurality of pieces of knowledge into the association model to be trained as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the association model to be trained on the training samples approaches to the preset association coefficient of the plurality of pieces of knowledge.
The embodiment of the invention also discloses an electronic device, which comprises:
a memory and a processor;
the memory is used for storing a program, and the processor is used for executing at least the following automatic association method of knowledge in the knowledge base:
acquiring information of a plurality of target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
extracting a first target feature from information of a plurality of target dimensions of each piece of knowledge;
inputting the first target characteristics into a preset relation analysis model to obtain a correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and establishing the association relation among the knowledge in the knowledge base according to the association coefficient of the knowledge.
The embodiment of the invention discloses a method and a device for automatically associating knowledge in a knowledge base. Therefore, the association degree of each knowledge in the knowledge base can be analyzed through the pre-trained relationship analysis model, the purpose of intelligent knowledge association is achieved, the established association degree of the knowledge can be reflected, the knowledge which is more in line with the user expectation can be provided for the user when the user searches for the relevant knowledge, information of multiple dimensions is considered when the knowledge is associated, the association relation which possibly exists among the knowledge is considered more comprehensively, and the established association relation among the knowledge is more accurate.
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 flow chart illustrating a method for automatically associating knowledge in a knowledge base according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for training a relational analysis model according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an apparatus for automatically associating knowledge in a knowledge base according to an embodiment of the present invention;
fig. 4 shows a schematic structural diagram of an electronic device 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 flow chart of a method for automatically associating knowledge in a knowledge base according to an embodiment of the present invention is shown, in this embodiment, the method includes:
s101: acquiring information of a plurality of target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
in this embodiment, the attribute information of the knowledge may include multiple types, in this embodiment, the selected attribute information has an influence on the association between the knowledge, or the selected attribute information has a large influence on the association between the knowledge, where the selected attribute information in this embodiment may include: knowledge title, creator, creation time, tag, knowledge source, etc.
The content information of the knowledge may include various kinds, and may include, for example, the content of the knowledge itself.
Or in order to further improve the accuracy of knowledge association, the content information of the knowledge may adopt the similarity of the keywords and the text similarity.
The method for acquiring keyword similarity includes multiple methods, which are not limited in this embodiment, and preferably, the keyword similarity may be acquired in the following manner:
firstly, removing stop words, then segmenting the knowledge content to form a plurality of key words, and calculating the proportion of the same key words among any knowledge, wherein the proportion of the same key words can be calculated by the following formula 1):
1) the keyword proportion is the number of the same keywords/the total number of the keywords in the knowledge;
for example, a keyword similarity ratio of knowledge a and knowledge B is calculated, which is the number of identical keywords of knowledge a and knowledge B/the number of keywords of knowledge a).
In this embodiment, the text similarity may be understood as a similarity of contents between two pieces of knowledge, where the text similarity between the two pieces of knowledge may be obtained by a plurality of methods, which is not limited in this embodiment.
In this embodiment, the knowledge stored in the knowledge base includes information of a plurality of different dimensions, where information of some dimensions in the information is information having a large influence on association of the knowledge, and information of some dimensions may have a small influence on association between the knowledge, and in this embodiment, the information of the plurality of dimensions may be screened out in a feature engineering manner, and preferably, may be acquired in the following manner:
acquiring preset historical information of multiple dimensions from account information of a user;
acquiring a second target feature from the historical information of each dimension;
determining the weight of a second target feature of the historical information of each dimension;
and screening out the target dimension from the plurality of dimensions according to the weight of the second target characteristic of the historical information of each dimension.
S102: extracting a first target feature from information of a plurality of target dimensions of each piece of knowledge;
in this embodiment, the method for extracting the first target feature from the information of the multiple target dimensions of the knowledge includes multiple methods, which is not limited in this embodiment.
Preferably, a model of feature engineering may be used to perform feature extraction, the feature engineering model may include multiple types, and is not limited in this embodiment, and for example, a principal component analysis model, a linear discriminant analysis model, or the like may be used.
S103: inputting the first target characteristics into a preset relation analysis model to obtain a correlation coefficient of each piece of knowledge;
the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples.
In this embodiment, the relationship analysis model may be any model capable of performing clustering, and before executing S103, the relationship analysis model is trained in advance, specifically, parameters in the relationship analysis model are optimized in a training manner, and the specific training manner will be described in detail below, which is not described in detail in this embodiment.
S104: and establishing the association relation among the knowledge in the knowledge base according to the association coefficient of the knowledge.
In this embodiment, the correlation coefficient between different pieces of knowledge may be understood as a degree of correlation between different pieces of knowledge, where the greater the correlation coefficient, the higher the degree of correlation of the knowledge is considered.
In this embodiment, parameters of the relational analysis model are optimized by using historical data of a plurality of target dimensions of a plurality of pieces of knowledge in the knowledge base as training samples to obtain a trained relational analysis model, and the correlation coefficient of each piece of knowledge in the knowledge base is calculated by using the trained relational analysis model, so that the correlation relationship between the pieces of knowledge is established by using the correlation coefficient. Therefore, the association degree of each knowledge in the knowledge base can be analyzed through the pre-trained relation analysis model, and therefore when the user searches for the related knowledge, the knowledge which is more in line with the user expectation can be provided for the user.
Further, after receiving new knowledge in the knowledge base, the association coefficient between the knowledge and other knowledge may be determined through a pre-trained relationship analysis model, and specifically, the method further includes:
acquiring information of a plurality of target dimensions of the target knowledge, and extracting a third target feature from the information of the plurality of target dimensions of the target knowledge;
and inputting the third target characteristic into a relational analysis model to obtain a correlation coefficient between the knowledge and other knowledge in a knowledge base.
The existing knowledge in the knowledge base is clustered in advance in the relational analysis model, then the clustering result of the existing knowledge in the knowledge base is stored in the relational analysis model, and the correlation coefficient between the newly added target knowledge and the existing knowledge can be determined through the clustering result of the existing knowledge in the knowledge base.
Referring to fig. 2, the relational analysis model may also be trained by methods including:
s201: acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge in a knowledge base;
in this embodiment, the knowledge stored in the knowledge base includes information of a plurality of different dimensions, where information of some dimensions in the information is information having a large influence on association of the knowledge, and information of some dimensions may have a small influence on association between the knowledge, and in this embodiment, the information of the plurality of dimensions may be screened out in a feature engineering manner, and preferably, may be acquired in the following manner:
acquiring preset historical information of multiple dimensions from account information of a user;
acquiring a second target feature from the historical information of each dimension;
determining the weight of a second target feature of the historical information of each dimension;
and screening out second target characteristics of a plurality of target dimensions from the plurality of dimensions according to the weight of the second target characteristics of the historical information of each dimension.
S202: and inputting second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge in a knowledge base into a trained association model as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the relation analysis model to be trained on the training samples approaches to the preset association coefficient of the knowledge.
In this embodiment, the association coefficient of the preset knowledge may be set by the existing knowledge or experience.
In the embodiment, the association degree of each knowledge in the knowledge base can be analyzed through the pre-trained relation analysis model, so that the knowledge which is more in line with the user expectation can be provided for the user when the user searches for the relevant knowledge.
Alternatively, the relational analysis model may be trained by other methods, such as an unsupervised machine learning model, and the process may include:
s301: extracting second target features from historical data of a plurality of target dimensions of a plurality of pieces of knowledge in a knowledge base;
in this embodiment, the knowledge stored in the knowledge base includes information of a plurality of different dimensions, where information of some dimensions in the information is information having a large influence on association of the knowledge, and information of some dimensions may have a small influence on association between the knowledge, and in this embodiment, the information of the plurality of dimensions may be screened out in a feature engineering manner, and preferably, may be acquired in the following manner:
acquiring preset historical information of multiple dimensions from account information of a user;
acquiring a second target feature from the historical information of each dimension;
determining the weight of a second target feature of the historical information of each dimension;
and screening out second target characteristics of a plurality of target dimensions from the plurality of dimensions according to the weight of the second target characteristics of the historical information of each dimension.
S302: inputting the second target characteristics into a relational analysis model, and optimizing the relational analysis model by adjusting the target.
In this embodiment, the objective optimization function may be preset, and for example, the loss function may be constructed by similarity of output knowledge, or constructed by similarity of features of knowledge.
In the embodiment, the association degree of each knowledge in the knowledge base can be analyzed through the pre-trained relation analysis model, so that the knowledge which is more in line with the user expectation can be provided for the user when the user searches for the relevant knowledge.
Referring to fig. 3, a schematic structural diagram of an apparatus for automatically associating knowledge in a knowledge base according to an embodiment of the present invention is shown, in this embodiment, the apparatus includes:
an obtaining unit 401, configured to obtain information of multiple target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
a feature extraction unit 402, configured to extract a first target feature from information of a plurality of target dimensions of each piece of knowledge;
the correlation coefficient calculating unit 403 is configured to input the first target feature into a preset relationship analysis model, so as to obtain a correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and the relationship building unit 404 is configured to build an association relationship between the pieces of knowledge in the knowledge base according to the association coefficients of the knowledge.
Optionally, the attribute knowledge includes:
knowledge title, creator, creation time, catalog, tag, knowledge source.
Optionally, the content information of the knowledge includes:
keyword similarity information and text similarity information of knowledge.
Optionally, the method further includes:
an association model training unit:
acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge;
and inputting second characteristics of the historical data of a plurality of target dimensions of the plurality of pieces of knowledge into the association model to be trained as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the association model to be trained on the training samples approaches to the preset association coefficient of the plurality of pieces of knowledge.
Optionally, the association model training unit further includes:
acquiring preset historical data of multiple dimensions from account information of a user;
acquiring a second target feature from the historical data of each dimension;
determining a weight of each second target feature that is a history of dimensions;
and screening out the second target characteristics of the target dimension from the plurality of dimensions according to the weight of the second target characteristics of the historical data of each dimension.
According to the device, parameters of the relational analysis model are optimized by taking historical data of a plurality of target dimensions of a plurality of pieces of knowledge in the knowledge base as training samples, the trained relational analysis model is obtained, the correlation coefficient of each piece of knowledge in the knowledge base is calculated through the trained relational analysis model, and then the correlation relationship between the knowledge is established through the correlation coefficient. Therefore, the association degree of each knowledge in the knowledge base can be analyzed through the pre-trained relation analysis model, and therefore when the user searches for the related knowledge, the knowledge which is more in line with the user expectation can be provided for the user.
Referring to fig. 4, a schematic structural diagram of an electronic device according to an embodiment of the present invention is shown, where in this embodiment, the electronic device includes:
a memory 401 and a processor 402;
the memory is used for storing programs, and the processor is used for executing the automatic association method of knowledge in the knowledge base as follows:
acquiring information of a plurality of target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
extracting a first target feature from information of a plurality of target dimensions of each piece of knowledge;
inputting the first target characteristics into a preset relation analysis model to obtain a correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and establishing the association relation among the knowledge in the knowledge base according to the association coefficient of the knowledge.
Optionally, the attribute knowledge includes:
knowledge title, creator, creation time, catalog, tag, knowledge source.
Optionally, the content information of the knowledge includes:
keyword similarity information and text similarity information of knowledge.
Optionally, the training process of the association model includes:
acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge;
and inputting second characteristics of the historical data of a plurality of target dimensions of the plurality of pieces of knowledge into the association model to be trained as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the association model to be trained on the training samples approaches to the preset association coefficient of the plurality of pieces of knowledge.
Optionally, the obtaining a second target feature of the historical data of the multiple target dimensions of the multiple pieces of knowledge includes:
acquiring preset historical data of multiple dimensions from account information of a user;
acquiring a second target feature from the historical data of each dimension;
determining a weight of each second target feature that is a history of dimensions;
and screening out the second target characteristics of the target dimension from the plurality of dimensions according to the weight of the second target characteristics of the historical data of each dimension.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
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 method for automatically associating knowledge in a knowledge base is characterized by comprising the following steps:
acquiring information of a plurality of target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
extracting a first target feature from information of a plurality of target dimensions of each piece of knowledge;
inputting the first target characteristics into a preset relation analysis model to obtain a correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and establishing the association relation among the knowledge in the knowledge base according to the association coefficient of the knowledge.
2. The method of claim 1, wherein the knowledge of attributes comprises:
knowledge title, creator, creation time, catalog, tag, knowledge source.
3. The method of claim 1, wherein the content information of the knowledge comprises:
keyword similarity information and text similarity information of knowledge.
4. The method of claim 1, wherein the training process of the correlation model comprises:
acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge;
and inputting second characteristics of the historical data of a plurality of target dimensions of the plurality of pieces of knowledge into the association model to be trained as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the association model to be trained on the training samples approaches to the preset association coefficient of the plurality of pieces of knowledge.
5. The method of claim 4, wherein obtaining a second target feature of historical data for a plurality of target dimensions of a plurality of pieces of knowledge comprises:
acquiring preset historical data of multiple dimensions from account information of a user;
acquiring a second target feature from the historical data of each dimension;
determining a weight of each second target feature that is a history of dimensions;
and screening out the second target characteristics of the target dimension from the plurality of dimensions according to the weight of the second target characteristics of the historical data of each dimension.
6. An apparatus for automatically associating knowledge in a knowledge base, comprising:
the acquisition unit is used for acquiring information of a plurality of target dimensions of each piece of knowledge in the knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
the characteristic extraction unit is used for extracting first target characteristics from information of a plurality of target dimensions of each piece of knowledge;
the correlation coefficient calculation unit is used for inputting the first target characteristic into a preset relation analysis model to obtain the correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and the relation construction unit is used for establishing the incidence relation among the knowledge in the knowledge base according to the incidence coefficient of the knowledge.
7. The apparatus of claim 6, wherein the knowledge of attributes comprises:
knowledge title, creator, creation time, catalog, tag, knowledge source.
8. The apparatus of claim 6, wherein the content information of the knowledge comprises:
keyword similarity information and text similarity information of knowledge.
9. The apparatus of claim 6, further comprising:
an association model training unit:
acquiring second target characteristics of historical data of a plurality of target dimensions of a plurality of pieces of knowledge;
and inputting second characteristics of the historical data of a plurality of target dimensions of the plurality of pieces of knowledge into the association model to be trained as training samples, and training the association model to be trained by aiming at the purpose that the association coefficient output by the association model to be trained on the training samples approaches to the preset association coefficient of the plurality of pieces of knowledge.
10. An electronic device, comprising:
a memory and a processor;
the memory is used for storing a program, and the processor is used for executing at least the following automatic association method of knowledge in the knowledge base:
acquiring information of a plurality of target dimensions of each piece of knowledge in a knowledge base; the information of the plurality of target dimensions at least comprises: attribute information of knowledge and/or content information of knowledge;
extracting a first target feature from information of a plurality of target dimensions of each piece of knowledge;
inputting the first target characteristics into a preset relation analysis model to obtain a correlation coefficient of each piece of knowledge; the relational analysis model is obtained by optimally training parameters of the relational analysis model by taking historical data of a plurality of target dimensions of knowledge in a knowledge base as training samples;
and establishing the association relation among the knowledge in the knowledge base according to the association coefficient of the knowledge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110546194.5A CN113627148A (en) | 2021-05-19 | 2021-05-19 | Automatic association method and device for knowledge in knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110546194.5A CN113627148A (en) | 2021-05-19 | 2021-05-19 | Automatic association method and device for knowledge in knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627148A true CN113627148A (en) | 2021-11-09 |
Family
ID=78377998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110546194.5A Pending CN113627148A (en) | 2021-05-19 | 2021-05-19 | Automatic association method and device for knowledge in knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627148A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194459A (en) * | 2023-09-22 | 2023-12-08 | 天翼爱音乐文化科技有限公司 | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977312A (en) * | 2019-03-27 | 2019-07-05 | 安庆师范大学 | A kind of knowledge base recommender system based on content tab |
| WO2020156389A1 (en) * | 2019-01-30 | 2020-08-06 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
| CN111752922A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Method and device for establishing knowledge database and realizing knowledge query |
| CN111984688A (en) * | 2020-08-19 | 2020-11-24 | 中国银行股份有限公司 | Method and device for determining business knowledge association relation |
-
2021
- 2021-05-19 CN CN202110546194.5A patent/CN113627148A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020156389A1 (en) * | 2019-01-30 | 2020-08-06 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
| CN109977312A (en) * | 2019-03-27 | 2019-07-05 | 安庆师范大学 | A kind of knowledge base recommender system based on content tab |
| CN111752922A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Method and device for establishing knowledge database and realizing knowledge query |
| CN111984688A (en) * | 2020-08-19 | 2020-11-24 | 中国银行股份有限公司 | Method and device for determining business knowledge association relation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194459A (en) * | 2023-09-22 | 2023-12-08 | 天翼爱音乐文化科技有限公司 | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event |
| CN117194459B (en) * | 2023-09-22 | 2024-05-10 | 天翼爱音乐文化科技有限公司 | Operation and maintenance knowledge base updating method, system, device and medium based on operation and maintenance event |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111324784B (en) | Character string processing method and device | |
| US20220019739A1 (en) | Item Recall Method and System, Electronic Device and Readable Storage Medium | |
| CN110019668A (en) | A kind of text searching method and device | |
| CN108427686A (en) | Text data querying method and device | |
| CN108733694B (en) | Retrieval recommendation method and device | |
| CN110795613A (en) | Commodity searching method, device and system and electronic equipment | |
| CN108228612B (en) | Method and device for extracting network event keywords and emotional tendency | |
| CN117785834A (en) | Database structure and index optimization method, equipment and medium | |
| CN117688155A (en) | Service problem replying method and device, storage medium and electronic equipment | |
| CN105653548A (en) | Method and system for identifying page type of electronic document | |
| CN115329048A (en) | Statement retrieval method and device, electronic equipment and storage medium | |
| CN113627148A (en) | Automatic association method and device for knowledge in knowledge base | |
| CN110019670A (en) | A kind of text searching method and device | |
| CN110955760B (en) | Evaluation method of judgment result and related device | |
| CN110019783B (en) | Attribute word clustering method and device | |
| CN117290481A (en) | Question and answer method and device based on deep learning, storage medium and electronic equipment | |
| CN110941952A (en) | Method and device for perfecting audit analysis model | |
| CN116415156A (en) | Document similarity calculation method, device and medium | |
| CN111539208B (en) | Sentence processing method and device, electronic device and readable storage medium | |
| CN110019771B (en) | Text processing method and device | |
| CN113157870B (en) | Knowledge association method and device and electronic equipment | |
| JP2017010376A (en) | Mart-less verification support system and mart-less verification support method | |
| CN116992111B (en) | Data processing method, device, electronic equipment and computer storage medium | |
| CN118152645B (en) | Enterprise-level search result optimization method, equipment and medium based on large model | |
| CN110909533B (en) | Resource theme judging 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 |