CN114510595A - Intelligent data analysis system based on big data - Google Patents

Abstract

The invention discloses an intelligent data analysis system based on big data, which comprises a big data updating library, a clothing classification module and a shoe outlet control module, and is characterized in that: the big data updating library is used for big data learning and updating clothes type characteristics, the clothes classification module is used for analyzing the type of the person wearing the shoe on the same day and judging the current trip travel type of the person, the shoe-out control module is used for controlling the shoe cabinet where the corresponding type of shoe is located to be pushed out according to the trip travel of the person, so that the person can directly and randomly select the shoes according with the travel type, the big data updating library is electrically connected with the clothes classification module, the clothes classification module is electrically connected with the shoe-out control module, the big data updating library comprises a data acquisition module and a characteristic learning module, and the data acquisition module is used for acquiring main profile characteristics of different types of clothes through a network.

Description

Intelligent data analysis system based on big data

technical field

The invention relates to the technical field of image processing, in particular to an intelligent data analysis system based on big data.

Background technique

In daily life, the basic needs of human beings are the basic needs of clothing, food, shelter and behavior. However, with the improvement of living conditions, people have higher and higher requirements for daily wear. Different occasions require different Dress up effect. After changing into suitable clothes in the cloakroom, people also need to go to the shoe cabinet to select the corresponding footwear to suit the overall outfit and travel.

With the continuous progress of society and the continuous improvement of people's living standards, people's pursuit of beauty is getting higher and higher, and the number of shoes in the shoe cabinet is becoming more and more. However, both clothing and footwear are generally divided into business, leisure There are three categories of clothing and sports. Among them, business clothing is mostly suits, with a smooth shape and a straight silhouette. The overall shape and style of leisure clothing are diverse, with twists and turns and dense clothing outlines, while sports clothing is looser and has more outlines. It changes regularly in a large wave shape at the bend.

However, the pace of urban life is accelerating. Many times, when people are in the cloakroom and ready to go out, there are many shoes in the shoe cabinet. It is difficult to identify and find the shoes that match the clothes at a glance. , a serious waste of time to go out, and even cause the trip to be late. Therefore, it is necessary to design an intelligent data analysis system based on big data that has strong practicability and can intelligently launch footwear according to clothing.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an intelligent data analysis system based on big data to solve the problems raised in the above background art.

In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent data analysis system based on big data, including a big data update library, a clothing classification module and a shoe control module, the big data update library is used for big data learning and updating clothes Type features, the clothing classification module is used to analyze the type of personal wear on the day and determine the type of the individual's current travel itinerary, and the shoe out control module is used to control the corresponding type of shoes according to the personal travel itinerary. The shoes that conform to the itinerary type are directly selected arbitrarily, the big data update library is electrically connected with the clothing classification module, and the clothing classification module is electrically connected with the shoe output control module.

According to the above technical solution, the big data update library includes a data acquisition module and a feature learning module, the data acquisition module is used to collect main outline features of different types of clothing through a network, and the feature learning module is electrically connected to the data acquisition module, The feature learning module is used for learning and sorting out the comprehensive feature contour curve data of different types of clothes.

According to the above technical solution, the clothing classification module includes a photosensitive photographing unit, an imaging data analysis module and a logic judgment module, the photosensitive photographing unit is used to trigger the photographing of an image according to the photosensitive transformation signal, and the imaging data analysis module is electrically connected to the photosensitive photographing unit. connected, the imaging data analysis module is used to analyze and calculate the type of clothing that the current individual wears according to the imaging information, the logic judgment module is electrically connected with the imaging data analysis module and the big data update library, and the logic judgment module is used for according to the clothing type. Analyze and determine the current travel itinerary type of an individual.

According to the above technical solution, the shoe output control module includes an inductive label unit and an execution unit, the inductive label unit is used to record the footwear data, and fit with the shoe cabinet for inductive transmission, and the execution unit is used to control the shoe cabinet in The bottom of the corresponding shoe is moved, so that the corresponding shoe is moved out from the inside of the shoe cabinet.

According to the above technical solution, the imaging data analysis module includes a recognizing and matting sub-module, a contour fitting sub-module and a data calculation sub-module, and the recognizing and matting sub-module is used to perform clothing outline clipping on the imaging picture, and the outline The fitting sub-module is used for fitting the contour line to the outline of the clothing picture after buttoning and cutting, and the data calculating sub-module is used for calculating the fluctuation value of the contour line and analyzing and judging the clothing type.

According to the above technical solution, the operation method of the intelligent data analysis system based on big data includes the following steps:

Step S1: the big data update library continuously updates the current clothing body style data of different types, and organizes the learning body style feature data to obtain the main feature database of different types of clothing;

Step S2: After getting up, the individual enters the cloakroom according to the current itinerary type to change the type of clothing that matches the itinerary, and arranges his clothes in front of the mirror;

Step S3: when the individual is at the mirror, the clothing classification module captures the current individual image, analyzes and judges the clothing type, judges the current travel type of the individual, and transmits the judgment result to the shoe control module in the form of an electrical signal;

Step S4: The shoe-out control module matches the same type of sensing tag units according to the current itinerary type, and executes movement at the shoe cabinet where the same sensing tag unit is located, so as to control the corresponding type of shoes to be removed from the inside of the shoe cabinet.

According to the above technical solution, the step S3 further includes the following steps:

Step S31: the photosensitive photographing unit senses ambient light in real time, and converts the sensed photosensitive signal into an electrical signal;

Step S32: when the individual is at the mirror, the body blocks the light source in the cloakroom, the photosensitive shooting unit senses the weakening of the light and triggers the electrical signal to shoot, and transmits the electrical signal of the captured image to the imaging data analysis module;

Step S33: the imaging data analysis module obtains the image data of the clothing worn by the individual in front of the mirror, and after performing data analysis on the image data, transmits the electrical signal of the data analysis result to the logic judgment module;

Step S34: The logic judgment module obtains the main characteristic data of different types of clothing in the big data update database and judges the data analysis results of the clothing currently worn by the individual, and obtains the current travel itinerary type of the individual after judging the current personal clothing type.

According to the above technical solution, the step S33 further includes the following steps:

Step S331: After acquiring the image data captured by the photosensitive capturing unit, the recognition and matting sub-module intelligently recognizes the image;

Step S332: according to the difference in depth of field between the person and the background in the image, matting the picture of the person in the image;

Step S333: the image after the cutout is a personal body image, and the contour fitting submodule calibrates the contour of the personal body image at a fixed interval distance, and connects the calibrated points to form a personal body contour fitting line;

Step S334: the data calculation module intercepts a segment of the personal body fitting line, and connects the two ends of the line segment to obtain a standard line, and sequentially measures the distances from all calibration point values in this segment of the personal body fitting line to the standard line;

Step S335: Taking one side of the standard line as positive and the other side as negative, obtain a sequence of distances {l ₁ , l ₂ , l ₃ ...l _n } from all calibration points to the standard line;

Step S336: Randomly obtain any value in the sequence, and when the values on both sides of it are positive and negative, mark the current value, and finally obtain the number m of marked values in the current sequence, and pass the marked value m and all calibration points. The ratio of n gets the fluctuation frequency H of the current contour;

Step S337: Calculate the fluctuation degree S ² of all calibration points in the personal body fitting line relative to the standard line by using the variance formula.

According to the above technical solution, the calculation formula of the fluctuation frequency H of the current contour in the step S336 is:

In the formula, when the number m of marked values is larger, more adjacent values in the sequence are positive and negative, and the fluctuation frequency is higher relative to the standard line.

In the step S337, the calculation ^formula of the fluctuation degree S2 of all the calibration points in the personal body fitting line relative to the standard line is:

In the formula, the degree of fluctuation of the sequence relative to the standard line is calculated by the variance formula. When the degree of dispersion between the calibration point as a whole and the standard line is large, the degree of fluctuation is greater.

According to the above technical solution, the step S34 further includes:

Step S341: The logic judgment module obtains the fluctuation frequency and fluctuation degree standards of the main clothing styles corresponding to the business, leisure and sports clothing respectively by acquiring the big data update library;

Step S342: Obtain the data analyzed and calculated by the current data calculation sub-module;

Step S343: when the fluctuation frequency H is relatively large, the logic judgment module judges that it is casual clothing, and outputs the itinerary type of free travel;

Step S344: when the fluctuation frequency H is small and the fluctuation degree S2 is large, the logic judgment module judges that it is sports clothing, and outputs the itinerary type of the sports trip ^;

Step S345: When the fluctuation frequency H is small and the fluctuation degree ^S2 is small, the logic judgment module judges that it is business clothing, and outputs the itinerary type of business travel.

Compared with the prior art, the beneficial effects achieved by the present invention are: the present invention, by being provided with a big data update library, a clothing classification module and a shoe output control module, can monitor daily clothing, judge the type of clothing and automatically control The shoe cabinet removes the same type of shoes for individuals to directly pick up and wear them, which greatly reduces the time wasted by rummaging for matching shoes when traveling, and improves travel efficiency.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the attached image:

FIG. 1 is a schematic diagram of the composition of the system modules of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Please refer to FIG. 1, the present invention provides a technical solution: an intelligent data analysis system based on big data, including a big data update library, a clothing classification module and a shoe control module, the big data update library is used for big data to learn and update clothing type characteristics, clothing The classification module is used to analyze the type of personal wear on the day and determine the current travel itinerary type of the individual. The shoe out control module is used to control the shoe cabinet where the corresponding type of shoes is located according to the personal travel itinerary. Arbitrary selection, the big data update library is electrically connected with the clothing classification module, and the clothing classification module is electrically connected with the shoe control module; by setting the big data update library, the clothing classification module and the shoe control module, the daily clothing can be monitored and judged. Wear the type of clothing and automatically control the shoe cabinet to remove the same type of shoes for individuals to directly pick up and wear them, which greatly reduces the time wasted by rummaging for matching shoes when traveling, and improves travel efficiency.

The big data update library includes a data acquisition module and a feature learning module. The data acquisition module is used to collect the main outline features of different types of clothing through the network. The feature learning module is electrically connected to the data acquisition module. The feature learning module is used to learn to organize different types of clothing. Characteristic profile curve data.

The clothing classification module includes a photosensitive shooting unit, an imaging data analysis module and a logic judgment module. The photosensitive shooting unit is used for triggering the shooting of images according to the photosensitive transformation signal, the imaging data analysis module is electrically connected with the photosensitive shooting unit, and the imaging data analysis module is used according to the imaging information. Analyzing and calculating the clothing type currently worn by the individual, the logic judgment module is electrically connected with the imaging data analysis module and the big data update library, and the logic judgment module is used for analyzing and judging the current travel itinerary type of the individual according to the clothing type.

The shoe-out control module includes an inductive label unit and an execution unit. The inductive label unit is used to record the shoe data and inductively transmit with the shoe cabinet. The execution unit is used to control the bottom movement of the shoe cabinet at the corresponding shoe, so that the corresponding shoe Classes are removed from the inside of the shoe cabinet.

The imaging data analysis module includes a recognizing and matting sub-module, a contour fitting sub-module and a data computing sub-module. The recognizing and matting sub-module is used to perform clothing contour clipping on the imaging picture, and the contour fitting sub-module is used for clipping and clipping. The outline of the clothing picture fits the outline, and the data calculation sub-module is used to calculate the fluctuation value of the outline and analyze and judge the type of clothing.

The operation method of the intelligent data analysis system based on big data includes the following steps:

Step S1: the big data update library continuously updates the current clothing body style data of different types, and organizes the learning body style feature data to obtain the main feature database of different types of clothing;

Step S2: After getting up, the individual enters the cloakroom according to the current itinerary type to change the type of clothing that matches the itinerary, and arranges his clothes in front of the mirror;

Step S3: when the individual is at the mirror, the clothing classification module captures the current individual image, analyzes and judges the clothing type, judges the current travel type of the individual, and transmits the judgment result to the shoe control module in the form of an electrical signal;

Step S4: the shoe-out control module matches the same type of sensing tag unit according to the current itinerary type, and executes movement to the shoe cabinet where the same sensing tag unit is located, so as to control the corresponding type of shoes to be moved out from the inside of the shoe cabinet; thereby greatly reducing travel When choosing the time to find the corresponding type of shoes in the shoe cabinet, it can effectively avoid delaying the travel itinerary.

Step S3 further includes the following steps:

Step S31: the photosensitive photographing unit senses ambient light in real time, and converts the sensed photosensitive signal into an electrical signal;

Step S32: when the individual is at the mirror, the body blocks the light source in the cloakroom, the photosensitive shooting unit senses the weakening of the light and triggers the electrical signal to shoot, and transmits the electrical signal of the captured image to the imaging data analysis module;

Step S33: the imaging data analysis module obtains the image data of the clothing worn by the individual in front of the mirror, and after performing data analysis on the image data, transmits the electrical signal of the data analysis result to the logic judgment module;

Step S34: The logic judgment module obtains the main characteristic data of different types of clothing in the big data update database and judges the data analysis results of the clothing currently worn by the individual, and obtains the current travel itinerary type of the individual after judging the current personal clothing type.

Step S33 further includes the following steps:

Step S331: After acquiring the image data captured by the photosensitive capturing unit, the recognition and matting sub-module intelligently recognizes the image;

Step S332: according to the difference in depth of field between the person and the background in the image, matting the picture of the person in the image;

Step S333: the image after the cutout is a personal body image, and the contour fitting submodule calibrates the contour of the personal body image at a fixed interval distance, and connects the calibrated points to form a personal body contour fitting line;

Step S334: the data calculation module intercepts a segment of the personal body fitting line, and connects the two ends of the line segment to obtain a standard line, and sequentially measures the distances from all calibration point values in this segment of the personal body fitting line to the standard line;

Step S335: Taking one side of the standard line as positive and the other side as negative, obtain a sequence of distances {l ₁ , l ₂ , l ₃ ...l _n } from all calibration points to the standard line;

Step S336: Randomly obtain any value in the sequence, and when the values on both sides of it are positive and negative, mark the current value, and finally obtain the number m of marked values in the current sequence, and pass the marked value m and all calibration points. The ratio of n gets the fluctuation frequency H of the current contour;

Step S337: Calculate the fluctuation degree S ² of all calibration points in the personal body fitting line relative to the standard line by using the variance formula.

The calculation formula of the fluctuation frequency H of the current contour in step S336 is:

In the formula, when the number m of marked values is larger, more adjacent values in the sequence are positive and negative, and the fluctuation frequency is higher relative to the standard line.

In step S337, the calculation ^formula of the fluctuation degree S2 of all calibration points in the personal body fitting line relative to the standard line is:

In the formula, the degree of fluctuation of the sequence relative to the standard line is calculated by the variance formula. When the degree of dispersion between the calibration point as a whole and the standard line is large, the degree of fluctuation is greater.

Step S34 further includes:

Step S341: The logic judgment module obtains the fluctuation frequency and fluctuation degree standards of the main clothing styles corresponding to the business, leisure and sports clothing respectively by acquiring the big data update library;

Step S342: Obtain the data analyzed and calculated by the current data calculation sub-module;

Step S343: when the fluctuation frequency H is relatively large, the logic judgment module judges that it is casual clothing, and outputs the itinerary type of free travel;

Step S344: when the fluctuation frequency H is small and the fluctuation degree S2 is large, the logic judgment module judges that it is sports clothing, and outputs the itinerary type of the sports trip ^;

Step S345: When the fluctuation frequency H is small and the fluctuation degree ^S2 is small, the logic judgment module judges that it is business clothing, and outputs the itinerary type of business travel.

Example: After the individual wakes up, the current itinerary is for travel and business negotiation. After entering the cloakroom and changing into formal clothes, he arranges his clothes in front of the mirror. The clothes classification module captures the current personal image, and performs a cutout to calculate the image data. The fluctuation frequency of the contour is H = 4%, and the fluctuation degree S ² = 3 cm. It is obtained from the large database that the fluctuation frequency is greater than 30%, and the fluctuation degree is greater than 10 cm. The data is larger, because 4% < 30%, and 3 cm < 10 cm , the logic judgment module judges that it is business clothing, outputs the itinerary type of business travel, and then matches the location of the sensor tag of the business shoes at the shoe cabinet, and finally the shoe cabinet moves at the bottom of the business shoes, so that the business shoes are removed from the shoe cabinet. Move out inside.

It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus.

Finally, it should be noted that the above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, the The technical solutions described in the foregoing embodiments may be modified, or some technical features thereof may be equivalently replaced. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. an intelligent data analysis system based on big data, comprising a big data update library, a clothing classification module and a shoe control module, it is characterized in that: the big data update library is used for big data to learn and update clothing type features, and the clothing classification The module is used to analyze the type of personal wear on the day and determine the current travel itinerary type of the individual. The shoe out control module is used to control the shoe cabinet where the shoes of the corresponding type are located according to the personal travel itinerary. The big data update library is electrically connected with the clothing classification module, and the clothing classification module is electrically connected with the shoe output control module. 2. the intelligent data analysis system based on big data according to claim 1, is characterized in that: described big data update library comprises data collection module and feature learning module, and described data collection module is used for collecting different types of clothing by network The feature learning module is electrically connected with the data acquisition module, and the feature learning module is used for learning and sorting out the comprehensive feature contour curve data of different types of clothes. 3. The intelligent data analysis system based on big data according to claim 2, wherein the clothing classification module comprises a photosensitive shooting unit, an imaging data analysis module and a logical judgment module, and the photosensitive shooting unit is used for according to the photosensitive shooting unit. The transformation signal triggers the shooting of images, the imaging data analysis module is electrically connected with the photosensitive shooting unit, the imaging data analysis module is used to analyze and calculate the type of clothing that the current individual is wearing according to the imaging information, and the logic judgment module is connected to the imaging data analysis module and The big data update library is electrically connected, and the logic judgment module is used for analyzing and judging the current travel itinerary type of the individual according to the clothing type. 4. The intelligent data analysis system based on big data according to claim 3, wherein the shoe-out control module comprises an inductive label unit and an execution unit, and the inductive label unit is used for recording footwear data, and with The shoe cabinet is fitted with inductive transmission, and the execution unit is used to control the movement of the bottom of the shoe cabinet at the corresponding shoe, so that the corresponding shoe can be moved out from the inside of the shoe cabinet. 5. The intelligent data analysis system based on big data according to claim 4, characterized in that: the imaging data analysis module comprises a recognition matting sub-module, a contour fitting sub-module and a data calculation sub-module, and the recognition matting sub-module The figure sub-module is used to deduct and cut the clothing outline on the imaged image, the contour fitting sub-module is used to fit the outline of the deducted garment image, and the data calculation sub-module is used to calculate the fluctuation value of the outline. And analyze and judge the type of clothing. 6. The big data-based intelligent data analysis system according to claim 5, wherein the operation method of the big data-based intelligent data analysis system comprises the following steps: Step S1: the big data update library continuously updates the current clothing body style data of different types, and organizes the learning body style feature data to obtain the main feature database of different types of clothing; Step S2: After getting up, the individual enters the cloakroom according to the current itinerary type to change the type of clothing that matches the itinerary, and arranges his clothes in front of the mirror; Step S3: when the individual is at the mirror, the clothing classification module captures the current individual image, analyzes and judges the clothing type, judges the current travel type of the individual, and transmits the judgment result to the shoe control module in the form of an electrical signal; Step S4: The shoe-out control module matches the same type of sensing tag units according to the current itinerary type, and executes movement at the shoe cabinet where the same sensing tag unit is located, so as to control the corresponding type of shoes to be removed from the inside of the shoe cabinet. 7. The intelligent data analysis system based on big data according to claim 6, wherein the step S3 further comprises the following steps: Step S31: the photosensitive photographing unit senses ambient light in real time, and converts the sensed photosensitive signal into an electrical signal; Step S32: when the individual is at the mirror, the body blocks the light source in the cloakroom, the photosensitive shooting unit senses the weakening of the light and triggers the electrical signal to shoot, and transmits the electrical signal of the captured image to the imaging data analysis module; Step S33: the imaging data analysis module obtains the image data of the clothing worn by the individual in front of the mirror, and after performing data analysis on the image data, transmits the electrical signal of the data analysis result to the logic judgment module; Step S34: The logic judgment module obtains the main characteristic data of different types of clothing in the big data update database and judges the data analysis results of the clothing currently worn by the individual, and obtains the current travel itinerary type of the individual after judging the current personal clothing type. 8. The intelligent data analysis system based on big data according to claim 7, wherein the step S33 further comprises the following steps: Step S331: After acquiring the image data captured by the photosensitive capturing unit, the recognition and matting sub-module intelligently recognizes the image; Step S332: according to the difference in depth of field between the person in the image and the background, the image of the person in the image is cut out; Step S333: the image after the cutout is a personal body image, and the contour fitting submodule calibrates the contour of the personal body image at a fixed interval distance, and connects the calibrated points to form a personal body contour fitting line; Step S334: the data calculation module intercepts a segment of the personal body fitting line, and connects the two ends of the line segment to obtain a standard line, and sequentially measures the distances from all calibration point values in this segment of the personal body fitting line to the standard line; Step S335: Taking one side of the standard line as positive and the other side as negative, obtain a sequence of distances {l ₁ , l ₂ , l ₃ ...l _n } from all calibration points to the standard line; Step S336: Randomly obtain any value in the sequence, and when the values on both sides of it are positive and negative, mark the current value, and finally obtain the number m of marked values in the current sequence, and pass the marked value m and all calibration points. The ratio of n gets the fluctuation frequency H of the current contour; Step S337: Calculate the fluctuation degree S ² of all calibration points in the personal body fitting line relative to the standard line by using the variance formula. 9. The intelligent data analysis system based on big data according to claim 8, wherein the calculation formula of the fluctuation frequency H of the current profile in the step S336 is:

In the formula, when the number m of marked values is larger, more adjacent values in the sequence are positive and negative, and the fluctuation frequency is higher relative to the standard line. In the step S337, the calculation ^formula of the fluctuation degree S2 of all the calibration points in the personal body fitting line relative to the standard line is:

In the formula, the degree of fluctuation of the sequence relative to the standard line is calculated by the variance formula. When the degree of dispersion between the calibration point as a whole and the standard line is large, the degree of fluctuation is greater. 10. The intelligent data analysis system based on big data according to claim 9, wherein the step S34 further comprises: Step S341: The logic judgment module obtains the fluctuation frequency and fluctuation degree standards of the main clothing styles corresponding to the business, leisure and sports clothing respectively by acquiring the big data update library; Step S342: Obtain the data analyzed and calculated by the current data calculation sub-module; Step S343: when the fluctuation frequency H is relatively large, the logic judgment module judges that it is casual clothing, and outputs the itinerary type of free travel; Step S344: when the fluctuation frequency H is small and the fluctuation degree S2 is large, the logic judgment module judges that it is sports clothing, and outputs the itinerary type of the sports trip ^; Step S345: When the fluctuation frequency H is small and the fluctuation degree ^S2 is small, the logic judgment module judges that it is business clothing, and outputs the itinerary type of business travel.

Images