A knowledge recommendation method and device, and a storage medium

Abstract

The application belongs to the technical field of database and data platform construction, and particularly relates to a knowledge recommendation method and device and a storage medium, wherein the method comprises the following steps: firstly, acquiring a domain keyword, and generating a first text data set based on text data obtained based on the domain keyword; then, generating a second text data set by evaluating first knowledge elements in the first text data set; and finally, generating a knowledge recommendation result by evaluating second knowledge elements in the second text data set. The method provided by the application can not be limited by a knowledge domain, the core content of text data is evaluated multiple times to generate a knowledge recommendation result, high matching degrees among knowledge elements are realized, and the concepts among knowledge and knowledge correlations are clear.

Description

Technical Field

[0001] This invention belongs to the field of database and data platform construction technology, specifically, it relates to a knowledge recommendation method, device and storage medium. Background Technology

[0002] As the primary carriers and disseminators of knowledge, scientific and technological literature contains a wealth of undiscovered scientific knowledge. The discovery of these implicit connections is more significant than the increase in information itself. Typically, the implicit knowledge contained in literature can only be acquired by researchers through reading each article. However, with the rapid pace of scientific and technological development, the number of different types of scientific and technological literature, such as scientific papers, patents, and scientific reports, is exploding. Simultaneously, driven by big data technology, human scientific research activities are undergoing a transformation from a "computational science paradigm" to a "data-intensive scientific discovery paradigm." Therefore, automatically extracting potentially useful knowledge and information from literature has become particularly urgent. The core task of information services is to meet users' knowledge needs through knowledge retrieval. Users can locate the knowledge they need through search, thus clarifying their goals for further knowledge acquisition. Currently, to accurately reflect the relevance of knowledge, knowledge service systems based on knowledge graphs have emerged. For example, knowledge graphs provide retrieval services for disease and drug knowledge, visually representing the relationships between core concepts to help doctors understand the development of academic research and discover connections between knowledge points. Building knowledge graphs from large-scale, multi-source, heterogeneous medical text data can significantly improve the matching accuracy of knowledge retrieval. However, this also poses significant challenges to the data processing efficiency of computing devices, the storage capacity of storage devices, and memory access efficiency. Currently, the knowledge domain has a wide variety of entities with complex relationships, making it impossible to generate structured knowledge graphs from unstructured text data. On the other hand, the current operation of matching by simply searching for keywords ignores the relevance between knowledge, resulting in the output containing a large amount of useless knowledge as well as isolated useful knowledge.

[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 knowledge recommendation method, so that when users perform knowledge retrieval, they can be free from the limitation of knowledge domain, and by identifying knowledge elements that represent the core content of the text, and comprehensively considering its network structure characteristics and temporal characteristics, to achieve knowledge recommendation.

[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 knowledge recommendation method is provided, the method comprising: acquiring domain keywords; generating a first text dataset based on text data obtained from the domain keywords; generating a second text dataset by evaluating a first knowledge element in the first text dataset; and generating a knowledge recommendation result by evaluating a second knowledge element in the second text dataset.

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

[0007] Optionally, the first knowledge element includes: the paper title field of the first text dataset, the paper keyword field of the first text dataset, and the paper abstract field of the first text dataset.

[0008] Optionally, the second knowledge element includes: the text content field of the second text dataset.

[0009] Optionally, before evaluating the knowledge elements in the text dataset, the method further includes labeling the knowledge elements in the text dataset using machine learning, including: randomly selecting a target number of text data in the text dataset for labeling to establish a knowledge element training set; randomly selecting a target number of text data in the text dataset as a knowledge element test set; training a model on the knowledge element training set and establishing a knowledge element recognition model based on the knowledge element features in the knowledge element training set; detecting the knowledge element recognition model based on the knowledge element test set and the knowledge element training set, obtaining a score for the knowledge element recognition model, and using the knowledge element recognition model with the highest score as the target knowledge element recognition model; and recognizing the text information in the text dataset according to the target knowledge element recognition model and labeling it as a knowledge element.

[0010] Optionally, the method for evaluating knowledge elements in the text dataset includes: using a complex network method to evaluate the relevance of the knowledge elements in the text dataset and obtain a relevance score; using the temporal features of the network to evaluate the trend of the knowledge elements in the text dataset and obtain a trend score; and performing a weighted average of the relevance score and the trend score according to the weight coefficients corresponding to the relevance score and the trend score to obtain a standard score for the knowledge elements in the text dataset.

[0011] Optionally, generating the knowledge recommendation result includes: sorting the standard scores of the second knowledge element in descending order to obtain a second text dataset in descending order; obtaining the second knowledge element with the highest target percentage in the second text dataset in descending order; and generating the knowledge recommendation result based on the text data labeled by the second knowledge element.

[0012] According to a second aspect of the present invention, a knowledge recommendation apparatus is provided, the apparatus comprising: a first generation device configured to acquire domain keywords and generate a first text dataset based on text data obtained from the domain keywords; a second generation device configured to generate a second text dataset by evaluating a first knowledge element in the first text dataset; and a third generation device configured to generate a knowledge recommendation result by evaluating a second knowledge element in the second text dataset.

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

[0014] Optionally, the first knowledge element in the second generation device includes: the paper title field of the first text dataset, the paper keyword field of the first text dataset, and the paper abstract field of the first text dataset.

[0015] Optionally, the second knowledge element in the third generation device includes: the text content field of the second text dataset.

[0016] Optionally, before the second or third generation device evaluates the knowledge elements in the text dataset, it further includes labeling the knowledge elements in the text dataset using a machine learning method, including: randomly selecting a target number of text data in the text dataset for labeling to establish a knowledge element training set; randomly selecting a target number of text data in the text dataset as a knowledge element test set; training a model on the knowledge element training set and establishing a knowledge element recognition model based on the knowledge element features in the knowledge element training set; detecting the knowledge element recognition model based on the knowledge element test set and the knowledge element training set, obtaining a score for the knowledge element recognition model, and using the knowledge element recognition model with the highest score as the target knowledge element recognition model; and recognizing the text information in the text dataset according to the target knowledge element recognition model and labeling it as a knowledge element.

[0017] Optionally, the method for evaluating knowledge elements in a text dataset using the second or third generating device includes: evaluating the relevance of knowledge elements in the text dataset using a complex network method to obtain a relevance score; evaluating the trend of knowledge elements in the text dataset using the temporal features of the network to obtain a trend score; and performing a weighted average of the relevance score and the trend score based on the weight coefficients corresponding to the relevance score and the trend score to obtain a standard score for the knowledge elements in the text dataset.

[0018] Optionally, the third generation device is used to generate knowledge recommendation results, including: sorting the standard scores of the second knowledge elements in descending order to obtain a second text dataset in descending order; obtaining the second knowledge elements with the highest target percentage in the second text dataset in descending order; and generating knowledge recommendation results based on the text data labeled by the second knowledge elements.

[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 knowledge recommendation method provided by the first aspect of the present disclosure or any of the embodiments 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 knowledge recommendation method 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 first text dataset is generated based on the text data obtained from the domain keywords; then, a second text dataset is generated by evaluating the first knowledge elements in the first text dataset; finally, a knowledge recommendation result is generated by evaluating the second knowledge elements in the second text dataset. The method provided by the present invention is not limited by the knowledge domain, and generates knowledge recommendation results by evaluating the core content of the text data multiple times, thereby achieving a high degree of matching between knowledge elements and making the concepts between knowledge and knowledge associations clear.

[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 knowledge recommendation method according to an embodiment of the present invention;

[0025] Figure 2 This is a block diagram of a knowledge recommendation device according to an embodiment of the present invention;

[0026] Figure 3 This is a block diagram of an electronic device according to an embodiment of the present invention.

[0027] 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

[0028] 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.

[0029] 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.

[0030] 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."

[0031] Example 1

[0032] Figure 1 This is a flowchart of a knowledge recommendation method according to an embodiment of the present invention. Figure 1 As shown, it includes steps S101-S103.

[0033] In step S101, domain keywords are obtained, and a first text dataset is generated based on the text data obtained from the domain keywords.

[0034] In this embodiment, the content of the first text dataset includes a collection of all text data generated using the acquired domain keywords as indexes. The acquisition methods include: keywords based on user input, keywords based on character recognition, keywords based on speech recognition, keywords based on image recognition, etc.

[0035] The first text dataset includes: bibliographic information, citation information, and text information.

[0036] The fields of the first text dataset include at least: title, abstract, keywords, author, author affiliation, publication date, cited references, unique identifier, and main text content.

[0037] The method for generating a first text dataset based on text data obtained from the domain keywords includes: determining the domain knowledge scope based on the domain keywords; generating a first text dataset by cleaning the domain knowledge scope, wherein the scope of the domain knowledge, i.e., the data scope limitation, is determined by the obtained domain keywords. The method further involves setting the domain knowledge scope based on the obtained search terms and obtaining scientific literature data to generate the first text dataset.

[0038] The scientific and technological literature data includes, but is not limited to, scientific and technological books, scientific and technological journals, scientific and technological reports, patent specifications, conference proceedings, dissertations, product information, and technical archives.

[0039] For example, taking carbon fiber materials as an example, a total of 4,960 journal articles were retrieved and downloaded using "carbon fiber" as the subject. After removing papers with irrelevant research content and incomplete information, 3,258 text data entries were finally obtained, thus forming the first text data set of carbon fiber. Its fields include "paper title", "paper keywords", "paper abstract", "paper author", "author affiliation", "cited references", "introduction", "experiment", "discussion", "introduction", "publication time", "paper source", "paper unique identifier", and "paper type".

[0040] In step S102, a second text dataset is generated by evaluating the first knowledge elements in the first text dataset.

[0041] In this embodiment, the first knowledge element has a relatively independent and complete meaning, including knowledge mentioned or cited in text data based on scientific and technological literature data. The first knowledge element includes: the paper title field of the first text dataset, the paper keyword field of the first text dataset, and the paper abstract field of the first text dataset.

[0042] Before evaluating the knowledge elements in the text dataset, the method further includes labeling the knowledge elements in the text dataset using machine learning, including: randomly selecting a target number of text data in the text dataset for labeling to establish a knowledge element training set; randomly selecting a target number of text data in the text dataset as a knowledge element test set; training a model on the knowledge element training set and establishing a knowledge element recognition model based on the knowledge element features in the knowledge element training set; detecting the knowledge element recognition model based on the knowledge element test set and the knowledge element training set, obtaining a score for the knowledge element recognition model, and using the knowledge element recognition model with the highest score as the target knowledge element recognition model; and identifying the text information in the text dataset according to the target knowledge element recognition model and labeling it as a knowledge element.

[0043] In this embodiment, the knowledge elements in the text dataset are evaluated twice. The first evaluation is performed on the first knowledge element in the first text dataset to generate the second text dataset; the second evaluation is performed on the second knowledge element in the second text dataset to generate the third text dataset. Furthermore, in this embodiment, the knowledge elements in the text dataset are first labeled before evaluation.

[0044] The method for labeling a first knowledge element in a first text dataset includes: randomly selecting a target number of text data from the first text dataset for labeling to establish a first knowledge element training set; randomly selecting a target number of text data from the first text dataset as a first knowledge element test set; training a model on the first knowledge element training set and establishing a first knowledge element recognition model based on the knowledge element features in the first knowledge element training set; detecting the first knowledge element recognition model based on the first knowledge element test set and the first knowledge element training set, obtaining a score for the knowledge element recognition model, and sorting the knowledge element recognition models in descending order according to the score to obtain a first target knowledge element recognition model; and recognizing text information in the first text dataset according to the first target knowledge element recognition model and labeling it as a first knowledge element.

[0045] The method for constructing a second text dataset by evaluating a first knowledge element in the first text dataset includes: using a complex network method to evaluate the relevance of the first knowledge element in the first text dataset and obtain a first relevance score; using the temporal characteristics of the network to evaluate the trend of the first knowledge element in the first text dataset and obtain a first trend score; performing a weighted average of the first relevance score and the first trend score according to the weight coefficients corresponding to the first relevance score and the first trend score to obtain a standard score of the first knowledge element in the first text dataset; sorting the standard scores of the first knowledge elements in descending order to obtain a first text dataset in descending order; obtaining the top target percentage of knowledge elements in the first text dataset in descending order, and constructing a second text dataset based on the text data labeled by the knowledge elements.

[0046] For example, taking carbon fiber materials as an example, the first knowledge element can be an algorithm name, model name, theory name, software name, chemical substance name, etc. When the knowledge elements of the first text data set of carbon fiber are labeled, the knowledge elements of the carbon fiber text dataset can be identified based on the fields of "paper title" and "paper keywords", including 889 first knowledge elements such as SiO2, CNTs, steel, concrete, and epoxy, and listed in the field "first knowledge element".

[0047] After evaluating the first carbon fiber text dataset and generating the first carbon fiber text dataset in descending order, the text data labeled by the top 287 first knowledge elements, which account for 80% of the total number of papers, were used to form the second text dataset.

[0048] In step S103, a knowledge recommendation result is generated by evaluating the second knowledge elements in the second text dataset.

[0049] In this embodiment, the second knowledge element has a relatively independent and complete meaning, represented by a named entity that represents the core content of scientific and technological literature. The second knowledge element includes the text content field of the second text dataset.

[0050] The method for labeling second knowledge elements in a second text dataset includes: randomly selecting a target number of text data from the second text dataset for labeling to establish a training set for second knowledge elements; randomly selecting a target number of text data from the second text dataset as a test set for second knowledge elements; training a model on the training set for second knowledge elements and establishing a second knowledge element recognition model based on the knowledge element features in the training set; detecting the second knowledge element recognition model based on the test set and the training set, obtaining a score for the recognition model, and sorting the recognition models in descending order based on the score to obtain a second target knowledge element recognition model; and recognizing text information in the second text dataset using the second target knowledge element recognition model and labeling it as a second knowledge element.

[0051] A method for generating knowledge recommendation results by evaluating second knowledge elements in the second text dataset includes: using a complex network method to evaluate the relevance of the second knowledge elements in the second text dataset and obtain a second relevance score; using the temporal features of the network to evaluate the trend of the second knowledge elements in the second text dataset and obtain a second trend score; taking a weighted average of the second relevance score and the second trend score according to the weight coefficients corresponding to the second relevance score and the second trend score to obtain a standard score of the second knowledge elements in the second text dataset; sorting the standard scores of the second knowledge elements in descending order to obtain a descending-ordered second text dataset; obtaining the top target percentage of knowledge elements in the descending-ordered second text dataset, and generating knowledge recommendation results based on the text data labeled by the knowledge elements.

[0052] For example, taking carbon fiber materials as an example, when evaluating the second text dataset of carbon fiber and generating the second text dataset of carbon fiber in descending order, the top 69 second knowledge elements, which account for 50% of the total number of papers, are taken. Among them, there are 48 text data labeled by the second knowledge elements. Recommendation results are generated based on these 48 text data and output to the user.

[0053] This application provides a knowledge recommendation method based on complex knowledge networks. First, domain keywords are obtained, and a first text dataset is generated based on the text data obtained from the domain keywords. Then, a second text dataset is generated by evaluating the first knowledge elements in the first text dataset. Finally, a knowledge recommendation result is generated by evaluating the second knowledge elements in the second text dataset. This application's solution is not limited by knowledge domain; it generates knowledge recommendation results by evaluating the core content of the text data multiple times, achieving a high degree of matching between knowledge elements and making the concepts of knowledge and knowledge associations clear. By comprehensively considering network structure features and temporal features, knowledge recommendation is completed. It has high knowledge matching degree, small data storage volume, and convenient computation. Furthermore, the concepts of knowledge and knowledge associations in this method are clear, and with the continuous improvement of computer technology and text processing technology, it has strong practicality.

[0054] Example 2

[0055] Figure 2 This is a block diagram of a knowledge recommendation device according to an embodiment of the present invention, such as... Figure 2 As shown, the device 200 includes a first generating device 201, a second generating device 202, and a third generating device 203.

[0056] The first generation device 201 is configured to acquire domain keywords and generate a first text dataset based on text data obtained from the domain keywords.

[0057] The second generation device 202 is configured to generate a second text dataset by evaluating a first knowledge element in the first text dataset;

[0058] The third generation device 203 is configured to generate knowledge recommendation results by evaluating the second knowledge elements in the second text dataset.

[0059] Optionally, the method for the first generating device 201 to generate a first text dataset based on text data obtained from the domain keywords includes: determining the domain knowledge scope based on the domain keywords; and generating the first text dataset by cleaning the domain knowledge scope.

[0060] Optionally, the first knowledge element in the second generation device 202 includes: the paper title field of the first text dataset, the paper keyword field of the first text dataset, and the paper abstract field of the first text dataset.

[0061] Optionally, the second knowledge element in the third generation device 203 includes: the text content field of the second text dataset.

[0062] Optionally, before the second generation device 202 or the third generation device 203 evaluates the knowledge elements in the text dataset, it further includes labeling the knowledge elements in the text dataset using a machine learning method, including: randomly selecting a target number of text data in the text dataset for labeling to establish a knowledge element training set; randomly selecting a target number of text data in the text dataset as a knowledge element test set; training a model on the knowledge element training set, and establishing a knowledge element recognition model based on the knowledge element features in the knowledge element training set; detecting the knowledge element recognition model based on the knowledge element test set and the knowledge element training set, obtaining a score for the knowledge element recognition model, and using the knowledge element recognition model with the highest score as the target knowledge element recognition model; and recognizing the text information in the text dataset according to the target knowledge element recognition model and labeling it as a knowledge element.

[0063] Optionally, the method for evaluating knowledge elements in a text dataset by the second generation device 202 or the third generation device 203 includes: using a complex network method to evaluate the relevance of the knowledge elements in the text dataset and obtain a relevance score; using the temporal characteristics of the network to evaluate the trend of the knowledge elements in the text dataset and obtain a trend score; and performing a weighted average of the relevance score and the trend score according to the weight coefficients corresponding to the relevance score and the trend score to obtain a standard score for the knowledge elements in the text dataset.

[0064] Optionally, the third generation device 203 is used to generate knowledge recommendation results, including: sorting the standard scores of the second knowledge elements in descending order to obtain a second text dataset in descending order; obtaining the second knowledge elements with the highest target percentage in the second text dataset in descending order; and generating knowledge recommendation results based on the text data labeled by the second knowledge elements.

[0065] 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.

[0066] Example 3

[0067] Figure 3 This is a block diagram of an electronic device according to an embodiment of the present invention. Please refer to the attached diagram. Figure 3 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.

[0068] The present invention also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of a knowledge recommendation method provided by the present invention.

[0069] 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.

[0070] 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 knowledge recommendation method described in any embodiment of this specification, and / or implements the steps of the knowledge recommendation method 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".

[0071] 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.

[0072] 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.

[0073] 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 or control of the operation of a knowledge recommendation device. 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 knowledge recommendation device. 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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 knowledge recommendation method, characterized in that, include: Obtain domain keywords, determine the domain knowledge scope based on the domain keywords, and generate a first text dataset by cleaning the domain knowledge scope; The relevance of the first knowledge element in the first text dataset is evaluated using a complex network method, and the trend of the first knowledge element is evaluated using the temporal features of the network. The standard score of the first knowledge element is determined by the weighted average of the first relevance score obtained by the relevance evaluation and the first trend score obtained by the trend evaluation. The first text dataset is obtained by sorting the standard scores of the first knowledge element in descending order; the knowledge elements with the highest target percentage in the first text dataset are obtained, and the text data labeled by the knowledge elements are used to form a second text dataset. The relevance of the second knowledge element in the second text dataset is evaluated using a complex network method, and the trend of the second knowledge element is evaluated using the temporal features of the network. The standard score of the second knowledge element is determined by the weighted average of the second relevance score obtained by the relevance evaluation and the second trend score obtained by the trend evaluation. By sorting the standard scores of the second knowledge element in descending order, a second text dataset in descending order is obtained. The second knowledge element with the highest target percentage in the second text dataset in descending order is obtained. Knowledge recommendation results are generated based on the text data labeled by the second knowledge element.

2. The knowledge recommendation method according to claim 1, characterized in that, The first knowledge element includes: the paper title field of the first text dataset, the paper keyword field of the first text dataset, and the paper abstract field of the first text dataset.

3. The knowledge recommendation method according to claim 1, characterized in that, The second knowledge element includes: the text content field of the second text dataset.

4. The knowledge recommendation method according to claim 2 or 3, characterized in that, Before evaluating the knowledge elements in the text dataset, the method further includes labeling the knowledge elements in the text dataset using machine learning methods, including: A target number of text data are randomly selected from the text dataset and labeled to establish a knowledge element training set. A target number of text data are randomly selected from the text dataset as the knowledge element test set; The model is trained on the knowledge element training set, and a knowledge element recognition model is established based on the characteristics of the knowledge elements in the knowledge element training set. The knowledge element recognition model is tested based on the knowledge element test set and the knowledge element training set, and a score of the knowledge element recognition model is obtained. The knowledge element recognition model with the highest score is taken as the target knowledge element recognition model. Based on the target knowledge element recognition model, the text information in the text dataset is identified and marked as knowledge elements.

5. The knowledge recommendation method according to claim 1, characterized in that, A method for evaluating knowledge elements in the text dataset includes: Using complex network methods, the relevance of knowledge elements in the text dataset is evaluated to obtain a relevance score; By utilizing the temporal characteristics of the network, trend evaluation is performed on the knowledge elements in the text dataset to obtain trend scores; Based on the weight coefficients corresponding to the relevance score and the trend score, a weighted average is performed on the relevance score and the trend score to obtain the standard score of the knowledge element in the text dataset.

6. A knowledge recommendation device using the method of any one of claims 1 to 5, characterized in that, include: A first generation device is configured to acquire domain keywords and generate a first text dataset based on text data obtained from the domain keywords. The second generation device is configured to generate a second text dataset by evaluating a first knowledge element in the first text dataset. The third generating device is configured to generate knowledge recommendation results by evaluating the second knowledge elements in the second text 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 method of 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 method of any one of claims 1 to 5.

Images