Entry processing method and device for knowledge sharing platform

Abstract

The invention discloses an entry processing method and device for a knowledge sharing platform, and the method comprises the steps: obtaining the detailed parameter information of an unfamiliar entry on the knowledge sharing platform, and determining a multi-dimensional evaluation score of the unfamiliar entry according to the detailed parameter information; determining whether the unfamiliar entries meet the display requirements of the knowledge sharing platform or not based on the multi-dimensional evaluation scores, and if yes, calling correlation storage entry parameters of the unfamiliar entries from the knowledge sharing platform; determining semantic feature similarity between the correlation storage entry parameters and entry parameters of the unfamiliar entries, and extracting valued information of the unfamiliar entries based on the semantic feature similarity; and associating the valued information with the unfamiliar entries, and storing the valued information and the unfamiliar entries on a knowledge sharing platform for resource allocation. Qualification, normalization and integrity of secondary entry parameters can be guaranteed, entry data quality is guaranteed, sensitive, false and illegal information of entries is prevented, storage memory of a platform is saved, and value of entry content can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a term processing method and device for a knowledge sharing platform. Background Art

[0002] At present, with the rapid development of Internet technology, more and more content can be provided to users on the Internet, and Internet users are more inclined to search for the content they want to know on the Internet. However, when users search for the content they want to know on the Internet, the results that the Internet can provide are usually too complicated and may not be very relevant to the content that users want to know, which makes users feel very inconvenient. The knowledge sharing platform provided on the Internet is an online data application that allows users to check the required knowledge and factual information, and usually provides users with relevant knowledge content in the form of entries. And because the Internet can provide more abundant information, the entry content that can be provided by the current Internet encyclopedia application is becoming more and more detailed, including not only the description of the entry, but also some other content related to the entry. The knowledge sharing platform is edited by a large number of users for various entries to help people in need to understand. When a new entry is uploaded, it will be reviewed and approved by the system. When the system recognizes the uploaded entry, it will search the platform database. When it is found that it is not stored, it is determined to be qualified for storage and stored. However, there are the following problems: the specific parameters of the uploaded entry are not deeply evaluated, resulting in the uploaded entry information having low reference value and quality, and even involving sensitive, false and illegal information, which reduces the user experience. Summary of the invention

[0003] In response to the above-mentioned problems, the present invention provides a method and device for processing entries on a knowledge sharing platform to solve the problem mentioned in the background technology that the platform system review fails to conduct an in-depth evaluation of the specific parameters of the uploaded entries, resulting in the uploaded entry information having a low reference value and low quality, and even involving sensitive, false and illegal information, thereby reducing the user experience.

[0004] A method for processing entries on a knowledge sharing platform comprises the following steps:

[0005] Obtain detailed parameter information of unfamiliar terms on the knowledge sharing platform, and determine multi-dimensional evaluation scores of the unfamiliar terms based on the detailed parameter information;

[0006] Determine whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieve the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform;

[0007] Determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term, and extract the value information of the unfamiliar term based on the semantic feature similarity;

[0008] Associate valuable information with unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

[0009] Preferably, the obtaining of detailed parameter information of the unfamiliar terms on the knowledge sharing platform and determining the multi-dimensional evaluation scores of the unfamiliar terms according to the detailed parameter information includes:

[0010] Obtain the uploaded term on the knowledge sharing platform, confirm whether the uploaded term is a stored term, and if not, set the uploaded term as an unfamiliar term;

[0011] Obtain definition parameters, category parameters, characteristic parameters, application scenario parameters, and related term explanation parameters of the unfamiliar term as detailed parameter information;

[0012] Obtaining multidimensional evaluation indicators, and determining evaluation content of detailed parameter information of unfamiliar terms according to the multidimensional evaluation indicators;

[0013] Perform multi-dimensional evaluation on the evaluation content of unfamiliar terms based on multi-dimensional evaluation indicators and preset scoring rules to obtain a comprehensive score;

[0014] Among them, the multiple dimensions include: content standardization, content completeness, content readability and content value.

[0015] Preferably, the method of determining whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieving the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform, includes:

[0016] Confirm whether the multi-dimensional evaluation score is greater than or equal to the preset score. If so, determine that the unfamiliar entry meets the display requirements of the knowledge sharing platform. If not, determine that the unfamiliar entry does not meet the display requirements of the knowledge sharing platform.

[0017] Obtaining a word frequency index and an intertextual index of the unfamiliar word according to the word parameter of the unfamiliar word, and determining a related topic of the unfamiliar word according to the word frequency index and the intertextual index;

[0018] Retrieving a vocabulary database corresponding to a relevant topic from a knowledge sharing platform, extracting description features from vocabulary parameters, and retrieving stored vocabulary parameters similar to the unfamiliar vocabulary from the vocabulary database based on the description features;

[0019] Highly relevant storage term parameters are screened out from similar storage term parameters according to the object attributes and application attributes of the unfamiliar term.

[0020] Preferably, the determining of the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term, and extracting the value information of the unfamiliar term based on the semantic feature similarity, includes:

[0021] Respectively obtain semantic statistical description features of the relevant storage term parameters and the term parameters of the unfamiliar term;

[0022] Compare the semantic statistical description features of the two to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term;

[0023] Determine a text scanning method according to the similarity of semantic features, and scan the common paragraphs of the first text content of the unfamiliar term and the second text content of the related term by the text scanning method;

[0024] Extracting the preceding paragraph information and the following paragraph information of the common paragraph, performing statistical correlation analysis and cluster analysis on the preceding paragraph information and the following paragraph information, and determining the value according to the analysis results;

[0025] Target preceding paragraph information and succeeding paragraph information whose value is greater than or equal to a preset threshold are screened out as valued information.

[0026] Preferably, the step of associating the valued information with the unfamiliar terms and storing them on the knowledge sharing platform for resource allocation includes:

[0027] Perform entity recognition on unfamiliar terms and determine the annotation format of unfamiliar terms and valuable information based on the entity attributes of the recognized entities;

[0028] Select an association method based on the annotation format, associate unfamiliar terms with valuable information through the association method, and store them on the knowledge sharing platform through a private upload channel;

[0029] Define unfamiliar terms as unresourced terms, determine the display form of unfamiliar terms, and determine the basic resource volume and deep resource volume based on the display form;

[0030] Based on the basic resource volume and deep resource volume, proportional resources are retrieved to resourceize unfamiliar entries.

[0031] A term processing device for a knowledge sharing platform, the device comprising:

[0032] A determination module, used to obtain detailed parameter information of unfamiliar terms on the knowledge sharing platform, and determine the multi-dimensional evaluation score of the unfamiliar terms according to the detailed parameter information;

[0033] A retrieval module is used to determine whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieve the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform;

[0034] An extraction module, used to determine the semantic feature similarity between the related storage term parameters and the term parameters of the unfamiliar term, and extract the value information of the unfamiliar term based on the semantic feature similarity;

[0035] The storage module is used to associate the valuable information with the unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

[0036] Preferably, the determining module includes:

[0037] The first confirmation submodule is used to obtain the uploaded entry on the knowledge sharing platform and confirm whether the uploaded entry is a stored entry. If not, the uploaded entry is set as an unfamiliar entry;

[0038] A first acquisition submodule is used to acquire definition parameters, category parameters, characteristic parameters, application scenario parameters and related term explanation parameters of the unfamiliar term as detailed parameter information;

[0039] A first determination submodule is used to obtain a multi-dimensional evaluation index and determine the evaluation content of the detailed parameter information of the unfamiliar term according to the multi-dimensional evaluation index;

[0040] An evaluation submodule is used to perform a multi-dimensional evaluation on the evaluation content of unfamiliar terms based on multi-dimensional evaluation indicators and preset scoring rules to obtain a comprehensive score;

[0041] Among them, the multiple dimensions include: content standardization, content completeness, content readability and content value.

[0042] Preferably, the calling module includes:

[0043] The second confirmation submodule is used to confirm whether the multi-dimensional evaluation score is greater than or equal to a preset score. If so, it is determined that the unfamiliar entry meets the display requirements of the knowledge sharing platform. If not, it is determined that the unfamiliar entry does not meet the display requirements of the knowledge sharing platform.

[0044] The second determination submodule is used to obtain the word frequency index and intertextual index of the unfamiliar word according to the word parameter of the unfamiliar word, and determine the relevant topic of the unfamiliar word according to the word frequency index and the intertextual index;

[0045] The retrieval submodule is used to retrieve the entry library corresponding to the relevant topic from the knowledge sharing platform, extract the description features from the entry parameters, and retrieve the stored entry parameters similar to the unfamiliar entry from the entry library according to the description features;

[0046] The first screening submodule is used to screen out highly relevant storage term parameters from similar storage term parameters according to the object attributes and application attributes of the unfamiliar term.

[0047] Preferably, the extraction module comprises:

[0048] The second acquisition submodule is used to respectively acquire semantic statistical description features of the relevant storage term parameters and the term parameters of the unfamiliar term;

[0049] A comparison submodule is used to compare the semantic statistical description features of the two to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term;

[0050] A scanning submodule, used for determining a text scanning method according to the similarity of semantic features, and scanning a common paragraph of a first text content of an unfamiliar term and a second text content of a related term by means of the text scanning method;

[0051] The analysis submodule is used to extract the preceding paragraph information and the following paragraph information of the common paragraph, perform statistical correlation analysis and cluster analysis on the preceding paragraph information and the following paragraph information, and determine the value according to the analysis results;

[0052] The second screening submodule is used to screen out target preceding paragraph information and succeeding paragraph information whose value is greater than or equal to a preset threshold as valued information.

[0053] Preferably, the storage module comprises:

[0054] The third determination submodule is used to perform entity recognition on the unfamiliar terms and determine the annotation format of the unfamiliar terms and the value-added information according to the entity attributes of the recognized entities;

[0055] A storage submodule is used to select an association method according to the annotation format, associate the unfamiliar terms with the valuable information through the association method, and store them on the knowledge sharing platform through a private upload channel;

[0056] A fourth determination submodule is used to define the unfamiliar terms as unresourced terms, determine the display form of the unfamiliar terms, and determine the basic resource amount and the deep resource amount according to the display form;

[0057] The resourceization submodule is used to resourceize unfamiliar terms by retrieving proportional resources based on the basic resource quantity and the deep resource quantity.

[0058] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0061] Figure 1 A workflow diagram of a method for processing entries of a knowledge sharing platform provided by the present invention;

[0062] Figure 2 Another workflow diagram of a method for processing entries of a knowledge sharing platform provided by the present invention;

[0063] Figure 3 A schematic diagram of the structure of a term processing device of a knowledge sharing platform provided by the present invention;

[0064] Figure 4 A schematic diagram of the structure of a determination module in a term processing device of a knowledge sharing platform provided by the present invention. DETAILED DESCRIPTION

[0065] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0066] At present, with the rapid development of Internet technology, more and more content can be provided to users on the Internet, and Internet users are more inclined to search for the content they want to know on the Internet. However, when users search for the content they want to know on the Internet, the results that the Internet can provide are usually too complicated and may not be very relevant to the content that users want to know, which makes users feel very inconvenient. The knowledge sharing platform provided on the Internet is an online data application that allows users to check the required knowledge and factual information, and usually provides users with relevant knowledge content in the form of entries. And because the Internet can provide more abundant information, the entry content that can be provided by the current Internet encyclopedia application is becoming more and more detailed, including not only the description of the entry, but also some other content related to the entry. The knowledge sharing platform is edited by a large number of users for various entries to help people in need to understand. When a new entry is uploaded, it will be reviewed and approved by the system. When the system recognizes the uploaded entry, it searches the platform database. When it is found that it is not stored, it is determined to meet the storage conditions and stored. There are the following problems: the specific parameters of the uploaded entry are not deeply evaluated, resulting in the uploaded entry information having low reference value and low quality, and even involving sensitive false and illegal information, which reduces the user experience. In order to solve the above problems, this embodiment discloses a method for processing entries on a knowledge sharing platform.

[0067] A method for processing entries in a knowledge sharing platform, such as Figure 1 As shown, the following steps are included:

[0068] Step S101, obtaining detailed parameter information of unfamiliar terms on the knowledge sharing platform, and determining a multi-dimensional evaluation score of the unfamiliar terms according to the detailed parameter information;

[0069] Step S102: determining whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieving the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform;

[0070] Step S103, determining the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term, and extracting the value information of the unfamiliar term based on the semantic feature similarity;

[0071] Step S104: associate the valued information with the unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

[0072] In this embodiment, the unfamiliar terms are represented as terms that cannot be found on the knowledge sharing platform;

[0073] In this embodiment, the detailed parameter information is represented by the relevant parameter information such as the entry definition, entry type, entry attribute, and entry characteristics of the unfamiliar entry;

[0074] In this embodiment, the multi-dimensional evaluation score is represented by the system scoring result of multiple dimensions for the unfamiliar word, including: sensitivity dimension, content standard dimension and content completeness dimension;

[0075] In this embodiment, the display requirements are expressed as specific information requirements of entries displayed on the knowledge sharing platform, such as: requirements for the standardization of entry content and description accuracy.

[0076] The working principle of the above technical solution is: obtain detailed parameter information of unfamiliar terms on the knowledge sharing platform, and determine the multidimensional evaluation score of the unfamiliar terms based on the detailed parameter information; determine whether the unfamiliar terms meet the display requirements of the knowledge sharing platform based on the multidimensional evaluation score, and if so, retrieve the relevance storage term parameters of the unfamiliar terms from the knowledge sharing platform; determine the semantic feature similarity between the relevance storage term parameters and the term parameters of the unfamiliar terms, and extract the value information of the unfamiliar terms based on the semantic feature similarity; associate the value information with the unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

[0077] The beneficial effects of the above technical solution are: by performing multi-dimensional score evaluation on the parameter information of unfamiliar entries, the qualification, standardization and completeness of the entry parameters can be guaranteed, the entry data quality can be guaranteed and the entries can be prevented from containing sensitive, false and illegal information. Furthermore, by comparing the specific parameters of unfamiliar entries with the relevant stored entries on the shared knowledge platform and then extracting valuable entry information for storage, it can save the platform's storage memory while ensuring the value of the entry content, thereby improving the user's reference experience. It solves the problem mentioned in the prior art that the platform system review fails to conduct an in-depth evaluation of the specific parameters of the uploaded entries, resulting in the uploaded entry information having a low reference value and low quality, and even involving sensitive, false and illegal information, thereby reducing the user's experience.

[0078] In one embodiment, Figure 2 As shown, the obtaining of detailed parameter information of unfamiliar terms on the knowledge sharing platform and determining the multi-dimensional evaluation scores of the unfamiliar terms according to the detailed parameter information include:

[0079] Step S201, obtaining an uploaded entry on the knowledge sharing platform, confirming whether the uploaded entry is a stored entry, and if not, setting the uploaded entry as an unfamiliar entry;

[0080] Step S202, obtaining definition parameters, category parameters, feature parameters, application scenario parameters and related term explanation parameters of the unfamiliar term as detailed parameter information;

[0081] Step S203: obtaining a multi-dimensional evaluation index, and determining the evaluation content of the detailed parameter information of the unfamiliar term according to the multi-dimensional evaluation index;

[0082] Step S204: Perform a multi-dimensional evaluation on the evaluation content of the unfamiliar terms based on the multi-dimensional evaluation indicators and preset scoring rules to obtain a comprehensive score;

[0083] Among them, the multiple dimensions include: content standardization, content completeness, content readability and content value.

[0084] The beneficial effects of the above technical solution are: obtaining detailed parameter information of unfamiliar terms, and determining the evaluation content of the detailed parameter information based on multidimensional evaluation indicators, and conducting multidimensional evaluation of unfamiliar terms in combination with preset scoring rules, which can make the evaluation process more objective and scientific, avoid evaluation bias caused by subjective factors, and improve the accuracy and reliability of the evaluation, thereby improving evaluation efficiency.

[0085] In one embodiment, the method of determining whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieving the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform, includes:

[0086] Confirm whether the multi-dimensional evaluation score is greater than or equal to the preset score. If so, determine that the unfamiliar entry meets the display requirements of the knowledge sharing platform. If not, determine that the unfamiliar entry does not meet the display requirements of the knowledge sharing platform.

[0087] Obtaining a word frequency index and an intertextual index of the unfamiliar word according to the word parameter of the unfamiliar word, and determining a related topic of the unfamiliar word according to the word frequency index and the intertextual index;

[0088] Retrieving a vocabulary database corresponding to a relevant topic from a knowledge sharing platform, extracting description features from vocabulary parameters, and retrieving stored vocabulary parameters similar to the unfamiliar vocabulary from the vocabulary database based on the description features;

[0089] Highly relevant storage term parameters are screened out from similar storage term parameters according to the object attributes and application attributes of the unfamiliar term.

[0090] The beneficial effects of the above technical solution are: determining the relevant topics of the unfamiliar terms based on the word frequency index and intertextual index of the unfamiliar terms, extracting descriptive features from the term parameters, and screening out stored term parameters similar to the unfamiliar terms from the term library based on the descriptive features, and quickly locating the terms most similar to the unfamiliar terms based on the to which the unfamiliar terms belong, thereby reducing the number of terms that need to be queried and the time for comparison, and improving data retrieval efficiency.

[0091] In this embodiment, the word frequency index and intertextual index of the unfamiliar word are obtained according to the word parameter of the unfamiliar word, and the related topics of the unfamiliar word are determined according to the word frequency index and the intertextual index, including:

[0092] Obtain principal component data based on the entry parameters of unfamiliar entries, and decompose the principal component data to obtain multiple data indicators;

[0093] Filter out high-frequency words based on multiple data indicators, and determine the frequency indicators of unfamiliar words based on the high-frequency words;

[0094] Confirm the mutual correlation coefficient between two adjacent data indicators, obtain the high-correlation data indicators according to the mutual correlation coefficient, and obtain the text dimension vectors of the high-correlation data indicators;

[0095] Determine the domain attributes of each highly relevant data indicator according to the text dimension vector, and determine the sample objects of each highly relevant data indicator based on the domain attributes;

[0096] Determine the relevance index and complementarity index of the sample objects, and determine the intertextual index of the unfamiliar terms based on the relevance index and complementarity index;

[0097] Determine the semantic themes of unfamiliar words based on word frequency index and intertextual index and construct a semantic theme map;

[0098] The discreteness of each semantic topic in the semantic topic graph is assigned through the topic relationship matrix, and the relevant matching degree between each semantic topic and the unfamiliar word is determined according to the assignment result;

[0099] The top three target semantic topics with the highest relevance matches are selected as the relevant topics of the unfamiliar terms.

[0100] The beneficial effects of the above technical solution are as follows: by determining the word frequency index based on the high-frequency words appearing in the term description parameters of the unfamiliar terms, the word frequency index can be quickly and accurately located and retrieved, thereby improving the retrieval efficiency; further, by utilizing the intertextual index for topic mapping and then determining the related topics of the unfamiliar terms based on the discrete degree calculation method, all related topics of the unfamiliar terms can be accurately identified and then the related topics with the highest matching degree can be screened out, thereby avoiding the occurrence of topic omissions and ensuring the high adaptability and high relevance of the screened topics.

[0101] In one embodiment, determining the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term, and extracting the value information of the unfamiliar term based on the semantic feature similarity includes:

[0102] Respectively obtain semantic statistical description features of the relevant storage term parameters and the term parameters of the unfamiliar term;

[0103] Compare the semantic statistical description features of the two to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term;

[0104] Determine a text scanning method according to the similarity of semantic features, and scan the common paragraphs of the first text content of the unfamiliar term and the second text content of the related term by the text scanning method;

[0105] Extracting the preceding paragraph information and the following paragraph information of the common paragraph, performing statistical correlation analysis and cluster analysis on the preceding paragraph information and the following paragraph information, and determining the value according to the analysis results;

[0106] Target preceding paragraph information and succeeding paragraph information whose value is greater than or equal to a preset threshold are screened out as valued information.

[0107] The beneficial effects of the above technical solution are: according to the semantic statistical description features of the entry parameters and the entry parameters of the unfamiliar entry stored in correlation, the similarity of the semantic features of the two is determined, and the similarity between different entries can be quickly determined. Further, the scanning method is determined and the leading paragraph information and the trailing paragraph information of the common paragraph are extracted for analysis to obtain valuable information, which can ensure accurate acquisition of valuable information of the unfamiliar entry, thereby better understanding the unfamiliar entry and quickly and accurately obtaining the core entry value information of the unfamiliar entry.

[0108] In one embodiment, associating the valued information with the unfamiliar terms and storing them on the knowledge sharing platform for resource allocation includes:

[0109] Perform entity recognition on unfamiliar terms and determine the annotation format of unfamiliar terms and valuable information based on the entity attributes of the recognized entities;

[0110] Select an association method based on the annotation format, associate unfamiliar terms with valuable information through the association method, and store them on the knowledge sharing platform through a private upload channel;

[0111] Define unfamiliar terms as unresourced terms, determine the display form of unfamiliar terms, and determine the basic resource volume and deep resource volume based on the display form;

[0112] Based on the basic resource volume and deep resource volume, proportional resources are retrieved to resourceize unfamiliar entries.

[0113] The beneficial effects of the above technical solution are: by determining the annotation format of the valuable information through the entity attributes of the unfamiliar terms, and selecting the association method to store it on the knowledge sharing platform, the display stability and reliability of the unfamiliar terms on the knowledge sharing platform can be guaranteed, and the privacy of the upload process can be guaranteed. Furthermore, the basic resource amount and the deep resource amount are determined according to the display form of the unfamiliar terms, and reasonable display resources can be allocated to ensure the display effect, thereby improving the display stability of the terms.

[0114] In one embodiment, this embodiment also discloses a term processing device of a knowledge sharing platform, such as Figure 3 As shown, the device comprises:

[0115] Determination module 301, used to obtain detailed parameter information of the unfamiliar terms on the knowledge sharing platform, and determine the multi-dimensional evaluation score of the unfamiliar terms according to the detailed parameter information;

[0116] A retrieval module 302 is used to determine whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieve the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform;

[0117] Extraction module 303, used to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term, and extract the value information of the unfamiliar term based on the semantic feature similarity;

[0118] The storage module 304 is used to associate the valued information with the unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

[0119] The working principle and beneficial effects of the above technical solution have been described in the method claims and will not be repeated here.

[0120] In one embodiment, Figure 4 As shown, the determination module 301 includes:

[0121] The first confirmation submodule 3011 is used to obtain the uploaded entry on the knowledge sharing platform and confirm whether the uploaded entry is a stored entry. If not, the uploaded entry is set as an unfamiliar entry.

[0122] The first acquisition submodule 3012 is used to acquire definition parameters, category parameters, characteristic parameters, application scenario parameters and related term explanation parameters of the unfamiliar term as detailed parameter information;

[0123] The first determination submodule 3013 is used to obtain multi-dimensional evaluation indicators and determine the evaluation content of the detailed parameter information of the unfamiliar term according to the multi-dimensional evaluation indicators;

[0124] Evaluation submodule 3014, for performing multi-dimensional evaluation on the evaluation content of the unfamiliar terms based on multi-dimensional evaluation indicators and preset scoring rules to obtain a comprehensive score;

[0125] Among them, the multiple dimensions include: content standardization, content completeness, content readability and content value.

[0126] In one embodiment, the calling module includes:

[0127] The second confirmation submodule is used to confirm whether the multi-dimensional evaluation score is greater than or equal to a preset score. If so, it is determined that the unfamiliar entry meets the display requirements of the knowledge sharing platform. If not, it is determined that the unfamiliar entry does not meet the display requirements of the knowledge sharing platform.

[0128] The second determination submodule is used to obtain the word frequency index and intertextual index of the unfamiliar word according to the word parameter of the unfamiliar word, and determine the relevant topic of the unfamiliar word according to the word frequency index and the intertextual index;

[0129] The retrieval submodule is used to retrieve the entry library corresponding to the relevant topic from the knowledge sharing platform, extract the description features from the entry parameters, and retrieve the stored entry parameters similar to the unfamiliar entry from the entry library according to the description features;

[0130] The first screening submodule is used to screen out highly relevant storage term parameters from similar storage term parameters according to the object attributes and application attributes of the unfamiliar term.

[0131] In one embodiment, the extraction module comprises:

[0132] The second acquisition submodule is used to respectively acquire semantic statistical description features of the relevant storage term parameters and the term parameters of the unfamiliar term;

[0133] A comparison submodule is used to compare the semantic statistical description features of the two to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term;

[0134] A scanning submodule, used for determining a text scanning method according to the similarity of semantic features, and scanning a common paragraph of a first text content of an unfamiliar term and a second text content of a related term by means of the text scanning method;

[0135] The analysis submodule is used to extract the preceding paragraph information and the following paragraph information of the common paragraph, perform statistical correlation analysis and cluster analysis on the preceding paragraph information and the following paragraph information, and determine the value according to the analysis results;

[0136] The second screening submodule is used to screen out target preceding paragraph information and succeeding paragraph information whose value is greater than or equal to a preset threshold as valued information.

[0137] In one embodiment, the storage module comprises:

[0138] The third determination submodule is used to perform entity recognition on the unfamiliar terms and determine the annotation format of the unfamiliar terms and the value-added information according to the entity attributes of the recognized entities;

[0139] A storage submodule is used to select an association method according to the annotation format, associate the unfamiliar terms with the valuable information through the association method, and store them on the knowledge sharing platform through a private upload channel;

[0140] A fourth determination submodule is used to define the unfamiliar terms as unresourced terms, determine the display form of the unfamiliar terms, and determine the basic resource amount and the deep resource amount according to the display form;

[0141] The resourceization submodule is used to resourceize unfamiliar terms by retrieving proportional resources based on the basic resource quantity and the deep resource quantity.

[0142] Those skilled in the art should understand that the first and second in the present invention merely refer to different application stages.

[0143] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0144] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for processing entries on a knowledge sharing platform, characterized in that: The following steps are involved: Obtain detailed parameter information of unfamiliar terms on the knowledge sharing platform, and determine multi-dimensional evaluation scores of the unfamiliar terms based on the detailed parameter information; Determine whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieve the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform; Determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term, and extract the value information of the unfamiliar term based on the semantic feature similarity; Associate valuable information with unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

2. The entry processing method of the knowledge sharing platform according to claim 1 is characterized in that: The obtaining of detailed parameter information of the unfamiliar terms on the knowledge sharing platform and determining the multi-dimensional evaluation scores of the unfamiliar terms according to the detailed parameter information include: Obtain the uploaded term on the knowledge sharing platform, confirm whether the uploaded term is a stored term, and if not, set the uploaded term as an unfamiliar term; Obtain definition parameters, category parameters, characteristic parameters, application scenario parameters, and related term explanation parameters of the unfamiliar term as detailed parameter information; Obtaining multidimensional evaluation indicators, and determining evaluation content of detailed parameter information of unfamiliar terms according to the multidimensional evaluation indicators; Perform multi-dimensional evaluation on the evaluation content of unfamiliar terms based on multi-dimensional evaluation indicators and preset scoring rules to obtain a comprehensive score; Among them, the multiple dimensions include: content standardization, content completeness, content readability and content value.

3. The entry processing method of the knowledge sharing platform according to claim 1 is characterized in that: The method of determining whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieving the relevant storage term parameters of the unfamiliar term from the knowledge sharing platform, includes: Confirm whether the multi-dimensional evaluation score is greater than or equal to the preset score. If so, determine that the unfamiliar entry meets the display requirements of the knowledge sharing platform. If not, determine that the unfamiliar entry does not meet the display requirements of the knowledge sharing platform. Obtaining a word frequency index and an intertextual index of the unfamiliar word according to the word parameter of the unfamiliar word, and determining a related topic of the unfamiliar word according to the word frequency index and the intertextual index; Retrieving a vocabulary database corresponding to a relevant topic from a knowledge sharing platform, extracting description features from vocabulary parameters, and retrieving stored vocabulary parameters similar to the unfamiliar vocabulary from the vocabulary database based on the description features; Highly relevant storage term parameters are screened out from similar storage term parameters according to the object attributes and application attributes of the unfamiliar term.

4. The entry processing method of the knowledge sharing platform according to claim 1 is characterized in that: The determining of the semantic feature similarity between the relevant storage term parameter and the term parameter of the unfamiliar term, and extracting the value information of the unfamiliar term based on the semantic feature similarity, includes: Respectively obtain semantic statistical description features of the relevant storage term parameters and the term parameters of the unfamiliar term; Compare the semantic statistical description features of the two to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term; Determine a text scanning method according to the similarity of semantic features, and scan the common paragraphs of the first text content of the unfamiliar term and the second text content of the related term by the text scanning method; Extracting the preceding paragraph information and the following paragraph information of the common paragraph, performing statistical correlation analysis and cluster analysis on the preceding paragraph information and the following paragraph information, and determining the value according to the analysis results; Target preceding paragraph information and succeeding paragraph information whose value is greater than or equal to a preset threshold are screened out as valued information.

5. The entry processing method of the knowledge sharing platform according to claim 1 is characterized in that: The method of associating the valuable information with the unfamiliar terms and storing them on the knowledge sharing platform for resource allocation includes: Perform entity recognition on unfamiliar terms and determine the annotation format of unfamiliar terms and valuable information based on the entity attributes of the recognized entities; Select an association method based on the annotation format, associate unfamiliar terms with valuable information through the association method, and store them on the knowledge sharing platform through a private upload channel; Define unfamiliar terms as unresourced terms, determine the display form of unfamiliar terms, and determine the basic resource volume and deep resource volume based on the display form; Based on the basic resource volume and deep resource volume, proportional resources are retrieved to resourceize unfamiliar entries.

6. A term processing device for a knowledge sharing platform, characterized in that: The device includes: A determination module, used to obtain detailed parameter information of unfamiliar terms on the knowledge sharing platform, and determine the multi-dimensional evaluation score of the unfamiliar terms according to the detailed parameter information; A retrieval module is used to determine whether the unfamiliar term meets the display requirements of the knowledge sharing platform based on the multi-dimensional evaluation score, and if so, retrieve the relevance storage term parameters of the unfamiliar term from the knowledge sharing platform; An extraction module, used to determine the semantic feature similarity between the related storage term parameters and the term parameters of the unfamiliar term, and extract the value information of the unfamiliar term based on the semantic feature similarity; The storage module is used to associate the valuable information with the unfamiliar terms and store them on the knowledge sharing platform for resource allocation.

7. The entry processing device of the knowledge sharing platform according to claim 6, characterized in that: The determining module comprises: The first confirmation submodule is used to obtain the uploaded entry on the knowledge sharing platform and confirm whether the uploaded entry is a stored entry. If not, the uploaded entry is set as an unfamiliar entry; A first acquisition submodule is used to acquire definition parameters, category parameters, characteristic parameters, application scenario parameters and related term explanation parameters of the unfamiliar term as detailed parameter information; A first determination submodule is used to obtain a multi-dimensional evaluation index and determine the evaluation content of the detailed parameter information of the unfamiliar term according to the multi-dimensional evaluation index; An evaluation submodule is used to perform a multi-dimensional evaluation on the evaluation content of unfamiliar terms based on multi-dimensional evaluation indicators and preset scoring rules to obtain a comprehensive score; Among them, the multiple dimensions include: content standardization, content completeness, content readability and content value.

8. The entry processing device of the knowledge sharing platform according to claim 6, characterized in that: The calling module includes: The second confirmation submodule is used to confirm whether the multi-dimensional evaluation score is greater than or equal to a preset score. If so, it is determined that the unfamiliar entry meets the display requirements of the knowledge sharing platform. If not, it is determined that the unfamiliar entry does not meet the display requirements of the knowledge sharing platform. The second determination submodule is used to obtain the word frequency index and intertextual index of the unfamiliar word according to the word parameter of the unfamiliar word, and determine the relevant topic of the unfamiliar word according to the word frequency index and the intertextual index; The retrieval submodule is used to retrieve the entry library corresponding to the relevant topic from the knowledge sharing platform, extract the description features from the entry parameters, and retrieve the stored entry parameters similar to the unfamiliar entry from the entry library according to the description features; The first screening submodule is used to screen out highly relevant storage term parameters from similar storage term parameters according to the object attributes and application attributes of the unfamiliar term.

9. The entry processing device of the knowledge sharing platform according to claim 6, characterized in that: The extraction module comprises: The second acquisition submodule is used to respectively acquire semantic statistical description features of the relevant storage term parameters and the term parameters of the unfamiliar term; A comparison submodule is used to compare the semantic statistical description features of the two to determine the semantic feature similarity between the relevant storage term parameters and the term parameters of the unfamiliar term; A scanning submodule, used for determining a text scanning method according to the similarity of semantic features, and scanning a common paragraph of a first text content of an unfamiliar term and a second text content of a related term by means of the text scanning method; The analysis submodule is used to extract the preceding paragraph information and the following paragraph information of the common paragraph, perform statistical correlation analysis and cluster analysis on the preceding paragraph information and the following paragraph information, and determine the value according to the analysis results; The second screening submodule is used to screen out target preceding paragraph information and succeeding paragraph information whose value is greater than or equal to a preset threshold as valued information.

10. The entry processing device of the knowledge sharing platform according to claim 6, characterized in that: The storage module comprises: The third determination submodule is used to perform entity recognition on the unfamiliar terms and determine the annotation format of the unfamiliar terms and the value-added information according to the entity attributes of the recognized entities; A storage submodule is used to select an association method according to the annotation format, associate the unfamiliar terms with the valuable information through the association method, and store them on the knowledge sharing platform through a private upload channel; A fourth determination submodule is used to define the unfamiliar terms as unresourced terms, determine the display form of the unfamiliar terms, and determine the basic resource amount and the deep resource amount according to the display form; The resourceization submodule is used to resourceize unfamiliar terms by retrieving proportional resources based on the basic resource quantity and the deep resource quantity.

Images