Event report generation method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides an event report generation method, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring report requirement information of a preset event; acquiring first media content corresponding to the preset event according to the report requirement information; acquiring second media content corresponding to the preset event according to the report requirement information and the first media content; and generating an event report of the preset event based on the first media content and the second media content. According to the embodiment of the invention, by utilizing the technical scheme, the generation efficiency of the event report and the accuracy of the generated event report can be improved through technologies such as artificial intelligence and large models.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a method for generating an event report, an electronic device, a storage medium, and a program product. Background Art

[0002] With the rapid development of artificial intelligence technology, machine learning-based text generation systems have been widely used in various fields. These systems use trained models to generate text, such as extracting features from input data, using the trained model to generate preliminary text, and then optimizing the quality of the generated text through post-processing steps.

[0003] However, in related technologies, text generation systems often find it difficult to achieve efficient and comprehensive information collection when processing complex event reports, resulting in low accuracy and generation efficiency of event reports. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method for generating an event report, an electronic device, a storage medium, and a program product to improve the accuracy and generation efficiency of event reports.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for generating an event report, comprising:

[0006] Obtain information on reporting requirements for pre-defined events;

[0007] acquiring first media content corresponding to the preset event according to the report request information;

[0008] Acquiring second media content corresponding to the preset event according to the report request information and the first media content;

[0009] An event report of the preset event is generated based on the first media content and the second media content.

[0010] In a second aspect, an embodiment of the present disclosure further provides a device for generating an event report, including:

[0011] A requirement acquisition module is used to obtain reporting requirement information of preset events;

[0012] A first content acquisition module, configured to acquire first media content corresponding to the preset event according to the report requirement information;

[0013] A second content acquisition module, configured to acquire second media content corresponding to the preset event according to the report request information and the first media content;

[0014] A report generating module is configured to generate an event report of the preset event based on the first media content and the second media content.

[0015] In a third aspect, an embodiment of the present disclosure further provides an electronic device, including:

[0016] one or more processors;

[0017] a memory for storing one or more programs,

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating an event report as described in the embodiment of the present disclosure.

[0019] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating an event report as described in the embodiment of the present disclosure.

[0020] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product. When the computer program product is executed by a computer, the computer implements the method for generating an event report as described in the embodiment of the present disclosure.

[0021] The event report generation method, electronic device, storage medium and program product provided by the embodiments of the present disclosure, after obtaining the first media content based on the reporting requirement information of the preset event, continue to obtain the second media content associated with the preset event based on the preset reporting requirement information and the first media content that has been obtained, which can improve the comprehensiveness of the obtained media content and the efficiency of obtaining the media content, thereby improving the accuracy and generation efficiency of the generated event report, for example, through technologies such as artificial intelligence and big models, to improve the accuracy and generation efficiency of event reports. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0023] Figure 1 A flowchart of a method for generating an event report provided in an embodiment of the present disclosure;

[0024] Figure 2 A flowchart of another method for generating an event report provided in an embodiment of the present disclosure;

[0025] Figure 3 A schematic diagram of a process for generating an event report provided in an embodiment of the present disclosure;

[0026] Figure 4A schematic diagram of an information collection process provided by an embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of a clustering deduplication and opinion extraction process provided by an embodiment of the present disclosure;

[0028] Figure 6 A structural block diagram of a device for generating an event report provided in an embodiment of the present disclosure;

[0029] Figure 7 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0031] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0032] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0033] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0034] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0035] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0036] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0037] Figure 1 This is a flow chart of a method for generating an event report provided in an embodiment of the present disclosure. This method can be performed by an event report generation device, wherein the device can be implemented by software and / or hardware and can be configured in an electronic device, typically a computer, mobile phone, or tablet computer. The event report generation method provided in an embodiment of the present disclosure is suitable for scenarios where an event report is automatically generated based on report request information input by a user.

[0038] With the development of artificial intelligence technology, it is now possible to use text generation systems based on natural language processing to generate event reports, in order to overcome the problem that traditional report generation methods rely on predefined templates and simple rule matching and are difficult to handle complex semantic understanding and information integration.

[0039] Natural language processing technology generally involves text summarization, information retrieval, and sentiment analysis. For example, natural language processing technology can analyze large amounts of text data to extract key information and generate concise text summaries.

[0040] Take, for example, machine learning-based text generation systems. These systems utilize trained models to generate text, such as incident reports. These systems typically follow these steps: first, they extract features from the input data; second, they utilize the trained model to generate preliminary text; and finally, they optimize the quality of the generated text through post-processing. However, these systems often struggle to efficiently and comprehensively gather information when processing complex incident reports, resulting in low accuracy and inefficient generation of incident reports.

[0041] In view of this, an embodiment of the present disclosure provides a method for generating an event report. After obtaining the first media content based on the reporting requirement information of a preset event, the method continues to obtain the second media content associated with the preset event based on the preset reporting requirement information and the first media content that has been obtained, so as to improve the comprehensiveness of the obtained media content and the efficiency of obtaining the media content, thereby improving the accuracy and generation efficiency of the event report.

[0042] like Figure 1 As shown, the method for generating an event report provided in this embodiment may include:

[0043] S101: Obtain reporting requirement information for a preset event.

[0044] Among them, the preset event can be understood as the event for which the event report is to be generated, such as the event corresponding to the report requirement information input by the user. The type of preset event is not limited, such as preset events can include accidents, emergencies or social events, etc. The associated media content of the preset event can be media content associated with the preset event, such as media content released for the preset event. The type of associated media content is not limited, for example, the associated media content of the preset event can include picture content, text content, and a combination of picture content and video content, etc. The report requirement information of the preset event can be understood as the requirement information input by the user for the event report to be generated. This report requirement information can be used to describe the user's requirements for the event report to be generated, such as the event for which the event report to be generated is targeted (i.e., the preset event) and / or the requirements for each content component of the event report to be generated, etc.

[0045] In this embodiment, the reporting requirement information of the preset event can be obtained. For example, when the report generation operation is received, the user intention information entered by the user in the information input area can be obtained as the reporting requirement information of the event report to be generated, so as to facilitate the subsequent generation of an event report that meets this reporting requirement information.

[0046] S102: Acquire first media content corresponding to the preset event according to the report request information.

[0047] The first media content may be media content obtained based on the report request information input by the user, such as picture content, text content, and a combination of picture content and video content obtained based on the report request information input by the user.

[0048] In this embodiment, after obtaining the reporting requirement information for a preset event, information collection can be performed based on the reporting requirement information to obtain first media content that matches the reporting requirement information. For example, the obtained reporting requirement information can be parsed to determine the preset event for which an event report is to be generated, and media content corresponding to the preset event can be obtained as the first media content. For example, media content published under a topic associated with the preset event can be obtained as the first media content corresponding to the preset event, and so on.

[0049] In some embodiments, one or more search information can be generated based on the report request information input by the user, and the first media content corresponding to the preset event can be searched based on this search information, so as to further improve the correlation between the obtained first media content and the preset event while ensuring the comprehensiveness of the obtained first media content.

[0050] Optionally, obtaining the first media content corresponding to the preset event according to the report request information includes: generating at least one first search information according to the report request information; performing media content search based on each of the first search information, and using at least part of the media content obtained from the search as the first media content corresponding to the preset event.

[0051] The first search information may be understood as search information generated based on the report request information of the preset event. The search information may be understood as information used for content search, such as search terms.

[0052] For example, after obtaining the reporting requirement information of a preset event, the reporting requirement information can be parsed to generate one or more search information associated with the reporting requirement information (i.e., first search information), such as inputting the event requirement information of the preset event into a pre-trained first search information generation model, and obtaining the search information output by the first search information as the first search information.

[0053] After generating search information, a media content search can be performed based on each piece of generated search information, and search results can be obtained. At least a portion of the media content in the search results can be used as the first media content corresponding to the preset event. For example, the first n pieces of media content in the search results can be obtained according to the order in which the media content is arranged in the search results, and used as the first media content corresponding to the preset event to further improve the relevance between the obtained first media content and the preset event. Here, n is a positive integer, and its value can be set as needed. For example, n can be set to a value such as 10, 20, or 30.

[0054] S103: Acquire second media content corresponding to the preset event according to the report request information and the first media content.

[0055] The second media content may be media content acquired based on the report request information input by the user and the acquired media content for the preset event. The second media content may include image content, text content, and a combination of image content and video content. This acquired media content may be understood as media content corresponding to the preset event that was acquired prior to the current acquisition of the second media content. It may include, but is not limited to, the first media content. For example, in some cases, this acquired media content may further include acquired second media content.

[0056] In this embodiment, after the first media content corresponding to the preset event is acquired, media content acquisition can continue based on the reporting requirement information of the preset event and the acquired first media content to further improve the comprehensiveness of the acquired media content.

[0057] Specifically, if there is already acquired media content (e.g., first media content) for a preset event, after acquiring the first media content corresponding to the preset event, information collection can continue based on the reporting requirement information of the preset event and the acquired media content for the preset event to acquire second media content corresponding to the preset event. For example, media content that is associated with the acquired media content for the preset event and meets the reporting requirement information for the preset event can be acquired as the second media content corresponding to the preset event, and so on.

[0058] It should be noted that in this embodiment, the step of continuing to collect information (e.g., media content) based on the reporting requirement information of the preset event and the acquired media content of the preset event can be performed once or multiple times, and this embodiment is not limited to this. For example, the step of acquiring the second media content based on the reporting requirement information of the preset event and the acquired media content of the preset event can be repeatedly performed until the preset acquisition condition for the second media content is no longer met.

[0059] Optionally, obtaining the second media content corresponding to the preset event based on the report requirement information and the first media content includes: generating at least one second search information based on the report requirement information, the obtained media content of the preset event, and the generated search information of the preset event, wherein the obtained media content includes the first media content, and the generated search information includes the first search information generated based on the report requirement information; in response to the current condition satisfying the preset acquisition condition of the second media content, performing a media content search based on each of the second search information; obtaining at least part of the media content obtained by the search as the second associated media content corresponding to the preset event, and returning to execute the operation of generating at least one second search information based on the report requirement information, the obtained media content of the preset event, and the generated search information of the preset event, until the current condition does not satisfy the preset acquisition condition.

[0060] The second search information can be understood as search information generated based on the reporting requirement information of the preset event, the acquired media content of the preset event, and the generated search information of the preset event. The generated search information can be understood as search information that has been generated for the preset event, which may include but is not limited to the first search information generated based on the reporting requirement information of the preset event. For example, in some cases, the generated search information may further include the second search information generated for the preset event.

[0061] The preset acquisition condition for the second media content can be understood as a pre-set condition that must be met in order to continue acquiring the second media content. The preset acquisition condition can be set as needed. For example, the preset acquisition condition may include the number of times the second media content has been acquired repeatedly reaching a preset number, or the duration of acquiring the second media content reaching a preset duration, etc.

[0062] In some examples, the preset acquisition condition corresponds to the correlation information between the at least one second search information and the preset event. For example, it can be flexibly determined whether it is necessary to continue to perform the step of collecting information based on the reporting requirement information of the preset event and the acquired media content of the preset event according to the information collection situation of the preset event, so as to reduce the time spent on acquiring media content that is less correlated with the preset event while ensuring the comprehensiveness of the acquired media content, thereby further improving the speed of generating event reports. Among them, the correlation information between the second search information and the preset event can be understood as information used to describe the correlation between the generated second search information and the preset event, such as the correlation information between each second search information and the reporting requirement information of the preset event, and / or the proportion of the second search information that has a strong correlation with the reporting requirement information of the preset event (such as a correlation higher than a preset correlation threshold, etc.) in the second search information generated this time, and so on.

[0063] For example, after acquiring the first media content, one or more pieces of second search information may be generated based on the acquired first media content, the reporting requirement information for the preset event, and the first search information. For example, the acquired first media content, the reporting requirement information for the preset event, and the generated first search information may be input into a pre-trained second search information generation model, and search information output by the second search information generation model that is different from the generated first search information may be obtained as the second search information.

[0064] After obtaining the second search information, a media content search can be performed based on each piece of second search information generated this time, and search results can be obtained. At least a portion of the media content in the search results can be used as the second media content corresponding to the preset event. For example, the first m pieces of media content in the search results can be obtained according to the order in which the media content is arranged in the search results, and used as the second media content corresponding to the preset event to further improve the relevance between the obtained second media content and the preset event. Here, m is a positive integer, and its value can be set as needed. For example, m can be set to a value such as 10, 20, or 30.

[0065] After acquiring the second media content, one or more pieces of second search information may be regenerated based on the acquired first media content, the acquired second media content, the reporting requirement information for the preset event, and the already generated first search information and second search information. For example, the acquired first media content, the acquired second media content, the reporting requirement information for the preset event, and the already generated first search information and second search information may be input into a pre-trained second search information generation model, and search information output by the second search information generation model that is different from the already generated first search information and second search information may be acquired as the newly generated second search information.

[0066] After obtaining the newly generated second search information, if the current conditions satisfy the preset conditions for obtaining the second media content, the second media content can continue to be obtained based on the newly generated second search information. Taking the correspondence between the preset conditions for obtaining the second media content and the correlation between each piece of second search information and the reporting requirement information of a preset event as an example, after obtaining the newly generated second search information, the determination of whether to continue obtaining the second media content can be made based on the correlation between each piece of the newly generated second search information and the reporting requirement information of the preset event. For example, the correlation between each piece of the newly generated second search information and the reporting requirement information of the preset event can be calculated, and the proportion of second search information with correlations greater than a preset correlation threshold in the newly generated second search information can be calculated. If this proportion is greater than the preset proportion threshold, the operation of performing a media content search based on each piece of the second search information generated this time and obtaining search results can be repeated until it is determined that further obtaining the second media content is no longer necessary. The preset proportion threshold can be set as needed, for example, 50%, 60%, or 70%.

[0067] It should be noted that when continuing to obtain the second media content based on the already obtained media content, the second media content can be continued to be obtained based on the content data of the already obtained media content itself; or the second media content can be continued to be obtained based on the media content summary (such as information summary) of the media content. This embodiment does not limit this.

[0068] S104: Generate an event report of the preset event based on the first media content and the second media content.

[0069] An incident report is a document that systematically records and analyzes a specific incident. It can be used to objectively describe the course of events, analyze the causes, and / or summarize the impact of the incident, and may also propose recommendations or countermeasures. An incident report may consist of multiple parts, illustratively including at least part of an incident summary, an incident context (e.g., a record of the incident process), a perspective analysis, an impact analysis (e.g., risk and controversy), a communication analysis, improvement suggestions (e.g., reflections), and a report summary.

[0070] Specifically, after the second media content is acquired, an event report for a preset event can be generated based on the acquired first media content and second media content. For example, the acquired first media content and second media content can be used as associated media content for the preset event, and at least a portion of the associated media content for the preset event can be input into one or more pre-trained report content generation models. The report content generation models can then generate various parts of the preset event, including an event summary, event context, opinion analysis, event impact analysis, communication analysis, improvement suggestions, and / or report summary. The generated parts of the content can then be summarized and polished to obtain an event report for the preset event.

[0071] The method for generating an event report provided in this embodiment obtains reporting requirement information of a preset event; obtains first media content corresponding to the preset event based on the reporting requirement information of the preset event; obtains second media content corresponding to the preset event based on the reporting requirement information of the preset event and the first media content corresponding to the preset event; and generates an event report for the preset event based on the first media content and the second media content. This embodiment utilizes the above-mentioned technical solution, and after obtaining the first media content based on the reporting requirement information of the preset event, continues to obtain the second media content associated with the preset event based on the preset reporting requirement information and the already obtained first media content, which can improve the comprehensiveness of the obtained media content and the efficiency of obtaining the media content, thereby improving the accuracy and generation efficiency of the generated event report. For example, the accuracy and generation efficiency of the event report can be improved through technologies such as artificial intelligence and large models.

[0072] Figure 2A flow chart of another method for generating an event report provided for an embodiment of the present disclosure. The scheme in this embodiment can be combined with one or more optional schemes in the above-mentioned embodiments. Optionally, the method for generating an event report for the preset event based on the first media content and the second media content includes: taking the first media content and the second media content as associated media content of the preset event, and clustering the associated media content to obtain a clustering result; obtaining at least one associated media content from the associated media content of the preset event as target associated media content according to the clustering result; and generating an event report for the preset event based on the target associated media content.

[0073] Correspondingly, such as Figure 2 As shown, the method for generating an event report provided in this embodiment may include:

[0074] S201: Obtain reporting requirement information for a preset event.

[0075] S202: Acquire first media content corresponding to the preset event according to the report request information.

[0076] S203: Acquire second media content corresponding to the preset event according to the report request information and the first media content.

[0077] S204: Use the first media content and the second media content as associated media content of the preset event, and cluster the associated media content to obtain a clustering result.

[0078] The associated media content of the preset event can be understood as media content associated with the preset event.

[0079] In this embodiment, the acquired first media content and second media content may both be used as associated media content of a preset event, and cluster analysis may be performed on the associated media content.

[0080] For example, after both the first media content and the second media content have been acquired, if it is determined that there is no need to continue acquiring the second media content, the acquired first media content and the second media content can be deduplicated to remove duplicated media content in the first media content and the second media content, and the remaining first media content and the second media content after deduplication can be acquired as the associated media content of the preset event. After acquiring the associated media content of the preset event, a cluster analysis can be performed on the associated media content, such as clustering the associated media content using a pre-trained clustering model; or, content information such as a content summary or content theme of each associated media content can be extracted, and the associated media content of the preset event can be clustered based on the similarity between the content information of each associated media content, thereby obtaining a clustering result for each associated media content.

[0081] In some embodiments, the associated media contents of a preset event may be clustered based on the feature vectors of the associated media contents to improve the accuracy of the clustering result, thereby further improving the accuracy of the subsequently generated event report.

[0082] Optionally, clustering the associated media contents to obtain clustering results includes: using a preset vectorization model to vectorize each of the associated media contents to obtain a feature vector of each of the associated media contents; and clustering the associated media contents based on the feature vectors to obtain multiple media content clusters.

[0083] The preset vectorization model can be a pre-set vectorization model. This vectorization model can be used to vectorize media content to obtain a feature vector of the media content. The type of the preset vectorization model can be set as needed. Exemplarily, the preset vectorization model can be a semantic vector model, such as an embedded model. The following description uses the preset vectorization model as an embedded model as an example. This embedded model can be used to convert high-dimensional unstructured data (such as text and / or images, etc.) into a low-dimensional embedded vector. The feature vector of the associated media content can be understood as a vector obtained by vectorizing the associated media content. This feature vector can be used to represent important features such as the semantic information of the media content. A media content cluster can be a subset of media content obtained by clustering the associated media content. Each media content cluster can include one or more associated media content. The associated media content in the same media content cluster has a high degree of similarity. For example, the associated media content in the same media content cluster can have similar themes.

[0084] For example, after obtaining the associated media content of a preset event, the obtained associated media content can be input into a pre-trained vectorization model (i.e., a preset vectorization model), and the associated media content of the preset event can be vectorized by this vectorization model to obtain feature vectors of each associated media content.

[0085] After obtaining the feature vectors of each associated media content, cluster analysis is performed on each associated media content of the preset event based on the feature vectors of each associated media content. For example, similarities between each associated media content of the preset event can be calculated based on the feature vectors of each associated media content. Cluster analysis is then performed on each associated media content of the preset event based on the similarities, resulting in multiple media content clusters as clustering results of the associated media content.

[0086] In some examples, the associated media content of a preset event can be clustered based on a pre-set similarity search library and combined with feature vectors of each associated media content to identify clusters of media content with similar themes. This similarity search library can be flexibly configured as needed. For example, this similarity search library may include, but is not limited to, the Facebook AI Similarity Search (FAISS).

[0087] S205 : Acquire at least one associated media content from the associated media content of the preset event according to the clustering result as target associated media content.

[0088] The target associated media content may be understood as media content used to generate an event report of a preset event. The target associated media content may be representative key media content among multiple associated media contents of the preset event, ie, typical associated media content.

[0089] Specifically, after clustering the associated media content of a preset event, representative key media content from the associated media content of the preset event can be determined based on the clustering results and used as target associated media content. For example, at least a portion of the associated media content of the preset event can be selected as target associated media content based on the location information of each associated media content within its corresponding cluster and / or the publication attribute information of each associated media content.

[0090] S206: Generate an event report of the preset event based on the target-related media content.

[0091] Specifically, after determining the target-related media content of the preset event, an event report for the preset event can be generated based on the target-related media content of the preset event. For example, the target-related media content of the preset event can be input into one or more pre-trained report content generation models (such as a large language model, etc.), and the report content generation model can be used to generate various parts of the preset event, such as an event summary, event context, opinion analysis, event impact analysis, communication analysis, improvement suggestions, and / or report summary. The generated parts of the content are then summarized and polished to obtain an event report for the preset event.

[0092] The event report generation method provided in this embodiment clusters related media content and selects some representative related media content based on the clustering results of the related media content to generate event reports. This can reduce the amount of media content that needs to be processed, improve the accuracy of the related media content used as the basis for generating event reports, and thus improve the generation efficiency of event reports and the accuracy of the generated event reports.

[0093] In some embodiments, the clustering result includes multiple media content clusters, and obtaining at least one associated media content from the associated media content of the preset event according to the clustering result as the target associated media content includes: for the target media content cluster in the multiple media content clusters, obtaining at least one associated media content from the target media content cluster according to the attribute information of each associated media content in the target media content cluster as the target associated media content in the target media content cluster, wherein the attribute information includes clustering attribute information and / or release attribute information.

[0094] In particular, a media content cluster can be understood as a cluster obtained by clustering the associated media content of a preset event. Each media content cluster may include one or more associated media content of the preset event. The attribute information of the associated media content can be understood as the attribute information used as a basis for selecting target associated media content. This attribute information can be flexibly configured as needed. For example, this attribute information can include cluster attribute information and / or publication attribute information. The cluster attribute information of the associated media content can be information describing the clustering attributes of the associated media content in the clustering results, such as the media content cluster to which the associated media content belongs in the clustering results and the distance between the associated media content and the cluster center of the media content cluster. The publication attribute information of the associated media content can be information describing the publication attributes of the associated media content, such as information about the publisher and / or publication time of the associated media content. The target media content cluster can be the cluster from which the target associated media content is currently being acquired; in other words, the current media content cluster from which the target associated media content is being extracted.

[0095] Specifically, for at least part of the media content clusters obtained by clustering (such as the target media content cluster), attribute information of each associated media content in this media content cluster can be determined, and associated media content in this media content cluster whose attribute information meets preset attribute conditions can be obtained as the target associated media content in this media content cluster.

[0096] In some examples, for at least a portion of the media content clusters obtained through clustering, associated media content in the media content cluster whose clustering attribute information satisfies a preset clustering attribute condition can be obtained, such as obtaining the distance between each associated media content in the media content cluster and the cluster center of the media content cluster, and determining the target associated media content in the media content cluster based on the distance. Specifically, a preset number or preset proportion of associated media content can be obtained from the media content cluster in ascending order of distance, or media content whose distance from the cluster center of the media content cluster is less than a preset distance threshold can be obtained from the associated media content cluster as the target associated media content in the media content cluster. The preset number, preset proportion, and preset distance threshold can all be set as needed and are not limited in this embodiment.

[0097] In some examples, for at least a portion of the media content clusters obtained through clustering, associated media content in the media content cluster whose publishing attribute information satisfies preset publishing attribute conditions can be obtained. For example, a publishing attribute evaluation value of each associated media content can be calculated based on the publisher information and / or publishing time information of each associated media content, and based on the publishing attribute evaluation value, one or more media content can be selected from the media content cluster as target associated media content in the media content cluster. For example, a preset number or a preset proportion of associated media content can be obtained from the media content cluster in descending order of the publishing attribute evaluation value, or media content whose publishing attribute evaluation value is greater than a first evaluation threshold can be obtained from the associated media content cluster as target associated media content in the media content cluster.

[0098] In some examples, clustering attribute information and publication attribute information of each associated media content in the cluster can be obtained for at least a portion of the clustered media content clusters. Based on the clustering attribute information and publication attribute information of each associated media content and a preset weight value, a media content evaluation value of each associated media content can be calculated. Based on the media content evaluation value, one or more media content can be selected from the cluster as target associated media content in the cluster. For example, a preset number or ratio of associated media content can be selected from the cluster in descending order of media content evaluation value, or media content with a media content evaluation value greater than a second evaluation threshold can be selected from the cluster as target associated media content in the cluster.

[0099] In some optional examples, clustering attribute information of each associated media content in at least a portion of the clustered media content clusters can be obtained. For example, the distance between each media content and the cluster center of the cluster is obtained, and K media content is obtained from the cluster in ascending order of distance from the cluster center as target associated media content in the cluster. When obtaining the K media content, for associated media content with the same distance from the cluster center, for example, associated media content with a relatively authoritative publisher and / or an earlier release time can be obtained based on the publisher's source level and / or release time as the target associated media content. For example, for associated media content with the same distance from the cluster center, the relatively authoritative publisher can be obtained based on the source level from highest to lowest as the target associated media content; and for associated media content with the same distance from the cluster center and the same source level, the earlier release time can be obtained based on the earlier release time as the target associated media content. Here, K is a positive integer, and its specific value can be set as needed. For example, K can be set to 10, 20, or 30, etc.

[0100] It should be noted that after clustering multiple media content clusters for a preset event, each media content cluster can be used as a target media content cluster to obtain target associated media content within the cluster. Alternatively, the obtained multiple media content clusters can be filtered to remove those containing fewer associated media content (e.g., less than a preset threshold), and each remaining media content cluster can be used as a target media content cluster to obtain target associated media content within the cluster. This embodiment is not limited to this. The preset threshold can be set as needed, for example, 5, 10, or 15.

[0101] In this embodiment, based on the clustering attribute information and / or publication attribute information of the associated media, target associated media content in the corresponding media content clusters is obtained from multiple media content clusters respectively, which can further improve the comprehensiveness and accuracy of the obtained target associated media content, thereby further improving the accuracy of the generated event report.

[0102] In some embodiments, after obtaining the target-associated media content in at least part of the media content cluster, association extraction can be performed based on the target-associated media content in each media content cluster to obtain event viewpoint information of each media content cluster, so as to improve the comprehensiveness and accuracy of the extracted event viewpoint information.

[0103] Optionally, the event report includes opinion analysis content, and generating the event report of the preset event based on the target-associated media content includes: extracting the event opinion information of the preset event according to the target-associated media content in each media content cluster and the reporting requirement information of the preset event; performing opinion analysis on the preset event according to the event opinion information, and generating opinion analysis content of the preset event.

[0104] The opinion analysis content may be content contained in the event report that analyzes the opinions of the preset event. The event opinion information may be information used to describe the public's position or views on the preset event, such as an event opinion set for the preset event.

[0105] Specifically, for each media content cluster that has target-related media content, viewpoints can be extracted based on the target-related media content in this media content cluster to obtain event viewpoint information of the media content in this media content cluster; the event viewpoint information of each media content cluster can be merged and optimized to obtain event viewpoint information of a preset event; and, viewpoint analysis can be performed based on the event viewpoint information of the preset event to generate viewpoint analysis content of the preset event.

[0106] In some examples, when obtaining event viewpoint information of a preset event based on target-associated media content in each media content cluster, illustratively, the reporting requirement information of the preset event and the extracted target-associated media content in this media content cluster can first be input into a pre-trained viewpoint extraction model for each media content cluster. This viewpoint extraction model is used to extract views based on the reporting requirement information of the preset event and the media contents of this media content cluster, and obtains event views that meet the reporting requirement information input by the user as the event views corresponding to this media content cluster. After obtaining the event views of each media content cluster, the event views of each media content cluster can be input into a pre-trained viewpoint merging model. This viewpoint merging model is used to deduplicate and merge the event views of each media content cluster to obtain high-quality views for the preset event as the event views of the preset event.

[0107] In some examples, when obtaining event viewpoint information of a preset event based on target-associated media content in each media content cluster, for example, the extracted target-associated media content in each media content cluster can be first input into a pre-trained viewpoint extraction model for each media content cluster, and this viewpoint extraction model is used to extract views based on the media contents of this media content cluster to obtain event views corresponding to this media content cluster; after obtaining the event views of each media content cluster, the event report of the preset event and the event views of each media content cluster can be input into a pre-trained viewpoint merging model, and this viewpoint merging model is used to deduplicate and merge the event views of each media content cluster, while eliminating views that are irrelevant to the report requirement information input by the user, to obtain high-quality views for the preset event as the event views of the preset event.

[0108] In this embodiment, the method for generating the viewpoint analysis content can be configured as needed. For example, a pre-set viewpoint analysis content template can be used to generate the viewpoint analysis content for a preset event based on the event viewpoint information of the preset event. Alternatively, the event viewpoint information of the preset event can be input into a pre-trained viewpoint analysis model, and the viewpoint analysis content for the preset event can be generated based on the event viewpoint information of the preset event through this viewpoint analysis model, and so on.

[0109] Among them, the opinion extraction model, the opinion merging model and the opinion analysis model can be the same or different models. They can be large language models (LLM) or other data processing models except large speech models. This embodiment does not limit this.

[0110] Figure 3 A schematic diagram of the generation process of an event report provided by an embodiment of the present disclosure. In an optional embodiment, this embodiment may provide a method for generating an event report based on a large language model, so as to achieve efficient and accurate event report generation through intelligent information collection and processing. Figure 3 As shown, the method for generating an event report provided in this embodiment can be described as follows:

[0111] A1. Collect information (ie, related media content) through an information collection agent module.

[0112] Figure 4 A schematic diagram of an information collection process provided by an embodiment of the present disclosure is shown in FIG. Figure 4As shown, the information collection Agent module can use the Agent and network tool calling method to understand the user's intention and gradually collect relevant information. Specifically, in the first round of loop, the user's intention (i.e., report request data) can be analyzed by the first language model to generate a first query (i.e., first search information), and information collection is performed based on this first query to obtain the first media content; in the Lth (L is a positive integer greater than 1) round of loop, the user's intention, the query generated in the previous L-1 rounds (i.e., generated search information) and the collected information (i.e., acquired media content) can be analyzed by the second language model to generate multiple second queries (i.e., second search information) that are different from the generated query, and the third language model is used to determine whether to continue information collection based on the second query generated in this round (i.e., determine whether the current conditions meet the preset acquisition conditions), and if it is determined that information collection can continue, continue to collect information based on the second query. Among them, these queries can be used to call the search engine to obtain the latest relevant information. The information collection process can ensure that the information that meets the user's intention is obtained by merging, deduplication and screening. Figure 1 The first language model, the second language model, and the third language model can be the same or different models.

[0113] A2. Perform clustering and deduplication through the clustering and deduplication module.

[0114] Figure 5 A schematic diagram of a clustering deduplication and opinion extraction process provided by an embodiment of the present disclosure is shown as follows: Figure 5 As shown, the clustering deduplication module can perform cluster analysis on the collected information to reduce redundant information and extract key viewpoints (i.e., event viewpoint information). Specifically, the collected information can be clustered. For example, Faiss can be used in combination with a semantic vector model to cluster the collected information to identify information clusters with similar themes (i.e., media content clusters). For each information cluster, it is sorted by distance from the cluster center, source level, and / or release time, and K key information (i.e., target-related media content) that is relatively authoritative and released earlier is extracted to reduce the amount of information.

[0115] A3. Generate an event report through the report generation module.

[0116] The report generation module integrates all collected and processed information to generate the final incident report. Specifically, based on the LLM model, it generates the various sections of the incident report using the input key information, and then summarizes and polishes each section to obtain the completed incident report. During the incident report generation process, Direct Preference Optimization (DPO) technology can be used to optimize the generation process and improve the stability and quality of the incident report.

[0117] Taking the analysis of the viewpoints of generating an event report as an example, for example, Figure 5 As shown, after determining the key information, opinion generation can be performed. For example, for each information cluster, the user intent and extracted key information are input into the fourth language model to extract opinions and sentiments, generating an event opinion that aligns with the user intent. The generated opinions can then be merged and optimized using the fifth language model. For example, combining the user intent, the generated opinions can be merged and optimized again using the fifth language model to resolve duplicate opinions and obtain the key opinion for the preset event. After obtaining the key opinion for the preset event, event analysis content for the preset event can be generated based on this key opinion. The fourth and fifth language models can be the same as or different from the first, second, or third language models.

[0118] By adopting the above-mentioned technical solutions, this embodiment can quickly respond to user needs and generate high-quality reports. Specifically, traditional text generation systems have difficulty achieving efficient information integration when processing complex event reports. However, this embodiment, through information collection agent technology, can gradually acquire and integrate information in a self-loop, improving the efficiency of information collection and processing, that is, improving the efficiency of information integration, thereby significantly increasing the speed of complex event report generation and being able to respond to user needs more quickly. Through clustering deduplication and opinion extraction technology, it can extract core opinions and emotions from a large amount of information, reduce redundant information, and enhance the accuracy of opinion extraction. This overcomes the technical problem of related technologies that cannot accurately extract the core opinions and emotions of events, improves the accuracy and depth of event reports, and makes the generated event reports more insightful and valuable. Related technologies use large models to generate reports, which generally require high computing resources and result in high generation costs. However, this embodiment, by optimizing the model call process, can reduce the computing resource consumption of the large model of the opinion extraction module, reduce generation costs, and make it more economical and efficient when processing large-scale data.

[0119] Figure 6 This is a structural block diagram of an event report generation device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can be configured in an electronic device, typically a computer, a mobile phone, or a tablet computer. It can be used to automatically generate an event report based on the report request information input by the user by executing the event report generation method. Figure 6 As shown, the event report generation device provided by this embodiment may include: a requirement acquisition module 601, a first content acquisition module 602, a second content acquisition module 603 and a report generation module 604, wherein:

[0120] Requirement acquisition module 601, used to obtain reporting requirement information of a preset event;

[0121] A first content acquisition module 602 is configured to acquire first media content corresponding to the preset event according to the report request information;

[0122] A second content acquisition module 603 is configured to acquire second media content corresponding to the preset event according to the report request information and the first media content;

[0123] The report generating module 604 is configured to generate an event report of the preset event based on the first media content and the second media content.

[0124] The method for generating an event report provided in this embodiment obtains the report requirement information of a preset event through a requirement acquisition module; obtains the first media content corresponding to the preset event according to the report requirement information of the preset event through a first content acquisition module; obtains the second media content corresponding to the preset event according to the report requirement information of the preset event and the first media content corresponding to the preset event through a second content acquisition module; and generates an event report of the preset event based on the first media content and the second media content through a report generation module. This embodiment utilizes the above technical solution, and after obtaining the first media content based on the report requirement information of the preset event, continues to obtain the second media content associated with the preset event based on the preset report requirement information and the already obtained first media content, which can improve the comprehensiveness of the obtained media content and the efficiency of obtaining the media content, thereby improving the accuracy and generation efficiency of the generated event report, for example, by using technologies such as artificial intelligence and large models to improve the accuracy and generation efficiency of event reports.

[0125] Optionally, the first content acquisition module 602 can be specifically used to: generate at least one first search information according to the report requirement information; perform media content search based on each first search information, and use at least part of the media content obtained from the search as the first media content corresponding to the preset event.

[0126] Optionally, the second content acquisition module 603 can be specifically used to: generate at least one second search information based on the report requirement information, the acquired media content of the preset event, and the generated search information of the preset event, wherein the acquired media content includes the first media content, and the generated search information includes the first search information generated based on the report requirement information; in response to the current condition satisfying the preset acquisition condition of the second media content, perform media content search based on each of the second search information respectively; obtain at least part of the media content obtained by the search as the second associated media content corresponding to the preset event, and return to execute the operation of generating at least one second search information based on the report requirement information, the acquired media content of the preset event, and the generated search information of the preset event, until the current condition does not satisfy the preset acquisition condition.

[0127] Optionally, the preset acquisition condition corresponds to information on the degree of association between the at least one piece of second search information and the preset event.

[0128] Optionally, the report generation module 604 includes: a clustering unit, used to take the first media content and the second media content as associated media content of the preset event, and cluster the associated media content to obtain a clustering result; a content acquisition unit, used to acquire at least one associated media content from the associated media content of the preset event as target associated media content according to the clustering result; and a report generation unit, used to generate an event report of the preset event based on the target associated media content.

[0129] Optionally, the clustering unit may be specifically configured to: perform vectorization processing on each of the associated media contents respectively using a preset vectorization model to obtain a feature vector of each of the associated media contents; and cluster the associated media contents based on the feature vector to obtain a plurality of media content clusters.

[0130] Optionally, the clustering result includes multiple media content clusters, and the content acquisition unit can be specifically used to: for a target media content cluster among the multiple media content clusters, obtain at least one associated media content from the target media content cluster as the target associated media content in the target media content cluster based on the attribute information of each associated media content in the target media content cluster, wherein the attribute information includes clustering attribute information and / or publication attribute information.

[0131] Optionally, the event report includes opinion analysis content, and the report generation unit can be specifically used to: extract the event opinion information of the preset event based on the target-associated media content in each media content cluster and the event requirement information of the preset event; perform opinion analysis on the preset event based on the event opinion information to generate opinion analysis content of the preset event.

[0132] The event report generation device provided in the embodiments of the present disclosure can execute the event report generation method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of executing the event report generation method. For technical details not fully described in this embodiment, please refer to the event report generation method provided in any embodiment of the present disclosure.

[0133] Reference below Figure 7 , which shows a schematic structural diagram of an electronic device (e.g., a terminal device or a server) 700 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0134] like Figure 7 As shown, the electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the electronic device 700 are also stored in the RAM 703. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0135] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7The electronic device 700 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0136] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0137] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0138] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0139] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0140] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device is enabled to: obtain multiple associated media content of a preset event; cluster the multiple associated media content to obtain clustering results of the multiple associated media content; obtain at least one associated media content from the multiple associated media content as target associated media content based on the clustering results; and generate an event report for the preset event based on the target associated media content.

[0141] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0143] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a module does not, in some cases, limit the unit itself.

[0144] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0145] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] According to one or more embodiments of the present disclosure, Example 1 provides a method for generating an event report, including:

[0147] Obtain information on reporting requirements for pre-defined events;

[0148] acquiring first media content corresponding to the preset event according to the report request information;

[0149] Acquiring second media content corresponding to the preset event according to the report request information and the first media content;

[0150] An event report of the preset event is generated based on the first media content and the second media content.

[0151] According to one or more embodiments of the present disclosure, Example 2 is the method according to Example 1, wherein obtaining the first media content corresponding to the preset event according to the report requirement information includes:

[0152] generating at least one first search information according to the report request information;

[0153] A media content search is performed based on each of the first search information, and at least a portion of the media content obtained through the search is used as the first media content corresponding to the preset event.

[0154] According to one or more embodiments of the present disclosure, Example 3, according to the method of Example 1, wherein acquiring, based on the report request information and the first media content, second media content corresponding to the preset event includes:

[0155] generating at least one second search information according to the report request information, the acquired media content of the preset event, and the generated search information of the preset event, wherein the acquired media content includes the first media content, and the generated search information includes the first search information generated based on the report request information;

[0156] In response to the current condition satisfying the preset acquisition condition of the second media content, performing a media content search based on each piece of the second search information;

[0157] Acquire at least part of the media content obtained by the search as second associated media content corresponding to the preset event, and return to execute the operation of generating at least one second search information based on the report requirement information, the acquired media content of the preset event, and the generated search information of the preset event, until the current condition does not meet the preset acquisition condition.

[0158] According to one or more embodiments of the present disclosure, Example 4 is the method according to Example 3, wherein the preset acquisition condition corresponds to information on the degree of association between the at least one piece of second search information and the preset event.

[0159] According to one or more embodiments of the present disclosure, Example 5 is the method according to any one of Examples 1-4, wherein generating the event report of the preset event based on the first media content and the second media content includes:

[0160] Taking the first media content and the second media content as associated media content of the preset event, and clustering the associated media content to obtain a clustering result;

[0161] acquiring at least one associated media content from the associated media content of the preset event according to the clustering result as target associated media content;

[0162] An event report of the preset event is generated based on the target-related media content.

[0163] According to one or more embodiments of the present disclosure, Example 6, according to the method of Example 5, clustering the associated media content to obtain a clustering result includes:

[0164] Performing vectorization processing on each of the associated media contents using a preset vectorization model to obtain a feature vector of each of the associated media contents;

[0165] The associated media content is clustered based on the feature vector to obtain multiple media content clusters.

[0166] According to one or more embodiments of the present disclosure, Example 7 is the method according to Example 5, wherein the clustering result includes multiple media content clusters, and obtaining at least one associated media content from the associated media content of the preset event as target associated media content according to the clustering result includes:

[0167] For a target media content cluster among the multiple media content clusters, at least one associated media content is obtained from the target media content cluster based on attribute information of each associated media content in the target media content cluster as the target associated media content in the target media content cluster, wherein the attribute information includes clustering attribute information and / or release attribute information.

[0168] According to one or more embodiments of the present disclosure, Example 8 is the method according to Example 7, wherein the event report includes opinion analysis content, and generating the event report of the preset event based on the target-related media content includes:

[0169] extracting event viewpoint information of the preset event according to the target-related media content in each media content cluster and the event requirement information of the preset event;

[0170] Performing a viewpoint analysis on the preset event according to the event viewpoint information to generate viewpoint analysis content of the preset event.

[0171] According to one or more embodiments of the present disclosure, Example 9 provides an electronic device, including:

[0172] one or more processors;

[0173] a memory for storing one or more programs,

[0174] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating an event report as described in any one of Examples 1-8.

[0175] According to one or more embodiments of the present disclosure, Example 10 provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating an event report as described in any one of Examples 1-8.

[0176] According to one or more embodiments of the present disclosure, Example 11 provides a computer program product. When the computer program product is executed by a computer, the computer implements the method for generating an event report as described in any one of Examples 1-8.

[0177] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0178] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0179] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for generating an event report, characterized in that: include: Obtain information on reporting requirements for pre-defined events; acquiring first media content corresponding to the preset event according to the report request information; Acquiring second media content corresponding to the preset event according to the report request information and the first media content; An event report of the preset event is generated based on the first media content and the second media content.

2. The method according to claim 1, characterized in that The acquiring, according to the report request information, the first media content corresponding to the preset event includes: generating at least one first search information according to the report request information; A media content search is performed based on each of the first search information, and at least a portion of the media content obtained through the search is used as the first media content corresponding to the preset event.

3. The method according to claim 1, characterized in that The acquiring, according to the report request information and the first media content, second media content corresponding to the preset event includes: generating at least one second search information according to the report request information, the acquired media content of the preset event, and the generated search information of the preset event, wherein the acquired media content includes the first media content, and the generated search information includes the first search information generated based on the report request information; In response to the current condition satisfying the preset acquisition condition of the second media content, performing a media content search based on each piece of the second search information; Acquire at least part of the media content obtained by the search as second associated media content corresponding to the preset event, and return to execute the operation of generating at least one second search information based on the report requirement information, the acquired media content of the preset event, and the generated search information of the preset event, until the current condition does not meet the preset acquisition condition.

4. The method according to claim 3, characterized in that The preset acquisition condition corresponds to the correlation information between the at least one piece of second search information and the preset event.

5. The method according to any one of claims 1 to 4, characterized in that: The generating an event report of the preset event based on the first media content and the second media content includes: Taking the first media content and the second media content as associated media content of the preset event, and clustering the associated media content to obtain a clustering result; acquiring at least one associated media content from the associated media content of the preset event according to the clustering result as target associated media content; An event report of the preset event is generated based on the target-related media content.

6. The method according to claim 5, characterized in that Clustering the associated media content to obtain a clustering result includes: Performing vectorization processing on each of the associated media contents using a preset vectorization model to obtain a feature vector of each of the associated media contents; The associated media content is clustered based on the feature vector to obtain multiple media content clusters.

7. The method according to claim 5, characterized in that The clustering result includes a plurality of media content clusters, and obtaining at least one associated media content from the associated media content of the preset event according to the clustering result as target associated media content includes: For a target media content cluster among the multiple media content clusters, at least one associated media content is obtained from the target media content cluster based on attribute information of each associated media content in the target media content cluster as the target associated media content in the target media content cluster, wherein the attribute information includes clustering attribute information and / or release attribute information.

8. The method according to claim 7, characterized in that The event report includes opinion analysis content, and the event report of the preset event generated based on the target-related media content includes: extracting event viewpoint information of the preset event according to the target-related media content in each media content cluster and the event requirement information of the preset event; Performing a viewpoint analysis on the preset event according to the event viewpoint information to generate viewpoint analysis content of the preset event.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the method for generating an event report according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating an event report according to any one of claims 1 to 8 when executed.

11. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the method for generating an event report according to any one of claims 1 to 8.

Images