Airline luggage feature recognition method, device and equipment and storage medium

Abstract

The invention discloses a luggage feature recognition method and device based on stacking efficiency and stacking toughness, equipment and a storage medium. The method comprises the following steps: firstly, collecting luggage feature information, and preprocessing the collected feature information; obtaining feature data; the length-width-height ratio of the luggage case is calculated according to the feature data, and the stacking efficiency evaluation value is calculated according to the length-width-height ratio; a luggage stacking toughness index system is obtained according to the feature data; obtaining a luggage stacking toughness evaluation value through a fuzzy evaluation method according to the luggage stacking toughness index system; and finally, an evaluation result and a feature visualization effect picture are obtained according to the stacking efficiency evaluation value and the stacking toughness evaluation value, the luggage feature recognition capacity and the aviation luggage stacking efficiency can be improved, luggage damage is reduced, the labor intensity of carrying workers is reduced, and the method has good application prospects along with promotion of intelligent airport construction.

Description

Technical Field

[0001] The present invention relates to the field of aviation baggage stacking feature recognition, and in particular to a baggage feature recognition method, device, equipment and storage medium based on stacking efficiency and stacking toughness. Background Art

[0002] With the rapid development of my country's civil aviation industry, the volume of civil aviation passenger transport and airport passenger throughput has continued to rise, and the volume of baggage transport has also risen accordingly. At present, except for the manual labor required to carry luggage to the luggage cart, the self-service check-in and luggage stacking process have basically been automated. Faced with a large amount of luggage, airport luggage handlers are under great pressure, labor-intensive, and inefficient, and workers are inevitably subject to overwork injuries; correspondingly, there will also be violent loading and unloading by loading and unloading workers, resulting in deformation and damage of passenger luggage. Baggage transportation issues account for a high proportion of airline complaints. It can be seen that the development of unmanned autonomous handling and stacking of luggage is in line with the inevitable trend of the construction and development of the four types of airports in the future. In order to realize the unmanned handling and stacking of aviation luggage, luggage size and weight information is an important data support. Therefore, a set of intelligent, high-precision, and strong stability feature recognition methods can improve the efficiency of luggage transportation and sorting, realize unmanned handling and stacking instead of heavy manual labor, and is conducive to the unmanned and automated process of aviation luggage transportation in the future, and improve airport operation efficiency.

[0003] The commonly used method for sensing baggage feature information is computer vision, which mainly includes binocular stereo vision, structured light method and other methods; binocular stereo vision method uses imaging equipment to obtain two images of the object to be measured from different positions, and obtains the three-dimensional geometric information of the baggage by calculating the position deviation between corresponding points of the images; structured light method projects specifically coded light to the baggage, calculates the time of the return light to obtain the three-dimensional information of the baggage. The disadvantage of this method is that it does not have enough depth and accuracy, and performs poorly in low-light environments.

[0004] The inventor has found through research that the baggage feature recognition method in the prior art still has at least the following defects:

[0005] The binocular stereo vision method is not suitable for scenes with sparse textures, and its measurement accuracy and speed depend on the algorithm. The structured light method is not capable of extracting features and cannot provide more direct data support for baggage stacking. Therefore, there is an urgent need for an identification method that can get rid of the excessive reliance on algorithms for detection speed and accuracy while solving the problem of insufficient baggage feature recognition capabilities.

[0006] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0007] The purpose of the present invention is to improve the baggage feature recognition capability and the baggage stacking efficiency.

[0008] The present invention provides a baggage feature recognition method based on stacking efficiency and stacking toughness, comprising the steps of:

[0009] S11, collecting baggage feature information, and preprocessing the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data;

[0010] S12, calculating the length-width-height ratio of the suitcase according to the characteristic data; and calculating the stacking efficiency evaluation value according to the length-width-height ratio;

[0011] S13, obtaining a baggage stacking resilience index system according to the characteristic data; obtaining a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes a primary index and a secondary index of baggage;

[0012] S14. Obtaining a feature evaluation result and a feature effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

[0013] Preferably, in the embodiment of the present invention, the preprocessing of the collected feature information includes:

[0014] Obtaining three-dimensional size data of the luggage according to the three-dimensional point cloud data, and calculating the normalization of the first-order moment of the image according to the three-dimensional size data to obtain the center of gravity position of the luggage;

[0015] The weight data is cleaned, and the variance of the cleaned data is calculated using the following formula:

[0016]

[0017] In the formula, σ 2 is the variance; N is the total number of available data samples after data cleaning; x i is a single sample value; μ is the mean of the sample data.

[0018] Preferably, in an embodiment of the present invention, the step of calculating the stacking efficiency evaluation value according to the aspect ratio includes:

[0019] S121, dividing the ratio of the length, width and height into a plurality of ratio intervals according to stability;

[0020] S122, according to the ratio interval being represented as a function in the corresponding coordinate system, calculating the degree of each of the ratio intervals in the first quadrant of the coordinate system, and calculating the proportion value of each of the ratio intervals according to the degree;

[0021] S123, using a Softmax function to process each of the ratio values ​​to obtain an initial stacking efficiency value;

[0022] S124, calculating the weight value of each ratio value in the stacking efficiency evaluation by using an entropy method;

[0023] S125 . Obtain a stacking efficiency evaluation value according to the initial stacking efficiency value and the weight value of each of the proportion values.

[0024] Preferably, in an embodiment of the present invention, obtaining the baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system includes:

[0025] S131. Construct a high-order CFA model based on the baggage stacking resilience index system through the following formula;

[0026] X=λ x φ+r

[0027] ρ=Γζ+ξ

[0028] In the formula, X is the secondary index; λ x is the first-order loading; φ is the first-order factor latent variable; r is the measurement error; ρ is the primary indicator; Γ is the loading of the second-order factor latent variable on the first-order factor latent variable; ζ is the second-order factor latent variable; ξ is the first-order factor residual;

[0029] S132, obtaining the standardized factor loading of each of the first-level indicators and the second-level indicators through AMOS26.0 structural equation model fitting analysis;

[0030] S133, according to the factor loading of the same facet in the high-order CFA model, the indicator weight value is calculated by the following formula;

[0031]

[0032] In the formula, y i is the indicator weight value; Q i is the factor loading of the indicator; n is the number of indicators at the same level; Q 1 +Q 2 +…+Q n It is the sum of the factor loadings of all indicators at the same level;

[0033] S134, based on the comment set of the secondary indicator, generate a primary indicator fuzzy judgment matrix based on the membership degree of the secondary indicator on the comment set; and generate a secondary indicator weight vector based on the weight value of each indicator;

[0034] S135, performing a first-level fuzzy evaluation on the first-level indicators according to the first-level indicator fuzzy judgment matrix and the second-level indicator weight vector; and obtaining a fuzzy judgment matrix of baggage stacking toughness according to the first-level fuzzy evaluation;

[0035] S136, performing a secondary fuzzy evaluation based on the fuzzy judgment matrix of the baggage stacking resilience and the indicator weight values ​​of the primary indicators;

[0036] S137, obtaining a fuzzy comprehensive evaluation value of the luggage according to the secondary fuzzy evaluation and the evaluation value; the evaluation value is obtained by dividing the corresponding comment set into multiple evaluation intervals and taking the median of each evaluation interval;

[0037] S138. Match the fuzzy comprehensive evaluation value with each evaluation interval to obtain a baggage stacking toughness evaluation value.

[0038] Preferably, in an embodiment of the present invention, constructing the comment set includes:

[0039] Quantify the impact of each secondary indicator on the primary indicator based on historical data;

[0040] The review set includes: very good, good, average, poor, and very poor.

[0041] Preferably, in the embodiment of the present invention,

[0042] The first-level indicators include: the center of gravity position, edge regularity coefficient, material and weight stability of the luggage;

[0043] The secondary indicators include: the exact center, corners and other positions corresponding to the center of gravity;

[0044] a shape corresponding to the edge regularity coefficient;

[0045] Soft and hard corresponding to the material.

[0046] Preferably, in an embodiment of the present invention, obtaining an evaluation result and a feature visualization effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value includes:

[0047] Generate a point cloud recognition result map according to the three-dimensional point cloud data;

[0048] Annotate the basic information of the suitcase on the point cloud recognition result diagram; the basic information includes: the centroid position of the suitcase, the length, width and height of the suitcase, the type of suitcase and the edge shape of the suitcase;

[0049] The stacking efficiency evaluation value and the stacking toughness evaluation value are displayed in the point cloud recognition result diagram, and the efficiency evaluation result, the toughness evaluation result and the evaluation index are given.

[0050] In another aspect of the present invention, a baggage feature recognition device based on stacking efficiency and stacking toughness is provided, comprising:

[0051] A feature data collection unit is used to collect baggage feature information and pre-process the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data;

[0052] A stacking efficiency evaluation value calculation unit, used to calculate the length-width-height ratio of the suitcase according to the characteristic data, and calculate the stacking efficiency evaluation value according to the length-width-height ratio;

[0053] a stacking resilience evaluation value calculation unit, configured to obtain a baggage stacking resilience index system according to the characteristic data; and obtain a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes primary indicators and secondary indicators of the baggage;

[0054] A feature result generating unit is used to obtain a feature evaluation result and a feature effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

[0055] On the other hand, a baggage feature recognition device based on stacking efficiency and stacking toughness is provided. The baggage feature recognition device based on stacking efficiency and stacking toughness includes a computer program stored on a medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the methods described in the above aspects and achieves the same technical effects.

[0056] On the other hand, a storage medium is provided on which a computer program is stored. When the computer program is executed by a processor, each step of the baggage feature recognition method based on stacking efficiency and stacking toughness as described in any one of the above items is implemented.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] In the present invention, firstly, baggage feature information is collected, and the collected feature information is preprocessed to obtain feature data; then, the length, width and height ratio of the suitcase is calculated according to the feature data, and the stacking efficiency evaluation value is calculated according to the length, width and height ratio; then, a baggage stacking toughness index system is obtained according to the feature data; a baggage stacking toughness evaluation value is obtained by a fuzzy evaluation method according to the baggage stacking toughness index system; finally, an evaluation result and a feature visualization effect diagram are obtained according to the stacking efficiency evaluation value and the stacking toughness evaluation value. The present invention can improve baggage feature recognition capability and aviation baggage stacking efficiency, reduce baggage damage and reduce the labor intensity of porters, and has good application prospects as the construction of smart airports advances.

[0059] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, and to make the above and other purposes, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 is a step diagram of the baggage feature recognition method based on stacking efficiency and stacking toughness described in the present invention;

[0062] Figure 2 is a flow chart of the baggage feature recognition method based on stacking efficiency and stacking toughness described in the present invention;

[0063] Figure 3 It is a schematic diagram of the weight information feature collection structure of the present invention;

[0064] Figure 4 It is a schematic diagram of the image information feature acquisition structure described in the present invention;

[0065] Figure 5 It is the three-dimensional point cloud recognition result diagram described in the present invention;

[0066] Figure 6 It is the visualization effect diagram described in the present invention;

[0067] Figure 7 It is a schematic diagram of the structure of the baggage feature recognition device based on stacking efficiency and stacking toughness in the present invention;

[0068] Figure 8 It is a schematic diagram of the structure of the baggage feature recognition device based on stacking efficiency and stacking toughness described in the present invention. DETAILED DESCRIPTION

[0069] The specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific implementation modes.

[0070] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0071] In this document, the terms "first", "second", etc. are used to distinguish two different elements or parts, and are not used to limit a specific position or relative relationship. In other words, in some embodiments, the terms "first", "second", etc. can also be interchangeable.

[0072] Embodiment 1

[0073] In order to improve the baggage feature recognition capability and baggage stacking efficiency, such as Figure 1 and Figure 2 As shown, in an embodiment of the present invention, a baggage feature recognition method based on stacking efficiency and stacking toughness is provided, comprising the steps of:

[0074] S11, collecting baggage feature information, and preprocessing the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data;

[0075] In the embodiment of the present invention, basic characteristic information of the luggage, such as the material, length, width, height, weight and other basic information of the luggage, is collected. The weight information characteristic is collected as follows: Figure 3 As shown in Figure 4 shown.

[0076] Next, the collected feature information is preprocessed, including:

[0077] Obtaining three-dimensional size data of the luggage according to the three-dimensional point cloud data, and calculating the normalization of the first-order moment of the image according to the three-dimensional size data to obtain the center of gravity position of the luggage;

[0078] The weight data is cleaned, and the variance of the cleaned data is calculated using the following formula:

[0079]

[0080] In the formula, σ 2 is the variance; N is the total number of available data samples after data cleaning; x i is a single sample value; μ is the mean of the sample data.

[0081] S12, calculating the length-width-height ratio of the suitcase according to the characteristic data; and calculating the stacking efficiency evaluation value according to the length-width-height ratio;

[0082] In the embodiment of the present invention, the stacking efficiency evaluation value is calculated according to the aspect ratio, including:

[0083] S121, dividing the ratio of the length, width and height into a plurality of ratio intervals according to stability;

[0084] S122, according to the ratio interval being represented as a function in the corresponding coordinate system, calculating the degree of each of the ratio intervals in the first quadrant of the coordinate system, and calculating the proportion value of each of the ratio intervals according to the degree;

[0085] S123, using a Softmax function to process each of the ratio values ​​to obtain an initial stacking efficiency value;

[0086] S124, using entropy method to calculate the weight value of each ratio value in the evaluation of stacking efficiency;

[0087] S125 . Obtain a stacking efficiency evaluation value according to the initial stacking efficiency value and the weight value of each of the proportion values.

[0088] S13, obtaining a baggage stacking resilience index system according to the characteristic data; obtaining a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes a primary index and a secondary index of baggage;

[0089] In the embodiment of the present invention, the primary index includes: the center of gravity position, edge regularity coefficient, material and weight stability of the luggage; the secondary index includes: the exact center, corners and other positions corresponding to the center of gravity position; the shape corresponding to the edge regularity coefficient; the softness and hardness corresponding to the material.

[0090] According to the baggage stacking resilience index system, the baggage stacking resilience evaluation value is obtained through the fuzzy evaluation method, including:

[0091] S131. Construct a high-order CFA model based on the baggage stacking resilience index system through the following formula;

[0092] X=λ x φ+r

[0093] ρ=Γζ+ξ

[0094] In the formula, X is the secondary index; λ x is the first-order loading; φ is the first-order factor latent variable; r is the measurement error; ρ is the primary indicator; Γ is the loading of the second-order factor latent variable on the first-order factor latent variable; ζ is the second-order factor latent variable; ξ is the first-order factor residual;

[0095] S132, obtaining the standardized factor loading of each of the first-level indicators and the second-level indicators through AMOS26.0 structural equation model fitting analysis;

[0096] S133, according to the factor loading of the same facet in the high-order CFA model, the indicator weight value is calculated by the following formula;

[0097]

[0098] In the formula, y i is the indicator weight value; Q i is the factor loading of the indicator; n is the number of indicators at the same level; Q 1 +Q 2 +…+Q n It is the sum of the factor loadings of all indicators at the same level;

[0099] S134, based on the comment set of the secondary indicator, generate a primary indicator fuzzy judgment matrix based on the membership degree of the secondary indicator on the comment set; and generate a secondary indicator weight vector based on the weight value of each indicator;

[0100] In the embodiment of the present invention, a comment set is first constructed, and the influence of each secondary indicator on the primary indicator is obtained from the collected historical feature data to quantify and construct a comment set. The comment set can be set as M = {M 1 , M 2 , …, M 5}, the review set includes: {very good, good, average, poor, very poor}.

[0101] S135, performing a first-level fuzzy evaluation on the first-level indicators according to the first-level indicator fuzzy judgment matrix and the second-level indicator weight vector; and obtaining a fuzzy judgment matrix of baggage stacking toughness according to the first-level fuzzy evaluation;

[0102] In the embodiment of the present invention, the membership degree of the secondary index on the comment set is used to form the fuzzy judgment matrix R of each primary index. 1 ~R 4 , and then the weight values ​​of each secondary indicator are combined to form the weight vector W of the secondary indicator 1 ~W 4 , based on the method of weight vector and fuzzy judgment matrix, the first-level indicators are evaluated by the following formula:

[0103] B i =W i R i i=1,2,3,4

[0104] Then, by the fuzzy evaluation of the first-level index, the fuzzy judgment matrix R of the luggage stacking toughness can be obtained:

[0105] R=(B 1 B 2 B 3 B 4 ) T

[0106] S136, performing a secondary fuzzy evaluation based on the fuzzy judgment matrix of the baggage stacking resilience and the indicator weight values ​​of the primary indicators;

[0107] In the embodiment of the present invention, according to the fuzzy judgment matrix of the baggage stacking toughness and in combination with the weight value of the first-level index, the second-level fuzzy evaluation is calculated by the following formula:

[0108] B=WR

[0109] In the formula, B is the secondary fuzzy evaluation; W is the primary indicator weight value.

[0110] S137, obtaining a fuzzy comprehensive evaluation value of the luggage according to the secondary fuzzy evaluation and the evaluation value; the evaluation value is obtained by dividing the corresponding comment set into multiple evaluation intervals and taking the median of each evaluation interval;

[0111] In the embodiment of the present invention, the corresponding comment set can be divided into M 1 (80, 100], M 2 (60, 80], M 3 (40, 60], M 4 (20,40],M 5 (0, 20] five evaluation intervals, take the median of the interval for evaluation, that is, M = (9070503010) T , the fuzzy comprehensive evaluation value F of the luggage is:

[0112] F=BM

[0113] S138. Match the fuzzy comprehensive evaluation value with each evaluation interval to obtain a baggage stacking toughness evaluation value.

[0114] In the embodiment of the present invention, the overall stacking toughness evaluation value of the luggage can be obtained by matching the fuzzy comprehensive evaluation value F of the luggage with the evaluation interval.

[0115] S14. Obtaining an evaluation result and a feature visualization effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

[0116] In the embodiment of the present invention, the evaluation results and the feature visualization effect diagram are obtained according to the stacking efficiency evaluation value and the stacking toughness evaluation value, including:

[0117] Generate a point cloud recognition result map based on the three-dimensional point cloud data;

[0118] Mark the basic information of the suitcase on the point cloud recognition result map; the basic information includes: the center of mass position of the suitcase, the length, width and height of the suitcase, the type of suitcase and the shape of the edge of the suitcase;

[0119] The stacking efficiency evaluation value and the stacking toughness evaluation value are displayed in the point cloud recognition result diagram, and the efficiency evaluation results, toughness evaluation results and evaluation indicators are given.

[0120] In the embodiment of the present invention, a point cloud recognition result map is first generated, such as Figure 5 As shown in the figure, the center of mass of the luggage, the length, width and height of the luggage, whether the luggage is made of regular luggage, soft baggage or special-shaped luggage, and whether the edge of the luggage is a regular shape are marked on the point cloud recognition result map; the final visualization effect map is as follows Figure 6 shown.

[0121] The evaluation results include performance evaluation results, toughness evaluation results and evaluation indicators. The performance evaluation results include: extremely high, high, medium, low, and extremely low; the toughness evaluation results include: extremely strong, strong, medium, weak, and extremely weak; the evaluation indicators include: suitcase material, weight stability, edge regularity coefficient, and center of gravity position.

[0122] In summary, in the embodiments of the present invention, first, baggage feature information is collected, and the collected feature information is preprocessed to obtain feature data; then, the length, width and height ratio of the suitcase is calculated according to the feature data, and the stacking efficiency evaluation value is calculated according to the length, width and height ratio; then, a baggage stacking toughness index system is obtained according to the feature data; a baggage stacking toughness evaluation value is obtained by a fuzzy evaluation method according to the baggage stacking toughness index system; finally, an evaluation result and a feature visualization effect diagram are obtained according to the stacking efficiency evaluation value and the stacking toughness evaluation value. The present invention can improve the baggage feature recognition capability and the aviation baggage stacking efficiency, reduce baggage damage and reduce the labor intensity of porters, and has good application prospects as the construction of smart airports advances.

[0123] Embodiment 2

[0124] Corresponding to the method embodiment, in another aspect of the embodiment of the present invention, a baggage feature recognition device based on stacking efficiency and stacking toughness is also provided. Figure 3 The schematic diagram of the structure of the baggage feature recognition device based on stacking efficiency and stacking toughness provided by the embodiment of the present invention is shown. The baggage feature recognition device based on stacking efficiency and stacking toughness is Figure 1 The device corresponding to the baggage feature recognition method based on stacking efficiency and stacking toughness described in the corresponding embodiment is implemented by means of a virtual device. Figure 1 In the corresponding embodiment, the baggage feature recognition method based on stacking efficiency and stacking toughness, each virtual module constituting the baggage feature recognition device based on stacking efficiency and stacking toughness can be executed by an electronic device, such as a network device, a terminal device or a server. Specifically, the baggage feature recognition device based on stacking efficiency and stacking toughness in the embodiment of the present invention includes:

[0125] S11, collecting baggage feature information, and preprocessing the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data;

[0126] In the embodiment of the present invention, preprocessing the collected feature information includes:

[0127] Obtaining three-dimensional size data of the luggage according to the three-dimensional point cloud data, and calculating the normalization of the first-order moment of the image according to the three-dimensional size data to obtain the center of gravity position of the luggage;

[0128] The weight data is cleaned, and the variance of the cleaned data is calculated using the following formula:

[0129]

[0130] In the formula, σ 2 is the variance; N is the total number of available data samples after data cleaning; x i is a single sample value; μ is the mean of the sample data.

[0131] S12, calculating the length-width-height ratio of the suitcase according to the characteristic data; and calculating the stacking efficiency evaluation value according to the length-width-height ratio;

[0132] In the embodiment of the present invention, the stacking efficiency evaluation value is calculated according to the aspect ratio, including:

[0133] S121, dividing the ratio of the length, width and height into a plurality of ratio intervals according to stability;

[0134] S122, according to the ratio interval being represented as a function in the corresponding coordinate system, calculating the degree of each of the ratio intervals in the first quadrant of the coordinate system, and calculating the proportion value of each of the ratio intervals according to the degree;

[0135] S123, using a Softmax function to process each of the ratio values ​​to obtain an initial stacking efficiency value;

[0136] S124, calculating the weight value of each ratio value in the stacking efficiency evaluation by using an entropy method;

[0137] S125 . Obtain a stacking efficiency evaluation value according to the initial stacking efficiency value and the weight value of each of the proportion values.

[0138] S13, obtaining a baggage stacking resilience index system according to the characteristic data; obtaining a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes a primary index and a secondary index of baggage;

[0139] In the embodiment of the present invention, the primary index includes: the center of gravity position, edge regularity coefficient, material and weight stability of the luggage; the secondary index includes: the exact center, corners and other positions corresponding to the center of gravity position; the shape corresponding to the edge regularity coefficient; the softness and hardness corresponding to the material.

[0140] According to the baggage stacking resilience index system, the baggage stacking resilience evaluation value is obtained through the fuzzy evaluation method, including:

[0141] S131. Construct a high-order CFA model based on the baggage stacking resilience index system through the following formula;

[0142] X=λ x φ+r

[0143] ρ=Γζ+ξ

[0144] In the formula, X is the secondary index; λ x is the first-order loading; φ is the first-order factor latent variable; r is the measurement error; ρ is the primary indicator; Γ is the loading of the second-order factor latent variable on the first-order factor latent variable; ζ is the second-order factor latent variable; ξ is the first-order factor residual;

[0145] S132, obtaining the standardized factor loading of each of the first-level indicators and the second-level indicators through AMOS26.0 structural equation model fitting analysis;

[0146] S133, according to the factor loading of the same facet in the high-order CFA model, the indicator weight value is calculated by the following formula;

[0147]

[0148] In the formula, y i is the indicator weight value; Q i is the factor loading of the indicator; n is the number of indicators at the same level; Q 1 +Q 2 +…+Q n It is the sum of the factor loadings of all indicators at the same level;

[0149] S134, based on the comment set of the secondary indicator, generate a primary indicator fuzzy judgment matrix based on the membership degree of the secondary indicator on the comment set; and generate a secondary indicator weight vector based on the weight value of each indicator;

[0150] In the embodiment of the present invention, a comment set is first constructed, and the influence of each secondary indicator on the primary indicator is obtained from the collected historical feature data to quantify and construct a comment set. The comment set can be set as M = {M 1 , M 2 , …, M 5}, the review set includes: {very good, good, average, poor, very poor}.

[0151] S135, performing a first-level fuzzy evaluation on the first-level indicators according to the first-level indicator fuzzy judgment matrix and the second-level indicator weight vector; and obtaining a fuzzy judgment matrix of baggage stacking toughness according to the first-level fuzzy evaluation;

[0152] In the embodiment of the present invention, the membership degree of the secondary index on the comment set is used to form the fuzzy judgment matrix R of each primary index. 1 ~R 4 , and then the weight values ​​of each secondary indicator are combined to form the weight vector W of the secondary indicator 1 ~W 4 , based on the method of weight vector and fuzzy judgment matrix, the first-level indicators are evaluated by the following formula:

[0153] B i =W i R i i=1,2,3,4

[0154] Then, by the fuzzy evaluation of the first-level index, the fuzzy judgment matrix R of the luggage stacking toughness can be obtained:

[0155] R=(B 1 B 2 B 3 B 4 ) T

[0156] S136, performing a secondary fuzzy evaluation based on the fuzzy judgment matrix of the baggage stacking resilience and the indicator weight values ​​of the primary indicators;

[0157] In the embodiment of the present invention, according to the fuzzy judgment matrix of the baggage stacking toughness and in combination with the weight value of the first-level index, the second-level fuzzy evaluation is calculated by the following formula:

[0158] B=WR

[0159] In the formula, B is the secondary fuzzy evaluation; W is the primary indicator weight value.

[0160] S137, obtaining a fuzzy comprehensive evaluation value of the luggage according to the secondary fuzzy evaluation and the evaluation value; the evaluation value is obtained by dividing the corresponding comment set into multiple evaluation intervals and taking the median of each evaluation interval;

[0161] In the embodiment of the present invention, the corresponding comment set can be divided into M 1 (80, 100], M 2 (60, 80], M 3 (40, 60], M 4 (20,40],M 5(0, 20] five evaluation intervals, take the median of the interval for evaluation, that is, M = (9070503010) T , the fuzzy comprehensive evaluation value F of the luggage is:

[0162] F=BM

[0163] S138. Match the fuzzy comprehensive evaluation value with each evaluation interval to obtain a baggage stacking toughness evaluation value.

[0164] By matching the fuzzy comprehensive evaluation value F of the luggage with the evaluation interval, the overall stacking toughness evaluation value of the luggage can be obtained.

[0165] S14. Obtaining an evaluation result and a feature visualization effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

[0166] In the embodiment of the present invention, the evaluation results and the feature visualization effect diagram are obtained according to the stacking efficiency evaluation value and the stacking toughness evaluation value, including:

[0167] Generate a point cloud recognition result map based on the three-dimensional point cloud data;

[0168] Mark the basic information of the suitcase on the point cloud recognition result map; the basic information includes: the center of mass position of the suitcase, the length, width and height of the suitcase, the type of suitcase and the shape of the edge of the suitcase;

[0169] The stacking efficiency evaluation value and the stacking toughness evaluation value are displayed in the point cloud recognition result diagram, and the efficiency evaluation results, toughness evaluation results and evaluation indicators are given.

[0170] It should be noted that the specific implementation and technical effects of the baggage feature recognition device based on stacking efficiency and stacking toughness in the embodiment of the present invention can be referred to Figure 1 The corresponding baggage feature recognition method based on stacking efficiency and stacking toughness will not be described in detail here.

[0171] Embodiment 3

[0172] Corresponding to the method embodiment, in the embodiment of the present invention, there is also provided a baggage feature recognition device based on stacking efficiency and stacking toughness, such as a terminal, a server, etc. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto.

[0173] An example of a hardware structure block diagram of a baggage feature recognition device based on stacking efficiency and stacking toughness provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, it may include:

[0174] Processor 1, communication interface 2, memory 3 and communication bus 4;

[0175] The processor 1, the communication interface 2, and the memory 3 communicate with each other via the communication bus 4;

[0176] Optionally, the communication interface 2 may be an interface of a communication module, such as an interface of a GSM module;

[0177] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0178] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0179] The processor 1 is specifically used to execute the computer program stored in the memory 3 to perform the following steps:

[0180] S11, collecting baggage feature information, and preprocessing the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data;

[0181] S12, calculating the length-width-height ratio of the suitcase according to the characteristic data; and calculating the stacking efficiency evaluation value according to the length-width-height ratio;

[0182] S13, obtaining a baggage stacking resilience index system according to the characteristic data; obtaining a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes a primary index and a secondary index of baggage;

[0183] S14. Obtaining an evaluation result and a feature visualization effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

[0184] The above product can execute the method provided in the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the baggage feature recognition method based on stacking efficiency and stacking toughness provided in the embodiment of the present invention.

[0185] Embodiment 4

[0186] In an embodiment of the present invention, a storage medium is further provided, which may store a program suitable for execution by a processor, wherein the program is used to:

[0187] S11, collecting baggage feature information, and preprocessing the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data;

[0188] S12, calculating the length-width-height ratio of the suitcase according to the characteristic data; and calculating the stacking efficiency evaluation value according to the length-width-height ratio;

[0189] S13, obtaining a baggage stacking resilience index system according to the characteristic data; obtaining a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes a primary index and a secondary index of baggage;

[0190] S14. Obtaining an evaluation result and a feature visualization effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

[0191] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0192] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the methods provided by other embodiments of the present invention.

[0193] 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, or a combination of computer software and electronic hardware. 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 this application.

[0194] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0195] 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 solution of this embodiment.

[0196] In addition, each functional unit in each embodiment of the present application 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.

[0197] It should be understood that in the embodiments of the present application, the various embodiments and features can be combined with each other to solve the aforementioned technical problems.

[0198] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several 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 methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0199] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A baggage feature recognition method based on stacking efficiency and stacking toughness, characterized in that: Includes steps: S11, collecting baggage feature information, and preprocessing the collected feature information to obtain feature data; the feature data includes weight data and three-dimensional point cloud data; S12, calculating the length-width-height ratio of the suitcase according to the characteristic data; and calculating the stacking efficiency evaluation value according to the length-width-height ratio; S13, obtaining a baggage stacking resilience index system according to the characteristic data; obtaining a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes a primary index and a secondary index of baggage; S14. Obtaining an evaluation result and a feature visualization effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

2. The baggage feature recognition method based on stacking efficiency and stacking toughness according to claim 1, characterized in that: The preprocessing of the collected feature information includes: Obtaining three-dimensional size data of the luggage according to the three-dimensional point cloud data, and calculating the normalization of the first-order moment of the image according to the three-dimensional size data to obtain the center of gravity position of the luggage; The weight data is cleaned, and the variance of the cleaned data is calculated using the following formula: In the formula, σ 2 is the variance; N is the total number of available data samples after data cleaning; x i is a single sample value; μ is the mean of the sample data.

3. The baggage feature recognition method based on stacking efficiency and stacking toughness according to claim 2 is characterized in that: The calculating the stacking efficiency evaluation value according to the aspect ratio includes: S121, dividing the ratio of the length, width and height into a plurality of ratio intervals according to stability; S122, according to the ratio interval being represented as a function in the corresponding coordinate system, calculating the degree of each of the ratio intervals in the first quadrant of the coordinate system, and calculating the ratio value of each of the ratio intervals according to the degree; S123, using a Softmax function to process each of the ratio values ​​to obtain an initial stacking efficiency value; S124, calculating the weight value of each ratio value in the stacking efficiency evaluation by using an entropy method; S125 . Obtain a stacking efficiency evaluation value according to the initial stacking efficiency value and the weight value of each of the proportion values.

4. The baggage feature recognition method based on stacking efficiency and stacking toughness according to claim 3 is characterized in that: The step of obtaining the baggage stacking resilience evaluation value by using a fuzzy evaluation method according to the baggage stacking resilience index system includes: S131. Construct a high-order CFA model based on the baggage stacking resilience index system through the following formula; X=λ x f+r ρ=Γζ+ξ In the formula, X is the secondary index; λ x is the first-order loading; φ is the first-order factor latent variable; r is the measurement error; ρ is the primary indicator; Γ is the loading of the second-order factor latent variable on the first-order factor latent variable; ζ is the second-order factor latent variable; ξ is the first-order factor residual; S132, obtaining the standardized factor loading of each of the first-level indicators and the second-level indicators through AMOS26.0 structural equation model fitting analysis; S133, according to the factor loading of the same facet in the high-order CFA model, the indicator weight value is calculated by the following formula; In the formula, y i is the indicator weight value; Q i is the factor loading of the indicator; n is the number of indicators at the same level; Q1+Q2+…+Q n It is the sum of the factor loadings of all indicators at the same level; S134, based on the comment set of the secondary indicator, generate a primary indicator fuzzy judgment matrix based on the membership of the secondary indicator on the comment set; and generate a secondary indicator weight vector based on the weight value of each indicator; S135, performing a first-level fuzzy evaluation on the first-level indicators according to the first-level indicator fuzzy judgment matrix and the second-level indicator weight vector; and obtaining a fuzzy judgment matrix of baggage stacking toughness according to the first-level fuzzy evaluation; S136, performing a secondary fuzzy evaluation based on the fuzzy judgment matrix of the baggage stacking resilience and the indicator weight values ​​of the primary indicators; S137, obtaining a fuzzy comprehensive evaluation value of the luggage according to the secondary fuzzy evaluation and the evaluation value; the evaluation value is obtained by dividing the corresponding comment set into multiple evaluation intervals and taking the median of each evaluation interval; S138. Match the fuzzy comprehensive evaluation value with each evaluation interval to obtain a baggage stacking toughness evaluation value.

5. The baggage feature recognition method based on stacking efficiency and stacking toughness according to claim 4, characterized in that: Constructing the review set includes: Quantify the impact of each secondary indicator on the primary indicator based on historical data; The review set includes: very good, good, average, poor, and very poor.

6. The baggage feature recognition method based on stacking efficiency and stacking toughness according to claim 4, characterized in that: The first-level indicators include: the center of gravity position, edge regularity coefficient, material and weight stability of the luggage; The secondary indicators include: the exact center, corners and other positions corresponding to the center of gravity; a shape corresponding to the edge regularity coefficient; Soft and hard corresponding to the material.

7. The baggage feature recognition method based on stacking efficiency and stacking toughness according to claim 1, characterized in that: An evaluation result and a feature visualization effect diagram are obtained according to the stacking efficiency evaluation value and the stacking toughness evaluation value, including: Generate a point cloud recognition result map according to the three-dimensional point cloud data; Annotate the basic information of the suitcase on the point cloud recognition result diagram; the basic information includes: the centroid position of the suitcase, the length, width and height of the suitcase, the type of suitcase and the edge shape of the suitcase; The stacking efficiency evaluation value and the stacking toughness evaluation value are displayed in the point cloud recognition result diagram, and the efficiency evaluation result, the toughness evaluation result and the evaluation index are given.

8. A baggage feature recognition device based on stacking efficiency and stacking toughness, characterized in that: include: A characteristic data collection unit, used to collect characteristic information of the baggage and pre-process the collected characteristic information to obtain characteristic data; The characteristic data includes weight data and three-dimensional point cloud data; A stacking efficiency evaluation value calculation unit, used to calculate the length-width-height ratio of the suitcase according to the characteristic data; and calculate the stacking efficiency evaluation value according to the length-width-height ratio; a stacking resilience evaluation value calculation unit, configured to obtain a baggage stacking resilience index system according to the characteristic data; and obtain a baggage stacking resilience evaluation value by a fuzzy evaluation method according to the baggage stacking resilience index system; the baggage stacking resilience index system includes primary indicators and secondary indicators of the baggage; A feature result generating unit is used to obtain a feature evaluation result and a feature effect diagram according to the stacking efficiency evaluation value and the stacking toughness evaluation value.

9. A baggage feature recognition device based on stacking efficiency and stacking toughness, characterized in that: include: Memory for storing computer programs; A processor is used to call and execute the computer program to implement the steps of the baggage feature recognition method based on stacking efficiency and stacking toughness as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The method comprises a software program, wherein the software program is suitable for executing, by a processor, the steps of the baggage feature recognition method based on stacking efficiency and stacking toughness as claimed in any one of claims 1 to 7.

Images