A method and system for refining and displaying news content

Abstract

The present invention relates to the field of news push management, and discloses a news content extraction and display method and system, which is applicable to the quality screening management of the user side of Internet promotion content. By performing natural language recognition on the content and title of pre-loaded push news, judging the evaluation elements of multiple corresponding news key point contents included therein, and then tracing the element content of the news based on the multiple evaluation elements, so as to judge the patchiness and integrity of the news content according to the multiple result information obtained by tracing, achieving the purpose of evaluating push news and screening news quality for users. Compared with the simple preference push mode, it can ensure that the push news to users has higher quality and authenticity.

Description

Technical Field

[0001] The present invention relates to the field related to news push management, and specifically to a method and system for refining and displaying news content. Background Art

[0002] The Internet is an important way for people to obtain and receive information. Thanks to the characteristics of the Internet that it can carry a large amount of data and transmit it quickly, the Internet has become the current information transmission channel. Especially for time-sensitive news information, various media continuously generate and push a large amount of news content to users. As the consumers of news content, thousands of news contents of uneven quality are received every day.

[0003] In the current network environment, there are too many meaningless junk news contents. The whole content is clickbait, exaggerated excessively, or even fake news is fabricated entirely by piecing together to gain traffic, resulting in extremely limited information finally transmitted or even completely meaningless. It not only completely wastes the viewers' time but also causes unnecessary public opinion guidance storms. Therefore, in order to ensure that people can obtain higher-quality news content and maintain the network environment, it is very necessary to refine and screen news content. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for refining and displaying news content to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A method for refining and displaying news content includes:

[0007] Obtain the pushed news and preload the news content, process the news content based on natural language understanding, and obtain multiple evaluation elements, where the evaluation elements include time element, location element, event subject element, and event result element;

[0008] Conduct traceability retrieval according to random combinations of multiple evaluation elements to obtain multiple first source information in the time series, extract content elements from the multiple first source information, and conduct traceability quality evaluation on the current news content based on the multiple content elements. The traceability quality is used to characterize the non-pieced authenticity of the current news content;

[0009] Conduct correlation quality evaluation on the proportion of element-related content and the news title of the current news content through natural language processing. The proportion of element-related content is used to characterize the proportion of the effective information space in the news content;

[0010] Generate an evaluation level for the news content based on the traceability quality result and the associated quality result, and perform a floating mark on the pushed news according to the evaluation level. The floating mark is used to represent a variable display layer that follows the position of the news preview title.

[0011] As a further solution of the present invention: it further includes a title relevance evaluation step, specifically including:

[0012] Perform content recognition on the news title based on natural language processing to obtain multiple core expression words;

[0013] Perform relevance judgment on multiple core expression words, distinguish the main expression words and the defining expression words, and judge the association relationship between multiple defining expression words and the main expression words based on the expression content. The main expression words are used to represent the event content, and the defining expression words are used to modify and define the main expression words;

[0014] Judge the logical and causal relationship between the defining expression words and the main expression words, and perform description verification of the logical and causal relationship in the news content to generate a verification result;

[0015] If the verification result indicates that the defining expression word or the main expression word does not conform to the news content, mark this news as a title deceptive news;

[0016] If the verification result indicates that the defining expression word is exaggerated compared to the news content or there is no direct causal relevance between the defining expression word and the main expression word in the news content, mark this news as a content exaggerated news.

[0017] As a still further solution of the present invention: the step of performing traceability quality evaluation on the current news content based on multiple content elements includes:

[0018] Perform content category classification on multiple content elements of multiple first source information and the current evaluation element, and compare the evaluation element within the same content category with multiple content elements to obtain a traceability result;

[0019] If the traceability result indicates that the evaluation element and multiple content elements in the same content category are inconsistent, perform traceability evaluation on the news content based on the proportion of inconsistent evaluation elements. The traceability evaluation process is characterized as a proportional assignment and deduction process, and each pushed news is provided with a highest basic promotion score;

[0020] If the traceability result indicates that there is a content category that the current pushed news does not contain among multiple content elements, compare multiple content elements of the first source information corresponding to this content category. If they are consistent, mark the first source information as a news content supplementary source and push it.

[0021] As a further solution of the present invention: it further includes an auxiliary association step for low-quality news, specifically including:

[0022] If the traceability quality result or the association quality result of the currently recommended news is less than the preset value, then classify the recommended news as low-quality news;

[0023] Obtain multiple evaluation elements that do not match the first source information in the traceability retrieval, perform traceability retrieval on the non-matching elements, obtain the first source information in multiple time series, and establish an association link based on the first source information. The association link is used to guide the jump to the corresponding first source information link;

[0024] Generate a guiding interface at the corresponding entry of the evaluation element in the recommended news, connect the association link to the guiding interface, and correspondingly generate a visual guiding layer.

[0025] As a further solution of the present invention: it further includes a traceability step for image content, specifically including:

[0026] Obtain the image information in the news content as the visual element of the pushed news, perform traceability retrieval on the visual element based on the image features, and obtain the first source information in the time series;

[0027] Match the image association content of the first source information. If the information content is inconsistent with multiple evaluation elements of the current news content, then mark the current recommended news with an unassociated picture, and the unassociated picture mark is output through a floating mark.

[0028] The embodiment of the present invention aims to provide a news content refinement and display system, including:

[0029] A news preprocessing module, which is used to obtain the pushed news and preload the news content, process the news content based on natural language understanding, and obtain multiple evaluation elements. The evaluation elements include time elements, location elements, event subject elements, and event result elements;

[0030] A traceability retrieval module, which is used to perform traceability retrieval according to random combinations of multiple evaluation elements, obtain the first source information in multiple time series, extract content elements from the multiple first source information, and perform traceability quality evaluation on the current news content based on the multiple content elements. The traceability quality is used to characterize the non-patchwork authenticity of the current news content;

[0031] An association evaluation module, which is used to perform association quality evaluation on the proportion of the element association content of the current news content and the news title through natural language processing. The proportion of the element association content is used to characterize the proportion of the effective information space in the news content;

[0032] A hierarchical promotion module, configured to generate an evaluation level for the news content based on the traceability quality result and the associated quality result, and perform a floating mark on the pushed news according to the evaluation level, where the floating mark is used to represent a variable display layer following the position of the news preview title.

[0033] As a further solution of the present invention: it further includes a title association module, specifically including:

[0034] A core expression acquisition unit, configured to perform content recognition on the news title based on natural language processing to obtain multiple core expression words;

[0035] A core association evaluation unit, configured to perform relevance judgment on multiple core expression words, distinguish the main expression words and the defining expression words, and judge the association relationship between multiple defining expression words and the main expression words based on the expression content, where the main expression words are used to represent the event content, and the defining expression words are used to modify and define the main expression words;

[0036] A logical association verification unit, configured to judge the logical and causal relationship between the defining expression words and the main expression words, and perform description verification of the logical and causal relationship in the news content to generate a verification result;

[0037] A title non - conformity determination unit, configured to label the news as a title - deceptive news if the verification result indicates that the defining expression words or the main expression words do not conform in the news content;

[0038] A title exaggeration determination unit, configured to label the news as a content - exaggerating news if the verification result indicates that the defining expression words are exaggerated compared to the news content or there is no direct causal relevance between the defining expression words and the main expression words in the news content.

[0039] As a still further solution of the present invention: the traceability retrieval module includes:

[0040] An element comparison unit, configured to perform content - category classification on multiple content elements of multiple first - source information and the current evaluation elements, and compare the information expression meanings of the evaluation elements and multiple content elements within the same content category to obtain a traceability result;

[0041] An element judgment unit, configured to perform a traceability evaluation on the news content based on the proportion of inconsistent evaluation elements if the traceability result indicates that the evaluation elements and multiple content elements in the same content category are inconsistent, where the traceability evaluation process is a proportional assignment and deduction process, and each pushed news is provided with a highest basic promotion score;

[0042] An element expansion unit, which is used to compare multiple content elements corresponding to the first source information of the content category if the traceability result indicates that there is a content category not included in the currently pushed news among the multiple content elements. If they are consistent, the first source information is marked as a news content supplementary source and pushed.

[0043] As a further aspect of the present invention: It further includes a low-quality auxiliary association module, specifically including:

[0044] A low-quality determination unit, which is used to classify the recommended news as low-quality news if the traceability quality result or the association quality result of the currently recommended news is less than a preset value;

[0045] An association guidance unit, which is used to obtain multiple evaluation elements that do not match the first source information in the traceability search, perform a traceability search on the unmatched elements, obtain multiple first source information in the time series, and establish an association link based on the first source information. The association link is used to guide the jump to the corresponding first source information link;

[0046] A guidance push unit, which is used to generate a guidance interface at the corresponding entry of the evaluation element in the recommended news, connect the association link to the guidance interface, and correspondingly generate a visual guidance layer.

[0047] As a further aspect of the present invention: It further includes an image traceability module, specifically including:

[0048] A visual traceability unit, which is used to obtain the image information in the news content as the visual element of the pushed news, perform a traceability search on the visual element based on the image features, and obtain the first source information in the time series;

[0049] A visual judgment unit, which is used to match the image-related content of the first source information. If the information content is inconsistent with multiple evaluation elements of the current news content, a non-associated picture mark is made for the current recommended news, and the non-associated picture mark is output through a floating mark.

[0050] Compared with the prior art, the beneficial effects of the present invention are: It is applicable to the quality screening and management of the user side of Internet promotion content. By performing natural language recognition on the content and title of the pre-loaded pushed news, it judges multiple evaluation elements of the corresponding news key point content it contains, and then traces the element content of the news based on the multiple evaluation elements, so as to judge the patchwork and integrity of the news content according to the multiple traceability result information, achieving the purpose of evaluating the pushed news and screening the news quality for users. Compared with the simple preference push mode, it can ensure that the pushed news to users has higher quality and authenticity. Description of the Drawings

[0051] Figure 1 It is a flow chart of a method for refining and displaying news content.

[0052] Figure 2 It is a flow chart of the step of evaluating the relevance of the title in a method for refining and displaying news content.

[0053] Figure 3 It is a block diagram of the composition of a news content refining and displaying system. Detailed implementation manners

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The following describes in detail the specific implementation manners of the present invention with reference to specific embodiments.

[0056] As Figure 1 described, a method for refining and displaying news content provided by an embodiment of the present invention includes the following steps:

[0057] S10. Obtain the pushed news and preload the news content, process the news content based on natural language understanding, and obtain multiple evaluation elements, where the evaluation elements include a time element, a location element, an event subject element, and an event result element;

[0058] S20. Perform traceability retrieval according to random combinations of multiple evaluation elements, obtain multiple first source information in a time series, extract content elements from the multiple first source information, and perform traceability quality evaluation on the current news content based on the multiple content elements, where the traceability quality is used to characterize the non-assembled authenticity of the current news content;

[0059] S30. Perform correlation quality evaluation on the proportion of element-correlated content and the news title of the current news content through natural language processing, where the proportion of element-correlated content is used to characterize the proportion of the length of effective information in the news content;

[0060] S40. Generate an evaluation level for the news content based on the traceability quality result and the correlation quality result, and perform a floating mark on the pushed news according to the evaluation level, where the floating mark is used to characterize a variable display layer that follows the position of the news preview title.

[0061] In this embodiment, a method for refining and displaying news content is provided, which is applicable to the quality screening and management of the user side of Internet promotion content. By performing natural language recognition on the content and title of pre-loaded push news, the evaluation elements of multiple corresponding news key points contained therein are judged, and then the origin tracing of the element content of the news is carried out based on multiple evaluation elements, so as to judge the patchwork and integrity of the news content according to the multiple result information obtained from the origin tracing, achieving the purpose of evaluating the push news and screening the news quality for users. Compared with the simple preference push mode, it can ensure that the push news to users has higher quality and authenticity; the Internet is an important way for people to obtain and receive information. Thanks to the characteristics of the Internet that it can carry a large amount of data and transmit it quickly, the Internet has become the current information transmission channel. Especially for time-sensitive news information, a variety of media continuously generate and push a large amount of news content to users. As the consumer side of news content, thousands of news content of uneven quality are received every day. Therefore, in order to ensure that the consumer side can click and view the push content more frequently, the screening and targeted push of the push content are also very important; the existing promotion screening methods mainly include two directions. One is the screening push according to popularity, which selects and pushes according to the popularity information of different content on the Internet, and gives priority to the push of popularity information. The other is the screening push according to preference, that is, relevant content is pushed according to the historical browsing preferences of the consumer side; however, there are a large number of low-quality or even false news content in the push content under the current screening and promotion mode, which affects the evaluation of the consumer side on real events and wastes a lot of time of the consumer side, including but not limited to various false types such as content patchwork, over-exaggeration and content non-conformity; therefore, this embodiment introduces the natural language understanding (NLP) technology. When the platform pushes news to the consumer side, multiple pushed news are pre-loaded in the background, and the news content and title are recognized through natural language understanding, and are summarized into multiple evaluation elements according to the type of content elements (for example, what happened at what time, where, and what consequences were finally produced. Here, multiple "whats" can correspond to different evaluation elements, and what happened can be further split into multiple elements such as start, cause, and process), and these elements are randomly combined and retrieved (for example, evaluation element A + evaluation element C) for origin tracing to find earlier matching news content. If these matching news content are all consistent, it means that the current news has factual basis. If the results traced by multiple elements correspond to the elements of multiple different events, it means that the current content may be patchwork and inaccurate and has no meaning for browsing. Such push content does not need to be pushed to the consumer side anymore;Moreover, some current media tend to use exaggerated and even content-irrelevant headlines to attract consumers to click on their content. Such news push has no value in pushing to consumers. Therefore, the compliance of the headline can be judged by matching the key words of the headline elements and the words describing the degree with the main content of the news push. Here, the floating mark is a newly established regional display layer, and the coordinates of the display area are followed through image recognition to achieve following the corresponding news display area when the page is flipped.

[0062] As Figure 2 shown, as another preferred embodiment of the present invention, it further includes a headline relevance evaluation step, specifically including:

[0063] S51, Perform content recognition on the news headline based on natural language processing to obtain multiple core expression words;

[0064] S52, Perform relevance judgment on multiple core expression words, distinguish the main expression words and the defining expression words, and judge the association relationship between multiple defining expression words and the main expression words based on the expression content. The main expression words are used to represent the event content, and the defining expression words are used to modify and define the main expression words;

[0065] S53, Judge the logical and causal relationship between the defining expression words and the main expression words, and verify the description of the logical and causal relationship in the news content to generate a verification result;

[0066] S54, If the verification result indicates that the defining expression word or the main expression word does not conform to the news content, mark this news as a headline deceptive news;

[0067] S55, If the verification result indicates that the defining expression word is exaggerated compared to the news content or there is no direct causal relevance between the defining expression word and the main expression word in the news content, mark this news as a content exaggeration news.

[0068] In this embodiment, the evaluation steps of headline relevance are supplemented. First, the headline is recognized through natural language processing (NLP) technology to judge multiple core expression words (i.e., element words) in the headline, including content expression and modification expression, and perform logical association judgment on these core expression words (for example, a certain modifier is used to express the degree of a certain content expression core keyword). According to these core expression words and the relevance between the core expression words, match the content of the news push. If it does not match the content, relevance or modification degree of the core expression words in the news content, it indicates that the current headline has false guidance or excessive exaggeration, etc., and this news does not have the meaning of being pushed for consumers to view.

[0069] As another preferred embodiment of the present invention, the step of tracing and evaluating the quality of the current news content based on the plurality of content elements includes:

[0070] Classify the content elements of a plurality of first source information and the current evaluation elements into the same content category, and compare the evaluation elements and the content elements within the same content category in terms of the meaning of information expression to obtain a tracing result;

[0071] If the tracing result shows that the evaluation elements and the content elements in the same content category are inconsistent, then conduct a tracing evaluation of the news content based on the proportion of inconsistent evaluation elements. The tracing evaluation process is characterized as a proportional assignment and deduction process, and each push news is provided with a highest basic promotion score;

[0072] If the tracing result shows that there is a content category in the plurality of content elements that is not included in the current push news, then compare the content elements of the first source information corresponding to the content category. If they are consistent, mark the first source information as a news content supplementary source and push it.

[0073] In this embodiment, among the different results retrieved by different element combinations, there may be multiple news that are partially overlapping but the elements are not completely consistent and can be complementary. It should be noted that the incomplete consistency of the elements here means that the content traced is basically the same as the current content, but there are different content elements. This content element expresses different event key points, rather than expressing the same event key points but with different contents. Therefore, the traced content of this part can be regarded as the relevant follow-up of the news and other parts not described in the current news. Through the supplementation and improvement of content tracing, it can help consumers more comprehensively understand the overall event content and prevent news compilers from guiding the emotions and positions of viewers through malicious content deletion.

[0074] As another preferred embodiment of the present invention, it further includes an auxiliary association step for low-quality news, specifically including:

[0075] If the tracing quality result or the association quality result of the current recommended news is less than a preset value, then classify the recommended news as low-quality news;

[0076] Obtain a plurality of evaluation elements that do not match the first source information in the tracing retrieval, and conduct a tracing retrieval on the non-matching elements to obtain a plurality of first source information in the time series. Establish an association link based on the first source information, and the association link is used to guide the jump to the corresponding first source information link;

[0077] Generate a guiding interface at the corresponding entry of the evaluation element in the recommended news, connect the association link to the guiding interface, and correspondingly generate a visual guiding layer.

[0078] In this embodiment, an auxiliary association step for low-quality news is introduced. When it is determined through traceability that the current news is fabricated and pieced together as low-quality news, multiple different original news used for piecing can be found based on the traceability results of multiple evaluation elements. These original news are associated with the keywords of their pieced parts and displayed in the current push. If the current consumer has a great interest in some of the key contents, they can quickly jump to the corresponding pieced news source through the associated first source information link, facilitating their quick access to the content they are interested in.

[0079] As another preferred embodiment of the present invention, it further includes a traceability step for image content, specifically including:

[0080] Obtain the image information in the news content as the visual element of the pushed news, perform traceability retrieval on the visual element based on image features, and obtain the first source information in the time series;

[0081] Match the image-related content of the first source information. If the information content is inconsistent with multiple evaluation elements of the current news content, mark the current recommended news as having an unassociated picture, and the unassociated picture mark is output through a floating mark.

[0082] In this embodiment, in the news content, in addition to the traditional text information expression, it also includes image reference content. Through the image content, the status and situation of the scene corresponding to the news content can be intuitively and quickly understood. Therefore, the image content is also a very important part of the news. However, currently, there are some editors who randomly quote images of irrelevant events, resulting in consumers of the news obtaining incorrect information, and even some may cause relatively serious misguidance of public opinion. Therefore, the traceability judgment of images is also very important. By judging the compliance of the images through traceability and matching the understanding and recognition of the image content with the news content, the rationality of the quoted images is judged, so as to evaluate and classify the news according to the results.

[0083] As Figure 3 shown, the present invention also provides a news content extraction and display system, which includes:

[0084] A news preprocessing module 100, which is used to obtain the pushed news and preload the news content, process the news content based on natural language understanding, and obtain multiple evaluation elements, where the evaluation elements include time elements, location elements, event subject elements, and event result elements;

[0085] The traceability retrieval module 200 is used to perform traceability retrieval according to random combinations of multiple evaluation elements, obtain multiple pieces of first source information in a time series, extract content elements from the multiple pieces of first source information, and perform traceability quality evaluation on the current news content based on the multiple content elements. The traceability quality is used to characterize the non-patchwork authenticity of the current news content;

[0086] The association evaluation module 300 is used to perform association quality evaluation on the proportion of element-associated content and the news title of the current news content through natural language processing. The proportion of element-associated content is used to characterize the proportion of the length of effective information in the news content;

[0087] The grading and promotion module 400 is used to generate an evaluation level for the news content based on the traceability quality result and the association quality result, and perform a floating mark on the pushed news according to the evaluation level. The floating mark is used to characterize a variable display layer that follows the position of the news preview title.

[0088] As another preferred embodiment of the present invention, it further includes a title association module, specifically including:

[0089] The core expression acquisition unit is used to perform content recognition on the news title through natural language processing to obtain multiple core expression words;

[0090] The core association evaluation unit is used to perform relevance judgment on multiple core expression words, distinguish the main expression word and the defining expression word, and judge the association relationship between the multiple defining expression words and the main expression word based on the expression content. The main expression word is used to characterize the event content, and the defining expression word is used to modify and define the main expression word;

[0091] The logical association verification unit is used to judge the logical and causal relationship of the defining expression word to the main expression word, and perform description verification of the logical and causal relationship in the news content to generate a verification result;

[0092] The title mismatch determination unit is used to mark the news as a title-deceptive news if the verification result indicates that the defining expression word or the main expression word does not conform in the news content;

[0093] The title exaggeration determination unit is used to mark the news as a content-exaggerated news if the verification result indicates that the defining expression word is exaggerated compared to the news content or there is no direct causal relevance between the defining expression word and the main expression word in the news content.

[0094] As another preferred embodiment of the present invention, the traceability retrieval module includes:

[0095] An element comparison unit, configured to classify the content elements of multiple first source information and the current evaluation element into the same content category, and compare the evaluation elements and multiple content elements within the same content category for the meaning of information expression, so as to obtain a traceability result;

[0096] An element judgment unit, configured to, if the traceability result shows that the evaluation element and multiple content elements in the same content category are inconsistent, perform a traceability evaluation on the news content based on the proportion of inconsistent evaluation elements, and the traceability evaluation process is characterized as a proportional assignment and deduction process, and each of the push news is provided with a highest basic promotion score;

[0097] An element expansion unit, configured to, if the traceability result shows that there is a content category not included in the current push news among the multiple content elements, compare the multiple content elements of the first source information corresponding to the content category, and if they are consistent, mark the first source information as a news content supplementary source and push it.

[0098] As another preferred embodiment of the present invention, it further includes a low-quality auxiliary association module, which specifically includes:

[0099] A low-quality determination unit, configured to classify the recommended news as low-quality news if the traceability quality result or the association quality result of the current recommended news is less than a preset value;

[0100] An association guidance unit, configured to obtain multiple evaluation elements that do not match the first source information in the traceability retrieval, perform a traceability retrieval on the unmatched elements, obtain multiple first source information in the time series, and establish an association link based on the first source information, and the association link is used to guide the jump to the corresponding first source information link;

[0101] A guidance push unit, configured to generate a guidance interface at the corresponding entry of the evaluation element in the recommended news, connect the association link to the guidance interface, and correspondingly generate a visual guidance layer.

[0102] As another preferred embodiment of the present invention, it further includes an image traceability module, which specifically includes:

[0103] A visual traceability unit, configured to obtain the image information in the news content as the visual element of the push news, perform a traceability retrieval on the visual element based on the image feature, and obtain the first source information in the time series;

[0104] A visual judgment unit, configured to match the image-related content of the first source information, and if the information content is inconsistent with multiple evaluation elements of the current news content, mark the current recommended news with an unassociated picture, and the unassociated picture mark is output through a floating mark.

[0105] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0106] After considering the specification and the disclosure of the embodiments, those skilled in the art will readily conceive of other embodiments of the present disclosure. 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 known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0107] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A news content extraction and display method, characterized in that: Include: Acquire push news and preload news content, process the news content based on natural language understanding, and acquire multiple evaluation elements, wherein the evaluation elements include a time element, a location element, an event subject element, and an event result element; Performing source retrieval according to a random combination of multiple evaluation elements, obtaining multiple first source information in a time series, extracting content elements from the multiple first source information, and evaluating the source quality of the current news content based on the multiple content elements, wherein the source quality is used to characterize the non-patchwork authenticity of the current news content; The relevance quality of the content ratio of the elements in the current news content and the news title is evaluated by natural language processing, wherein the content ratio of the elements is used to represent the proportion of effective information in the news content; Based on the result of the traceability quality evaluation and the result of the association quality evaluation, an evaluation level of the news content is generated, and a floating mark is placed on the pushed news according to the evaluation level, wherein the floating mark is used to represent a position variable display layer following the news preview title; It also includes the title relevance evaluation step, including: Based on natural language processing, the content of news headlines is identified to obtain multiple core expressions; Performing correlation judgment on multiple core expressions, distinguishing between subject expressions and definition expressions, and judging the correlation between multiple definition expressions and the subject expressions based on the expression content, wherein the subject expressions are used to represent the event content, and the definition expressions are used to modify and define the subject expressions; Determine the logic and causal relationship between the definition expression and the subject expression, and perform description verification of the logic and causal relationship in the news content to generate a verification result; If the verification result indicates that the definition expression word or the subject expression word does not match the news content, the news is marked as news with a deceptive title; If the verification result indicates that the definition expression is exaggerated compared to the news content or has no direct causal relationship with the main expression in the news content, the news is marked as news with exaggerated content; The step of evaluating the source quality of the current news content based on the multiple content elements comprises: Classify multiple content elements of multiple first source information and the current evaluation element into the same content category, and compare the information expression meanings of the evaluation element and the multiple content elements in the same content category to obtain a tracing result; If the tracing result is characterized by the inconsistency between the evaluation element and multiple content elements in the same content category, the news content is traced and evaluated based on the proportion of the inconsistent evaluation elements. The tracing evaluation process is characterized by a proportional scoring process, and each of the pushed news has a highest basic promotion score. If the tracing result indicates that there is a content category that the currently pushed news does not contain among the multiple content elements, multiple content elements of the first source information corresponding to the content category are compared, and if they are consistent, the first source information is marked as a news content supplement source and pushed.

2. A news content extraction and display method according to claim 1, characterized in that: It also includes auxiliary association steps for low-quality news, including: If the result of the traceability quality evaluation or the result of the association quality evaluation of the current recommended news is less than a preset value, the recommended news is classified as low-quality news; Acquire multiple evaluation elements that do not match the first source information in the traceability search, perform traceability search on the unmatched elements, acquire the first source information on multiple time series, and establish an associated link based on the first source information, wherein the associated link is used to guide the jump to the corresponding first source information link; A guidance interface is generated at the corresponding entry of the evaluation element in the recommended news, and the associated link is connected to the guidance interface, and a visual guidance layer is generated accordingly.

3. A news content extraction and display method according to claim 1, characterized in that: It also includes the steps of tracing the source of the image content, including: Acquire image information in news content as the visual element of the pushed news, perform source tracing search on the visual element based on image features, and acquire first source information in a time series; The image-related content of the first source information is matched. If the information content is inconsistent with multiple evaluation factors of the current news content, an unrelated picture mark is added to the current recommended news, and the unrelated picture mark is output through a floating mark.

4. A news content extraction and display system, characterized in that: Include: A news preprocessing module, used to obtain push news and preload news content, process the news content based on natural language understanding, and obtain multiple evaluation elements, wherein the evaluation elements include time elements, location elements, event subject elements, and event result elements; A source retrieval module, used to perform source retrieval according to a random combination of multiple evaluation elements, obtain multiple first source information in a time series, extract content elements from the multiple first source information, and perform source quality evaluation on the current news content based on the multiple content elements, wherein the source quality is used to characterize the non-patchwork authenticity of the current news content; A relevance evaluation module is used to evaluate the relevance quality of the element relevance content ratio of the current news content and the news title through natural language processing, wherein the element relevance content ratio is used to represent the length ratio of effective information in the news content; A graded promotion module, for generating an evaluation level for the news content based on the result of the traceability quality evaluation and the result of the association quality evaluation, and placing a floating mark on the pushed news according to the evaluation level, wherein the floating mark is used to represent a position variable display layer following the news preview title; It also includes title association modules, including: A core expression acquisition unit, used to perform content recognition on news titles based on natural language processing to acquire multiple core expression words; A core association evaluation unit is used to judge the association of multiple core expressions, distinguish between subject expressions and definition expressions, and judge the association relationship between multiple definition expressions and the subject expression based on the expression content, wherein the subject expression is used to represent the event content, and the definition expression is used to modify and define the subject expression; A logic association verification unit, used to determine the logic and causal relationship between the definition expression and the subject expression, and to perform description verification of the logic and causal relationship in the news content to generate a verification result; a title non-matching determination unit, configured to mark the news as news with a deceptive title if the verification result indicates that the definition expression word or the subject expression word does not match the news content; A title exaggeration determination unit, configured to mark the news as news with exaggerated content if the verification result indicates that the definition expression word is exaggerated compared to the news content or has no direct causal relationship with the main expression word in the news content; The traceability retrieval module includes: An element comparison unit, configured to classify the content elements of the plurality of first source information and the current evaluation element into the same category, and compare the information expression meanings of the evaluation element and the plurality of content elements in the same content category to obtain a tracing result; An element judgment unit, for, if the tracing result is characterized as an inconsistency between the evaluation element and multiple content elements in the same content category, then tracing the evaluation of the news content based on the proportion of the inconsistent evaluation elements, the tracing evaluation process is characterized as a proportional scoring process, and each of the pushed news has a highest basic promotion score; The element extension unit is used to compare the multiple content elements of the first source information corresponding to the content category if the tracing result is characterized by the fact that the currently pushed news does not contain a content category among the multiple content elements. If they are consistent, the first source information is marked as a news content supplement source and pushed.

5. A news content extraction and display system according to claim 4, characterized in that: It also includes low-quality auxiliary association modules, including: A low-quality demarcation unit, configured to classify the recommended news as low-quality news if the result of the traceability quality evaluation or the result of the association quality evaluation of the currently recommended news is less than a preset value; An association guiding unit, used to obtain multiple evaluation elements that do not match the first source information in the traceability search, and perform traceability search on the unmatched elements to obtain the first source information on multiple time series, and establish an association link based on the first source information, wherein the association link is used to guide the jump to the corresponding first source information link; The guidance push unit is used to generate a guidance interface at the corresponding entry of the evaluation element in the recommended news, connect the associated link to the guidance interface, and generate a visual guidance layer accordingly.

6. A news content extraction and display system according to claim 4, characterized in that: It also includes an image tracing module, which includes: A visual tracing unit, used to obtain image information in news content as a visual element of the pushed news, perform a tracing search on the visual element based on image features, and obtain first source information in a time series; The visual judgment unit is used to match the image-related content of the first source information. If the information content is inconsistent with multiple evaluation factors of the current news content, the current recommended news is marked with an unrelated picture, and the unrelated picture mark is output through a floating mark.

Images