Method and apparatus for information processing

Abstract

According to embodiments of this disclosure, a method and apparatus for information processing are provided. The method includes generating a first event graph corresponding to media content, comprising at least a first node representing a first event, a second node representing a second event, and a first directed edge representing a first event relationship between the first and second events, wherein the first event, the second event, and the first event relationship are determined from the media content. The method further includes determining a third event from a reference event graph, based on a first event element possessed by at least one of the first or second events, that has a second event element matching the first event element. The method further includes combining the first event graph with a second event graph, the second event graph including at least a third node representing the third event. In this manner, the efficiency of processing media information can be improved, helping users efficiently obtain information of interest.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods and apparatus for information processing. Background Technology

[0002] With the development of internet and multimedia technologies, the amount of news is growing exponentially every day, and a large amount of it is repetitive. Generally speaking, news events do not occur in isolation. Users may want to understand the ins and outs of an event or to further understand its trajectory by looking at historical events, thereby predicting the potential impact of the current event. For users, the process of searching and filtering information related to events is very cumbersome. Therefore, there is a need for a solution that can automatically sort, refine, and provide insights into various news items. Summary of the Invention

[0003] In a first aspect of this disclosure, an information processing method is provided. The method includes: generating a first event graph corresponding to media content, the first event graph including at least a first node representing a first event, a second node representing a second event, and a first directed edge representing a first event relationship between the first event and the second event, the first event, the second event, and the first event relationship being determined from the media content; determining a third event having second event elements matching the first event elements from a reference event graph based on first event elements possessed by at least one of the first or second events; and combining the first event graph with a second event graph, the second event graph including at least a third node representing the third event.

[0004] In a second aspect of this disclosure, an electronic device is provided. The electronic device includes at least one processing circuit. The at least one processing circuit is configured to: generate a first event graph corresponding to media content, the first event graph including at least a first node representing a first event, a second node representing a second event, and a first directed edge representing a first event relationship between the first event and the second event, the first event, the second event, and the first event relationship being determined from the media content; determine a third event having a second event element matching the first event element from a reference event graph based on a first event element possessed by at least one of the first or second events; and combine the first event graph with a second event graph, the second event graph including at least a third node representing the third event.

[0005] In some embodiments of the second aspect, at least one processing circuit is configured to: determine a fourth event that has a second event relationship with the first event from a reference event graph; add a fourth node representing the fourth event to the first event graph; and add a second directed edge representing the second event relationship between the first node and the fourth node.

[0006] In some embodiments of the second aspect, at least one processing circuit is further configured to store the degree of association of the first event relationship in association with the first directed edge.

[0007] In some embodiments of the second aspect, the second event graph is determined by: determining the number of levels to be expanded for the first event element; and determining a subgraph with a number of levels as the second event graph, starting from the node representing the third event in the reference event graph.

[0008] In some embodiments of the second aspect, the number is specified by user input.

[0009] In some embodiments of the second aspect, at least one processing circuit is further configured to: determine a first similarity between the first event and the fifth event represented by the fifth node in the reference event graph, and a second similarity between the second event and the sixth event represented by the sixth node in the reference event graph; and update the reference event graph based on the first similarity, the second similarity, the first threshold, and the second threshold which is less than the first threshold.

[0010] In some embodiments of the second aspect, at least one processing circuit is further configured to add a directed edge representing a first event relationship between the fifth node and the sixth node in response to a first similarity exceeding a first threshold and a second similarity exceeding the first threshold.

[0011] In some embodiments of the second aspect, at least one processing circuit is further configured to: add a seventh node representing a second event in the reference event graph in response to a first similarity exceeding a first threshold and a second similarity less than a second threshold; and add a directed edge representing a first event relationship between the fifth node and the seventh node.

[0012] In some embodiments of the second aspect, at least one processing circuit is further configured to: add a first event graph to the reference event graph in response to both the first similarity and the second similarity being between the first threshold and the second threshold; and add an indication that the first event is similar to the fifth event and an indication that the second event is similar to the sixth event to the reference event graph.

[0013] In some embodiments of the second aspect, at least one processing circuit is further configured to present a combined first and second logic graph in response to media content being presented or selected.

[0014] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0015] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0016] It should be understood that the content described in this summary section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0017] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0018] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0019] Figure 2 A flowchart illustrating an information processing procedure according to some embodiments of the present disclosure is shown;

[0020] Figure 3 A flowchart illustrating the process of constructing an individual event graph according to some embodiments of this disclosure is shown;

[0021] Figures 4A to 4F A schematic diagram of an example individual matter graph constructed according to some embodiments of the present disclosure is shown;

[0022] Figure 5 A schematic diagram illustrating the association of event elements to individual event graphs according to some embodiments of the present disclosure is shown;

[0023] Figures 6A to 6C Examples of updated reference reasoning diagrams according to some embodiments of this disclosure are shown;

[0024] Figures 7A to 7C Examples of extended individual reasoning graphs according to some embodiments of the present disclosure are shown;

[0025] Figures 8A to 8C Examples of visual representations of media content according to some embodiments of this disclosure are shown;

[0026] Figure 9 A flowchart illustrating an information processing procedure according to some embodiments of the present disclosure is shown; and

[0027] Figure 10 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0028] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0030] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0031] As used herein, the term "circuit" can refer to hardware circuitry and / or a combination of hardware circuitry and software. For example, a circuit can be a combination of analog and / or digital hardware circuitry with software / firmware. As another example, a circuit can be any part of a hardware processor with software, including (multiple) digital signal processors, software, and (multiple) memories, which work together to enable a device to function and perform various functions. In yet another example, a circuit can be hardware circuitry and / or a processor, such as a microprocessor or a portion thereof, which requires software / firmware for operation, but may be absent when not required for operation. As used herein, the term "circuit" also encompasses the implementation of hardware circuitry or a processor alone, or a portion thereof, and its accompanying software and / or firmware.

[0032] As used in this article, the term "event" refers to a change in a thing or state that occurs in a specific time and place and involves one or more actions by one or more event subjects.

[0033] As briefly mentioned earlier, users need to invest a significant amount of time to read news and obtain information, and the process of searching and filtering news is quite cumbersome. On the other hand, with the development of internet and multimedia technologies, news can be presented in various media formats, such as text, images, video, audio, or combinations thereof. This further increases the volume of news. To avoid the massive amount of news consuming users' reading time, it is desirable to be able to organize and refine the news.

[0034] Traditionally, news reports are manually searched, categorized, and organized to provide users with relevant information. This method is extremely costly in terms of manpower. Another approach utilizes information processing technologies such as search and clustering to collect, organize, and sort news by publication time. However, this method struggles to allow users to understand the development of events. It can only display the current event in isolation and cannot automatically link it to matching events (such as those with the same subject or industry), making it difficult to demonstrate the relationships and evolution of events. Furthermore, this method cannot predict the potential impact of events or provide users with references based on the development of similar historical events.

[0035] To this end, embodiments of this disclosure propose a scheme for information processing. The scheme includes generating a first event graph corresponding to media content. The first event graph includes at least a first node representing a first event, a second node representing a second event, and a first directed edge representing a first event relationship between the first and second events, wherein the first event, the second event, and the first event relationship are determined from the media content. The scheme further includes determining a third event from a reference event graph, based on a first event element possessed by at least one of the first or second events, that has a second event element matching the first event element. The scheme further includes combining the first event graph with a second event graph, the second event graph including at least a third node representing the third event.

[0036] In the embodiments of this disclosure, the originally isolated individual event graphs of media content are expanded. Using the expanded event graph, events with the same or similar elements are linked together. Thus, complex events can be organized in a graph-like manner. This improves the efficiency of processing media information and helps users efficiently obtain information of interest. Expanding the related events also allows users to gain deeper insights into the media content and understand the surrounding dynamics of the events described in the media content.

[0037] Example environment and overall process

[0038] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In environment 100, electronic device 120 acquires media content 110 and processes it to generate a physics graph 130.

[0039] In environment 100, electronic device 120 can be any type of computing-capable device, including terminal devices or server devices. Terminal devices can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. Server devices may include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, and so on.

[0040] Media content 110 can be any suitable form of content capable of providing information. For example, media content 110 can be news reports in the form of text, images, audio, video, or a combination thereof. Media content 110 can be media content obtained from various platforms (e.g., news platforms) or stored media content. For text-based media content 110, electronic device 120 can directly extract information from the text for constructing the context graph 130. For media content 110 in the form of images, videos, audio, etc., electronic device 120 can utilize any known or future-developed technology to extract information from the images, audio, or video for constructing the context graph 130. For example, electronic device 120 can directly extract relevant information from image, video, or audio formats based on image recognition or speech recognition technology.

[0041] Event graphs are used to represent events and the relationships between different events. For example, an event graph can use a directed logical graph to represent events and their relationships. Such a directed logical graph uses events as nodes and event relationships as directed edges.

[0042] In this article, the event relationship is also referred to as an association relationship or simply a relationship. Such event relationships can include, but are not limited to, causal relationships, conditional relationships, reversal relationships, sequential relationships, hierarchical relationships, component relationships, concurrent relationships, similarity relationships, and so on. For example, a causal relationship means that the occurrence of a preceding event (cause) leads to the occurrence of a subsequent event (effect). A conditional relationship means that the preceding event is a condition for the occurrence of the subsequent event. A reversal relationship means that one event is opposed to another; for example, although one event occurs later, the other event develops rapidly. A sequential relationship means that the preceding and subsequent events occur successively in time. A hierarchical relationship means that one event is a superior or inferior event of another event, including both nominal and verbal hierarchical relationships. For example, the events "food price increases" and "vegetable price increases" constitute a nominal hierarchical relationship; the events "murder" and "assassination" are verbal hierarchical relationships. A component relationship means that one event is a component of another event. A concurrent relationship means that one event occurs simultaneously with another event. A similarity relationship refers to the fact that one event is similar to another event to a certain extent. For example, a similarity relationship can be established through similarity calculation. The above event relationships are merely exemplary and are not intended to limit the scope of this disclosure.

[0043] An event can have one or more event elements. In this document, event elements are also referred to simply as elements. Event elements can include, but are not limited to, event subject, event object, time, location, people, industry, company, product, and so on. In some embodiments, event elements can be stored as attributes of the event and associated with the nodes representing the event.

[0044] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. Although Figure 1 Only one electronic device 120 is shown herein, but in some embodiments, multiple electronic devices may perform the various operations described herein. For example, a server device may collect media content 110 and generate a context graph 130, which is then presented by a terminal device. Alternatively, a backend device may build, update, or expand the context graph 130, which is then presented by a foreground device.

[0045] refer to Figure 2The following describes an example process 200 of information processing implemented to generate a context graph 130. Process 200 can be implemented in environment 100. To construct the context graph 130, electronic device 120 first generates a context graph corresponding to media content 110, also referred to as an individual context graph. For this purpose, in box 210, electronic device 120 constructs an individual context graph of the media content. The individual context graph is used to represent events extracted from a single piece of media content 110 and the relationships between these events. Therefore, the individual context graph includes multiple nodes, each representing a different event extracted from the media content 110. The individual context graph also includes at least one directed edge, representing the event relationship between different events.

[0046] Further, in box 230, the electronic device 120 expands the individual event graph corresponding to the media content 110 to obtain event graph 130. In this document, expanding the individual event graph means combining it with one or more additional event graphs (also called supplementary event graphs). Supplementary event graphs may include one or more nodes, each node representing an event. Therefore, in this document, the expanded individual event graph may also be referred to as a combined event graph.

[0047] The event source used to extend an individual event graph can be a reference event graph. For example, electronic device 120 can determine a subgraph from the reference event graph that satisfies the extension conditions and combine that subgraph with the individual event graph. It should be understood that an individual event graph can be a graph for a specific number (e.g., one) of media content, while a reference event graph is a graph for a wider range of media content and can be considered a global event graph. In some embodiments, the reference event graph can be constructed for a specific domain, such as the financial domain or the semiconductor domain. Alternatively, the reference event graph can be constructed across multiple domains or can be domain-free.

[0048] The electronic device 120 can expand the individual reasoning graph based on any suitable factors. In some embodiments, the electronic device 120 can expand the individual reasoning graph based on event elements. Alternatively, in some embodiments, the electronic device 120 can expand the individual reasoning graph based on event relationships. In some embodiments, the electronic device 120 can expand the individual reasoning graph based on both event elements and event relationships.

[0049] Additionally, in some embodiments, process 200 can also be used to present a reasoning graph. Specifically, at block 240, electronic device 120 can present an expanded individual reasoning graph. In some embodiments, electronic device 120 can be a server device. In this embodiment, the expanded individual reasoning graph can be presented by a terminal device communicating with electronic device 120.

[0050] Additionally, in some embodiments, process 200 can also be used to update the reference event graph. Specifically, at block 220, electronic device 120 uses the individual event graph to update the reference event graph. Electronic device 120 can also store and periodically update the reference event graph to provide matching event sources when expanding the individual event graph.

[0051] The above is for reference only. Figure 2 The overall flow of an example process 200 that can be implemented in environment 100 is described below. Example implementations of the various blocks within process 200 will then be described with reference to the accompanying drawings.

[0052] Example process of constructing individual reasoning graphs

[0053] As mentioned above, in box 210, electronic device 120 constructs an individual event graph of media content 110. For example, an event graph can be constructed for a news report.

[0054] Figure 3 A flowchart of a process 300 for constructing an individual event graph according to some embodiments of the present disclosure is shown. Process 300 can be considered as an example implementation of block 210. References are as follows. Figure 1 Describe the process 300.

[0055] In box 310, electronic device 120 collects media content. Media content may include, for example, current affairs news, social news, and popular science information. Taking news as an example of media content 110, electronic device 120 can collect news periodically through interfaces provided by websites based on a list of news websites. The list of news websites may include, for example, mainstream news platforms, industry-specific news platforms, policy release platforms, knowledge-sharing platforms, etc. The list of news websites can also be specified by the user.

[0056] In box 320, electronic device 120 performs deduplication processing on the collected media content. The media content can be, for example, current events news; taking the collection of news from a list of news websites as an example, different news websites may reference and reprint each other's news, potentially resulting in duplicate news items. Electronic device 120 can filter the collected news based on a deduplication algorithm.

[0057] In some embodiments, the electronic device 120 may employ the Simhash algorithm to deduplicatize the acquired media content. The deduplication process may include steps such as word segmentation, hash value calculation, weighting, merging, dimensionality reduction, and deduplication. Specifically, the electronic device 120 may segment the text in the media content or the text identified or converted from the media content to obtain effective feature vectors, and then assign weights to each feature vector. The electronic device 120 may calculate the hash value of each feature vector using a hash function and assign weights to each feature vector. The electronic device 120 may then weight the feature vectors based on their hash values. Further, the electronic device 120 may accumulate the weighted results of each feature vector to obtain a sequence string. The electronic device 120 judges each digit of this sequence string. For digits greater than 0, it sets them to 1; for digits less than 0, it sets them to 0. In this way, the electronic device 120 obtains the Simhash value corresponding to the media content. Finally, the electronic device 120 calculates the hash distance between any two media contents based on the Simhash value of each media content. If the hash distance is less than a preset threshold, the two media contents are considered duplicates. Electronic device 120 can remove one of the media contents to achieve deduplication.

[0058] It should be understood that the Simhash algorithm is merely an example. In the embodiments of this disclosure, any suitable algorithm can be used to achieve deduplication.

[0059] In box 330, electronic device 120 extracts events and event relationships. Box 330 can be executed for any deduplicated media content or for each piece of media content. Electronic device 120 can automatically extract events and event relationships from the deduplicated media content based on an event extraction algorithm. One or more events can be extracted from a single piece of media content. It is also possible that no events can be extracted from a particular piece of media content. Event relationships may include those mentioned above. Figure 1 The described event relationships. For example, in a news article about "enriching feed sources to address the problem of increased farming costs due to rising feed prices," electronic device 120 can extract the first event "rising feed prices," the second event "increased farming costs," and the causal relationship between the two.

[0060] Additionally, in some embodiments, the electronic device 120 may also determine the degree of association of event relationships, also referred to herein as the association coefficient. The degree of association may indicate the strength of the event relationship, the probability of event transition, or the reliability of the event relationship, etc. In some embodiments, the electronic device 120 may store the degree of association of the event relationship represented by a directed edge in association with a directed edge.

[0061] In box 330, any suitable event extraction algorithm can be used to extract events and event relationships. Examples of event extraction algorithms may include, but are not limited to, classification-based event extraction methods, sequence labeling-based event extraction methods, reading comprehension-based event extraction methods, generative event extraction methods, and so on. The scope of this disclosure is not limited in this respect.

[0062] As an example, electronic device 120 can utilize a sequence labeling-based event extraction algorithm to extract events and event relationships. Continuing with the news text example, electronic device 120 can preprocess the deduplicated news text, such as filtering redundant spaces and garbled characters, performing text segmentation, and replacing interfering strings, etc. Electronic device 120 can identify the start and end positions of events in the preprocessed news text by training a continuous event character sequence model to obtain descriptive fragments of the events, i.e., event names. Event names typically include event trigger words, which specify the event type. Furthermore, electronic device 120 can determine the event relationships between events based on the event trigger words, and then calculate the degree of correlation between events.

[0063] In box 340, electronic device 120 extracts event elements. Electronic device 120 can extract the event elements possessed by an event. Event elements may include, but are not limited to, the event subject, the event object, time, location, people, industry, company, and product. Depending on the information content of the media content, each event may have one or more event elements, or none at all. For example, extracting the event "Increased Livestock Costs" and its corresponding event elements from a news text. The event elements for "Increased Livestock Costs" may include the time element "April 1, 2022," the industry element "Livestock Industry," and the location element "XX County."

[0064] In box 350, electronic device 120 generates an individual event graph. Specifically, electronic device 120 generates an individual event graph based on the events and event relationships extracted in box 330. Continuing with the example of the aquaculture industry above, the generated individual event graph may include a node representing the first event "increased feed prices", a node representing the second event "increased farming costs", and a directed edge connecting these two nodes to represent the causal relationship between the two events. In this example, the directed edge points from the node representing the first event "increased feed prices" to the node representing the second event "increased farming costs".

[0065] Depending on the specific media content, the constructed individual reasoning graphs can have different structures. Figures 4A to 4F A schematic diagram of an example individual reasoning graph constructed according to some embodiments of the present disclosure is shown. Figure 4AExample individual event graph 400A represents the two extracted events and their corresponding event relationships. Figure 4B Example individual event graph 400B represents the six extracted events and their corresponding relationships. These events are pairwise related but isolated from each other. Figure 4C Example Individual Logic Graph 400C and Figure 4D The example individual event graph 400D represents the four extracted events and their corresponding relationships. Each event is associated with the other three events. Figure 4E Example Individual Logic Graph 400E and Figure 4F The example individual event graph 400F represents five extracted events and their corresponding relationships. Each event has one to three relationships with other events. In the example above, circles filled with diagonal lines are used as nodes to represent events in the individual event graph; solid arrows are used as directed edges to represent relationships between events. The style of the arrows can indicate the type of relationship, such as hierarchical relationships, causal relationships, etc.

[0066] In box 360, electronic device 120 associates event elements with corresponding events in the individual event graph. For example, the event elements of an event can be stored as attributes of the event and associated with the node representing the event. Figure 5 A schematic diagram illustrating the association of event elements to individual event graphs according to some embodiments of the present disclosure is shown. Figure 5 In the example, electronic device 120 extracts event A represented by node 501, event B represented by node 502, the event relationship between event A and event B, and the event elements corresponding to each event from media content 110. Specifically, electronic device 120 extracts event elements 1, 2, and 3 corresponding to event A, and event elements 4, 5, and 6 corresponding to event B. Accordingly, event elements 1, 2, and 3 are associated with node 501 representing event A, while event elements 4, 5, and 6 are associated with node 502 representing event B.

[0067] The above-described process 300 describes an example process for constructing an individual event graph. However, it should be understood that this is merely exemplary, and individual event graphs can be constructed in any suitable manner within the embodiments of this disclosure. Furthermore, the events, event relationships, number of events, event elements, and graph styles described in process 300 are merely exemplary and are not intended to limit the scope of this disclosure.

[0068] Example of updating the reference principle graph

[0069] As referenced above Figure 2As described, in some embodiments, at block 220, electronic device 120 can utilize individual event graphs to update a reference event graph. In this document, updating the reference event graph can also be referred to as fusing the individual event graph with the reference event graph. Fusion can refer to merging one or more nodes in the individual event graph with one or more nodes in the reference event graph, or adding the individual event graph itself to the reference event graph as part of it. Specific operations are merely exemplary and are not intended to limit the scope of this disclosure. Therefore, relative to the reference event graph or the global event graph, the individual event graph can be considered a subgraph of the event graph.

[0070] Reference event graphs can be, for example, fused event graphs generated from a large amount of media content for a specific industry, field, or website. Reference event graphs can describe the relationships between various events from a global perspective. The following describes an example of updating a reference event graph.

[0071] In some embodiments, in order to fuse an individual event graph with a reference event graph, the electronic device 120 can calculate the similarity between events in the individual event graph and events in the reference event graph. Then, the individual event graph and the reference event graph can be fused based on the similarity. The electronic device 120 can calculate the similarity between events based on event names, event elements, etc.

[0072] As an example, electronic device 120 can determine the similarity between events based on Jaccard similarity. Continuing... Figure 5 For example, electronic device 120 compares event A in an individual event graph with another event in a reference event graph. It segments the name and elements of event A to obtain a first set of segmented words for event A. Electronic device 120 then segments the name and elements of the event to be compared in the reference event graph to obtain a second set of segmented words. Based on the first and second set of segmented words, electronic device 120 determines the number of words in the intersection and the number of words in the union of these two sets. Furthermore, electronic device 120 calculates the ratio of the number of words in the intersection to the number of words in the union, obtaining a Jaccard similarity. Based on the Jaccard similarity, electronic device 120 merges the individual event graph and the reference event graph.

[0073] Electronic device 120 can fuse individual event graphs and reference event graphs based on the relationship between similarity and one or more preset thresholds. In some embodiments, two thresholds can be preset, namely a first threshold and a second threshold, with the first threshold being greater than the second threshold. If the similarity between two compared events is greater than the first threshold, the two events can be considered the same event. Accordingly, electronic device 120 can merge nodes in the individual event graph with corresponding nodes in the reference event graph without adding new nodes to the reference event graph. If the similarity between two events is less than the second threshold, the two events can be considered independent events. Accordingly, electronic device 120 adds nodes from the individual event graph to the reference event graph to achieve graph fusion. If the similarity between two events is between the first and second thresholds, the two events can be considered similar events. Accordingly, electronic device 120 can add nodes from the individual event graph to the reference event graph and establish indications of similarity relationships for similar events (e.g., represented by directed edges of different styles).

[0074] Figures 6A to 6C Examples of updated reference causal diagrams according to some embodiments of this disclosure are shown. Combined with Figure 5 To describe Figures 6A to 6C Examples.

[0075] exist Figure 6A In the example, the individual event graph includes node 501 representing event A and node 502 representing event B. Electronic device 120 performs a traversal calculation of the similarity between event A and event B and the events represented by each node in the reference event graph (dashed arrows in the figure indicate similarity calculations between two events, but not all dashed arrows are shown in the traversal calculation). The similarity between event A and the event represented by node 601 in the reference event graph is greater than a first threshold (e.g., 0.9). Electronic device 120 merges node 501 and node 601. The similarity between event B and the event represented by node 602 in the reference event graph is also greater than the first threshold (e.g., 0.9). Electronic device 120 merges node 502 and node 602. To preserve the original relationship between event A and event B, a directed edge 611 from node 601 to node 602 is added to the reference event graph. As shown in the figure, after fusion, no new nodes are added to the reference event graph; instead, a directed edge is added between event A and event B.

[0076] exist Figure 6BIn the example, electronic device 120 performs a traversal calculation of the similarity between events A and B in the individual event graph and each event in the reference event graph (only the dashed arrows of the traversal calculation are shown in the figure). The similarity between event A and the event represented by node 601 in the reference event graph is greater than a first threshold (e.g., 0.9). Electronic device 120 merges node 501 with node 601. The similarity between event B and the events represented by each node in the reference event graph is less than a second threshold (e.g., 0.6). Electronic device 120 adds node 604 representing event B to the reference event graph. Accordingly, in order to preserve the original relationship between event A and event B, a directed edge 612 from node 601 to node 604 is added to the reference event graph. After merging, a new node is added to the reference event graph, and a directed edge between event A and event B is added.

[0077] exist Figure 6C In the example, electronic device 120 performs a traversal calculation of the similarity between events A and B in the individual event graph and each event in the reference event graph (only the dashed arrows of the traversal calculation are shown in the figure). The similarity between event A and the event represented by node 601 in the reference event graph is between a first threshold and a second threshold. Accordingly, electronic device 120 adds node 501 to the reference event graph and adds a directed edge 613 (which is a bidirectional edge) between node 501 and node 601 to indicate that event A has a similarity relationship with the event represented by node 601. The similarity between event B and the event represented by node 602 in the reference event graph is also between the first threshold and the second threshold. Accordingly, electronic device 120 adds node 502 to the reference event graph and adds a directed edge 614 (which is a bidirectional edge) between node 502 and node 602 to indicate that event B has a similarity relationship with the event represented by node 602. After merging, new nodes were added to the reference event graph, and similarity indicators were established between event A and similar events, as well as between event B and similar events.

[0078] The update process of the reference event graph described above can be viewed as an incremental construction of the reference event graph. This incremental construction can be used for the initial creation of the reference event graph, or for incrementally updating an already created reference event graph. By continuously integrating newly added individual event graphs into the reference event graph, the reference event graph is continuously updated. In this way, a rich and comprehensive event chain and event relationship network can be formed.

[0079] Examples of expanding individual reasoning maps

[0080] As referenced above Figure 2As described, in box 230, electronic device 120 expands the individual reasoning graph. Specifically, one or more subgraphs can be determined from the reference reasoning graph as one or more additional reasoning graphs based on the factors considered in the expansion. Furthermore, the one or more additional reasoning graphs can be combined with the individual reasoning graph to generate the expanded individual reasoning graph.

[0081] In some embodiments, the individual event graph can be expanded based on event elements. To help users obtain richer information, events with matching event elements can be found in the reference event graph based on the event elements corresponding to the event, and the individual event graph can be expanded based on the event.

[0082] Specifically, for a specific event element possessed by an event included in an individual event graph, events with matching event elements can be found in a reference event graph; these are also called matched events. In this paper, matching two event elements can mean that the two event elements are the same or similar. Similarity can mean that the difference between the two event elements is less than a threshold difference. For example, for the time element, if the difference between two specific time values ​​is less than a threshold difference, the two time elements can be considered matched. Matching two event elements can also mean that the two event elements have corresponding characteristics. For example, for the product element, the commonly used "plug" and "socket" can have matching product elements. Continuing with the example of the aquaculture industry, the event element corresponding to the event "increased aquaculture costs" includes the industry element "aquaculture industry". Electronic device 120 can determine the event "large-scale aquaculture" with the industry element "aquaculture industry" from the reference event graph based on the industry element "aquaculture industry" and use it as a matched event.

[0083] After identifying the matching events, an additional event graph can be determined based on the matching events, and then combined with the individual event graphs. This expands the individual event graphs. The combination of the additional event graphs and the individual event graphs can be achieved through matching event elements.

[0084] Additional event graphs can have any suitable number of levels. For example, nodes representing matching events can be added to the individual event graph as additional event graphs. That is, in this case, a one-level expansion is performed.

[0085] In some embodiments, the electronic device 120 can determine the number of levels to be expanded. The number of levels to be expanded may be predetermined or may be specified by user input. Then, starting from the nodes representing matching events in the reference event graph, a subgraph with that number of levels can be determined. This subgraph is combined with the individual event graph as an additional event graph. For example, when the number of levels to be expanded is 2, the electronic device 120 can determine the nodes representing matching events and the nodes directly connected to those nodes (if any) as an additional event graph from the reference event graph.

[0086] Based on individual event graphs and expanded upon event elements, related events with identical, similar, or corresponding elements and their evolutionary rules can be identified. This approach provides users with richer information. By analyzing matching events with the same subject or from the same industry, the causes, development, or impacts of the first and / or second events can be determined.

[0087] Figure 7A An individual event graph 700A based on event elements, according to some embodiments of this disclosure, is shown. Combined with... Figure 5 To describe Figure 7A An example. An individual event graph includes event A and event B. See reference... Figure 5 As described, event B has event element 5.

[0088] exist Figure 7A In the example, electronic device 120 expands the individual event graph based on event element 5. Electronic device 120 finds expanded events 1 and 2 in the reference event graph that have event elements matching event element 5. Therefore, at least node 701 representing expanded event 1 and node 702 representing expanded event 2 are added to the individual event graph. Additionally or alternatively, electronic device 120 may expand the individual event graph based on a pre-set or user-set expansion level. For example, if two levels of expanded events are set, electronic device 120 finds expanded event 3 that is associated with expanded event 1. Therefore, a subgraph including node 701 and node 703 representing expanded event 3 is added to the individual event graph and associated with event B via event element 5. Furthermore, electronic device 120 also finds expanded event 4 that is associated with expanded event 2. Thus, a subgraph including node 702 and node 704 representing extended event 4 is added to the individual event graph and associated with event B via event element 5.

[0089] As an example without any intention of limitation, event A could be "rising feed prices," and event B could be "increased breeding costs." Event element 5 of event B could be the industry element "livestock farming." Then, extended event 1 "losses in pig farming" and extended event 2 "large-scale farming" can be found. Furthermore, electronic device 120 finds extended event 3 "significant decline in profits," which is related to extended event 1, and extended event 4 "high industrialization conversion rate," which is related to extended event 2. In this example, the industry element "livestock farming" has been expanded to facilitate users in obtaining relevant events within the same industry, thereby understanding the recent dynamics of that industry.

[0090] Alternatively or additionally, in some embodiments, the electronic device 120 can expand the individual event graph based on event relationships. Specifically, for a specific event represented by a node in the individual event graph, events with event relationships to that event can be searched in a reference event graph. Then, expansion can be performed at a certain number of levels based on the found events. In this way, it can help the user understand the ins and outs of events. The event relationships used herein include, but are not limited to, reference events. Figure 1 Those described.

[0091] Figure 7B An individual event graph 700B, based on event relationships and extended according to some embodiments of this disclosure, is shown. Combined with... Figure 5 To describe Figure 7B An example. An individual event graph includes event A and event B.

[0092] exist Figure 7BIn the example, electronic device 120 finds extended event 5, which has a hierarchical relationship with event A, in the reference event graph. Accordingly, nodes representing extended event 5 and directed edges representing the hierarchical relationship between event A and extended event 5 can be added to the individual event graph for expansion. For example, event A could be "feed price increase," and extended event 5 could be "food price increase." Extended events 6 and 7, which have a hierarchical relationship with event A, are also found in the reference event graph, such as "chicken feed price increase" and "pig feed price increase," respectively. Accordingly, nodes representing extended event 6 and directed edges representing the hierarchical relationship between event A and extended event 6 can be added to the individual event graph for expansion. Furthermore, nodes representing extended event 7 and directed edges representing the hierarchical relationship between event A and extended event 7 can be added to the individual event graph for expansion. Electronic device 120 finds extended event 8, which has a causal relationship with event B, in the reference event graph, such as "revenue decrease." Accordingly, nodes representing extended event 8 and directed edges representing the causal relationship between event B and extended event 8 can be added to the individual event graph for expansion.

[0093] In some embodiments, the electronic device 120 may expand the individual event graph based on event relationships and event elements. Figure 7C An individual event graph 700C, extended based on event relationships and event elements according to some embodiments of the present disclosure, is shown. Event graph 700C can be viewed as a superposition of event graphs 700A and 700B. Specifically, the extended individual event graph includes nodes representing extended events 1 to 4 obtained based on event elements, and nodes representing extended events 5 to 8 obtained based on event relationships.

[0094] The above is for reference only. Figures 7A to 7C Examples of extensions are described. It should be understood that the number of nodes, relationships between events, and the style of the event graphs shown in these diagrams are merely exemplary and are not intended to limit the scope of this disclosure. Furthermore, the basis for extension based on which event elements(s) may be default or user-selected. Alternatively or additionally, the basis for extension based on which event relationships(s) may be default or user-selected.

[0095] Examples of extended individual reasoning maps

[0096] As briefly mentioned above, when a user browses media content 110, a logic graph related to media content 110 can be displayed. See below for reference. Figures 8A to 8CTo illustrate some examples, the following description of the presentation of the event graph is provided with respect to electronic device 120 for illustrative purposes only, but is merely exemplary. The presentation of the event graph can be performed by any suitable device, such as other devices communicating with electronic device 120.

[0097] exist Figure 8A In the example, when a user browses media content 110, electronic device 120 presents a visualization 800A. The visualization 800A includes an individual event graph 810 corresponding to the media content 110. The individual event graph 810 includes multiple nodes, in this example nodes 801, 802, 803, and 804. These nodes are visually represented as circles filled with diagonal lines. Each node represents an event extracted from the media content 110; for example, node 801 represents event C, node 802 represents event D, node 803 represents event E, and node 804 represents event F.

[0098] The individual event graph 810 also includes at least one directed edge, which in this example are directed edge 811, directed edge 812, and directed edge 813. These directed edges are visually represented as solid lines with arrows. Each directed edge represents an event relationship; for example, directed edge 811 represents the event relationship between event C and event D, directed edge 812 represents the event relationship between event D and event E, and directed edge 813 represents the event relationship between event D and event F.

[0099] For reference Figure 1 As described, an event may have one or more event elements. In some embodiments, the electronic device 120 may further present multiple interface elements representing multiple event elements, each event element belonging to an event in the individual event graph 810. For example, in Figure 8A In the example, event C has time, people, and location elements. Accordingly, associated with node 801, a time interface element representing the event element, a people interface element representing the people element, and a location interface element representing the location element are displayed. As another example, event D has time and product elements. Accordingly, associated with node 802, a time interface element representing the time element and a product interface element representing the product element are displayed.

[0100] In embodiments of this disclosure, interface elements representing event elements can have any suitable form or effect. Figure 8AIn the accompanying drawings, the interface elements representing event elements have visual effects corresponding to the event elements they represent. For example, the person interface element is a person icon, the location interface element is a location icon, and the product interface element is an icon of a specific product. In this way, users can visually and intuitively understand how different events are related to each other through what type of elements. However, it should be understood that this is only exemplary, and interface elements can be presented in other ways. In some embodiments, interface elements can be presented as nodes (e.g., similar to nodes representing events, and may have the same or different shapes) and / or text. For example, the interface element representing a person element can be presented as a node with a certain shape (such as a circle), and the node is identified with information such as the person's name.

[0101] The above describes an example presentation of the individual event graph 810 and its corresponding event elements. Please refer to the above text for further information. Figure 3 The individual event map 810 and event elements are obtained in the manner described.

[0102] In addition to the individual event graph, the electronic device 120 also presents one or more additional event graphs based on event elements. (Continue) Figure 8A For example, the visualization 800A also includes supplementary event graphs 820, 830, and 840. These supplementary event graphs supplement the individual event graph 810, helping users clarify the cause and effect of events or understand related event information. As an example, supplementary event graph 820 includes node 805, which has a hollow circle visual style. The event represented by node 805 has a matching event element with event C represented by node 801, which is a time element in this example. The visualization 800A includes a corresponding interface element, which is a time interface element 809 in this example. The time interface element 809 has a clock icon visual style.

[0103] In some embodiments, the additional event graph, extended based on event elements, can have multiple levels. That is, the additional event graph can include multiple nodes. Figure 8A In the example, the additional event graph 820 also includes node 806, which represents an event that has an event relationship with the event represented by node 805. This event relationship is represented by directed edges, which are visually represented as solid lines with arrows. Additional event graphs 830 and 840 are similar to additional event graph 820, so their descriptions will not be repeated.

[0104] In some embodiments, the electronic device 120 may also present directed elements pointing from interface elements to nodes to indicate that the event represented by the node has the event element represented by the interface element. Specifically, for two events with matching event elements, the nodes representing the two events can be visually associated through interface elements representing the matching event elements. Figure 8A In the example, the visualization 800A also includes directed elements between interface elements and nodes. For instance, the events represented by nodes 801 and 805 have matching event elements. Accordingly, a directed element 814 is presented pointing from the time interface element 809 to node 801, and a directed element 815 is presented pointing from the time interface element 809 to node 805. These directed elements are visually styled as dashed lines with arrows.

[0105] It should be understood that the above descriptions of the visual styles of the elements in the visualization presentation 800A, and the descriptions of the visual relationships between individual and supplementary reasoning graphs, are merely exemplary and are not intended to limit the scope of this disclosure. The electronic device 120 can present elements in these graphs using various visual styles, such as using nodes with different patterns to represent events in different graphs, using the length, thickness, line type, or arrow direction of directed edges to represent the types of event relationships, and using interface elements with different icons to represent the types of event elements. The electronic device 120 can present the visual relationships between individual and supplementary reasoning graphs using different layout methods. For example, the electronic device 120 can center on the time interface element 809, presenting the individual reasoning graph 810 and the supplementary reasoning graph 820 on both sides. As another example, the electronic device 120 can center on the time interface element 809, presenting the elements in the individual reasoning graph 810 and the elements in the supplementary reasoning graph 820 around it.

[0106] Additional event logic diagrams 820, 830, and 840 are extensions based on event elements. For details on how to extend individual event logic diagrams based on event elements, please refer to the above section. Figures 7A to 7C The description.

[0107] Further examples of the presented event graphs are described below. In some embodiments, the electronic device 120 may also present one or more additional event graphs based on event relationships. References Figure 8BThe visualization 800B is shown. Visualization 800B differs from visualization 800A in that it includes additional event graphs. Each of these additional event graphs represents at least one event that has an event relationship with an event in the individual event graph 810. For example, visualization 800B includes an additional event graph 850 extending from node 801. Additional event graph 850 includes node 807. The event represented by node 807 has an event relationship with the event represented by node 801, as shown in the reference above. Figure 1 The relationships described. Additionally or alternatively, the visualization 800B may also include directed edges 816 representing the relationship of the event.

[0108] In some embodiments, the additional event graph extended based on event relationships can have multiple levels. That is, the additional event graph can include multiple nodes. For example, the additional event graph 850 also includes node 808. The event represented by node 808 has an event relationship with the event represented by node 807, such as a causal relationship.

[0109] In some embodiments, in addition to individual event graphs and extended supplementary event graphs, the electronic device 120 may also explicitly or implicitly present additional information about these event graphs, such as the degree of correlation between events. (See reference) Figure 8C Example. Visualization 800C differs from Visualization 800B in that it also includes an indication of the degree of association corresponding to the event relationship. In this example, these degree of association indicators are presented numerically. For example, the degree of association between the event represented by node 805 and the event represented by node 806 is 0.81. This degree of association value is labeled on the directed edge 817 between the two nodes. Figure 8C The document also shows the degree of correlation between other events, which will not be described in detail here.

[0110] exist Figure 8C In the example, electronic device 120 explicitly presents the degree of association numerically. However, this is merely exemplary. Alternatively or additionally, in some embodiments, the degree of association may be implicitly presented. The visual style of the presented directed edge may correspond to the degree of association of the event relationship represented by that directed edge. For example, the thickness of the directed edge may depend on the degree of association of the event relationship it represents.

[0111] In this embodiment, by explicitly or implicitly presenting the degree of correlation to the user, more information can be provided. Such information is more helpful in assisting the user to judge the possible course of events and / or possible causes, etc.

[0112] The above reference Figures 8A to 8CExamples of visual presentations of media content are described. One or more settings for the visualization may be default or pre-defined. Alternatively or additionally, in some embodiments, one or more settings for the visualization may be determined through user interaction. That is, users can customize the visualization of media content according to their own needs. Some such examples are described below.

[0113] In some embodiments, the number of additional logic graph levels presented can be specified by the user. Accordingly, the electronic device 120 can present a corresponding number of levels based on the number of additional logic graph levels specified by the user input. Figure 8A For example, if the specified number of levels is 2, the supplementary event graph 820 presents two levels of events. For instance, the supplementary event graph 820 includes nodes 805 representing first-level events and nodes 806 representing second-level events. If the specified number of levels is 1, the supplementary event graph 820 presents only one level of events. For instance, the supplementary event graph 820 includes only nodes 805 representing first-level events. In this way, related events can be filtered, helping users focus on events of interest or most relevant to them.

[0114] In some embodiments, the conditions or factors for expanding an individual event graph can be user-specified. Accordingly, the electronic device 120 can present additional event graphs that meet the conditions or factors specified by the user. As an example, the user can specify which event elements(s) to expand the individual event graph. For instance, if the user specifies expansion based on a time element without considering other event elements, the electronic device 120 can present additional event graph 820, but not additional event graphs 830 and 840. This helps users quickly find events of interest or concern.

[0115] In some embodiments, the presentation of additional event graphs is in response to a user's selection of event elements. Specifically, electronic device 120 may receive a user's selection representing an event element and accordingly present additional event graphs expanded based on that event element. For example, by default, electronic device 120 initially presents only the individual event graph 810 and interface elements representing event elements. If the user selects a time interface element, electronic device 120 further presents additional event graph 820. Additional event graph 820 is obtained by expanding the individual event graph 810 based on the time element. If the user continues to select an industry interface element, electronic device 120 presents additional event graph 840. In this way, it helps the user selectively view events of interest.

[0116] In some embodiments, the presentation of additional event graphs is in response to a user's selection of an event. Specifically, electronic device 120 may receive a user's selection of a node and accordingly present additional event graphs extending from that node. For example, electronic device 120 presents one or more of the following: an individual event graph 810, interface elements representing event elements, and additional event graphs 820 to 840 extending based on the event elements. If the user selects node 801, electronic device 120 presents additional event graph 850 (see [link to relevant documentation]). Figure 8B The additional event graph 850 is an extension of the individual event graph 810 based on event relationships. In this way, users can selectively view events of interest.

[0117] In some embodiments, the electronic device 120 may present an indication of the degree of association based on the user's selection of directed edges. For example, the electronic device 120 initially presents an individual event graph, interface elements representing event elements, and one or more additional event graphs. If the user selects directed edge 817, the electronic device 120 presents an indication of the degree of association of the event relationship represented by directed edge 817, i.e., a value of 0.81.

[0118] It should be understood that Figures 8A to 8C The presentation styles shown are merely exemplary and are not intended to limit the scope of this disclosure. In embodiments of this disclosure, media content can be visualized in any suitable style.

[0119] Depend on Figures 8A to 8C It is evident that the visual presentations 800A to 800C presented to users by electronic devices 120 include different amounts of information, but all are intuitive and concise, which can improve the efficiency of users in obtaining media information.

[0120] In summary, according to the various embodiments of this disclosure, the electronic device 120 can automatically extract events, event relationships, and event elements contained in all media content 110 within a specified range to establish a reference event graph. The electronic device 120 can also automatically extract events, event relationships, and event elements contained in specific media content 110 to construct an individual event graph. The electronic device 120 can also merge the individual event graph with the reference event graph to achieve dynamic updates to the reference event graph and facilitate the expansion of the individual event graph. Furthermore, the electronic device 120 can match events from the reference event graph based on event elements and / or event relationships to expand the individual event graph. In this way, users can efficiently obtain intuitive and concise media information using event graphs, and also gain deeper insights into events, analyze the causes of events, and predict the subsequent impact of events.

[0121] Example process

[0122] Figure 9 A flowchart of an information processing procedure 900 according to some embodiments of the present disclosure is shown. Procedure 900 may be implemented at an electronic device 120. For ease of discussion, reference is made to... Figure 1 To describe process 900.

[0123] In box 910, electronic device 120 presents a first event graph corresponding to the media content. The first event graph includes at least a first node representing a first event, a second node representing a second event, and a first directed edge representing the first event relationship between the first event and the second event. The first event, the second event, and the first event relationship are determined from the media content.

[0124] In box 920, electronic device 120 presents a second event graph in association with a first event graph, the second event graph including at least a third node representing a third event, wherein a first event element of at least one of the first or second events matches a second event element of the third event.

[0125] In some embodiments, in order to present a second logic graph in association with a first logic graph, the electronic device 120 visually associates the second logic graph with the first logic graph through interface elements representing first event elements.

[0126] In some embodiments, in order to visually associate the second event graph with the first event graph, the electronic device 120 presents a first directed element that points from an interface element to a node in the first event graph that represents at least one event; and presents a second directed element that points from an interface element to a third node.

[0127] In some embodiments, process 900 further includes: electronic device 120 presenting a plurality of interface elements representing a plurality of event elements, each event element belonging to at least one of a first event or a second event, and the plurality of event elements including the first event element.

[0128] In some embodiments, process 900 further includes: electronic device 120 receiving selection of an interface element from a plurality of interface elements, wherein presenting a second event graph in association with a first event graph is in response to the selection of an interface element representing a first event element.

[0129] In some embodiments, process 900 further includes: electronic device 120 presenting a fourth node representing a fourth event, the fourth event having a second event relationship with the first event; and presenting a second directed edge representing the second event relationship between the first node and the fourth node.

[0130] In some embodiments, process 900 further includes at least one of the following: electronic device 120 presents an indication of the degree of association of the first event relationship, or presents the first directed edge in a visual style corresponding to the degree of association.

[0131] In some embodiments, process 900 further includes: electronic device 120 receiving user input, the user input specifying the number of levels to be expanded for a first event element, and wherein the presented second event graph has the specified number of levels.

[0132] In some embodiments, the second event graph is determined by the electronic device 120 determining a subgraph with a number of levels as the second event graph, starting from the node representing the third event in the reference event graph.

[0133] In some embodiments, the third node has a different visual effect than the first and second nodes.

[0134] Example device

[0135] Figure 10 A block diagram is shown illustrating an electronic device 1000 in which one or more embodiments of the present disclosure may be implemented. It should be understood that... Figure 10 The electronic device 1000 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 10 The electronic device 1000 shown can be used to achieve Figure 1 120 electronic devices.

[0136] like Figure 10 As shown, electronic device 1000 is in the form of a general-purpose electronic device. Components of electronic device 1000 may include, but are not limited to, one or more processors or processing units 1010, memory 1020, storage device 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 1060. Processing unit 1010 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1020. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 1000.

[0137] Electronic device 1000 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 1020 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 1030 can be a removable or non-removable medium and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data (e.g., training data for training) and can be accessed within electronic device 1000.

[0138] Electronic device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 10 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 1020 may include computer program product 1025 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0139] The communication unit 1040 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 1000 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 1000 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0140] Input device 1050 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1060 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 1000 can also communicate with one or more external devices (not shown) via communication unit 1040 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 1000, or with any device that enables electronic device 1000 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0141] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0142] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0143] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0144] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0145] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0146] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: Generate a first event graph corresponding to the media content. The first event graph includes at least a first node representing a first event, a second node representing a second event, and a first directed edge representing a first event relationship between the first event and the second event. The first event, the second event, and the first event relationship are determined from the media content. Based on the first event element possessed by at least one of the first event or the second event, a third event with a second event element matching the first event element is determined from the reference event graph; Determine the number of levels to be expanded for the first event element; Starting from the node representing the third event in the reference event graph, a subgraph with the specified number of levels is determined as the second event graph; as well as The first event graph is combined with the second event graph, wherein the second event graph includes at least a third node representing the third event.

2. The method according to claim 1, further comprising: Determine a fourth event from the reference event graph that has a second event relationship with the first event; Add a fourth node representing the fourth event to the first event graph; as well as Add a second directed edge between the first node and the fourth node to represent the second event relationship.

3. The method according to claim 1, further comprising: The degree of association regarding the first event relationship is stored in association with the first directed edge.

4. The method of claim 1, wherein the number is specified by user input.

5. The method according to claim 1, further comprising: Determine the first similarity between the first event and the fifth event represented by the fifth node in the reference event graph, and the second similarity between the second event and the sixth event represented by the sixth node in the reference event graph; The reference logic graph is updated based on the first similarity, the second similarity, the first threshold, and the second threshold which is less than the first threshold.

6. The method of claim 5, wherein updating the reference event graph comprises: In response to the first similarity exceeding the first threshold and the second similarity exceeding the first threshold, a directed edge representing the first event relationship is added between the fifth node and the sixth node.

7. The method of claim 5, wherein updating the reference event graph comprises: In response to the first similarity exceeding the first threshold and the second similarity being less than the second threshold, a seventh node representing the second event is added to the reference event graph; as well as Add a directed edge between the fifth node and the seventh node to represent the first event relationship.

8. The method of claim 5, wherein updating the reference event graph comprises: In response to the fact that both the first similarity and the second similarity are between the first threshold and the second threshold, the first logic graph is added to the reference logic graph; as well as Add an indication that the first event is similar to the fifth event and an indication that the second event is similar to the sixth event to the reference event graph.

9. The method according to claim 1, further comprising: In response to the media content being presented or selected, the combined first and second logic graphs are presented.

10. An electronic device, comprising: At least one processing circuit, the at least one processing circuit being configured to perform the method according to any one of claims 1 to 9.

Images