Integrated Clothing Style Recommendation Method Based on Team Requirements

Abstract

The present invention provides an integrated clothing style recommendation method based on team needs, which belongs to the field of intelligent recommendation technology. The method comprises: parsing team needs based on team themes, obtaining a global parameter set and a local parameter set around the team theme, and collecting a first clothing recommendation set that matches each global parameter in the global parameter set; mapping the local parameter set to the own profile structure of each individual member, and obtaining a second clothing recommendation set for each individual member; performing clothing integration processing according to the first clothing recommendation set and all second clothing recommendation sets, and obtaining clothing recommendation results, thereby improving the team experience on the basis of effectively meeting the needs, and effectively improving the matching efficiency through a series of intelligent recommendations.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent recommendation, and particularly to an integrated clothing style recommendation method based on team requirements. Background Art

[0002] When a team performs, in addition to having excellent personal abilities, the overall clothing matching is also an important factor in creating the stage effect. In many cases, the clothing matching needs to be planned and implemented by the team's own matchmaker. From the large-scale fabric to the small-scale clothing shape, and during the matching process, it is necessary to repeatedly adjust the rationality of the matching manually, which will undoubtedly waste a lot of time and reduce the experience and matching efficiency of meeting the team's requirements.

[0003] Therefore, the present invention proposes an integrated clothing style recommendation method based on team requirements. Summary of the Invention

[0004] The present invention provides an integrated clothing style recommendation method based on team requirements, which is used to determine the global parameter set and the local parameter set in combination with the team theme and team requirements, provide a data basis for subsequent clothing recommendations, and improve the team experience on the basis of effectively meeting the requirements through obtaining the clothing recommendation sets of different parameter sets and the integrated processing of the clothing recommendation sets, and effectively improve the matching efficiency through a series of intelligent recommendations.

[0005] The present invention provides an integrated clothing style recommendation method based on team requirements, including:

[0006] Step 1: Analyze the team requirements based on the team theme to obtain a global parameter set and a local parameter set surrounding the team theme, where the global parameter set is related to the overall clothing style of the team, and the local parameter set is related to the individual clothing styles of the team members;

[0007] Step 2: Collect the first clothing recommendation sets that match each global parameter in the global parameter set;

[0008] Step 3: Map the local parameter set to the own contour framework of each individual member and obtain the second clothing recommendation set for each individual member;

[0009] Step 4: Perform clothing integration processing according to the first clothing recommendation set and all the second clothing recommendation sets to obtain a clothing recommendation result, where the clothing recommendation result includes the overall dressing clothing of the team and the individual dressing clothing of the individual members.

[0010] Preferably, analyzing the team requirements based on the team theme to obtain a global parameter set and a local parameter set surrounding the team theme includes:

[0011] Match the requirement analysis model from the theme-model comparison table based on the team theme;

[0012] Analyze the team requirements according to the requirement analysis model to obtain a number of first initial parameters and a number of second initial parameters;

[0013] Set an initial radius for the corresponding first initial parameter based on the requirement role of each first initial parameter in the analysis process;

[0014] Set a first weight for the corresponding first initial parameter based on all the initial radii;

[0015] Meanwhile, assign an equal weight to each second initial parameter as the second weight;

[0016] Count all the first initial parameters with the first weight set as the global parameter set;

[0017] Count all the second initial parameters with the second weight set as the local parameter set.

[0018] Preferably, setting a first weight for the corresponding first initial parameter based on all the initial radii includes:

[0019] Determine the circumference and area of the circle corresponding to the first initial parameter based on the set initial radius;

[0020] Perform a first normal distribution process on all the circumferences to obtain a first radius. Meanwhile, perform a second normal distribution process on all the areas of the circles to obtain a second radius;

[0021] Screen the maximum radius and the minimum radius from all the initial radii, and rely on the difference between the maximum radius and the minimum radius, and combine the first radius and the second radius to set a radius threshold;

[0022] ;

[0023] Among them, represents the corresponding radius threshold; respectively represent the average values based on all the first radii and all the second radii; respectively represent the maximum radius and the minimum radius; respectively represent the number of all the first radii and the number of all the second radii; represents the radius fine-tuning function;

[0024] Perform an intersection process on the first initial quantities with long side radii outside the first normal distribution and the first initial quantities with long side radii outside the second normal distribution to obtain intersection initial parameters;

[0025] If the number of the intersection initial parameters is 0, set a first importance value for each first initial parameter according to the difference between the initial radius of each first initial parameter and the radius threshold;

[0026] ;

[0027] Among them, represents the first importance value of the i1-th first initial parameter; represents the initial radius of the i1-th first initial parameter;

[0028] If the number of the intersection initial parameters is not 0, set a second importance value for each first initial parameter according to the number of the initial radii corresponding to each first initial parameter that belong to the long-side radii, and in combination with the difference between the initial radius of each first initial parameter and the radius threshold;

[0029] ;

[0030] Among them, represents the second importance value of the i1-th first initial parameter; represents the number of the initial radii corresponding to the i1-th first initial parameter that belong to the long-side radii; represents the number of the parameters whose initial radii belong to the long-side radii among all the first initial parameters; ln represents the logarithmic function symbol;

[0031] Set a first weight for the corresponding first initial parameter based on the importance values of all the first initial parameters.

[0032] Preferably, collect a first clothing recommendation set that matches each global parameter in the global parameter set, including:

[0033] Match a first clothing recommendation set that matches the parameter attribute from the attribute-clothing database according to the parameter attribute of the global parameter.

[0034] Preferably, map the local parameter set to the own contour framework of each individual member, including:

[0035] Determine the action position of each local parameter in the local parameter set, compare the action position with the own contour framework, and in combination with the initial set performance result of each local parameter, obtain the initial local sequence of the corresponding individual member;

[0036] Obtain the prominent advantages and convertible advantages of the own contour framework of each individual member, and in combination with the prominent characteristics of the team theme, adjust the initial local sequence;

[0037] Obtain a second clothing recommendation set for the corresponding individual member according to the adjusted local sequence.

[0038] Preferably, adjusting the initial local sequence includes:

[0039] Obtaining the convertible advantages and prominent advantages of each individual member based on its own profile framework;

[0040] Determining a first imbalance coefficient corresponding to the convertible advantage of the corresponding individual member, and at the same time, determining a second imbalance coefficient corresponding to the prominent advantage of the corresponding individual member;

[0041] ;

[0042] Among them, represents the first imbalance coefficient corresponding to the j1-th convertible advantage of the corresponding individual member; represents the second imbalance coefficient corresponding to the j2-th prominent advantage of the corresponding individual member; represents the number of successful historical clothing recommendations and adjustments for the j1-th convertible advantage of the corresponding individual member; represents the total number of historical occurrences consistent with the j1-th convertible advantage of the corresponding individual member; represents the number of failed historical recommendation adjustments consistent with the j1-th convertible advantage of the corresponding individual member; represents the advantage prominence coefficient of the j1-th convertible advantage of the corresponding individual member; represents the advantage prominence coefficient of the j2-th prominent advantage of the corresponding individual member; represents the total number of convertible advantages involved by the corresponding individual member; represents the total number of convertible advantages involved by all individual members; represents the variance of the advantage prominence coefficients of the convertible advantages involved by all individual members;

[0043] Extracting the adaptation factors based on each action position from the first imbalance factors and the second imbalance factors of all individual members, and calculating the overall adaptation value corresponding to the action position;

[0044] If the overall adaptation value is greater than the preset adaptation value of the corresponding action position, then adjust the corresponding sequence according to the first imbalance factor and the second imbalance factor involved in the corresponding action position and in combination with the prominent characteristics of the team theme, so as to achieve local clothing adjustment;

[0045] Otherwise, do not adjust the sequence of the corresponding action position;

[0046] Obtain the adjusted local sequence according to the final result of each action position.

[0047] Preferably, obtaining the second clothing recommendation set corresponding to the corresponding individual member according to the adjusted local sequence, including:

[0048] Compare the adjusted partial sequence with the personalized clothing database;

[0049] According to the comparison result, obtain the second clothing recommendation set corresponding to the individual members.

[0050] Preferably, perform clothing integration processing based on the first clothing recommendation set and all the second clothing recommendation sets to obtain clothing recommendation results, including:

[0051] Input the first clothing recommendation set and each second clothing recommendation set into the team clothing analysis table in turn, where the team clothing analysis table includes the overall clothing elements and unique clothing elements of different individual members;

[0052] Statistically analyze the coordination between the unique clothing elements in each column and each overall clothing element respectively;

[0053] If all the coordinations are greater than the corresponding preset values, retain the corresponding unique clothing elements;

[0054] Otherwise, lock the elements with coordinations less than the preset values among all the unique clothing elements of each individual member as the first elements, and screen out the elements to be adjusted and the personnel to be adjusted by statistically analyzing the first quantity of the first elements involved for each individual member and the second quantity of the first elements involved in the unique clothing elements of each column;

[0055] Weaken the local parameter set of the personnel to be adjusted according to the global parameter set and in combination with the division roles of the personnel to be adjusted;

[0056] Perform information standardization processing on the element information of the unique clothing elements in the column corresponding to the element to be adjusted according to the clothing set under the maximum recommendation coefficient in the first clothing recommendation set;

[0057] Obtain clothing recommendation results according to the weakening processing result and the information standardization processing result.

[0058] Compared with the prior art, the beneficial effects of the present application are as follows:

[0059] Determine the global parameter set and the local parameter set in combination with the team theme and team requirements, provide a data basis for subsequent clothing recommendations, and improve the team experience while effectively meeting the requirements by obtaining clothing recommendation sets of different parameter sets and performing integration processing on the clothing recommendation sets, and effectively improve the matching efficiency through a series of intelligent recommendations.

[0060] Other features and advantages of the present invention will be described in the subsequent description, and some of them will become obvious from the description, or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written description and the drawings.

[0061] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0062] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, but do not constitute a limitation to the present invention. In the accompanying drawings:

[0063] Figure 1 It is a flowchart of an integrated clothing style recommendation method based on team requirements in an embodiment of the present invention. Detailed Embodiments

[0064] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0065] The present invention provides an integrated clothing style recommendation method based on team requirements, as Figure 1 shown, including:

[0066] Step 1: Analyze the team requirements based on the team theme to obtain a global parameter set and a local parameter set around the team theme. Among them, the global parameter set is related to the overall clothing style of the team, and the local parameter set is related to the individual clothing styles of the team members;

[0067] Step 2: Collect a first clothing recommendation set that matches each global parameter in the global parameter set;

[0068] Step 3: Map the local parameter set to the own contour framework of each individual member and obtain a second clothing recommendation set for each individual member;

[0069] Step 4: Perform clothing integration processing according to the first clothing recommendation set and all the second clothing recommendation sets to obtain a clothing recommendation result, where the clothing recommendation result includes the overall dressing clothing of the team and the individual dressing clothing of the individual members.

[0070] In this embodiment, the team theme can be a performance theme related to a chorus theme, a drama theme, etc.

[0071] In this embodiment, the team requirements refer to the performance effect requirements, atmosphere requirements, etc. put forward by the organizing teacher or team members for performances such as chorus and drama.

[0072] In this embodiment, the global parameter set is constructed based on the overall clothing style of the team. For example, the clothing fabrics, clothing colors, clothing styles, etc. of the entire team.

[0073] The local parameter set is constructed based on the personal styles of individual members in the team. For example, the personalized structure of the clothing cutting and the clothing accessories of each member, etc.

[0074] In this embodiment, the first clothing recommendation set includes clothing sample recommendation results related to clothing fabric, clothing color, and clothing style.

[0075] In this embodiment, the self-profile framework refers to the 3D body model of the corresponding member.

[0076] In this embodiment, the local parameter set is mapped to the corresponding self-profile framework for personalized design.

[0077] In this embodiment, the second clothing recommendation set includes personalized clothing recommendations for individual members, that is, highlighting the advantages of the members as much as possible.

[0078] In this embodiment, the integrated processing means that on the premise of meeting the overall theme, the advantages of each member can be highlighted, and without affecting the overall clothing style of the team while highlighting them.

[0079] In this embodiment, the clothing recommendation results can be parameters related to clothing such as the shape and size of the clothing, which can be input into the clothing model to obtain the AI virtual display clothing effect for the member. Then, it can be cut and adjusted again to obtain the targeted clothing for the member, and then a nesting plan can be generated.

[0080] The beneficial effects of the above technical solutions are: determining the global parameter set and the local parameter set in combination with the team theme and team requirements, providing a data basis for subsequent clothing recommendations, and improving the team experience on the basis of effectively meeting the requirements through obtaining clothing recommendation sets of different parameter sets and the integrated processing of the clothing recommendation sets, and effectively improving the matching efficiency through a series of intelligent recommendations.

[0081] The present invention provides an integrated clothing style recommendation method based on team requirements, which analyzes the team requirements based on the team theme to obtain a global parameter set and a local parameter set around the team theme, including:

[0082] Matching a requirement analysis model from a theme-model comparison table based on the team theme;

[0083] Analyzing the team requirements according to the requirement analysis model to obtain a number of first initial parameters and a number of second initial parameters;

[0084] Setting an initial radius for the corresponding first initial parameter based on the requirement function of each first initial parameter in the analysis process;

[0085] Set the first weight for all initial radii corresponding to the first initial parameters;

[0086] Meanwhile, assign an equal weight to each second initial parameter as the second weight;

[0087] Statistically count all the first initial parameters with the first weight set as the global parameter set;

[0088] Statistically count all the second initial parameters with the second weight set as the local parameter set.

[0089] In this embodiment, the team theme refers to the theme that the team needs to perform. For example, for the theme of the chorus of "Green Whirlwind", a requirement analysis model related to the chorus theme is matched from the theme - model comparison table. This table contains different team themes and the corresponding requirement analysis models, and the requirement analysis model is trained on a neural network model with the requirements of the theme based on different team themes and the required matching parameters for this requirement as samples.

[0090] In this embodiment, the first initial parameter is for the overall team, and the second initial parameter is for individual members in the team.

[0091] In this embodiment, the requirement effect refers to the situation where the corresponding initial parameter is applied to the team costumes. The more irreplaceable the application situation is, the greater its effect.

[0092] In this embodiment, the initial radius is obtained by matching from the effect - radius comparison table. This comparison table contains different requirement effects and the initial radii matched with the effects, and the value range of the initial radius is from 0 to 1 cm.

[0093] In this embodiment, the global parameter set is the first initial parameter with the first weight set.

[0094] In this embodiment, the local parameter set is the second initial parameter with the second weight set.

[0095] The beneficial effects of the above - mentioned technical solution are: By obtaining the model related to the theme from the comparison table to achieve the analysis of requirements, and then by obtaining the requirement effect of the parameter in the analysis process, set the corresponding weight for the parameter, and then obtain the global parameter and the local parameter.

[0096] The present invention provides an integrated clothing style recommendation method based on team requirements. Set the first weight for all initial radii corresponding to the first initial parameters, including:

[0097] Based on the set initial radius, determine the circumference and area of the circle corresponding to the first initial parameter;

[0098] Perform the first normal distribution processing on all circumferences to obtain the first radius. At the same time, perform the second normal distribution processing on all circular areas to obtain the second radius;

[0099] Select the maximum radius and the minimum radius from all the initial radii, and set the radius threshold depending on the difference between the maximum radius and the minimum radius, and in combination with the first radius and the second radius;

[0100] ;

[0101] Among them, represents the corresponding radius threshold; respectively represent the averages based on all the first radii and all the second radii; respectively represent the maximum radius and the minimum radius; respectively represent the quantities of all the first radii and all the second radii; represents the radius fine-tuning function;

[0102] Perform an intersection process on the first initial quantity of the long-side radii outside the first normal distribution and the first initial quantity of the long-side radii outside the second normal distribution to obtain the intersection initial parameter;

[0103] If the quantity of the intersection initial parameter is 0, set the first importance value for each first initial parameter according to the difference between the initial radius of each first initial parameter and the radius threshold;

[0104] ;

[0105] Among them, represents the first importance value of the i1-th first initial parameter; represents the initial radius of the i1-th first initial parameter;

[0106] If the quantity of the intersection initial parameter is not 0, set the second importance value for each first initial parameter according to the quantity of the initial radius corresponding to each first initial parameter belonging to the long-side radius, and in combination with the difference between the initial radius of each first initial parameter and the radius threshold;

[0107] ;

[0108] Among them, represents the second importance value of the i1-th first initial parameter; represents the quantity of the initial radius corresponding to the i1-th first initial parameter belonging to the long-side radius; represents the quantity of the parameters among all the first initial parameters whose initial radii belong to the long-side radius; ln represents the logarithmic function symbol;

[0109] Set a first weight for the corresponding first initial parameter based on the importance values of all the first initial parameters.

[0110] In this embodiment, the calculation formula for the circumference of a circle is: , and the calculation formula for the area of a circle is: .

[0111] In this embodiment, normal distribution processing refers to satisfying the normal distribution probability. Among them, the normal distribution probability of the first normal distribution processing is 80%, and the normal distribution probability of the second normal distribution processing is 70%. Therefore, at positions where the circumferences and areas are distributed other than satisfying the normal distribution probability, there are two parts. One part is the position of the small radius, that is, the position less than the minimum radius within the normal distribution probability distribution, and the other part is the position of the large radius, that is, the position greater than the maximum radius within the normal distribution probability distribution.

[0112] In this embodiment, for example, the first initial quantities of the long-side radii outside the first normal distribution are: u1, u2, and the first initial quantities of the long-side radii outside the second normal distribution are: u1, u2, u3. At this time, the intersection initial parameters are: u1, u2.

[0113] In this embodiment, the first weight = the importance value of the corresponding first initial parameter / the sum of the importance values of all the first initial parameters.

[0114] The beneficial effects of the above technical solution are: starting from the demand effect to determine the circumference and area, and then combining normal distribution processing to set the radius threshold. Based on the intersection processing results, determine the importance values of the initial parameters in different intersection cases, thereby providing a convenient basis for setting the first weight.

[0115] The present invention provides an integrated clothing style recommendation method based on team requirements, which collects a first clothing recommendation set that matches each global parameter in the global parameter set, including:

[0116] According to the parameter attributes of the global parameter, match the first clothing recommendation set that matches the parameter attributes from the attribute-clothing database.

[0117] In this embodiment, the parameter attributes can be fabric, color, style, etc.

[0118] In this embodiment, the attribute-clothing database contains combinations of different parameter attributes and the clothing recommendation results matching the combinations. Moreover, there is more than one clothing recommendation result. Therefore, a first clothing recommendation set is constructed, and this first clothing recommendation set contains at least one clothing recommendation result.

[0119] The beneficial effects of the above technical solution are: directly obtain the first clothing recommendation set by obtaining the attributes and comparing and analyzing them with the database.

[0120] The present invention provides an integrated clothing style recommendation method based on team requirements, which maps the local parameter set to the own contour framework of each individual member, including:

[0121] Determine the action position of each local parameter in the local parameter set, compare the action position with the own contour framework, and combine the initial setting performance results of each local parameter to obtain the initial local sequence of the corresponding individual member;

[0122] Obtain the prominent advantages and convertible advantages of the own contour framework of each individual member, and combine the prominent characteristics of the team theme to adjust the initial local sequence;

[0123] Obtain the second clothing recommendation set for the corresponding individual member according to the adjusted local sequence.

[0124] In this embodiment, the action position refers to the decoration position of the local parameter on the relevant framework. For example, it is necessary to set a personnel pendant on the waist of the framework, or wear a scarf around the neck, which can be a cotton scarf, a silk scarf, etc.

[0125] In this embodiment, the initial setting performance result refers to first using an ideal effect for matching display, but whether this ideal effect is suitable for the person himself still needs to be analyzed again, that is, adjusting the initial local sequence. Among them, the ideal effects are all pre-determined, generally the ideal effects determined by the standard framework, which can be preliminarily determined by software.

[0126] In this embodiment, prominent advantages, such as being tall. At this time, head ornaments of light strip clothing that creates an atmosphere can be configured for these members to drive the overall atmosphere.

[0127] In this embodiment, convertible advantages, such as having short legs. At this time, the defect of short legs can be covered by wearing clothing that covers the legs, etc.

[0128] In this embodiment, the initial local sequence: {the initial setting performance results of each local parameter involved in the corresponding individual member}.

[0129] In this embodiment, the adjusted local sequence: {the fitting setting performance results after adjusting each sequence in the initial local sequence}.

[0130] In this embodiment, the prominent characteristics of the team theme refer to the performance characteristics that the team needs to highlight. For example, the "Green Whirlwind" chorus targets the characteristics of special forces and teamwork.

[0131] The beneficial effects of the above technical solution are as follows: By comparing and analyzing local parameters with the framework, the initial local sequence can be effectively obtained. Then, by combining the prominent advantages, convertible advantages, and prominent characteristics, the adjustment of the sequence can be realized, and the second clothing recommendation set can be effectively obtained.

[0132] The present invention provides an integrated clothing style recommendation method based on team requirements, which adjusts the initial local sequence, including:

[0133] Obtain the convertible advantages and prominent advantages of each individual member based on their own contour framework;

[0134] Determine the first imbalance coefficient corresponding to the convertible advantage of the corresponding individual member, and at the same time, determine the second imbalance coefficient corresponding to the prominent advantage of the corresponding individual member;

[0135] ; ;

[0136] wherein, represents the first imbalance coefficient corresponding to the j1-th convertible advantage of the corresponding individual member; represents the second imbalance coefficient corresponding to the j2-th prominent advantage of the corresponding individual member; represents the number of times of successful adjustment of the historical clothing recommendation corresponding to the j1-th convertible advantage of the corresponding individual member; represents the total number of historical occurrences consistent with the j1-th convertible advantage of the corresponding individual member; represents the number of times of failed adjustment of the historical recommendation consistent with the j1-th convertible advantage of the corresponding individual member; represents the advantage prominence coefficient of the j1-th convertible advantage of the corresponding individual member; represents the advantage prominence coefficient of the j2-th prominent advantage of the corresponding individual member; represents the total number of convertible advantages involved by the corresponding individual member; represents the total number of convertible advantages involved by all individual members; represents the variance of the advantage prominence coefficients of the convertible advantages involved by all individual members;

[0137] Extract the adaptation factors based on each action position from the first imbalance factors and the second imbalance factors of all individual members, and calculate the overall adaptation value corresponding to the action position;

[0138] If the overall adaptation value is greater than the preset adaptation value corresponding to the action position, then adjust the corresponding sequence according to the first imbalance factor and the second imbalance factor involved in the action position and in combination with the prominent characteristics of the team theme, so as to realize the local clothing adjustment;

[0139] Otherwise, adjust according to the sequence that does not correspond to the corresponding action position;

[0140] According to the final result of each action position, an adjusted local sequence is obtained.

[0141] In this embodiment, the body model framework and the head model framework are combined to obtain the self-profile framework.

[0142] In this embodiment, the convertible advantages are, for example, short legs, and the disadvantages can be covered up by dressing up. The prominent advantages refer to the existing advantages of oneself, and these advantages can be used to make the overall performance atmosphere more prominent.

[0143] In this embodiment, each convertible advantage and prominent advantage is realized based on the self-profile framework, that is, there is a certain position correspondence relationship with the self-profile framework. At this time, in addition to determining the first imbalance factor and the second imbalance factor, position matching is required to determine the imbalance factor based on this position and regard it as an adaptation factor to calculate the overall adaptation value.

[0144] For example, for the first imbalance factor a1 and the second imbalance factor a2 involved in action position 1, at this time, a1 and a2 are the adaptation factors corresponding to the action position, and the overall adaptation value of this position = the position weight of this position × (a1 + a2).

[0145] In this embodiment, the preset adaptation value is preset and stored in the position-adaptation value comparison table, which contains different action positions and the preset adaptation values matched with these positions.

[0146] In this embodiment, the adjustment of the corresponding sequence is the result obtained by inputting the initial set performance result, the first imbalance factor and the second imbalance factor involved, and combining the prominent characteristics of the team theme into the combined analysis model for analysis. The combined analysis model contains different set combinations and the sequence adjustment results corresponding to the combinations as samples for training the neural network model, and can be directly trained.

[0147] In this embodiment, the difference between the final result and the initial set performance result is that the result is more in line with the members themselves while meeting the overall requirements of the team.

[0148] The beneficial effects of the above technical solutions are: by determining the imbalance coefficients of the convertible advantages and prominent advantages, it is convenient to calculate the overall adaptation value, and then through the size judgment and analysis of the overall adaptation value, the reasonable adjustment of the sequence is realized. While meeting the overall demand effect, it is also more in line with the personnel themselves, providing a basis for the integration of clothing.

[0149] The present invention provides an integrated clothing style recommendation method based on team needs, which obtains a second clothing recommendation set corresponding to a single member by adjusting a local sequence, including:

[0150] comparing the adjusted local sequence with a personalized clothing database;

[0151] According to the comparison result, a second clothing recommendation set corresponding to the individual member is obtained.

[0152] In this embodiment, the personalized clothing database includes recommended clothing under different combination realization results, and is a pre-set storage database.

[0153] The beneficial effect of the above technical solution is that by comparing the sequence with the database, it is easy to obtain a recommendation set, which facilitates subsequent integration.

[0154] The present invention provides an integrated clothing style recommendation method based on team needs, which performs clothing integration processing according to the first clothing recommendation set and all second clothing recommendation sets to obtain clothing recommendation results, including:

[0155] Inputting the first clothing recommendation set and each second clothing recommendation set into a team clothing analysis table in sequence, wherein the team clothing analysis table includes overall clothing elements and unique clothing elements of different individual members;

[0156] Count the coordination between each column's unique clothing element and each overall clothing element;

[0157] If all coordination is greater than the corresponding preset, the corresponding unique clothing elements will be retained;

[0158] Otherwise, the elements whose coordination is less than the preset among all the unique clothing elements of each individual member are locked and regarded as the first elements, and the elements to be adjusted and the personnel to be adjusted are screened by counting the first number of the first elements involved in each individual member and counting the second number of the first elements involved in each column of unique clothing elements;

[0159] Weakening the local parameter set of the personnel to be adjusted according to the global parameter set and in combination with the division of labor roles of the personnel to be adjusted;

[0160] Performing information standardization processing on the element information of the unique clothing element in the column corresponding to the element to be adjusted according to the clothing set with the maximum recommendation coefficient in the first clothing recommendation set;

[0161] According to the weakening processing results and the information standardization processing results, the clothing recommendation results are obtained.

[0162] In this embodiment, the team clothing analysis form includes descriptions of all clothing elements, and the clothing elements are divided into overall clothing elements and unique clothing elements. Among them, the clothing recommendation set is input into the clothing element analysis model to obtain the clothing elements of the corresponding members, and this model is trained on a neural network model with different clothing recommendation sets and the analysis results of the clothing elements in the recommendation set by a clothing stylist as samples. Therefore, the clothing elements involved by each member can be directly obtained. Among them, the overall clothing elements correspond to global parameters, and the unique clothing elements correspond to local parameters.

[0163] In this embodiment, all the results in the corresponding table are standardized to obtain corresponding values, which is convenient for subsequent calculations.

[0164] In this embodiment, coordination = the average value of the sum of the relative matching values of the unique clothing elements in the corresponding column and the corresponding overall clothing elements, and the relative matching value is obtained from the unique-overall clothing comparison table. This table includes the result coordination degrees of different unique clothing elements and the results of overall clothing elements, that is, whether the clothes match. The more coordinated, the higher the result coordination degree, and the average value of all result coordination degrees is the coordination.

[0165] In this embodiment, the presupposition is set in advance. For example, the coordination between a silk scarf and a one-piece coat is 0.6, and the presupposition is 0.4. At this time, the corresponding unique clothing elements are retained. Otherwise, first lock the unique elements with coordination less than the presupposition as the first elements, and at the same time, lock the second elements with result coordination degrees less than the presupposition from each column;

[0166] If the number of the first elements of the same member is greater than half of the number of all clothing elements, the member is regarded as a person to be adjusted.

[0167] If the number of the second elements is greater than half of the number of all individual members, then the element is regarded as an element to be adjusted, and the element to be adjusted is only for unique clothing elements.

[0168] In this embodiment, the purpose of the weakening process is to weaken the effect of each local parameter in the corresponding local parameter set on the corresponding person. For example, originally, the person to be adjusted was supposed to wear high-necked clothes, but after weakening, it can be round-necked clothes.

[0169] In this embodiment, the first recommended clothing in the first clothing recommendation set is sorted in descending order of the recommendation coefficient, and the first recommended clothing is obtained during the matching process according to the global parameter set. This matching process can directly obtain the corresponding recommendation coefficient, that is, the higher the matching degree, the higher the corresponding recommendation coefficient.

[0170] In this embodiment, information standardization refers to standardizing the element information of unique clothing elements based on the clothing set with the maximum recommended coefficient, so as to meet the overall clothing effect.

[0171] In this embodiment, the clothing recommendation result is the result of weakening processing, information standardization processing, and the original unchanged result.

[0172] For example, the weakening processing is to change the high collar to a round collar, and the information standardization processing is to adjust the 1*1m wide silk scarf of the corresponding element to a 0.5*0.5m wide silk scarf, or to increase the number of buttons on the cuffs from 2 to 5, etc.

[0173] The beneficial effects of the above technical solution are as follows: through the coordinated analysis of unique clothing elements and overall clothing elements in the team clothing analysis form, and then determining the quantity of different elements through size comparison to initially determine the elements to be adjusted and the personnel to be adjusted, and combining weakening processing and information standardization processing to ensure the integrity and integration of the result, which is convenient for ensuring the atmosphere of the overall performance and improving the clothing recommendation efficiency.

[0174] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. An integrated clothing style recommendation method based on team needs, characterized in that: include: Step 1: Analyze team needs based on team theme to obtain a global parameter set and a local parameter set around the team theme, wherein the global parameter set is related to the overall clothing style of the team, and the local parameter set is related to the clothing style of individuals in the team; Step 2: Collect the first clothing recommendation set matching each global parameter in the global parameter set; Step 3: Mapping the local parameter set to the self-contour framework of each individual member, and obtaining a second clothing recommendation set for each individual member; Step 4: Performing clothing integration processing according to the first clothing recommendation set and all the second clothing recommendation sets to obtain clothing recommendation results, wherein the clothing recommendation results include the overall dress of the team and the individual dress of each member; The team requirements are parsed based on the team theme to obtain a global parameter set and a local parameter set around the team theme, including: Based on the team theme, a demand analysis model is obtained by matching from a theme-model comparison table; Analyze the team requirements according to the requirements analysis model to obtain a plurality of first initial parameters and a plurality of second initial parameters; Based on the required role of each first initial parameter in the parsing process, an initial radius is set to the corresponding first initial parameter; Setting a first weight based on the first initial parameters corresponding to all initial radii; At the same time, an equal weight is assigned to each second initial parameter as a second weight; Counting all first initial parameters set with first weights as a global parameter set; Counting all second initial parameters set with second weights as a local parameter set; The first weight is set based on the first initial parameters corresponding to all the initial radii, including: Determine the circumference and the circumference area of ​​the circle corresponding to the first initial parameter based on the set initial radius; Performing a first normal distribution process on all the circumferences of the circles to obtain a first radius, and at the same time, performing a second normal distribution process on all the circumference areas to obtain a second radius; Selecting a maximum radius and a minimum radius from all initial radii, and setting a radius threshold based on a difference between the maximum radius and the minimum radius and in combination with the first radius and the second radius; ;in, Indicates the corresponding radius threshold; Respectively represent the average values ​​based on all first radii and all second radii; Respectively represent the maximum radius and the minimum radius; Respectively represent the number of all first radii and the number of all second radii; represents the radius fine-tuning function; Performing intersection processing on the first initial quantity of the long side radius outside the first normal distribution and the first initial quantity of the long side radius outside the second normal distribution to obtain an intersection initial parameter; If the number of the intersection initial parameters is 0, setting a first importance value for each first initial parameter according to a difference between an initial radius of each first initial parameter and a radius threshold; ;in, represents the first important value of the i1th first initial parameter; represents the initial radius of the i1th first initial parameter; If the number of the intersection initial parameters is not 0, then according to the number of long side radii corresponding to each first initial parameter and in combination with the difference between the initial radius of each first initial parameter and the radius threshold, a second important value is set for each first initial parameter; ;in, represents the second most important value of the i1th first initial parameter; Indicates that the initial radius corresponding to the i1th first initial parameter belongs to the number of long side radii; It indicates the number of parameters whose initial radius belongs to the long side radius among all the first initial parameters; ln indicates the sign of the logarithmic function; based on the important values ​​of all the first initial parameters, a first weight is set for the corresponding first initial parameter.

2. The integrated clothing style recommendation method based on team needs according to claim 1 is characterized in that: Collecting a first clothing recommendation set matching each global parameter in the global parameter set, including: According to the parameter attribute of the global parameter, a first clothing recommendation set matching the parameter attribute is matched from an attribute-clothing database.

3. The integrated clothing style recommendation method based on team needs according to claim 1 is characterized in that: Mapping the local parameter set to the self-profile framework of each individual member includes: Determine the action position of each local parameter in the local parameter set, compare the action position with the self-contour framework, and combine the initial setting performance result of each local parameter to obtain the initial local sequence corresponding to the individual member; Obtain the outstanding advantages and convertible advantages of each individual member's own profile structure, and adjust the initial local sequence in combination with the outstanding characteristics of the team theme; The second clothing recommendation set corresponding to the individual member is obtained by adjusting the local sequence.

4. The integrated clothing style recommendation method based on team needs according to claim 3 is characterized in that: The initial local sequence is adjusted, including: Acquire the transferable and outstanding advantages of each individual member based on their own profile framework; Determine a first imbalance coefficient corresponding to the convertible advantage of the individual member, and at the same time, determine a second imbalance coefficient corresponding to the outstanding advantage of the individual member; ； ;in, represents the first imbalance coefficient corresponding to the j1th convertible advantage of the individual member; represents the second imbalance coefficient corresponding to the j2th prominent advantage of the individual member; It indicates the number of times the historical costumes corresponding to the j1-th convertible advantage of a single member are recommended and adjusted successfully; represents the total number of historical occurrences consistent with the j1th convertible advantage of the corresponding individual member; represents the number of failed historical recommended adjustments consistent with the j1th convertible advantage of the corresponding individual member; It represents the advantage prominence coefficient corresponding to the j1th convertible advantage of the individual member; It represents the advantage prominence coefficient corresponding to the j2th prominence of the individual member; Indicates the total number of convertible advantages involved in the corresponding individual member; It represents the total number of convertible advantages involved by all individual members; The variance of the advantage salience coefficient representing the convertible advantages involved by all individual members; Extracting the adaptation factor based on each action position from the first imbalance factors and the second imbalance factors of all individual members, and calculating the overall adaptation value of the corresponding action position; If the overall adaptation value is greater than the preset adaptation value of the corresponding action position, the corresponding sequence is adjusted according to the first imbalance factor and the second imbalance factor involved in the corresponding action position and in combination with the prominent characteristics of the team theme to achieve partial clothing adjustment; Otherwise, the sequence of the corresponding action positions is not adjusted; According to the final result of each action position, an adjusted local sequence is obtained.

5. The integrated clothing style recommendation method based on team needs according to claim 4 is characterized in that: According to the adjustment of the local sequence, the second clothing recommendation set corresponding to the individual member is obtained, including: comparing the adjusted local sequence with a personalized clothing database; According to the comparison result, a second clothing recommendation set corresponding to the individual member is obtained.

6. The integrated clothing style recommendation method based on team needs according to claim 1 is characterized in that: Performing clothing integration processing according to the first clothing recommendation set and all second clothing recommendation sets to obtain clothing recommendation results, including: inputting the first clothing recommendation set and each second clothing recommendation set into a team clothing analysis table in sequence, wherein the team clothing analysis table includes overall clothing elements and unique clothing elements of different individual members; Count the coordination between each column's unique clothing element and each overall clothing element; If all coordination is greater than the corresponding preset, the corresponding unique clothing elements will be retained; Otherwise, the elements whose coordination is less than the preset among all the unique clothing elements of each individual member are locked and regarded as the first elements, and the elements to be adjusted and the personnel to be adjusted are screened by counting the first number of the first elements involved in each individual member and counting the second number of the first elements involved in each column of unique clothing elements; Weakening the local parameter set of the personnel to be adjusted according to the global parameter set and in combination with the division of labor roles of the personnel to be adjusted; performing information standardization processing on the element information of the unique clothing element in the column corresponding to the element to be adjusted according to the clothing set with the maximum recommendation coefficient in the first clothing recommendation set; According to the weakening processing results and the information standardization processing results, the clothing recommendation results are obtained.

Images