Method, device, apparatus and readable storage medium for determining product target attributes

Abstract

The present disclosure provides a method, device, equipment and readable storage medium for determining the target attributes of a product, including: obtaining at least two product attributes corresponding to a product category; determining a combination of product attributes based on the product attributes, and determining a product group based on the combination of product attributes; grouping the commodities of the category according to the product group, and determining the target attributes in the product attributes according to the information of the commodities included in the product group. The method, device, equipment and readable storage medium provided by the present disclosure can classify commodities according to product attributes, and analyze the information of the commodities included in each group to determine the target attributes. The method, device, equipment and readable storage medium provided by the present disclosure do not rely on human factors, but analyze based on the information of the commodity itself, and the obtained results are more accurate, so as to guide the product manufacturer to carry out product research and development.

Description

Technical Field

[0001] The present disclosure relates to data processing technology, and in particular to a method, device, equipment and readable storage medium for determining a target attribute of a product. Background Art

[0002] At present, there are many categories of products on the market, and similar products are also abundant. When it is necessary to develop new products, it is necessary to determine the development direction so as to develop competitive products.

[0003] In the prior art, product manufacturers determine the development direction based on the sales of their own brands, personal experience, etc., and then develop related products.

[0004] However, this method is greatly affected by human factors and cannot accurately predict product trends, causing the developed products to be uncompetitive in the market, which in turn leads to the problem of low product survival rate. Summary of the invention

[0005] The present disclosure provides a method, device, equipment and readable storage medium for determining product target attributes, so as to solve the problem in the prior art that the determination of the development direction of new products is greatly affected by human factors.

[0006] A first aspect of the present disclosure is to provide a method for determining a target attribute of a product, comprising:

[0007] Obtain at least two product attributes corresponding to a product category;

[0008] Determining a product attribute combination according to the product attributes, and determining a product group according to the product attribute combination;

[0009] The commodities of the category are grouped according to the product group, and a target attribute is determined from the product attributes according to information of the commodities included in the product group. Another aspect of the present disclosure is to provide an apparatus for determining a target attribute of a product, comprising:

[0010] An acquisition module, used to acquire at least two product attributes corresponding to a product category;

[0011] A group determination module, used to determine a product attribute combination according to the product attributes, and determine a product group according to the product attribute combination;

[0012] a grouping module for grouping the commodities of the category according to the product group;

[0013] An analysis module is used to determine a target attribute from the product attributes according to information of the commodities included in the product group. Another aspect of the present disclosure is to provide a device for determining a target attribute of a product, comprising:

[0014] Memory;

[0015] Processor; and

[0016] Computer programs;

[0017] Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the method for determining the target attributes of a product as described in the first aspect above.

[0018] Yet another aspect of the present disclosure is to provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for determining target attributes of a product as described in the first aspect above.

[0019] The technical effects of the method, device, equipment and readable storage medium for determining product target attributes provided by the present disclosure are:

[0020] The method, device, equipment and readable storage medium for determining the target attributes of a product provided by the present disclosure include: obtaining at least two product attributes corresponding to a product category; determining a combination of product attributes based on the product attributes, and determining a product group based on the combination of product attributes; grouping the commodities of the category according to the product group, and determining the target attributes in the product attributes according to the information of the commodities included in the product group. The method, device, equipment and readable storage medium provided by the present disclosure can classify commodities according to product attributes, and analyze the information of the commodities included in each group to determine the target attributes. The method, device, equipment and readable storage medium provided by the present disclosure do not rely on human factors, but analyze based on the information of the commodity itself, and the results obtained are more accurate, so as to guide product manufacturers to carry out product research and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of a method for determining a target attribute of a product is shown as an exemplary embodiment of the present invention;

[0022] Figure 2 A flowchart of a method for determining a target attribute of a product is shown as another exemplary embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a user interface shown as an exemplary embodiment of the present invention;

[0024] Figure 4 A flowchart of a method for determining a target attribute of a product is shown as another exemplary embodiment of the present invention;

[0025] Figure 5 A schematic diagram of a user interface shown as another exemplary embodiment of the present invention;

[0026] Figure 6 A structural diagram of an apparatus for determining a target attribute of a product according to an exemplary embodiment of the present invention;

[0027] Figure 7 A structural diagram of an apparatus for determining a target attribute of a product according to another exemplary embodiment of the present invention;

[0028] Figure 8 A structural diagram of a device for determining target attributes of a product according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0029] At present, before developing new products, the new product manufacturer needs to determine the product development direction. In the existing technology, the product development direction is usually determined based on manual experience and historical sales information. The product development direction determined in this way relies on manual experience, resulting in inaccurate results.

[0030] The solution provided by the embodiment of the present invention groups various commodities according to product attributes, and determines target attributes according to the information of the commodities included in each group, so that product manufacturers can develop products according to the target attributes, thereby producing competitive products.

[0031] Figure 1 The flowchart of the method for determining the target attributes of a product is shown as an exemplary embodiment of the present invention.

[0032] like Figure 1 As shown, the method for determining the target attribute of a product provided in this embodiment includes:

[0033] Step 101: Obtain at least two product attributes corresponding to a product category.

[0034] The method provided in this embodiment may be executed by an electronic device with computing capabilities, for example, a computer.

[0035] Specifically, the product-related data to be analyzed can be stored in the electronic device so that the electronic device can directly read the data. A front end for interacting with the user can also be provided, and the user can upload the product-related data to be analyzed through the front end, and the electronic device executing the method provided in this embodiment receives the data and processes it.

[0036] Furthermore, the product-related data to be analyzed may include attribute information, sales information, etc.

[0037] In actual application, product attributes can be preset. For example, the attributes of shampoo can include gender attributes, such as male and female, and functional attributes, such as anti-dandruff, smoothness, and maintenance. When analyzing a product, its included product attributes can be obtained.

[0038] Among them, the solution provided in this embodiment mines the product attributes and determines the potential attributes therein, thereby guiding the product manufacturer to develop new products.

[0039] Specifically, the product attributes corresponding to a product category may be some pre-set important attributes. These attributes are the attributes corresponding to a product category, such as the attributes of a mobile phone, the attributes of shampoo, the attributes of facial cleanser, etc.

[0040] Furthermore, a product that belongs to the product category may have some of the attributes of the product. For example, the attributes of shampoo may include smoothness, anti-dandruff, freshness, and conditioning, and the attributes of a shampoo may include anti-dandruff, that is, it includes some of the product attributes of the products in the category to which it belongs.

[0041] Step 102, determining a product attribute combination according to the product attributes, and determining a product group according to the product attribute combination.

[0042] In practical applications, in one case, product attributes can be directly grouped to obtain product groups corresponding to various combinations of product attributes. For example, there are 10 product attributes in total, and 3 attributes can be randomly selected for combination to obtain multiple attribute combinations. When determining product attribute combinations, all possible combinations can be exhausted, for example, all possible combinations of three attributes can be determined.

[0043] For example, a product manufacturer wishes to develop a new product but has no development direction. In this case, the development direction can be determined based on the product attributes of the category to which the new product belongs.

[0044] Specifically, each product attribute combination can be regarded as a product group. For example, if the product attribute combination includes A, B, and C, it can correspond to a product group, and the products in the group have the three attributes of A, B, and C.

[0045] Furthermore, in another case, the product manufacturer wants to develop a new product and has determined the product attributes corresponding to the development direction, but also wants to further understand the important attributes of each attribute. In this case, the product attributes and demand attributes can be combined to determine the product category. For example, the product attributes can be grouped according to the demand attributes, and then the product group can be determined according to the combination of product attributes.

[0046] Step 103: Group the commodities of the category according to the product group, and determine the target attribute in the product attributes according to the information of the commodities included in the product group.

[0047] In actual application, one product category may include multiple types of goods, and the goods may be grouped according to the determined product category.

[0048] Each product group has corresponding product attributes, which may specifically refer to a corresponding combination of product attributes. Therefore, the commodities under the product category may be classified according to the product attribute information corresponding to the product group.

[0049] Specifically, each product has its own attributes, and the products can be grouped according to the attributes of each product and the product attribute information corresponding to the product group. For example, if a product includes three product attributes A, B, and C, the product can be divided into a product group corresponding to the product attribute combination A+B+C.

[0050] Furthermore, after grouping the products, they can be clustered, so that the characteristics of the products in each group can be analyzed and potential product attributes can be determined.

[0051] In actual application, analysis can be performed based on the product information included in each product group. For a product group, it may include multiple commodities, such as M commodities, each of which has its own commodity information, such as sales information. Based on the information of each commodity, it can be determined whether a product attribute can be used as a development direction for a new product. For example, if a product group includes a small number of commodities, a new product belonging to the product group can be developed.

[0052] Among them, multiple product groups with a small number of goods can be determined, and the target attribute can be determined based on the product attributes corresponding to these product groups. For example, if multiple product groups with a small number of goods all correspond to the same product attribute, the product attribute can be determined as the target attribute.

[0053] Specifically, the product groups can be further grouped to determine potential groups and other groups. For example, the average output capacity of each commodity in a product group can be determined based on the information of each commodity included in the product group. If the average output capacity is high, the product group can be considered to be a potential group.

[0054] Furthermore, the target attribute can be determined based on the product attributes corresponding to the potential groups and the product attributes corresponding to the other groups. For example, if a product attribute corresponds to a plurality of potential groups and corresponds to a few other groups, the product attribute can be considered as the target attribute.

[0055] In actual application, the product development direction can be determined according to the determined target attributes. For example, if the product category to be analyzed is shampoo, and if the determined target attribute is anti-hair loss, then anti-hair loss can be used as the research and development direction of the new product.

[0056] The method provided in this embodiment is used to mine target attributes of products. The method is executed by a device equipped with the method provided in this embodiment, and the device is usually implemented in hardware and / or software.

[0057] The method for determining the target attributes of a product provided in this embodiment includes: obtaining at least two product attributes corresponding to a product category; determining a product attribute combination based on the product attributes, and determining a product group based on the product attribute combination; grouping the commodities of the category according to the product group, and determining the target attributes in the product attributes based on the information of the commodities included in the product group. The method provided in this embodiment can group the commodities according to the product attributes, and analyze the information of the commodities included in each group to determine the target attributes. The method provided in this embodiment does not rely on human factors, but analyzes the information of the commodities themselves, and the obtained results are more accurate, so as to guide the product manufacturer to carry out product research and development.

[0058] Figure 2 The present invention is a flowchart of a method for determining target attributes of a product according to another exemplary embodiment of the present invention.

[0059] Figure 2 The illustrated embodiment is applicable to an uncertain product development direction. The product data can be processed by the method provided in this embodiment to determine the product development direction.

[0060] Figure 3 A schematic diagram of a user interface is shown as an exemplary embodiment of the present invention.

[0061] like Figure 3 As shown, the user can select no product requirement in the user interface, and can also select a product category, such as toothbrush, shampoo, etc. Thus, the electronic device executes the method provided in this embodiment and processes data corresponding to the product category.

[0062] like Figure 2 As shown, the method for determining the target attribute of a product provided in this embodiment includes:

[0063] Step 201: Obtain at least two product attributes corresponding to a product category.

[0064] The specific principle and implementation method of step 201 are similar to those of step 101 and will not be repeated here.

[0065] Step 202: Select a preset number of attributes from the product attributes as a product attribute combination.

[0066] Among them, product attribute combinations include all possible combinations.

[0067] Specifically, if the number of product attributes is an even number, the preset number may be half of the number of product attributes; if the number of product attributes is an odd number, the preset number may be obtained by adding 1 to the number of product attributes and then dividing by 2. For example, if a product includes 20 attributes in total, the preset number corresponding to the product may be 10.

[0068] Furthermore, a preset number of attributes may be arbitrarily selected from the product attributes for combination to obtain a product attribute combination.

[0069] In practical applications, all possible combinations can be exhausted. For example, if the product attributes include 20 in total and the preset number is 10, then By setting all possible combinations of product attributes, you can get a more comprehensive product classification.

[0070] Step 203, determining a product group according to the product attribute combination.

[0071] Among them, the product attribute combination can be used as a feature of a type of product, so as to determine the product group according to the product attribute combination. For example, a product attribute combination consists of attribute A, attribute B, and attribute C. Then the product attribute combination can correspond to a product group. The goods included in this product group have the corresponding product attributes, that is, attribute A, attribute B, and attribute C.

[0072] Step 204, grouping the commodities of the category according to the product groups.

[0073] Specifically, after the product group is determined, the corresponding commodities of this category may be grouped according to the product group.

[0074] Furthermore, the attribute information of each product can be obtained, and the attribute information can be matched with the product attribute combination corresponding to the product group. The matched product group is used as the group to which the product belongs. For example, if the attribute of a product matches the attribute combination of product group 1, the product can be classified into product group 1.

[0075] In actual application, if the attribute information of a product includes the attributes in the product attribute combination corresponding to the product group, then the product can be considered to match the product group. For example, if the attribute information of a product includes "anti-dandruff, men, 70-80 yuan, post-perm repair", and the product attribute combination corresponding to a product group is "anti-dandruff, men, 70-80 yuan", then the product can be considered to belong to this product group.

[0076] If a product matches more than one product group, the product can be divided into multiple product groups.

[0077] Optionally, after the products are grouped, the product groups can be processed according to the products included in the product groups, such as screening some product groups and excluding some product groups.

[0078] Step 205, determining a small-volume product group according to the quantity of commodities included in the product group.

[0079] Specifically, if the number of commodities included in a product group is small, it can be considered that there are few similar commodities in the market, which is an unsaturated situation. Therefore, a small product group with a small number of commodities can be screened out.

[0080] Furthermore, a quantity threshold may be preset, for example, a quantity threshold corresponding to a product category, such as a threshold corresponding to toothbrushes or a threshold corresponding to shampoo. If the quantity of goods included in a product group is less than or equal to the corresponding threshold, the product group may be considered to be a small quantity product group.

[0081] Step 206, obtaining first commodity information corresponding to commodities included in the small-volume product group, and determining a brand-concentrated product group in the small-volume product group according to the first commodity information.

[0082] In actual application, the first commodity information corresponding to the commodities included in the small-volume product group may be obtained, for example, the sales information corresponding to each commodity, the brand information corresponding to each commodity, and the like.

[0083] Among them, it can be determined whether the product brands in the small-volume product group are highly concentrated based on the first product information. For example, if most of the products in a small-volume product group belong to the same brand, it can be considered that a brand has occupied most of the market for this type of product. In this case, new products belonging to this group are unlikely to survive.

[0084] Specifically, the brand information corresponding to each product can be determined based on the first product information corresponding to the small-volume product group. For example, in the small-volume product group, the brand information of the 1st to 10th products is brand A, the brand information of the 11th to 16th products is brand B, and the brand information of the 17th to 20th products is brand C.

[0085] Furthermore, the sales information corresponding to each product can be determined based on the first product information corresponding to the small-volume product group. For example, the sales of the 1st to 10th products are GMV1, the sales of the 11th to 16th products are GMV2, and the sales of the 17th to 20th products are GMV3.

[0086] In actual application, the target brand with the largest sales share can also be determined in each small-volume product group based on brand information and sales information.

[0087] Among them, the total transaction amount corresponding to a brand in each small-volume product group can be determined based on brand information and sales information; the ratio of the total transaction amount corresponding to the brand to the total transaction amount of the small-volume product group is determined as the sales share corresponding to the brand; based on the sales share corresponding to each brand in the small-volume product group, the target brand with the largest sales share is determined.

[0088] For example, in the above-mentioned small-volume product group, the sales share of Brand A is GMV1 / (GMV1+GMV2+GMV3), the sales share of Brand B is GMV2 / (GMV1+GMV2+GMV3), and the sales share of Brand C is GMV2 / (GMV1+GMV2+GMV3).

[0089] Specifically, the target brand with the largest sales share can be determined based on the sales share of each brand in a small-volume product group. The sales share of each brand in a small-volume product group can be compared to determine the target brand with the largest sales share.

[0090] Furthermore, a corresponding target brand can be determined for each small-volume product group. For example, if there are 50 small-volume product groups, 50 target brands can be determined.

[0091] In actual application, the average sales share can be determined based on the sales share of each target brand. For example, the sales share of 50 target brands can be averaged to obtain the average sales share.

[0092] Among them, the brand-concentrated small-volume product group can also be determined based on the sales share of each target brand and the average sales share. If the sales share of the target brand is greater than the average sales share, it can be considered that the brand concentration in the small-volume product group corresponding to the target brand is high, that is, the products in this group have been occupied by the target brand and it is not easy to enter such a market.

[0093] Meanwhile, the method provided in this embodiment determines a product group with concentrated brands in a small-volume product group, that is, a product group with a small number of products and a relatively concentrated brand, and new products belonging to such a product category are not easily accepted by consumers. Therefore, the method provided in this embodiment may also include step 207.

[0094] Step 207, eliminating the product groups with concentrated brands from the product groups with small volumes.

[0095] Specifically, brand-concentrated product categories can be eliminated from small-volume product groups, that is, product groups with poor future sales trends can be eliminated.

[0096] Optionally, the method provided in this embodiment may further include the following steps for determining a group in the style set in the product group.

[0097] If the following steps are arranged after step 207, the following steps may be performed according to the remaining product groups after removing the product groups in the brand concentration.

[0098] The following steps may also be set before step 205. In this case, steps 205-207 may be performed in the remaining product groups after removing the groups in the style set.

[0099] The specific execution timing can be set according to requirements.

[0100] Step 208, determining the style concentration corresponding to the product group according to the sales information and quantity of each product in the product group.

[0101] Among them, all existing product groups can be analyzed to determine the categories with higher style concentration.

[0102] Specifically, the style concentration corresponding to the product group can be determined according to the following formula:

[0103]

[0104] in, It refers to the sales of product i in product group j. The average GMV of all categories is the average sales of products in all product groups. For example, the sales of each product can be added up and then the sum can be divided by the number of products included in all product groups.

[0105] Specifically, the concentration of product group j can be determined according to the above formula, where j is used to represent the product group. For example, if there are 100 groups in total, the value range of j is 1-100.

[0106] Step 209, based on the style concentration and the concentration threshold, remove the high concentration groups in the product groups.

[0107] Furthermore, the product groups may be sorted according to style concentration, and a concentration threshold may be set to determine high concentration groups.

[0108] In practical applications, the concentration threshold may include various forms, for example, it may be a value used to measure the concentration. It can be considered that when the concentration is greater than the concentration threshold, the product group is a high concentration group.

[0109] The concentration threshold may be a percentage, such as 20%, and the product groups may be sorted according to their concentration, and 20% of the product groups with higher concentration may be determined as high-concentration groups.

[0110] Specifically, after determining the product groups with high concentration, these product groups can also be eliminated.

[0111] Step 210, determining potential groups and other groups in the product groups according to the commodity information corresponding to the remaining product groups.

[0112] After eliminating product groups with a high brand concentration and / or eliminating product groups with a high style concentration, the method provided in this embodiment can perform attribute mining based on the remaining product groups to determine the target attributes of the products.

[0113] Furthermore, in the method provided in this embodiment, the remaining product groups can be classified into potential groups and other groups. The potential group refers to the group to which products with sales prospects belong, and the other group refers to the group to which products without sales prospects belong.

[0114] In actual application, the remaining product groups can be divided according to the commodities included in the remaining product groups. For example, the analysis can be conducted according to the remaining small-volume product groups, or the remaining small-volume product groups can be analyzed after removing the products with high brand concentration and high style concentration.

[0115] Among them, the output capacity corresponding to the product category can be determined according to the commodity sales information and quantity corresponding to each remaining product group. The output capacity can be used to measure the value brought by the commodity.

[0116] Specifically, the average sales amount of a product can be determined based on the sales information of each product in a product group and the number of products included in the product group, and used as the output capacity of the product group.

[0117] Furthermore, the average output capacity of the product can be determined, and the average output capacity can be determined specifically based on the sales information and total quantity of all commodities corresponding to all remaining product categories. For example, the sales of all commodities in the remaining product groups can be added together to obtain the total commodity sales. The number of commodities included in each remaining product group can also be added together to obtain the total number of styles, and the ratio of the total product sales to the total number of styles can be calculated to obtain the average output capacity.

[0118] In actual application, potential groups and other groups can be determined from the remaining product groups according to the output capacity and average output capacity corresponding to each product group. The product group with an output capacity greater than the average output capacity can be determined as a potential category, and the product group with an output capacity less than or equal to the average output capacity in the remaining product groups can be determined as the other groups. If the output capacity is greater than the average output capacity, it can be considered that the goods in the product group can bring higher profits, so it can be determined as a potential group.

[0119] Step 211, determine the target attributes according to the product attributes corresponding to the potential group and other groups.

[0120] Among them, the product group is determined based on the product attributes, so each potential group and other groups have corresponding product attributes. For example, a potential group may correspond to a combination of product attributes A, B, and C.

[0121] Specifically, the first proportion of the number of words that appear in the potential group and the second proportion of the product attribute in the potential group and other groups can be determined; the potential value of the product attribute is determined based on the first proportion and the second proportion, and the target attribute is determined among the product attributes based on the potential value.

[0122] Furthermore, the first proportion may be the proportion of the number of times the product attribute appears in the potential groups, and the ratio of the number of times the product attribute appears in the potential groups to the number of potential groups may be used as the first proportion.

[0123] In actual application, the second proportion can be the proportion of the number of times the product attribute appears in the potential group and other groups. The ratio of the number of times the product attribute appears in the potential group and other groups to the sum of the number of potential groups and other groups can be used as the second proportion.

[0124] If a product attribute appears more often in the potential group, it can be considered to be a potential attribute. If a product attribute appears more often in all product groups, it can be considered to be a common attribute, not a potential attribute.

[0125] Therefore, in the method provided in this embodiment, mining can be performed based on the first proportion and the second proportion of the product attribute to determine the potential attribute. For example, the difference between the first proportion and the second proportion can be determined as the potential value of the product attribute. If the potential value is greater than 0, the product attribute can be considered to be a potential attribute, that is, a target attribute.

[0126] For example, there are 50 "potential groups" and 50 "other groups" marked in total, of which attribute A appears in 10 "potential groups" and in 30 "other groups", and attribute B appears in 40 "potential groups" and in 10 "other groups", then:

[0127] The "potential value" of attribute A = 10 / 50-30 / 100 = -0.1333 < 0, so A is not the target attribute;

[0128] The "potential value" of attribute B = 40 / 50-10 / 100 = 0.7>0, then B is the target attribute.

[0129] Figure 4 The flowchart of the method for determining the target attribute of a product is shown as another exemplary embodiment of the present invention.

[0130] Figure 4 The illustrated embodiment is suitable for determining the direction of product development. However, if one wishes to determine the potential of the general direction of the product development, the product data may be processed by the method provided in this embodiment.

[0131] Figure 5 A schematic diagram of a user interface is shown according to another exemplary embodiment of the present invention.

[0132] like Figure 5 As shown, the user can select a product requirement in the user interface, input the corresponding requirement, and select a product category, such as toothbrush, shampoo, etc. Thus, the electronic device executes the method provided in this embodiment and processes the data corresponding to the product category and the product requirement.

[0133] like Figure 4 As shown, the method for determining the target attribute of a product provided in this embodiment includes:

[0134] Step 401, obtaining at least two product attributes corresponding to a product category.

[0135] The specific principle and implementation method of step 401 are similar to those of step 101 and will not be repeated here.

[0136] Step 402, determining a product attribute combination according to product requirements and product attributes, and determining a product group according to the product attribute combination.

[0137] In the method provided in this embodiment, a rough product demand may also be set, and the product demand may be, for example, a product characteristic that the user wishes to analyze, such as the applicable population of the product, the product price range, etc. The product group may be determined in combination with the product demand and the product attribute.

[0138] For example, the product demand is suitable for middle-aged people, the price is 50-100, and the product effect is to prevent hair loss. The attribute values ​​of the applicable population in the product attributes can include male, female, age range, etc. Therefore, matching product attributes can be determined according to the product demand, such as male, female, 30-50 years old, 50-100 yuan, and anti-hair loss.

[0139] Specifically, a product attribute combination may be determined based on matching product requirements, and then a product group may be determined based on the product attribute combination. Specifically, product attributes matching the product requirements may be combined to obtain a product attribute combination, and a product group corresponding to the combination may be determined.

[0140] Step 403, grouping the commodities of the category according to the product group.

[0141] The specific principle and implementation method of classifying product styles in step 403 are similar to those in step 103 .

[0142] In the method provided in this embodiment, product styles can be divided to determine commodities that meet the product attributes corresponding to the product categories. For example, commodities that meet the attributes of male, female, 30-50 years old, 50-100 yuan, and anti-hair loss can be divided into the determined product categories.

[0143] Step 404, determining sales information based on the commodity information corresponding to the product group.

[0144] After the products are grouped, the product group may include multiple products, and analysis can be performed based on the information of the products included in the product group.

[0145] Among them, the corresponding sales information can be determined based on the product information of each commodity. Specifically, the average sales value, average sales volume, average traffic flow, and average traffic conversion rate corresponding to the product group can be determined.

[0146] Among them, the average sales value = GMV 总 / Quantity of goods. GMV 总 The total sales of all products included in the product group. The unit quantity is the quantity of all products included in the product group.

[0147] Average sales volume = Sales 总 / Quantity of goods. 总 This is the total sales volume for all products included in the product group.

[0148] Flow mean = Pv 总 / Quantity of goods. 总 Refers to the total traffic of all products included in the product group.

[0149] Average traffic conversion rate = Order 总 / Pv 总 . Order 总 Refers to the number of traffic conversions for all the deals included in the product group.

[0150] You can also determine the sales information of each product, specifically the sales volume, sales volume, traffic, and traffic conversion rate of each product.

[0151] Step 405, determining defective goods and non-defective goods based on sales information.

[0152] Among them, defective products and non-defective products can be determined among these products based on the sales information corresponding to the product group and the sales information corresponding to each product.

[0153] Specifically, if each sales indicator of a product is lower than the indicator of the corresponding product category, the product can be considered a bad product. For example, if the sales of a product is lower than the average sales, the sales volume is lower than the average sales, the traffic is lower than the average traffic, and the traffic conversion rate is lower than the average traffic conversion rate, then the product can be considered a bad product.

[0154] Furthermore, if the sales index of a product is lower than the average index, it can be considered that the sales of this product is not good, so it can be confirmed as a defective product. Other products are non-defective products.

[0155] Step 406, determining the target attribute according to the product attributes corresponding to the defective goods and the non-defective goods.

[0156] In actual application, a commodity may include multiple product attributes, that is, it may also include other attributes besides the attributes corresponding to user needs. Therefore, we can conduct in-depth research based on the product attributes to determine the key research and development directions within the product range that meets user needs.

[0157] Among them, the target attributes can be determined based on the product attributes corresponding to defective products and non-defective products.

[0158] Specifically, the third proportion of a product attribute appearing in defective goods and the fourth proportion of a product attribute appearing in non-defective goods can be determined. The third proportion can be the ratio of the frequency of a product attribute appearing in defective goods to the number of defective goods; the fourth proportion can be the ratio of the frequency of a product attribute appearing in non-defective goods to the number of non-defective goods.

[0159] Furthermore, the product attributes may be attributes possessed by products in a product group. For example, if a product has 20 product attributes, the third proportions and the fourth proportions of the 20 product attributes may be determined respectively.

[0160] In actual application, the potential value of the product attribute can also be determined according to the third proportion and the fourth proportion, and the target attribute can be determined in the product attributes according to the potential value.

[0161] The difference between the fourth proportion and the third proportion can be determined and used as the potential value. If the proportion of a product attribute in non-defective products is relatively large, it can be considered that the sales of products with the product attribute are good, and the product attribute can be determined as the target attribute.

[0162] Specifically, when the potential value is greater than 0, it is considered that the corresponding product attribute accounts for a large proportion of non-defective products. Therefore, the product attribute with a potential value greater than 0 can be determined as the target attribute.

[0163] Figure 6 This is a structural diagram of an apparatus for determining target attributes of a product according to an exemplary embodiment of the present invention.

[0164] like Figure 6 As shown, the device for determining a target attribute of a product provided in this embodiment includes:

[0165] An acquisition module 61 is used to acquire at least two product attributes corresponding to a product category;

[0166] A group determination module 62, configured to determine a product attribute combination according to the product attributes, and determine a product group according to the product attribute combination;

[0167] A grouping module 63, for grouping the commodities of the category according to the product group;

[0168] The analysis module 64 is used to determine the target attribute from the product attributes according to the information of the commodities included in the product group.

[0169] The device for determining the target attributes of a product provided in this embodiment includes: an acquisition module for acquiring at least two product attributes corresponding to a product category; a group determination module for determining a combination of product attributes based on the product attributes, and determining a product group based on the combination of product attributes; a grouping module for grouping the commodities of the category according to the product group; and an analysis module for determining the target attributes in the product attributes according to the information of the commodities included in the product group. The device provided in this embodiment can group the commodities according to the product attributes, and analyze the information of the commodities included in each group to determine the target attributes. The device provided in this embodiment does not rely on human factors, but analyzes based on the information of the commodities themselves, and the results obtained are more accurate, so that the product manufacturer can be guided in product research and development.

[0170] The specific principles and implementation methods of the device for determining product target attributes provided in this embodiment are similar to Figure 1The embodiments shown are similar and will not be described again here.

[0171] Figure 7 This is a structural diagram of an apparatus for determining target attributes of a product according to another exemplary embodiment of the present invention.

[0172] like Figure 7 As shown, based on the above embodiment, the device for determining product target attributes provided in this embodiment, optionally, the group determination module 62 is specifically used for:

[0173] Selecting a preset number of attributes from the product attributes as a product attribute combination;

[0174] The product attribute combinations include all possible combinations.

[0175] Optionally, the device further comprises a first rejection module 65, which is used for: after the grouping module 63 groups the commodities of the category according to the product groups:

[0176] Determine a small-volume product group based on the number of commodities included in the product group;

[0177] Acquire first commodity information corresponding to the commodities included in the small-volume product group, and determine a product group with concentrated brands in the small-volume product group according to the first commodity information;

[0178] The brand-concentrated product groups are eliminated from the small-volume product groups.

[0179] Optionally, the first rejection module 65 is specifically used for:

[0180] Determine brand information and sales information corresponding to each product according to the first product information corresponding to the small-volume product group;

[0181] Determine the target brand with the largest sales volume in each of the small-volume product groups based on the brand information and the sales information;

[0182] The average sales share is determined based on the sales share of the target brand corresponding to each small-volume product group, and in the small-volume product group, the brand-concentrated product group is determined based on the sales share of the target brand and the average sales share.

[0183] Optionally, the first elimination module 65 is specifically used to: determine the total transaction amount corresponding to a brand in each of the small-volume product groups according to the brand information and the sales information;

[0184] The ratio of the total transaction amount corresponding to the brand to the total transaction amount of the small-volume product group is determined as the sales proportion corresponding to the brand;

[0185] Based on the sales share of each brand in the small-volume product group, determine the target brand with the largest sales share.

[0186] Optionally, the device further comprises a second rejection module 66, which is used for: after the grouping module 63 groups the commodities of the category according to the product group:

[0187] Determine the style concentration corresponding to the product group according to the sales information and quantity of each product in the product group;

[0188] According to the style concentration and concentration threshold, the high concentration groups in the product group are eliminated.

[0189] Optionally, the analysis module 64 includes:

[0190] A division unit 641 is used to determine potential groups and other groups in the product group according to the remaining commodity information corresponding to the product group;

[0191] The determination unit 642 is used to determine the target attribute according to the product attributes corresponding to the potential group and the other groups.

[0192] Optionally, the dividing unit 641 is specifically used for:

[0193] Determine the output capacity corresponding to each remaining product group according to the commodity sales information and quantity corresponding to the product group;

[0194] Determine the average output capacity based on all product sales information and all quantities corresponding to all remaining product groups;

[0195] According to the output capacity corresponding to each product group and the average output capacity, potential groups and other groups are determined from the remaining product groups.

[0196] Optionally, the dividing unit 641 is specifically used for:

[0197] Among the remaining product groups, the product groups whose output capacity is greater than the average output capacity are determined as the potential categories;

[0198] Among the remaining product groups, the product groups whose output capacity is less than or equal to the average output capacity are determined as the other groups.

[0199] Optionally, the determining unit 642 is specifically configured to:

[0200] Determine a first proportion of occurrences of a product attribute in a potential group, and a second proportion of occurrences of the product attribute in the potential group and the other groups;

[0201] The potential value of the product attribute is determined according to the first proportion and the second proportion, and the target attribute is determined among the product attributes according to the potential value.

[0202] Optionally, the determining unit 642 is specifically configured to:

[0203] The difference between the first proportion and the second proportion is determined as the potential value of the product attribute.

[0204] Optionally, the grouping module 63 is specifically used for:

[0205] Determine a product attribute combination according to product requirements and the product attributes;

[0206] The analysis module 64 is specifically used for:

[0207] determining sales information according to the product information corresponding to the product category;

[0208] Determine defective goods and non-defective goods according to the sales information;

[0209] Determine the target attributes based on the product attributes corresponding to the defective and non-defective product categories.

[0210] Optionally, the analysis module 64 is specifically used for:

[0211] Determine sales information based on the product information corresponding to the product group;

[0212] Determine defective goods and non-defective goods according to the sales information;

[0213] Determine the target attributes based on the product attributes corresponding to defective goods and non-defective goods.

[0214] The specific principles and implementation methods of the device for determining the target attributes of a product provided in this embodiment are similar to Figure 2-4 The embodiments shown are similar and will not be described again here.

[0215] Figure 8 A structural diagram of a device for determining target attributes of a product according to an exemplary embodiment of the present invention.

[0216] like Figure 8 As shown, the device for determining the target attribute of a product provided in this embodiment includes:

[0217] Memory 81;

[0218] Processor 82; and

[0219] Computer programs;

[0220] The computer program is stored in the memory 81 and is configured to be executed by the processor 82 to implement any of the methods for determining a target attribute of a product as described above.

[0221] This embodiment also provides a computer-readable storage medium having a computer program stored thereon.

[0222] The computer program is executed by a processor to implement any one of the methods for determining a target attribute of a product as described above.

[0223] This embodiment also provides a computer program, including program code. When a computer runs the computer program, the program code executes any one of the methods for determining a target attribute of a product as described above.

[0224] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0225] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a target attribute of a product, characterized in that: include: Obtain at least two product attributes corresponding to a product category; Determining a product attribute combination according to the product attributes, and determining a product group according to the product attribute combination; The commodities of the category are grouped according to the product attributes corresponding to the product group and the attributes of the commodities, and the target attributes are determined from the product attributes according to the information of the commodities included in the product group; After grouping the commodities of the category according to the product group, the method further includes: Determine a small-volume product group based on the number of commodities included in the product group; Acquire first commodity information corresponding to the commodities included in the small-volume product group, and determine brand information and sales information corresponding to each commodity according to the first commodity information corresponding to the small-volume product group; Determine the target brand with the largest sales volume in each of the small-volume product groups based on the brand information and the sales information; Determine the average sales share according to the sales share of the target brand corresponding to each small-volume product group, and determine the product group where the target brand is concentrated according to the sales share of the target brand and the average sales share in the small-volume product group; Eliminate the product group with concentrated brands from the product group with small volume; After grouping the commodities of the category according to the product group, the method further includes: Determine the style concentration corresponding to the product group according to the sales information and quantity of each product in the product group; According to the style concentration and concentration threshold, remove the high concentration group in the product group; The determining of the target attribute from the product attributes according to the information of the commodities included in the product group includes: Determine potential groups and other groups in the remaining product groups according to the commodity information corresponding to the remaining product groups; The target attributes are determined according to the product attributes corresponding to the potential group and the other groups.

2. The method according to claim 1, characterized in that The determining of a product attribute combination according to the product attributes comprises: Selecting a preset number of attributes from the product attributes as a product attribute combination; The product attribute combinations include all possible combinations.

3. The method according to claim 1, characterized in that Determining the target brand with the largest sales volume in each small-volume product group based on the brand information and the sales information includes: Determine the total transaction amount corresponding to a brand in each of the small-volume product groups according to the brand information and the sales information; The ratio of the total transaction amount corresponding to the brand to the total transaction amount of the small-volume product group is determined as the sales proportion corresponding to the brand; Based on the sales share of each brand in the small-volume product group, determine the target brand with the largest sales share.

4. The method according to claim 1, characterized in that: Determining potential groups and other groups from the remaining product groups according to the commodity information corresponding to the remaining product groups includes: Determine the output capacity corresponding to the remaining product groups according to the commodity sales information and quantity corresponding to each remaining product group; Determine the average output capacity based on all product sales information and all quantities corresponding to all remaining product groups; According to the output capacity corresponding to each of the remaining product groups and the average output capacity, potential groups and other groups are determined from the remaining product groups.

5. The method according to claim 4, characterized in that Determining potential groups and other groups from the remaining product groups according to the output capacity corresponding to each of the remaining product groups and the average output capacity includes: Among the remaining product groups, the product groups whose output capacity is greater than the average output capacity are determined as potential categories; Among the remaining product groups, the product groups whose output capacity is less than or equal to the average output capacity are determined as the other groups.

6. The method according to claim 1, characterized in that Determining target attributes according to the product attributes corresponding to the potential group and the other groups: Determine a first proportion of occurrences of a product attribute in a potential group, and a second proportion of occurrences of the product attribute in the potential group and the other groups; The potential value of the product attribute is determined according to the first proportion and the second proportion, and the target attribute is determined among the product attributes according to the potential value.

7. The method according to claim 6, characterized in that The determining the potential value of the product attribute according to the first proportion and the second proportion includes: The difference between the first proportion and the second proportion is determined as the potential value of the product attribute.

8. The method according to claim 1, characterized in that The determining of a product attribute combination according to the product attributes further includes: Determine a product attribute combination according to product requirements and the product attributes; The determining of the target attribute from the product attributes according to the information of the products included in the product group includes: Determine sales information based on the product information corresponding to the product group; Determine defective goods and non-defective goods according to the sales information; Determine the target attributes based on the product attributes corresponding to defective goods and non-defective goods.

9. The method according to claim 8, characterized in that Determining target attributes according to product attributes corresponding to defective goods and non-defective goods; Determine a third percentage of the product attribute appearing in defective products, and determine a fourth percentage of the product attribute appearing in non-defective products; The potential value of the product attribute is determined according to the third proportion and the fourth proportion, and a target attribute is determined among the product attributes according to the potential value.

10. The method according to claim 9, characterized in that Determining the potential value of the product attribute according to the third proportion and the fourth proportion, and determining a target attribute from the product attributes according to the potential value, includes: The difference between the fourth proportion and the third proportion is determined as the potential value of the product attribute.

11. A device for determining a target attribute of a product, characterized in that: include: An acquisition module, used to acquire at least two product attributes corresponding to a product category; A group determination module, used to determine a product attribute combination according to the product attributes, and determine a product group according to the product attribute combination; A grouping module, used for grouping the commodities of the category according to the product attributes corresponding to the product group and the attributes of the commodities; An analysis module, configured to determine a target attribute from among the product attributes according to information of the commodities included in the product group; A first elimination module, used for determining a small quantity product group according to the quantity of commodities included in the product group; Acquire first commodity information corresponding to the commodities included in the small-volume product group, and determine a product group with concentrated brands in the small-volume product group according to the first commodity information; Eliminate the product group with concentrated brands from the product group with small volume; The first elimination module is specifically used to determine the brand information and sales information corresponding to each product according to the first product information corresponding to the small-volume product group; Determine the target brand with the largest sales volume in each of the small-volume product groups based on the brand information and the sales information; Determine the average sales share according to the sales share of the target brand corresponding to each small-volume product group, and determine the product group where the target brand is concentrated according to the sales share of the target brand and the average sales share in the small-volume product group; A second elimination module is used to determine the style concentration corresponding to the product group according to the sales information and quantity of each commodity in the product group; According to the style concentration and concentration threshold, remove the high concentration group in the product group; The analysis module comprises: A division unit, configured to determine potential groups and other groups from the remaining product groups according to the commodity information corresponding to the remaining product groups; The determination unit is used to determine the target attribute according to the product attributes corresponding to the potential group and the other groups.

12. A device for determining a target attribute of a product, characterized in that: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: A computer program is stored thereon, The computer program is executed by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images