Video tag sharing and multiplexing method and device, electronic equipment and medium

Abstract

The invention discloses a video tag sharing and multiplexing method and device, electronic equipment and a medium, and relates to the technical field of video processing, and the method comprises the steps: obtaining city video image information, dividing the city video image information, and obtaining a plurality of pieces of sub-image information; determining a similar region according to the sub-image information and preset standard image information; determining the similarity of each similar region; if the similarity is greater than a preset similarity, determining landform features and objective environment features of the similar region; determining common label information according to the landform features and the objective environment features; and determining video tag information based on the common tag information. According to the invention, the accuracy of video tag sharing and multiplexing can be improved.

Description

Technical Field

[0001] The present application relates to the field of video processing technology, and in particular to a video tag sharing and multiplexing method, device, electronic device and medium. Background Art

[0002] With the accelerated advancement of smart city construction, video surveillance systems have become an important component. However, since there are many video resources in a video aggregation platform, from thousands of videos to hundreds of thousands of videos, and the video points are scattered in different places, the video data is huge and the analysis work is more difficult. Therefore, the management and utilization of massive video information has become a key issue.

[0003] Traditional video labeling methods mainly involve staff analyzing a single video stream in real time, designing a fixed template, and using the fixed template to label the video.

[0004] However, traditional video label sharing and reuse methods are susceptible to human interference when faced with large-scale, multi-source heterogeneous video data, resulting in inaccurate video labels and low efficiency. Summary of the invention

[0005] In order to improve the accuracy of video tag sharing and multiplexing, the present application provides a video tag sharing and multiplexing method, device, electronic device and medium.

[0006] In a first aspect, the present application provides a video tag sharing and multiplexing method, which adopts the following technical solution:

[0007] A video tag sharing and multiplexing method, comprising:

[0008] Acquire city video image information, and divide the city video image information to obtain a plurality of sub-image information;

[0009] Determining a similar area according to the sub-image information and preset standard image information;

[0010] Determining the similarity of each similar region;

[0011] If the similarity is greater than a preset similarity, determining the geomorphic features and objective environmental features of the similar area;

[0012] Determining shared tag information according to the geomorphic features and the objective environmental features;

[0013] Based on the common tag information, video tag information is determined.

[0014] By adopting the above technical scheme, after obtaining the city video image information, the city video image information is divided to obtain multiple sub-image information, thereby improving the accuracy of image analysis; then the sub-image information is compared with the preset standard image information to determine the similar area; then, the similarity between the sub-image information and the similar area corresponding to the preset standard image information is determined; the similarity is compared with the preset similarity, if the similarity is greater than the preset similarity, it means that the overlap between the sub-image information and the preset standard image information is relatively high at this time, and then the landform features and objective environmental features corresponding to the similar area are determined; the landform features and objective environmental features are analyzed to determine the common label information; then based on the common label information, the video label information is determined, thereby improving the accuracy of video label sharing and reuse.

[0015] In a possible implementation, the city video image information is divided to obtain a plurality of sub-image information, including:

[0016] Determining video element information according to the city video image information;

[0017] Determining element classification according to the video element information;

[0018] Based on the element classification, determining an image division standard;

[0019] Based on the image division standard, the plurality of sub-image information is obtained.

[0020] In a possible implementation manner, determining the similar area according to the sub-image information and preset standard image information includes:

[0021] Extracting features from the sub-image information to determine first feature information;

[0022] Extracting features from the preset standard image information to determine second feature information;

[0023] Determining first edge information and second edge information according to the sub-image information and the preset standard image information;

[0024] Calculating a similarity value between the first feature information and the second feature information;

[0025] If the similarity value is greater than a preset similarity value, determining the degree of overlap between the first edge information and the second edge information;

[0026] If the degree of overlap is greater than a preset degree of overlap, the similar area is determined.

[0027] In a possible implementation, determining the geomorphic features and objective environmental features of the similar area includes:

[0028] Determining a city landform image according to the city video image information;

[0029] Determining the landform features based on the urban landform image;

[0030] Obtain urban environmental information;

[0031] Determining environmental factors according to the urban environmental information;

[0032] Based on the environmental factors, the objective environmental characteristics are determined.

[0033] In a possible implementation manner, the determining the shared tag information also includes:

[0034] Obtain city attribute information and scene information;

[0035] Determining a classification standard according to the city attribute information and the scene information;

[0036] Determine topic label information according to the classification standard;

[0037] Based on the topic tag information, determine a tag tree;

[0038] A preset shared tag library is established according to the tag tree.

[0039] In a possible implementation manner, determining the common tag information according to the landform feature and the objective environment feature includes:

[0040] Get city coordinate information;

[0041] Determining a first keyword according to the geomorphic features and the city coordinate information;

[0042] Determining a second keyword according to the objective environmental characteristics;

[0043] Determine a common keyword according to the first keyword and the second keyword;

[0044] The shared tag information is determined based on the shared keywords and the preset shared tag library.

[0045] In a possible implementation manner, determining the video tag information based on the common tag information includes:

[0046] Based on the shared tag information, determining a tag theme and a tag category;

[0047] Determine a target shared tag according to the tag subject and the tag category;

[0048] Determining first tag information according to the target common tag;

[0049] Determining the accuracy of the first tag information;

[0050] If the accuracy is greater than the preset accuracy, it is determined that the first tag information is the video tag information.

[0051] In a second aspect, the present application provides a video tag sharing and multiplexing device, which adopts the following technical solution:

[0052] A video tag sharing and multiplexing device comprises: a sub-image information determination module, a similar area determination module, a similarity determination module, a feature determination module, a common tag information determination module and a video tag information determination module, wherein:

[0053] A sub-image information determination module is used to obtain city video image information, divide the city video image information, and obtain a plurality of sub-image information;

[0054] A similar region determination module, used to determine a similar region based on the sub-image information and preset standard image information;

[0055] A similarity determination module, used to determine the similarity of each similar region;

[0056] A feature determination module, configured to determine the geomorphic features and objective environmental features of the similar area if the similarity is greater than a preset similarity;

[0057] A common tag information determination module, used to determine the common tag information according to the landform features and the objective environment features;

[0058] The video tag information determining module is used to determine the video tag information based on the common tag information.

[0059] By adopting the above technical solution, after acquiring the city video image information, the sub-image information determination module divides the city video image information to obtain multiple sub-image information, thereby improving the accuracy of image analysis; then the similar area determination module compares the sub-image information with the preset standard image information to determine the similar area; then, the similarity determination module determines the similarity between the sub-image information and the similar area corresponding to the preset standard image information; the feature determination module compares the similarity with the preset similarity, if the similarity is greater than the preset similarity, it means that the overlap between the sub-image information and the preset standard image information is high at this time, and then the landform features and objective environmental features corresponding to the similar area are determined; the shared label information determination module analyzes the landform features and objective environmental features to determine the shared label information; then the video label information determination module determines the video label information based on the shared label information, thereby improving the accuracy of video label sharing and reuse.

[0060] In a possible implementation, the sub-image information determination module includes: a video element information determination unit, an element classification determination unit, an image division standard determination unit, and a sub-image information determination unit, wherein:

[0061] A video element information determining unit, used to determine video element information according to the city video image information;

[0062] An element classification determination unit, used to determine an element classification according to the video element information;

[0063] An image division standard determination unit, configured to determine an image division standard based on the element classification;

[0064] The sub-image information determining unit is used to obtain the plurality of sub-image information based on the image division standard.

[0065] In a possible implementation, the similar region determination module includes: a first feature information determination unit, a second feature information determination unit, an edge information determination unit, a similarity value determination unit, a coincidence determination unit, and a similar region determination unit, wherein:

[0066] A first feature information determining unit, configured to extract features from the sub-image information to determine first feature information;

[0067] A second feature information determining unit, configured to extract features from the preset standard image information to determine second feature information;

[0068] an edge information determining unit, configured to determine first edge information and second edge information according to the sub-image information and the preset standard image information;

[0069] a similarity value determining unit, configured to calculate a similarity value between the first feature information and the second feature information;

[0070] a coincidence determination unit, configured to determine a coincidence between the first edge information and the second edge information if the similarity value is greater than a preset similarity value;

[0071] The similar region determining unit is configured to determine the similar region if the overlap degree is greater than a preset overlap degree.

[0072] In a possible implementation, the feature determination module includes: an urban landform image determination unit, a landform feature determination unit, an urban environment information acquisition unit, an environmental element determination unit, and an objective environment feature determination unit, wherein:

[0073] A city landform image determination unit, used to determine a city landform image according to the city video image information;

[0074] A landform feature determination unit, configured to determine the landform feature based on the urban landform image;

[0075] An urban environment information acquisition unit, used for acquiring urban environment information;

[0076] An environmental factor determination unit, used to determine environmental factors according to the urban environmental information;

[0077] The objective environment feature determination unit is used to determine the objective environment feature based on the environmental elements.

[0078] In a possible implementation, the video tag sharing and multiplexing device further includes: a first information acquisition module, a classification standard determination module, a topic tag information determination module, a tag tree determination module, and a preset shared tag library establishment module, wherein:

[0079] The first information acquisition module is used to acquire city attribute information and scene information;

[0080] A classification standard determination module, used to determine a classification standard according to the city attribute information and the scene information;

[0081] A topic label information determination module, used to determine the topic label information according to the classification standard;

[0082] A tag tree determination module, used to determine a tag tree based on the topic tag information;

[0083] The preset shared tag library establishment module is used to establish a preset shared tag library according to the tag tree.

[0084] In a possible implementation, the shared tag information determination module includes: a city coordinate information acquisition unit, a first keyword determination unit, a second keyword determination unit, a shared keyword determination unit, and a shared tag information determination unit, wherein:

[0085] A city coordinate information acquisition unit, used to acquire city coordinate information;

[0086] A first keyword determining unit, configured to determine a first keyword according to the geomorphic features and the city coordinate information;

[0087] A second keyword determining unit, configured to determine a second keyword according to the objective environment feature;

[0088] a common keyword determining unit, configured to determine a common keyword according to the first keyword and the second keyword;

[0089] The shared tag information determining unit is used to determine the shared tag information based on the shared keywords and the preset shared tag library.

[0090] In a possible implementation, the video tag information determination module includes: a tag theme determination unit, a target common tag determination unit, a first tag information determination unit, an accuracy determination unit, and a video tag information determination unit, wherein:

[0091] A tag theme determination unit, configured to determine a tag theme and a tag category based on the shared tag information;

[0092] a target common tag determining unit, configured to determine a target common tag according to the tag subject and the tag category;

[0093] A first label information determining unit, configured to determine first label information according to the target common label;

[0094] an accuracy determination unit, configured to determine the accuracy corresponding to the first tag information;

[0095] The video tag information determining unit is configured to determine that the first tag information is the video tag information if the accuracy is greater than a preset accuracy.

[0096] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0097] An electronic device, comprising:

[0098] at least one processor;

[0099] Memory;

[0100] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned video tag sharing and multiplexing method.

[0101] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0102] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned video tag sharing and multiplexing method.

[0103] In summary, this application includes the following beneficial technical effects:

[0104] After obtaining the city video image information, the city video image information is divided to obtain multiple sub-image information, thereby improving the accuracy of image analysis; then the sub-image information is compared with the preset standard image information to determine the similar area; then, the similarity between the sub-image information and the similar area corresponding to the preset standard image information is determined; the similarity is compared with the preset similarity, if the similarity is greater than the preset similarity, it means that the sub-image information and the preset standard image information have a high degree of overlap, then the landform features and objective environmental features corresponding to the similar area are determined; the landform features and objective environmental features are analyzed to determine the common label information; then based on the common label information, the video label information is determined, thereby improving the accuracy of video label sharing and reuse. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] Figure 1 It is a flowchart of the video tag sharing and multiplexing method of the present application;

[0106] Figure 2 It is a block diagram of a video tag sharing and multiplexing device of the present application;

[0107] Figure 3 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0108] The following combination Figure 1-Figure 3 This application is described in further detail.

[0109] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0110] The embodiment of the present application provides a video tag sharing and multiplexing method, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed device composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application.

[0111] Reference Figure 1 The method comprises: step S101, step S102, step S103, step S104, step S105 and step S106, wherein:

[0112] Step S101: Acquire city video image information, divide the city video image information, and obtain a plurality of sub-image information.

[0113] Specifically, corresponding image acquisition devices are deployed in public places, such as roads, squares, and around construction units. At the same time, the image acquisition devices capture multi-source video streams according to administrative divisions and scene requirements to ensure coverage of key areas. After the electronic device obtains the city video image information collected by the image acquisition device, the electronic device then divides the city video image according to different video element information to obtain multiple sub-image information, and the electronic device will classify and store the video element information corresponding to the sub-image information.

[0114] Step S102: Determine a similar area according to the sub-image information and the preset standard image information.

[0115] Step S103: Determine the similarity of each similar region.

[0116] In the embodiment of the present application, the preset standard image is a standard image corresponding to the video element information.

[0117] Specifically, the electronic device performs image preprocessing on the sub-image information, performs noise elimination and distortion correction, and adopts super-resolution reconstruction technology (such as a motion compensation algorithm based on multiple frames of continuous low-resolution images) to improve image clarity and eliminate the interference of blur on feature extraction; then the electronic device extracts features from the sub-image information and preset standard image information, and performs feature matching; the electronic device determines the corresponding similar areas based on the successfully matched feature pairs using a deep learning method; then, the electronic device performs data statistics on the feature pairs and calculates the similarity between each similar area and the preset standard image information.

[0118] Step S104: If the similarity is greater than a preset similarity, the geomorphic features and objective environmental features of the similar area are determined.

[0119] Specifically, the electronic device compares the similarity with the preset similarity. If the similarity is less than or equal to the preset similarity, it means that the sub-image information does not accurately match the preset standard image information; if the similarity is greater than the preset similarity, it means that the sub-image information accurately matches the preset standard image information at this time; then, the electronic device analyzes and processes the urban video image information and the urban environment information transmitted by the staff to determine the geomorphological features and objective environmental features of each similar area.

[0120] Step S105: Determine the shared tag information according to the topographic features and objective environmental features.

[0121] Specifically, when the image acquisition device is acquiring images, the positioning device equipped in the image acquisition device will transmit the corresponding city coordinate information to the electronic device, and the electronic device will integrate the corresponding city coordinate information to determine the range corresponding to the city coordinate information; then, the electronic device will extract keywords based on the topographic features and the city coordinate information to determine the first keyword; at the same time, the electronic device will extract keywords from the objective environmental features to determine the second keyword; the electronic device will compare the first keyword with the second keyword, analyze the semantic association and overlapping parts between the first keyword and the second keyword, and determine the common keyword; the electronic device will match the common keyword with the preset shared tag library to determine the common tag information corresponding to the final common keyword.

[0122] Step S106: Determine video tag information based on the shared tag information.

[0123] Specifically, the electronic device analyzes and processes the shared tag information, clarifies the tag subject and tag category represented by each shared tag information, and counts the quantity information and importance corresponding to each tag subject and tag category, so as to determine which shared tag information occupies a dominant position in the shared tag information, and sets it as the target shared tag; then the electronic device determines the first tag information corresponding to the city video image information based on the target shared tag; the electronic device verifies the first tag information, determines the accuracy and consistency corresponding to the first tag information, and if the accuracy and consistency are respectively greater than the preset accuracy and preset consistency, the first tag information is set as the video tag information.

[0124] The embodiment of the present application provides a video tag sharing and reuse method. After obtaining city video image information, the city video image information is divided to obtain multiple sub-image information, thereby improving the accuracy of image analysis; the sub-image information is then compared with preset standard image information to determine similar areas; thereafter, the similarity between the sub-image information and the similar areas corresponding to the preset standard image information is determined; the similarity is compared with the preset similarity, and if the similarity is greater than the preset similarity, it means that the sub-image information and the preset standard image information have a high degree of overlap, and then the landform features and objective environmental features corresponding to the similar areas are determined; the landform features and objective environmental features are analyzed to determine the shared tag information; then the video tag information is determined based on the shared tag information, thereby improving the accuracy of video tag sharing and reuse.

[0125] The city video image information is divided to obtain a plurality of sub-image information, including: determining video element information according to the city video image information; determining element classification according to the video element information; determining image division criteria based on element classification; and obtaining a plurality of sub-image information based on the image division criteria.

[0126] Specifically, the electronic device extracts features from the city video image information, determines all the video element information corresponding to the city video image information, and then the electronic device classifies and organizes the obtained video element information, and classifies and stores the attributes corresponding to each video element information, such as name, position (coordinate range in the image), size, color, texture, etc.; then the electronic device determines the element classification according to the characteristics corresponding to the video element information and the purpose of analysis; the electronic device marks the element classification to the city image information, uses the image boundary corresponding to each element classification as the dividing boundary, and sets it as the image dividing standard; then the electronic device divides the city image information according to the image dividing standard, and sets the divided area as sub-image information.

[0127] Determine a similar area based on sub-image information and preset standard image information, including: extract features from the sub-image information to determine first feature information; extract features from the preset standard image information to determine second feature information; determine first edge information and second edge information based on the sub-image information and the preset standard image information; calculate a similarity value between the first feature information and the second feature information; if the similarity value is greater than a preset similarity value, determine a degree of overlap between the first edge information and the second edge information; if the degree of overlap is greater than a preset degree of overlap, determine a similar area.

[0128] Specifically, the electronic device extracts features from the preprocessed sub-image information, and sets the feature information corresponding to the sub-image information as the first feature information; at the same time, after receiving the preset standard image transmitted by the staff, the electronic device extracts features from the preset standard image to determine the second feature information; then the electronic device extracts edges from the sub-image information and the preset standard image information to determine the first edge information corresponding to the sub-image information and the second edge information corresponding to the preset standard brick image information; then, the electronic device calculates the similarity between the first feature information and the second feature information using a feature matching method; the electronic device compares the similarity value with the preset similarity value. If the similarity value is less than or equal to the preset similarity value, it means that the first feature information is similar to the second feature information at this time. If the feature information does not match, it means that the sub-image information does not match the preset standard image information; if the similarity value is greater than the preset similarity value, it means that the first feature information and the second feature information match successfully at this time, which means that the sub-image information and the preset standard image information match successfully at this time; then the electronic device determines the degree of overlap between the first edge information and the second edge information by calculating the overlapping pixel data after the first edge information and the second edge information are binarized; if the overlap is less than or equal to the preset overlap, it means that the sub-image information and the preset standard image information have no matching overlapping area; if the overlap is greater than the preset overlap, it means that the sub-image information and the preset standard image information have a corresponding overlapping area, and then the electronic device sets the overlapping area as a similar area.

[0129] Determine the geomorphic features and objective environmental features of similar areas, including: determine the urban geomorphic image based on the urban video image information; determine the geomorphic features based on the urban geomorphic image; obtain the urban environmental information; determine the environmental elements based on the urban environmental information; determine the objective environmental features based on the environmental elements.

[0130] In the embodiment of the present application, urban environmental information includes meteorological information, environmental pollution information, ecological information, and hydrological environmental information, and environmental elements include climate elements, ecological elements, and pollution elements.

[0131] Specifically, the electronic device extracts the image features of the urban landforms in the urban video image information, separates the landform part from other parts, such as buildings, pedestrians, etc., and then the electronic device draws the landform part in the urban video image information in 3D and sets it as the urban landform image; the electronic device uses the digital elevation model data to calculate the terrain parameters such as the slope, slope direction, poster height, etc. of the urban landform in the urban landform image, and the electronic device performs texture analysis on the urban landform image, and finally analyzes and determines the landform features; after receiving the urban environmental information transmitted by the staff, the electronic device identifies the elements of the urban environmental information and identifies the main environmental elements, for example, climate elements include temperature, precipitation, light, etc.; ecological elements include vegetation type, biodiversity, etc.; pollution elements include pollutant concentration in the air and pollutant content in the water; then, the electronic device defines and classifies each environmental element, and clarifies the unique environmental elements in the city. The electronic device performs statistical analysis on the environmental elements, analyzes the statistical quantities such as the average value, standard deviation, and change trend, determines the objective environmental characteristics, and transmits them to the display device in the form of charts and maps.

[0132] Determining the shared tag information also includes: obtaining city attribute information and scene information; determining classification standards based on the city attribute information and scene information; determining thematic tag information based on the classification standards; determining a tag tree based on the thematic tag information; and establishing a preset shared tag library based on the tag tree.

[0133] In an embodiment of the present application, the historical city database contains city attribute information and scene information of the city in the past five years.

[0134] Specifically, after the electronic device obtains the city attribute information and scene information transmitted by the historical city information database, the electronic device integrates and analyzes the city attribute information and scene information to determine the classification standard for classifying the tags; then the electronic device determines each topic tag information according to the classification standard, and the topic tag information includes a place tag, a basic attribute tag, a business tag, a topic tag, and an AI tag. The basic attribute tag may include the device's coding type, access method, and device type. The place tags are divided into administrative offices, parks, medical care, life services, and catering. The topic tags are divided into May Day holidays, education, smart construction sites, forest fire prevention, and flood prevention. The electronic device analyzes each topic tag information, determines the logical relationship between each topic tag information, and builds a corresponding tag tree; the electronic device selects a suitable data storage structure to establish a preset shared tag library, such as a relational database (such as MySQL, Oracle) or a non-relational database (such as MongoDB). According to the structure of the tag tree, the electronic device designs the table structure or data model of the database to ensure that the name, hierarchical relationship, description, and other information of the tag can be stored; at the same time, the electronic device enters the topic tag information in the tag tree into the preset shared tag library to establish a preset shared tag library.

[0135] Determine shared tag information based on geomorphic features and objective environmental features, including: obtaining city coordinate information; determining a first keyword based on geomorphic features and city coordinate information; determining a second keyword based on objective environmental features; determining shared keywords based on the first keyword and the second keyword; and determining shared tag information based on shared keywords and a preset shared tag library.

[0136] Specifically, after receiving the city coordinate information transmitted by the geographic information system database, the electronic device combines the landform features and the city coordinate information to clarify the geographical location characteristics of the city and extract keywords. For the landform features, if it is a mountainous area, keywords such as "mountain city", "surrounded by mountains", and "hilly landform" can be extracted; if it is a plain, "plain terrain", "vast plains", etc. can be extracted. The electronic device screens the extracted keywords, removes keywords with repeated meanings or are too broad and lack specificity, and finally determines the first keyword that can accurately reflect the relationship between the city's landform and coordinates; at the same time, the electronic device combines the specific geographical areas or landmarks involved in the coordinate information to add relevant keywords, such as "city on the south foot of [mountain name]", "plain city near [river name]", etc.; then the electronic device classifies the objective environmental characteristics in detail according to factors such as climate, vegetation, soil, and hydrology. For example, in terms of climate, the city's temperature zones, precipitation patterns, seasonal changes, etc. are analyzed; in terms of vegetation, attention is paid to the main vegetation types, vegetation coverage, etc.; for each category of environmental elements, keywords that can reflect the uniqueness of the city's objective environment are extracted; in terms of climate, if the city has a subtropical monsoon climate, keywords such as "subtropical monsoon climate", "humid climate", and "four distinct seasons" can be extracted; in terms of vegetation, if it is dominated by evergreen broad-leaved forests, "evergreen broad-leaved forest vegetation" and "high forest coverage" can be extracted. The electronic equipment will integrate the keywords extracted from various environmental elements, screen them again, remove the parts that are repeated or not strongly related to the keywords of other elements, and determine the final second keyword.

[0137] Furthermore, the electronic device uses a text matching algorithm to compare the first keyword with the second keyword, thereby measuring the similarity between the first keyword and the second keyword, and by comparison, finds out the keywords that exist in both the first keyword and the second keyword, and these keywords are the common keywords. For example, if the first keyword set includes "cities along the river" and the second keyword set includes "clear river water quality", then "river" can be used as a common keyword; in the preset shared tag library, the electronic device searches according to the common keywords. The preset shared tag library is a database table or data structure that stores various tags and related information. The electronic device uses a database query statement (such as an SQL statement) or a corresponding data operation method to find a tag that matches the common keyword; the electronic device determines the common tag information based on the matching result. In the matching process, the electronic device combines fuzzy matching in addition to precise matching. For example, if the common keyword is "river", it can search for tags with similar semantics such as "river channel" and "water system". For the matched multiple tags, they can be screened and sorted according to factors such as the tag weight, usage frequency, and relevance to the common keywords, and finally determine the common tag information that can most accurately describe the characteristics of the city.

[0138] Based on the common tag information, the video tag information is determined, including: based on the common tag information, determining the tag subject and the tag category; determining the target common tag according to the tag subject and the tag category; determining the first tag information according to the target common tag; determining the accuracy corresponding to the first tag information; if the accuracy is greater than the preset accuracy, determining that the first tag information is the video tag information.

[0139] Specifically, the electronic device performs text analysis on the shared tag information and extracts keywords and key phrases in the tags; clustering algorithms (such as K-Means clustering and hierarchical clustering) are used to aggregate shared tag information with similar semantics into different groups; the electronic device defines a clear tag theme name for each cluster group, and the name should be able to summarize the core content of the shared tag information of the group. At the same time, the electronic device further divides the theme into different categories according to the nature and characteristics of the tag theme, and names them as tag categories; then the electronic device counts the quantity information and importance corresponding to each tag theme and tag category, so as to determine which shared tag information occupies a dominant position in the shared tag information, and sets it as the target shared tag; then, the electronic device analyzes the target shared tag, and considers whether it is necessary to expand or supplement the relevant tags according to the urban video image information. The electronic device integrates the expanded and supplemented tags with the target shared tags, removes duplicate tags, and generates first tag information; the electronic device compares the first tag information with the urban video image information, checks whether each first tag information accurately reflects the actual content in the urban video image information, and determines the accuracy score for each tag. For example, if the first label information completely matches the content of the city video image information, the score is 1; if it partially matches, the score is between 0 and 1; if it does not match, the score is 0. The average accuracy score of all labels is calculated as the specific value of the accuracy of the first label information; then the electronic device compares the accuracy with the preset accuracy, and if the accuracy is greater than the preset accuracy, the electronic device sets the first label information as the video label information.

[0140] Reference Figure 2 The video tag sharing and multiplexing device 20 may specifically include: a sub-image information determination module 201, a similar region determination module 202, a similarity determination module 203, a feature determination module 204, a common tag information determination module 205 and a video tag information determination module 206, wherein:

[0141] The sub-image information determination module 201 is used to obtain the city video image information, divide the city video image information, and obtain a plurality of sub-image information;

[0142] A similar region determination module 202, configured to determine a similar region based on sub-image information and preset standard image information;

[0143] A similarity determination module 203, used to determine the similarity of each similar region;

[0144] The feature determination module 204 is used to determine the geomorphic features and objective environmental features of the similar area if the similarity is greater than a preset similarity;

[0145] The common tag information determination module 205 is used to determine the common tag information according to the landform characteristics and objective environmental characteristics;

[0146] The video tag information determining module 206 is used to determine the video tag information based on the common tag information.

[0147] In a possible implementation of the embodiment of the present application, the sub-image information determination module 201 includes: a video element information determination unit, an element classification determination unit, an image division standard determination unit, and a sub-image information determination unit, wherein:

[0148] A video element information determining unit, used to determine video element information according to the city video image information;

[0149] An element classification determination unit, used to determine the element classification according to the video element information;

[0150] An image division standard determination unit, used for determining an image division standard based on element classification;

[0151] The sub-image information determining unit is used to obtain a plurality of sub-image information based on the image division standard.

[0152] In a possible implementation of the embodiment of the present application, the similar region determination module 202 includes: a first feature information determination unit, a second feature information determination unit, an edge information determination unit, a similarity value determination unit, a coincidence determination unit, and a similar region determination unit, wherein:

[0153] A first feature information determining unit, used to extract features from the sub-image information to determine first feature information;

[0154] A second feature information determining unit, used to extract features from preset standard image information to determine second feature information;

[0155] An edge information determining unit, configured to determine first edge information and second edge information according to the sub-image information and preset standard image information;

[0156] A similarity value determination unit, used to calculate a similarity value between the first feature information and the second feature information;

[0157] a coincidence determination unit, configured to determine a coincidence between the first edge information and the second edge information if the similarity value is greater than a preset similarity value;

[0158] The similar region determining unit is used to determine a similar region if the overlap degree is greater than a preset overlap degree.

[0159] In a possible implementation of the embodiment of the present application, the feature determination module 204 includes: an urban landform image determination unit, a landform feature determination unit, an urban environment information acquisition unit, an environmental element determination unit, and an objective environment feature determination unit, wherein:

[0160] The urban landform image determination unit is used to determine the urban landform image according to the urban video image information;

[0161] A landform feature determination unit, used for determining landform features based on the urban landform image;

[0162] An urban environment information acquisition unit, used for acquiring urban environment information;

[0163] An environmental factor determination unit, used for determining environmental factors according to urban environmental information;

[0164] The objective environment feature determination unit is used to determine the objective environment features based on the environmental factors.

[0165] In a possible implementation of the embodiment of the present application, the video tag sharing and multiplexing device 20 further includes: a first information acquisition module, a classification standard determination module, a topic tag information determination module, a tag tree determination module, and a preset shared tag library establishment module, wherein:

[0166] The first information acquisition module is used to acquire city attribute information and scene information;

[0167] A classification standard determination module is used to determine the classification standard based on city attribute information and scene information;

[0168] The topic label information determination module is used to determine the topic label information according to the classification standard;

[0169] A tag tree determination module is used to determine the tag tree based on the topic tag information;

[0170] The preset shared tag library establishment module is used to establish a preset shared tag library according to the tag tree.

[0171] In a possible implementation of the embodiment of the present application, the shared tag information determination module 205 includes: a city coordinate information acquisition unit, a first keyword determination unit, a second keyword determination unit, a shared keyword determination unit, and a shared tag information determination unit, wherein:

[0172] A city coordinate information acquisition unit, used to acquire city coordinate information;

[0173] A first keyword determining unit, used to determine the first keyword according to the geomorphic features and the city coordinate information;

[0174] A second keyword determination unit, used to determine the second keyword according to objective environmental characteristics;

[0175] A common keyword determining unit, configured to determine a common keyword based on the first keyword and the second keyword;

[0176] The shared tag information determining unit is used to determine the shared tag information based on the shared keywords and a preset shared tag library.

[0177] In a possible implementation of the embodiment of the present application, the video tag information determination module 206 includes: a tag theme determination unit, a target common tag determination unit, a first tag information determination unit, an accuracy determination unit, and a video tag information determination unit, wherein:

[0178] A tag theme determination unit, used to determine a tag theme and a tag category based on the shared tag information;

[0179] A target common tag determination unit, used to determine the target common tag according to the tag subject and the tag category;

[0180] A first label information determining unit, configured to determine the first label information according to the target common label;

[0181] An accuracy determination unit, used to determine the accuracy corresponding to the first tag information;

[0182] The video tag information determining unit is used to determine that the first tag information is video tag information if the accuracy is greater than a preset accuracy.

[0183] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0184] The present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0185] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0186] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0187] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0188] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0189] The electronic devices include, but are 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-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0190] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0191] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A video tag sharing and multiplexing method, characterized in that: include: Acquire city video image information, and divide the city video image information to obtain a plurality of sub-image information; Determining a similar area according to the sub-image information and preset standard image information; Determining the similarity of each similar region; If the similarity is greater than a preset similarity, determining the geomorphic features and objective environmental features of the similar area; Determining shared tag information according to the geomorphic features and the objective environmental features; Based on the common tag information, video tag information is determined.

2. A video tag sharing and multiplexing method according to claim 1, characterized in that: The city video image information is divided to obtain a plurality of sub-image information, including: Determining video element information according to the city video image information; Determining element classification according to the video element information; Based on the element classification, determining an image division standard; Based on the image division standard, the plurality of sub-image information is obtained.

3. A video tag sharing and multiplexing method according to claim 1, characterized in that: The determining of the similar area according to the sub-image information and the preset standard image information includes: Extracting features from the sub-image information to determine first feature information; Extracting features from the preset standard image information to determine second feature information; Determining first edge information and second edge information according to the sub-image information and the preset standard image information; Calculating a similarity value between the first feature information and the second feature information; If the similarity value is greater than a preset similarity value, determining the degree of overlap between the first edge information and the second edge information; If the degree of overlap is greater than a preset degree of overlap, the similar area is determined.

4. A video tag sharing and multiplexing method according to claim 1, characterized in that: The determining of the geomorphic features and objective environmental features of the similar area includes: Determining a city landform image according to the city video image information; Determining the landform features based on the urban landform image; Obtain urban environmental information; Determining environmental factors according to the urban environmental information; Based on the environmental factors, the objective environmental characteristics are determined.

5. A video tag sharing and multiplexing method according to claim 1, characterized in that: The determining of the shared tag information also includes: Obtain city attribute information and scene information; Determining a classification standard according to the city attribute information and the scene information; Determine topic label information according to the classification standard; Based on the topic tag information, determine a tag tree; A preset shared tag library is established according to the tag tree.

6. A video tag sharing and multiplexing method according to claim 5, characterized in that: The determining of the common tag information according to the geomorphic features and the objective environmental features includes: Get city coordinate information; Determining a first keyword according to the geomorphic features and the city coordinate information; Determining a second keyword according to the objective environmental characteristics; Determine a common keyword according to the first keyword and the second keyword; The shared tag information is determined based on the shared keywords and the preset shared tag library.

7. A video tag sharing and multiplexing method according to claim 1, characterized in that: The determining of the video tag information based on the common tag information includes: Based on the shared tag information, determining a tag theme and a tag category; Determine a target shared tag according to the tag subject and the tag category; Determining first tag information according to the target common tag; Determining the accuracy of the first tag information; If the accuracy is greater than the preset accuracy, it is determined that the first tag information is the video tag information.

8. A video tag sharing and multiplexing device, characterized in that: include: A sub-image information determination module is used to obtain city video image information, divide the city video image information, and obtain a plurality of sub-image information; A similar region determination module, used to determine a similar region based on the sub-image information and preset standard image information; A similarity determination module, used to determine the similarity of each similar region; A feature determination module, configured to determine the geomorphic features and objective environmental features of the similar area if the similarity is greater than a preset similarity; A common tag information determination module, used to determine the common tag information according to the landform features and the objective environment features; The video tag information determining module is used to determine the video tag information based on the common tag information.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a video tag sharing and multiplexing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the video tag sharing and multiplexing method according to any one of claims 1 to 7.

Images