Recording marking method and device, recording event display method and device, and equipment

Abstract

The embodiment of the invention relates to a recording marking method and device, a recording event display method and device and equipment, and the method comprises the steps: collecting multimedia data through a data collection module under the condition that recording equipment is in a target recording scene, the target recording scene comprises a scene in which the duration of continuously recording the multimedia by the recording equipment is greater than a duration threshold; in response to the triggered marking operation, determining marking information corresponding to the marked target multimedia data; and sending the at least part of multimedia data collected by the data collection module and the mark information to the electronic equipment, so that the electronic equipment performs analysis according to target multimedia data in the at least part of multimedia data and the mark information through an event recognition model to obtain first recording event information corresponding to the mark information. The recording equipment can support portable multimedia data recording, the use convenience of the recording equipment is improved, and the accuracy of analyzing the multimedia data recorded by the recording equipment is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a recording marking method and device, a recording event display method and device, and equipment. BACKGROUND

[0002] Recording equipment (such as smart glasses, action cameras, voice recorders, etc.) is widely used in various scenarios such as daily life, sports recording, and conference recording due to its convenience and practicality. These recording equipment usually has the ability to record multimedia data (such as video and audio) and / or analyze multimedia data, and also supports data synchronization with electronic equipment. However, the current recording equipment has certain randomness in analyzing the content of part of the multimedia data, resulting in low accuracy and poor reliability of the analysis results of the multimedia data. SUMMARY

[0003] The embodiments of the present application disclose a recording marking method and device, a recording event display method and device, and equipment. The recording equipment can support portable multimedia data recording, improve the use convenience of the recording equipment, and improve the accuracy and reliability of analyzing the multimedia data recorded by the recording equipment.

[0004] In a first aspect, the embodiments of the present application disclose a recording marking method applied to recording equipment, wherein the recording equipment comprises a data acquisition module; the method comprises:

[0005] acquiring multimedia data through the data acquisition module when the recording equipment is in a target recording scene, wherein the target recording scene includes a scene in which the recording equipment continuously records multimedia for a duration greater than a duration threshold;

[0006] determining marking information corresponding to target multimedia data to be marked in response to a triggered marking operation;

[0007] sending at least part of the multimedia data acquired by the data acquisition module and the marking information to an electronic equipment, so that the electronic equipment analyzes the target multimedia data in the at least part of the multimedia data and the marking information according to an event recognition model to obtain first recording event information corresponding to the marking information, wherein the electronic equipment comprises a terminal device and / or a server, and the first recording event information is used for display on the terminal device.

[0008] In the embodiment of the present application, the recording device supports recording in a target recording scene, that is, supports long-time continuous recording of multimedia data. In the case of long-time continuous recording of multimedia data by the recording device, the user can trigger a marking operation according to the user's own needs, and the recording device can mark the target multimedia data according to the triggered marking operation. The electronic device can analyze the multimedia data collected by the recording device and the marking information corresponding to the marking operation through the event recognition model, so as to accurately obtain the first recording event information corresponding to the marking information. This can avoid the situation that the result output by the artificial intelligence model does not match the content expected by the user due to the randomness and uncertainty of the artificial intelligence model when analyzing a large amount of multimedia data. The event recognition model in the embodiment of the present application can output the first recording event information expected by the user according to the marking information corresponding to the marking operation triggered by the user, accurately meet the user's needs, and improve the accuracy and reliability of analyzing the multimedia data recorded by the recording device. Moreover, the recording device can support portable multimedia data recording, improving the use convenience of the recording device.

[0009] As an optional implementation, the marking information includes marking time information; and / or,

[0010] The marking information includes marking content information.

[0011] In this implementation, the recording device can provide a basis for time cutting according to the marking time information to quickly locate and obtain the recording data corresponding to the user marking time; and can provide a guide for content cutting according to the marking content information to accurately filter the recording data segment related to the user marking time; and the recording device can better cater to the recording data corresponding to the user marking through the above-mentioned time cutting or content cutting.

[0012] As an optional implementation, the marking information includes marking time information; and the response to the triggered marking operation, determining the marking information corresponding to the marked target multimedia data, includes:

[0013] Obtaining an operation triggering time corresponding to the marking operation;

[0014] Determining the marking time information corresponding to the marked target multimedia data according to the operation time.

[0015] In this implementation, the operation triggering time corresponding to the marking operation is obtained, and the marking time information of the target multimedia data is determined accordingly, so that the occurrence time point of the content interested by the user can be accurately recorded, and the multimedia data marked by the user can be quickly located and reviewed subsequently. Especially in the case of long-time continuous recording, the retrieval efficiency of the multimedia data marked by the user can be improved.

[0016] As an optional implementation, the marked time information is any one of the following:

[0017] The marked time information is used to indicate a first time period before the operation trigger moment;

[0018] The marked time information is used to indicate a second time period after the operation trigger moment;

[0019] The marked time information is used to indicate a third time period before the operation trigger moment and a fourth time period after the operation trigger moment.

[0020] In this implementation, the three kinds of marked time information setting modes around the operation trigger moment, by flexibly defining the marked interval range, meet the marking needs of different scenarios, so that both the key content at the operation trigger moment (such as the starting point of the event) can be focused on, and the event background (the time period before the trigger) or the subsequent influence (the time period after the trigger) can be traced back, or even the complete capture of the event panorama (the combined time period before and after the trigger) can be completed, so as to complete the marking of complex time range and improve the operation convenience in long-time recording environment.

[0021] As an optional implementation, the marking operation includes a start marking operation and an end marking operation;

[0022] The marked time information is used to indicate a time period between a first operation trigger moment corresponding to the start marking operation and a second operation trigger moment corresponding to the end marking operation.

[0023] In this implementation, through the time period corresponding to the start marking operation and the end marking operation, the recording device can accurately mark the recording content interested by the user, so that the electronic device can analyze the recording content really concerned by the user, and the accuracy of analyzing the multimedia data recorded by the recording device is improved.

[0024] As an optional implementation, the marking information includes marking content information; the marking information corresponding to the target multimedia data marked by the marking operation triggered in response, includes:

[0025] Obtaining the multimedia data segment corresponding to the marking operation, and identifying the multimedia data segment to obtain recording key information, and taking the recording key information as the marking content information, the marking content information is used for the electronic device to find multimedia data matching the recording key information from the at least part of the multimedia data according to the recording key information as the target multimedia data marked.

[0026] In this embodiment, the recording device obtains the multimedia data segment corresponding to the marking operation and automatically identifies the recording key information therein as the marking content information, thereby realizing intelligent content marking, and the user can quickly generate meaningful marks without manual input, improving the marking efficiency and accuracy of the multimedia data. Meanwhile, the electronic device can directly locate and extract the target multimedia data from the multimedia data according to the recording key information, simplifying the information retrieval process.

[0027] As an optional embodiment, the method further comprises:

[0028] obtaining the multimedia data segment corresponding to the marking operation, taking the multimedia data segment as the marking content information, and using the marking content information to identify the recording key information by the electronic device, and searching for the multimedia data matching the recording key information from the at least part of the multimedia data as the target multimedia data of the mark according to the recording key information.

[0029] In this embodiment, the multimedia data segment corresponding to the marking operation is directly sent to the electronic device as the marking content information, and the electronic device is used to identify the multimedia data segment to extract the recording key information, which can improve the accuracy of the recording key information extraction, and further search for the matching content in the multimedia data as the target multimedia data according to the accurate recording key information, which can improve the accuracy and efficiency of the target multimedia data, especially when processing a large amount of multimedia data, which can enhance the speed of extracting the target multimedia data and reduce the analysis and processing time.

[0030] As an optional embodiment, the recording key information comprises at least one of a keyword, a key sentence, and object information corresponding to a target recording object.

[0031] In this embodiment, the recording key information can include various information to flexibly describe the marking content information, and the accuracy of determining the target multimedia data can be improved by the recording key information, thereby realizing more accurate event identification.

[0032] As an optional embodiment, the marking information further comprises marking time information.

[0033] The marking content information is used by the electronic device to search for the multimedia data matching the recording key information in the multimedia data corresponding to the marking time information as the target multimedia data of the mark according to the recording key information.

[0034] In this embodiment, by combining the marking time information and the marking content information, the recording device can quickly locate the multimedia data matching the recording key information within a specific time range, so as to quickly and accurately determine the target multimedia data to be marked.

[0035] As an optional implementation, in response to the triggered marking operation, the marking information corresponding to the target multimedia data to be marked is determined, including:

[0036] In response to the triggered marking operation, a target marking mode is determined; the target marking mode includes a first marking mode or a second marking mode; the first marking mode is a mode of marking based on time; the second marking mode is a mode of marking based on recording content;

[0037] According to the target marking mode, the marking information corresponding to the target multimedia data to be marked is determined.

[0038] In this embodiment, two marking modes are divided according to two different dimensions of marking information, and the marking mode can be flexibly selected according to the marking operation, so as to improve the accuracy and efficiency of marking, meet the diversified marking requirements in different scenarios, and enhance the interaction with the user.

[0039] As an optional implementation, the first marking mode corresponds to a first marking operation, and the second marking mode corresponds to a second marking operation, and the first marking operation is different from the second marking operation.

[0040] In response to the triggered marking operation, the target marking mode is determined, including:

[0041] If the first marking operation is detected, the target marking mode is determined as the first marking mode in response to the first marking operation.

[0042] If the second marking operation is detected, the target marking mode is determined as the second marking mode in response to the second marking operation.

[0043] In this embodiment, by assigning different marking operations (first marking operation and second marking operation) to different marking modes (first marking mode and second marking mode), the marking interaction between the recording device and the user is realized.

[0044] As an optional implementation, in response to the triggered marking operation, the marking information corresponding to the target multimedia data to be marked is determined, including:

[0045] The mode information sent by the terminal device is received, and the mode information is used to indicate the target marking mode;

[0046] According to the target marking mode, marking information corresponding to the marked target multimedia data is determined.

[0047] In this embodiment, the target marking mode is set and synchronized to the recording device by the terminal device, which can reduce the complexity of the recording device, so that the recording device can focus more on marking, thereby improving the marking accuracy and use convenience of the recording device.

[0048] As an optional embodiment, the operation mode of the marking operation includes at least one of a knocking operation, a touch operation, a control pressing operation, an operation of inputting a target voice instruction, and an operation of a target action on the recording device.

[0049] In this embodiment, the marking operation can include various specific operation modes to flexibly mark, thereby improving the convenience and user experience of the marking operation, and also reducing the possibility of misoperation, ensuring the accuracy and reliability of the marking information.

[0050] As an optional embodiment, the sending of the at least part of the multimedia data collected by the data collection module and the marking information to the electronic device includes:

[0051] After the marking information is acquired, the at least part of the multimedia data collected by the data collection module and the marking information are sent to the electronic device.

[0052] In this embodiment, after the recording device completes the acquisition of the marking information, the at least part of the multimedia data collected and the corresponding marking information are immediately transmitted to the electronic device, so that the electronic device synchronously receives the marking information and the collected multimedia data, thereby timely analyzing the marking information by the event recognition model to determine the first recording event information corresponding to the marking information.

[0053] As an optional embodiment, the sending of the at least part of the multimedia data collected by the data collection module and the marking information to the electronic device includes:

[0054] If the preset sending condition is met, the at least part of the multimedia data collected by the data collection module and the marking information are sent to the electronic device.

[0055] In the embodiment, the recording device triggers the sending of the multimedia data and the mark information by setting the preset sending condition, realizes flexible control of data transmission, avoids unnecessary frequent transmission to cause power loss of the recording device, and affects the recording time of the recording device. Meanwhile, the recording device can timely and reliably send the multimedia data and the mark information to the electronic device when the condition is met, thereby avoiding the problems of unsynchronized recording device and electronic device or too long analysis time of the recording device on long-time recording data caused by sending complete long-time recording data to the electronic device at one time.

[0056] As an optional embodiment, the preset sending condition comprises at least one of the following:

[0057] The remaining power of the recording device is less than a power threshold;

[0058] The recording device enters a charging state;

[0059] The time length from the last sending time to the current time reaches a cycle time length, and the last sending time is the time when the recording device last sent data and mark information to the electronic device;

[0060] A sending operation is detected.

[0061] In the embodiment, by setting multiple preset sending conditions, the recording device can reduce the power loss caused by unnecessary data sending in different working scenarios, and gradually send the large amount of multimedia data collected for a long time to the electronic device in the preset sending condition, improve the accuracy of multimedia data transmission, and improve the accuracy of analyzing the multimedia data recorded by the recording device.

[0062] As an optional embodiment, the at least part of the multimedia data is also used for the electronic device to analyze the at least part of the multimedia data to obtain one or more second recording event information.

[0063] In the embodiment, since the recording device performs long-time recording, the recording content can contain rich content. In addition to the first recording event information corresponding to the mark information, the electronic device also analyzes the multimedia data collected by the data collection module of the recording device to generate multiple second recording event information. The multiple second recording event information is not all related to the mark information, which helps the user to clearly know the events and content of the recording performed by the recording device according to the first recording event information and the multiple second recording event information.

[0064] As an optional embodiment, the multimedia data comprises one or more of audio data, video data and image data.

[0065] In a second aspect, the embodiments of the present application disclose a recording event display method applied to an electronic device, the method comprising:

[0066] displaying first recording event information;

[0067] The first recording event information is obtained by the electronic device through an event recognition model based on target multimedia data in at least part of multimedia data and mark information, the at least part of multimedia data is collected by a data collection module of a recording device in a target recording scene and sent to the electronic device, the target recording scene includes a scene in which the recording device continuously records multimedia for a time length greater than a time length threshold, the mark information is determined by the recording device in response to a triggered mark operation, and the mark information is used to indicate marked target multimedia data, and the electronic device includes the terminal device and / or a server.

[0068] In the embodiments of the present application, the electronic device receives multimedia data and mark information sent by the recording device, and analyzes the target multimedia data and the mark information through the event recognition model, so as to accurately obtain the first recording event information corresponding to the mark information, which can avoid the situation that the result output by the artificial intelligence model does not match the content expected by the user due to the randomness and uncertainty of the artificial intelligence model when analyzing a large amount of multimedia data, and can output the first recording event information according to the mark information corresponding to the mark operation triggered by the user, so that the first recording event information displayed by the terminal device can accurately meet the needs of the user, and the accuracy and reliability of analyzing the multimedia data recorded by the recording device are improved.

[0069] As an optional implementation, the method further comprises:

[0070] In the display area corresponding to the first recording event information, a first identifier is displayed, and the first identifier is used to indicate that the first recording event information is recording event information corresponding to the mark operation.

[0071] In this implementation, the first identifier is added in the display area of the first recording event information, which can directly indicate that the recording event information is directly related to the mark operation of the user, so that the user can quickly identify and focus on the recording event information, and the pertinence of displaying the recording event information is enhanced.

[0072] As an optional implementation, the method further comprises:

[0073] In response to the information viewing operation on the first recording event information, a recording event page corresponding to the first recording event information is displayed, the recording event page corresponding to the first recording event information being configured to display event content corresponding to the first recording event information and / or event content of a recording event associated with the first recording event information.

[0074] In this embodiment, by responding to the information viewing operation on the first recording event information and displaying the corresponding recording event page, the terminal device can not only display the first recording event information, but also display the specific event content of the first recording event information and / or the event content of the associated recording event through page jumping, so that the user can observe the marked information (information of interest) and related events completely.

[0075] As an optional embodiment, the method further comprises:

[0076] In response to the recording search operation, the input search content is obtained;

[0077] According to the search content, the at least part of the multimedia data is searched to obtain multimedia data matching the search content;

[0078] The matched multimedia data is analyzed by the event recognition model to obtain third recording event information, and the third recording event information is displayed.

[0079] In this embodiment, the terminal device can respond to the recording search operation to reorganize the third recording event information related to the search content in the at least part of the multimedia data, and use the event recognition model to analyze the matched data in depth to extract and display the third recording event information. The intelligent analysis (event recognition model) can help the user to quickly find the information point (search content) required by the user from a large amount of multimedia data, improve the efficiency and accuracy of information searching, and meet the user's demand for quick search of specific content.

[0080] As an optional embodiment, the method further comprises:

[0081] In response to the recording play operation on the first recording event information, the multimedia data corresponding to the first recording event information is played.

[0082] In this embodiment, the terminal device can directly play the target multimedia data corresponding to the user marking operation according to the recording play operation, so that the user can quickly watch and listen to the target multimedia data segment by simply operating, without the need to search in the lengthy multimedia data, so that the playing of the multimedia data of the terminal device is more intuitive, efficient and accurate.

[0083] As an optional implementation, the method further comprises:

[0084] analyzing the at least part of the multimedia data by the event recognition model to obtain one or more second recording event information;

[0085] displaying the one or more second recording event information.

[0086] In this implementation, in addition to displaying the first recording event information corresponding to the marking information, the terminal device also displays a plurality of second recording event information obtained by comprehensively analyzing the received at least part of the multimedia data by the event recognition model, so that the user can obtain the content event contained in the at least part of the multimedia data recorded by the recording device while obtaining the marking information, thereby displaying more comprehensive information for the user.

[0087] As an optional implementation, the display area corresponding to the first recording event information is located above the display areas corresponding to the one or more second recording event information respectively.

[0088] In this implementation, the terminal device displays the first recording event information corresponding to the marking information above the plurality of second recording event information without marking, highlights the first recording event information, so that the user can pay more attention to the first recording event information more intuitively.

[0089] As an optional implementation, the method further comprises:

[0090] obtaining the starting recording time corresponding to the first recording event information, and the starting recording time corresponding to the one or more second recording event information respectively;

[0091] displaying the first recording event information and the one or more second recording event information in turn according to the time sequence of the starting recording time.

[0092] In this implementation, the terminal device displays the first recording event information and the second recording event information in turn according to the recording time, can connect the recording event information marked by the user and recognized by the electronic device through the time axis, and construct a relatively complete event development context, so that the user can intuitively perceive the event order and relevance, and the logicality of information display is improved.

[0093] As an optional implementation, the method further comprises:

[0094] displaying the first recording event information according to a first display style;

[0095] displaying the one or more second recording event information according to a second display style, the first display style being different from the second display style.

[0096] In this embodiment, the terminal device displays the first recording event information corresponding to the marking information in a display manner different from the second recording event information, which can visually distinguish and emphasize the importance of the recording event information marked by the user, and highlight the first recording event information.

[0097] As an optional embodiment, the recording event information includes an event theme, the first display style includes a first font style corresponding to the first event theme of the first recording event information, and the second display style includes a second font style corresponding to the second event theme of the second recording event information; the first font style is different from the second font style.

[0098] In this embodiment, the first recording event information and the second recording event information are visually distinguished by setting different font styles for the event themes of the first recording event information and the second recording event information, which can directly highlight the first recording event information by the difference in font styles.

[0099] As an optional embodiment, the first display style includes a first event image, and the second display style includes a second event image, and the displaying the first recording event information in the first display style includes:

[0100] displaying a first event image corresponding to the first recording event information in a display area corresponding to the first recording event information;

[0101] The displaying the one or more second recording event information in the second display style includes:

[0102] displaying a second event image corresponding to each of the second recording event information in a display area corresponding to each of the second recording event information.

[0103] In this embodiment, the terminal device configures corresponding event images for the first recording event information (marked by the user) and the second recording event information (identified by the electronic device), and displays them in different display areas, which can visually highlight the first recording event information, and can also help the user quickly understand the content of the recording event information through the images.

[0104] As an optional embodiment, the method further includes:

[0105] analyzing the first recording event information and the one or more second recording event information, and determining one or more target second recording event information associated with the first recording event information from the one or more second recording event information;

[0106] displaying a second mark in each display area corresponding to the target second recording event information, the second mark being used to indicate that the corresponding target second recording event information is associated with the first recording event information.

[0107] In this embodiment, the terminal device screens the target second recording event information associated with the mark information from the second recording event information, and adds a second mark in the display area thereof, so that the association relationship between the recording event information can be intuitively displayed through visual means, and the visibility of the display page of the terminal device is improved.

[0108] As an optional embodiment, the display styles of the one or more target second recording event information are different; the display style of the target second recording event information is determined according to the association degree of the target second recording event information and the first recording event information.

[0109] In this embodiment, the terminal device dynamically adjusts the display style of the target second recording event information according to the association degree of the target second recording event information and the first recording event information, so that the association strength between the recording event information can be intuitively reflected through a visual gradient, so as to facilitate the user to quickly obtain the association relationship.

[0110] As an optional embodiment, the method further comprises:

[0111] obtaining historical marked recording event information;

[0112] analyzing the association relationship between the first recording event information and the one or more second recording event information and the historical marked recording event information respectively, to determine one or more fourth recording event information associated with the historical marked recording event information;

[0113] displaying a third mark in each display area corresponding to the fourth recording event information, the third mark being used to indicate that the corresponding fourth recording event information is associated with the historical marked recording event information.

[0114] In this embodiment, the terminal device analyzes the potential association between the first recording event information and the second recording event information and the historical marked recording event information, and adds a third mark in the display area of the associated fourth recording event information, so that the current recording event information can be associated with the historical mark information of the user, and the continuity of the event context is displayed, which is beneficial to subsequent recording event information processing.

[0115] In a third aspect, the embodiments of the present application disclose a recording marking device applied to a recording device, the recording device comprising a data acquisition module; the device comprises:

[0116] The recording module is configured to collect multimedia data by the data collection module when the recording device is in a target recording scene, where the target recording scene includes a scene in which the recording device continuously records multimedia for a duration greater than a duration threshold.

[0117] The marking module is configured to determine marking information corresponding to the target multimedia data in response to a triggered marking operation.

[0118] The sending module is configured to send at least part of the multimedia data collected by the collection module and the marking information to an electronic device, so that the electronic device analyzes the target multimedia data in the at least part of the multimedia data and the marking information according to an event recognition model to obtain first recording event information corresponding to the marking information. The electronic device includes a terminal device and / or a server, and the first recording event information is used for display on the terminal device.

[0119] In the embodiments of the present application, the recording device supports recording in a target recording scene, that is, supports long-time continuous recording of multimedia data. In the case of long-time continuous recording of multimedia data by the recording device, the user can trigger a marking operation according to the user's own needs, and the recording device can mark target multimedia data according to the triggered marking operation. The electronic device can analyze the multimedia data collected by the recording device and the marking information corresponding to the marking operation according to the event recognition model, so as to accurately obtain the first recording event information corresponding to the marking information. This can avoid the situation that the result output by the artificial intelligence model does not match the content expected by the user due to the randomness and uncertainty of the artificial intelligence model when analyzing a large amount of multimedia data. The event recognition model in the embodiments of the present application can output the first recording event information expected by the user according to the marking information corresponding to the marking operation triggered by the user, accurately meet the user's needs, and improve the accuracy and reliability of analyzing the multimedia data recorded by the recording device. Moreover, the recording device can support portable multimedia data recording, improving the use convenience of the recording device.

[0120] In a fourth aspect, the embodiments of the present application disclose a recording event display device applied to a terminal device. The device comprises:

[0121] The display module is configured to display the first recording event information.

[0122] The first recording event information is obtained by the electronic device through an event recognition model based on target multimedia data in at least part of the multimedia data and the marking information; the at least part of the multimedia data is collected by a data collection module of the recording device in a target recording scene, and is sent to the electronic device; the target recording scene includes a scene in which the recording device continuously records multimedia for a duration greater than a duration threshold; the marking information is determined by the recording device in response to a triggered marking operation, and the marking information is used to indicate the marked target multimedia data; and the electronic device includes the terminal device and / or a server.

[0123] In the embodiments of the present application, the electronic device receives the multimedia data and the marking information sent by the recording device, and analyzes the target multimedia data and the marking information through an event recognition model, thereby accurately obtaining the first recording event information corresponding to the marking information. This can avoid the situation that the result output by the artificial intelligence model does not match the content expected by the user due to the randomness and uncertainty of the artificial intelligence model when analyzing a large amount of multimedia data. In this way, the first recording event information can be output according to the marking information corresponding to the marking operation triggered by the user, so that the first recording event information displayed by the terminal device can accurately meet the needs of the user, and the accuracy and reliability of analyzing the multimedia data recorded by the recording device are improved.

[0124] In a fifth aspect, the embodiments of the present application disclose a recording device, comprising a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to realize the method of any one of the embodiments of the first aspect.

[0125] In a sixth aspect, the embodiments of the present application disclose a terminal device, comprising a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to realize the method of any one of the embodiments of the second aspect.

[0126] In a seventh aspect, the embodiments of the present application disclose a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the method of any one of the embodiments.

[0127] In an eighth aspect, the embodiments of the present application disclose a computer program product, comprising a computer program, and the computer program is executed by a processor to realize the method of any one of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0128] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0129] Figure 1A Application scenario diagram of the recording device and the electronic device in one embodiment;

[0130] Figure 1B Application scenario diagram of the recording device and the electronic device in another embodiment;

[0131] Figure 1C Structural block diagram of the recording device and the electronic device in one embodiment;

[0132] Figure 2 Flow chart of the recording marking method applied to the recording device in one embodiment;

[0133] Figure 3 Flow chart of the marking information determination in one embodiment;

[0134] Figure 4 Flow chart of the recording marking method applied to the recording device in one embodiment;

[0135] Figure 5 Flow chart of the recording marking method applied to the recording device in another embodiment;

[0136] Figure 6 Flow chart of the recording marking method applied to the recording device in another embodiment;

[0137] Figure 7A Flow chart of the recording event display method applied to the terminal device in one embodiment;

[0138] Figure 7B Schematic diagram of the display page of the terminal device in one embodiment;

[0139] Figure 7C Schematic diagram of the display page of the terminal device in another embodiment;

[0140] Figure 7D Schematic diagram of the display page of the terminal device in another embodiment;

[0141] Figure 7E Schematic diagram of the display page of the terminal device in another embodiment;

[0142] Figure 8A Flow chart of the recording event display method applied to the terminal device in one embodiment;

[0143] Figure 8B a display page of a terminal device in one embodiment;

[0144] Figure 9A a flowchart of a recording event display method applied to a terminal device in one embodiment;

[0145] Figure 9B a display page of a terminal device in one embodiment;

[0146] Figure 9C a display page of a terminal device in another embodiment;

[0147] Figure 10A a flowchart of a recording event display method applied to a terminal device in one embodiment;

[0148] Figure 10B a display page of a terminal device in one embodiment;

[0149] Figure 10C a display page of a terminal device in another embodiment;

[0150] Figure 11A a flowchart of a recording event display method applied to a terminal device in one embodiment;

[0151] Figure 11B a display page of a terminal device in one embodiment;

[0152] Figure 11C a display page of a terminal device in another embodiment;

[0153] Figure 12A a flowchart of a recording event display method applied to a terminal device in one embodiment;

[0154] Figure 12B a display page of a terminal device in one embodiment;

[0155] Figure 13 a block diagram of a recording marker device applied to a recording device in one embodiment;

[0156] Figure 14 a block diagram of a recording event display device applied to a terminal device in one embodiment;

[0157] Figure 15 a structural block diagram of a recording device in one embodiment;

[0158] Figure 16 a structural block diagram of a terminal device in one embodiment. DETAILED DESCRIPTION

[0159] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0160] It is understood that the terms "first," "second," and the like used herein may be used to describe various elements, but these elements are not limited by these terms. These terms are used solely to distinguish a first element from another element. For example, without departing from the scope of this application, first recorded event information may be referred to as second recorded event information, and similarly, second recorded event information may be referred to as first recorded event information. The first recorded event information and the second recorded event information are different recorded event information.

[0161] In related technologies, the interaction between recording devices and users mainly relies on physical buttons or touch screens. When using physical buttons for operation, because the physical buttons require precise pressing, in certain scenarios, such as when the user is running, cycling, or when the hands are wet, they are easily affected by sweat or the external environment, making the user's pressing operation inconvenient or even malfunctioning. When using a touch screen for operation, if it is in a humid environment or the user is wearing gloves, the problem of touch failure will also occur, thus affecting the user experience.

[0162] Furthermore, recording devices or electronic devices in related technologies may often use AI (Artificial Intelligence) to summarize recorded content. While AI summarization can be convenient to a certain extent, it is somewhat random and may be based on factors such as the amount and relevance of recorded content. This method of summarization is unlikely to target content that users are particularly interested in. More importantly, users cannot actively interfere with the process and results of AI summarization, resulting in the results of AI summarization not fully meeting users' actual needs.

[0163] The embodiments of the present application disclose a recording marking method and device, a recording event display method and device, and a device. The recording device can support portable multimedia data recording, improve the convenience of using the recording device, and improve the accuracy and reliability of analyzing the multimedia data recorded by the recording device.

[0164] Figure 1A FIG is an application scenario diagram of a recording device and an electronic device in one embodiment. Figure 1AAs shown, the recording marking method provided by the embodiments of the present application can be applied to the recording device 110, and the recording event display method provided by the embodiments of the present application can be applied to the electronic device 120. The recording device 110 and the electronic device 120 establish a communication connection. The recording device 110 can be wearable, such as a neck clip, a wristband, a neck hanging type, and a magnetic chest badge. The recording device 110 can also be portable, such as a box, a pen, a pendant, and the like. The electronic device 120 can include a terminal device and / or a server.

[0165] The communication connection mode that can be used includes but is not limited to Bluetooth connection, Wi-Fi connection, NFC (Near Field Communication) connection, mobile network connection, and the like. For example, as shown in Figure 1A As shown, after the recording device 110 and the electronic device 120 establish a communication connection, the recording device 110 can directly send multimedia data to the electronic device 120; and the electronic device 120 directly receives the multimedia data sent by the recording device 110.

[0166] Alternatively, the recording device 110 and the electronic device 120 can also be connected through a network, and data transmission is performed through the cloud as a medium. For example, as shown in Figure 1B As shown, the recording device 110 uploads and stores data to the cloud 140, and then the cloud 140 synchronizes the data to the electronic device 120. The analysis and processing of the data can be performed on the electronic device 120, or the data can be analyzed on the cloud 140 and then synchronized to the electronic device 120.

[0167] Optionally, the communication connection between the recording device 110 and the electronic device 120 is flexible. Specifically, the recording device 110 and the electronic device 120 can maintain a persistent connection state to ensure the real-time and stability of data transmission; or the connection can be established only when the recording device 110 needs to send multimedia data to the electronic device 120, thereby saving device resources and energy consumption.

[0168] The recording device 110 refers to a device that can be worn on the human body or clothes and has a recording function. The recording device 110 can include but is not limited to a smart watch, smart glasses, a head-mounted recording device, a recording device that can be clipped (or pasted) on clothes, and the like.

[0169] The recording device 110 can include but is not limited to an audio recording device and / or a video recording device, for example, the recording device 110 can be a recording twist buckle, a wearable camera, and the like. The recording device 110 can support long-time recording.

[0170] The electronic device 120 refers to a device for receiving, processing, storing or displaying multimedia data recorded by the recording device 110. The electronic device 120 can include, but is not limited to, a mobile phone, a computer, a cloud server, and the like.

[0171] Figure 1C FIG. 1 is a structural block diagram of a recording device and an electronic device in one embodiment. As shown in FIG. 1, the recording device 110 can include a data acquisition module 112. Figure 1C

[0172] The data acquisition module 112 is configured to record various target objects and related activities in the environment where the user 130 is located, and acquire multimedia data. The data acquisition module 112 can include, but is not limited to, a microphone and / or a camera, and the like.

[0173] Specifically, the microphone can capture sound signals in the surrounding environment, whether it is a conversation between people, a live music performance, or the sound of the wind and rain in nature, etc. can be converted into an electrical signal through the microphone and recorded. The camera can acquire video image information, and the camera can include a high-definition camera, a wide-angle camera, or a camera with special functions, etc.

[0174] As shown in FIG. 1, the electronic device 120 can store an event recognition model 122. The event recognition model 122 is an analysis model based on artificial intelligence algorithms, which can use technologies in the fields of machine learning and deep learning, etc. Through the learning and analysis of a large number of sample multimedia data of known events, it can master the characteristic patterns and laws of different events, thereby having the ability to intelligently analyze and judge the event information contained in the input multimedia data. Figure 1B

[0175] The event recognition model 122 can be used for automatic event recognition processing of the multimedia data (covering one or more forms of audio, video, image, etc.) collected by the recording device 110. For example, when the recording device 110 records the activity video of the user 130 in a day, the event recognition model 122 can identify various daily events such as “getting up”, “washing”, “eating”, “traveling”, “working”, “exercising”, “resting”, etc. from the video, and summarize these events to form corresponding recording event information.

[0176] ​​In some embodiments, the user 130 wears the recording device 110 on the body and starts the recording device 110, so that the recording device 110 is in a target recording scene for long-time recording, and the multimedia data is collected by the data collection module 112 on the recording device 110. During the recording process of the recording device 110, the user 130 can mark the recording device 110 according to the user's own needs when the recording device 110 records the content of interest and / or importance, so that the recording device 110 marks the recorded multimedia data accordingly. The recording device 110 determines the marking information corresponding to the target multimedia data in response to the triggered marking operation; the recording device 110 sends at least part of the multimedia data collected by the data collection module 112 and the marking information to the electronic device 120. The electronic device 120 analyzes the target multimedia data in the received at least part of the multimedia data and the marking information according to the event recognition model 122, obtains the first recording event information corresponding to the marking information, and displays the first recording event information through the terminal device, so that the user 130 can intuitively watch the content marked (interested) by himself.

[0177] As shown in FIG. 1, in one embodiment, a recording and marking method is provided, which can be applied to the recording device described above. The method can include the following steps 210-230. Figure 2

[0178] Step 210, under the condition that the recording device is in a target recording scene, multimedia data is collected by a data collection module.

[0179] The target recording scene refers to a scene in which the recording device continuously records multimedia for a duration greater than a duration threshold. The target recording scene can include but is not limited to recording the user's daily activities (such as going out for a trip, attending a party, etc.), the user's work report demonstration, the user's learning course explanation, etc., the user's sports and fitness (such as running, aerobics, ball games, etc.) process, etc. which need to be recorded for a long time.

[0180] The multimedia data refers to a data set containing various information forms obtained by the recording device through various sensors and collection means in the target recording scene. The multimedia data includes one or more of audio data, video data and image data.

[0181] Specifically, the multimedia data can include human voice, music, environmental sound effects, etc. sound signals, temperature, humidity, etc. physical quantity information collected by various sensors, etc.

[0182] For example, the user wears the recording device on the body and starts the recording device during the process of going out for a trip; the recording device collects multimedia data such as video, image and audio through the data collection module to record the scenery along the way, interesting human events encountered, characteristic foods tasted, etc.​

[0183] At step 220, in response to the triggered marking operation, the marking information corresponding to the marked target multimedia data is determined.

[0184] The marking operation refers to a specific interaction behavior of the user with the recording device; and is used to instruct the recording device to mark the currently collected multimedia data.

[0185] In some embodiments, the operation mode of the marking operation can include at least one of a knocking operation, a touch operation, a control pressing operation, an operation of inputting a target voice instruction, and an operation of a target action on the recording device.

[0186] The knocking operation on the recording device refers to an interaction behavior in which the user knocks the recording device in a rhythmic or specific manner to convey a marking instruction to the recording device. Specifically, the knocking operation includes at least one of an operation of a preset number of knocks, an operation of a preset knocking frequency, and an operation of a preset knocking force.

[0187] For example, when the user records content of interest and / or importance, the user can knock the recording device a preset number of times, and / or knock the recording device at a specific time interval, and / or knock the recording device with a force greater than or equal to a preset force threshold, to trigger the marking operation on the recording device.

[0188] The touch operation refers to a preset action of clicking, sliding, or long pressing on a touch screen of the recording device directly using a finger or a special touch pen, so that the recording device determines whether the touch is a triggered marking operation according to parameters such as the position, trajectory, and duration of the touch.

[0189] The control pressing operation refers to a preset operation of pressing, rotating, or sliding a specific physical control or virtual control, such as a button or a knob, provided on the recording device, to trigger the marking operation.

[0190] The operation of inputting a target voice instruction refers to speaking a specific voice instruction by the user through the voice recognition function of the recording device, and the recording device converts the voice into text and matches the text with a preset instruction. If the matching is successful, the marking is performed.

[0191] The operation of a target action refers to detecting a specific action, such as rapidly shaking the device or making a specific gesture, made by the user using an acceleration sensor, a gyroscope, or other sensors built-in the recording device. When the action matches a preset model to a threshold value, the action is determined as a triggered marking operation.

[0192] In some embodiments, the marked target multimedia data contains the content of interest to the user. During the process of using the recording device to record multimedia, if the user records the content of interest and / or importance, and expects to mark the currently recorded multimedia data, the user will perform a marking operation on the recording device, so that the recording device determines the marking information corresponding to the marked target multimedia data, that is, determines the content of interest to the user, in response to the triggered marking operation.

[0193] The marking information corresponding to the marked target multimedia data refers to information used to locate or record the marked target multimedia data such as a specific picture, video, audio, etc.

[0194] Optionally, the marking information includes marking time information; and / or, the marking information includes marking content information.

[0195] The marking time information refers to information capable of explicitly indicating the time when the marking operation occurs, or accurately locating the specific position time point in the target multimedia data.

[0196] Specifically, the marking time information can be absolute time, for example, specific year, month, day, hour, minute, and second, such as "2024-10-20 15:20:35", indicating the time when the marking operation occurs in real time. The marking time information can also be relative time, for example, the time after the recording device starts recording, such as "01:15:20", indicating that the marking point is at the 1st hour 15 minutes and 20 seconds after the recording device starts recording.

[0197] The marking content information refers to information used to describe the content contained in the target multimedia data, or a specific multimedia data segment collected by the data collection module.

[0198] Specifically, the marking content information can be a short label word. The marking content information can also be a detailed textual description. The marking content information can also be a specific symbol or professional term, etc.

[0199] In step 230, at least part of the multimedia data collected by the data collection module and the marking information are sent to the electronic device, so that the electronic device analyzes the target multimedia data in the at least part of the multimedia data and the marking information according to the event recognition model to obtain first recording event information corresponding to the marking information.

[0200] The first recording event information refers to information about a recording event in the target multimedia data pointed by the mark information. The first recording event information is used for display on the terminal device. Specifically, if the mark information is a time point, the first recording event information can be a summary of an event occurring in the target multimedia data at the time point. For example, at least part of the multimedia data is a performance of a welcome party, and the mark information is a time point corresponding to the third program, and the first recording event information can include a summary of the performance content of the third program in the welcome party.

[0201] Optionally, the recording event information can include, but is not limited to, event theme (a brief description of an event occurring in the target multimedia data), time information (explicit time point or time period of event occurrence), related elements (such as involved characters, objects, scenes, etc.).

[0202] In some embodiments, after obtaining the mark information, the recording device can send at least part of the multimedia data collected by the data collection module and the mark information to the electronic device. After receiving at least part of the multimedia data and the mark information sent by the recording device, the electronic device analyzes the target multimedia data in at least part of the multimedia data according to the mark information through the event recognition model, obtains the first recording event information corresponding to the mark information, and displays the first recording event information on the terminal device.

[0203] In some embodiments, at least part of the multimedia data is also used by the electronic device to analyze at least part of the multimedia data to obtain one or more second recording event information. This allows the user to obtain the content events contained in at least part of the multimedia data recorded by the recording device while obtaining the mark information, thereby providing the user with more comprehensive information.

[0204] The second recording event information is an event-related description generated by the electronic device based on all the content contained in at least part of the multimedia data, without relying on the mark information. One or more second recording event information covers the key elements of various events occurring in the recording process, which can include the time span, spatial distribution, interaction relationship of participating objects, development trend of the event, etc. For example, during the user's travel, the electronic device obtains multiple second recording event information from the video data collected by the data collection module of the recording device, which can be event descriptions of multiple scenic spots.

[0205] Taking an electronic device as a server as an example, the server is in communication connection with a recording device, and the server is in communication connection with a terminal device. When a user encounters content of interest, the user triggers the recording device through a marking operation. The recording device responds to the marking operation, marks current multimedia data, generates marking information, and sends the collected multimedia data and the marking information to the server. The server analyzes the received multimedia data according to the received marking information according to an event recognition model to obtain first recording event information corresponding to the marking information; the server sends the first recording event information to the terminal device, and the terminal device displays the first recording event information.

[0206] Taking an electronic device as a terminal device as an example, the recording device can be directly connected in communication with the terminal device. After the recording device generates the marking information, the recording device directly sends the collected multimedia data and the marking information to the terminal device. The terminal device analyzes the received multimedia data according to the received marking information according to an event recognition model to obtain first recording event information corresponding to the marking information, and displays the first recording event information.

[0207] Taking an electronic device as a terminal device as an example, the recording device and the terminal device are connected through a cloud server as a medium. After the recording device generates the marking information, the recording device sends the collected multimedia data and the marking information to the server. The server forwards the multimedia data and the marking information sent by the recording device to the terminal device. The terminal device analyzes the multimedia data according to the marking information sent by the server according to an event recognition model to obtain first recording event information corresponding to the marking information, and displays the first recording event information.

[0208] In some embodiments, due to the actual situation of the target recording scene in which the user is located, there are many variables, including physical environment, personnel flow, device distribution, network infrastructure and other variables in the target recording scene, so that the stability, bandwidth and delay of network connection and other parameters are in dynamic change; for example, in the scene that the user participates in a large outdoor music festival and performs video recording, as the performance proceeds, a large number of audiences gather and disperse, the load of the temporarily built network base station in the surrounding fluctuates constantly, and the network connection of the recording device and the electronic device changes due to factors such as changes in personnel density and enhanced signal interference. The recording device can determine a target electronic device according to the network connection, and send at least part of the multimedia data collected by the data acquisition module and the marking information to the target electronic device.

[0209] Specifically, in the case that the network connection state is stable and the bandwidth is sufficient, and there are multiple electronic devices that can receive data, the recording device can select any one of the electronic devices as the target electronic device; in the case that the network connection state is stable or the bandwidth can meet the real-time transmission requirement, and the terminal device stores an event recognition model, the recording device can take the terminal device as the target electronic device; in the case that the network connection state is unstable or the bandwidth is limited, or the terminal device has insufficient processing capability to guarantee complete reception of data, or the terminal device does not store the event recognition model, the recording device can take the server as the target electronic device.

[0210] For example, taking audio data as multimedia data, the recording device can select a recording device, and the data acquisition module of the recording device corresponds to a microphone on the recording device. When the user attends a large-scale meeting, the recording device can be worn before the meeting starts, and the recording function is started, at which time the microphone starts to collect audio data. Since the content of the whole process of the large-scale meeting is rich and varied, when the artificial intelligence summarizes or records the content of the whole process of the meeting, the summary or record result may not be the content of the meeting that the user is interested in or considers important due to randomness and uncertainty.

[0211] In the embodiments of the present application, during the meeting, if the user hears the content that he is interested in or considers important, or the speech of a specific person, the user can trigger the recording device through a convenient marking operation such as continuous tapping. The recording device responds to the marking operation, marks the current audio data, generates marking information corresponding to the current audio data, and sends the audio data and the marking information to the electronic device. The electronic device uses the event recognition model to analyze the marked audio data according to the marking information, summarizes and analyzes the audio data that the user is interested in or considers important, and further generates first recording event information that meets the user's demand.

[0212] For example, taking video data as multimedia data, the recording device can be a video recording device, and the data acquisition module is a camera. When the user goes out for a long trip, the video recording device is started, and the camera records the user's travel. Since there are many unpredictable factors during the trip, such as unpredictable weather, temporary adjustment of travel schedule, unexpected situations, etc., the final video recording device records the travel video content, which is miscellaneous and lacks emphasis. When the artificial intelligence summarizes or extracts key information from the whole process of the video content, it is often difficult to accurately identify the content that the user is really interested in or considers important due to the randomness and uncertainty of the data itself.

[0213] In the embodiment of the present application, during the travel, when the user sees a breathtaking view, meets an interesting person or an event occurs, the user can trigger the marking function by pressing a specific mark button on the recording device or other convenient operation. The recording device responds to the marking operation, marks the currently captured video data, generates corresponding marking information, and sends the video data and marking information to the electronic device. The electronic device uses the event recognition model to analyze the marked video data according to the marking information, sorts and summarizes the video clips that the user is interested in or considers important, and generates event information of the travel-related video that meets the user's needs, making it convenient for the user to review and share later.

[0214] In the embodiment of the present application, the recording device supports recording in the target recording scene, that is, it supports long-time continuous recording of multimedia data. In the case of long-time continuous recording of multimedia data by the recording device, the user can trigger the marking operation according to his own needs, and the recording device can mark the target multimedia data according to the triggered marking operation. The electronic device can analyze the multimedia data collected by the recording device and the marking information corresponding to the marking operation through the event recognition model, so as to accurately obtain the first recording event information corresponding to the marking information. This can avoid the situation that the result output by the artificial intelligence model does not match the content expected by the user due to the randomness and uncertainty of the artificial intelligence model when analyzing a large amount of multimedia data. The event recognition model in the embodiment of the present application can output the first recording event information expected by the user according to the marking information corresponding to the marking operation triggered by the user, accurately meet the user's needs, and improve the accuracy and reliability of analyzing the multimedia data recorded by the recording device. Moreover, the recording device can support portable multimedia data recording, improving the use convenience of the recording device.

[0215] In one embodiment, as shown in Figure 3 Steps of determining the marking information corresponding to the marked target multimedia data in response to the triggered marking operation can further include steps 302-304.

[0216] Step 302: Obtain the operation triggering time corresponding to the marking operation.

[0217] The operation triggering time refers to the starting moment when the user performs the marking operation, which is accurately recorded in the system time dimension of the recording device.

[0218] In some embodiments, since the event recorded by the target multimedia data has a time continuity, i.e., is a multimedia data in a period of time, in order to clearly define the start and end positions of the event in the multimedia data, the marking operation can include two operations, i.e., a start marking operation and an end marking operation. Through the time period corresponding to the start marking operation and the end marking operation, the recording device can accurately mark the recording content of interest to the user by triggering the operation twice, so that the electronic device can analyze the recording content that the user is really interested in, and improve the accuracy of analyzing the multimedia data recorded by the recording device.

[0219] The start marking operation refers to a marking action performed by the user to mark the start of a specific event or segment in the multimedia data. The recording device starts to record the multimedia data information related to the marking. For example, when the multimedia data is a video of a sports match, the start marking operation is an operation performed by the user at the moment when the player shoots the ball.

[0220] The end marking operation refers to a marking action performed by the user to mark the end of a specific event or segment in the multimedia data. The end marking operation corresponds to the start marking operation and jointly defines a complete event or segment range. For example, in the video of the sports match described above, the end marking operation can be an operation performed by the user after the celebration action of the player ends after the goal is scored; and through the start marking operation and the end marking operation, the target multimedia data can include the video segment related to the shooting of the ball by the player to the celebration of the goal.

[0221] In step 304, the marking time information corresponding to the marked target multimedia data is determined according to the operation time.

[0222] In some embodiments, the recording device can determine the marking time information corresponding to the marked target multimedia data according to the operation time and a preset time length.

[0223] In some embodiments, the marking time information is any one of the following:

[0224] The marking time information is used to indicate a first time period before the operation trigger time;

[0225] The marking time information is used to indicate a second time period after the operation trigger time;

[0226] The marking time information is used to indicate a third time period before the operation trigger time and a fourth time period after the operation trigger time;

[0227] The marking time information is used to indicate a time period between a first operation trigger time corresponding to the start marking operation and a second operation trigger time corresponding to the end marking.

[0228] Optionally, the third time period and the fourth time period may both be preset time lengths. For example, if the preset time length is 5 minutes, then the third time period is 5 minutes long, and the fourth time period is also 5 minutes long. Alternatively, the sum of the lengths of the third time period and the fourth time period is the preset time length. In this case, the specific lengths of the third time period and the fourth time period are not limited. For example, if the preset time length is 5 minutes, the length of the third time period may be 3 minutes, and the length of the fourth time period may be 2 minutes. Alternatively, the length of the third time period may be 1 minute, and the length of the fourth time period may be 4 minutes.

[0229] For example, assuming that the preset time length is 10 minutes and the time lengths of the above-mentioned time periods are the same, the marked time information may be 10 minutes before the operation trigger moment; it may also be 10 minutes after the operation trigger moment; it may also be 10 minutes before the operation trigger moment plus 10 minutes after the operation trigger moment, a total of 20 minutes; it may also be 3 minutes before the operation trigger moment plus 7 minutes after the operation trigger moment, a total of 10 minutes.

[0230] It should be noted that the lengths of the above-mentioned time periods can be equal or different, and are set according to actual conditions and are not limited here.

[0231] In an embodiment of the present application, the recording device obtains the operation trigger moment corresponding to the marking operation and determines the marking time information of the target multimedia data based on this, so as to accurately record the time point of occurrence of the content of interest to the user, facilitate subsequent rapid positioning and review of the multimedia data marked by the user, especially in long-term continuous recording scenarios, and can improve the efficiency of retrieval of multimedia data marked by the user.

[0232] like Figure 4 As shown, in one embodiment, a recording marking method is provided, which can be applied to the above recording device. The method may include the following steps 402 to 406.

[0233] Step 402: When the recording device is in the target recording scene, multimedia data is collected by the data collection module.

[0234] For the description of step 402 , please refer to the description of step 210 in the above embodiment, which will not be repeated here.

[0235] Step 404: Acquire the multimedia data segment corresponding to the marking operation, identify the multimedia data segment, obtain recording key information, and use the recording key information as marking content information.

[0236] The multimedia data segment corresponding to the marking operation refers to a part of multimedia data collected by the data collection module, which is circled according to the triggered marking operation (user interested) in the multimedia data.

[0237] For example, in a two-hour conference video, the participants perform two operations (start marking operation and end marking operation) on the period when a leader expounds important points, and the video content in the period from the start marking operation to the end marking operation is the multimedia data segment corresponding to the marking operation.

[0238] The recording key information refers to the information that can accurately summarize and reflect the core content or important features of the multimedia data segment corresponding to the marking operation.

[0239] Optionally, the recording key information includes at least one of keywords, key sentences, and object information corresponding to a target recording object.

[0240] The keyword refers to a single word with representative and key meaning extracted from the multimedia data segment. For example, in a video segment about the introduction of a science and technology product, the keywords can be "smartphone", "high-definition camera", etc. The number of keywords is not limited here, that is, a multimedia data segment can have one keyword or multiple keywords.

[0241] The key sentence refers to a sentence that can express the core meaning of the multimedia data segment. For example, in a video of a player shooting in a sports match, the key sentence can be "player No. 10 uses a hook to kick the ball into the opponent's goal".

[0242] The object information corresponding to the target recording object refers to the relevant information of the object concerned in the multimedia data segment. Specifically, the object information corresponding to the target recording object can include but is not limited to the vocal color (sound characteristics and emotional expression), appearance (face, figure, dress), and other (behavior, scene) of the target recording object contained in the video data; the vocal color (sound characteristics, emotional atmosphere) and other (language style, background sound effect) of the target recording object in the audio data; the appearance (overall shape, color matching, detail features) and other (position relationship, light and shadow effect) of the target recording object in the image data.

[0243] For example, in a segment of playing in the zoo, the target recording object is a lion, and the object information can include the sound and shape of the lion.

[0244] In some embodiments, the recording device can convert the voice content in the multimedia data segment corresponding to the marking operation into text through a voice recognition algorithm; analyze and extract the text through natural language processing technology to obtain the recording key information.

[0245] Optionally, the recording device can also analyze each frame of image in the multimedia data segment corresponding to the marking operation through an image recognition algorithm, recognize the target recording object, and search in a preset database to obtain the recording key information.

[0246] In some embodiments, the marking content information is used by the electronic device to search for multimedia data matching the recording key information from at least part of the multimedia data as the target multimedia data of the marking according to the recording key information.

[0247] In some embodiments, the marking information can include the marking content information and the marking time information; the recording device can obtain the multimedia data segment corresponding to the marking operation, recognize the multimedia data segment to obtain the recording key information, and take the recording key information as the marking content information; and the marking content information is also used by the electronic device to search for multimedia data matching the recording key information in the multimedia data corresponding to the marking time information as the target multimedia data of the marking according to the recording key information.

[0248] It should be noted that the multimedia data segment corresponding to the marking operation and the target multimedia data of the marking are not necessarily the same multimedia data. The multimedia data segment corresponding to the marking operation is the multimedia data circled by the user through the marking operation, which is locally targeted, has a relatively small and accurate range, and is a specific event or detail. The target multimedia data of the marking is more extensive and can cover multiple multimedia data segments.

[0249] For example, in a monitoring video lasting for several hours, the multimedia data segment corresponding to the marking operation can be only the picture of an abnormal person appearing in several minutes; but the target multimedia data of the marking can be all video pictures containing the abnormal person in the monitoring video lasting for several hours.

[0250] Optionally, the recording device can obtain the multimedia data segment corresponding to the marking operation, take the multimedia data segment as the marking content information. The marking content information is used by the electronic device to recognize the multimedia data segment to obtain the recording key information, and search for multimedia data matching the recording key information from at least part of the multimedia data as the target multimedia data of the marking according to the recording key information.

[0251] Step 406: sending the at least part of the multimedia data collected by the data collection module and the marking content information to the electronic device.

[0252] The related description of step 406 can refer to the related description of step 230 in the above embodiments, which will not be repeated here.

[0253] In some embodiments, the recording device sends the at least part of the multimedia data collected by the data collection module and the tagging content information containing the recording key information to the electronic device after tagging the recording key information as the tagging content information. The electronic device can find, according to the recording key information in the received tagging content information, the multimedia data matching the recording key information from the at least part of the multimedia data as the target multimedia data of tagging; and then perform event analysis on the target multimedia data of tagging through the event recognition model to obtain the first recording event information corresponding to the tagging content information.

[0254] Specifically, after sending the at least part of the multimedia data collected by the data collection module and the tagging content information containing the multimedia data segment to the electronic device. The electronic device identifies the multimedia data segment according to the multimedia data segment in the tagging content information, obtains the recording key information, and finds, according to the recording key information, the multimedia data matching the recording key information from the at least part of the multimedia data as the target multimedia data of tagging; and then performs event analysis on the target multimedia data of tagging through the event recognition model to obtain the first recording event information corresponding to the tagging content information.

[0255] In the embodiments of the present application, the recording device automatically identifies the recording key information in the multimedia data segment corresponding to the tagging operation and takes it as the tagging content information, realizes intelligent content tagging, and the user can quickly generate meaningful tags without manual input, thereby improving the tagging efficiency and accuracy of the multimedia data. Meanwhile, the electronic device can directly locate and extract the target multimedia data from the multimedia data according to the recording key information.

[0256] As shown in FIG. 5, Figure 5 In one embodiment, a recording tagging method is provided, which can be applied to the recording device described above. The method can include the following steps 502-508.

[0257] Step 502: collecting multimedia data through a data collection module when the recording device is in a target recording scene.

[0258] The related description of step 502 can refer to the related description of step 210 in the above-mentioned embodiments, which will not be repeated here.

[0259] Step 504: determining a target tagging mode in response to a triggered tagging operation.

[0260] In some embodiments, the target marking mode can include a first marking mode or a second marking mode; wherein the first marking mode is a mode of marking based on time; and the second marking mode is a mode of marking based on recording content. The first marking mode corresponds to a first marking operation, and the second marking mode corresponds to a second marking operation, wherein the first marking operation is different from the second marking operation.

[0261] Optionally, when the recording device is in the first marking mode, the marking information corresponding to the target multimedia data to be marked is marking time information; and when the recording device is in the second marking mode, the marking information corresponding to the target multimedia data to be marked is marking content information.

[0262] Optionally, the first marking mode can correspond to a plurality of different first marking operations; and the second marking mode can also correspond to a plurality of different second marking operations; wherein each of the first marking operations is different from each of the second marking operations.

[0263] For example, the first marking operation can include continuous tapping for 2 times, tapping according to a specific rhythm (e.g. a rhythm of “fast-slow-fast”), and tapping with a force reaching a first force threshold (e.g. 4N (Newton)); and the second marking operation can include continuous tapping for 3 times, tapping according to another specific rhythm (e.g. a rhythm of “slow-fast-slow”), and tapping with a force reaching a second force threshold (e.g. 7N (Newton)).

[0264] In some embodiments, the recording device can identify the triggered marking operation, and determine the corresponding marking mode according to the identification result. Specifically, if the recording device detects the first marking operation, the recording device determines the target marking mode as the first marking mode in response to the first marking operation; and if the recording device detects the second marking operation, the recording device determines the target marking mode as the second marking mode in response to the second marking operation.

[0265] In some embodiments, the target marking mode can also be set by the electronic device and synchronized to the recording device. By setting the target marking mode by the electronic device and synchronizing the target marking mode to the recording device, the complexity of the recording device can be reduced, so that the recording device can concentrate more on recording and marking, thereby improving the marking accuracy and use convenience of the recording device.

[0266] At step 506, the marking information corresponding to the target multimedia data to be marked is determined according to the target marking mode.

[0267] In some embodiments, the recording device determines the marking information corresponding to the target multimedia data to be marked as marking time information or marking content information according to the target marking mode; the marking time information is determined according to the related description of steps 302-304 above; or the marking content information is determined according to the related description of step 404 above.

[0268] Specifically, if the target marking mode is the first marking mode, the recording device can determine the marking information corresponding to the target multimedia data marked as the marking time information; if the target marking mode is the second marking mode, the recording device can determine the marking information corresponding to the target multimedia data marked as the marking content information.

[0269] In some embodiments, in addition to determining the target marking mode in response to the triggered marking operation, the recording device can receive the mode information sent by the terminal device, the mode information being used to indicate the target marking mode; and determine the marking information corresponding to the target multimedia data marked according to the target marking mode.

[0270] Specifically, the terminal device can determine the target marking mode corresponding to the selection operation of the user on the display page in response to the selection operation; generate the mode information according to the target marking mode, and send the mode information to the recording device, so that the recording device determines the marking information corresponding to the target multimedia data marked according to the target marking mode in the mode information.

[0271] In step 508, the recording device sends the at least part of the multimedia data collected by the data collection module and the marking information to the electronic device.

[0272] The related description of step 508 can refer to the related description of step 230 in the above embodiments, which will not be repeated here.

[0273] In the embodiments of the present application, the recording device can provide a basis for time interception according to the marking time information, so as to quickly locate and obtain the recording data corresponding to the marking time of the user; can provide a guide for content interception according to the marking content information, so as to accurately filter the recording data segment related to the marking time of the user; and the recording device can better cater to the recording data corresponding to the marking time of the user through the above time interception or content interception.

[0274] As shown in FIG. 6, Figure 6 In one embodiment, a recording marking method is provided, which can be applied to the above recording device. The method can include the following steps 602-608.

[0275] In step 602, the recording device collects multimedia data through a data collection module in a target recording scene.

[0276] In step 604, the recording device determines the marking information corresponding to the target multimedia data marked in response to the triggered marking operation.

[0277] The related description of steps 602-604 can refer to the related description of steps 210-220 in the above embodiments, which will not be repeated here.

[0278] In step 606, it is determined whether the preset sending condition is met. If the preset sending condition is met, step 608 is performed. If the preset sending condition is not met, step 602 is performed.

[0279] In some embodiments, the preset sending condition comprises at least one of the following:

[0280] The remaining power of the recording device is less than a power threshold;

[0281] The recording device enters a charging state;

[0282] The time length from the last sending time reaches a cycle time length, and the last sending time is a time when the recording device last sent data and the marking information to the electronic device;

[0283] The sending operation is detected.

[0284] Optionally, the recording device stores the multimedia data and the marking information, continues to collect the multimedia data through the data collection module, and continues to determine the marking information corresponding to the target multimedia data of the new marking in response to the triggered new marking operation, when it is detected that the preset sending condition is not met at present. When the preset sending condition is met next time, all the multimedia data and one or more marking information that are not sent are sent to the electronic device.

[0285] In step 608, at least part of the multimedia data collected by the data collection module and the marking information are sent to the electronic device.

[0286] In some embodiments, when the preset sending condition comprises multiple sending conditions, the recording device sends at least part of the multimedia data collected by the data collection module and the marking information to the electronic device as long as any one of the preset sending conditions is met.

[0287] Specifically, the recording device sends at least part of the multimedia data and the marking information to the electronic device when it is detected that the remaining power is less than the preset power threshold, which can avoid data loss caused by power depletion of the recording device. At the same time, timely sending at least part of the multimedia data and the marking information can also reduce the running burden of the recording device when the power is insufficient, and prolong the continuous recording time of the recording device. For example, the power threshold can be 5%.

[0288] Specifically, the recording device enters the charging state after detecting the charging signal, and then sends at least part of the multimedia data and the marking information accumulated in the recording device to the electronic device, so that the recording device timely sends data and reduces the energy consumption of the recording device when sending data in the non-charging state.

[0289] Specifically, the recording device periodically sends at least part of the multimedia data and marking information to the electronic device when the time elapsed reaches a preset period, starting from the time the recording device last sent at least part of the multimedia data and marking information to the electronic device. This can prevent excessive data accumulation due to the recording device not sending for a long time, and also facilitates the electronic device to obtain the latest multimedia data and marking information in a timely manner. For example, assuming the period is set to 1 day and the recording device last sent at 10:00 am on Monday, then at 10:00 am on Tuesday, the recording device will again send at least part of the multimedia data and marking information to the electronic device.

[0290] Specifically, the recording device can send at least some multimedia data and tag information to the electronic device in response to a triggered send operation. By triggering a preset send operation, the user can prompt the recording device to send the stored multimedia data and tag information to the electronic device, thereby meeting the user's proactive needs and improving the flexibility and controllability of data transmission. For example, a user can "tap" the recording device four times in a row to request the recording device to send data and tag information.

[0291] For the description of step 608 , please refer to the description of step 230 in the above embodiment, which will not be repeated here.

[0292] In an embodiment of the present application, the recording device triggers the sending of multimedia data and marking information by setting preset sending conditions, thereby achieving flexible control of data transmission, avoiding unnecessary frequent transmission causing power consumption loss of the recording device, and affecting the recording time of the recording device. At the same time, when the conditions are met, the recording device can deliver the multimedia data and marking information to the electronic device in a timely and reliable manner, thereby avoiding sending complete long-term recording data to the electronic device at one time, resulting in the recording device and the electronic device being unable to synchronize or the recording device taking too long to analyze the long-term recording data.

[0293] like Figure 7A As shown, in another embodiment, a recording event display method is provided, which can be applied to the above terminal device. The method may include the following steps 702.

[0294] Step 702: Display the first recording event information.

[0295] The first recording event information is obtained by the electronic device through an event recognition model based on target multimedia data in at least part of the multimedia data and the marking information; the at least part of the multimedia data is collected by a data collection module of the recording device in a target recording scene, and is sent to the electronic device; the target recording scene includes a scene in which the recording device continuously records multimedia for a time period greater than a time period threshold; the marking information is determined by the recording device in response to a triggered marking operation, and the marking information is used to indicate the target multimedia data marked; and the electronic device includes a terminal device and / or a server.

[0296] The at least part of the multimedia data is collected by the data collection module of the recording device in a target recording scene; the target recording scene refers to a scene in which the recording device continuously records multimedia for a time period greater than a time period threshold; and the marking information is determined by the recording device in response to a triggered marking operation, and the marking information is used to indicate the target multimedia data marked.

[0297] In some embodiments, the user can carry the recording device in communication connection with the electronic device, and determine that the recording device performs long-time multimedia recording; the recording device determines the marking information corresponding to the target multimedia data marked in response to a marking operation triggered by the user during the process of collecting multimedia data by the data collection module, and sends at least part of the multimedia data and the marking information to the electronic device; and the electronic device receives at least part of the multimedia data and the marking information for further analysis.

[0298] Specifically, the recording device obtains the related description of at least part of the multimedia data and the marking information, which can refer to the related description of steps 210-230 in the above embodiments, and will not be described here.

[0299] The event recognition model can perform automatic event recognition processing on the multimedia data based on an artificial intelligence algorithm.

[0300] Specifically, the marking information can be used to assist the event recognition model to quickly locate the target multimedia data in at least part of the multimedia data; and the marking information can also provide semantic clues about the target multimedia data for the event recognition model.

[0301] For example, during a football match, a user uses a recording device to continuously collect multimedia data such as video and audio, and through marking operations, the recording device marks multiple key time points, such as the time of the opening whistle, the moment of the goal, the moment of the foul, etc. as marking information; at the same time, the video data containing the wonderful offensive clip is used as the target multimedia data; the recording device sends the multimedia data and marking information obtained by the above recording to the electronic device. The electronic device analyzes the target video data marked as the moment of the goal through an event recognition model. In the event recognition model, the target player's action and the position of the football are recognized by the image, and combined with the cheers of the audience in the audio, etc., the first recorded event information containing the performance of the player in this football match is obtained. The first recorded event information can specifically include the time of the player's goal (accurate to the second), the way the goal was scored (such as a header, a hook shot, etc.), an overview of the offensive route before and after the goal, etc.

[0302] In some embodiments, the electronic device is a server, and the server is in communication with the recording device. The server uses an event recognition model to obtain first recording event information based on the multimedia data and tag information sent by the recording device, and transmits the information to the terminal device. The terminal device may receive the first recording event information sent by the server and display the first recording event information.

[0303] In some embodiments, the electronic device is a terminal device, and the terminal device is communicatively connected to the recording device; the terminal device obtains the first recording event information based on the multimedia data and marking information sent by the recording device through the event recognition model, and displays the first recording event information.

[0304] In some embodiments, a server is in communication with a recording device; the recording device sends multimedia data and tag information to the server; the server forwards the multimedia data and tag information to a terminal device. The terminal device uses an event recognition model to obtain first recording event information based on the multimedia data and tag information sent by the server, and displays the first recording event information.

[0305] Optionally, the terminal device may display the first recording event information on the home page of an application corresponding to the recording device, that is, after the user opens the application, he or she can observe the first recording event information corresponding to the mark information.

[0306] In some embodiments, the terminal device may display a first identifier in a display area corresponding to the first recording event information. The first identifier is used to indicate that the first recording event information is the recording event information corresponding to the marking operation. The first identifier may include, but is not limited to, graphics (such as stars, flags, circular identifiers, etc.), colors (such as highlight colors, special contrasting colors, etc.), text (such as specific keywords, custom text, etc.), and animations (such as flashing effects, dynamic icons, etc.).

[0307] Optionally, the shape and / or color of the first mark can be distinctive and bright, so that the terminal device can more intuitively indicate that the display region is the display region of the first recording event information corresponding to the mark information.

[0308] For example, as shown in FIG. 7, in the display page 710 of the terminal device, the region 712 can be used to display the recording time of the target multimedia data corresponding to the first recording event information. The first recording event information is “event A”, and the display region 714 corresponding to “event A” has a “five-point star” mark, which is used to indicate that “event A” is the recording event information corresponding to the user marking operation, i.e., “event A” is the event content that the user is interested in. Figure 7B

[0309] In some embodiments, the terminal device can display a recording event page corresponding to the first recording event information in response to the information viewing operation on the first recording event information, the recording event page corresponding to the first recording event information being used to display the event content corresponding to the first recording event information and / or the event content of the recording event associated with the first recording event information.

[0310] Optionally, the information viewing operation on the first recording event information can include, but is not limited to, performing a touch operation such as single-click, double-click, or long-press on the display region corresponding to the first recording event information; performing a specific gesture sliding operation such as left-right sliding or up-down sliding on the display region corresponding to the first recording event information to trigger the viewing function; triggering the viewing by voice instruction, and the user speaks a specific voice keyword to indicate viewing the first recording event information.

[0311] Optionally, the recording event page corresponding to the first recording event information can be displayed in full screen, for example, the terminal device controls the display page to jump to the recording event page corresponding to the first recording event information in response to the information viewing operation on the first recording event information. The recording event page can also be displayed in a pop-up window, which does not completely block the current display interface, so as to facilitate the user to quickly view the event details, and the user can return to the original interface at any time to perform other operations. The recording event page can also be displayed in a split screen, which divides the screen of the terminal device into multiple regions, one of which is used to display the recording event page, and the remaining regions can retain the content of the original display interface, so as to facilitate the user to view the related information.

[0312] Optionally, the event content corresponding to the recording event information can include a summary of the recording event information, for example, a concise text summarizing the key points, background, main influence, and other key information of the event. The event content can also include a detailed event description of the recording event information, covering the specific time, place, involved person, and detailed steps of the event.​

[0313] As shown in Figure 7C For example, when the user wants to view the event content corresponding to "event A" and / or the event content of the recording event associated with the first recording event information, the user can touch the display area 714 corresponding to "event A", so that the terminal device jumps from the display page 710 to the recording event page 720 of "event A". In the recording event page 720, the event content corresponding to "event A" can be displayed in the display area 722, and the event content corresponding to the recording event "event B" associated with "event A" can be displayed in the display area 724.

[0314] In some embodiments, the terminal device can play the multimedia data corresponding to the first recording event information in response to a recording play operation for the first recording event information.

[0315] For example, as shown in Figure 7D The display area 714 corresponding to "event A" can display a play control 732, a pause control 734 and a volume adjustment control 736. The user can touch the play control 732 to make the terminal device start playing the multimedia data corresponding to "event A". The user can also touch the pause control 734 to make the terminal device pause playing the multimedia data corresponding to "event A". The user can also touch the volume adjustment control 736 to make the terminal device adjust the volume of the playing multimedia data.

[0316] It should be noted that the types and number of controls related to the recording play operation in the display area corresponding to the first recording event information are not limited herein.

[0317] For example, as shown in Figure 7E When the user wants to listen to or watch the multimedia data corresponding to the first recording event information "event A", the user can also touch the display area 714 corresponding to "event A", so that the terminal device jumps from the display page 710 to the play page 740, and plays the multimedia data corresponding to "event A" through the play page 740.

[0318] Optionally, the play page 740 can also be displayed in the form of a pop-up window, or in the form of a split screen, which is not limited herein.

[0319] In an embodiment of the present application, an electronic device receives multimedia data and marking information sent by a recording device, and performs targeted analysis on the target multimedia data and marking information through an event recognition model, thereby accurately obtaining the first recording event information corresponding to the marking information. This can avoid the situation where the results output by the artificial intelligence model do not match the content expected by the user due to randomness and uncertainty in the artificial intelligence model when analyzing a large amount of multimedia data. The first recording event information can be output according to the marking information corresponding to the marking operation triggered by the user, so that the first recording event information displayed by the terminal device can accurately meet the user's needs, thereby improving the accuracy and reliability of the analysis of the multimedia data recorded by the recording device.

[0320] like Figure 8A As shown, in another embodiment, a recording event display method is provided, which can be applied to the above terminal device. The method may include the following steps 802 to 806.

[0321] Step 802: In response to the recorded search operation, obtain the input search content.

[0322] Optionally, the recorded search operation may include but is not limited to a touch operation on a special search control, a confirmation operation on the input search content, initiating a search through a voice command, etc.

[0323] For example, users can trigger the recording search operation by single-clicking, double-clicking, or long pressing the search button or search icon set in a specific area, or clicking confirmation buttons such as "Confirm" and "Search", or pressing the Enter key on the keyboard, or speaking specific voice keywords.

[0324] The search content may include but is not limited to keywords of the recorded event (such as the subject of the event, the names of the people involved, the key locations where it occurred, etc.), the time range of the recorded event (such as the specific start date and end date, or relative time expression, etc.), the type of recorded event, related information of the recorded event, etc.

[0325] Step 804: Search at least part of the multimedia data according to the search content to obtain multimedia data matching the search content.

[0326] In some embodiments, the terminal device can obtain multimedia content corresponding to at least part of the multimedia data; then calculate the similarity between each multimedia content and the search content, and take the multimedia data corresponding to the target multimedia content whose similarity is greater than the pixel point threshold as the multimedia data matching the search content.

[0327] Step 806 : Analyze the matched multimedia data using the event recognition model to obtain third recording event information, and display the third recording event information.

[0328] The third recording event information is obtained by the event recognition model in step 806. The description of the third recording event information can be obtained by the event recognition model in step 704 in the above embodiment, which will not be repeated here.

[0329] As shown in FIG. 8, the display page 810 of the terminal device includes an input box 812 and a search control 814. The user can input search content in the input box 812 and touch the search control 814, so that the terminal device obtains the search content in the input box 812 in response to the recording search operation. The terminal device searches at least part of the multimedia data according to the search content, obtains the multimedia data matching the search content, and analyzes the matching multimedia data by the event recognition model to obtain a plurality of third recording event information (event C, event D and event E). In addition, the input box 812 and the search control 814 in the display page 810 of the terminal device are hidden, and three display areas 816 are displayed for displaying event C, event D and event E, respectively. Figure 8B In the embodiments of the present application, the terminal device can respond to the recording search operation to reorganize the third recording event information related to the search content in at least part of the multimedia data, and deeply analyze the matching data by the event recognition model to extract and display the third recording event information. The user can quickly find the information point (search content) required by the user from a large amount of multimedia data by intelligent analysis (event recognition model), improve the efficiency and accuracy of information searching, and meet the user's demand for quick search of specific content.

[0330] As shown in FIG. 9, in another embodiment, a recording event display method is provided, which can be applied to the terminal device described above. The method can include the following step 902.

[0331] Figure 9A Step 902, display one or more second recording event information.

[0332] Step 902, display one or more second recording event information.

[0333] Optionally, the description of the second recording event information is obtained by the event recognition model. The description of the first recording event information obtained by the event recognition model in the above embodiment can be referred to, which will not be repeated here.

[0334] ​In some embodiments, since the first recording event information is the recording event information corresponding to the target multimedia data that the user is interested in, and the second recording time information is the recording event information summarized by the electronic device, the display area corresponding to the first recording event information can be located above the display area corresponding to one or more second recording event information, so as to highlight the first recording event information, so that the user can pay attention to the desired first recording event information at the first time.

[0335] For example, Figure 9B As shown, in the display page 910 of the terminal device, area 912 can be used to display the recording time of at least part of the multimedia data received by the terminal device; the first recording event information is "Event A", and the second recording event information includes "Event B" and "Event C". There is a "five-pointed star" logo in the display area 914 corresponding to "Event A", which is used to indicate that "Event A" is the recording event information corresponding to the user marking operation; the display area 916 of "Event B" and the display area 918 of "Event C" are both located below the display area 914 of the first recording event information "Event A".

[0336] Optionally, the display order of the one or more pieces of second recording event information located below the display area corresponding to the first recording event information is not limited herein.

[0337] In some embodiments, the terminal device can obtain the start recording time corresponding to the first recording event information, and the start recording time corresponding to one or more second recording event information; and display the first recording event information and one or more second recording event information in sequence according to the time sequence of the start recording time.

[0338] Specifically, if Figure 9C As shown, on the display page 910 of the terminal device, area 912 can be used to display the recording time of at least part of the multimedia data received by the terminal device; wherein, the start recording time corresponding to "event B" is earlier than the start recording time corresponding to "event A", and the start recording time corresponding to "event A" is earlier than the start recording time corresponding to "event C"; therefore, on the display page 910 of the terminal device, the display area 916 of "event B" is located above the display area 914 of "event A", and the display area 918 of "event C" is located below the display area 914 of "event A".

[0339] In an embodiment of the present application, in addition to displaying the first recording event information corresponding to the marking information, multiple second recording event information obtained by comprehensively analyzing at least part of the received multimedia data through the event recognition model will also be displayed, so that the user can obtain the content events contained in at least part of the multimedia data recorded by the recording device at the same time as obtaining the marking information, thereby displaying more comprehensive information to the user.

[0340] like Figure 10A As shown, in another embodiment, a recording event display method is provided, which can be applied to the above terminal device. The method may include the following steps 1002 to 1004.

[0341] Step 1002: Display first recording event information in a first display style.

[0342] Step 1004: display one or more second recording event information in a second display style, where the first display style is different from the second display style.

[0343] The display style may include but is not limited to image style, font style, layout style, dynamic effect style, etc.

[0344] Among them, image styles may include different icon shapes, icon styles, icon sizes, picture themes, picture clarity, picture display methods (such as tiling, scaling, cropping, etc.), picture borders, picture display effects (such as shadows, rounded corners, etc.), etc.

[0345] The font style may include font color, font type (such as Kaiti, Songti, etc.), font size, font style (such as bold, italic, underline, etc.), etc.

[0346] Layout styles may include arrangement methods (such as horizontal arrangement, vertical arrangement, grid arrangement, etc.), spacing settings, partition design, etc.

[0347] Dynamic effect styles may include animation effects (such as fade in, fade out, zoom, move, etc.), transition effects (such as mouse hover, click, etc.), interactive feedback effects (such as changing element color, size or displaying additional information when the mouse hovers, changing element status after clicking, etc.), etc.

[0348] Optionally, the second display styles corresponding to different second recording event information may be different, but all second display styles are different from the first display style.

[0349] In some embodiments, the recorded event information includes an event subject, the first display style includes a first font style corresponding to the first event subject of the first recorded event information, and the second display style includes a second font style corresponding to the second event subject of the second recorded event information; the first font style is different from the second font style.

[0350] The event theme refers to the core content, core purpose or main features contained in the recorded event information.

[0351] For example, Figure 10BAs shown in FIG. 10, on the display page 1010 of the terminal device, the area 1012 can be used to display the recording time of at least part of the multimedia data received by the terminal device; in the display area 1014 corresponding to the first recording event information "event A", the first event theme "math class" of the "event A" is displayed in the first font style of cursive script; in the display area 1016 corresponding to the second recording event information "event B" and the display area 1018 corresponding to "event C", the second event theme "physical class" and "music class" are displayed in the second font style of Songti.

[0352] Optionally, the first display style includes a first event image, and the second display style includes a second event image.

[0353] In the display area corresponding to the first recording event information, a first event image corresponding to the first recording event information is displayed; in the display area corresponding to each second recording event information, a second event image corresponding to each second recording event information is displayed.

[0354] Optionally, the second event images corresponding to different second recording event information can be the same or different. The second event image corresponding to each second recording event information can be associated with the event content of each second recording event information.

[0355] For example, Figure 10C As shown in FIG. 10, on the display page 1010 of the terminal device, the area 1012 can be used to display the recording time of at least part of the multimedia data received by the terminal device; assuming that the "event A" includes the shopping process of the user, the "event B" includes the process of the user playing the computer, and the "event C" includes the process of the user singing. The first event image can be displayed in the display area 1014 corresponding to the "event A" to represent shopping; the second event image can be displayed in the display area 1016 corresponding to the "event B" to represent playing the computer; and the second event image can be displayed in the display area 1018 corresponding to the "event C" to represent singing.

[0356] Optionally, the above-mentioned multiple different display styles can appear at the same time, that is, the first display style can include the font type of cursive script and the first event image at the same time; and the second display style can include the font type of Songti and the second event image at the same time.

[0357] In the embodiment of the present application, the terminal device displays the first recording event information corresponding to the mark information in a display manner different from other second recording event information, which can strengthen the importance of the recording event information marked by the user through visual differentiation, and highlight the first recording event information.

[0358] For example, Figure 11AAs shown, in another embodiment, a recording event display method is provided, which can be applied to the terminal device described above. The method can include the following steps 1102 to step 1104.

[0359] Step 1102, analyzing the first recording event information and one or more second recording event information, and determining one or more target second recording event information associated with the first recording event information from the one or more second recording event information.

[0360] In some embodiments, the recording event information can include a text description. The terminal device can map the text description in the first recording event information and the one or more second recording event information into a numerical vector, obtain a first vector corresponding to the first recording event information and a second vector corresponding to each second recording event information; calculate the similarity between the first vector and each second vector, and take the second recording event information corresponding to the second vector with a similarity greater than an association similarity threshold as one or more target second recording event information associated with the first recording event information.

[0361] Optionally, the method of mapping the text description into a numerical vector that can be used by the terminal device includes but is not limited to the bag-of-words model, the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm or the word embedding model (such as Word2Vec, BERT, etc.).

[0362] Optionally, the similarity calculation method that can be used by the terminal device includes cosine similarity, Euclidean distance, etc. Step 1104, displaying a second identifier in the display area corresponding to each target second recording event information.

[0363] The second identifier is used to indicate that the corresponding target second recording event information is associated with the first recording event information. It should be noted that the second identifier needs to be distinguished from the first identifier described above, so as to avoid that the user cannot distinguish the first recording event information from the target second event information.

[0364] For example, Figure 11B As shown, on the display page 1110 of the terminal device, the area 1112 can be used to display the recording time of at least part of the multimedia data received by the terminal device; "event A" is the first recording event information, and the first identifier "five-star" is displayed in the display area 1114 corresponding to "event A"; assuming that "event C" is the target second recording event information associated with "event A", the second identifier (the text identifier "related to event A") is displayed in the display area 1118 corresponding to "event C", which can directly determine the associated event of "event A"; and no second identifier is displayed in the display area 1116 corresponding to "event B".

[0365] In some embodiments, one or more target second recording event information has different display styles; the display style of the target second recording event information is determined according to the degree of association between the target second recording event information and the first recording event information.

[0366] For example, Figure 11C As shown, on the display page 1110 of the terminal device, area 1112 can be used to display the recording time of at least part of the multimedia data received by the terminal device; assuming that "Event C" is the target second recording event information associated with "Event A", and "Event B" is not the target second recording event information, then when the font size used in the display area 1114 of "Event A" is "12pt (Point, points)", the font size used in the display area 1116 of "Event B" is "8pt", and the font size used in the display area 1118 of "Event C" is "10pt", that is, the font size of "Event C" is closer to the font size of "Event A" than that of "Event B".

[0367] In an embodiment of the present application, the terminal device filters out the target second recording event information associated with the marking information from the second recording event information, and adds a second identifier in its display area, which can intuitively display the association relationship between each recording event information through visual means, thereby improving the visibility of the terminal device display page.

[0368] like Figure 12A As shown, in another embodiment, a recording event display method is provided, which can be applied to the above terminal device. The method may include the following steps 1102 to 1104.

[0369] Step 1202: Obtain historical marking recording event information.

[0370] The historically marked recording event information refers to first recording event information corresponding to the marking information sent by the recording device to the electronic device within a historical time period.

[0371] In some embodiments, if in a historical time period, when sending marking information to an electronic device, the recording device determines the first recording event information corresponding to the marking information and stores it locally, the terminal device can obtain the historical marking recording event information from the local database or memory.

[0372] Optionally, there is no limit to the number of historically marked recording event information obtained by the terminal device. The terminal device can associate the current recording event information with multiple historically marked recording event information, thereby connecting the content of interest to the user over a period of time, which helps the user organize recording events.

[0373] Step 1204, analyze the association between the first recording event information and one or more second recording event information and the historical marked recording event information respectively, to determine one or more fourth recording event information associated with the historical marked recording event information.

[0374] The related description of determining one or more fourth recording event information associated with the historical marked recording event information from the first recording event information and one or more second recording event information in step 1204 can refer to the related description of determining one or more target second recording event information associated with the first recording event information from one or more second recording event information in step 1102 of the above-mentioned embodiment, which will not be repeated here.

[0375] Step 1206, display the third identifier in the display area corresponding to each fourth recording event information.

[0376] The third identifier is used to indicate that the corresponding fourth recording event information is associated with the historical marked recording event information. It should be noted that the third identifier also needs to be distinguished from the first identifier and the second identifier described above.

[0377] For example, as shown in FIG. 12, the display page 1210 of the terminal device includes a display area 1212 for displaying the recording time of at least part of the multimedia data received by the terminal device, a display area 1214 for displaying the first recording event information, a display area 1216 for displaying the second recording event information, and a display area 1218 for displaying the third recording event information. Figure 12B For example, as shown in FIG. 12, the display page 1210 of the terminal device includes a display area 1212 for displaying the recording time of at least part of the multimedia data received by the terminal device, a display area 1214 for displaying the first recording event information, a display area 1216 for displaying the second recording event information, and a display area 1218 for displaying the third recording event information.

[0378] In the embodiments of the present application, by analyzing the potential association between the first recording event information and the second recording event information and the historical marked recording event information, and adding the third identifier in the display area of the associated fourth recording event information, the current recording event information can be associated with the historical marked information of the user, thereby displaying the continuity of the event context, which is beneficial to the subsequent recording event information processing.

[0379] For example, as shown in FIG. 12, the display page 1210 of the terminal device includes a display area 1212 for displaying the recording time of at least part of the multimedia data received by the terminal device, a display area 1214 for displaying the first recording event information, a display area 1216 for displaying the second recording event information, and a display area 1218 for displaying the third recording event information.Figure 13 As shown in one embodiment, a recording marking apparatus 1300 is provided, which can be applied to the recording device described above. The recording marking apparatus 1300 can include a recording module 1310, a marking module 1320, and a sending module 1330.

[0380] The recording module 1310 is configured to, when the recording device is in a target recording scene, collect multimedia data by a data collection module, the target recording scene including a scene in which the recording device continuously records multimedia for a duration greater than a duration threshold.

[0381] The marking module 1320 is configured to, in response to a triggered marking operation, determine marking information corresponding to the marked target multimedia data.

[0382] The sending module 1330 is configured to send at least part of the multimedia data collected by the collection module and the marking information to an electronic device, so that the electronic device analyzes target multimedia data in the at least part of the multimedia data and the marking information according to an event recognition model to obtain first recording event information corresponding to the marking information; the electronic device includes a terminal device and / or a server, and the first recording event information is used to display on the terminal device.

[0383] Optionally, the marking information includes marking time information; and / or, the marking information includes marking content information.

[0384] In some embodiments, the marking module 1320 is further configured to obtain an operation trigger moment corresponding to the marking operation; and determine, according to the operation moment, marking time information corresponding to the marked target multimedia data.

[0385] Optionally, the marking time information is any one of:

[0386] The marking time information is used to indicate a first time period before the operation trigger moment;

[0387] The marking time information is used to indicate a second time period after the operation trigger moment;

[0388] The marking time information is used to indicate a third time period before the operation trigger moment and a fourth time period after the operation trigger moment.

[0389] Optionally, the marking operation includes a start marking operation and an end marking operation; and the marking time information is used to indicate a time period between a first operation trigger moment corresponding to the start marking operation and a second operation trigger moment corresponding to the end marking operation.

[0390] In some embodiments, the marking module 1320 is further configured to acquire a multimedia data segment corresponding to the marking operation, and identify the multimedia data segment to obtain recording key information, and use the recording key information as the marking content information, and use the marking content information to enable the electronic device to search for multimedia data matching the recording key information from at least part of the multimedia data as the target multimedia data of the marking.

[0391] In some embodiments, the marking module 1320 is further configured to acquire a multimedia data segment corresponding to the marking operation, and use the multimedia data segment as the marking content information, and use the marking content information to enable the electronic device to identify the multimedia data segment to obtain recording key information, and search for multimedia data matching the recording key information from at least part of the multimedia data as the target multimedia data of the marking according to the recording key information.

[0392] Optionally, the recording key information includes at least one of a keyword, a key sentence, and object information corresponding to the target recording object.

[0393] Optionally, the marking content information is used to enable the electronic device to search for multimedia data matching the recording key information from the multimedia data corresponding to the marking time information as the target multimedia data of the marking according to the recording key information.

[0394] In some embodiments, the marking module 1320 is further configured to determine a target marking mode in response to the triggered marking operation, and the target marking mode includes a first marking mode or a second marking mode, the first marking mode is a mode of marking based on time, and the second marking mode is a mode of marking based on recording content, and determine the marking information corresponding to the target multimedia data of the marking according to the target marking mode.

[0395] Optionally, the first marking mode corresponds to a first marking operation, and the second marking mode corresponds to a second marking operation, and the first marking operation is different from the second marking operation.

[0396] In some embodiments, the marking module 1320 is further configured to determine the target marking mode as the first marking mode in response to the first marking operation if the first marking operation is detected, and determine the target marking mode as the second marking mode in response to the second marking operation if the second marking operation is detected.

[0397] Optionally, the operation mode of the marking operation includes at least one of a knocking operation, a touch operation, a control pressing operation, an operation of inputting a target voice instruction, and an operation of a target action on the recording device.

[0398] Optionally, the knocking operation includes at least one of an operation of a preset number of knocks, an operation of a preset knocking frequency, and an operation of a preset knocking force.

[0399] In some embodiments, the marking module 1320 is further configured to receive mode information sent by the terminal device, the mode information being used to indicate a target marking mode; and determine marking information corresponding to the target multimedia data to be marked according to the target marking mode.

[0400] In some embodiments, the sending module 1330 is further configured to send the at least part of the multimedia data collected by the data collection module and the marking information to the electronic device after the marking information is obtained.

[0401] In some embodiments, the sending module 1330 is further configured to send the at least part of the multimedia data collected by the data collection module and the marking information to the electronic device if a preset sending condition is met.

[0402] Optionally, the preset sending condition comprises at least one of the following:

[0403] a remaining power of the recording device is less than a power threshold;

[0404] the recording device enters a charging state;

[0405] a time length from a last sending time reaches a cycle time length, the last sending time being a time when the recording device last sent data and marking information to the electronic device;

[0406] a sending operation is detected.

[0407] Optionally, the at least part of the multimedia data is further used for the electronic device to analyze the at least part of the multimedia data to obtain one or more second recording event information.

[0408] Optionally, the multimedia data comprises one or more of audio data, video data and image data.

[0409] In the embodiment of the present application, the recording device supports recording in a target recording scene, that is, supports long-time continuous recording of multimedia data. In the case of long-time continuous recording of multimedia data by the recording device, the user can trigger a marking operation according to the user's own needs, and the recording device can mark the target multimedia data according to the triggered marking operation. The electronic device can analyze the multimedia data collected by the recording device and the marking information corresponding to the marking operation through the event recognition model, so as to accurately obtain the first recording event information corresponding to the marking information. This can avoid the situation that the result output by the artificial intelligence model does not match the content expected by the user due to the randomness and uncertainty of the artificial intelligence model when analyzing a large amount of multimedia data. The event recognition model in the embodiment of the present application can output the first recording event information expected by the user according to the marking information corresponding to the marking operation triggered by the user, accurately meet the user's needs, and improve the accuracy and reliability of analyzing the multimedia data recorded by the recording device. Moreover, the recording device can support portable multimedia data recording, improving the use convenience of the recording device.

[0410] As shown in FIG. 14, in one embodiment, a recording event display apparatus 1400 is provided, which can be applied to the terminal device described above. The recording event display apparatus 1400 can include a receiving module 1410, an identifying module 1420, and a display module 1430. Figure 14

[0411] The receiving module 1410 is configured to receive at least part of the multimedia data and the marking information sent by the recording device. The at least part of the multimedia data is collected by the data collection module of the recording device in the target recording scene. The target recording scene includes a scene in which the recording device continuously records multimedia data for a time period greater than a time threshold. The marking information is determined by the recording device in response to the triggered marking operation, and the marking information is used to indicate the target multimedia data marked.

[0412] The identifying module 1420 is configured to analyze the target multimedia data in the at least part of the multimedia data and the marking information through an event recognition model to obtain first recording event information corresponding to the marking information.

[0413] The display module 1430 is configured to display the first recording event information.

[0414] In some embodiments, the display module 1430 is further configured to display a first identifier in a display area corresponding to the first recording event information, and the first identifier is used to indicate that the first recording event information is the recording event information corresponding to the marking operation.

[0415] In some embodiments, the recording event display apparatus 1400 further includes a viewing module, a searching module, and a playing module. In some embodiments, the recording event display apparatus 1400 further includes a viewing module, a searching module, and a playing module.

[0416] The viewing module is configured to display a recording event page corresponding to the first recording event information in response to an information viewing operation for the first recording event information, the recording event page corresponding to the first recording event information being configured to display event content corresponding to the first recording event information and / or being configured to display event content of a recording event associated with the first recording event information.

[0417] The searching module is configured to obtain input search content in response to a recording search operation, search at least part of the multimedia data according to the search content to obtain multimedia data matching the search content, analyze the matching multimedia data by using the event recognition model to obtain third recording event information, and display the third recording event information.

[0418] The playing module is configured to play multimedia data corresponding to the first recording event information in response to a recording playing operation for the first recording event information.

[0419] In some embodiments, the identifying module 1420 is further configured to analyze at least part of the multimedia data by using the event recognition model to obtain one or more second recording event information.

[0420] In some embodiments, the display module 1430 is further configured to display the one or more second recording event information.

[0421] Optionally, the display area corresponding to the first recording event information is located above the display areas corresponding to the one or more second recording event information respectively.

[0422] In some embodiments, the display module 1430 is further configured to obtain a starting recording time corresponding to the first recording event information and starting recording times corresponding to the one or more second recording event information respectively, and display the first recording event information and the one or more second recording event information in a time sequence of the starting recording times.

[0423] In some embodiments, the display module 1430 is further configured to display the first recording event information in a first display style and display the one or more second recording event information in a second display style, the first display style being different from the second display style.

[0424] Optionally, the recording event information includes an event theme, the first display style includes a first font style corresponding to a first event theme of the first recording event information, and the second display style includes a second font style corresponding to a second event theme of the second recording event information, the first font style being different from the second font style.

[0425] Optionally, the first display style includes a first event image, and the second display style includes a second event image.

[0426] In some embodiments, the display module 1430 is further configured to display a first event image corresponding to the first recording event information in a display area corresponding to the first recording event information, and display a second event image corresponding to each second recording event information in a display area corresponding to the second recording event information.

[0427] In some embodiments, the display module 1430 is further configured to analyze the first recording event information and the one or more second recording event information, determine one or more target second recording event information associated with the first recording event information from the one or more second recording event information, and display a second identifier in a display area corresponding to each target second recording event information, where the second identifier is used to indicate that the corresponding target second recording event information is associated with the first recording event information.

[0428] Optionally, the display styles of the one or more target second recording event information are different, and the display style of the target second recording event information is determined according to the association degree between the target second recording event information and the first recording event information.

[0429] In some embodiments, the display module 1430 is further configured to obtain historical recording event information, analyze the association relationship between the first recording event information and the one or more second recording event information and the historical recording event information respectively, determine one or more fourth recording event information associated with the historical recording event information, and display a third identifier in a display area corresponding to each fourth recording event information, where the third identifier is used to indicate that the corresponding fourth recording event information is associated with the historical recording event information.

[0430] In the embodiments of the present application, the electronic device receives the multimedia data and the marking information sent by the recording device, and analyzes the target multimedia data and the marking information through the event recognition model, so as to accurately obtain the first recording event information corresponding to the marking information. The randomness and uncertainty of the artificial intelligence model in analyzing a large amount of multimedia data can be avoided. When the result output by the artificial intelligence model does not match the content expected by the user, the first recording event information can be output according to the marking information corresponding to the marking operation triggered by the user. The first recording event information displayed by the terminal device can accurately meet the needs of the user, and the accuracy and reliability of analyzing the multimedia data recorded by the recording device are improved.

[0431] Figure 15 FIG. 1 is a structural block diagram of a recording device in an embodiment. As shown in FIG. 1, the recording device includes a recording module 101, a marking module 102, a storage module 103, a communication module 104, and a processor 105. Figure 15As shown, the recording device 1500 may include one or more of the following components: a processor 1510, and a memory 1520 coupled to the processor 1510, wherein the memory 1520 may store one or more computer programs, and the one or more computer programs may be configured to implement the recording marking method described in the above embodiments when executed by one or more processors 1510.

[0432] The processor 1510 may include one or more processing cores. The processor 1510 connects various components within the entire recording device 1500 using various interfaces and lines. The processor 1510 executes various functions of the recording device 1500 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1520 and calling data stored in the memory 1520.

[0433] The memory 1520 may include random access memory (RAM) or read-only memory (ROM). The memory 1520 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1520 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, and the like. The data storage area may also store data created by the recording device 1500 during use.

[0434] It can be understood that the recording device 1500 may include more or fewer structural elements than those in the above structural block diagram, for example, including a power supply, input buttons, a camera, a speaker, a screen, an RF (Radio Frequency) circuit, a Wi-Fi (Wireless Fidelity) module, a Bluetooth module, a sensor, etc., and is not limited here.

[0435] Figure 16 FIG. 1 is a block diagram of a terminal device in one embodiment. Figure 16 As shown, the terminal device 1600 may include one or more of the following components: a processor 1610, and a memory 1620 coupled to the processor 1610, wherein the memory 1620 may store one or more computer programs, and the one or more computer programs may be configured to implement the recording event display method described in the above embodiments when executed by one or more processors 1610.

[0436] The processor 1610 can include one or more processing cores. The processor 1610 connects various parts within the terminal device 1600 by various interfaces and lines, and performs various functions and processes data of the terminal device 1600 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1620, and calling data stored in the memory 1620.

[0437] The memory 1620 can include a random access memory (RAM) and can also include a read-only memory (ROM). The memory 1620 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1620 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can also store data created by the terminal device 1600 in use, etc.

[0438] It can be understood that the terminal device 1600 can include more or fewer structural elements than the above structural block diagram, for example, including a power supply, an input button, a camera, a speaker, a screen, an RF (Radio Frequency) circuit, a Wi-Fi (Wireless Fidelity) module, a Bluetooth module, a sensor, etc., and can also not be limited herein.

[0439] The embodiments of the present application disclose a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the recording mark method applied to a recording device or the recording event display method applied to a terminal device as in the above-mentioned various embodiments.

[0440] The embodiments of the present application disclose a computer program product including a computer program, and the computer program can be executed by a processor to implement the recording mark method applied to a recording device or the recording event display method applied to a terminal device as in the above-mentioned various embodiments.

[0441] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), etc.

[0442] Any reference to storage, memory, database or other medium as used herein can include non-volatile and / or volatile storage. Suitable non-volatile storage can include ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), or flash memory. Volatile storage can include random access memory (RAM), which is used as external cache memory.

[0443] The recording mark method and device, the recording event display method and device, and the equipment disclosed in the embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by using specific examples. The above embodiment descriptions are only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, the specific implementation manners and application ranges can be changed according to the idea of the present application. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A recording marking method, characterized in that: Applied to a recording device, the recording device includes a data acquisition module; the method includes: When the recording device is in a target recording scene, the data collection module collects multimedia data, and the target recording scene includes a scene in which the recording device continuously records multimedia for a time period greater than a time period threshold; In response to the triggered marking operation, determining marking information corresponding to the marked target multimedia data; At least part of the multimedia data and the tag information collected by the data collection module are sent to an electronic device, so that the electronic device analyzes the target multimedia data and the tag information in the at least part of the multimedia data through an event recognition model to obtain first recording event information corresponding to the tag information. The electronic device includes a terminal device and / or a server, and the first recording event information is used to be displayed on the terminal device.

2. The method according to claim 1, characterized in that The marking information includes marking time information; and / or, The tag information includes tag content information.

3. The method according to claim 2, characterized in that The marking information includes marking time information; and the determining, in response to the triggered marking operation, the marking information corresponding to the marked target multimedia data includes: Obtaining the operation triggering time corresponding to the marking operation; The marking time information corresponding to the marked target multimedia data is determined according to the operation moment.

4. The method according to claim 3, characterized in that The marking time information is any one of the following: The marking time information is used to indicate a first time period before the operation triggering moment; The marked time information is used to indicate a second time period after the operation triggering moment; The marked time information is used to indicate a third time period before the operation triggering moment and a fourth time period after the operation triggering moment.

5. The method according to claim 3, characterized in that The marking operation includes a start marking operation and an end marking operation; The marking time information is used to indicate a time period between a first operation triggering moment corresponding to the start marking operation and a second operation triggering moment corresponding to the end marking operation.

6. The method according to claim 2, characterized in that The marking information includes marking content information; and the determining, in response to the triggered marking operation, the marking information corresponding to the marked target multimedia data includes: Obtain a multimedia data segment corresponding to the marking operation, identify the multimedia data segment, obtain recording key information, and use the recording key information as the marking content information. The marking content information is used by the electronic device to search for multimedia data that matches the recording key information from at least part of the multimedia data based on the recording key information, as the marked target multimedia data.

7. The method according to claim 6, characterized in that The method further comprises: Obtain a multimedia data segment corresponding to the marking operation, and use the multimedia data segment as the marking content information. The marking content information is used by the electronic device to identify the multimedia data segment, obtain recording key information, and based on the recording key information, search for multimedia data that matches the recording key information from at least part of the multimedia data as the marked target multimedia data.

8. The method according to claim 6, characterized in that The recording key information includes at least one of keywords, key sentences, and object information corresponding to the target recording object.

9. The method according to claim 6, characterized in that The marking information also includes marking time information; The marking content information is used by the electronic device to search for multimedia data matching the recording key information in the multimedia data corresponding to the marking time information according to the recording key information, and use the multimedia data as the marked target multimedia data.

10. The method according to any one of claims 2 to 9, characterized in that: The determining, in response to the triggered marking operation, marking information corresponding to the marked target multimedia data includes: In response to the triggered marking operation, a target marking mode is determined; the target marking mode includes a first marking mode or a second marking mode; the first marking mode is a time-based marking mode; the second marking mode is a recording content-based marking mode; According to the target marking mode, marking information corresponding to the marked target multimedia data is determined.

11. The method according to claim 10, characterized in that The first marking mode corresponds to a first marking operation, the second marking mode corresponds to a second marking operation, and the first marking operation is different from the second marking operation; The determining of a target marking mode in response to the triggered marking operation includes: If the first marking operation is detected, determining the target marking mode to be the first marking mode in response to the first marking operation; If the second marking operation is detected, the target marking mode is determined to be the second marking mode in response to the second marking operation.

12. The method according to any one of claims 2 to 9, characterized in that: The determining, in response to the triggered marking operation, marking information corresponding to the marked target multimedia data includes: receiving mode information sent by a terminal device, where the mode information is used to indicate a target marking mode; According to the target marking mode, marking information corresponding to the marked target multimedia data is determined.

13. The method according to any one of claims 1 to 9, characterized in that The operation mode of the marking operation includes at least one of a tapping operation, a touch operation, a control pressing operation, an operation of inputting a target voice instruction, and an operation of a target action on the recording device.

14. The method according to any one of claims 1 to 9, characterized in that The sending of at least part of the multimedia data collected by the data collection module and the tag information to the electronic device includes: After acquiring the tag information, at least part of the multimedia data collected by the data collection module and the tag information are sent to the electronic device.

15. The method according to any one of claims 1 to 9, characterized in that The sending of at least part of the multimedia data collected by the data collection module and the tag information to the electronic device includes: If the preset sending condition is met, at least part of the multimedia data collected by the data collection module and the marking information are sent to the electronic device.

16. The method according to claim 15, characterized in that The preset sending condition includes at least one of the following: The remaining battery power of the recording device is less than a battery threshold; The recording device enters a charging state; The time duration from the last sending time reaches the cycle duration, where the last sending time is the time when the recording device last sent data and marking information to the electronic device; A send operation was detected.

17. The method according to claim 1, wherein The at least part of the multimedia data is further used by the electronic device to analyze the at least part of the multimedia data to obtain one or more pieces of second recording event information.

18. The method according to claim 1, wherein The multimedia data includes one or more of audio data, video data and image data.

19. A recording event display method, characterized in that: Applied to a terminal device; the method comprises: Displaying the first recording event information; Among them, the first recording event information is obtained by the electronic device through analysis of the target multimedia data and marking information in at least part of the multimedia data through an event recognition model; the at least part of the multimedia data is collected by the data collection module of the recording device when the recording device is in a target recording scene and sent to the electronic device; the target recording scene includes a scene in which the recording device continuously records multimedia for a time period greater than a time threshold; the marking information is determined by the recording device in response to a triggered marking operation, and the marking information is used to indicate the marked target multimedia data; the electronic device includes the terminal device and / or server.

20. The method according to claim 19, characterized in that The method further comprises: In the display area corresponding to the first recording event information, a first identifier is displayed, where the first identifier is used to indicate that the first recording event information is the recording event information corresponding to the marking operation.

21. The method according to claim 19, wherein The method further comprises: In response to an information viewing operation for the first recording event information, a recording event page corresponding to the first recording event information is displayed. The recording event page corresponding to the first recording event information is used to display the event content corresponding to the first recording event information, and / or to display the event content of the recording event associated with the first recording event information.

22. The method according to claim 19, wherein The method further comprises: In response to the recorded search operation, obtaining input search content; Searching the at least part of the multimedia data according to the search content to obtain multimedia data matching the search content; The matched multimedia data is analyzed by using the event recognition model to obtain third recording event information, and the third recording event information is displayed.

23. The method according to claim 19, wherein The method further comprises: In response to the recording and playing operation on the first recording event information, multimedia data corresponding to the first recording event information is played.

24. The method according to any one of claims 19 to 23, characterized in that: The method further comprises: Analyzing at least a portion of the multimedia data using the event recognition model to obtain one or more pieces of second recording event information; The one or more second recording event information is displayed.

25. The method according to claim 24, characterized in that The display area corresponding to the first recording event information is located above the display areas corresponding to the one or more second recording event information.

26. The method according to claim 24, characterized in that The method further comprises: The start recording time corresponding to the first recording event information and the one or more second recording event information are obtained, and the first recording event information and the one or more second recording event information are displayed in sequence according to the time sequence of the start recording time.

27. The method according to claim 24, characterized in that The method further comprises: displaying the first recording event information in a first display style; The one or more second recording event information are displayed in a second display style, where the first display style is different from the second display style.

28. The method according to claim 27, characterized in that The recorded event information includes an event subject, the first display style includes a first font style corresponding to the first event subject of the first recorded event information, and the second display style includes a second font style corresponding to the second event subject of the second recorded event information; the first font style is different from the second font style.

29. The method according to claim 27, characterized in that The first display style includes a first event image, the second display style includes a second event image, and displaying the first recorded event information according to the first display style includes: Displaying a first event image corresponding to the first recording event information in a display area corresponding to the first recording event information; The displaying of the one or more second recording event information in a second display style includes: In the display area corresponding to each piece of the second recording event information, the second event image corresponding to each piece of the second recording event information is displayed.

30. The method according to claim 24, wherein The method further comprises: analyzing the first recording event information and the one or more second recording event information, and determining one or more target second recording event information associated with the first recording event information from the one or more second recording event information; A second identifier is displayed in a display area corresponding to each target second recording event information, where the second identifier is used to indicate that the corresponding target second recording event information is associated with the first recording event information.

31. The method according to claim 30, wherein The display styles of the one or more target second recording event information are different; the display style of the target second recording event information is determined according to the degree of association between the target second recording event information and the first recording event information.

32. The method according to claim 24, wherein The method further comprises: Get historical marker recording event information; analyzing associations between the first recording event information and the one or more second recording event information and the historically marked recording event information, respectively, to determine one or more fourth recording event information associated with the historically marked recording event information; A third identifier is displayed in a display area corresponding to each fourth recording event information, where the third identifier is used to indicate that the corresponding fourth recording event information is associated with the historical mark recording event information.

33. A recording and marking device, characterized in that: Applied to a recording device, the recording device includes a data acquisition module; The device comprises: a recording module configured to collect multimedia data through the data collection module when the recording device is in a target recording scenario, wherein the target recording scenario includes a scenario in which the recording device continuously records multimedia for a duration greater than a duration threshold; a marking module, configured to determine, in response to a triggered marking operation, marking information corresponding to the marked target multimedia data; A sending module is used to send at least part of the multimedia data collected by the collection module and the marking information to an electronic device, so that the electronic device analyzes the target multimedia data and the marking information in the at least part of the multimedia data through an event recognition model to obtain first recording event information corresponding to the marking information. The electronic device includes a terminal device and / or a server, and the first recording event information is used to be displayed on the terminal device.

34. A recording event display device, characterized in that: Applicable to terminal equipment; the device includes: A display module, configured to display first recording event information; Among them, the first recording event information is obtained by the electronic device through analysis of the target multimedia data and marking information in at least part of the multimedia data through an event recognition model; the at least part of the multimedia data is collected by the data collection module of the recording device when the recording device is in a target recording scene and sent to the electronic device; the target recording scene includes a scene in which the recording device continuously records multimedia for a time period greater than a time threshold; the marking information is determined by the recording device in response to a triggered marking operation, and the marking information is used to indicate the marked target multimedia data; the electronic device includes the terminal device and / or server.

35. A recording device, characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 18.

36. A terminal device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 19 to 32.

37. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 18 or claims 19 to 32 is implemented.

Images