Data processing method, device and storage medium

Abstract

The present disclosure relates to a data processing method, device and storage medium. The method comprises: obtaining commodity data of a target commodity; determining the credibility of the commodity data of the target commodity according to the commodity data of the target commodity and the commodity data of a sample commodity stored in a sample commodity database, wherein the commodity data comprises at least one commodity attribute of the corresponding commodity and the attribute value of the commodity attribute. By using the commodity data of the sample commodity stored in the sample database as reference data to determine the credibility of the commodity data of the target commodity, a more objective and accurate credibility result can be obtained for the commodity data of the target commodity, thereby improving the accuracy of commodity data evaluation.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular, to a data processing method, device and storage medium. Background Art

[0002] With the development of the e-commerce industry, more and more products are available online, resulting in a great enrichment of product data. However, due to the lack of uniform understanding of e-commerce business among e-commerce practitioners and the different management models of various types of merchants, the accuracy and completeness of product data vary, and the product data format is not uniform, making it impossible to evaluate product data in a unified standard. For existing online products, due to the lack of uniform data format and the lack of a complete product evaluation system, it is impossible to determine the credibility of product data and determine whether the product is genuine. Summary of the invention

[0003] The purpose of the present disclosure is to provide a data processing method, device and storage medium to accurately evaluate the credibility of goods.

[0004] In order to achieve the above objective, according to a first aspect of the present disclosure, a data processing method is provided, comprising:

[0005] Get product data of the target product;

[0006] The credibility of the product data of the target product is determined according to the product data of the target product and the product data of the sample product stored in the sample product database, wherein the product data includes at least one product attribute of the corresponding product and the attribute value of the product attribute.

[0007] Optionally, determining the credibility of the product data of the target product according to the product data of the target product and the product data of sample products stored in a sample product database includes:

[0008] Determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity;

[0009] The credibility of the product data of the target product is determined according to the credibility of the attribute value of each product attribute of the target product and the attribute weight value corresponding to each product attribute of the target product.

[0010] Optionally, the method is applied to a first platform, and the sample commodity database includes a local sample commodity database of the first platform;

[0011] The determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity includes:

[0012] Determine the target parameters corresponding to each commodity attribute of the target commodity respectively, wherein the target parameters include: the dispersion of the attribute value of the commodity attribute in the first commodity data, and / or the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database; wherein the first commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity; the second commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity and the attribute value of the commodity attribute included is the same as the attribute value of the commodity attribute of the target commodity;

[0013] For each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

[0014] Optionally, the sample commodity database further includes at least one third-party sample commodity database acquired by the first platform from other platforms;

[0015] The step of determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity further includes:

[0016] Acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity;

[0017] The target parameter corresponding to each commodity attribute of the target commodity further includes: the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity;

[0018] Among them, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the product attribute is the same as the attribute value of the product attribute of the target product, then the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product is determined as the support degree of the third-party sample product database for the product attribute of the target product; otherwise, the support degree of the third-party sample product database for the product attribute of the target product is determined to be zero, wherein the valid product attribute is the product attribute common to the product data of the target product and the product data of the target sample product.

[0019] Optionally, the method is applied to a first platform, and the sample commodity database includes at least one third-party sample commodity database acquired by the first platform from other platforms;

[0020] The determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity includes:

[0021] Acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity;

[0022] Determine the target parameters corresponding to each product attribute of the target product respectively, wherein the target parameters include: the sum of the support of each third-party sample product database for the product attribute of the target product; wherein, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the included product attribute is the same as the attribute value of the product attribute of the target product, then determine the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product as the support of the third-party sample product database for the product attribute of the target product; otherwise, determine that the support of the third-party sample product database for the product attribute of the target product is zero; wherein, the valid product attribute is the product attribute shared by the product data of the target product and the product data of the target sample product;

[0023] For each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

[0024] Optionally, the target parameters further include: sales volume information of the target product within a specified time period, and / or a merchant attribute coefficient corresponding to a merchant selling the target product.

[0025] Optionally, the method further comprises:

[0026] Display the credibility of the product data of the target product; and / or,

[0027] If the credibility of the commodity data of the target commodity is lower than a preset threshold, a prompt message is displayed, where the prompt message is used to prompt that the credibility of the commodity data of the target commodity is lower than the preset threshold.

[0028] Optionally, the commodity attributes are selected from: commodity category, commodity brand, and commodity specifications.

[0029] According to a second aspect of the present disclosure, there is provided a data processing device, comprising:

[0030] an acquisition module, configured to acquire commodity data of a target commodity;

[0031] The processing module is configured to determine the credibility of the product data of the target product based on the product data of the target product and the product data of the sample product stored in the sample product database, wherein the product data includes at least one product attribute of the corresponding product and the attribute value of the product attribute.

[0032] Optionally, the processing module includes:

[0033] A first determination submodule, configured to determine the credibility of an attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity;

[0034] The second determination submodule is used to determine the credibility of the commodity data of the target commodity according to the credibility of the attribute value of each commodity attribute of the target commodity and the attribute weight value corresponding to each commodity attribute of the target commodity.

[0035] Optionally, the method is applied to a first platform, and the sample commodity database includes a local sample commodity database of the first platform;

[0036] The first determining submodule includes:

[0037] A third determination submodule is used to respectively determine the target parameters corresponding to each commodity attribute of the target commodity, wherein the target parameters include: the dispersion of the attribute value of the commodity attribute in the first commodity data, and / or the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database; wherein the first commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity; and the second commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity and includes the same attribute value of the commodity attribute as the attribute value of the target commodity;

[0038] The fourth determination submodule is used to determine the credibility of the attribute value of each commodity attribute of the target commodity according to the target parameter corresponding to the commodity attribute.

[0039] Optionally, the sample commodity database further includes at least one third-party sample commodity database acquired by the first platform from other platforms;

[0040] The first determining submodule further includes:

[0041] A first acquisition submodule is used to acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity;

[0042] The target parameter corresponding to each commodity attribute of the target commodity further includes: the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity;

[0043] Among them, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the product attribute is the same as the attribute value of the product attribute of the target product, then the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product is determined as the support degree of the third-party sample product database for the product attribute of the target product; otherwise, the support degree of the third-party sample product database for the product attribute of the target product is determined to be zero, wherein the valid product attribute is the product attribute common to the product data of the target product and the product data of the target sample product.

[0044] Optionally, the method is applied to a first platform, and the sample commodity database includes at least one third-party sample commodity database acquired by the first platform from other platforms;

[0045] The first determining submodule includes:

[0046] A second acquisition submodule is used to acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity;

[0047] a fifth determination submodule, for respectively determining target parameters corresponding to each commodity attribute of the target commodity, wherein the target parameters include: the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity; wherein, for each third-party sample commodity database, if the commodity data of the target sample commodity obtained from the third-party sample commodity database includes the commodity attribute of the target commodity, and the attribute value of the included commodity attribute is the same as the attribute value of the commodity attribute of the target commodity, then the ratio of the number of valid commodity attributes to the total number of commodity attributes included in the commodity data of the target sample commodity is determined as the support of the third-party sample commodity database for the commodity attribute of the target commodity; otherwise, the support of the third-party sample commodity database for the commodity attribute of the target commodity is determined to be zero; wherein, the valid commodity attribute is the commodity attribute common to the commodity data of the target commodity and the commodity data of the target sample commodity;

[0048] The sixth determination submodule is used to determine the credibility of the attribute value of each commodity attribute of the target commodity according to the target parameter corresponding to the commodity attribute.

[0049] Optionally, the target parameters further include: sales volume information of the target product within a specified time period, and / or a merchant attribute coefficient corresponding to a merchant selling the target product.

[0050] Optionally, the device further comprises:

[0051] A first display module is used to display the credibility of the commodity data of the target commodity; and / or,

[0052] The second display module is used to display a prompt message if the credibility of the commodity data of the target commodity is lower than a preset threshold, wherein the prompt message is used to prompt that the credibility of the commodity data of the target commodity is lower than the preset threshold.

[0053] Optionally, the commodity attributes are selected from: commodity category, commodity brand, and commodity specifications.

[0054] According to a third aspect of the present disclosure, there is provided a data processing device, comprising:

[0055] a memory having a computer program stored thereon;

[0056] A processor is used to execute the computer program in the memory to implement the steps of the method described in the first aspect of the present disclosure.

[0057] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0058] Through the above technical solution, the commodity data of the target commodity is obtained, and the credibility of the commodity data of the target commodity is determined based on the commodity data of the target commodity and the commodity data of the sample commodity stored in the sample commodity database. The credibility of the commodity data of the target commodity is determined by using the commodity data of the sample commodity stored in the sample database as reference data, so that a more objective and accurate credibility result can be obtained for the commodity data of the target commodity, thereby improving the accuracy of commodity data evaluation.

[0059] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0061] Figure 1 is a flow chart of a data processing method provided according to an embodiment of the present disclosure;

[0062] Figure 2 It is a flowchart of an exemplary implementation of a step of determining the credibility of the commodity data of a target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity stored in the sample commodity database in the data processing method provided by the present disclosure;

[0063] Figure 3 It is a flowchart of an exemplary implementation of a step of determining the credibility of an attribute value of each commodity attribute of a target commodity according to commodity data of a target commodity and commodity data of a sample commodity in a data processing method provided by the present disclosure;

[0064] Figure 4 is a block diagram of a data processing device provided according to an embodiment of the present disclosure;

[0065] Figure 5 is a block diagram of a data processing device according to an exemplary embodiment;

[0066] Figure 6 It is a block diagram of a data processing device according to an exemplary embodiment. DETAILED DESCRIPTION

[0067] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0068] Figure 11 is a flow chart of a data processing method provided according to an embodiment of the present disclosure. Figure 1 As shown, the method may include the following steps.

[0069] In step 11, the commodity data of the target commodity is obtained.

[0070] The target product is the product whose product data credibility is to be evaluated. If the credibility of the product data of a certain product needs to be evaluated, the product can be used as the target product. Among them, the product data can include at least one product attribute of the corresponding product and the attribute value of the product attribute. The product attribute can be selected from but not limited to the following: product category, product brand, and product specification. The product category is obtained based on the corresponding characteristics of the product. For example, the product category can be divided into hardware, chemical, food, aquatic products, etc. For another example, under the food category, the product category can also be divided into vegetables, fruits, dairy products, etc. Among them, different product categories correspond to different attribute values ​​of the product category. The product brand is an identification mark of the product, such as a company name, a trademark of a product or a service. The same type of product can come from different product brands. Taking cola as an example, its brand can be Pepsi or Coca-Cola. Among them, different product brands correspond to different attribute values ​​of product brands. Product specifications refer to certain main indicators used to reflect the quality of the product, such as ingredients, content, purity, strength, size, color, style, model, capacity, etc. For example, product specifications can be divided into different specifications such as 20 ml, 50 ml, 100 ml, etc. according to capacity. Different product specifications correspond to different attribute values ​​of product specifications.

[0071] In step 12, the credibility of the product data of the target product is determined based on the product data of the target product and the product data of the sample product stored in the sample product database.

[0072] The commodity data of the sample commodities stored in the sample commodity database can more objectively reflect the real situation of the commodities. Therefore, the credibility of the commodity data of the target commodity can be determined based on the commodity data of the target commodity and the commodity data of the sample commodities stored in the sample commodity database. For example, based on the commodity data of the sample commodities stored in the sample commodity database, the attribute values ​​corresponding to various commodity attributes of the target commodity and the sample commodities are compared to determine the credibility of the commodity data of the target commodity.

[0073] Through the above technical solution, after obtaining the commodity data of the target commodity, the credibility of the commodity data of the target commodity is determined according to the commodity data of the target commodity and the commodity data of each sample commodity stored in the sample commodity database. By using the commodity data of the sample commodity stored in the sample database as reference data to determine the credibility of the commodity data of the target commodity, a more objective and accurate credibility result can be obtained for the commodity data of the target commodity, thereby improving the accuracy of commodity data evaluation.

[0074] In order to enable those skilled in the art to better understand the technical solution provided by the embodiment of the present invention, the corresponding steps in the above text are described in detail below.

[0075] First, the determination of the credibility of the commodity data of the target commodity based on the commodity data of the target commodity and the commodity data of the sample commodity stored in the sample commodity database in step 12 is described in detail.

[0076] The commodity data includes at least one commodity attribute, and each commodity attribute has a corresponding attribute value. It can be seen that to determine the credibility of the commodity data, we can start from the various commodity attributes and their attribute values ​​included in the commodity data. Therefore, in a possible implementation, step 12 may include the following steps: Figure 2 shown.

[0077] In step 21, the credibility of the attribute value of each commodity attribute of the target commodity is determined based on the commodity data of the target commodity and the commodity data of the sample commodity.

[0078] According to the commodity data of the target commodity and the commodity data of the sample commodity, the credibility of the attribute value of each commodity attribute included in the commodity data can be determined.

[0079] In a possible implementation, the data processing method provided by the present disclosure may be applied to a first platform, and the sample commodity database includes a local sample commodity database of the first platform. In this implementation, step 21 may include the following steps.

[0080] In step 31, target parameters corresponding to each commodity attribute of the target commodity are determined respectively;

[0081] In step 32, for each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

[0082] In a possible embodiment, the target parameter may include: the discreteness of the attribute value of the commodity attribute in the first commodity data, and / or the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database. The first commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity, and the second commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity, and the attribute value of the commodity attribute included is the same as the attribute value of the commodity attribute of the target commodity. For example, if the commodity attribute of the target commodity is the commodity brand, the corresponding attribute value is "Coca-Cola", and there are 85 sample commodity data in the local sample commodity database whose attribute value corresponding to the commodity brand is "Coca-Cola", then the number of the second commodity data is 85.

[0083] The range, standard deviation, variance, etc. can reflect the degree of dispersion of a set of data. For commodity data, the lower the distribution dispersion of the attribute value of a commodity attribute, the more the attribute value can represent the commodity attribute, and the higher the credibility of the corresponding commodity. The higher the distribution dispersion of the attribute value of a commodity attribute, the more difficult it is for the attribute value to represent the commodity attribute, and the lower the credibility of the corresponding commodity data. Therefore, the target parameter can include the dispersion of the attribute value of the commodity attribute in the first commodity data.

[0084] The more times an attribute value of a certain commodity attribute of a commodity appears in each attribute value of the corresponding commodity attribute, the higher its frequency of occurrence, indicating that more commodities in the commodity data use this attribute value, and the higher the credibility of the corresponding commodity data. Therefore, the target parameter may include the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database.

[0085] Alternatively, if the target parameter only includes the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database, then in step 32, for the i-th commodity attribute of the target commodity p, based on the target parameter of the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database, the credibility s(p, i) of the attribute value of the i-th commodity attribute determined can be calculated according to the following formula (1):

[0086] s(p, i) = rate(p, i) (1)

[0087] Among them, rate(p, i) is the credibility score of the target parameter, which is the ratio of the number of second product data corresponding to the attribute value of the i-th product attribute of the target product to the total number of product data in the local sample product database.

[0088] For example, the rate (p, i) corresponding to the i-th commodity attribute of the target commodity p can be calculated by the following formula (2):

[0089]

[0090] Among them, N p is the number of the second product data, N available is the total number of product data in the attribute value database of the local sample product. is the target parameter of the ratio of the number of second product data to the total number of product data in the local sample product database, C base is the first score constant. In addition, in the local sample product database, the attribute value of the product attribute may be empty. Since the empty attribute value does not contribute to the subsequent calculation here, such product data can be regarded as invalid product data. Therefore, when determining the target parameter of the ratio of the number of second product data to the total number of product data in the local sample product database, if there is invalid product data in the product data in the local sample product database, the invalid product data in the local sample product database can be removed first to obtain the number of remaining valid product data, and use it as the total number of product data N in the local sample product database. available .

[0091] For example, if the product attribute of the target product is the product brand, the corresponding attribute value is "Coca-Cola", and there are 85 sample product data with the attribute value "Coca-Cola" corresponding to the product brand in the local sample product database, that is, N p is 85, and the total number of product data in the local sample product database is 100, that is, N available is 100, the first score constant C base is 100, then the credibility s(p,i) of the brand attribute value of "Coca-Cola" is: (85 / 100)*100=85.

[0092] Optionally, if the target parameter only includes the dispersion of the attribute value of the commodity attribute in the first commodity data, then in step 32, for the i-th commodity attribute of the target commodity p, according to the target parameter of the dispersion of the attribute value of the commodity attribute in the first commodity data, the credibility s(p, i) of the attribute value of the i-th commodity attribute determined can be calculated according to the following formula:

[0093] s(p, i) = Dis(data, i)

[0094] Wherein, Dis(data, i) is the discreteness of a set of data data of the i-th commodity attribute. For example, data can be the credibility score rate(p, i) of the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database, that is, the discreteness of the credibility score of the ratio of the number of second commodity data of the i-th commodity attribute to the total number of commodity data in the local sample commodity database. Thus, the credibility s(p, i) of the attribute value of the i-th commodity attribute can be calculated according to the following formula (3):

[0095] s(p,i)=Dis(rate(p,i),i) (3)

[0096] The dispersion Dis(rate(p, i), i) of the credibility score of the ratio of the number of second commodity data of the i-th commodity attribute of the target commodity p to the total number of commodity data in the local sample commodity database can be calculated by the following formula (4):

[0097]

[0098] Among them, rate k The kth score in the score sequence obtained by sorting the credibility scores of the ratios of the number of second product data corresponding to the n product attribute values ​​of the i-th product attribute to the total number of product data in the local sample product database in descending order. For example, if there are 10 attribute values ​​in the local sample product database for the product attribute of the target product specification, including 300ml and 80ml, and 8 attribute values ​​are 300ml and 2 attribute values ​​are 80ml, if the first score constant is 100, then the credibility score of the ratio of the number of second product data corresponding to the attribute value of 300ml to the total number of product data in the local sample product database is: (8 / 10)*100=80, the credibility score of the ratio of the number of second product data corresponding to the attribute value of 80ml to the total number of product data in the local sample product database is: (2 / 10)*100=20, and the score sequence obtained after sorting in descending order is {80, 20}. It can be seen that n=2, and rate1=80, rate2=20. Therefore, the target parameter corresponding to the product attribute of product specification can be calculated, Dis=(80-20) 2 / (80 2 +20 2 )≈0.529. According to the above formula (3), it can be determined that the reliability of the attribute value of the commodity specification is the result of the above formula 0.529.

[0099] Optionally, if the target parameter includes the dispersion of the attribute value of the commodity attribute in the first commodity data and the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database, then in step 32, for the i-th commodity attribute of the target commodity p, the credibility s(p, i) of the attribute value of the i-th commodity attribute determined according to the target parameter can be calculated according to the following formula:

[0100] s(p,i)=rate(p,i)*Dis(rate(p,i),i)

[0101] The definitions and calculation methods of rate(p, i) and Dis(rate(p, i), i) have been given above, such as formula (2) and formula (4), and will not be repeated here.

[0102] By adopting the above method, the credibility of each commodity attribute value is determined by utilizing any one or both of the two target parameters: the discreteness of the attribute value of the commodity attribute in the first commodity data and the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database. That is, the credibility of the attribute value of the commodity attribute is determined from two perspectives: the proportion of the attribute value of the commodity attribute and the discreteness of the attribute value distribution. This can make the subsequent credibility calculation of the commodity data of the target commodity more accurate.

[0103] Optionally, the sample product database may also include at least one third-party sample product database obtained by the first platform from other platforms. Therefore, in another possible embodiment, based on the steps of the previous embodiment, step 21 may also include the following steps:

[0104] The product data of the target sample product is obtained from each third-party sample product database.

[0105] According to the third-party sample product database, if the attribute value of a product attribute of the target product is the same as the product data of the third-party sample product, it means that other platforms are selling products with the attribute value of the product attribute, which to a certain extent indicates that the credibility of the product with the attribute value is high.

[0106] The target sample product is a sample product whose product code is consistent with the product code of the target product. The target parameter corresponding to each product attribute of the target product may also include: the sum of the support of each third-party sample product database for the product attribute of the target product. That is to say, based on any one or two target parameters of the discreteness of the attribute value of the product attribute in the first product data and the ratio of the number of the second product data to the total number of product data in the local sample product database, the target parameter also includes the sum of the support of each third-party sample product database for the product attribute of the target product. By way of example, the product code may be UPC, i.e., the uniform product code.

[0107] Among them, for each third-party sample database, if the commodity data of the target sample commodity obtained from the third-party sample commodity database includes the commodity attribute of the target commodity, and the attribute value of the commodity attribute included is the same as the attribute value of the commodity attribute of the target commodity, then the ratio of the number of valid commodity attributes to the total number of commodity attributes included in the commodity data of the target sample commodity is determined as the support degree of the third-party sample commodity database for the commodity attribute of the target commodity, otherwise, the support degree of the third-party sample commodity database for the commodity attribute of the target commodity is determined to be zero. The valid commodity attribute is the commodity attribute shared by the commodity data of the target commodity and the commodity data of the target sample commodity. For example, for the product attribute A (attribute value is A1) of the target product, if there are two third-party sample databases B1 and B2: if a target sample product whose product data includes product attribute A and whose attribute value of product attribute A is A1 can be obtained from the third-party sample database B1, and the number of product attributes shared with the product data of the target product in the target sample product is D, and the total number of product attributes included in the product data of the target sample product is C, then the support degree of the third-party sample product database B1 for the product attribute A of the target product is D / C; if a target sample product whose product data includes product attribute A and whose attribute value of product attribute A is A1 cannot be obtained from the third-party sample database B2, then the support degree of the third-party sample database B2 for the product attribute A of the target product is determined to be 0, and then the target parameter of the sum of the support degrees of each third-party sample product database for the product attribute of the target product can be determined to be D / C+0=D / C.

[0108] For example, if the target parameter includes two types: the dispersion of the attribute value of the commodity attribute in the first commodity data and the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity, then in step 32, for the i-th commodity attribute of the target commodity p, the credibility s(p, i) of the attribute value of the i-th commodity attribute can be calculated according to the following formula:

[0109]

[0110] The meaning and calculation method of Dis(rate(p, i), i) have been given above, such as formula (4), and will not be repeated here. m is the number of third-party sample product databases, Other(j, p, i) is the credibility score of the support of the jth third-party sample product database for the i-th product attribute of the target product p, That is, the credibility score of the target parameter which is the sum of the support of the i-th product attribute of each third-party sample product database for the target product p.

[0111] For example, the credibility score of the target parameter, which is the sum of the support of the i-th product attribute of each third-party sample product database for the target product p, can be calculated by the following formula (5):

[0112]

[0113] Among them, Column j is the number of valid product attributes, Column p is the total number of commodity attributes included in the commodity data of the target sample commodity, and for the i-th commodity attribute of the target commodity p (attribute value is x), if the target sample commodity whose commodity data includes the i-th commodity attribute and whose attribute value is x can be obtained from the third-party sample database, then Same(i) is 1; if the target sample commodity whose commodity data includes the i-th commodity attribute and whose attribute value is x cannot be obtained from the third-party sample database, then Same(i) is 0. In other words, is the support of the i-th commodity attribute of the target commodity p in the j-th third-party sample database, This is the target parameter, which is the sum of the support of the target product attributes in each third-party sample product database. extra is the second score constant. It can be seen that the product obtained by multiplying the sum of the support of each third-party sample product database for the product attribute of the target product by the second score constant is the credibility score of the target parameter, which is the sum of the support of each third-party sample product database for the product attribute of the target product. It is easy to obtain: That is, the above formula (5). For example, the second score constant may be 5.

[0114] For another example, if the target parameter includes two types: the ratio of the number of second product data to the total number of product data in the local sample product database and the sum of the support of each third-party sample product database for the product attribute of the target product, then in step 32, for the i-th product attribute of the target product p, the credibility s(p, i) of the attribute value of the i-th product attribute can be calculated according to the following formula:

[0115]

[0116] Among them, rate(p,i) and The meaning and calculation method of have been given above, such as formula (2) and (5), and will not be repeated here.

[0117] For another example, if the target parameters include the dispersion of the attribute value of the commodity attribute in the first commodity data, the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database, and the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity, then in step 32, for the i-th commodity attribute of the target commodity p, the credibility s(p, i) of the attribute value of the i-th commodity attribute can be calculated according to the following formula:

[0118]

[0119] Among them, rate(p, i), Dis(rate(p, i), i) and The meaning and calculation method of have been given above, such as formulas (2), (4), and (5), and will not be repeated here.

[0120] By adopting the above method, when calculating the credibility of the attribute value of a product attribute, a parameter of the sum of the support of each third-party sample product database for the product attribute of the target product is also introduced. Combined with the product data in the third-party sample product database, the credibility result of the attribute value of the product attribute can be made more accurate, which is conducive to obtaining more accurate product data credibility for the target product in the subsequent step.

[0121] In another possible embodiment, step 21 may include the following steps:

[0122] Obtain product data of target sample products from each third-party sample database;

[0123] Determine the target parameters corresponding to each commodity attribute of the target commodity respectively;

[0124] For each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

[0125] The target sample product is a sample product whose product code is consistent with the target product code. The target parameter may include: the sum of the support of each third-party sample product database for the product attribute of the target product. For example, the product code may be UPC, i.e., the unified product code.

[0126] Among them, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the included product attribute is the same as the attribute value of the product attribute of the target product, then the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product is determined as the support degree of the third-party sample product database for the product attribute of the target product, otherwise, the support degree of the third-party sample product database for the product attribute of the target product is determined to be zero. The valid product attribute is the product attribute shared by the product data of the target product and the product data of the target sample product.

[0127] According to the third-party sample product database, if the attribute value of a product attribute of the target product is the same as the product data of the third-party sample product, it means that other platforms are selling products with the attribute value of the product attribute, which to a certain extent indicates that the credibility of the product with the attribute value is high.

[0128] For example, if the target parameter only includes the sum of the support of each third-party sample product database for the product attribute of the target product, the target parameter corresponding to each product attribute of the target product is determined respectively, and then for each product attribute of the target product, the credibility of the attribute value of the product attribute is determined according to the target parameter corresponding to the product attribute. For the i-th product attribute of the target product p, the credibility s(p, i) of the attribute value of the i-th product attribute can be calculated according to the following formula:

[0129]

[0130] Where m is the number of third-party sample product databases, Other(j, p, i) is the credibility score of the support of the j-th third-party sample product database for the i-th product attribute of the target product p, That is, the credibility score of the target parameter, which is the sum of the support of the i-th product attribute of each third-party sample product database for the target product p. For example, It can be calculated using the formula (5) given above.

[0131] By adopting the above method, when calculating the credibility of the attribute value of a product attribute, the parameter of the sum of the support of each third-party sample product database for the product attribute of the target product is introduced. Combined with the product data in the third-party sample product database, the credibility result of the attribute value of the product attribute can be made more accurate, which is conducive to obtaining more accurate product data credibility for the target product in the subsequent process.

[0132] In another possible embodiment, in addition to the several cases of target parameters given in the above embodiments, the target parameters may also include: sales information of the target product within a specified time period, and / or merchant attribute coefficients corresponding to merchants selling the target product.

[0133] For target products, the sales quantities of different products vary, and the degree of the difference can reflect the accuracy of the product data, that is, its reliability, to a certain extent.

[0134] Optionally, if the target parameters include four types: the dispersion of the attribute value of the commodity attribute in the first commodity data, the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database, the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity, and the sales information of the target commodity in a specified period of time, then for the i-th commodity attribute of the target commodity p, the credibility s(p, i) of the attribute value of the i-th commodity attribute can be calculated according to the following formula:

[0135]

[0136] Among them, rate(p, i), Dis(rate(p, i), i) and The meaning and calculation method of have been given above, such as formulas (2), (4), and (5), and will not be repeated here. Sales(p) is the credibility score of the target parameter, which is the sales volume information of the target product p in the specified period.

[0137] For example, Sales(p) can be calculated by the following formula (6):

[0138] Sales(p)=tanh(Sales t / C sale ) (6)

[0139] Among them, Sales t is the sales information of the target product p in the specified period t, C sale In a possible embodiment, since merchants may conduct discounts, promotions and other activities in the actual sales cycle, the sales curve will have peaks and troughs. In order to avoid the impact of this situation on sales information, Sales t The average sales volume of the target product p in a specified period t can be used. For example, the specified period t can be one month, then Sales tThat is, the average monthly sales volume of the target product, where the average monthly sales volume can be calculated by dividing the annual sales volume by 12 (the number of months in a year). For example, the third score constant can be 2000. In the method provided by the present disclosure, the tanh function and the third score constant can be used to make the sales volume information of the target product in a specified period of time, which is the target parameter, affect the credibility of the attribute value of the product attribute within an open interval of (0, 1).

[0140] By adopting the above method, when calculating the credibility of the attribute value of the commodity attribute, the sales information of the target commodity in the specified time period is also introduced as a parameter. The credibility of the attribute value of the commodity attribute is calculated in combination with the actual sales volume of the commodity. This can make the calculation result more accurate, which is conducive to obtaining more accurate commodity data credibility for the target commodity in the future.

[0141] Commodity data is generally established by the merchants themselves. Different merchants have different management methods, and the accuracy and completeness of commodity data vary, which will affect the credibility of commodity data to a certain extent. Therefore, the target parameters can also include the merchant attribute coefficient corresponding to the merchant selling the target commodity. Different merchant attribute coefficients can be assigned to different merchants. For example, large merchants maintain higher accuracy of commodity information than small merchants (retail merchants). Therefore, the merchant attribute coefficient corresponding to large merchants can be relatively high, and the merchant attribute coefficient corresponding to small merchants can be relatively low. For example, the merchant attribute coefficient corresponding to the merchant selling the target commodity can be artificially set according to the actual scale of the merchant. For example, the merchant attribute coefficient of a large merchant selling the target commodity is 1, and the merchant attribute coefficient of a small merchant selling the target commodity is 0.7.

[0142] Optionally, if the target parameter includes five types: the dispersion of the attribute value of the commodity attribute in the first commodity data, the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database, the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity, the sales information of the target commodity in a specified period, and the merchant attribute coefficient corresponding to the merchant selling the target commodity, then for the i-th commodity attribute of the target commodity p, the credibility s(p, i) of the attribute value of the i-th commodity attribute can be calculated according to the following formula:

[0143]

[0144] Among them, rate(p,i), Dis(rate(p,i),i), Sales(p) and The interpretation and calculation method of have been given above, such as formulas (2), (4), (5), and (6), and will not be repeated here. Poi(p) is the credibility score of the target parameter, the merchant attribute coefficient, corresponding to the merchant selling the target product. For example, Poi(p) can be the same as the target parameter, the merchant attribute coefficient.

[0145] By adopting the above method, when calculating the credibility of the attribute value of the commodity attribute, the merchant attribute coefficient corresponding to the merchant selling the target commodity is also introduced. The credibility of the attribute value of the commodity attribute is calculated in combination with the scale of the merchant selling the commodity. This can make the calculation result more accurate, which is conducive to obtaining more accurate commodity data credibility for the target commodity in the future.

[0146] For cases where the target parameters are other possible combinations, reference can be made to the above-mentioned calculation method of the credibility s(p, i) of the attribute value of the i-th product attribute for the target product p. For other possible target parameter cases, this disclosure will no longer list them one by one.

[0147] Back to Figure 2 In step 22, the credibility of the commodity data of the target commodity is determined according to the credibility of the attribute value of each commodity attribute of the target commodity and the attribute weight value corresponding to each commodity attribute of the target commodity.

[0148] Since the product data of the target product includes at least one product attribute and the attribute value of the product attribute. Each product attribute corresponds to its own credibility, and the credibility of each attribute has different effects on the overall credibility of the product data of the target product. For example, some product attributes have higher requirements for credibility and have a greater impact on the overall credibility of the product data. Therefore, it is necessary to assign different weight values ​​to each product attribute according to the actual situation of each product attribute, so that the credibility of the product data finally obtained through various product attributes is more accurate.

[0149] For example, the credibility Score(p) of the product data of the target product p can be calculated by the following formula:

[0150]

[0151] Wherein, y is the number of all product attributes included in the product data of the target product, s(p, i) is the credibility of the attribute value of the i-th product attribute of the target product p, and Weight(p, i) is the attribute weight value corresponding to the i-th product attribute of the target product p.

[0152] In a possible embodiment, for the target parameters including the dispersion of the attribute values ​​of the commodity attribute in the first commodity data, the ratio of the number of the second commodity data to the total number of commodity data in the local sample commodity database, the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity, the sales information of the target commodity in a specified period, and the merchant attribute coefficient corresponding to the merchant selling the target commodity, for the target commodity p, the credibility Score(p) of the commodity data of the target commodity p can be calculated according to the following formula:

[0153]

[0154] The definitions and calculation methods of the relevant calculation factors have been given above and will not be repeated here.

[0155] By adopting the above method, the credibility of the product data of the target product is determined by utilizing the credibility of the attribute value of each product attribute of the target product and the attribute weight value corresponding to each product attribute of the target product. This method not only takes into account multiple product attributes, but also assigns a corresponding weight value to each product attribute, thereby improving the accuracy of the credibility calculation of the product data of the target product.

[0156] In addition, Figure 1 Based on the steps shown, the method of the present disclosure may further include the following steps:

[0157] Indicate the credibility of the product data of the target product; and / or

[0158] If the credibility of the product data of the target product is lower than the preset threshold, a prompt message is displayed.

[0159] The prompt information is used to prompt that the credibility of the commodity data of the target commodity is lower than a preset threshold.

[0160] After obtaining the credibility of the commodity data of the target commodity, the credibility of the commodity data of the target commodity can be displayed for the target commodity. For example, the credibility of the commodity data of the target commodity can be displayed in the display area where the target commodity is located or near the display area where the target commodity is located. In this way, the credibility of the commodity data of the target commodity can be intuitively displayed for easy viewing.

[0161] In addition, by setting a preset threshold, when the credibility of the commodity data of the target commodity is lower than the preset threshold, a prompt message is displayed to prompt that the credibility of the commodity data of the target commodity is lower than the preset threshold. In this way, a prompt can be given when the credibility of the commodity data of the target commodity is lower than the preset threshold, so that the user can know it easily.

[0162] Figure 4is a block diagram of a data processing device provided according to an embodiment of the present disclosure. Figure 4 As shown, the data processing device 40 includes:

[0163] An acquisition module 41 is configured to acquire commodity data of a target commodity;

[0164] The processing module 42 is configured to determine the credibility of the product data of the target product based on the product data of the target product and the product data of the sample product stored in the sample product database, wherein the product data includes at least one product attribute of the corresponding product and the attribute value of the product attribute.

[0165] Optionally, the processing module 42 includes:

[0166] A first determination submodule, configured to determine the credibility of an attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity;

[0167] The second determination submodule is used to determine the credibility of the commodity data of the target commodity according to the credibility of the attribute value of each commodity attribute of the target commodity and the attribute weight value corresponding to each commodity attribute of the target commodity.

[0168] Optionally, the method is applied to a first platform, and the sample commodity database includes a local sample commodity database of the first platform;

[0169] The first determining submodule includes:

[0170] A third determination submodule is used to respectively determine the target parameters corresponding to each commodity attribute of the target commodity, wherein the target parameters include: the dispersion of the attribute value of the commodity attribute in the first commodity data, and / or the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database; wherein the first commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity; and the second commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity and includes the same attribute value of the commodity attribute as the attribute value of the target commodity;

[0171] The fourth determination submodule is used to determine the credibility of the attribute value of each commodity attribute of the target commodity according to the target parameter corresponding to the commodity attribute.

[0172] Optionally, the sample commodity database further includes at least one third-party sample commodity database acquired by the first platform from other platforms;

[0173] The first determining submodule further includes:

[0174] A first acquisition submodule is used to acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity;

[0175] The target parameter corresponding to each commodity attribute of the target commodity further includes: the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity;

[0176] Among them, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the product attribute is the same as the attribute value of the product attribute of the target product, then the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product is determined as the support degree of the third-party sample product database for the product attribute of the target product; otherwise, the support degree of the third-party sample product database for the product attribute of the target product is determined to be zero, wherein the valid product attribute is the product attribute common to the product data of the target product and the product data of the target sample product.

[0177] Optionally, the method is applied to a first platform, and the sample commodity database includes at least one third-party sample commodity database acquired by the first platform from other platforms;

[0178] The first determining submodule includes:

[0179] A second acquisition submodule is used to acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity;

[0180] a fifth determination submodule, for respectively determining target parameters corresponding to each commodity attribute of the target commodity, wherein the target parameters include: the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity; wherein, for each third-party sample commodity database, if the commodity data of the target sample commodity obtained from the third-party sample commodity database includes the commodity attribute of the target commodity, and the attribute value of the included commodity attribute is the same as the attribute value of the commodity attribute of the target commodity, then the ratio of the number of valid commodity attributes to the total number of commodity attributes included in the commodity data of the target sample commodity is determined as the support of the third-party sample commodity database for the commodity attribute of the target commodity; otherwise, the support of the third-party sample commodity database for the commodity attribute of the target commodity is determined to be zero; wherein, the valid commodity attribute is the commodity attribute common to the commodity data of the target commodity and the commodity data of the target sample commodity;

[0181] The sixth determination submodule is used to determine the credibility of the attribute value of each commodity attribute of the target commodity according to the target parameter corresponding to the commodity attribute.

[0182] Optionally, the target parameters further include: sales volume information of the target product within a specified time period, and / or a merchant attribute coefficient corresponding to a merchant selling the target product.

[0183] Optionally, the device 40 further includes:

[0184] A first display module is used to display the credibility of the commodity data of the target commodity; and / or,

[0185] The second display module is used to display a prompt message if the credibility of the commodity data of the target commodity is lower than a preset threshold, wherein the prompt message is used to prompt that the credibility of the commodity data of the target commodity is lower than the preset threshold.

[0186] Optionally, the commodity attributes are selected from: commodity category, commodity brand, and commodity specifications.

[0187] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0188] Figure 5 FIG. 1 is a block diagram of a data processing device according to an exemplary embodiment. Figure 5 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0189] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned data processing method. The memory 702 is used to store various types of data to support the operation of the electronic device 700. For example, these data may include instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 707 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0190] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned data processing method.

[0191] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by the processor, the steps of the above-mentioned data processing method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned data processing method.

[0192] Figure 6 1 is a block diagram of a data processing device according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Figure 6 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing a computer program executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processor 1922 may be configured to execute the computer program to perform the above-mentioned data processing method.

[0193] In addition, the electronic device 1900 may further include a power supply component 1926 and a communication component 1950, wherein the power supply component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to implement communication of the electronic device 1900, for example, wired or wireless communication. In addition, the electronic device 1900 may further include an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, etc.

[0194] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned data processing method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 1932 including program instructions, and the above-mentioned program instructions can be executed by the processor 1922 of the electronic device 1900 to complete the above-mentioned data processing method.

[0195] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0196] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0197] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A data processing method, characterized in that: include: Get product data of the target product; Determining the credibility of the product data of the target product according to the product data of the target product and the product data of the sample product stored in the sample product database, wherein the product data includes at least one product attribute of the corresponding product and the attribute value of the product attribute; determining the credibility of the product data of the target product according to the product data of the target product and the product data of the sample product stored in the sample product database includes: Determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity; Determining the credibility of the product data of the target product according to the credibility of the attribute value of each product attribute of the target product and the attribute weight value corresponding to each product attribute of the target product; The method is applied to a first platform, and the sample commodity database includes a local sample commodity database of the first platform; The determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity includes: Determine the target parameters corresponding to each commodity attribute of the target commodity respectively, wherein the target parameters include: the dispersion of the attribute value of the commodity attribute in the first commodity data, and / or the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database; wherein the first commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity; the second commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity and the attribute value of the commodity attribute included is the same as the attribute value of the commodity attribute of the target commodity; For each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

2. The method according to claim 1, characterized in that The sample commodity database also includes at least one third-party sample commodity database obtained by the first platform from other platforms; The step of determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity further includes: Acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity; The target parameter corresponding to each commodity attribute of the target commodity further includes: the sum of the support of each third-party sample commodity database for the commodity attribute of the target commodity; Among them, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the product attribute is the same as the attribute value of the product attribute of the target product, then the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product is determined as the support degree of the third-party sample product database for the product attribute of the target product; otherwise, the support degree of the third-party sample product database for the product attribute of the target product is determined to be zero, wherein the valid product attribute is the product attribute common to the product data of the target product and the product data of the target sample product.

3. The method according to claim 1, characterized in that The method is applied to a first platform, and the sample commodity database includes at least one third-party sample commodity database obtained by the first platform from other platforms; The determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity includes: Acquire commodity data of a target sample commodity from each third-party sample commodity database, wherein the target sample commodity is a sample commodity whose commodity code is consistent with the commodity code of the target commodity; Determine the target parameters corresponding to each product attribute of the target product respectively, wherein the target parameters include: the sum of the support of each third-party sample product database for the product attribute of the target product; wherein, for each third-party sample product database, if the product data of the target sample product obtained from the third-party sample product database includes the product attribute of the target product, and the attribute value of the included product attribute is the same as the attribute value of the product attribute of the target product, then determine the ratio of the number of valid product attributes to the total number of product attributes included in the product data of the target sample product as the support of the third-party sample product database for the product attribute of the target product; otherwise, determine that the support of the third-party sample product database for the product attribute of the target product is zero; wherein, the valid product attribute is the product attribute shared by the product data of the target product and the product data of the target sample product; For each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

4. The method according to any one of claims 1 to 3, characterized in that The target parameters also include: sales information of the target product within a specified period of time, and / or a merchant attribute coefficient corresponding to a merchant selling the target product.

5. The method according to claim 1, characterized in that The method further includes: Displaying the credibility of the product data of the target product; and / or, if the credibility of the product data of the target product is lower than a preset threshold, displaying a prompt message, wherein the prompt message is used to prompt that the credibility of the product data of the target product is lower than the preset threshold.

6. The method according to claim 1, characterized in that The commodity attributes are selected from: commodity category, commodity brand, and commodity specifications.

7. A data processing device, characterized in that: include: an acquisition module, configured to acquire commodity data of a target commodity; a processing module configured to determine the credibility of the commodity data of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity stored in the sample commodity database, wherein the commodity data includes at least one commodity attribute of the corresponding commodity and an attribute value of the commodity attribute; The determining the credibility of the commodity data of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity stored in the sample commodity database includes: Determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity; Determining the credibility of the product data of the target product according to the credibility of the attribute value of each product attribute of the target product and the attribute weight value corresponding to each product attribute of the target product; The device is applied to a first platform, and the sample commodity database includes a local sample commodity database of the first platform; The determining the credibility of the attribute value of each commodity attribute of the target commodity according to the commodity data of the target commodity and the commodity data of the sample commodity includes: Determine the target parameters corresponding to each commodity attribute of the target commodity respectively, wherein the target parameters include: the dispersion of the attribute value of the commodity attribute in the first commodity data, and / or the ratio of the number of second commodity data to the total number of commodity data in the local sample commodity database; wherein the first commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity; the second commodity data is the commodity data in the local sample commodity database that includes the commodity attribute of the target commodity and the attribute value of the commodity attribute included is the same as the attribute value of the commodity attribute of the target commodity; For each commodity attribute of the target commodity, the credibility of the attribute value of the commodity attribute is determined according to the target parameter corresponding to the commodity attribute.

8. A data processing device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

Images