Video special effect adaptive feedback processing system and method based on tourist feature analysis

Abstract

The embodiment of the invention discloses a video special effect adaptive feedback processing system and method based on tourist feature analysis, and the system comprises a tourist feature scoring module which carries out the scoring of tourist types based on the shot video data; classifying the final score into a corresponding section; the special effect scoring module is used for scoring a preset video special effect; dividing all the special effect combinations into different sections according to different scores to form a plurality of subsets of the special effect combinations; the matching module is used for matching the final score and the subset in combination with a preset matching mode so as to obtain an initial matching relationship; the feedback module is used for carrying out self-adaptive adjustment on the tourist type score and the matching relationship according to the feedback data of the formed short video purchase rate so as to realize automatic adjustment of the matching relationship between the tourist type and the special effect combination; the method has the advantages that corresponding video special effects are customized for different tourists, and a more accurate special effect matching result matched with the maximum purchase rate is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of short video marketing in the Vlog shooting business of scenic spots, and specifically to a video special effect adaptive feedback processing system and method based on tourist feature analysis. Background Art

[0002] In the business of automatically shooting short videos in scenic spots, tourists obtain their own travel commemorative videos through QR codes. Tourists pay for the purchase after previewing the short videos and being satisfied. How to improve tourists' satisfaction with short videos and thus increase the purchase rate is an important task. Adding various creative special effects to tourists' videos is an effective means. But different tourists have different tastes, personalities, and preferences. For example, young people like special effects that are more animated, while the elderly like special effects that are more simple; women like cute special effects, while men like cool and explosive special effects. At present, most other products adopt the method of users pre-selecting the required special effects. On the one hand, it is inconvenient to operate, time-consuming and laborious; on the other hand, the artistic level of tourists is uneven, and it is difficult to combine their own characteristics with special effects in a short time, resulting in poor film effects. Whether it is a long operation or a poor video effect, it will affect the purchase rate of short videos.

[0003] Therefore, this application proposes a solution for video special effects adaptive feedback and matching mechanism based on tourist feature analysis, which allows it to automatically adjust the special effects combination according to the differences in tourists' own characteristics and feedback on purchase rates, to achieve more accurate special effects matching results that match the maximum purchase rate. Summary of the invention

[0004] In order to overcome the deficiencies in the prior art, the object of the present invention is to provide a video special effects adaptive feedback processing system and method based on visitor feature analysis.

[0005] To achieve the above objectives, in a first aspect, an embodiment of the present invention provides a video special effects adaptive feedback processing system based on visitor feature analysis, comprising:

[0006] Visitor characteristic scoring module, used to:

[0007] Scoring of tourist types based on captured video data;

[0008] According to the final score, they are divided into corresponding sections;

[0009] Special effects scoring module, used for:

[0010] Rate preset video effects;

[0011] Divide all special effect combinations into different sections according to different scores to form multiple subsets of special effect combinations;

[0012] A matching module, used to match the final score and the subset in combination with a preset matching mode to obtain an initial matching relationship;

[0013] The feedback module is used to adaptively adjust the visitor type score and matching relationship according to the feedback data of the short video purchase rate, so as to automatically adjust the matching relationship between the visitor type and the special effect combination.

[0014] As a preferred implementation of the present application, the tourist type scoring based on the shot video data includes sub-items: body clothing feature scoring, smile frequency scoring, age scoring, gender scoring and comprehensive style scoring.

[0015] As a preferred implementation mode of the present application, the preset video special effects include music, stickers, filters, transitions and animation special effects types, and each type contains a variety of different styles and is saved as different subsets.

[0016] As a preferred implementation of the present application, the scoring of preset video effects specifically includes: music style scoring, texture style scoring, filter style scoring, transition style scoring, animation style scoring and comprehensive scoring.

[0017] As a preferred implementation of the present application, the adaptive adjustment of the tourist type score and the matching relationship includes a tourist type score self-adjustment mechanism and a matching mode self-adjustment mechanism.

[0018] As a preferred implementation of the present application, the tourist type score self-adjustment mechanism includes:

[0019] Automatically adjust the weight of each sub-item in the type score and loop through all weight values ​​in a preset manner.

[0020] As a preferred implementation of the present application, the matching mode self-adjustment mechanism includes:

[0021] First, according to the initial matching relationship, traverse various special effect combinations in the corresponding set;

[0022] Match across subsets, and then traverse the various special effect combinations in them;

[0023] A round of iteration is completed based on the set time period until the final matching relationship between the tourist and special effect combination is recorded.

[0024] In a second aspect, an embodiment of the present invention further provides a method for processing video special effects adaptive feedback based on visitor feature analysis, the method comprising:

[0025] Score the tourist types based on the video data and divide them into corresponding sections according to the final scores;

[0026] Rate preset video effects;

[0027] Divide all special effect combinations into different sections according to different scores to form multiple subsets of special effect combinations;

[0028] Matching the final score and the subset in combination with a preset matching mode to obtain an initial matching relationship;

[0029] According to the feedback data formed, the tourist type score and the matching relationship are adaptively adjusted to achieve automatic adjustment of the matching relationship between the tourist type and the special effect combination.

[0030] By implementing the embodiment of the present invention, each tourist is scored and the special effects are double-scored, the characteristics of the tourist are matched with the special effects, and the relationship between the tourist type and the special effects is automatically adjusted based on the feedback data. The corresponding video special effects are tailored for each different tourist, thereby achieving a more accurate special effects matching result that matches the maximum purchase rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0032] Figure 1 It is a principle block diagram of a video special effect adaptive feedback processing system based on tourist feature analysis provided by an embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram of a process of tourist type scoring provided by an embodiment of the present invention;

[0034] Figure 3 is a schematic diagram of a special effect scoring process provided by an embodiment of the present invention;

[0035] Figure 4 It is a process schematic diagram of a tourist type scoring self-adjustment mechanism provided by an embodiment of the present invention;

[0036] Figure 5 It is a process schematic diagram of a matching mode self-adjustment mechanism provided by an embodiment of the present invention;

[0037] Figure 6 It is a flow chart of a method for processing video special effects adaptive feedback based on visitor feature analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0039] It should be understood that when used in this specification and the appended claims, the terms "comprise" and "include" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0040] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0041] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0042] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the invention belongs.

[0043] Please refer to Figures 1 to 5 , is a video special effects adaptive feedback processing system based on tourist feature analysis provided by the first embodiment of the present invention, comprising:

[0044] Visitor characteristic scoring module, used to:

[0045] Scoring of tourist types based on captured video data;

[0046] According to the final score, they are divided into corresponding sections;

[0047] Special effects scoring module, used for:

[0048] Rate preset video effects;

[0049] Divide all special effect combinations into different sections according to different scores to form multiple subsets of special effect combinations;

[0050] A matching module, used to match the final score and the subset in combination with a preset matching mode to obtain an initial matching relationship;

[0051] The feedback module is used to adaptively adjust the visitor type score and matching relationship according to the generated feedback data, so as to automatically adjust the matching relationship between the visitor type and the special effect combination.

[0052] In this embodiment, the video data is obtained by shooting short videos with fixed cameras installed on tourist tour routes;

[0053] Reference Figure 2 The sub-items of the tourist type scoring based on the captured video data include: tourist clothing feature scoring, smile frequency scoring, age range scoring, gender scoring and comprehensive style scoring.

[0054] Specifically, human body detection is first performed: human body detection of tourists in video data is completed by a pre-trained deep learning model, and the detection result is a pixel-level human body result;

[0055] Tourist clothing feature scoring: Tourist clothing feature scoring is divided into upper body clothing and lower body clothing. The pre-trained deep learning model recognizes the upper body and lower body respectively; it is divided into three categories: lively, ordinary, and conservative. The scores are given 10 points, 5 points, and 0 points respectively.

[0056] Smile frequency score: All camera snapshots in the project are used to detect smiles using a pre-trained deep learning model. For the same tourist, if the frequency of smiling faces in more than 50% of the camera shots is greater than 50%, it is considered a cheerful type; if the frequency of smiling faces in 20%-50% of the camera shots is a normal type; and if the frequency of smiling faces in less than 20% of the shots is less than 20%, it is considered a serious type. The scores are 10, 5, and 0 respectively.

[0057] Age range scoring: The age range of tourists is divided, and the recognition results are output by the pre-trained deep learning model. They are divided into four categories: children, youth, middle-aged, and elderly. They are given 10 points, 8 points, 6 points, and 4 points respectively.

[0058] Gender scoring: The tourists are identified by gender, and the pre-trained deep learning model outputs the identification results. They are divided into female and male. They are given 10 points and 5 points respectively.

[0059] Comprehensive style score: take four weight parameters, denoted as a, b, c, and d respectively.

[0060] Comprehensive style score = a*body clothing score + b*smile score + c*age score + d*gender score.

[0061] Initialization assignment: a=b=c=d=1, and a, b, c, d are all integers between 1 and 10.

[0062] The final score is divided into 5 sections, namely A (0-20), B (21-40), C (41-60), D (61-80), and E (81-100).

[0063] Furthermore, the preset video special effects include music, stickers, filters, transitions and animation special effects types, and each type includes a variety of different styles and is saved as different subsets.

[0064] Reference Figure 3 The preset video special effects are scored, specifically including: music style scoring, texture style scoring, filter style scoring, transition style scoring, animation style scoring and comprehensive scoring.

[0065] Specifically, music style scoring: music is divided into three subsets according to the frequency of the audio: fast rhythm, normal rhythm and slow rhythm, and is assigned 20 points, 10 points and 0 points respectively.

[0066] Sticker style scoring: divided into three subsets: cartoon characters, outline stickers, and character OSD, which are assigned 20 points, 10 points, and 0 points respectively.

[0067] Filter style rating: divided into four subsets: skin beauty, vividness, texture, and nostalgia, with 20 points, 15 points, 10 points, and 5 points respectively.

[0068] Transition style score: divided into two subsets: dynamic three-dimensional and classic, with 20 points and 10 points respectively.

[0069] Animation style rating: divided into three subsets: gorgeous dynamics, ordinary dual-camera fusion, and no animation, which are assigned 20 points, 10 points, and 0 points respectively.

[0070] Comprehensive score = music style score + sticker style score + filter style score + transition style score + animation style score.

[0071] The final score is divided into 5 sections, namely AA (0-20), BB (21-40), CC (41-60), DD (61-80), and EE (81-100). All special effects combinations are divided into different sections according to different scores to form subsets of 5 special effects combinations.

[0072] In this embodiment, the preset matching mode is the matching of the corresponding segments; based on the above examples, the initial matching is performed in the manner of A-AA, B-BB, C-CC, D-DD, and E-EE.

[0073] Feedback data is purchase rate feedback, including: statistics of short video purchase rates of tourists for 7 days a week to form data, and save the current maximum purchase rate value, recorded as max; and the corresponding matching relationship. The purchase rate is calculated as follows: assuming that X tourists scan the code to preview the short video, and Y tourists purchase it, then the purchase rate Z = (Y / X)*100%.

[0074] In this embodiment, the adaptive adjustment of the visitor type score and the matching relationship includes a visitor type score self-adjustment mechanism and a matching mode self-adjustment mechanism.

[0075] The above scheme, by scoring each tourist and doubly scoring the special effects, combines the characteristics of the tourist with the special effects for matching, and then automatically adjusts the relationship between tourist type and special effects based on feedback data, tailors the corresponding video special effects for each different tourist, and achieves more accurate special effects matching results that match the maximum purchase rate.

[0076] The tourist type score self-adjustment mechanism is Figure 4 Style scores in are adjusted automatically, including:

[0077] Automatically adjust the weight of each sub-item in the type score, and loop through all weight values ​​in a preset manner; the specific process is as follows Figure 4 shown.

[0078] The matching mode self-adjustment mechanism is Figure 5 The matching score self-adjustment mechanism in includes:

[0079] First, according to the initial matching relationship, traverse various special effect combinations in the corresponding set;

[0080] Match across subsets, and then traverse the various special effect combinations in them;

[0081] A round of iteration is completed based on the set time period until the final matching relationship between the tourist and special effect combination is recorded.

[0082] For example, the initialization is B-BB matching. First, traverse all combinations in BB, record the highest purchase rate and the corresponding matching relationship; then match B-AA and B-CC, and repeat the above operations until all traversals of the initial matching set and adjacent sets are completed.

[0083] An adaptive feedback processing system for video special effects based on tourist feature analysis provided by an embodiment of the present invention can distinguish different groups of people's different tastes in video appreciation and different personality preferences according to the dimensions of tourists' clothing characteristics, mood state, personality and age range, and automatically match appropriate special effects accordingly to achieve better short video revenue results.

[0084] Based on the same inventive concept, Figure 6 Based on the video special effects adaptive feedback processing system based on tourist feature analysis provided in the above embodiment, the embodiment of the present invention further provides a video special effects adaptive feedback processing method based on tourist feature analysis, the method comprising:

[0085] S101, scoring the tourist types based on the captured video data, and classifying them into corresponding sections according to the final scores;

[0086] S102, scoring the preset video special effects;

[0087] S103, dividing all special effect combinations into different sections according to different scores to form a plurality of subsets of special effect combinations;

[0088] S104, matching the final score and the subset in combination with a preset matching mode to obtain an initial matching relationship;

[0089] S105, adaptively adjusting the visitor type score and the matching relationship based on the feedback data of the short video purchase rate, so as to automatically adjust the matching relationship between the visitor type and the special effect combination.

[0090] Furthermore, the sub-items of the tourist type scoring based on the captured video data include: tourist clothing feature scoring, smile frequency scoring, age range scoring, gender scoring and comprehensive style scoring;

[0091] The scoring of the preset video special effects specifically includes: music style scoring, texture style scoring, filter style scoring, transition style scoring, animation style scoring and comprehensive scoring.

[0092] In this embodiment, the adaptive adjustment of the visitor type score and the matching relationship includes a visitor type score self-adjustment mechanism and a matching mode self-adjustment mechanism.

[0093] The tourist type score self-adjustment mechanism includes:

[0094] Automatically adjust the weight of each sub-item in the type score, and loop through all weight values ​​in a preset manner;

[0095] The matching mode self-adjustment mechanism includes:

[0096] First, according to the initial matching relationship, traverse various special effect combinations in the corresponding set;

[0097] Match across subsets, and then traverse the various special effect combinations in them;

[0098] A round of iteration is completed based on the set time period until the final matching relationship between the tourist and special effect combination is recorded.

[0099] It should be noted that, in the above method claims, the specific implementation methods and beneficial effects of each step can be found in the above system embodiment section and will not be repeated here.

[0100] By implementing the embodiment of the present invention, each tourist is scored for his / her type and for the special effects, the tourist's own personality traits are matched with the special effects, and the relationship between the tourist type and the special effects is automatically adjusted based on the feedback data. The corresponding video special effects are tailored for each different tourist, thereby achieving a more accurate special effects matching result that matches the maximum purchase rate.

[0101] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the above-mentioned method for adaptive feedback processing of video special effects based on visitor feature analysis is implemented.

[0102] It should be understood that in the embodiments of the present invention, the processor referred to may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0106] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0108] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A video special effects adaptive feedback processing system based on tourist feature analysis, characterized in that: include: Visitor characteristic scoring module, used to: Scoring of tourist types based on captured video data; According to the final score, they are divided into corresponding sections; Special effects scoring module, used for: Rate preset video effects; Divide all special effect combinations into different sections according to different scores to form multiple subsets of special effect combinations; A matching module, used to match the final score and the subset in combination with a preset matching mode to obtain an initial matching relationship; The feedback module is used to adaptively adjust the visitor type score and matching relationship according to the feedback data of the short video purchase rate, so as to automatically adjust the matching relationship between the visitor type and the special effect combination.

2. The system according to claim 1, characterized in that The sub-items of the tourist type scoring based on the captured video data include: human clothing feature scoring, smile frequency scoring, age range scoring, gender scoring and comprehensive style scoring.

3. The system according to claim 1, characterized in that The preset video effects include music, stickers, filters, transitions and animation effects, and each type includes a variety of different styles and is saved as different subsets.

4. The system according to claim 3, characterized in that The scoring of the preset video special effects specifically includes: music style scoring, texture style scoring, filter style scoring, transition style scoring, animation style scoring and comprehensive scoring.

5. The system according to claim 2, characterized in that The adaptive adjustment of the visitor type score and the matching relationship includes a visitor type score self-adjustment mechanism and a matching mode self-adjustment mechanism.

6. The system according to claim 5, characterized in that The tourist type score self-adjustment mechanism includes: Automatically adjust the weight of each sub-item in the type score and loop through all weight values ​​in a preset manner.

7. The system according to claim 6, characterized in that The matching mode self-adjustment mechanism includes: First, according to the initial matching relationship, traverse various special effect combinations in the corresponding set; Match across subsets, and then traverse the various special effect combinations in them; A round of iteration is completed based on the set time period until the final matching relationship between the tourist and special effect combination is recorded.

8. A video special effects adaptive feedback processing method based on tourist feature analysis, characterized in that: The method comprises: Score the tourist types based on the video data and divide them into corresponding sections according to the final scores; Rate preset video effects; Divide all special effect combinations into different sections according to different scores to form multiple subsets of special effect combinations; Matching the final score and the subset in combination with a preset matching mode to obtain an initial matching relationship; According to the feedback data of the short video purchase rate, the tourist type score and the matching relationship are adaptively adjusted to achieve automatic adjustment of the matching relationship between the tourist type and the special effect combination.

9. The method according to claim 8, characterized in that The adaptive adjustment of the visitor type score and the matching relationship includes a visitor type score self-adjustment mechanism and a matching mode self-adjustment mechanism.

10. The method according to claim 9, characterized in that The tourist type score self-adjustment mechanism includes: Automatically adjust the weight of each sub-item in the type score, and loop through all weight values ​​in a preset manner; The matching mode self-adjustment mechanism includes: First, according to the initial matching relationship, traverse various special effect combinations in the corresponding set; Match across subsets, and then traverse the various special effect combinations in them; A round of iteration is completed based on the set time period until the final matching relationship between the tourist and special effect combination is recorded.

Images