Intelligent analysis method and system for fabric texture of children's clothing

Abstract

The application discloses a fabric texture intelligent analysis method and system based on children's clothes, and the method comprises the following steps: acquiring a plurality of sensing collection information of a plurality of users when wearing children's clothes, and user parameters and fabric types corresponding to each sensing collection information; according to the sensing collection information and the fabric types, predicting fabric feeling parameters corresponding to each fabric type based on a neural network algorithm; establishing a fabric-user-feeling prediction mathematical relationship model according to the fabric feeling parameters corresponding to each fabric type and the user parameters; and determining the fabric types corresponding to a target user group based on the fabric-user-feeling prediction mathematical relationship model according to user parameters and sensing parameters of the target user group. It can be seen that the application can realize more intelligent and accurate quantitative evaluation of the comfort of clothes, and improve the effect and efficiency of user clothing customization services.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of clothing big data analysis, and particularly relates to a fabric texture intelligent analysis method and system based on children's clothing. BACKGROUND

[0002] Sensing technology has begun to be widely applied in the clothing industry, and more and more clothing will combine sensing data when designing to improve the efficiency of design and the comfort of the designed clothing. However, in the analysis of fabric texture, the existing technology still generally relies heavily on manual data analysis and judgment, and does not effectively combine sensing data and intelligent algorithms to improve the accuracy and effect of analysis. It can be seen that the existing technology has defects and needs to be solved urgently. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a fabric texture intelligent analysis method and system based on children's clothing, which can realize more intelligent and accurate quantitative evaluation of the comfort of clothing and improve the effect and efficiency of user clothing customization service.

[0004] To solve the above technical problems, the present application discloses a fabric texture intelligent analysis method based on children's clothing, which comprises:

[0005] Obtaining a plurality of sensing collection information of a plurality of users when wearing children's clothing, and user parameters and fabric types corresponding to each sensing collection information;

[0006] According to the sensing collection information and the fabric type, based on a neural network algorithm, predicting a fabric feeling parameter corresponding to each fabric type;

[0007] According to the fabric feeling parameter corresponding to each fabric type and the user parameter, a fabric-user-feeling prediction mathematical relationship model is established;

[0008] In response to a clothing production request of a target user group, according to the user parameters and sensing parameters of the target user group, based on the fabric-user-feeling prediction mathematical relationship model, the fabric type corresponding to the target user group is determined.

[0009] As an optional implementation, in the first aspect of the present application, the sensor collected information or the sensor parameter includes one or more of image sensor information, infrared ranging information, sound sensor information, positioning sensor information and temperature sensor information; and / or, the fabric type includes one or more of pure cotton fabric type, cotton type chemical fabric type, worsted wool fabric type, woolen fabric type, silk fabric type, silk fabric type, rayon fabric type, hemp fabric type, elastic fabric type, suede fabric type and environmentally friendly fabric type; and / or, the user parameter includes at least one of user gender, user age, user body physical parameter and user physiological index parameter.

[0010] As an optional implementation, in the first aspect of the present application, the prediction of the fabric feeling parameter corresponding to each fabric type based on the neural network algorithm according to the sensor collected information and the fabric type includes:

[0011] All the sensor collected information corresponding to the same fabric type is classified into a sensor information set corresponding to the fabric type;

[0012] For each sensor information set, the sensor information set is divided into a skin-attached sensor information set and an outer-wearing sensor information set according to the skin distance of each sensor collected information in the sensor information set;

[0013] The skin-attached sensor information set is input into a corresponding trained fabric skin-attached feeling prediction model to obtain the skin-attached feeling parameter corresponding to the sensor information set; the fabric skin-attached feeling prediction model is trained by a plurality of training skin-attached sensor information corresponding to the fabric type and a corresponding training data set of skin-attached feeling goodness annotation;

[0014] The outer-wearing sensor information set is input into a corresponding trained fabric outer-wearing feeling prediction model to obtain the outer-wearing feeling parameter corresponding to the sensor information set; the fabric outer-wearing feeling prediction model is trained by a plurality of training outer-wearing sensor information corresponding to the fabric type and a corresponding training data set of outer-wearing feeling goodness annotation;

[0015] The fabric feeling parameter corresponding to the fabric type corresponding to the sensor information set is determined according to the skin-attached feeling parameter and the outer-wearing feeling parameter corresponding to the sensor information set.

[0016] As an optional implementation, in the first aspect of the present application, for each sensor information set, the sensor information set is divided into a skin-attached sensor information set and an outer-wearing sensor information set according to the skin distance of each sensor collected information in the sensor information set, including:

[0017] acquire a collection time skin distance, a history skin distance record and a device preset type of a collection device corresponding to each of the sensing collection information; the device preset type is a skin-attached type or an external-wearing type; the skin distance is calculated by communication between the collection device and a sensing device arranged on the skin;

[0018] for each of the sensing collection information, determine whether the collection time skin distance corresponding to the sensing collection information meets a distance mathematical rule corresponding to the device preset type, to obtain a first determination result;

[0019] if the first determination result is yes, determine the distance type of the sensing collection information as the device preset type;

[0020] if the first determination result is no, filter a plurality of difference distance records with a similarity less than a preset similarity threshold from the history skin distance record of the sensing collection information;

[0021] determine whether the plurality of difference distance records and corresponding record times meet a preset stable distance record rule, to obtain a second determination result; the stable distance record rule is a mathematical rule for limiting record times of the plurality of difference distance records to form a stable maintenance time period;

[0022] if the second determination result is yes, determine the distance type of the sensing collection information as the device preset type;

[0023] if the second determination result is no, determine the distance type of the sensing collection information as a type different from the device preset type;

[0024] divide the sensing collection information belonging to the skin-attached type in each of the sensing information sets into a skin-attached sensing information set, and divide the sensing collection information belonging to the external-wearing type into an external-wearing sensing information set, to obtain the skin-attached sensing information set and the external-wearing sensing information set corresponding to the sensing information set.

[0025] As an optional implementation, in the first aspect of the present application, the determination of the fabric feeling parameter corresponding to the fabric type according to the skin-attached feeling parameter and the external-wearing feeling parameter corresponding to the sensing information set comprises:

[0026] calculating a history application record of the fabric type corresponding to the sensing information set; the history application record comprises a record of the fabric corresponding to the fabric type being applied in a skin-attached type or an external-wearing type of garment in a history time period;

[0027] According to the historical application record, a skin weight and an outer wear weight corresponding to the set of sensing information are calculated; a size relationship between the skin weight and the outer wear weight is consistent with a size relationship between a number of records of the fabric type applied to a skin type and a number of records of the fabric type applied to an outer wear type in the historical application record; the skin weight is proportional to a proportion of records of the fabric type applied to the skin type in the historical application record; and the outer wear weight is proportional to a proportion of records of the fabric type applied to the outer wear type in the historical application record.

[0028] A first product of the skin feeling parameter and the skin weight is calculated.

[0029] A second product of the outer wear feeling parameter and the outer wear weight is calculated.

[0030] A sum of the first product and the second product is calculated to obtain a fabric feeling parameter corresponding to the fabric type corresponding to the set of sensing information.

[0031] As an optional implementation, in the first aspect of the present application, the fabric-user-feeling prediction mathematical relationship model is established according to the fabric feeling parameter corresponding to each fabric type and the user parameter, and includes:

[0032] Each fabric type and the corresponding fabric feeling parameter are taken as a training data set of a neural network model, and a fabric-feeling prediction mathematical relationship model is established, which is used to output a predicted fabric feeling prediction value according to an input fabric type;

[0033] A user-fabric tendency prediction mathematical relationship model is established according to the sensing collection information corresponding to each user parameter and the fabric feeling parameter, which is used to output a predicted tendency prediction parameter corresponding to a different fabric type according to an input user parameter;

[0034] The fabric-feeling prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model are determined as the fabric-user-feeling prediction mathematical relationship model.

[0035] As an optional implementation, in the first aspect of the present application, the user-fabric tendency prediction mathematical relationship model is established according to the sensing collection information corresponding to each user parameter and the fabric feeling parameter, and includes:

[0036] All the sensing collection information corresponding to each user parameter is taken as a data group corresponding to each user parameter, and a plurality of user classification indexes are screened out based on a principal component analysis algorithm; each user classification index includes at least one user parameter.

[0037] Determine all fabric types corresponding to all sensor collection information corresponding to all user parameters in each of the user classification indicators, to obtain a plurality of fabric types corresponding to each of the user classification indicators;

[0038] Calculate the average value of all fabric perception parameters corresponding to each fabric type corresponding to each of the user classification indicators, to obtain a tendency parameter corresponding to each fabric type corresponding to each of the user classification indicators;

[0039] All user parameters of all user classification indicators and tendency parameters corresponding to each fabric type corresponding to the user classification indicators are used as a training data set of a neural network model, and a user-fabric tendency prediction mathematical relationship model is established.

[0040] As an optional implementation, in the first aspect of the present application, the determination of the fabric type corresponding to the target user group based on the user parameters and sensor parameters of the target user group and based on the fabric-user-perception prediction mathematical relationship model comprises:

[0041] Obtain user parameters of all users of the target user group to obtain a user parameter set;

[0042] Calculate the parameter similarity between the user parameter set and each of the user classification indicators, and determine the user classification indicator with the highest parameter similarity as the target user classification indicator;

[0043] Determine the intersection between the user parameter set and the target user classification indicator, input all user parameters in the intersection into the user-fabric tendency prediction mathematical relationship model, and obtain a plurality of fabric types and corresponding tendency prediction parameters as output;

[0044] Determine the plurality of fabric types with the tendency prediction parameter greater than a preset first parameter threshold as a plurality of candidate fabric types;

[0045] Input each of the candidate fabric types into the fabric-perception prediction mathematical relationship model to obtain a fabric perception prediction value corresponding to each of the candidate fabric types as output;

[0046] Calculate the weighted sum average value of the tendency prediction parameter and the fabric perception prediction value corresponding to each of the candidate fabric types to obtain a selection parameter corresponding to each of the candidate fabric types;

[0047] Determine the candidate fabric type with the selection parameter greater than a preset second parameter threshold as the fabric type corresponding to the target user group.

[0048] The second aspect of the present application discloses a fabric texture intelligent analysis system based on children's clothing, which comprises:

[0049] an acquisition module, configured to acquire a plurality of sensor collection information of a plurality of users when wearing a child garment, and a user parameter and a fabric type corresponding to each of the sensor collection information;

[0050] a prediction module, configured to predict, based on a neural network algorithm, a fabric feeling parameter corresponding to each of the fabric types according to the sensor collection information and the fabric type;

[0051] a modeling module, configured to establish a fabric-user-feeling prediction mathematical relationship model according to the fabric feeling parameter corresponding to each of the fabric types and the user parameter;

[0052] a determination module, configured to determine a fabric type corresponding to a target user group based on the fabric-user-feeling prediction mathematical relationship model according to a user parameter and a sensor parameter of the target user group in response to a garment making request of the target user group.

[0053] As an optional implementation, in the second aspect of the present application, the sensor collection information or the sensor parameter includes one or more of image sensor information, infrared distance measurement information, sound sensor information, positioning sensor information and temperature sensor information; and / or, the fabric type includes one or more of pure cotton fabric type, cotton type chemical fiber fabric type, worsted wool fabric type, woolen fabric type, silk type, silk type, artificial silk type, hemp fabric type, elastic fabric type, suede fabric type and environment-friendly fabric type; and / or, the user parameter includes at least one of user gender, user age, user body physical parameter and user physiological index parameter.

[0054] As an optional implementation, in the second aspect of the present application, the specific manner in which the prediction module predicts the fabric feeling parameter corresponding to each of the fabric types based on a neural network algorithm according to the sensor collection information and the fabric type includes:

[0055] all the sensor collection information corresponding to the same fabric type are classified into a sensor information set corresponding to the fabric type;

[0056] for each of the sensor information sets, each of the sensor collection information in the sensor information set is classified into a skin sensor information set and an external sensor information set according to the skin distance of the sensor collection information;

[0057] the skin sensor information set is input into a corresponding trained fabric skin feeling prediction model to obtain a skin feeling parameter corresponding to the sensor information set; the fabric skin feeling prediction model is trained by a plurality of training skin sensor information corresponding to the fabric type and a corresponding training data set of skin feeling goodness annotation;

[0058] inputting the set of the outer-wearing sensing information into a corresponding trained fabric outer-wearing feeling prediction model to obtain an outer-wearing feeling parameter corresponding to the set of the sensing information; the fabric outer-wearing feeling prediction model is trained by a plurality of training sets of outer-wearing sensing information corresponding to a plurality of fabric types and a plurality of corresponding outer-wearing feeling goodness annotations;

[0059] determining a fabric feeling parameter corresponding to the fabric type corresponding to the set of the sensing information according to the skin-attached feeling parameter and the outer-wearing feeling parameter corresponding to the set of the sensing information.

[0060] As an optional implementation, in the second aspect of the present application, the specific manner in which the prediction module divides the set of the sensing information into the set of the skin-attached sensing information and the set of the outer-wearing sensing information according to the skin distance of each sensing collection information in the set of the sensing information includes:

[0061] obtaining the collection skin distance, the historical skin distance record and the preset type of the collection device corresponding to each sensing collection information; the preset type of the collection device is a skin-attached type or an outer-wearing type; the skin distance is calculated by communication between the collection device and the sensing device arranged on the skin;

[0062] for each sensing collection information, determining whether the collection skin distance corresponding to the sensing collection information meets the distance mathematical rule corresponding to the preset type of the collection device to obtain a first determination result;

[0063] if the first determination result is yes, the distance type of the sensing collection information is determined as the preset type of the collection device;

[0064] if the first determination result is no, a plurality of difference distance records with a similarity less than a preset similarity threshold to the collection skin distance are screened out from the historical skin distance record of the sensing collection information;

[0065] determining whether the plurality of difference distance records and the corresponding record time meet a preset stable distance record rule to obtain a second determination result; the stable distance record rule is a mathematical rule for limiting the record time of the plurality of difference distance records to form a stable maintenance time period;

[0066] if the second determination result is yes, the distance type of the sensing collection information is determined as the preset type of the collection device;

[0067] if the second determination result is no, the distance type of the sensing collection information is determined as a type different from the preset type of the collection device;

[0068] Divide the sensing information belonging to the skin type in each of the sensing information sets into a skin sensing information set, and divide the sensing information belonging to the outer type into an outer sensing information set, to obtain the skin sensing information set and the outer sensing information set corresponding to the sensing information set.

[0069] As an optional implementation, in the second aspect of the present application, the specific manner in which the prediction module determines the fabric feeling parameter corresponding to the fabric type corresponding to the sensing information set according to the skin feeling parameter and the outer feeling parameter corresponding to the sensing information set comprises:

[0070] Calculate the historical application record of the fabric type corresponding to the sensing information set; the historical application record comprises the record of the fabric corresponding to the fabric type being applied in the clothing of the skin type or the outer type in the historical time period;

[0071] According to the historical application record, calculate the skin weight and the outer weight corresponding to the sensing information set; the size relationship between the skin weight and the outer weight is consistent with the size relationship between the number of records in the historical application record in which the fabric type is applied in the skin type and the number of records in the historical application record in which the fabric type is applied in the outer type; the skin weight is proportional to the proportion of the record in the historical application record in which the fabric type is applied in the skin type; the outer weight is proportional to the proportion of the record in the historical application record in which the fabric type is applied in the outer type;

[0072] Calculate the first product of the skin feeling parameter and the skin weight;

[0073] Calculate the second product of the outer feeling parameter and the outer weight;

[0074] Calculate the sum of the first product and the second product, to obtain the fabric feeling parameter corresponding to the fabric type corresponding to the sensing information set.

[0075] As an optional implementation, in the second aspect of the present application, the specific manner in which the modeling module establishes the fabric-user-feeling prediction mathematical relationship model according to the fabric feeling parameter corresponding to each of the fabric types and the user parameter comprises:

[0076] Use each of the fabric types and the corresponding fabric feeling parameter as the training data set of the neural network model, to establish the fabric-feeling prediction mathematical relationship model, which is used to output the predicted fabric feeling prediction value according to the input fabric type;

[0077] According to the sensing collection information corresponding to each of the user parameters and the fabric feeling parameters, a user-fabric tendency prediction mathematical relationship model is established, which is used to output a predicted tendency prediction parameter corresponding to a different fabric type according to an input user parameter;

[0078] The fabric-feeling prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model are determined as a fabric-user-feeling prediction mathematical relationship model.

[0079] As an optional implementation, in the second aspect of the present application, the specific manner in which the modeling module establishes the user-fabric tendency prediction mathematical relationship model according to the sensing collection information corresponding to each of the user parameters and the fabric feeling parameters comprises:

[0080] All the sensing collection information corresponding to each of the user parameters is taken as a data group corresponding to each of the user parameters, and a plurality of user classification indexes are screened out based on a principal component analysis algorithm; each user classification index comprises at least one of the user parameters;

[0081] All the fabric types corresponding to all the sensing collection information corresponding to all the user parameters in each of the user classification indexes are determined to obtain a plurality of fabric types corresponding to each of the user classification indexes;

[0082] An average value of all the fabric feeling parameters corresponding to each of the fabric types corresponding to each of the user classification indexes is calculated to obtain a tendency parameter corresponding to each of the fabric types corresponding to each of the user classification indexes;

[0083] All the user parameters of all the user classification indexes and the tendency parameter corresponding to each of the fabric types corresponding to the user classification indexes are taken as a training data set of a neural network model to establish a user-fabric tendency prediction mathematical relationship model.

[0084] As an optional implementation, in the second aspect of the present application, the specific manner in which the determining module determines the fabric type corresponding to the target user group according to the user parameters and the sensing parameters of the target user group based on the fabric-user-feeling prediction mathematical relationship model comprises:

[0085] User parameters of all the users of the target user group are obtained to obtain a user parameter set;

[0086] A parameter similarity between the user parameter set and each of the user classification indexes is calculated, and the user classification index with the highest parameter similarity is determined as a target user classification index;

[0087] determining an intersection between the user parameter set and the target user classification index, inputting all user parameters in the intersection into the user-fabric inclination prediction mathematical relationship model to obtain a plurality of fabric types and corresponding inclination prediction parameters as output;

[0088] determining a plurality of fabric types with inclination prediction parameters greater than a preset first parameter threshold as a plurality of candidate fabric types;

[0089] inputting each of the candidate fabric types into the fabric-feeling prediction mathematical relationship model to obtain a fabric-feeling prediction value corresponding to each of the candidate fabric types as output;

[0090] calculating a weighted sum average value of the inclination prediction parameter and the fabric-feeling prediction value corresponding to each of the candidate fabric types to obtain a selection parameter corresponding to each of the candidate fabric types;

[0091] determining the candidate fabric type with the selection parameter greater than a preset second parameter threshold as the fabric type corresponding to the target user group.

[0092] A third aspect of the present application discloses another fabric texture intelligent analysis system based on children's clothing, which comprises:

[0093] a memory storing executable program codes;

[0094] a processor coupled with the memory;

[0095] The processor invokes the executable program codes stored in the memory to execute part or all of the steps of the fabric texture intelligent analysis method based on children's clothing disclosed in the first aspect of the present application.

[0096] A fourth aspect of the present application discloses a computer storage medium storing computer instructions, which are invoked to execute part or all of the steps of the fabric texture intelligent analysis method based on children's clothing disclosed in the first aspect of the present application.

[0097] Compared with the prior art, the present application has the following beneficial effects:

[0098] The present application can predict and establish a big data prediction model according to the try-on sensing data of a plurality of users, can combine the prediction model according to the parameters of a requested user group, and predict an optimal fabric type, so as to realize more intelligent and accurate quantitative evaluation of the comfort of clothing and improve the effect and efficiency of user clothing customization service. BRIEF DESCRIPTION OF DRAWINGS

[0099] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative effort.

[0100] Figure 1 is a flow diagram of a fabric texture intelligent analysis method based on children's clothing disclosed by an embodiment of the present application;

[0101] Figure 2 is a structural diagram of a fabric texture intelligent analysis system based on children's clothing disclosed by an embodiment of the present application;

[0102] Figure 3 is a structural diagram of another fabric texture intelligent analysis system based on children's clothing disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0103] In order to make the personnel in the technical field better understand the present application scheme, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0104] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or end.

[0105] In this paper, the phrase "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0106] The application discloses a fabric texture intelligent analysis method and system based on children's clothes, can predict and establish a big data prediction model according to the try-on sensing data of multiple users, can combine the prediction model according to the parameters of a requested user group, and predict an optimal fabric type, so that the comfort of the clothes can be more intelligently and accurately quantitatively evaluated, and the effect and efficiency of the user's clothes customization service are improved. The following will be described in detail.

[0107] Embodiment one

[0108] Please refer to Figure 1 , Figure 1 is a flowchart of a fabric texture intelligent analysis method based on children's clothes disclosed by the embodiment of the application. Wherein, Figure 1 The method described can be applied to a corresponding data processing device, data processing terminal, data processing server, and the server can be a local server or a cloud server, and the embodiment of the application does not limit Figure 1 As shown, the fabric texture intelligent analysis method based on children's clothes can include the following operations:

[0109] 101, obtaining multiple sensing collection information of multiple users when wearing children's clothes and user parameters and fabric types corresponding to each sensing collection information.

[0110] Optionally, the sensing collection information or sensing parameter includes one or more of image sensing information, infrared distance measuring information, sound sensing information, positioning sensing information and temperature sensing information.

[0111] Optionally, the fabric type includes one or more of pure cotton type, cotton type chemical fiber fabric type, worsted wool fabric type, woolen fabric type, silk type, silk type, artificial silk type, hemp fabric type, elastic fabric type, sanding fabric type and environment-friendly fabric type.

[0112] Optionally, the user parameter includes at least one of user gender, user age, user body physical parameter and user physiological index parameter.

[0113] 102, according to the sensing collection information and the fabric type, based on the neural network algorithm, predicting the fabric feeling parameter corresponding to each fabric type.

[0114] 103, according to the fabric feeling parameter corresponding to each fabric type and the user parameter, establishing a fabric-user-feeling prediction mathematical relationship model.

[0115] 104, in response to the clothes making request of the target user group, according to the user parameter and the sensing parameter of the target user group, based on the fabric-user-feeling prediction mathematical relationship model, determining the fabric type corresponding to the target user group.

[0116] It can be seen that the method described in the embodiment of the present application can predict and establish a big data prediction model according to the try-on sensing data of multiple users, and can combine the prediction model according to the parameters of the requested user group to predict the preferred fabric type, so as to realize more intelligent and accurate quantitative evaluation of the comfort of the garment and improve the effect and efficiency of the user's garment customization service.

[0117] As an optional embodiment, in the above step, the fabric feeling parameters corresponding to each fabric type are predicted based on the neural network algorithm according to the sensing collection information and the fabric type, including:

[0118] All sensing collection information corresponding to the same fabric type is classified into a sensing information set corresponding to the fabric type;

[0119] For each sensing information set, the sensing information set is divided into a skin-sensing information set and an outer-wearing sensing information set according to the skin distance of each sensing collection information in the sensing information set;

[0120] The skin-sensing information set is input into a corresponding trained fabric skin feeling prediction model to obtain the skin feeling parameters corresponding to the sensing information set; the fabric skin feeling prediction model is trained by a plurality of training skin-sensing information corresponding to the fabric type and a corresponding training data set of skin feeling goodness annotation;

[0121] The outer-wearing sensing information set is input into a corresponding trained fabric outer-wearing feeling prediction model to obtain the outer-wearing feeling parameters corresponding to the sensing information set; the fabric outer-wearing feeling prediction model is trained by a plurality of training outer-wearing sensing information corresponding to the fabric type and a corresponding training data set of outer-wearing feeling goodness annotation;

[0122] The fabric feeling parameters corresponding to the fabric type corresponding to the sensing information set are determined according to the skin feeling parameters and the outer-wearing feeling parameters corresponding to the sensing information set.

[0123] Through the above embodiment, the fabric skin feeling prediction model and the fabric outer-wearing feeling prediction model can be used to predict the skin feeling parameters and the outer-wearing feeling parameters corresponding to the sensing information set according to the skin-sensing information set and the outer-wearing sensing information set respectively, so as to realize more accurate measurement of the feeling parameters of the fabric type from different dimensions, and facilitate subsequent realization of more accurate modeling.

[0124] As an optional embodiment, in the above step, for each sensing information set, the sensing information set is divided into a skin-sensing information set and an outer-wearing sensing information set according to the skin distance of each sensing collection information in the sensing information set, including:

[0125] acquire the skin distance at collection time, the historical skin distance record and the preset type of the collection device corresponding to each sensing collection information; the preset type of the collection device is a skin-attached type or an external type; the skin distance is calculated by communication between the collection device and the sensing device arranged on the skin;

[0126] for each sensing collection information, determine whether the skin distance at collection time corresponding to the sensing collection information meets the distance mathematical rule corresponding to the preset type of the device, to obtain a first determination result;

[0127] if the first determination result is yes, the distance type of the sensing collection information is determined as the preset type of the device;

[0128] if the first determination result is no, a plurality of difference distance records with a similarity less than a preset similarity threshold to the skin distance at collection time are screened from the historical skin distance record of the sensing collection information;

[0129] determine whether the plurality of difference distance records and the corresponding record time meet a preset stable distance record rule, to obtain a second determination result; the stable distance record rule is a mathematical rule for limiting the record time of the plurality of difference distance records to form a stable maintenance time period;

[0130] if the second determination result is yes, the distance type of the sensing collection information is determined as the preset type of the device;

[0131] if the second determination result is no, the distance type of the sensing collection information is determined as a type different from the preset type of the device;

[0132] divide the sensing collection information belonging to the skin-attached type in each sensing information set into a skin-attached sensing information set, and divide the sensing collection information belonging to the external type into an external sensing information set, to obtain the skin-attached sensing information set and the external sensing information set corresponding to the sensing information set.

[0133] Optionally, the skin distance can be acquired by a position sensor arranged on the skin to acquire a skin position, and then the skin distance is calculated by the distance between the skin position and the device position corresponding to the sensing collection information, or the collection device of the sensing collection information is set as an infrared distance measuring device to directly acquire the skin distance according to the infrared distance measuring device.

[0134] Optionally, the distance mathematical rule and the stable distance record rule can be set by an operator according to experience or experimental data, for example, the distance mathematical rule can be a certain range of skin distance interval, and the stable distance record rule can be that the numerical difference between any difference distance records in a certain range of time interval cannot be greater than a preset numerical threshold.

[0135] Through the above embodiment, the sensing information set can be divided into the skin sensing information set and the outer sensing information set according to comprehensive and accurate data rules, so as to realize more accurate prediction and calculation of the feeling degree in the subsequent.

[0136] As an optional embodiment, in the above step, the fabric feeling parameter corresponding to the fabric type corresponding to the sensing information set is determined according to the skin feeling parameter and the outer feeling parameter corresponding to the sensing information set, and the step comprises:

[0137] The historical application record of the fabric type corresponding to the sensing information set is calculated; the historical application record comprises a record of the fabric type corresponding to the fabric being applied in the skin type or the outer type of clothing in a historical time period;

[0138] The skin weight and the outer weight corresponding to the sensing information set are calculated according to the historical application record; the size relationship between the skin weight and the outer weight is consistent with the size relationship between the record quantity of the fabric type being applied in the skin type and the outer type in the historical application record; the skin weight is proportional to the record proportion of the fabric type being applied in the skin type in the historical application record; the outer weight is proportional to the record proportion of the fabric type being applied in the outer type in the historical application record;

[0139] The first product of the skin feeling parameter and the skin weight is calculated;

[0140] The second product of the outer feeling parameter and the outer weight is calculated;

[0141] The sum of the first product and the second product is calculated to obtain the fabric feeling parameter corresponding to the fabric type corresponding to the sensing information set.

[0142] Specifically, the historical application record can be obtained by an operator according to historical clothing production records through data analysis means, or can be directly recorded and saved by a clothing production company or unit in the production process, and then directly called.

[0143] Through the above embodiment, the application preference of a specific fabric type can be calculated according to the historical application record, and the weight of the feeling parameter in different dimensions is adjusted according to the application preference to calculate the accurate fabric feeling parameter, so as to realize more accurate modeling in the subsequent.

[0144] As an optional embodiment, in the above step, the fabric- user- feeling prediction mathematical relationship model is established according to the fabric feeling parameter corresponding to each fabric type and the user parameter, and the step comprises:

[0145] The fabric-sensation prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model are determined as a fabric-user-sensation prediction mathematical relationship model.

[0146] The user-fabric tendency prediction mathematical relationship model is established according to the sensing collection information corresponding to each user parameter and the fabric sensation parameter.

[0147] The fabric-sensation prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model are determined as a fabric-user-sensation prediction mathematical relationship model.

[0148] Through the above embodiments, the fabric-sensation prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model can be established to comprehensively realize the prediction mathematical relationship between different parameters and improve the prediction effect.

[0149] As an optional embodiment, the user-fabric tendency prediction mathematical relationship model is established according to the sensing collection information corresponding to each user parameter and the fabric sensation parameter, and includes:

[0150] All the sensing collection information corresponding to each user parameter is taken as a data group corresponding to each user parameter, and a plurality of user classification indexes are screened out based on a principal component analysis algorithm. Each user classification index includes at least one user parameter.

[0151] All the fabric types corresponding to all the sensing collection information of all the user parameters in each user classification index are determined to obtain a plurality of fabric types corresponding to each user classification index.

[0152] The average value of all the fabric sensation parameters corresponding to each fabric type corresponding to each user classification index is calculated to obtain a tendency parameter corresponding to each fabric type corresponding to each user classification index.

[0153] All the user parameters of all the user classification indexes and the tendency parameter corresponding to each fabric type corresponding to the user classification index are taken as a training data set of a neural network model to establish the user-fabric tendency prediction mathematical relationship model.

[0154] Through the above embodiments, the principal component analysis can be used to effectively screen out more reasonable and relevant parameter groups, and the corresponding information of the parameter groups can be used to train a more accurate user-fabric tendency prediction mathematical relationship model to improve the prediction effect.

[0155] As an optional embodiment, in the above step, the fabric type corresponding to the target user group is determined based on the fabric-user-feeling prediction mathematical relationship model according to the user parameters and the sensing parameters of the target user group, and the determination includes:

[0156] Obtaining the user parameters of all users in the target user group to obtain a user parameter set;

[0157] Calculating the parameter similarity between the user parameter set and each user classification index, and determining the user classification index with the highest parameter similarity as the target user classification index;

[0158] Determining the intersection between the user parameter set and the target user classification index, and inputting all user parameters in the intersection into the user-fabric tendency prediction mathematical relationship model to obtain a plurality of fabric types and corresponding tendency prediction parameters as output;

[0159] Determining the plurality of fabric types with the tendency prediction parameters greater than the first preset parameter threshold as a plurality of candidate fabric types;

[0160] Inputting each candidate fabric type into the fabric-feeling prediction mathematical relationship model to obtain a fabric feeling prediction value corresponding to each candidate fabric type as output;

[0161] Calculating the weighted sum average of the tendency prediction parameter and the fabric feeling prediction value corresponding to each candidate fabric type to obtain a selection parameter corresponding to each candidate fabric type;

[0162] Determining the candidate fabric type with the selection parameter greater than the second preset parameter threshold as the fabric type corresponding to the target user group.

[0163] Through the above embodiment, the fabric-feeling prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model can be comprehensively utilized to screen out fabric types more suitable for the target user group, improve the prediction effect and user experience, and also improve the efficiency and effect of clothing customization.

[0164] Embodiment two

[0165] Please refer to Figure 2 , Figure 2 is a structure schematic diagram of a fabric texture intelligent analysis system based on children's clothing disclosed by the embodiment of the present application. Among them, Figure 2 The system described can be applied to a corresponding data processing device, data processing terminal, data processing server, and the server can be a local server or a cloud server, and the embodiment of the present application does not limit it. As Figure 2 shown, the system can include:

[0166] The acquisition module 201 is configured to acquire a plurality of sensing collection information of a plurality of users when wearing a child garment, and a user parameter and a fabric type corresponding to each sensing collection information.

[0167] The prediction module 202 is configured to predict a fabric feeling parameter corresponding to each fabric type based on a neural network algorithm according to the sensing collection information and the fabric type.

[0168] The modeling module 203 is configured to establish a fabric-user-feeling prediction mathematical relationship model according to the fabric feeling parameter corresponding to each fabric type and the user parameter.

[0169] The determination module 204 is configured to determine a fabric type corresponding to a target user group based on the fabric-user-feeling prediction mathematical relationship model according to a user parameter and a sensing parameter of the target user group in response to a garment manufacturing request of the target user group.

[0170] As an optional embodiment, the sensing collection information or the sensing parameter includes one or more of image sensing information, infrared distance measurement information, sound sensing information, positioning sensing information and temperature sensing information; and / or, the fabric type includes one or more of a pure cotton type, a cotton type chemical fiber fabric type, a worsted wool fabric type, a woolen fabric type, a real silk type, a silk type, a rayon type, a hemp fabric type, an elastic fabric type, a suede fabric type and an environmentally friendly fabric type; and / or, the user parameter includes at least one of a user gender, a user age, a user body physical parameter and a user physiological index parameter.

[0171] As an optional embodiment, the specific manner in which the prediction module 202 predicts the fabric feeling parameter corresponding to each fabric type based on a neural network algorithm according to the sensing collection information and the fabric type includes:

[0172] All sensing collection information corresponding to the same fabric type is classified into a sensing information set corresponding to the fabric type;

[0173] For each sensing information set, the sensing information set is divided into a skin sensing information set and an external sensing information set according to a skin distance of each sensing collection information in the sensing information set;

[0174] The skin sensing information set is input into a corresponding trained fabric skin feeling prediction model to obtain a skin feeling parameter corresponding to the sensing information set; the fabric skin feeling prediction model is trained by a plurality of training skin sensing information corresponding to the fabric type and a corresponding training data set of skin feeling goodness annotation;

[0175] inputting the outer-wearing sensing information set into a corresponding trained fabric outer-wearing feeling prediction model to obtain outer-wearing feeling parameters corresponding to the sensing information set; the fabric outer-wearing feeling prediction model is trained by a plurality of training outer-wearing sensing information corresponding to fabric types and a corresponding training data set of outer-wearing feeling good degree labels;

[0176] According to the skin feeling parameters and the outer-wearing feeling parameters corresponding to the sensing information set, the fabric feeling parameters corresponding to the fabric type corresponding to the sensing information set are determined.

[0177] As an optional embodiment, the prediction module 202 divides each sensing information set into a skin-wearing sensing information set and an outer-wearing sensing information set according to the skin distance of each sensing collection information in the sensing information set.

[0178] The collection skin distance, historical skin distance record and device preset type corresponding to the collection device of each sensing collection information are obtained; the device preset type is a skin type or an outer-wearing type; the skin distance is calculated by communication between the collection device and the sensing device arranged on the skin;

[0179] For each sensing collection information, it is judged whether the collection skin distance corresponding to the sensing collection information meets the distance mathematical rule corresponding to the device preset type, to obtain a first judgment result;

[0180] If the first judgment result is yes, the distance type of the sensing collection information is determined as the device preset type;

[0181] If the first judgment result is no, a plurality of difference distance records with a similarity less than a preset similarity threshold are selected from the historical skin distance record of the sensing collection information;

[0182] It is judged whether the plurality of difference distance records and the corresponding record time meet a preset stable distance record rule to obtain a second judgment result; the stable distance record rule is a mathematical rule for limiting the record time of the plurality of difference distance records to form a stable maintenance time period;

[0183] If the second judgment result is yes, the distance type of the sensing collection information is determined as the device preset type;

[0184] If the second judgment result is no, the distance type of the sensing collection information is determined as a type different from the device preset type;

[0185] The sensing collection information belonging to the skin type in each sensing information set is divided into the skin-wearing sensing information set, and the sensing collection information belonging to the outer-wearing type is divided into the outer-wearing sensing information set, to obtain the skin-wearing sensing information set and the outer-wearing sensing information set corresponding to the sensing information set.

[0186] As an optional embodiment, the prediction module 202 determines the specific manner of the fabric feeling parameter corresponding to the fabric type corresponding to the sensing information set according to the skin feeling parameter and the outer wearing feeling parameter corresponding to the sensing information set, which includes:

[0187] Calculating the historical application record of the fabric type corresponding to the sensing information set; the historical application record includes the record of the fabric type corresponding to the fabric being applied in the skin type or the outer wearing type of the garment in the historical time period;

[0188] According to the historical application record, the skin weight and the outer wearing weight corresponding to the sensing information set are calculated; the size relationship between the skin weight and the outer wearing weight is consistent with the size relationship between the record quantity of the fabric type applied in the skin type and the outer wearing type in the historical application record; the skin weight is proportional to the record proportion of the fabric type applied in the skin type in the historical application record; the outer wearing weight is proportional to the record proportion of the fabric type applied in the outer wearing type in the historical application record;

[0189] The first product of the skin feeling parameter and the skin weight is calculated;

[0190] The second product of the outer wearing feeling parameter and the outer wearing weight is calculated;

[0191] The sum of the first product and the second product is calculated to obtain the fabric feeling parameter corresponding to the fabric type corresponding to the sensing information set.

[0192] As an optional embodiment, the modeling module 203 establishes the fabric-user-feeling prediction mathematical relationship model according to the fabric feeling parameter corresponding to each fabric type and the user parameter, and the specific manner includes:

[0193] Each fabric type and the corresponding fabric feeling parameter are taken as the training data set of the neural network model, and the fabric-feeling prediction mathematical relationship model is established, which is used to output the predicted fabric feeling prediction value according to the input fabric type;

[0194] According to the sensing collection information and the fabric feeling parameter corresponding to each user parameter, a user-fabric tendency prediction mathematical relationship model is established, which is used to output the predicted tendency prediction parameter corresponding to different fabric types according to the input user parameter;

[0195] The fabric-feeling prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model are determined as the fabric-user-feeling prediction mathematical relationship model.

[0196] As an optional embodiment, the modeling module 203 establishes the user-fabric tendency prediction mathematical relationship model according to the sensing collection information and the fabric feeling parameter corresponding to each user parameter, and the specific manner includes:

[0197] collecting information corresponding to all user parameters corresponding to each user parameter as a data set corresponding to each user parameter, screening a plurality of user classification indicators based on a principal component analysis algorithm; each user classification indicator includes at least one user parameter;

[0198] determining all fabric types corresponding to all sensor collection information corresponding to all user parameters in each user classification indicator, obtaining a plurality of fabric types corresponding to each user classification indicator;

[0199] calculating the average value of all fabric perception parameters corresponding to each fabric type corresponding to each user classification indicator, obtaining the inclination parameter corresponding to each fabric type corresponding to each user classification indicator;

[0200] all user parameters of all user classification indicators, and the inclination parameter corresponding to each fabric type corresponding to the user classification indicator as the training data set of the neural network model, and establishing a user-fabric inclination prediction mathematical relationship model.

[0201] As an optional embodiment, the determining module 204 determines the specific manner of the fabric type corresponding to the target user group according to the user parameters and sensor parameters of the target user group based on the fabric-user-perception prediction mathematical relationship model, which includes:

[0202] obtaining the user parameters of all users of the target user group to obtain a user parameter set;

[0203] calculating the parameter similarity between the user parameter set and each user classification indicator, and determining the user classification indicator with the highest parameter similarity as the target user classification indicator;

[0204] determining the intersection between the user parameter set and the target user classification indicator, inputting all user parameters in the intersection into the user-fabric inclination prediction mathematical relationship model to obtain a plurality of fabric types and corresponding inclination prediction parameters outputted;

[0205] determining the plurality of fabric types with inclination prediction parameters greater than a preset first parameter threshold as a plurality of candidate fabric types;

[0206] inputting each candidate fabric type into the fabric-perception prediction mathematical relationship model to obtain the fabric perception prediction value corresponding to each candidate fabric type outputted;

[0207] calculating the weighted sum average value of the inclination prediction parameter and the fabric perception prediction value corresponding to each candidate fabric type to obtain the selection parameter corresponding to each candidate fabric type;

[0208] determining the candidate fabric type with the selection parameter greater than a preset second parameter threshold as the fabric type corresponding to the target user group.

[0209] Specifically, the technical details or technical effects of the above embodiments or modules can be referred to the description in Embodiment One, which will not be repeated here.

[0210] Embodiment Three

[0211] Please refer to Figure 3 , Figure 3 is another structure diagram of the fabric texture intelligent analysis system based on children's clothing disclosed by the embodiments of the present application. As shown in Figure 3 , the system can include:

[0212] a memory 301 storing executable program codes;

[0213] a processor 302 coupled with the memory 301;

[0214] The processor 302 invokes the executable program codes stored in the memory 301 to execute part or all of the steps of the fabric texture intelligent analysis method based on children's clothing disclosed by Embodiment One of the present application.

[0215] Embodiment Four

[0216] The embodiments of the present application disclose a computer storage medium, which stores computer instructions, and when the computer instructions are invoked, part or all of the steps of the fabric texture intelligent analysis method based on children's clothing disclosed by Embodiment One of the present application are executed.

[0217] The system embodiments described above are only schematic, wherein the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, that is, they can be located in one place, or distributed on multiple network modules. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0218] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and the necessary general hardware platform through the above specific description of the embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in the sense of contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, which includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM), or other optical disk storage, a magnetic disk storage, a magnetic tape storage, or any other medium that can be used to carry or store data in a computer readable manner.

[0219] Finally, it should be noted that: the disclosed method and system for intelligent analysis of fabric texture based on children's clothing disclosed by the embodiments of the present application are only the preferred embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that; it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent analysis of fabric texture based on children's clothing, characterized in that, The method comprises: obtaining a plurality of sensor collection information of a plurality of users when wearing children's clothes, and user parameters and fabric types corresponding to each of the sensor collection information; According to the sensor collection information and the fabric type, based on a neural network algorithm, predicting the fabric feeling parameter corresponding to each of the fabric types, comprising: all the sensor collection information corresponding to the same fabric type is classified into the sensor information set corresponding to the fabric type; for each of the sensor information set, according to the skin distance of each of the sensor collection information in the sensor information set, the sensor information set is divided into skin sensor information set and outer sensor information set; input the skin sensor information set into the corresponding trained fabric skin feeling prediction model to obtain the skin feeling parameter corresponding to the sensor information set; the fabric skin feeling prediction model is trained by a plurality of corresponding fabric types, training skin sensor information and corresponding skin feeling good degree label training data set; input the outer sensor information set into the corresponding trained fabric outer feeling prediction model to obtain the outer feeling parameter corresponding to the sensor information set; the fabric outer feeling prediction model is trained by a plurality of corresponding fabric types, training outer sensor information and corresponding outer feeling good degree label training data set; determining the fabric feeling parameter corresponding to the fabric type corresponding to the sensor information set according to the skin feeling parameter and the outer feeling parameter corresponding to the sensor information set; according to the fabric feeling parameter corresponding to each of the fabric types, and the user parameters, a fabric-user-feeling prediction mathematical relationship model is established; in response to the clothing making request of the target user group, according to the user parameters and sensor parameters of the target user group, based on the fabric-user-feeling prediction mathematical relationship model, the fabric type corresponding to the target user group is determined.

2. The child garment based fabric feel intelligent analysis method according to claim 1, wherein, The sensor collection information and the sensor parameter include one or more of image sensor information, infrared ranging information, sound sensor information, positioning sensor information and temperature sensor information; the fabric type includes one or more of pure cotton type, cotton type chemical fiber fabric type, worsted wool fabric type, woolen fabric type, silk type, silk type, artificial silk type, hemp fabric type, elastic fabric type, sanding fabric type and environmental protection fabric type; the user parameters include at least one of user age, user body physical parameters and user physiological index parameters.

3. The child garment based fabric feel intelligent analysis method of claim 1, wherein, The sensor collection information and the sensor parameter include one or more of image sensor information, infrared ranging information, sound sensor information, positioning sensor information and temperature sensor information; the fabric type includes one or more of pure cotton type, cotton type chemical fiber fabric type, worsted wool fabric type, woolen fabric type, silk type, silk type, artificial silk type, hemp fabric type, elastic fabric type, sanding fabric type and environmental protection fabric type; the user parameters include at least one of user age, user body physical parameters and user physiological index parameters. The sensor collection information and the sensor parameter include one or more of image sensor information, infrared ranging information, sound sensor information, positioning sensor information and temperature sensor information; the fabric type includes one or more of pure cotton type, cotton type chemical fiber fabric type, worsted wool fabric type, woolen fabric type, silk type, silk type, artificial silk type, hemp fabric type, elastic fabric type, sanding fabric type and environmental protection fabric type; the user parameters include at least one of user age, user body physical parameters and user physiological index parameters. For each of the sensor collection information, it is judged whether the skin distance corresponding to the sensor collection information meets the distance mathematical rule corresponding to the preset type of the device, to obtain a first judgment result; If the first judgment result is yes, the distance type of the sensor collection information is determined as the preset type of the device; If the first judgment result is no, a plurality of difference distance records with a similarity less than a preset similarity threshold are screened out from the historical skin distance records of the sensor collection information; It is judged whether the plurality of difference distance records and the corresponding record time meet a preset stable distance record rule, to obtain a second judgment result; the stable distance record rule is used to limit the mathematical rule that the record time of the plurality of difference distance records forms a stable maintenance time period; If the second judgment result is yes, the distance type of the sensor collection information is determined as the preset type of the device; If the second judgment result is no, the distance type of the sensor collection information is determined as a type different from the preset type of the device; The sensor collection information belonging to the skin type in each of the sensor information sets is divided into a skin sensor information set, and the sensor collection information belonging to the outer type is divided into an outer sensor information set, to obtain the skin sensor information set and the outer sensor information set corresponding to the sensor information set.

4. The child garment based fabric feel intelligent analysis method of claim 3, wherein, The fabric feeling parameter corresponding to the fabric type corresponding to the sensor information set is determined according to the skin feeling parameter and the outer feeling parameter corresponding to the sensor information set, including: A historical application record of the fabric type corresponding to the sensor information set is calculated; the historical application record includes a record that the fabric corresponding to the fabric type is applied in a skin type or an outer type of clothing in a historical time period; According to the historical application record, a skin weight and an outer weight corresponding to the sensor information set are calculated; the size relationship between the skin weight and the outer weight is consistent with the size relationship between the record quantity of the fabric type applied in the skin type and the outer type in the historical application record; the skin weight is proportional to the record proportion of the fabric type applied in the skin type in the historical application record; the outer weight is proportional to the record proportion of the fabric type applied in the outer type in the historical application record; A first product of the skin feeling parameter and the skin weight is calculated; A second product of the outer feeling parameter and the outer weight is calculated; The sum of the first product and the second product is calculated, to obtain the fabric feeling parameter corresponding to the fabric type corresponding to the sensor information set.

5. The child garment based fabric feel intelligent analysis method of claim 1, wherein, The fabric-user-feeling prediction mathematical relationship model is established according to the fabric feeling parameter corresponding to each of the fabric types and the user parameter, including: Each of the fabric types and the corresponding fabric feeling parameter is taken as a training data set of a neural network model, to establish a fabric-feeling prediction mathematical relationship model, which is used to output a predicted fabric feeling prediction value according to an input fabric type; According to the sensing collection information corresponding to each of the user parameters and the fabric feeling parameters, a user-fabric tendency prediction mathematical relationship model is established, which is used to output a predicted tendency prediction parameter corresponding to a different fabric type according to an input user parameter; The fabric-feeling prediction mathematical relationship model and the user-fabric tendency prediction mathematical relationship model are determined as a fabric-user-feeling prediction mathematical relationship model.

6. The child garment based fabric feel intelligent analysis method of claim 5, wherein, The user-fabric tendency prediction mathematical relationship model is established according to the sensing collection information corresponding to each of the user parameters and the fabric feeling parameters, and includes: All the sensing collection information corresponding to each of the user parameters is taken as a data group corresponding to each of the user parameters, and a plurality of user classification indexes are screened out based on a principal component analysis algorithm; each user classification index includes at least one user parameter; All fabric types corresponding to all the sensing collection information corresponding to all the user parameters in each of the user classification indexes are determined to obtain a plurality of fabric types corresponding to each of the user classification indexes; An average value of all the fabric feeling parameters corresponding to each fabric type corresponding to each of the user classification indexes is calculated to obtain a tendency parameter corresponding to each fabric type corresponding to each of the user classification indexes; All the user parameters of all the user classification indexes and the tendency parameter corresponding to each fabric type corresponding to each of the user classification indexes are taken as a training data set of a neural network model to establish a user-fabric tendency prediction mathematical relationship model.

7. The child garment based fabric feel intelligent analysis method of claim 6, wherein, The fabric type corresponding to the target user group is determined based on the fabric-user-feeling prediction mathematical relationship model according to the user parameters and the sensing parameters of the target user group, and includes: User parameters of all users of the target user group are obtained to obtain a user parameter set; A parameter similarity between the user parameter set and each of the user classification indexes is calculated, and the user classification index with the highest parameter similarity is determined as a target user classification index; An intersection between the user parameter set and the target user classification index is determined, all the user parameters in the intersection are input into the user-fabric tendency prediction mathematical relationship model, and a plurality of fabric types and corresponding tendency prediction parameters output are obtained; The plurality of fabric types with a tendency prediction parameter greater than a preset first parameter threshold value are determined as a plurality of candidate fabric types; Each of the candidate fabric types is input into the fabric-feeling prediction mathematical relationship model to obtain a fabric feeling prediction value corresponding to each of the candidate fabric types output; A weighted sum average value of the tendency prediction parameter and the fabric feeling prediction value corresponding to each of the candidate fabric types is calculated to obtain a selection parameter corresponding to each of the candidate fabric types; The candidate fabric type with the selection parameter greater than a preset second parameter threshold value is determined as the fabric type corresponding to the target user group.

8. A fabric texture intelligent analysis system based on children's clothing, characterized in that, The system includes: An acquisition module is configured to acquire a plurality of sensing collection information of a plurality of users when wearing a child garment, and user parameters and fabric types corresponding to each of the sensing collection information. The prediction module is configured to predict, based on a neural network algorithm, a fabric feel parameter corresponding to each of the fabric types according to the sensor collection information and the fabric types, including: grouping all the sensor collection information corresponding to the same fabric type into a sensor information set corresponding to the fabric type; for each of the sensor information sets, grouping the sensor information set into a skin sensor information set and an outer sensor information set according to a skin distance of each of the sensor collection information in the sensor information set; inputting the skin sensor information set into a trained fabric skin feel prediction model corresponding to the skin sensor information set to obtain a skin feel parameter corresponding to the sensor information set; the fabric skin feel prediction model is trained by a plurality of training skin sensor information corresponding to the fabric types and a training data set corresponding to a skin feel goodness annotation; inputting the outer sensor information set into a trained fabric outer feel prediction model corresponding to the outer sensor information set to obtain an outer feel parameter corresponding to the sensor information set; the fabric outer feel prediction model is trained by a plurality of training outer sensor information corresponding to the fabric types and a training data set corresponding to an outer feel goodness annotation; determining the fabric feel parameter corresponding to the fabric type corresponding to the sensor information set according to the skin feel parameter and the outer feel parameter corresponding to the sensor information set; the modeling module is configured to establish a fabric-user-feel prediction mathematical relationship model according to the fabric feel parameter corresponding to each of the fabric types and the user parameter; the determining module is configured to determine a fabric type corresponding to a target user group based on the fabric-user-feel prediction mathematical relationship model according to a user parameter and a sensor parameter of the target user group in response to a clothing making request of the target user group.

9. A fabric texture intelligent analysis system based on children's clothing, characterized in that, The system includes: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the fabric texture intelligent analysis method based on children's clothing according to any one of claims 1-7.

Images