Construction method and system of design inspiration library

Abstract

The invention relates to a method and system for constructing a design inspiration library, and relates to the field of costume design. Determining a matching number according to the matching picture; determining a single item number according to the matching number; determining the sales volume of the single items according to the serial numbers of the single items, and determining the matching sales volume according to the matching serial numbers; generating a comparison report according to the single-item sales volume and the collocation sales volume; and controlling a preset display device to display the matched sales volume change according to the comparison report. The design inspiration library construction method has the advantages that convenience of design inspiration library construction is improved, and popular design works can be quickly found out.

Description

Technical Field

[0001] The present invention relates to the field of clothing design, and in particular to a method and system for constructing a design inspiration library. Background Art

[0002] A design inspiration library is a resource library that collects, organizes and stores design inspiration to help designers quickly find ideas and inspiration when designing.

[0003] In the existing technology, designers generally create their own inspiration library locally by collecting materials in the form of pictures, articles, audio and video, and classifying and organizing them to form their own design inspiration library. As design trends and technologies continue to change, designers need to regularly update their inspiration library, delete outdated materials, and add new high-quality resources.

[0004] When designers update their inspiration libraries, they need to manually search the Internet for the latest design works and classify the works they find, which is time-consuming and labor-intensive, and there is room for improvement. Summary of the invention

[0005] In order to improve the convenience of constructing a design inspiration library and to quickly find popular design works, the present invention provides a method and system for constructing a design inspiration library.

[0006] In a first aspect, the present invention provides a method for constructing a design inspiration library, which adopts the following technical solution: A method for constructing a design inspiration library, comprising: Get matching pictures; Determine the matching number according to the matching picture; Determine the item number based on the matching number; Determine the sales volume of a single product based on the single product number, and determine the sales volume of a combination based on the combination number; Generate a comparative report based on single product sales and matching sales; According to the comparison report, the preset display device is controlled to show the sales changes after matching.

[0007] By adopting the above technical solution, the sales volume of single items before matching and the sales volume of suits after matching can be compared to intuitively show the popularity of matching, thereby reflecting the fashion trend of clothing, thereby helping designers to quickly find popular design works and improve the convenience of building a design inspiration library.

[0008] Optionally, a collocation screening method is also included, and the collocation screening method includes: Determine average sales based on unit sales; Determine sales growth based on collocation sales and average sales; When the sales volume growth exceeds the preset rising threshold, the dressing style is determined based on the matching pictures; Determine design priorities based on style and sales growth; Generate a design inspiration library based on dressing style and design priorities.

[0009] By adopting the above technical solution, the sales ratio of single items and sets is calculated, and then the combinations are sorted according to the styles and ratios of the combinations, so that designers can quickly find the more successful clothing combinations in the corresponding styles, thereby improving the convenience of building a design inspiration library.

[0010] Optionally, the collocation screening method further comprises: Determine best-selling sales based on single product sales; Determine the best-selling increase based on best-selling sales and matching sales; Determine the correction factor based on the growth rate of best-selling products; Update the design priorities based on the correction factor and the design priorities.

[0011] By adopting the above technical solution, the highest sales volume among the individual items constituting the set is compared with the sales volume of the set, thereby reducing the priority of the set that relies on excellent individual items to increase sales volume, thereby improving the accuracy of the sorting of the design inspiration library.

[0012] Optionally, a collocation optimization method is also included, and the collocation optimization method includes: Get historical evaluation based on collocation number; Determine time segments based on historical evaluation; Determine negative evaluations based on time periods; Determine the negative quantity based on the negative evaluation; Determine the number of evaluations based on time periods; Determine the negative ratio based on the number of negatives and the number of reviews; Generate feedback reports based on time segment, negative quantity and negative proportion; According to the feedback report, a preset display device is controlled to display the user evaluation.

[0013] By adopting the above technical solution, the evaluations of users in the corresponding time period are counted to obtain the users' overall evaluation of the suits, thereby obtaining a more accurate evaluation of the clothing combination from the outside world, which makes it easier for designers to quickly find clothes that are well received by users and improves the convenience of building a design inspiration library.

[0014] Optionally, the collocation optimization method further includes: When the negative ratio is lower than the preset welcome threshold, the product image is retrieved according to the product number; Determine the product elements based on the product pictures; Determine similar factors based on single product factors; Determine the product type based on the product image; Determine similar items based on similar elements and item types; Retrieve similar pictures based on similar items; Determine the differences between individual products based on similar images and individual product images; Generate product optimization suggestions based on product differences; Control the preset display device to show the differences between similar items based on the item optimization suggestions.

[0015] By adopting the above technical solution, the items in the popular suit are analyzed one by one, and the items similar to the items in the suit are found, so that the items in the suit are compared with the similar items, and the differences between the items are quickly displayed, which makes it easier for designers to analyze the design of the items.

[0016] Optionally, the collocation optimization method further includes: Determine the difference quantity based on the difference of the single product; When the difference quantity is 1, the comparison items are determined based on the item differences; Determine comparative sales volume based on comparative items; Determine the coefficient of difference based on the sales volume of the single product and the comparative sales volume; Positive differences are determined based on the coefficient of difference; Generate single product optimization suggestions based on positive differences and difference coefficients.

[0017] By adopting the above technical solution, the sales of single items with different differences and single items in sets are compared to evaluate the impact of different differences on sales, so as to screen out differences that have a positive effect on the sales of single products and show them to designers, thereby providing inspiration for designers to optimize single products.

[0018] Optionally, the collocation optimization method further includes: When the number of differences is 1, the single product difference is defined as the example difference; Determine phase differences based on paradigm differences and unit differences; Determine the phase difference amount based on the phase difference difference; When the difference in quantity is 1, retrieve the difference in single products according to the difference in quantity; Determine overlap differences based on item differences and example differences; Determine the coincidence coefficient based on the coincidence difference; Determine the revised sales volume based on the comparative sales volume and the overlap coefficient; Determine the coefficient of variance based on the unit sales volume and the revised sales volume.

[0019] By adopting the above technical solution, when the number of differences is large, the sales volume of the single product is corrected according to the impact of the known differences on the sales volume, thereby ignoring the impact of the known differences on the sales volume of the single product, thereby further screening out the differences that have a positive effect on the sales volume of the single product and showing them to the designer.

[0020] Optionally, the collocation optimization method further includes: When the phase difference number is not 1, the repeat difference is determined according to the phase difference difference; According to the repeated differences, it is judged whether the phase differences are all repeated differences; When the phase differences are all repeated differences, the phase differences are defined as composite differences, and the phase differences are updated according to the composite differences; Determine the residual difference based on the phase difference and the composite difference; Determine the remaining quantity based on the remaining variance; When the remaining number is 1, the phase difference number is determined according to the phase difference difference.

[0021] By adopting the above technical solution, when there are multiple differences with unknown effects in a single product, multiple repeated differences with unknown effects are combined into a whole, thereby reducing the number of differences that need to be considered in the single product, and then further screening out differences that have a positive effect on the sales of the single product and showing them to the designer.

[0022] Optionally, a data selection method is also included, and the data selection method includes: Get the meteorological season; Determine the seasonal period according to the meteorological season; Determine whether there is corresponding data in the comparison report and feedback report based on the seasonal period; When there is no corresponding data in the comparison report or feedback report, determine whether there is a similar meteorological season; When similar meteorological seasons exist, missing data are determined based on seasonal periods, comparison reports, and feedback reports; Determine similar time periods based on similar seasons; Determine whether there is corresponding data in the missing data based on similar time periods; When there are corresponding data in the missing data, the report is updated based on similar time periods and missing data; When corresponding data exists in the comparison report and feedback report, the comparison report and feedback report are updated according to the seasonal period, the comparison report and feedback report.

[0023] By adopting the above technical solution, the data of the time period closest to the current weather conditions are selected from the sales data and evaluation data, so as to show the most popular clothing designs in the current season, thereby improving the accuracy of the design inspiration library screening.

[0024] In a second aspect, the present application provides a system for constructing a design inspiration library, which adopts the following technical solutions: A system for building a design inspiration library, comprising: The acquisition module is used to obtain matching pictures, historical evaluations and meteorological seasons; A memory, used to store any of the above-mentioned methods for constructing a design inspiration library; The program in the memory can be loaded and executed by the processor.

[0025] By adopting the above technical solution, the sales volume of single items before matching and the sales volume of suits after matching can be compared to intuitively show the popularity of matching, thereby reflecting the fashion trend of clothing, thereby helping designers to quickly find popular design works and improve the convenience of building a design inspiration library.

[0026] In summary, the present application includes at least one of the following beneficial technical effects: By comparing the sales of single items before matching and the sales of suits after matching, the popularity of matching can be intuitively displayed, thus reflecting the fashion trend of clothing, and then helping designers to quickly find popular design works and improve the convenience of building a design inspiration library; Calculate the sales ratio of single items and sets, and sort the combinations according to the styles and ratios, so that designers can quickly find the more successful clothing combinations in the corresponding styles, thereby improving the convenience of building a design inspiration library; Compare the highest sales volume of the items constituting the set with the sales volume of the set, thereby reducing the priority of the sets that rely on excellent items to increase sales, thereby improving the accuracy of the sorting of the design inspiration library. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flowchart of a method for constructing a design inspiration library; Figure 2 It is the process of matching screening method Figure 1 ; Figure 3 It is the process of matching screening method Figure 2 ; Figure 4 It is the process of matching optimization method Figure 1 ; Figure 5 It is the process of collocation optimization method Figure 2 ; Figure 6 It is the process of collocation optimization method Figure 3 ; Figure 7 It is the process of matching optimization method Figure 4 ; Figure 8 It is the process of matching optimization method Figure 5 ; Fig. 9 It is a flow chart of the data extraction method. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0029] The embodiment of the present application discloses a method for constructing a design inspiration library, which is used to evaluate the quality of clothing designs from two aspects: sales volume of clothing and user evaluation, so as to screen out clothing designs with relatively excellent designs and popular with consumers, thereby facilitating designers to build a design inspiration library.

[0030] Reference Figure 1 , a method for constructing a design inspiration library, comprising: Step 100: Obtain matching pictures.

[0031] Matching pictures refer to images of clothing matching. Matching pictures can be pre-input by staff and then obtained by manual selection by users. The method for obtaining matching pictures is selected by staff based on actual conditions and will not be elaborated here.

[0032] Step 101: Determine the matching number according to the matching picture.

[0033] The matching number refers to the number used to distinguish clothing combinations. The setting method of the matching number is chosen by the staff based on actual conditions and will not be elaborated here.

[0034] Step 102: Determine the item number according to the matching number.

[0035] The item number refers to the number used to distinguish items. Each clothing combination is composed of multiple different items. The item number can be obtained by querying in the combination data table. The combination data table refers to a data table that records different combination numbers and their corresponding combination numbers.

[0036] Step 103: Determine the sales volume of the single product according to the single product number, and determine the sales volume of the combination according to the combination number.

[0037] Single product sales refer to the sales data of single products in different time periods, and combination sales refer to the sales data of clothing combinations in different time periods. Both single product sales and combination sales can be obtained from the sales data table. The sales data table refers to a data table that records the numbers of different clothing and their corresponding sales.

[0038] Step 104: Generate a comparison report based on the sales volume of the single product and the sales volume of the matching product.

[0039] A comparison report refers to information used to compare clothing combinations and the sales of individual items that make up the clothing combinations and displayed to users. A comparison report generally uses a line graph of time and sales. The method for generating a comparison report is common knowledge among people in this field and will not be elaborated here.

[0040] Step 105: Control a preset display device to display sales changes after matching according to the comparison report.

[0041] The display device refers to a device used to display information to the user. The display device is selected by the staff according to the actual situation and will not be described in detail here. The comparison report is displayed through the display device to intuitively show the popularity of clothing combinations, thereby reflecting the fashion trend of clothing, and then helping designers to quickly find popular design works and improve the convenience of building a design inspiration library.

[0042] Reference Figure 2 , collocation screening methods include: Step 200: Determine the average sales volume based on the sales volume of each product.

[0043] Average sales volume refers to the average sales volume of all products. The calculation method of average sales volume is common knowledge to those skilled in the art and will not be elaborated here.

[0044] Step 201: Determine the sales volume increase according to the matching sales volume and the average sales volume.

[0045] Sales volume growth refers to the increase or decrease in sales volume of a clothing combination relative to the sales volume of a single item. The quality of a clothing combination is judged by the sales volume growth. The calculation method of the sales volume growth is common knowledge among people in this field and will not be elaborated here.

[0046] Step 202: When the sales volume increase exceeds a preset rising threshold, the dressing style is determined based on the matching pictures.

[0047] The rising threshold refers to the sales increase value of the clothing combination that is popular with consumers. The rising threshold is selected by the staff according to the actual situation and will not be elaborated here. The sales increase exceeding the rising threshold means that the clothing combination is more popular with consumers, that is, the clothing combination is a high-quality design inspiration library material. The dressing style refers to the style of clothing combination in the matching pictures such as casual, sports, formal wear, etc. The dressing style can be determined by image recognition technology. The method of determining the dressing style is common knowledge among people in this field and will not be elaborated here.

[0048] Step 203: Determine design priorities based on dressing styles and sales growth.

[0049] Design priority refers to a numerical value used to show the excellence of clothing combinations of different dressing styles. Clothing combinations are classified according to dressing styles, and then each type of clothing combination is assigned a design priority from large to small according to the sales growth rate from high to low. The method for determining the design priority is common knowledge among people in this field and will not be elaborated here.

[0050] Step 204: Generate a design inspiration library based on the dressing style and design priority.

[0051] Calculate the sales ratio of single items and sets, and sort the combinations according to the style and ratio, so that designers can quickly find the better clothing combinations in the corresponding style, thereby improving the convenience of building a design inspiration library.

[0052] Reference Figure 3 , the matching screening method also includes: Step 205: Determine the best-selling sales volume based on the sales volume of the single product.

[0053] The best-selling sales volume refers to the highest sales volume among the sales volumes of a single product. The method for determining the best-selling sales volume is common knowledge among those skilled in the art and will not be elaborated here.

[0054] Step 206: Determine the best-selling increase rate based on the best-selling sales volume and the matching sales volume.

[0055] The best-selling increase refers to the increase or decrease in the sales volume of a clothing combination relative to the best-selling sales volume. The calculation method of the best-selling increase is common knowledge among people in this field and will not be elaborated here.

[0056] Step 207: Determine a correction coefficient based on the sales growth rate.

[0057] The correction coefficient refers to the numerical value used to correct the design priority. The lower the best-selling increase, the larger the correction coefficient. The correction coefficient can be obtained from the correction data table. The correction data table refers to a data table that records different best-selling increases and their corresponding correction coefficients.

[0058] Step 208: Update the design priority according to the correction coefficient and the design priority.

[0059] Compare the highest sales volume of the items that constitute the combination with the sales volume of the clothing combination, so as to reduce the priority of the sets that have achieved a higher sales increase by combining excellent items with inferior items, thereby improving the accuracy of the sorting of the design inspiration library.

[0060] Reference Figure 4 , the collocation optimization methods include: Step 300: Obtain historical evaluations based on the matching number.

[0061] Historical evaluation refers to consumers' evaluation of clothing with matching numbers and the time of their evaluation. Historical evaluation can be manually imported by staff. The method for obtaining historical evaluation is selected by staff based on actual conditions and will not be elaborated here.

[0062] Step 301: Determine time segments based on historical evaluations.

[0063] Time segmentation refers to the time period obtained by evenly segmenting the time of historical evaluation. The method for determining time segmentation is selected by the staff based on actual conditions and will not be elaborated here.

[0064] Step 302: Determine negative evaluations based on time segments.

[0065] Negative evaluations refer to evaluations in which users express dissatisfaction with various aspects of clothing in historical evaluations within a time segment. The evaluations in the historical evaluations within the time segment can be screened out, and then the negative evaluations in the evaluations are determined through semantic recognition technology. The method for determining negative evaluations is common knowledge among people in this field and will not be elaborated here.

[0066] Step 303: Determine the negative quantity according to the negative evaluation.

[0067] The negative number refers to the number of negative evaluations. The method for determining the negative number is common knowledge to those skilled in the art and will not be elaborated here.

[0068] Step 304: Determine the number of evaluations based on the time segment.

[0069] The number of evaluations refers to the number of historical evaluations within a time segment. The method for determining the number of evaluations is common knowledge among those skilled in the art and will not be elaborated here.

[0070] Step 305: Determine the negative ratio according to the negative quantity and the evaluation quantity.

[0071] The negative proportion refers to the ratio of the negative number to the evaluation number in a time segment. The calculation method of the negative proportion is common knowledge among people in this field and will not be elaborated here.

[0072] Step 306: Generate a feedback report based on the time segment, negative quantity and negative proportion.

[0073] Feedback report refers to information used to display negative evaluations within a time segment to users. Feedback report generally uses a dual-axis line chart with time segment as the horizontal axis and negative quantity and negative proportion as the vertical axis. The method of generating feedback report is common knowledge among people in this field and will not be elaborated here.

[0074] Step 307: Control a preset display device to display the user evaluation according to the feedback report.

[0075] The evaluations of users in the corresponding time period are counted to obtain the overall evaluation of users on the suits at different times, so as to obtain a more accurate evaluation of the outside world on the clothing combination, which makes it easier for designers to quickly find the clothes that are well received by users and improves the convenience of building a design inspiration library.

[0076] Reference Figure 5 , the collocation optimization method also includes: Step 308: When the negative ratio is lower than the preset welcome threshold, retrieve the product image according to the product number.

[0077] The welcome threshold refers to the maximum negative percentage of clothing combinations that are well received by consumers. The welcome threshold is selected by the staff based on actual conditions and will not be elaborated here. A negative percentage lower than the welcome threshold means that the clothing combination is well received by consumers, that is, the clothing combination is a high-quality material for the design inspiration library. The single product picture refers to the image of the single product, which can be obtained from the single product data table. The single product data table refers to a data table that records different single product numbers and their corresponding single product pictures.

[0078] Step 309: Determine the single product elements according to the single product image.

[0079] Single product elements refer to patterns or designs on a single product identified from a single product picture. Single product elements can be determined using image recognition technology. The method for determining single product elements is common knowledge among people in this field and will not be elaborated here.

[0080] Step 310: Determine similar elements based on the single product elements.

[0081] Similar elements refer to patterns or designs that are similar to single product elements. Similar elements can be obtained by querying from a material database using image recognition technology. A material database refers to a database that records single product elements of different single products.

[0082] Step 311: Determine the product type based on the product image.

[0083] The item type refers to the type of clothing such as trousers, dresses, jeans, etc. The item type can be determined using image recognition technology. The method for determining the item type is common knowledge among people in this field and will not be elaborated here.

[0084] Step 312: Determine similar items based on similar elements and item types.

[0085] Similar items refer to the item numbers of items that are consistent with the item type and have similar elements. The numbers of the source clothing of the similar elements can be retrieved based on the similar elements, and then similar items of the same type can be screened out based on the item type. The method for determining similar items is common knowledge among people in this field and will not be elaborated here.

[0086] Step 313: Retrieve similar pictures based on similar items.

[0087] Similar pictures refer to images of items corresponding to similar items. Similar pictures can be obtained by searching in the item data table.

[0088] Step 314: Determine the difference between the individual products based on the similar images and the individual product images.

[0089] Single product differences refer to the differences in color, pattern, size, etc. between similar pictures and single product pictures. Single product differences can be determined using image recognition technology. The method for determining single product differences is common knowledge among people in this field and will not be elaborated here.

[0090] Among them, when the number of similar items is too large, items with a lower number of item differences are preferentially selected as similar items.

[0091] Step 315: Generate single product optimization suggestions based on single product differences.

[0092] Single product optimization suggestions refer to information used to show users the differences between single products to facilitate designers to optimize single products. Single product optimization suggestions are generally presented in the form of comparative pictures of similar pictures and differences between single product pictures and introductory text. The method for generating single product optimization suggestions is common knowledge among people in this field and will not be elaborated here.

[0093] Step 316: Control a preset display device to display the differences between similar items according to the item optimization suggestion.

[0094] Analyze the items in the popular sets one by one, find out the items similar to the items in the sets, and then compare the items in the sets with similar items, so as to quickly show the differences between the items, which makes it easier for designers to analyze the design of the items.

[0095] Reference Figure 6 , the collocation optimization method also includes: Step 317: Determine the difference quantity based on the single product difference.

[0096] The difference quantity refers to the difference quantity between different similar items and items in a set. The method for determining the difference quantity is common knowledge among those skilled in the art and will not be elaborated here.

[0097] Step 318: When the difference quantity is 1, determine the comparison item according to the item difference.

[0098] A difference number of 1 means that there is only one difference between the similar items and the items in the set. At this time, the impact of the difference on the items can be analyzed through the similar items. The comparison item is the item number of the item with a difference number of 1. The method for determining the comparison item is common knowledge among people in this field and will not be elaborated here.

[0099] Step 319: Determine the comparative sales volume based on the comparative items.

[0100] Comparative sales volume refers to the sales volume of compared products, which can be obtained from the sales data table.

[0101] Step 320: Determine the coefficient of difference based on the sales volume of the single product and the comparative sales volume.

[0102] The coefficient of variation refers to a numerical value used to show the degree of impact of the differences between similar items and items in a set on sales. The coefficient of variation corresponding to the difference can be obtained by calculating the sales difference between the comparison sales volume and the sales volume of the item, and querying the coefficient data table. The coefficient data table refers to a data table that records different sales volume differences and their corresponding coefficients of variation.

[0103] Step 321: Determine the positive difference according to the difference coefficient.

[0104] A positive difference refers to a difference that has a positive impact on the sales volume of a single product. The difference coefficient that is higher than the positive threshold can be found from all the difference coefficients, and the single product difference corresponding to the difference coefficient is defined as a positive difference.

[0105] Step 322: Generate single product optimization suggestions based on the positive difference and the difference coefficient.

[0106] By comparing the sales of single items with different differences and the single items in the set to evaluate the impact of different differences on sales, we can screen out the differences that have a positive effect on the sales of single products and show them to designers. We can also quantify the impact of the differences on sales into numerical values, and then show the differences in order of impact from high to low, thereby providing inspiration for designers to optimize single products.

[0107] Reference Figure 7 , the collocation optimization method also includes: Step 323: When the difference quantity is 1, define the single product difference as a sample difference.

[0108] The example difference is the single product difference whose difference coefficient has been determined according to the above method.

[0109] Step 324: Determine the phase difference based on the example difference and the single product difference.

[0110] The phase difference is the difference information of the unknown difference coefficient obtained after removing the difference consistent with the example difference in the single product difference. The method for determining the phase difference is common knowledge among those skilled in the art and will not be elaborated here.

[0111] Step 325: Determine the phase difference amount according to the phase difference difference.

[0112] The phase difference number refers to the number of phase difference differences. The method for determining the phase difference number is common knowledge to those skilled in the art and will not be elaborated here.

[0113] Step 326: When the difference quantity is 1, retrieve the single product difference according to the difference quantity.

[0114] A difference of 1 means that there is only one unknown difference coefficient in the single product difference. At this time, the difference coefficient of the phase difference can be analyzed by comparing the phase difference, single product difference and difference coefficient. The single product difference is the single product difference corresponding to the phase difference quantity. The method of retrieving the single product difference is selected by the staff according to the actual situation and will not be elaborated here.

[0115] Step 327: Determine the overlap difference based on the single product difference and the example difference.

[0116] Overlapping differences refer to the difference information in the single product difference that is consistent with the example difference. The method for determining overlapping differences is common knowledge among those skilled in the art and will not be elaborated here.

[0117] Step 328: Determine the overlap coefficient based on the overlap difference.

[0118] The overlap coefficient refers to the difference coefficient corresponding to the overlap difference. The overlap difference can be obtained from the above method, or it can be determined by querying a data table that records the difference coefficients corresponding to different differences in advance.

[0119] Step 329: Determine the revised sales volume based on the comparison sales volume and the overlap coefficient.

[0120] Corrected sales volume refers to the sales volume after the comparative sales volume is corrected according to the overlap coefficient. The sales volume difference corresponding to the overlap coefficient can be obtained from the coefficient data table, and the sum of the sales volume difference and the comparative sales volume is calculated as the corrected sales volume.

[0121] Step 330: Determine the coefficient of variation based on the sales volume of the single product and the revised sales volume.

[0122] When the number of differences is large, the sales volume of the single product is corrected according to the impact of the known differences on the sales volume, thereby ignoring the impact of the known differences on the sales volume of the single product, and then further deriving the impact of the unknown differences on the sales volume of the single product, so as to further screen out the differences that have a positive effect on the sales volume of the single product and show them to the designer.

[0123] The above method can be repeatedly applied until the difference in quantity is not 1. When the difference in quantity is not 1, it means that there are only multiple unknown differences in the single product differences. At this time, it is impossible to continue to analyze the impact of the differences on sales.

[0124] Reference Figure 8 , the collocation optimization method also includes: Step 331: when the phase difference quantity is not 1, determine the repetition difference according to the phase difference difference.

[0125] The difference in number is not 1, which means that there are only multiple unknown differences in the single product differences. Repeated differences refer to repeated differences in the phase differences. The method for determining repeated differences is common knowledge among those skilled in the art and will not be elaborated here.

[0126] Step 332: Determine whether all phase differences are repeated differences based on the repeated differences.

[0127] By comparing the differences within the repetition differences and the phase difference differences, it is determined whether the phase difference differences are all repetition differences. The method for comparing the phase difference differences and the repetition differences is common knowledge among those skilled in the art and will not be described in detail here.

[0128] Step 333: When the phase differences are all repeated differences, the phase differences are defined as compound differences, and the phase differences are updated according to the compound differences.

[0129] The phase difference differences are all repeated differences, which means that the differences within the phase difference differences exist in other phase difference differences. The compound difference refers to a difference formed by combining multiple differences in the phase difference differences that are all repeated differences. The combination method of the compound difference is selected by the staff according to the actual situation and will not be elaborated here.

[0130] It is queried in the phase difference whether there is a phase difference difference containing a compound difference, and multiple differences in the phase difference difference containing the compound difference are replaced with the compound difference. For example, when the compound difference is A and the compound difference A consists of a and b, the phase difference difference containing (a, b, c...) is updated to (A, c...).

[0131] Step 334: Determine the residual difference based on the phase difference and the composite difference.

[0132] The residual difference refers to the difference information obtained after removing the difference consistent with the composite difference in the phase difference. The method for determining the residual difference is common knowledge among those skilled in the art and will not be described in detail here.

[0133] Step 335: Determine the remaining quantity based on the remaining difference.

[0134] The remaining quantity refers to the quantity of the difference within the remaining difference. The method for determining the remaining quantity is common knowledge among those skilled in the art and will not be elaborated here.

[0135] Step 336: When the remaining number is 1, determine the phase difference number according to the phase difference difference.

[0136] The remaining quantity of 1 means that in addition to the compound difference, there is only one unknown difference coefficient in the single product difference. At this time, the difference coefficient of the compound difference is analyzed first, and then the difference coefficient of the unknown difference is analyzed through the difference coefficient of the compound difference. The analysis method for compound differences and unknown differences refers to the analysis method of phase difference mentioned above.

[0137] When there are multiple differences with unknown effects in a single product, multiple repeated differences with unknown effects are combined into a whole, thereby reducing the number of differences that need to be considered in the single product, and then further screening out the differences that have a positive effect on the sales of the single product and showing them to the designer.

[0138] Reference Fig. 9 , data extraction methods include: Step 400: Obtain the meteorological season.

[0139] The meteorological season refers to the season at the current time. The meteorological season can be obtained through advance input by the staff. The method for obtaining the meteorological season is selected by the staff according to the actual situation and will not be elaborated here.

[0140] Step 401: Determine the seasonal time period according to the meteorological season.

[0141] The seasonal time period refers to the time period corresponding to the meteorological season. The seasonal time period can be obtained by querying from the meteorological data table. The meteorological data table refers to a data table that records the seasonal time periods corresponding to different meteorological seasons.

[0142] Step 402: Determine whether there is corresponding data in the comparison report and the feedback report according to the seasonal period.

[0143] The comparison report and feedback report are checked according to the seasonal period to see whether there is data in the seasonal period. The method of judging whether there is data in the comparison report and feedback report is common knowledge among those skilled in the art and will not be elaborated here.

[0144] Step 403: When there is no corresponding data in the comparison report or the feedback report, it is determined whether there is a similar meteorological season.

[0145] The absence of corresponding data in the comparison report or feedback report means that the current corresponding season data cannot be queried from the comparison report or feedback report. Similar seasons refer to seasons with similar meteorological conditions to the meteorological season. The method for determining similar seasons is common knowledge among people in this field and will not be elaborated here.

[0146] Step 404: When similar meteorological seasons exist, the missing data is determined based on the seasonal period, the comparison report and the feedback report.

[0147] When weather conditions are similar, consumers' choices of clothing are also similar. Similar weather seasons mean that the data of the current season can be replaced by data from similar seasons. Missing data refers to comparison reports or feedback reports that do not have data in the seasonal period. The method for determining missing data is common knowledge among people in this field and will not be elaborated here.

[0148] Step 405: Determine similar time periods according to similar seasons.

[0149] Similar time periods refer to time periods corresponding to similar seasons, and similar time periods can be obtained from meteorological data tables.

[0150] Step 406: Determine whether there is corresponding data in the missing data according to the similar time period.

[0151] The method of checking whether there is data in the similar time period for the missing data and whether there is data in the missing data is common knowledge known to those skilled in the art and will not be elaborated here.

[0152] Step 407: When there is corresponding data in the missing data, update the report based on the similar time period and the missing data.

[0153] The existence of corresponding data in the missing data means that the consumer's preferences can be reflected through reports of similar time periods. At this time, the data of similar time periods in the missing data are intercepted and displayed through a display device, thereby improving the accuracy of the data and increasing the convenience for designers to build a design inspiration library.

[0154] Step 408: When corresponding data exists in the comparison report and the feedback report, the comparison report and the feedback report are updated according to the seasonal period, the comparison report and the feedback report.

[0155] The existence of corresponding data in the comparison report and feedback report can reflect consumers' preferences through the comparison report and feedback report of the seasonal period. At this time, the data of the seasonal period in the comparison report and feedback report are intercepted and displayed through the display device, thereby improving the accuracy of the data and improving the convenience of designers in building a design inspiration library.

[0156] Based on the same inventive concept, an embodiment of the present invention provides a system for constructing a design inspiration library, including: The acquisition module is used to obtain matching pictures and historical evaluations; A memory, used to store any of the above-mentioned methods for constructing a design inspiration library; The program in the memory can be loaded and executed by the processor.

[0157] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0158] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for constructing a design inspiration library, characterized in that: include: Get matching pictures; Determine the matching number according to the matching picture; Determine the item number based on the matching number; Determine the sales volume of a single product based on the single product number, and determine the sales volume of a combination based on the combination number; Generate a comparative report based on single product sales and matching sales; According to the comparison report, the preset display device is controlled to show the sales volume change after matching.

2. A method for constructing a design inspiration library according to claim 1, characterized in that: Also included is a collocation screening method, the collocation screening method comprising: Determine average sales based on unit sales; Determine sales growth based on collocation sales and average sales; When the sales volume increase exceeds the preset rising threshold, the dressing style is determined based on the matching pictures; Determine design priorities based on style and sales growth; Generate a design inspiration library based on dressing style and design priorities.

3. The method for constructing a design inspiration library according to claim 2, characterized in that: The collocation screening method further comprises: Determine best-selling sales based on single product sales; Determine the best-selling increase based on best-selling sales and matching sales; Determine the correction factor based on the growth rate of best-selling products; Update the design priorities based on the correction factor and the design priorities.

4. The method for constructing a design inspiration library according to claim 1, characterized in that: Also included is a collocation optimization method, the collocation optimization method comprising: Get historical evaluation based on collocation number; Determine time segments based on historical evaluation; Determine negative evaluations based on time periods; Determine the negative quantity based on the negative evaluation; Determine the number of evaluations based on time periods; Determine the negative ratio based on the number of negatives and the number of reviews; Generate feedback reports based on time segment, negative quantity and negative proportion; According to the feedback report, a preset display device is controlled to display the user evaluation.

5. The method for constructing a design inspiration library according to claim 4, characterized in that: The collocation optimization method further includes: When the negative ratio is lower than the preset welcome threshold, the product image is retrieved according to the product number; Determine the product elements based on the product pictures; Determine similar factors based on single product factors; Determine the product type based on the product image; Determine similar items based on similar elements and item types; Retrieve similar pictures based on similar items; Determine the differences between individual products based on similar images and individual product images; Generate product optimization suggestions based on product differences; Control the preset display device to show the differences between similar items based on the item optimization suggestions.

6. A method for constructing a design inspiration library according to claim 5, characterized in that: The collocation optimization method further comprises: Determine the difference quantity based on the difference of the single product; When the difference quantity is 1, the comparison items are determined based on the item differences; Determine comparative sales volume based on comparative items; Determine the coefficient of difference based on the sales volume of the single product and the comparative sales volume; Positive differences are determined based on the coefficient of difference; Generate single product optimization suggestions based on positive differences and difference coefficients.

7. The method for constructing a design inspiration library according to claim 6, characterized in that: The collocation optimization method further comprises: When the number of differences is 1, the single product difference is defined as the example difference; Determine phase differences based on paradigm differences and unit differences; Determine the phase difference amount based on the phase difference difference; When the difference in quantity is 1, retrieve the difference in single products according to the difference in quantity; Determine overlap differences based on item differences and example differences; Determine the coincidence coefficient based on the coincidence difference; Determine the revised sales volume based on the comparative sales volume and the overlap coefficient; Determine the coefficient of variance based on the unit sales volume and the revised sales volume.

8. The method for constructing a design inspiration library according to claim 7, characterized in that: The collocation optimization method further comprises: When the phase difference number is not 1, the repeat difference is determined according to the phase difference difference; According to the repeated differences, it is judged whether the phase differences are all repeated differences; When the phase differences are all repeated differences, the phase differences are defined as composite differences, and the phase differences are updated according to the composite differences; Determine the residual difference based on the phase difference and the composite difference; Determine the remaining quantity based on the remaining variance; When the remaining number is 1, the phase difference number is determined according to the phase difference difference.

9. The method for constructing a design inspiration library according to claim 4, characterized in that: Also included is a data extraction method, the data extraction method comprising: Get the meteorological season; Determine the seasonal period according to the meteorological season; Determine whether there is corresponding data in the comparison report and feedback report based on the seasonal period; When there is no corresponding data in the comparison report or feedback report, determine whether there is a similar meteorological season; When similar meteorological seasons exist, missing data are determined based on seasonal periods, comparison reports, and feedback reports; Determine similar time periods based on similar seasons; Determine whether there is corresponding data in the missing data based on similar time periods; When there are corresponding data in the missing data, the report is updated based on similar time periods and missing data; When corresponding data exists in the comparison report and feedback report, the comparison report and feedback report are updated according to the seasonal period, the comparison report and feedback report.

10. A system for constructing a design inspiration library, characterized in that: include: The acquisition module is used to obtain matching pictures, historical evaluations and meteorological seasons; A memory, used to store a method for constructing a design inspiration library according to any one of claims 1 to 9; The program in the memory can be loaded and executed by the processor.

Images