Real-time news event processing method and device based on large model

Abstract

The invention provides a real-time news event processing method and device based on a large model, and relates to the technical field of application of multi-modal large models, and the method comprises the steps: obtaining at least one real-time news event in response to request information input for a graphical user interface; extracting corresponding key information from each real-time news event, inputting the key information into the multi-modal large model, and determining summary information corresponding to each real-time news event; determining the authenticity of the real-time news event corresponding to each piece of summary information according to a verification rule and a verification weight corresponding to each news element of the summary information in a second preset template; determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity and summary information of the real-time news events; inputting the request information and summary information of the target real-time news event into a multi-modal large model, and outputting a response for the request information; the technical problem that questions and answers of real-time news events cannot reach expected standards is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of application of multimodal large models, and in particular to a method and device for processing real-time news events based on large models. Background Art

[0002] With the emergence of multimodal large models (multimodal large language models), AI can communicate smoothly with people and has shown leaps and bounds in semantic understanding and logical reasoning.

[0003] Current multimodal large models generally obtain answers to user questions through a preset and updateable knowledge base; however, such answers are delayed and cannot meet the user's requirements for asking questions about real-time news events. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for processing real-time news events based on a large model, so as to alleviate the technical problem in the prior art that the answers to questions about real-time news events do not meet the expected standards.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing real-time news events based on a large model, comprising: In response to request information inputted into the graphical user interface, controlling the real-time search engine to retrieve at least one real-time news event corresponding to the request information; Extracting corresponding key information from each of the real-time news events, and inputting the key information into the multimodal macro model, to determine summary information corresponding to each of the real-time news events; wherein the first preset template is determined according to the format requirements and attribute requirements of the summary information; Determine the authenticity of the real-time news event corresponding to each of the summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template; Determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity of the real-time news event and the summary information; The request information and summary information of the target real-time news event are input into the multimodal macro model, and a response to the request information is output.

[0006] In combination with the first aspect, an embodiment of the present invention provides a first possible implementation of the first aspect, wherein the step of determining the authenticity of the real-time news event corresponding to each of the summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template includes: Compare each news element in each summary information with the verification rule corresponding to each news element in the second preset template to obtain the completeness of each news element; Determining the authenticity score of each summary information according to the verification weight of each news element and the completeness of each news element; The authenticity score of each summary information is compared with a preset score threshold to determine the authenticity of the real-time news event corresponding to each summary information.

[0007] In combination with the first aspect, an embodiment of the present invention provides a second possible implementation of the first aspect, wherein the steps of extracting corresponding key information from each of the real-time news events, inputting the key information into the multimodal big model, and determining summary information corresponding to each of the real-time news events include: Determine a first preset template for each real-time news event according to the format requirements and attribute requirements of the summary information; wherein the attribute requirements include one or more of the following: news elements of the real-time news event required to be displayed, the number of words of the summary required to be displayed, and the news type of the real-time news event required to be displayed; Extracting corresponding key information from each of the real-time news events and inputting it into a multimodal large model; Extract the corresponding first key information from the key information of each real-time news event according to the attribute requirements; Each first key information is processed according to the format requirements to obtain summary information of each real-time news event; wherein the format requirements include subject, predicate, object and qualifier, and the qualifier is located before the subject and the object.

[0008] In combination with the first aspect, the embodiment of the present invention provides a third possible implementation of the first aspect, wherein the step of determining the first preset template for each real-time news event according to the format requirements and attribute requirements of the summary information includes: Determining a preset initial template corresponding to each of the real-time news events according to the source URL and news type of each of the real-time news events; Each of the preset initial templates is processed based on the required display format and required display attributes of the summary information to obtain a first preset template corresponding to each of the real-time news events.

[0009] In combination with the first aspect, the embodiment of the present invention provides a fourth possible implementation manner of the first aspect, wherein the step of determining, according to the authenticity of the real-time news event and the summary information, a target real-time news event corresponding to the request information from the real-time news event includes: If the authenticity meets the requirements, the real-time news event is determined as a news fact, and a target real-time news event corresponding to the request information is determined from the news facts according to the qualifier in the summary information; If the authenticity does not meet the requirements, the real-time news event is determined as a news clue, and the news clue in the real-time news event is removed.

[0010] In combination with the first aspect, the embodiment of the present invention provides a fifth possible implementation of the first aspect, wherein the method further includes: If the real-time news event is a news clue, the target content is crawled according to the news clue to verify the authenticity of the news clue, and if the news clue meets the authenticity requirements, the real-time news event corresponding to the news clue is identified as a news fact.

[0011] In combination with the first aspect, an embodiment of the present invention provides a sixth possible implementation of the first aspect, wherein the step of determining, according to the qualifier in the summary information, a target real-time news event corresponding to the request information from the news facts includes: Determining, according to the category of the qualifier in the summary information, the real domain of the subject and / or object in the summary information defined by the qualifier; Based on the real domain of the summary information, a target real-time news event matching the request information is determined from the news facts.

[0012] In combination with the first aspect, the embodiment of the present invention provides a seventh possible implementation of the first aspect, wherein the step of inputting the request information and the summary information of the target real-time news event into the multimodal big model and outputting a response to the request information includes: Performing semantic recognition on the request information to determine the request type of the request information; If the request type is a question-answer request, generating an answer to the request information based on a reply rule determined from a third preset template of the multimodal macro model and summary information of the target real-time news event; If the request type is a non-question-and-answer request, a summary of the request information is generated based on the summary rules determined from the third preset template of the multimodal big model and the summary information of the target real-time news event.

[0013] In combination with the first aspect, an embodiment of the present invention provides an eighth possible implementation of the first aspect, wherein, in response to request information input to a graphical user interface, the step of controlling a real-time search engine to retrieve at least one real-time news event corresponding to the request information includes: Receiving request information input by a user in a graphical user interface; According to the request information, control the real-time search engine to crawl text content whose matching degree with the request information reaches a preset matching threshold value and the publishing time of the text content from at least one third-party website; At least one real-time news event is determined based on the text content whose publishing time meets the preset time range requirement.

[0014] In a second aspect, an embodiment of the present invention further provides a processing device for real-time news events based on a large model, comprising: A retrieval module, in response to request information inputted into the graphical user interface, controls the real-time search engine to retrieve at least one real-time news event corresponding to the request information; A first determination module extracts corresponding key information from each of the real-time news events, and inputs the key information into the multimodal macro model to determine summary information corresponding to each of the real-time news events; wherein the first preset template is determined according to the format requirements and attribute requirements of the summary information; A second determination module determines the authenticity of the real-time news event corresponding to each summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template; A third determining module, determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity of the real-time news event and the summary information; The response module inputs the request information and the summary information of the target real-time news event into the multimodal macro model, and outputs a response to the request information.

[0015] The embodiment of the present invention provides a method and device for processing real-time news events based on a large model. First, a request for a real-time news event is obtained through an interactive graphical user interface. According to the request information, a real-time search engine can crawl at least one real-time news event from each website; at this time, key information that can reflect the main content of the news is initially crawled from the real-time news event, and then the summary information of each real-time news event is extracted according to the first preset template in the multimodal model; the authenticity of each real-time news event is verified according to the second preset template and the summary information; based on the authenticity and summary information, a target real-time news event that meets the request information is determined from multiple real-time news events, and then the summary information and request information corresponding to the target real-time news event are input into the multimodal large model, so that the multimodal large model outputs a reply response to the request information of the target real-time news event; the above method can ensure the accuracy and real-time nature of the real-time news event question answering.

[0016] 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 are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flow chart of a method for processing real-time news events based on a large model provided by an embodiment of the present invention; Figure 2 A schematic diagram of functional modules of a large model-based real-time news event processing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] When the current multimodal big model asks questions about real-time news events, it may get some "outdated answers" that do not match the current real-time news, resulting in poor accuracy in answering questions about real-time news events. For example, how many gold medals did country X win in the Olympics? This request information is real-time during the Olympic Games, and its gold medal count is subject to change.

[0022] Based on this, an embodiment of the present invention provides a method and device for processing real-time news events based on a large model, which can screen out accurate target real-time news through question requests and news authenticity, and then reply to requests for the target real-time news based on response rules to ensure the accuracy of responses to real-time news event questions.

[0023] To facilitate understanding of this embodiment, a method for processing real-time news events based on a large model disclosed in an embodiment of the present invention is first introduced in detail. This method can be applied to intelligent devices such as controllers, host computers, servers, and touch-screen interactive terminals.

[0024] Figure 1 A flow chart of a method for processing real-time news events based on a large model provided by an embodiment of the present invention; Reference Figure 1 , the method mainly comprises the following steps: Step S102, in response to request information input into the graphical user interface, controlling the real-time search engine to retrieve at least one real-time news event corresponding to the request information.

[0025] Among them, the graphical user interface can be understood as an interface integrated in the above-mentioned smart device that is convenient for user interaction; the request information can be understood as a request statement for a real-time news event; the request statement may include multiple modal forms, such as voice, text, video, etc.; after converting each modal request statement into text, the statement text includes a first text information for locating the real-time news event, and a second text information for characterizing the corresponding request for the text information; based on the request information, at least one real-time news event can be retrieved accordingly.

[0026] Step S104, extracting corresponding key information from each real-time news event, and inputting the key information into the multimodal big model to determine summary information corresponding to each real-time news event.

[0027] Among them, the format requirements and attribute requirements that the expected summary information must meet are preset; the format requirements can be understood as the arrangement of the text in the summary information, and the attribute requirements can be understood as the content information of the text in the summary information and the attributes corresponding to the content information; and the first preset template is determined according to the format requirements and attribute requirements of the summary information; the first preset template is used to guide the multimodal large model to further extract summary information from the key information of each real-time news event; here, the key information can be understood as the information that is initially captured from each real-time news event and can reflect the main content of the real-time news event, usually including at least one complete news paragraph in the real-time news event.

[0028] Step S106, determining the authenticity of the real-time news event corresponding to each summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template.

[0029] It should be noted that the current real-time news events are captured only because they are related to the request information, and the authenticity of such real-time news events themselves cannot be guaranteed. In this embodiment of the present invention, the news elements corresponding to each real-time news event are verified by the second preset template to determine the authenticity of each real-time news event. Among them, each news event includes at most six news elements, such as time, people, place, cause, process, and result; the second preset template is pre-configured with verification rules for each news element, as well as the verification weight corresponding to each news element, that is, whether each news element is verified or not plays a different role in the authenticity of the real-time news event.

[0030] Step S108, determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity and summary information of the real-time news event.

[0031] It can be understood that, by combining the verification of the authenticity of each real-time news event in the aforementioned embodiment steps and the summary information extracted from each real-time news event, the target real-time news event with the highest match to the requested information is determined; in other words, the target real-time news event is generally a real-time news event that meets the requested information and has a higher degree of authenticity.

[0032] Step S110, input the request information and summary information of the target real-time news event into the multimodal macro model, and output a response to the request information.

[0033] The multimodal large model also includes a third preset template, which can respond to the input request information for the target real-time news event and output reply information for the request information.

[0034] In a preferred embodiment of actual application, first, a request for a real-time news event is obtained through an interactive graphical user interface, and according to the request information, the real-time search engine can crawl at least one real-time news event from each website; at this time, key information that can reflect the main content of the news is preliminarily crawled from the real-time news event, and then the summary information of each real-time news event is extracted according to the first preset template in the multimodal model; the authenticity of each real-time news event is verified according to the second preset template and the summary information; based on the authenticity and summary information, a target real-time news event that meets the request information is determined from multiple real-time news events, and then the summary information and request information corresponding to the target real-time news event are input into the multimodal large model, so that the multimodal large model outputs a reply response to the request information for the target real-time news event; the above method can ensure the accuracy and real-time nature of the answer to the question of the real-time news event.

[0035] In some embodiments, step S102 may be implemented in the following manners, including: Step 1.1), receiving the request information input by the user in the graphical user interface.

[0036] Here, the user can input the request information by interacting with the graphical user interface; for example, the user can input the request information in the corresponding modal form in the graphical user interface to form the request information in the graphical user interface, such as voice, video, text, etc., or by single clicking, long pressing, or double clicking a specific mark on the graphical user interface to achieve the purpose of inputting the request information in the graphical user interface. In actual applications, for multimodal input information, the multimodal large model converts it into text form, performs text extraction, and obtains at least one real-time news event accordingly.

[0037] Step 1.2), based on the request information, control the real-time search engine to crawl target content whose matching degree with the request information reaches a preset matching threshold from at least one third-party website, as well as the release time of the target content.

[0038] It should be noted that the target content crawled from the third-party website according to the request information may include multi-modal forms, such as crawling a video, audio, picture, text, etc. that closely matches the request information from the third-party website; Here, the multimodal large model can perform text extraction on the multimodal request information. The first text information and the second text information included in the extracted request information can locate text content that matches the first text information and meets the requirements from the website. Each text content has its corresponding release time. For example, the request information is how many gold medals country X has won in the Olympics, wherein the first text information used for positioning is "how many gold medals country X has won in the Olympics", and the second text information is used to represent the request corresponding to the real-time news as "how many"; based on the request information, various text contents matching "how many gold medals country X has won in the Olympics" and the publishing time of the text contents may be crawled.

[0039] The crawling rules can be set in advance, and the search results will be filtered through the search engine to obtain the search results that meet the preset time range requirements. For example, the contents of 5 websites that meet the preset time range requirements are retrieved.

[0040] Step 1.3), at least one real-time news event is determined based on the target content whose release time meets the preset time range requirement.

[0041] It is understandable that the news located by "Number of Olympic gold medals of country X" has real-time requirements, that is, the news content in different time periods, that is, the number of gold medals may change. Therefore, in order to ensure the reliability of the response, the embodiment of the present invention determines the real-time news event that matches the request information according to the release time within the preset time range; for example, the news event whose release time is within the current preset time range (one day, one hour, half an hour, etc.) and whose text content matches the request information is determined as a real-time news event.

[0042] On the basis of the above-mentioned embodiment, step S104 performs preliminary extraction on the determined real-time news events, and then inputs the extracted key information into the multimodal big model to further determine summary information, including: Step 2.1), according to the format requirements and attribute requirements of the summary information, determine the first preset template for each real-time news event.

[0043] Here, the first preset template for each real-time news event can be predetermined. The first preset template corresponding to each real-time news event may be the same or different. The first preset template is determined according to the format requirements and attribute requirements of the summary information. In other words, the expected requirements for the summary information corresponding to each real-time news event may be different, resulting in different real-time news events having different first preset templates.

[0044] As an optional embodiment, a preset initial template corresponding to each real-time news event can be determined based on the source URL and news type of each real-time news event; each preset initial template is then processed based on the required display format and required display attributes of the summary information to obtain a first preset template corresponding to each real-time news event.

[0045] In step 2.2), the corresponding key information is extracted from each real-time news event and input into the multimodal large model.

[0046] Here, the original disclosure of each real-time news event may contain some content that is not related to the news event itself, which is mainly reflected in the news event display paragraphs on the website page; for example, the main content of the news is presented in the second and third paragraphs of the page, and the first paragraph of the page is non-critical information that can be deleted; the embodiment of the present invention extracts the corresponding key paragraphs related to the main body of the news event from each real-time news event based on the request information, forms key information, and then inputs it into the multimodal large model.

[0047] Step 2.3), extract the corresponding first key information of each real-time news event according to the attribute requirements.

[0048] The attribute requirements include one or more of the following: news elements of real-time news events that require to be displayed, the number of words of abstracts that require to be displayed, and the news types of real-time news events that require to be displayed; Here, the key paragraphs including at least one news event body are extracted in the above steps, and several news elements corresponding to the real-time news event of a specific news type are extracted according to the attribute requirements, and the first key information is presented according to a specific number of words in the summary; For example, news types include sports, games, humanities, entertainment, society and the like. In the aforementioned embodiment, each real-time news event that matches the request information may correspond to a variety of different news types, or each real-time news event may include multiple news types. Here, the target news type of each real-time news event can be determined according to the attribute requirements in the first preset template, and the first key information only extracts information from key paragraphs of the real-time news event of the target news type.

[0049] In step 2.4), each first key information is processed according to the format requirements, and the summary information of each real-time news event is output.

[0050] Among them, the format requirements include subject, predicate, object and qualifier, and the qualifier is placed before the subject and object.

[0051] Here, on the basis that the first key information meets the attribute requirements, the specific sentence components in the first key information are arranged according to the format requirements; for example, the first key information "August 5 is the tenth competition day of the A Olympic Games, and 19 Olympic gold medals will be produced on this day." After processing, the summary information "The tenth competition day of the A Olympic Games - August 5 - will produce - 19 - Olympic gold medals" is obtained.

[0052] It should be noted that step 2.3) and step 2.4) are the process of processing key information according to the first preset template in the multimodal large model to generate output summary information.

[0053] In practical applications, the authenticity of each real-time news event can be verified to further ensure the reliability of the response based on the real-time news event. As an example, step S106 distinguishes news facts and news clues by the completeness of news elements, thereby obtaining the authenticity of each real-time news event, including: In step 3.1), each news element in each summary information is compared with the verification rules corresponding to each news element in the second preset template to obtain the completeness of each news element.

[0054] The second preset template configures corresponding verification rules for each news element according to the criticality of each news element; for example, the more critical the news element is, the higher the completeness requirement is, and the lower the probability of 100% matching is; generally speaking, in order of criticality from high to low, the news elements can be sorted as follows: time, result, person, place, process and cause; that is, the completeness requirement of the news element time is relatively high. Taking the summary information "The tenth competition day of the A Olympic Games - August 5 - will produce 19 Olympic gold medals" as an example, it can be determined whether there is a time news element in the summary information, and the completeness of the text information representing the time in the summary information can be verified. The time includes year, month, day, hour, minute and second, and the summary information contains month and day, so the completeness of the time news element can be determined.

[0055] In step 3.2), the authenticity score of each summary information is determined based on the verification weight of each news element and the completeness of each news element.

[0056] Based on the above-mentioned embodiment, the verification weight corresponding to the more critical news elements is also higher; the product of the completeness of each news element in each summary information and its verification weight is added together to obtain the authenticity score of each summary information.

[0057] In step 3.3), the authenticity score of each summary information is compared with the preset score threshold to determine the authenticity of the real-time news event corresponding to each summary information.

[0058] Here, if the authenticity score corresponding to the summary information of the real-time news event is higher than the preset score threshold, the real-time news event is deemed to meet the authenticity requirements, and such news event is a news fact; otherwise, the authenticity of the real-time news event does not meet the requirements, and such news event is classified as a news clue, which lacks the completeness of news elements and is likely to be false.

[0059] In practical applications, in order to ensure the authenticity and reliability of news events, step S108 further determines a target real-time news event from multiple real-time news events based on the authenticity of the real-time news event. The target real-time news event is not only authentic but also has a high degree of matching with the request information, thereby improving the reliability of the response results of the subsequent response steps, including: In step 4.1), if the authenticity meets the requirements, the real-time news event is determined as a news fact, and the target real-time news event corresponding to the requested information is determined from the news facts according to the qualifiers in the summary information.

[0060] Here, if the authenticity meets the requirements, that is, the news event is news authentic, then the association between the real-time news event and the requested information can be further determined, and the one that meets the requirements for association is determined as the target real-time news event; Exemplarily, according to the category of the qualifier in the summary information, the real domain of the subject and / or object in the summary information defined by the qualifier is determined; based on the real domain of the summary information, the target real-time news event matching the requested information is determined from the news facts.

[0061] Since the first text information in the request information may point to multiple news types or multiple application scenario types at the same time, the embodiment of the present invention can determine the target real-time news event corresponding to the target news type / target scenario / real field through the category of the qualifier in the summary information; Taking the above summary information as an example, the real-time news event may include other activities or competitions where gold medals were won. The gold medals won in the Olympic Games to which the summary information belongs can be determined by the qualifier Olympic Games before the name of the gold medal in the summary information "August 5, the tenth competition day of the Olympic Games A, will produce 19 Olympic gold medals", rather than the gold medals in the game scene. That is, the summary information of other real-time news events where gold medals were won in the game scene will be eliminated; For another example, "Xiao Li" may exist in multiple fields, such as celebrity artist Xiao Li, athlete Xiao Li, etc. If the information requested is "How many gold medals did Xiao Li win in the Olympics", based on the summary information "Xiao Li, a diving athlete, won gold medals in the Olympics", it can be known from the qualifiers before the subject and object that Xiao Li, who participated in the Olympics and won the gold medal, is a diving athlete. Therefore, the summary information of news events such as celebrity artists who also won gold medals but whose winners are Xiao Li are eliminated.

[0062] In step 4.2), if the authenticity does not meet the requirements, the real-time news event is determined as a news clue, and the news clue in the real-time news event is removed.

[0063] Similarly, news clues that do not meet the authenticity requirements will be eliminated.

[0064] As an optional embodiment, in addition to directly presenting news clues that do not meet the authenticity requirements, the method of the embodiment of the present invention also includes: In step 5.1), if the real-time news event is a news clue, the target content is crawled according to the news clue to verify the authenticity of the news clue, and if the news clue meets the authenticity requirements, the real-time news event corresponding to the news clue is identified as a news fact.

[0065] Here, based on the current news clue, the target content matching the current news clue can be crawled again to determine whether there are news elements in the target content that are missing in the current news clue, so that the news requirements of the real-time news event corresponding to the current news clue can be completed. Alternatively, in combination with the target content, the authenticity of the real-time news event corresponding to the current news clue can be re-judged according to the authenticity determination steps in the aforementioned embodiment. If the authenticity after re-determination meets the requirements, the current news clue can be converted into news facts.

[0066] It should be noted that the news facts and news clues can be understood as a label added to real-time news events to characterize authenticity.

[0067] In some embodiments, the request information may be further classified into different types. According to different request types, the multimodal large model may select corresponding processing logic to further ensure the reliability of the request information response. For example, step S110 includes: Step 6.1), semantic recognition is performed on the request information to determine the request type of the request information.

[0068] For example, if the request information is how many gold medals country X has won in the Olympics, it can be determined that the request information is a question-and-answer request; if the request information is a medal report of country X in the Olympics, it can be determined that the request information is a summary request.

[0069] In step 6.2), if the request type is a question-and-answer request, an answer to the requested information is generated based on the reply rule determined from the third preset template of the multimodal big model and the summary information of the target real-time news event.

[0070] Among them, the third preset template is used to guide the multimodal large model to respond to the request information. It pre-configures the processing response logic corresponding to various request types. For example, the third preset template determines the request type of the request information by identifying specific keywords in the request information, and selects the corresponding reply rule according to the corresponding request type. Under the action of the reply rule, based on the summary information of the target real-time news event, an answer to the request information is generated. For another example, the question corresponding to the request information is obtained based on the summary information. If the multimodal large model cannot generate an answer or summary based on the summary information, it outputs "no relevant information was retrieved."

[0071] In step 6.3), if the request type is a non-question-answer request, a summary of the requested information is generated based on the summary rules determined from the third preset template of the multimodal large model and the summary information of the target real-time news event.

[0072] The summary rule may be understood as obtaining the information to be summarized in the request information according to the summary information.

[0073] The embodiments of the present invention are dedicated to ensuring the authenticity and reliability of questions and answers for real-time news events. Due to the rapid development of current information technology and the emergence of self-media, there are large differences in the authenticity of news events appearing on the Internet today. If based on the summary information of a false news clue, the multimodal large model will inevitably output an incorrect answer result. Therefore, in addition to ensuring that the crawled news events match the requested information, it is also necessary to verify the authenticity of the crawled news events.

[0074] In some embodiments, Figure 2 As shown, an embodiment of the present invention provides a processing device for real-time news events based on a large model, comprising: A retrieval module, in response to request information inputted into the graphical user interface, controls the real-time search engine to retrieve at least one real-time news event corresponding to the request information; A first determination module extracts corresponding key information from each of the real-time news events, and inputs the key information into the multimodal macro model to determine summary information corresponding to each of the real-time news events; wherein the first preset template is determined according to the format requirements and attribute requirements of the summary information; A second determination module determines the authenticity of the real-time news event corresponding to each summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template; A third determining module, determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity of the real-time news event and the summary information; The response module inputs the request information and the summary information of the target real-time news event into the multimodal macro model, and outputs a response to the request information.

[0075] Furthermore, the second determination module is also used to compare each news element in each summary information with the verification rules corresponding to each news element in the second preset template to obtain the completeness of each news element; determine the authenticity score of each summary information based on the verification weight of each news element and the completeness of each news element; compare the authenticity score of each summary information with a preset score threshold to determine the authenticity of the real-time news event corresponding to each summary information.

[0076] Furthermore, the first determination module is also used to determine the first preset template for each of the real-time news events according to the format requirements and attribute requirements of the summary information; wherein the attribute requirements include one or more of the following: news elements required to be displayed for the real-time news event, the number of words required to be displayed for the summary, and the news type of the real-time news event required to be displayed; extracting the corresponding first key information from each of the real-time news events according to the attribute requirements; processing each of the first key information according to the format requirements to obtain the second key information corresponding to each of the real-time news events; wherein the format requirements include a subject, a predicate, an object and a qualifier, and the qualifier is located before the subject and the object; inputting the second key information into the multimodal large model to obtain summary information for each of the real-time news events.

[0077] Furthermore, the first determination module is also used to determine the preset initial template corresponding to each of the real-time news events according to the source URL and news type of each of the real-time news events; and process each of the preset initial templates based on the required display format and required display attributes of the summary information to obtain the first preset template corresponding to each of the real-time news events.

[0078] Furthermore, the third determination module is also used to, if the authenticity meets the requirements, determine the real-time news event as a news fact, and determine the target real-time news event corresponding to the request information from the news facts based on the qualifiers in the summary information; if the authenticity does not meet the requirements, determine the real-time news event as a news clue, and remove the news clue from the real-time news event.

[0079] Furthermore, the device is also used to, if the real-time news event is a news clue, crawl target content according to the news clue, verify the authenticity of the news clue, and if the news clue meets the authenticity requirements, identify the real-time news event corresponding to the news clue as a news fact.

[0080] Furthermore, the third determination module is also used to determine the real domain of the subject and / or object in the summary information defined by the qualifier according to the category of the qualifier in the summary information; and based on the real domain of the summary information, determine the target real-time news event that matches the request information from the news facts.

[0081] Furthermore, the response module is also used to perform semantic recognition on the request information to determine the request type of the request information; if the request type is a question-and-answer request, then based on the reply rule determined from the third preset template of the multimodal big model and the summary information of the target real-time news event, generate an answer to the request information; if the request type is a non-question-and-answer request, then based on the summary rule determined from the third preset template of the multimodal big model and the summary information of the target real-time news event, generate a summary of the request information.

[0082] Furthermore, the retrieval module is also used to receive request information input by a user in a graphical user interface; based on the request information, control the real-time search engine to crawl text content whose matching degree with the request information reaches a preset matching threshold, as well as the publishing time of the text content from at least one third-party website; and determine at least one real-time news event based on the text content whose publishing time meets the preset time range requirement.

[0083] It can be understood that the specific operation methods of each functional module in this embodiment can refer to the detailed description of the corresponding steps in the above method embodiment, and will not be repeated here.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0085] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0086] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0087] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the aforementioned embodiments, those of ordinary skill in the art should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed by the present invention, or can easily conceive of changes, or make equivalent replacements for some of the technical features therein. Such modifications, changes or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention.

Claims

1. A method for processing real-time news events based on a large model, characterized in that: include: In response to request information inputted into the graphical user interface, controlling the real-time search engine to retrieve at least one real-time news event corresponding to the request information; Extracting corresponding key information from each of the real-time news events, and inputting the key information into the multimodal big model, and determining summary information corresponding to each of the real-time news events; wherein the multimodal big model includes a first preset template for extracting the summary information, and the first preset template is determined according to the format requirements and attribute requirements of the summary information; Determine the authenticity of the real-time news event corresponding to each of the summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template; Determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity of the real-time news event and the summary information; The request information and summary information of the target real-time news event are input into the multimodal macro model, and a response to the request information is output.

2. The method according to claim 1, characterized in that The step of determining the authenticity of the real-time news event corresponding to each of the summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template includes: Compare each news element in each summary information with the verification rule corresponding to each news element in the second preset template to obtain the completeness of each news element; Determining the authenticity score of each summary information according to the verification weight of each news element and the completeness of each news element; The authenticity score of each summary information is compared with a preset score threshold to determine the authenticity of the real-time news event corresponding to each summary information.

3. The method according to claim 1, characterized in that: The step of extracting corresponding key information from each of the real-time news events, inputting the key information into the multimodal macro model, and determining summary information corresponding to each of the real-time news events comprises: Determine a first preset template for each real-time news event according to the format requirements and attribute requirements of the summary information; wherein the attribute requirements include one or more of the following: news elements of the real-time news event required to be displayed, the number of words of the summary required to be displayed, and the news type of the real-time news event required to be displayed; Extracting corresponding key information from each of the real-time news events and inputting it into a multimodal large model; Extracting corresponding first key information from the key information of each real-time news event according to the attribute requirements; Each of the first key information is processed according to the format requirements to obtain summary information of each of the real-time news events; wherein the format requirements include a subject, a predicate, an object and a qualifier, and the qualifier is located before the subject and the object.

4. The method according to claim 3, characterized in that The step of determining a first preset template for each real-time news event according to the format requirements and attribute requirements of the summary information comprises: Determining a preset initial template corresponding to each of the real-time news events according to the source URL and news type of each of the real-time news events; Each of the preset initial templates is processed based on the required display format and required display attributes of the summary information to obtain a first preset template corresponding to each of the real-time news events.

5. The method according to claim 3, characterized in that: The step of determining a target real-time news event corresponding to the request information from the real-time news event according to the authenticity of the real-time news event and the summary information comprises: If the authenticity meets the requirements, the real-time news event is determined as a news fact, and a target real-time news event corresponding to the request information is determined from the news facts according to the qualifier in the summary information; If the authenticity does not meet the requirements, the real-time news event is determined as a news clue, and the news clue in the real-time news event is removed.

6. The method according to claim 5, characterized in that The method further comprises: If the real-time news event is a news clue, the target content is crawled according to the news clue to verify the authenticity of the news clue, and if the news clue meets the authenticity requirements, the real-time news event corresponding to the news clue is identified as a news fact.

7. The method according to claim 5, characterized in that The step of determining a target real-time news event corresponding to the request information from the news facts according to the qualifier in the summary information comprises: Determining, according to the category of the qualifier in the summary information, the real domain of the subject and / or object in the summary information defined by the qualifier; Based on the real domain of the summary information, a target real-time news event matching the request information is determined from the news facts.

8. The method according to claim 3, characterized in that The step of inputting the request information and the summary information of the target real-time news event into the multimodal macro model and outputting a response to the request information comprises: Performing semantic recognition on the request information to determine the request type of the request information; If the request type is a question-answer request, generating an answer to the request information based on a reply rule determined from a third preset template of the multimodal macro model and summary information of the target real-time news event; If the request type is a non-question-and-answer request, a summary of the request information is generated based on the summary rules determined from the third preset template of the multimodal big model and the summary information of the target real-time news event.

9. The method according to claim 1, characterized in that: In response to request information inputted into the graphical user interface, the step of controlling the real-time search engine to retrieve at least one real-time news event corresponding to the request information comprises: Receiving request information input by a user in a graphical user interface; According to the request information, control the real-time search engine to crawl target content whose matching degree with the request information reaches a preset matching threshold value and the release time of the target content from at least one third-party website; At least one real-time news event is determined according to the target content whose release time meets the preset time range requirement.

10. A real-time news event processing device based on a large model, characterized in that: include: A retrieval module, in response to request information inputted into the graphical user interface, controls the real-time search engine to retrieve at least one real-time news event corresponding to the request information; A first determination module extracts corresponding key information from each of the real-time news events, and inputs the key information into the multimodal big model to determine summary information corresponding to each of the real-time news events; wherein the multimodal big model includes a first preset template for extracting the summary information, and the first preset template is determined according to the format requirements and attribute requirements of the summary information; A second determination module determines the authenticity of the real-time news event corresponding to each summary information according to the verification rules and verification weights corresponding to each news element of the summary information in the second preset template; A third determining module, determining a target real-time news event corresponding to the request information from the real-time news events according to the authenticity of the real-time news event and the summary information; The response module inputs the request information and the summary information of the target real-time news event into the multimodal macro model, and outputs a response to the request information.

Images