Data processing method, device and electronic device based on edge computing

Abstract

The present invention discloses a data processing method, device and electronic device based on edge computing, including: receiving video data collected by a first edge device, identifying the video data to obtain at least one target entity and scene information; determining the target introduction dimension to be identified for the target entity according to the scene information; searching for text data of the target entity in the target introduction dimension in the local database of the edge gateway; sending the text data to the first edge device, so that the first edge device synchronously displays the corresponding text data when playing the target entity. On the one hand, the determined part of the text data is transferred from the cloud server to the gateway, which reduces the pressure on the cloud server and alleviates the network pressure; on the other hand, by identifying the target entity and scene information in the video data, accurate introduction text is added to the target entity, without the need for users to conduct a secondary search, thereby improving the video consumption experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data processing method, device and electronic device based on edge computing. Background Art

[0002] With the continuous development of Internet technology, people's demand for video content consumption is also increasing. In order to meet consumer demand, more and more edge devices used for video production and consumption are connected to the gateway. The data packets that the gateway needs to upload to the server are getting larger and larger, which puts a lot of pressure on the server.

[0003] On the other hand, during the video production process, if there are entities (animals, people, events, etc.) that users are not familiar with in the video content, either the creator needs to manually add annotations to the entity after the video is recorded, or the user needs to search for the entity after consuming the video content, which reduces the efficiency of video production and interrupts the user's video consumption experience. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, the present invention provides a data processing method, device and electronic device based on edge computing, which can solve or partially solve the above-mentioned technical problems.

[0005] The present invention provides a data processing method based on edge computing, comprising:

[0006] The data processing method based on edge computing is characterized by comprising:

[0007] Receive video data collected by a first edge device, identify the video data to obtain at least one target entity and scene information; determine a target introduction dimension to be identified for the target entity based on the scene information; search for text data of the target entity in the target introduction dimension in a local database of an edge gateway; and send the text data to the first edge device so that the first edge device synchronously displays the corresponding text data when playing the target entity.

[0008] The embodiment of the present invention further provides a data processing device based on edge computing, including:

[0009] An identification module is used to receive video data collected by a first edge device, and identify the video data to obtain at least one target entity and scene information; a first determination module is used to determine the target introduction dimension to be identified of the target entity based on the scene information; a search module is used to search for text data of the target entity in the target introduction dimension in a local database of an edge gateway; and a first sending module is used to send the text data to the first edge device, so that the first edge device synchronously displays the corresponding text data when playing the target entity.

[0010] An embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0011] One or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method based on edge computing as described above.

[0012] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the data processing method based on edge computing as described above is implemented.

[0013] An embodiment of the present invention also provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the data processing method based on edge computing as described above is implemented.

[0014] The data processing method based on edge computing provided by the present invention, on the one hand, transfers a certain part of the text data from the cloud server to the gateway, greatly reducing the pressure on the cloud server and alleviating the network pressure; on the other hand, by identifying the target entity and scene information in the video data, accurate introduction text is added to the target entity, without the need for users to perform a secondary search, thereby improving the user's video consumption experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0016] Figure 1 A flow chart of a data processing method based on edge computing provided by an embodiment of the present invention;

[0017] Figure 2 A flow chart of a data processing method based on edge computing provided by another embodiment of the present invention;

[0018] Figure 3 A flow chart of a data processing method based on edge computing provided by another embodiment of the present invention;

[0019] Figure 4 A schematic diagram of a structure of data processing based on edge computing provided by another embodiment of the present invention;

[0020] Figure 5 A structural diagram of a data processing electronic device based on edge computing provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0023] It should be understood that although the terms first, second, third, etc. may be used to describe the acquisition modules in the embodiments of the present invention, the acquisition modules should not be limited to these terms. These terms are only used to distinguish the acquisition modules from each other.

[0024] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0025] It should be noted that the directional words such as "upper", "lower", "left", and "right" described in the embodiments of the present invention are described at the angles shown in the drawings and should not be understood as limiting the embodiments of the present invention. In addition, in the context, it should also be understood that when it is mentioned that an element is formed "on" or "under" another element, it can not only be formed directly "on" or "under" another element, but also be formed "on" or "under" another element indirectly through an intermediate element.

[0026] Edge computing is a distributed computing model that does not require cloud servers to calculate, store, and apply all data. It plays a very important role in alleviating the pressure on cloud servers in the cloud computing model, so it plays an increasingly important role in the field of the Internet of Things. In an embodiment of the present invention, multiple first edge devices can be connected to the edge gateway, and the first edge device is used for video production and video consumption. The first edge device includes but is not limited to a mobile phone, a tablet computer, a desktop computer with a camera, a smart TV, and a wearable device with a camera.

[0027] See also Figure 1 , an embodiment of the present invention proposes a data processing method based on edge computing, comprising the following steps:

[0028] Step S110: receiving video data collected by a first edge device, and identifying the video data to obtain at least one target entity and scene information.

[0029] In this step, after the first edge device completes the video shooting and generates video data, the edge gateway receives the video data, understands the video data, and identifies at least one target entity appearing in the video data and the scene information of the target entity. Specifically, the target entity includes but is not limited to entity types such as people, animals, plants, places of interest, events, etc. The scene information includes the environment information of the target entity in the video frame corresponding to the video data, which is used to further determine which dimension of the target entity is displayed in the video data. In this embodiment, the scene information can be a descriptive text of the environment in the video frame.

[0030] Among them, for the recognition of target entities and scene information, machine learning or deep learning technology can be used in advance to train a deep learning model with the ability to recognize target entities and scene information. It is understandable that multiple video samples are selected in advance for annotation to obtain the corresponding relationship between video samples, target entities and scene information, and then these video samples are used to train and optimize the initial model of deep learning, and the various model parameters in the initial model are continuously adjusted until the above-mentioned deep learning model is trained.

[0031] Furthermore, the video data may include multiple target entities. In this case, the start and end time of each target entity in the video data also needs to be recorded.

[0032] Step S120, determining the target introduction dimension of the target entity to be identified according to the scenario information.

[0033] Specifically, the target entity includes multiple introductory dimensions. For example, for a target person, the introductory dimensions include personal information, representative works, social activities, award records, etc.; for a target plant, the introductory dimensions include species, growth environment, cultivation methods, value and efficacy, etc.; for a target scenic spot, the introductory dimensions include historical trajectory, architectural style, geographical layout, etc. Therefore, it is necessary to determine which introductory dimension of the target entity is mainly captured in the video data based on the scene information.

[0034] Optionally, at least one scenario keyword may be generated according to the scenario information; based on the at least one scenario keyword and the entity type to which the target entity belongs, a target introduction dimension to be identified for the target entity is determined.

[0035] Specifically, the introduction dimension corresponding to each entity type and multiple keywords representing each introduction dimension can be pre-set. First, the scene information (description text) is segmented to obtain several phrases, and phrases without practical meaning are deleted to obtain at least one scene keyword. Then, each introduction dimension under the entity type corresponding to the target entity and multiple keywords representing each introduction dimension are determined, and the target keyword matching at least one scene keyword is found, and the introduction dimension to which the target keyword belongs is determined as the target introduction dimension.

[0036] Step S130, searching the local database of the edge gateway for text data of the target entity in the target introduction dimension.

[0037] In order to relieve the pressure on the server, a local database is set up in the edge gateway, which stores the text data of each introduction dimension of common entities. The text data is the summary information describing the entity under the introduction dimension. In this step, based on the identification of the target entity and the target introduction dimension, the text data of the target entity in the target introduction dimension can be directly found in the local database.

[0038] Step S140: sending the text data to the first edge device, so that the first edge device synchronously displays the corresponding text data when playing the target entity.

[0039] Specifically, the text data corresponding to the target entity is sent to the first edge device. On the one hand, the first edge device can synchronously display the text data corresponding to the target entity when playing the target entity. On the other hand, the first edge device merges and stores the text data with the video data to obtain new video data, and sends the new video data to the cloud server, so that the cloud server distributes the new video data. When other users consume the new video data, they can directly understand the target entity through the text content without the need for secondary search, thereby avoiding interrupting the user's immersive video consumption experience.

[0040] It should be noted that while sending the text data, the corresponding start and end time of the target entity in the video data is also sent to the first edge device, that is, the corresponding text data is displayed only when the target entity appears, thereby improving the consistency of the image and text.

[0041] The embodiment of the present invention provides a data processing method based on edge computing. On the one hand, it transfers a certain part of the text data from the cloud server to the gateway, which greatly reduces the pressure on the cloud server and alleviates the network pressure. On the other hand, by identifying the target entity and scene information in the video data, accurate introduction text is added to the target entity, which does not require the user to perform a secondary search, thereby improving the user's video consumption experience.

[0042] As some optional implementation modes of the embodiments of the present invention, the target entity corresponds to encyclopedia content, the encyclopedia content is stored in the local database, the encyclopedia content includes multiple modules, and the module title of each module is used to represent the introduction dimension keywords of the target entity.

[0043] like Figure 2 As shown, searching the local database of the edge gateway for text data of the target entity in the target introduction dimension includes:

[0044] Step S121, searching the local database for encyclopedia content corresponding to the target entity.

[0045] In this step, the corresponding encyclopedia content may be searched in the local database based on the identifier (eg, name, code) of the target entity.

[0046] Step S122, determining a matching target module title from the encyclopedia content of the target entity based on the target introduction dimension.

[0047] Specifically, the encyclopedia content includes multiple modules, and the module title of each module can indicate the introduction dimension from which the module mainly presents the target entity. Therefore, the module title can be compared with the target introduction dimension to determine the matching target module title.

[0048] Step S123, extracting the text data from the text content under the target module to which the target module title belongs.

[0049] The target module to which the target module title belongs corresponds to the target introduction dimension, so text data can be obtained from the encyclopedia text content under the target module. Specifically, since the text data is displayed in several frames where the target entity appears in the video data and cannot affect the user's consumption experience of the video, it is generally selected to extract core sentences or summary sentences from the text content as text data.

[0050] Furthermore, in this embodiment, the encyclopedia content also includes multiple video resources, that is, each module or several modules in the encyclopedia content includes a video resource introducing the module. In order to improve the readability of the text data, the narration or audio in the relevant video resources can be extracted and added to the video data. Then the method also includes:

[0051] Determine a matching target video resource based on the target introduction dimension; extract music audio data and / or narration audio data in the target resource; clip the music audio data and / or narration audio data according to the time feature information of the target entity in the video data to obtain target audio data and a timestamp corresponding to the target audio data; send the target audio data and the timestamp corresponding to the target audio data to the first edge device, so that the first edge device synchronously plays the target audio data starting from the timestamp when playing the video data.

[0052] As described above, first, determine the target video resource that matches the target introduction dimension. If the target introduction dimension includes multiple video resources, the one that best matches the text data can be determined as the target video resource based on the title and corresponding text description information of each video resource. Secondly, extract the music audio data and / or narration audio data in the target video resource; wherein the music audio data is the background music corresponding to the target video resource, and the narration audio data is the explanation audio corresponding to the target video resource. In the process of editing the music audio data and / or narration audio data to obtain the target audio data, it is necessary to consider the start time corresponding to the target entity and the matching with the text data. On the one hand, ensure that the time length of the target audio data is consistent with the time length corresponding to the target entity, and on the other hand, make the emotions expressed by the edited music audio data and the text data the same, and the content expressed by the narration audio data and the text data consistent; finally, send the target audio data and the timestamp corresponding to the target audio data to the first edge device, so that when the first edge device plays the target entity, it not only displays the text data corresponding to the target entity, but also plays the background music data and / or narration audio data synchronously, thereby improving the efficiency of users receiving information and enhancing the immersion of video consumption.

[0053] As some further optional implementations of the embodiments of the present invention, since the information of the entity is not static, it is necessary to update the encyclopedia content in real time. Specifically, the method further includes:

[0054] The collected editing information of the encyclopedia content by each second edge device is cached; wherein the editing information includes an entity identifier, an editing module, and editing content; the editing information is clustered according to the entity and the editing module, and the clustered editing content is deduplicated to obtain processed editing information; and the processed editing information is sent to a cloud server.

[0055] In this embodiment, in addition to the first edge device for video production, the edge gateway also includes a second edge device for updating and editing encyclopedia content. In the process of editing the encyclopedia content, the second edge device collects the entity identifier of the edited entity, the editing module in the encyclopedia content of the entity, and the specific editing content, and sends them as editing information to the edge gateway. In this process, it is possible that multiple second edge devices edit the same module of the same entity. Therefore, the multiple editing information collected are first clustered according to the entity and the editing module of each entity; then the editing content under each editing module is analyzed and deduplicated to obtain accurate editing content; finally, the accurate editing content, its corresponding editing target, and entity identifier are sent to the cloud server as processed editing information, so that the cloud server updates the encyclopedia data of the corresponding entity.

[0056] It should be noted that in the process of analyzing and removing duplicate editorial content, one method is to calculate the similarity between each editorial content one by one, remove the editorial content with a similarity lower than a preset value, score the remaining editorial content based on the content quality model, and use the editorial content with the highest score as the accurate editorial content; another method, since the encyclopedia includes structured modules (such as summary parts, entity information parts) and unstructured modules (modules that actually introduce specific dimensions of entities), the editorial content can be classified. For the editorial content of the structured module, since the editorial content is generally words or short sentences, the editorial content with the highest degree of repetition can be directly used as the accurate editorial content. For the unstructured editorial content, the latest information corresponding to the entity is obtained based on the editorial module title and entity identifier corresponding to the editorial content, the similarity between the editorial content and the latest information is calculated, and the editorial content with the highest similarity is used as the accurate editorial content.

[0057] Furthermore, since changes in encyclopedia data cannot be perceived in real time by the local database of the edge gateway, the edge gateway is required to poll the cloud server in real time, causing the architecture of the edge gateway and cloud server to be bloated and stressful.

[0058] In order to solve this problem, the method also includes: obtaining updated encyclopedia data according to a preset period through an update component and caching it in a local database; in response to not finding the text data of the target entity in the target introduction dimension in the local database, sending a request to obtain the text data of the target introduction dimension to the cloud server, so that the cloud server sends the text data to the first edge device; obtaining the text data of the target entity in the target introduction dimension in an asynchronous manner, and caching it in the text database.

[0059] First, an update component is set in the edge gateway to obtain updated encyclopedia data in the cloud server according to a preset period. Generally speaking, the update period of encyclopedia data for different entity types is different. For example, the update period of encyclopedia data for people is shorter than that of encyclopedia data for animals and plants. Therefore, different preset periods can be set according to entity types. Avoid excessive polling for entity types that are not updated frequently, further reducing the pressure on cloud servers and edge gateways.

[0060] Secondly, if the text data of the target entity in the target introduction dimension cannot be found in the local database, that is, the time interval requirement for updating the local database is not met, then the update polling to the cloud server is passively triggered. After obtaining the text data of the target introduction dimension from the cloud server, it is first sent to the first edge device to ensure the timeliness of video production; then the text data of the target introduction dimension is obtained asynchronously and stored in the local database of the edge device, which reduces the pressure on the cloud server and edge gateway while ensuring the real-time nature of data updates.

[0061] As another optional implementation of the embodiment of the present invention, when the entity type of the target entity is an animal or a plant, the first edge devices in different geographical locations may shoot videos of the same target entity at different times, and these videos are processed to provide rich information for the target entity, so as to analyze the growth status of the target entity in various geographical locations and the impact of environmental changes on it. Figure 3 As shown, the method also includes:

[0062] Step S310, extracting key video frames that can represent the state information of the target entity from the video data, and storing the target entity, key video frames, and time information and geographic location information of collecting the video data in association to obtain an information library corresponding to the target entity.

[0063] Specifically, the target entity state information includes but is not limited to the appearance, appearance growth state, and activity state of the target entity. The target entity, key video frames, and the time information and geographic location information of the video data are associated and stored, so that a state diagram of the target entity in a certain time period at a certain geographic location can be obtained. The video data collected by the first edge devices are extracted and stored according to this step, so as to obtain an information library corresponding to the target entity.

[0064] Step S320: Based on the information base corresponding to the target entity, a growth status map of the target entity is generated from a time dimension and / or a geographical dimension.

[0065] For the same geographical location, the state diagrams of the target entity can be arranged and compared according to the time dimension to obtain a growth state diagram of the target entity in the time dimension; for the same time, the state diagrams of the target entity can be arranged and compared according to the geographical dimension to obtain a growth state diagram of the target entity in the geographical dimension; in addition, a two-dimensional coordinate system can be established based on time and geographical location to obtain a state distribution map of the target entity at each time and geographical location, thereby providing important data for the research and protection of the target entity.

[0066] The embodiment of the present invention provides a data processing method based on edge computing, which combines video production with research on biodiversity protection, thereby enhancing users' awareness of content and social value.

[0067] In one embodiment, reference Figure 4 As shown, a schematic diagram of the structure of a data processing device based on edge computing is provided. The device can be used to perform Figure 1-Figure 3 The data processing method based on edge computing shown in the figure includes: an identification module 410, a determination module 420, a search module 430 and a sending module 440; wherein,

[0068] An identification module 410 is used to receive video data collected by a first edge device, and identify the video data to obtain at least one target entity and scene information; a first determination module 420 is used to determine a target introduction dimension to be identified for the target entity based on the scene information; a search module 430 is used to search for text data of the target entity in the target introduction dimension in a local database of an edge gateway; and a sending module 440 is used to send the text data to the first edge device so that the first edge device synchronously displays the corresponding text data when playing the target entity.

[0069] Furthermore, the first determination module 420 is further used to generate at least one scenario keyword according to the scenario information; and determine the target introduction dimension to be identified for the target entity based on the at least one scenario keyword and the entity type to which the target entity belongs.

[0070] Furthermore, the target entity corresponds to encyclopedia content, which is stored in the local database. The encyclopedia content includes multiple modules, and the module title of each module is used to represent the introduction dimension keywords of the target entity; the determination module 420 is further used to search the encyclopedia content corresponding to the target entity in the local database; determine the matching target module title from the encyclopedia content of the target entity based on the target introduction dimension; and extract the text data from the text content under the target module to which the target module title belongs.

[0071] Furthermore, the encyclopedia content also includes multiple video resources; the device also includes: a second determination module, an extraction module, a editing module and a second sending module; wherein the second determination module is used to determine the matching target video resource based on the target introduction dimension; the extraction module is used to extract the music audio data and / or narration audio data in the target resource; the editing module is used to edit the music audio data and / or narration audio data according to the time feature information of the target entity in the video data to obtain the target audio data and the timestamp corresponding to the target audio data; the second sending module is used to send the target audio data and the timestamp corresponding to the target audio data to the first edge device, so that the first edge device plays the target audio data synchronously from the timestamp when playing the video data.

[0072] Furthermore, the device also includes: a cache module, an editing module and a third sending module; wherein the cache module is used to cache the collected editing information of the encyclopedia content by each second edge device; wherein the editing information includes an entity identifier, an editing module and an editing content; the editing module is used to cluster the editing information according to the entity and the editing module, deduplicate the clustered editing content, and obtain processed editing information; the third sending module is used to send the processed editing information to the cloud server.

[0073] Furthermore, the device also includes: an acquisition module, a fourth sending module, and an asynchronous caching module; wherein the acquisition module is used to acquire updated encyclopedia data according to a preset period through an update component and cache it to a local database; the fourth sending module is used to send a text data acquisition request for the target introduction dimension to the cloud server in response to the fact that the text data of the target entity in the target introduction dimension cannot be found in the local database, so that the cloud server sends the text data to the first edge device; the asynchronous caching module is used to acquire the text data of the target entity in the target introduction dimension in an asynchronous manner and cache it to the text database.

[0074] Furthermore, the device further comprises: a third extraction module and a generation module; wherein,

[0075] The third extraction module is used to extract key video frames in the video data that can represent the state information of the target entity, and store the target entity, key video frames, and the time information and geographic location information of collecting the video data in an associated manner to obtain an information library corresponding to the target entity; the generation module is used to generate a growth state map of the target entity from the time dimension and / or geographic dimension based on the information library corresponding to the target entity.

[0076] It should be noted that the data processing device based on edge computing provided in the embodiment of the present invention corresponds to the technical solution that can be used to execute the above-mentioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0077] Figure 5 This is a schematic diagram of a data processing device based on edge computing in an embodiment of the present invention. Figure 5 , which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present invention. The electronic device 500 in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0078] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes to implement the method of the embodiment of the present invention according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0079] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0080] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart, thereby implementing the method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

[0081] It should be noted that the computer-readable medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0082] In some embodiments, the terminal and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText TransferProtocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0083] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0084] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0085] Receive video data collected by a first edge device, identify the video data to obtain at least one target entity and scene information; determine a target introduction dimension to be identified for the target entity based on the scene information; search for text data of the target entity in the target introduction dimension in a local database of an edge gateway; and send the text data to the first edge device so that the first edge device synchronously displays the corresponding text data when playing the target entity.

[0086] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the method, device and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0087] The units involved in the embodiments of the present invention may be implemented by software or hardware, wherein the name of a unit does not limit the unit itself in some cases.

[0088] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0089] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0090] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A data processing method based on edge computing, characterized in that: include: Receiving video data collected by the first edge device, and identifying the video data to obtain at least one target entity and scene information; The target entity corresponds to encyclopedia content, which is stored in a local database of the edge gateway. The encyclopedia content includes multiple modules, and the module title of each module is used to characterize the introduction dimension keywords of the target entity; the encyclopedia content also includes multiple video resources; the target introduction dimension to be identified for the target entity is determined according to the scene information; Searching for encyclopedia content corresponding to the target entity in a local database; determining a matching target module title from the encyclopedia content of the target entity based on the target introduction dimension; Extracting text data from the text content under the target module to which the target module title belongs; Sending the text data to the first edge device, so that the first edge device synchronously displays the corresponding text data when playing the target entity; Determine a matching target video resource based on the target introduction dimension; Extracting music audio data and / or narration audio data from a target video resource; editing the music audio data and / or narration audio data according to time feature information of the target entity in the video data to obtain target audio data and a timestamp corresponding to the target audio data; sending the target audio data and the timestamp corresponding to the target audio data to the first edge device, so that the first edge device synchronously plays the target audio data starting from the timestamp when playing the video data; Cache the collected editing information of the encyclopedia content by each second edge device; wherein the editing information includes an entity identifier, an editing module, and editing content; cluster the editing information according to the entity and the editing module, deduplicate the clustered editing content, and obtain processed editing information; send the processed editing information to the cloud server; Acquire updated encyclopedia data according to a preset period through an update component and cache it in a local database; in response to the text data of the target entity in the target introduction dimension not being found in the local database, send a request to acquire the text data of the target introduction dimension to a cloud server, so that the cloud server sends the text data to the first edge device; acquire the text data of the target entity in the target introduction dimension in an asynchronous manner and cache it in the text database; Extract key video frames in the video data that can represent the state information of the target entity, associate and store the target entity, key video frames, and time information and geographic location information for collecting the video data to obtain an information library corresponding to the target entity; based on the information library corresponding to the target entity, generate a growth state map of the target entity from the time dimension and / or geographic dimension.

2. The method according to claim 1, characterized in that The determining, according to the scenario information, a target introduction dimension to be identified for the target entity includes: generating at least one scene keyword according to the scene information; Based on the at least one scenario keyword and the entity type to which the target entity belongs, a target introduction dimension to be identified for the target entity is determined.

3. A data processing device based on edge computing, characterized in that: include: An identification module, configured to receive video data collected by the first edge device, and identify the video data to obtain at least one target entity and scene information; The target entity corresponds to encyclopedia content, which is stored in a local database of the edge gateway. The encyclopedia content includes multiple modules, and the module title of each module is used to represent the introduction dimension keyword of the target entity; the encyclopedia content also includes multiple video resources; A first determination module, configured to determine a target introduction dimension to be identified for the target entity according to the scenario information; A search module, used to search the encyclopedia content corresponding to the target entity in the local database; Determine a matching target module title from the encyclopedia content of the target entity based on the target introduction dimension; Extracting text data from the text content under the target module to which the target module title belongs; A first sending module, configured to send the text data to the first edge device, so that the first edge device synchronously displays the corresponding text data when playing the target entity; An audio synchronization playback module, used to determine a matching target video resource based on the target introduction dimension; Extracting music audio data and / or narration audio data from the target resource; editing the music audio data and / or narration audio data according to the time feature information of the target entity in the video data to obtain target audio data and a timestamp corresponding to the target audio data; sending the target audio data and the timestamp corresponding to the target audio data to the first edge device, so that the first edge device synchronously plays the target audio data from the timestamp when playing the video data; A data editing processing module is used to cache the collected editing information of the encyclopedia content by each second edge device; wherein the editing information includes an entity identifier, an editing module, and editing content; clustering the editing information according to the entity and the editing module, deduplicating the clustered editing content, and obtaining processed editing information; and sending the processed editing information to the cloud server; A data update acquisition module is used to acquire updated encyclopedia data according to a preset period through an update component and cache it in a local database; in response to the text data of the target entity in the target introduction dimension not being found in the local database, send a text data acquisition request of the target introduction dimension to a cloud server, so that the cloud server sends the text data to the first edge device; acquire the text data of the target entity in the target introduction dimension in an asynchronous manner, and cache it in the text database; A growth state map generation module is used to extract key video frames in the video data that can represent the state information of the target entity, associate and store the target entity, key video frames, and time information and geographic location information for collecting the video data to obtain an information library corresponding to the target entity; based on the information library corresponding to the target entity, generate a growth state map of the target entity from the time dimension and / or geographic dimension.

4. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in claim 1 or 2.

Images