A domain knowledge association method and device based on knowledge discovery and a storage medium

Abstract

This invention belongs to the field of data mining and knowledge engineering research technology. Specifically, it relates to a method, apparatus, and storage medium for domain knowledge association based on knowledge discovery. The method includes: first, acquiring domain keywords; generating a text dataset based on text data obtained from the domain keywords; second, labeling the knowledge elements identified in the text dataset to obtain a knowledge element association dataset; then, evaluating the knowledge elements in the knowledge element association dataset to obtain knowledge element association indices; and finally, ranking the knowledge element association dataset according to the knowledge element association indices to determine the domain knowledge elements and their datasets. The method proposed in this invention can reduce the influence of human factors and improve the scientific rigor and applicability of knowledge association measurement.

Description

Technical Field

[0001] This invention belongs to the field of data mining and knowledge engineering research technology. Specifically, it relates to a method, device and storage medium for domain knowledge association based on knowledge discovery. Background Technology

[0002] With the rapid pace of scientific and technological development, the number of scientific and technological documents, including scientific papers, patents, and reports, has exploded. As the primary carriers and disseminators of knowledge, scientific and technological documents contain a wealth of undiscovered scientific knowledge. Typically, the implicit knowledge contained within these documents can only be acquired by researchers through meticulous reading. Therefore, the need for automated methods to extract valuable information and discover new knowledge from massive amounts of literature has become particularly urgent. Computer technology can be used to extract unstructured or semi-structured information from the detailed descriptions of scientific and technological documents, transform and process it, extract latent knowledge, and thus enhance the value of information resources and facilitate the discovery of new knowledge. Currently, most knowledge association systems use user preferences or historical access data for calculations. For example, by considering historical data from multiple dimensions to optimize model parameters, it is possible to more comprehensively consider the possible relationships between knowledge. However, this method relies on historical data to build training samples, making it difficult to establish relationships between knowledge for new users who lack historical data. Another approach is to establish relationships between target knowledge points and their relationship strengths for subsequent knowledge point recommendations. This method can complete the recommended knowledge point associations without requiring user access records. However, the basic data for this method includes all knowledge points in the required domain, and the strength calculation unit completes the calculation of the explicit and implicit relationship strengths of all knowledge points. Therefore, this approach is complex, involves too many intermediate variables, involves too much calculation and statistics, and the entire process takes too long.

[0003] In view of this, the present invention is proposed. Summary of the Invention

[0004] The technical problem to be solved by this invention is to overcome the shortcomings of the prior art and provide a domain knowledge association method based on knowledge discovery. This method enables the association of knowledge elements in the form of knowledge network features by identifying knowledge elements that represent the core content of scientific and technological texts, without relying on user historical data, thereby inspiring the discovery of new knowledge.

[0005] To solve the above-mentioned technical problems, the basic concept of the technical solution adopted by the present invention is as follows: According to a first aspect of the embodiments of the present invention, a domain knowledge association method based on knowledge discovery is provided, the method comprising: acquiring domain keywords, generating a text dataset based on text data obtained from the domain keywords; labeling the knowledge elements identified in the text dataset to obtain a knowledge element association dataset; evaluating the knowledge elements in the knowledge element association dataset to obtain a knowledge element association index; and sorting the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their datasets.

[0006] Optionally, the method for generating a text dataset based on the text data obtained from the domain keywords includes: determining the domain knowledge scope based on the acquired domain keywords; and generating a text dataset by cleaning the domain knowledge scope.

[0007] Optionally, the method for labeling the knowledge elements identified in the text dataset includes: using natural language processing methods to identify entities of the knowledge elements in the text dataset, wherein each piece of text data includes at least one knowledge element; and labeling the entities.

[0008] Optionally, the method for evaluating knowledge elements in the knowledge element association dataset and obtaining knowledge element association indicators includes: constructing a knowledge network by using the knowledge elements as network nodes; and calculating knowledge element association indicators in the knowledge element association dataset based on the feature indicators of the knowledge network, wherein the feature indicators include: node importance indicators, community structure indicators, and main path feature indicators.

[0009] Optionally, the method for calculating the knowledge element association index in the knowledge element association dataset based on the feature index of the knowledge network includes: calculating the close association index of the knowledge element based on the node importance index and the community structure index of the knowledge element-text bipartite network; calculating the similarity association index of the knowledge element based on the node importance index and the main path feature index of the knowledge element reference network; and calculating the knowledge element association index in the text dataset according to the close association index and the similarity association index of the knowledge element.

[0010] Optionally, the method for sorting the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their dataset includes: sorting the knowledge element association index in descending order to obtain a knowledge element association dataset sorted based on the knowledge element association index; marking knowledge elements whose scores of the knowledge element association index are within a score threshold to obtain domain knowledge association elements and a domain knowledge association element dataset.

[0011] Optionally, the method for obtaining domain knowledge associated elements and a dataset of domain knowledge associated elements includes: sending the domain knowledge elements to a user interface; receiving user feedback on the domain knowledge elements; if the feedback is positive, exporting the domain knowledge elements and the text data marked by the domain knowledge associated elements, wherein the positive feedback indicates user approval of the domain knowledge elements; if the feedback is negative, re-identifying the knowledge elements in the text dataset, sending the domain knowledge elements to the user interface, receiving user feedback on the domain knowledge elements, and repeating this process until the feedback is positive.

[0012] According to a second aspect of the present invention, a domain knowledge association apparatus based on knowledge discovery is provided. The apparatus includes: a generation device configured to acquire domain keywords and generate a text dataset based on text data obtained from the domain keywords; a labeling device configured to label knowledge elements identified in the text dataset to obtain a knowledge element association dataset; an evaluation device configured to evaluate the knowledge elements in the knowledge element association dataset to obtain a knowledge element association index; and a determination device configured to sort the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their datasets.

[0013] Optionally, the method for generating a text dataset based on text data obtained from the domain keywords includes: determining the domain knowledge scope based on the acquired domain keywords; and generating a text dataset by cleaning the domain knowledge scope.

[0014] Optionally, the labeling device is used to label knowledge elements identified in the text dataset in a method comprising: identifying entities of knowledge elements in the text dataset using natural language processing methods, wherein a single text data includes at least one knowledge element; and labeling the entities.

[0015] Optionally, the evaluation device is used to evaluate the knowledge elements in the knowledge element association dataset and obtain the knowledge element association index. The method includes: constructing a knowledge network by using the knowledge elements as network nodes; and calculating the knowledge element association index in the knowledge element association dataset based on the feature index of the knowledge network, wherein the feature index includes: node importance index, community structure index, and main path feature index.

[0016] Optionally, the evaluation device is used to calculate the knowledge element association index in the knowledge element association dataset based on the feature index of the knowledge network, comprising: calculating the close association index of the knowledge element based on the node importance index and the community structure index of the knowledge element-text bipartite network; calculating the similarity association index of the knowledge element based on the node importance index and the main path feature index of the knowledge element reference network; and calculating the knowledge element association index in the text dataset according to the close association index and the similarity association index of the knowledge element.

[0017] Optionally, the determining device is used to sort the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their dataset. The method includes: sorting the knowledge element association index in descending order to obtain a knowledge element association dataset sorted based on the knowledge element association index; marking knowledge elements whose scores of the knowledge element association index are within a score threshold to obtain domain knowledge association elements and a domain knowledge association element dataset.

[0018] Optionally, the method for obtaining domain knowledge associated elements and a dataset of domain knowledge associated elements in the determining device includes: sending the domain knowledge elements to a user interface; receiving user feedback information on the domain knowledge elements; if the feedback information is positive feedback, exporting the domain knowledge elements and the text data marked by the domain knowledge elements and the domain knowledge associated elements, wherein the positive feedback is user approval of the domain knowledge elements; if the feedback information is negative feedback, re-identifying the knowledge elements in the text dataset, sending the domain knowledge elements to the user interface, receiving user feedback information on the domain knowledge elements, and repeating this process until the feedback information is positive feedback.

[0019] According to a third aspect of the present invention, a computer-readable storage medium is provided, having stored thereon computer program instructions that, when executed by a processor, are used to implement a domain knowledge association method based on knowledge discovery provided by the first aspect of the present disclosure or any embodiment of the first aspect.

[0020] According to a fourth aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute, through the computer program, a domain knowledge association method based on knowledge discovery provided by the first aspect of the present disclosure or any embodiment of the first aspect.

[0021] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: First, domain keywords are obtained, and a text dataset is generated based on the text data obtained from the domain keywords; second, the knowledge elements identified in the text dataset are labeled to obtain a knowledge element association dataset; then, the knowledge elements in the knowledge element association dataset are evaluated to obtain knowledge element association indicators; finally, the knowledge element association dataset is sorted according to the knowledge element association indicators to determine the domain knowledge elements and their datasets. The method proposed in this invention can be independent of user historical data. By using the knowledge elements identified in the text dataset as the core content of scientific and technological texts, the knowledge elements are evaluated, filtered, and updated to obtain a domain knowledge association dataset, thereby inspiring new knowledge discovery, reducing the influence of human factors, and improving the scientificity and applicability of knowledge association measurement.

[0022] The specific embodiments of the present invention will now be described in further detail with reference to the accompanying drawings. Attached Figure Description

[0023] The accompanying drawings, as part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention, but do not constitute an undue limitation of the invention. Obviously, the drawings described below are merely some embodiments, and those skilled in the art can obtain other drawings based on these drawings without creative effort. In the drawings:

[0024] Figure 1 This is a flowchart of a domain knowledge association method based on knowledge discovery according to an embodiment of the present invention;

[0025] Figure 2 This is a data graph of a text dataset according to an embodiment of the present invention;

[0026] Figure 3 This is a knowledge element association dataset data graph according to an embodiment of the present invention;

[0027] Figure 4 This is a block diagram of a domain knowledge association device based on knowledge discovery according to an embodiment of the present invention;

[0028] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present invention.

[0029] It should be noted that these accompanying drawings and textual descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art by referring to specific embodiments. Detailed Implementation

[0030] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0031] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0032] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0033] Example 1

[0034] Figure 1 This is a flowchart of a domain knowledge association method based on knowledge discovery according to an embodiment of the present invention. Figure 1 As shown, it includes steps S101-S104.

[0035] In step S101, domain keywords are obtained, and a text dataset is generated based on the text data obtained from the domain keywords.

[0036] In one embodiment, generating a text dataset based on the text data obtained from the domain keywords includes: determining the domain knowledge scope based on the acquired domain keywords; and generating a text dataset by cleaning the domain knowledge scope.

[0037] The scope of domain knowledge, i.e. the data scope, is determined by the acquired domain keywords. The methods for acquiring domain keywords include: keywords based on user input, keywords based on image recognition, keywords based on speech recognition, etc.

[0038] The data sources for the text dataset include journal articles, conference papers, etc.

[0039] The text dataset consists of bibliographic information, citation information, and a list of text information.

[0040] The fields of a text dataset should include at least: paper title, paper abstract, paper keywords, paper author, author affiliation, publication date, cited references, paper unique identifier, and main text content.

[0041] A text data set is formed by cleaning the data source, data composition, and fields. The cleaning operations include: deleting duplicate data, correcting identifiable errors in the data, and handling invalid and missing values.

[0042] For example, taking carbon fiber materials as an example, entering "carbon fiber" to search yields 4960 SCI-indexed papers. After removing papers irrelevant to this research and those with incomplete information, a text dataset of 3258 entries is obtained, generating a carbon fiber text data set, such as... Figure 2 As shown, Figure 2 This is a data graph of a text dataset according to an embodiment of the present invention.

[0043] In step S102, the knowledge elements identified in the text dataset are labeled to obtain a knowledge element association dataset.

[0044] In this embodiment, the knowledge element has an independent and complete meaning, including knowledge mentioned or referenced in the text data.

[0045] The knowledge elements identified in the text dataset are names representing the core content of the text.

[0046] In one embodiment, a method for labeling knowledge elements identified in the text dataset includes: identifying entities of knowledge elements in the text dataset using natural language processing methods, wherein a single text dataset includes at least one knowledge element; and labeling the entities.

[0047] Methods for labeling knowledge elements include: manually reading and labeling each element; and identifying and labeling knowledge elements in text datasets using a combination of human and machine methods.

[0048] For example, the knowledge elements in the text dataset can be manually read and labeled line by line. Let the content to be labeled be algorithm name, model name, theory name, software name, chemical substance name, etc. Taking carbon fiber as an example, the knowledge elements of the carbon fiber text dataset can be identified by manually reading and labeling line by line. 889 knowledge elements can be obtained, including SiO2, CNTs, steel, concrete, and epoxy, which are recorded in the field "Knowledge Element I".

[0049] For example, natural language processing methods can be used to identify knowledge elements in the text dataset. Let the content to be labeled be named entities. Taking carbon fiber material as an example, the software identifies the named entities in the experimental field of each data point, denoted as knowledge elements, and recorded in the "Knowledge Element II" field. However, the named entities identified by the software may have different descriptions for the same compound; therefore, manual screening and merging are necessary. For instance, the descriptions of carbon fiber material include: carbonfiber, carbon fibre, and CF. After merging, it is recorded as carbon fibre. Figure 3 As shown, Figure 3 This is a knowledge element association dataset data graph according to an embodiment of the present invention.

[0050] In step S103, the knowledge elements in the knowledge element association dataset are evaluated to obtain the knowledge element association index.

[0051] In one embodiment, the knowledge element association dataset is evaluated based on the knowledge element association index in the text dataset, wherein the knowledge element association index in the text dataset is determined based on a knowledge network.

[0052] In this embodiment, the method for evaluating knowledge elements in the knowledge element association dataset and obtaining knowledge element association indicators includes: constructing a knowledge network by using the knowledge elements as network nodes; and calculating knowledge element association indicators in the knowledge element association dataset based on the feature indicators of the knowledge network, wherein the feature indicators include: node importance indicators, community structure indicators, and main path feature indicators.

[0053] First, a knowledge element-text bipartite network is constructed using the knowledge elements and text as network nodes, and node importance and community structure indices are calculated. Then, a knowledge element reference network is constructed using the knowledge elements as network nodes, and node importance and main path feature indices are calculated. Next, based on the node importance and community structure indices of the knowledge element-text bipartite network, the closeness association index of the knowledge elements is calculated. Based on the node importance and main path feature indices of the knowledge element reference network, the similarity association index of the knowledge elements is calculated. Finally, based on the closeness association and similarity association indices of the knowledge elements, the knowledge element association index in the text dataset is calculated.

[0054] The knowledge network includes a knowledge element-text binary network with knowledge elements and text as network nodes, and a knowledge element reference network with knowledge elements as network nodes.

[0055] In one implementation, a knowledge element-text binary network is constructed using knowledge elements and text as network nodes, and its network model is G(U,V,E).

[0056] Where U represents the set of knowledge element nodes, U contains m nodes, U = {u1, u2, ..., u3} m}, u i ∈U; V represents the set of text nodes, V contains n nodes, V={v1,v2.....v n}, v j ∈V; E represents the set of edges of G, where there are no connecting edges within sets U and V.

[0057] The adjacency matrix of G is represented as:

[0058] Among them, 0 m*m With 0 n*n These are the m-th and n-th order zero matrices, respectively; A m*n =(a ij ) m*n , if u i With v j If there is a connecting line between them, then a ij =1, otherwise a ij =0.

[0059] In another implementation, a projection algorithm is used to convert the knowledge element-text bipartite network into a single-mode network. If two knowledge elements appear in a text data sample, an edge is established between the two knowledge elements, and the number of co-occurrences or a function is used as the weight of the edge. The network model of the single-mode network is G″(U,E″,W″).

[0060] Where U represents the set of knowledge element nodes, U contains m nodes, U = {u1, u2, ..., u3} m}, u i ∈U; E″ represents the set of edges of G″; W″ represents the weight of the edges of G″; A″ represents the adjacency matrix of G″, A″ = (a i ′ j ′) m*m .

[0061] If knowledge element u i With knowledge element u j If they appear simultaneously in the same text data sample, it indicates that G" contains u i with u j There are connecting edges between them, and the weight of the edge depends on u. i with u j The co-occurrence frequency.

[0062] In another implementation, a knowledge element reference network is constructed using knowledge elements as nodes, wherein the network model of the knowledge element reference network is G′(U,E′,W′).

[0063] Where U represents the set of knowledge element nodes, U contains m nodes, U = {u1, u2, ..., u3} m}, u i ∈U; E' represents the set of edges of G'; W' represents the weight of the edges of G'; A' represents the adjacency matrix of G', A′=(a i ′ j ) m*m .

[0064] If knowledge element u i The text referenced by the text contains the knowledge element u. j This means that there is a rule in G' consisting of u i Point to u j The weight of an edge depends on u. i with u j The frequency of citations between texts.

[0065] Taking carbon fiber material as an example, the correlation indices of knowledge elements graphene oxide, CNTs, steel, alalloy, and epoxy calculated based on knowledge networks are 0.45, 0.69, 0.53, 0.20, and 0.66, respectively.

[0066] In step S104, the knowledge element association dataset is sorted according to the knowledge element association index to determine the domain knowledge elements and their datasets.

[0067] In one embodiment, the method for sorting the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their dataset includes: sorting the knowledge element association index in descending order to obtain a knowledge element association dataset sorted based on the knowledge element association index; marking knowledge elements whose scores of the knowledge element association index are within a score threshold to obtain domain knowledge association elements and a domain knowledge association element dataset.

[0068] The domain knowledge association element dataset is obtained by sorting the knowledge element association indicators in descending order and taking the text data labeled by the top-ranked knowledge elements to form a new dataset.

[0069] The method for obtaining domain knowledge associated elements and a domain knowledge associated element dataset includes: sending the domain knowledge elements to a user interface; receiving user feedback information on the domain knowledge elements; if the feedback information is positive, exporting the domain knowledge elements and the text data marked by the domain knowledge associated elements, wherein the positive feedback indicates that the user approves of the domain knowledge elements; if the feedback information is negative, re-identifying the knowledge elements in the text dataset to form an updated knowledge element associated dataset, recalculating the knowledge element association index, sorting the updated knowledge element associated dataset according to the recalculated knowledge element association index, re-outputting the domain knowledge elements, obtaining user feedback information on the domain knowledge elements again, and repeating the process until positive feedback is obtained.

[0070] Taking carbon fiber materials as an example, knowledge elements are sorted in descending order of their association index scores. Knowledge elements such as CFRP, CF / epoxy, epoxy, and CNTs are selected and filtered to obtain 1176 text data entries containing these knowledge elements. This constitutes the domain knowledge association elements and dataset for carbon fiber. After obtaining the carbon fiber knowledge element association dataset, comments on the knowledge elements and their association indices are acquired and provided to users for new knowledge discovery. For example, if the first output of domain knowledge elements is: CFRP, CF / epoxy, epoxy, CNTs, etc., and the second output of domain knowledge elements is: Araldite LY556, CNTs modified epoxy, MWCNTs, maleic anhydride, graphenenanoplatelets, etc., then these knowledge elements are provided to users for new knowledge discovery.

[0071] This invention provides a domain knowledge association method based on knowledge discovery. It determines the scope of domain knowledge by obtaining domain keywords, thereby generating a text dataset. By labeling knowledge elements in the text dataset, a knowledge element association dataset is obtained. Based on this dataset, a knowledge element association network is constructed, and the association index score for each knowledge element is calculated. The obtained knowledge elements and their dataset are then displayed to the user to facilitate the discovery of new knowledge. With the continuous improvement of computer technology and text processing technology, this invention does not rely on historical user data. By using identified knowledge elements to represent the core content of scientific and technological texts and representing the associations between knowledge elements in the form of knowledge network features, it simplifies the process for users to obtain domain knowledge associations, reduces intermediate variable calculations, improves processing efficiency, and enhances the practicality of the data text. Furthermore, expressing knowledge element associations in the form of knowledge network features provides a more objective understanding of the associations established from the perspective of text content.

[0072] Example 2

[0073] Figure 4 This is a block diagram of a domain knowledge association device based on knowledge discovery according to an embodiment of the present invention, such as... Figure 4 As shown, the device 400 includes a generating device 401, a marking device 402, an evaluation device 403, and a determining device 404.

[0074] The generation device 401 is configured to acquire domain keywords and generate a text dataset based on the text data obtained from the domain keywords;

[0075] The labeling device 402 is configured to label the knowledge elements identified in the text dataset to obtain a knowledge element association dataset;

[0076] Evaluation device 403 is configured to evaluate knowledge elements in the knowledge element association dataset and obtain knowledge element association index;

[0077] The determining device 404 is configured to sort the knowledge element association dataset according to the knowledge element association index, and determine the domain knowledge element and its dataset.

[0078] Optionally, the method for generating a text dataset using the generation device 401 based on the text data obtained from the domain keywords includes: determining the domain knowledge scope based on the acquired domain keywords; and generating a text dataset by cleaning the domain knowledge scope.

[0079] Optionally, the labeling device 402 is used to label knowledge elements identified in the text dataset in a method comprising: identifying entities of knowledge elements in the text dataset using natural language processing methods, wherein a single text data includes at least one knowledge element; and labeling the entities.

[0080] Optionally, the evaluation device 403 is used to evaluate the knowledge elements in the knowledge element association dataset and obtain the knowledge element association index. The method includes: constructing a knowledge network by using the knowledge elements as network nodes; and calculating the knowledge element association index in the knowledge element association dataset based on the feature index of the knowledge network, wherein the feature index includes: node importance index, community structure index, and main path feature index.

[0081] Optionally, the evaluation device 403 is used to calculate the knowledge element association index in the knowledge element association dataset based on the feature index of the knowledge network, including: calculating the close association index of the knowledge element based on the node importance index and the community structure index of the knowledge element-text bipartite network; calculating the similarity association index of the knowledge element based on the node importance index and the main path feature index of the knowledge element reference network; and calculating the knowledge element association index in the text dataset according to the close association index and the similarity association index of the knowledge element.

[0082] Optionally, the determining device 404 is used to sort the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their dataset. The method includes: sorting the knowledge element association index in descending order to obtain a knowledge element association dataset sorted based on the knowledge element association index; marking the knowledge elements whose scores of the knowledge element association index are within a score threshold to obtain domain knowledge association elements and a domain knowledge association element dataset.

[0083] Optionally, the method for obtaining domain knowledge associated elements and a dataset of domain knowledge associated elements in the determining device 404 includes: sending the domain knowledge elements to a user interface; receiving user feedback information on the domain knowledge elements; if the feedback information is positive feedback, exporting the domain knowledge elements and the text data marked by the domain knowledge elements and the domain knowledge associated elements, wherein the positive feedback is user approval of the domain knowledge elements; if the feedback information is negative feedback, re-identifying the knowledge elements in the text dataset, sending the domain knowledge elements to the user interface, receiving user feedback information on the domain knowledge elements, and repeating this process until the feedback information is positive feedback.

[0084] Regarding the apparatus in the above embodiments, the specific manner in which each apparatus performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0085] Example 3

[0086] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present invention. Please refer to the attached diagram. Figure 5 The diagram illustrates the structure of the device, which includes a memory and a processor. The memory stores computer instructions that can run on the processor, and the processor executes the computer instructions to implement the methods described in any embodiment of this disclosure.

[0087] The present invention also provides a computer-readable storage medium having stored thereon computer program instructions, which, when executed by a processor, implement the steps of a domain knowledge association method based on knowledge discovery provided by the present invention.

[0088] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This specification also provides a computer-readable storage medium on which a computer program can be stored. When executed by a processor, the program implements the steps of the domain knowledge association method based on knowledge discovery described in any embodiment of this specification, and / or implements the steps of the domain knowledge association method based on knowledge discovery described in any embodiment of this specification. The term "and / or" indicates at least one of two options; for example, "A and / or B" includes three options: A, B, and "A and B".

[0090] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the data processing device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0091] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0093] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0094] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0095] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0096] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0097] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0098] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0099] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-described technical content to create equivalent embodiments without departing from the scope of the present invention. The implementation schemes in the above embodiments can also be further combined or replaced. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A domain knowledge association method based on knowledge discovery, characterized in that, include: Obtain domain keywords, and generate a text dataset based on the text data obtained from the domain keywords; The knowledge elements identified in the text dataset are labeled to obtain a knowledge element association dataset. Evaluate the knowledge elements in the aforementioned knowledge element association dataset to obtain the knowledge element association index; The knowledge element association datasets are sorted according to the knowledge element association index to determine the domain knowledge elements and their datasets. The method for evaluating knowledge elements in the knowledge element association dataset and obtaining knowledge element association indicators includes: constructing a knowledge network by using the knowledge elements as network nodes. Based on the feature indicators of the knowledge network, the knowledge element association indicators in the knowledge element association dataset are calculated, wherein the feature indicators include: node importance indicators, community structure indicators, and main path feature indicators. The method for calculating the knowledge element association index in the knowledge element association dataset based on the feature index of the knowledge network includes: Based on the node importance index and community structure index of the knowledge element-text binary network, the close association index of the knowledge element is calculated. Based on the node importance index and the main path feature index of the knowledge element reference network, the similarity association index of the knowledge element is calculated. Calculate the knowledge element association index in the text dataset based on the closeness association index and the similarity association index of the knowledge elements.

2. The domain knowledge association method based on knowledge discovery according to claim 1, characterized in that, The method for generating a text dataset based on text data obtained from the domain keywords includes: Based on the acquired domain keywords, the scope of domain knowledge is determined; A text dataset is generated by cleaning the knowledge scope of the domain.

3. The domain knowledge association method based on knowledge discovery according to claim 1, characterized in that, The method for labeling knowledge elements identified in the text dataset includes: The entity of the knowledge element in the text dataset is identified using natural language processing methods, wherein each text data includes at least one knowledge element; The entity is marked.

4. The domain knowledge association method based on knowledge discovery according to claim 1, characterized in that, The method for sorting the knowledge element association dataset according to the knowledge element association index to determine the domain knowledge elements and their datasets includes: By sorting the knowledge element association indicators in descending order, a knowledge element association dataset sorted based on the knowledge element association indicators is obtained. The knowledge elements whose scores in the association index are within the score threshold are labeled to obtain the domain knowledge association elements and the domain knowledge association element dataset.

5. The domain knowledge association method based on knowledge discovery according to claim 4, characterized in that, The method for obtaining domain knowledge association elements and the domain knowledge association element dataset includes: Send the domain knowledge elements to the user interface; Receive user feedback on the domain knowledge elements; If the feedback information is positive feedback, then the text data marked by the domain knowledge element and the domain knowledge related element are exported, wherein the positive feedback is the user's recognition of the domain knowledge element; If the feedback is negative, the knowledge elements in the text dataset are re-identified, and the domain knowledge elements are sent to the user interface. The user's feedback on the domain knowledge elements is received, and this process is repeated until the feedback is positive.

6. A domain knowledge association apparatus that applies the domain knowledge association method based on knowledge discovery as described in any one of claims 1-5, characterized in that, include: A generation device is configured to acquire domain keywords and generate a text dataset based on text data obtained from the domain keywords. A labeling device is configured to label knowledge elements identified in the text dataset to obtain a knowledge element association dataset; An evaluation device is configured to evaluate knowledge elements in the knowledge element association dataset to obtain knowledge element association indicators; The determining device is configured to sort the knowledge element association dataset according to the knowledge element association index, and determine the domain knowledge element and its dataset.

7. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the domain knowledge association method based on knowledge discovery as described in any one of claims 1 to 5 through the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the domain knowledge association method based on knowledge discovery as described in any one of claims 1 to 5.

Images