Electronic device and image segment extraction method thereof

Abstract

The invention provides an electronic device and an image segment extraction method thereof. The image segment extraction method includes the following steps. Acquiring event information of a plurality of game events of the game application program in the program execution time period; the event information of the plurality of game events is converted into an input text. The input text is provided to a text classification model. And extracting image segments from the recorded game film of the game application program according to the classification category of the input text predicted by the text classification model. Therefore, wonderful key image segments or key image segments with specific contents can be extracted from the recorded game film.

Description

Technical Field

[0001] The invention relates to an electronic device, and in particular to an electronic device and an image segment extraction method thereof. Background Art

[0002] With the advancement of technology, powerful performance and rich applications have made electronic devices an indispensable item in modern people's daily life. For example, playing games with electronic devices has become a very popular pastime. When gamers play games through electronic devices, they may want to record the wonderful moments or important moments in the game. At present, users can record the game process through screen recording, so that users can replay the recorded game videos to experience the pleasure of the game process or review the wonderful moments.

[0003] However, users generally need to manually edit these recorded game videos to obtain the highlights from the lengthy game videos. This is not only time-consuming and labor-intensive, but also makes it impossible to obtain the highlights in real time while the game is still in progress. Summary of the invention

[0004] The present invention relates to an image segment extraction method and an electronic device, which can solve the above technical problems.

[0005] The embodiment of the present invention provides a method for extracting image fragments, the method comprising the following steps: obtaining event information of multiple game events of a game application during a program execution period; converting the event information of the multiple game events into input text; providing the input text to a text classification model; and extracting image fragments from a recorded game video of the game application according to the classification category of the input text predicted by the text classification model.

[0006] An embodiment of the present invention provides an electronic device, which includes a storage device and a processor. The storage device records a plurality of modules, and the processor is coupled to the storage device and executes the modules to perform the following steps. Event information of a plurality of game events of a game application during a program execution period is obtained. The event information of the plurality of game events is converted into input text. The input text is provided to a text classification model. According to the classification category of the input text predicted by the text classification model, an image segment is extracted from a recorded game video of the game application.

[0007] Based on the above, in an embodiment of the present invention, after obtaining event information of multiple game events, the event information can be converted into input text. By inputting the input text into the trained text classification model, the text classification model will output the classification category of the input text. Therefore, according to the classification result of the input text, the wonderful key image fragments or those with specific content can be extracted from the recorded game video. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a schematic diagram of an electronic device according to an embodiment of the present invention;

[0009] Figure 2 is a flow chart of an image segment extraction method according to an embodiment of the present invention;

[0010] Figure 3 is a schematic diagram of multiple game events in one embodiment of the present case;

[0011] Figure 4 is a flow chart of generating input text according to an embodiment of the present invention;

[0012] Figure 5 is a schematic diagram of a text classification model of an embodiment of the present case;

[0013] Figure 6 is a flow chart of an image segment extraction method according to an embodiment of the present invention;

[0014] Figure 7 It is a schematic diagram of providing relevant information of an image segment to a game broadcasting platform according to an embodiment of the present invention.

[0015] Description of Reference Numerals

[0016] 100: electronic device;

[0017] 110: storage device;

[0018] 130: processor;

[0019] 120: transceiver;

[0020] A1: Gaming applications;

[0021] A2: Game event recording program;

[0022] T1: Game timeline;

[0023] C1, C2: image segments;

[0024] M1: text classification model;

[0025] 710: game streaming server;

[0026] 720: game broadcast server;

[0027] 730: gaming equipment;

[0028] S210~S240, S221~S222, S602~S620: steps. DETAILED DESCRIPTION

[0029] Reference will now be made in detail to exemplary embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Whenever possible, the same reference numerals are used in the drawings and the description to refer to the same or like parts.

[0030] Please refer to Figure 1 , the electronic device 100 of this embodiment is, for example, a laptop computer, a desktop computer, a server, or other electronic device with computing capabilities, and the present invention is not limited to this. It should be noted that in different embodiments, the electronic device 100 can be a server, or a server cluster composed of multiple servers, or other distributed systems, and the present case does not limit this. The electronic device 100 includes a storage device 110, a transceiver 120, and a processor 130. The processor 130 is coupled to the transceiver 120 and the storage device 110, and its functions are described as follows.

[0031] The storage device 110 is used to store files, images, instructions, program codes, software modules and other data, and can be, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk or other similar devices, integrated circuits or combinations thereof.

[0032] The transceiver 120 can transmit and receive signals wirelessly or wiredly. The transceiver 120 can also perform operations such as low noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and the like. The electronic device 100 can receive and send data through the transceiver 120.

[0033] The processor 130 is, for example, a central processing unit (CPU), an application processor (AP), or other programmable general-purpose or special-purpose microprocessor, digital signal processor (DSP), programmable controller, application specific integrated circuits (ASIC), programmable logic device (PLD), graphics processing unit (GPU) or other similar devices or combinations of these devices. The processor 130 can execute program codes, software modules, instructions, etc. recorded in the storage device 110 to implement the image segment extraction method of the present embodiment. The above-mentioned software module can be broadly interpreted as meaning instructions, instruction sets, codes, program codes, programs, applications, software suites, threads, programs, functions, etc.

[0034] In an embodiment of the present invention, the electronic device 100 can identify important content in the recorded game video based on event information of a game event (also called an in-game event) of a game application, and extract image segments containing the important content based on time information of the important content on the game timeline.

[0035] Please refer to Figure 1 as well as Figure 2 The method of this embodiment is applicable to the electronic device 100 in the above-mentioned embodiment. The following describes the detailed steps of the image segment extraction method of this embodiment in conjunction with various components in the electronic device 100.

[0036] In step S210, the processor 130 obtains event information of multiple game events of the game application program during the program execution period. Game events may include the user's manipulation behavior in the game during the game. For example, the player's release of game skills during the game process may be a game event, or the player's manipulation behavior of game equipment during the game process may be a game event, etc. For example, the game event may be the start of the game, the end of the game, the pass, the game victory, the continuous kill, the game stunt performance, or other types of game events. Event information may include the event occurrence time and event identification of each game event. The above-mentioned event identification is, for example, an event name or an event identifier, etc. Event time information is the event occurrence time of the game event on the game timeline.

[0037] In some embodiments, the electronic device 100 may be a device that executes a game application. When the player operates the electronic device 100 to play a game, in response to an event notification including event information provided by the game application during execution, the processor 130 may record the event information of the game event in the storage device 110. The processor 130 may record the event information of the game event in the metadata or other files of the recorded game video. Alternatively, in other embodiments, the electronic device 100 may receive the event information of the game event from another device that executes the game application in real time.

[0038] For example, Figure 3 is a schematic diagram of multiple game events in one embodiment of the present case. Figure 3 During the execution of the game application A1, the game event recording program A2 can obtain event information of multiple game events provided by the game application A1, and record the event information of these multiple game events as an event log file. Figure 3 In the example, the processor 130 can obtain multiple game events of the game application A1 and the event occurrence time on the game timeline T1, such as the game event "jump" corresponding to the event occurrence time "1 minute 12 seconds" and the game event "shoot" corresponding to the event occurrence time "3 minutes 01 seconds", etc.

[0039] In addition, in some embodiments, by executing game recording software or other screen recording software, the processor 130 can activate the video recording function and start recording the game screen to obtain a recorded game video recording the game process. Alternatively, in other embodiments, the electronic device 100 can receive the recorded game video from another device executing the game application. Alternatively, in other embodiments, the electronic device 100 can receive the recorded game video from a game streaming server.

[0040] In step S220, the processor 130 converts the event information of multiple game events into input text. Specifically, the processor 130 can utilize an event sampling time window to take out multiple game events for conversion into an input text. The event sampling time window can be used to indicate the program execution period including multiple game events. The length of this event sampling time window is, for example, 30 seconds, one minute, two minutes or other time lengths. By sliding the event sampling time window on the game time axis according to a sampling interval, the processor 130 can capture multiple game events according to the location of the event sampling time window, so as to generate input text according to the event information of the sampled multiple game events. The above-mentioned sampling interval is, for example, 10 seconds or other time grids. Assuming that the event sampling time window is 1 minute and the sampling interval is 10 seconds, the processor 130 will sample multiple game events within one minute every 10 seconds to generate input text.

[0041] Figure 4 This is a flowchart of generating input text in one embodiment of the present invention. Figure 4 In some embodiments, step S220 may be implemented as steps S221 to S222.

[0042] In step S221, the processor 130 calculates at least one time interval between the multiple game events according to the multiple event occurrence times of the multiple game events. In some embodiments, the processor 130 can calculate the time intervals between the two adjacent game events according to the event occurrence times of the two adjacent game events on the game timeline. It can be seen that these time intervals can indicate the compactness of the occurrence of the game events. Figure 3 For example, the processor 130 can calculate that the time interval between the game event “shoot” corresponding to the event occurrence time “3 minutes 01 seconds” and the game event “kill” corresponding to the event occurrence time “3 minutes 15 seconds” is 14 seconds.

[0043] In step S222, the processor 130 generates an input text according to at least one time interval and multiple event identifications of each game event. Specifically, by concatenating the event identification of each game event and at least one time interval, the processor 130 can obtain a corresponding input text. In other words, the input text is a text sequence generated by concatenating at least one time interval and multiple event identifications of each game event.

[0044] In some embodiments, the processor 130 sequentially arranges multiple event identifications and at least one time interval of multiple game events according to the order of occurrence of multiple game events to generate an input text including multiple event identifications and at least one time interval. In some embodiments, at least one time interval and multiple event identifications can be arranged in an interlaced manner. For example, the time interval between the first game event and the second game event can be connected in series between the event mark of the first game event and the event mark of the second game event. In addition, the order of arrangement of the event marks of each game event in the input text can be determined according to the order of occurrence of the game events on the game timeline.

[0045] In step S230, the processor 130 provides the input text to the text classification model. The model parameters of the text classification model trained based on the training data can be recorded in the storage device 110. Specifically, the text classification model can classify the input text into different categories or labels, which may include a convolutional neural network model, a random forest model, a decision tree model, a support vector machine model, or a natural language model with semantic recognition capabilities, etc. For example, the relevant details of using the text classification model can refer to the relevant technical literature (for example, "Yoon Kim at al., Convolutional Neural Networks for Sentence Classification,.", but it is not limited to this).

[0046] Figure 5 is a schematic diagram of a text classification model of an embodiment of this case. Figure 3 and Figure 5 , the processor 150 can generate an input text [5, shoot, 8, kill, 2, shoot, 1, reload, 1, kill, 3] according to the event information of multiple game events, and input the input text [5, shoot, 8, kill, 2, shoot, 1, reload, 1, kill, 3] to the text classification model M1. The text classification model M1 will classify the input text [5, shoot, 8, kill, 2, shoot, 1, reload, 1, kill, 3] into one of a plurality of preset categories. The preset categories are, for example, "like" and "dislike". Alternatively, in other embodiments, the preset categories are, for example, "first game annotation" and "second game annotation". Alternatively, the preset categories are, for example, "first game summary" and "second game summary".

[0047] More specifically, based on the event sampling time window, the processor 130 can sample the first sampled game event, the second sampled game event, the third sampled game event, the fourth sampled game event, and the fifth sampled game event. According to the first sampled game event "shoot" corresponding to the event occurrence time "4 minutes and 15 seconds" and the game event "load" corresponding to the event occurrence time "4 minutes and 07 seconds", the processor 130 can obtain a time interval of 5 seconds. Next, according to the first sampled game event "shoot" corresponding to the event occurrence time "4 minutes and 15 seconds" and the second sampled game event "kill" corresponding to the event occurrence time "4 minutes and 20 seconds", the processor 130 can obtain a time interval of 8 seconds. Similarly, the processor 130 can obtain subsequent time intervals of 2 seconds, 1 second, 1 second, and 3 seconds respectively.

[0048] Based on this, according to the first sampled game event "shoot" corresponding to the event occurrence time "4 minutes and 15 seconds", the second sampled game event "kill" corresponding to the event occurrence time "4 minutes and 20 seconds", the third sampled game event "shoot" corresponding to the event occurrence time "4 minutes and 22 seconds", the fourth sampled game event "reload" corresponding to the event occurrence time "4 minutes and 23 seconds", and the fifth sampled game event "kill" corresponding to the event occurrence time "4 minutes and 27 seconds", the processor 130 can obtain the input text [5, shoot, 8, kill, 2, shoot, 1, reload, 1, kill, 3] in which the time intervals and event labels are arranged alternately. The text classification model M1 can classify the input text [5, shoot, 8, kill, 2, shoot, 1, reload, 1, kill, 3] into one of the multiple preset categories.

[0049] In step S240, the processor 130 extracts image fragments from the recorded game video of the game application according to the classification category of the input text predicted by the text classification model. In some embodiments, when the text classification model determines that the input text is a first classification category (e.g., a preset classification category of "like" or "exciting"), the processor 130 may determine the timestamp information of the image fragment according to the event occurrence time or program execution period of at least one of the multiple game events. Then, the processor 130 may extract the image fragment from the recorded game video according to the timestamp information. On the other hand, when the text classification model determines that the input text is a second classification category (e.g., a preset classification category of "dislike" or "not exciting"), the processor 130 may not extract the image fragment according to the multiple game events corresponding to the input text.

[0050] More specifically, when the text classification model determines that the input text is of the first classification category, the processor 130 may determine the start timestamp and end timestamp of the image segment according to the event occurrence time of one or more game events corresponding to the input text. For example, assuming that the event occurrence time of the first game event corresponding to the input text is "3 minutes and 1 seconds", the processor 130 may determine the start timestamp of the image segment to be "3 minutes and 1 seconds" and the end timestamp to be "4 minutes and 10 seconds". Alternatively, assuming that the event occurrence time of the first game event corresponding to the input text is "4 minutes and 15 seconds", the processor 130 may determine the start timestamp of the image segment to be "4 minutes and 10 seconds" and the end timestamp to be "4 minutes and 40 seconds". Then, the processor 130 may edit interesting image segments from the recorded game video according to the start timestamp and the end timestamp. Figure 3 For example, the processor 130 may extract the image segments C1 and C2 from the recorded game video of the game application. Alternatively, in other embodiments, the processor 130 may directly set the program execution period corresponding to the input text as the extraction period of the image segments.

[0051] In some embodiments, the processor 130 may also determine the description information of the image segment according to the classification category of the input text predicted by the text classification model. The description information may include keywords, game content identification information, game summary or other game segment annotations. For example, when the text classification model determines that the input text belongs to a first classification category (e.g., the preset classification category "first game summary"), the processor 130 may determine the description information of the extracted image segment according to the first classification category. When the text classification model determines that the input text is a second classification category (e.g., the preset classification category "second game summary"), the processor 130 may determine the description information of the extracted image segment according to the second classification category. In other words, in different embodiments, by utilizing the text classification model, the processor 130 may predict the keywords, game summary or other game segment annotations of the game segment according to the event markers and time intervals in the input text.

[0052] It should be noted that in some embodiments, the text classification model needs to be established by machine learning based on training data. The training data may include a plurality of training video clips, which are annotated and correspond to classification labels. The following examples are given to illustrate.

[0053] Figure 6 is a flow chart of an image segment extraction method according to an embodiment of the present invention. Figure 1 as well as Figure 6 The method of this embodiment is applicable to the electronic device 100 in the above-mentioned embodiment. The following is a description of the detailed steps of the method for generating a thumbnail of a screen recording video of this embodiment in conjunction with the various components in the electronic device 100.

[0054] In step S602, the processor 130 obtains a plurality of training video clips. For example, the processor 130 may obtain training video clips uploaded by user terminal devices of a plurality of players via a network.

[0055] In step S604, the processor 130 determines a plurality of classification labels of the plurality of training video clips. In some embodiments, the processor 130 may obtain the plurality of classification labels of the training video clips based on manual annotation.

[0056] Alternatively, in some embodiments, the processor 130 may publish multiple training video clips on a webpage to collect the label content provided by multiple user terminals through the webpage. For example, after watching these training video clips, the viewer may click on the label "like" or the label "dislike" on the webpage. Afterwards, the processor 130 may receive the label content provided by multiple user terminals through the webpage to determine multiple classification labels of the multiple training video clips. More specifically, the processor 130 may count the number of votes for the label "like" of a certain training video clip. When the number of votes for the label "like" of a certain training video clip is greater than a critical value or greater than the number of votes for the label "dislike", the processor 130 may determine that the classification label of this training video clip is "like". Conversely, when the number of votes for the label "like" of a certain training video clip is less than a critical value or less than the number of votes for the label "dislike", the processor 130 may determine that the classification label of this training video clip is "dislike".

[0057] In step S606, the processor 130 obtains event information of multiple game events of multiple training film clips. In step S608, the processor 130 converts the event information of multiple game events of multiple training film clips into multiple training input texts. The method of generating the training input text is similar to the method of generating the input text, which has been described in the aforementioned embodiment and will not be repeated here. It can be seen that the training input text may include event identifiers of multiple game events and at least one time interval. By concatenating the event identifiers of multiple game events of a certain training film clip and at least one time interval, the processor 130 can obtain the training input text corresponding to the training film clip.

[0058] In step S610, the processor 130 trains a text classification model based on multiple training input texts and multiple classification labels of multiple training video clips. More specifically, each training video clip corresponds to a training input text and a classification label. In the model training stage, the processor 130 can input the training input text into the text classification model in training so that the text classification model in training outputs a model prediction result. The loss function can be used to measure the degree of difference between the model prediction result and the labeled classification label. The processor 130 can use the calculated loss function value to adjust the parameters of the text classification model to reduce the loss. This is achieved through back propagation and an optimizer. The optimizer updates the weights and biases of the model according to the gradient of the loss function to minimize the loss function. After completing the training of the text classification model, the parameters of the text classification model can be recorded in the storage device 110.

[0059] In step S612, the processor 130 obtains event information of multiple game events of the game application during the program execution period. In step S614, the processor 130 converts the event information of the multiple game events into input text. In step S616, the processor 130 provides the input text to the text classification model. In step S618, the processor 130 extracts image fragments from the recorded game video of the game application according to the classification category of the input text predicted by the text classification model. The detailed implementation content of steps S612 to S618 has been described in the aforementioned embodiment and will not be repeated here.

[0060] In step S620, the processor 130 provides the relevant information of the extracted image segment to the game broadcast server. Figure 7 FIG. 1 is a schematic diagram of providing relevant information of an image segment to a game broadcasting platform according to an embodiment of the present invention. Figure 7 , the electronic device 100 may obtain event information of the game event from the player's game device 730. The electronic device 100 may generate input text according to the event information of the game event, and extract the image segment using the classification category output by the text classification model. The electronic device 100 may also obtain relevant information of the extracted image segment, which may include timestamp information and classification category of the extracted image segment. The electronic device 100 may provide the relevant information of the extracted image segment to the game broadcast server 720.

[0061] It is worth mentioning that during the game broadcasting process, the game broadcasting server 720 receives the game screen stream from the game streaming server 710. Generally speaking, the transmission of the game screen stream has a delay. In this case, before the important game screen is transmitted to the game broadcasting server 720, the game broadcasting server 720 has obtained the relevant information of the extracted image fragments, so that the live broadcast personnel can know the important content that may occur later in advance and can prepare in advance.

[0062] In summary, in an embodiment of the present invention, after obtaining event information of multiple game events, the event information can be converted into input text. By inputting the input text into a trained text classification model, the text classification model will output the classification category of the input text. Thus, according to the classification result of the input text, exciting or key image segments with specific content can be extracted from the recorded game video. Based on this, there is no need for the user to manually edit the recorded game video or manually intervene in the judgment, and automatically generated key image segments that are interesting and have the focus of game development can be obtained. In addition, even if the game is still in progress, relevant information of the key image segments can be obtained to make the game live broadcast smoother and more convenient.

[0063] It is worth mentioning that compared to using game screen and image recognition models to identify important moments in the game, the text classification model in this case has less computational complexity and can more efficiently identify important image fragments in the game.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting image fragments, characterized in that: include: Acquire event information of multiple game events of the game application during the program execution period; converting the event information of the plurality of game events into input text; providing the input text to a text classification model; as well as According to the classification category of the input text predicted by the text classification model, image segments are extracted from the recorded game video of the game application.

2. The image segment extraction method according to claim 1, characterized in that: The step of converting the event information of the plurality of game events into the input text comprises: Calculating at least one time interval between the plurality of game events according to a plurality of event occurrence times of the plurality of game events; and The input text is generated according to the at least one time interval and a plurality of event identifications of each of the plurality of game events.

3. The image segment extraction method according to claim 2, characterized in that: The step of generating the input text according to the at least one time interval and the multiple event identifications of the multiple game events comprises: According to the occurrence order of the multiple game events, the multiple event identifications and the at least one time interval of the multiple game events are arranged in sequence to generate the input text including the multiple event identifications and the at least one time interval.

4. The image segment extraction method according to claim 1, characterized in that: The step of extracting the image segment from the recorded game video of the game application according to the classification category of the input text predicted by the text classification model comprises: Describing information of the image segment is determined according to the classification category of the input text predicted by the text classification model.

5. The image segment extraction method according to claim 1, characterized in that: The step of extracting the image segment from the recorded game video of the game application according to the classification category of the input text predicted by the text classification model comprises: When the text classification model determines that the input text is of a first classification category, determining timestamp information of the image segment according to an event occurrence time of at least one of the plurality of game events; and The image segment is extracted from the recorded game video according to the timestamp information.

6. The image segment extraction method according to claim 1, characterized in that: Also includes: Obtain multiple training video clips; Determining a plurality of classification labels for the plurality of training video clips; Acquire event information of a plurality of game events of the plurality of training movie clips; converting event information of the plurality of game events of the plurality of training movie clips into a plurality of training input texts; as well as The text classification model is trained according to the plurality of training input texts of the plurality of training video clips and the plurality of classification labels.

7. The image segment extraction method according to claim 6, characterized in that: The step of determining the plurality of classification labels of the plurality of training video clips comprises: Posting the plurality of training video clips on a webpage; and The multiple classification labels of the multiple training video clips are determined by receiving the marking contents provided by multiple user terminals through the webpage.

8. The image segment extraction method according to claim 1, characterized in that: Also includes: The relevant information of the extracted image segment is provided to the game broadcasting server.

9. An electronic device, characterized in that: include: A storage device for recording a plurality of modules; as well as A processor, coupled to the storage device, executes the modules and is configured to: Acquire event information of multiple game events of the game application during the program execution period; converting the event information of the plurality of game events into input text; providing the input text to a text classification model; as well as According to the classification category of the input text predicted by the text classification model, image segments are extracted from the recorded game video of the game application.

10. The electronic device according to claim 9, characterized in that: The processor is configured to: Calculating at least one time interval between the plurality of game events according to a plurality of event occurrence times of the plurality of game events; and The input text is generated according to the at least one time interval and a plurality of event identifications of each of the plurality of game events.

11. The electronic device according to claim 10, characterized in that: The processor is configured to: According to the occurrence order of the multiple game events, the multiple event identifications and the at least one time interval of the multiple game events are arranged in sequence to generate the input text including the multiple event identifications and the at least one time interval.

12. The electronic device according to claim 9, characterized in that: The processor is configured to: Describing information of the image segment is determined according to the classification category of the input text predicted by the text classification model.

13. The electronic device according to claim 9, characterized in that: The processor is configured to: When the text classification model determines that the input text is of a first classification category, determining timestamp information of the image segment according to an event occurrence time of at least one of the plurality of game events; as well as The image segment is extracted from the recorded game video according to the timestamp information.

14. The electronic device according to claim 9, characterized in that: The processor is configured to: Obtain multiple training video clips; Determining a plurality of classification labels for the plurality of training video clips; Acquire event information of a plurality of game events of the plurality of training movie clips; converting event information of the plurality of game events of the plurality of training movie clips into a plurality of training input texts; as well as The text classification model is trained according to the plurality of training input texts of the plurality of training video clips and the plurality of classification labels.

15. The electronic device according to claim 14, characterized in that: The processor is configured to: Posting the plurality of training video clips on a webpage; and The multiple classification labels of the multiple training video clips are determined by receiving the marking contents provided by multiple user terminals through the webpage.

16. The electronic device according to claim 9, characterized in that: The processor is configured to: The extracted relevant information of the image segment is provided to a game broadcasting platform.

Images