Method, device and server for identifying false transactions based on logistics data

Abstract

The present application provides a method, device and server for identifying false transactions based on logistics data, the method comprising: obtaining logistics data about transaction commodities in online transactions, the logistics data comprising the logistics order number of the transaction commodities and the commodity pictures of the transaction commodities; determining the first commodity type corresponding to the transaction commodities according to the logistics order number; determining the second commodity type of the transaction commodities according to the commodity pictures; determining whether the online transaction is a false transaction according to the first commodity type and the second commodity type. The technical solution of the present invention can avoid the seller and buyer of online transactions from negotiating false transactions in advance, and can also prohibit illegal sellers from cashing out, money laundering and other illegal behaviors through e-commerce platforms, making online transaction behaviors more standardized.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, device and server for identifying false transactions based on logistics data. Background Art

[0002] With the rapid development of Internet technology, e-commerce makes people's shopping more convenient. In order to quickly increase their account credit points and / or product sales, commodity providers (store owners or sellers) based on e-commerce platforms usually use false transactions to increase their product sales and account credit points in the early stage of opening a store. When commodity buyers (buyers) refer to the seller's account credit points or product sales, the above parameters do not fully reflect the seller's real information, thus hindering the buyer's rights and interests. In addition, unreal online transactions can enable illegal sellers to cash out, launder money and other illegal activities through e-commerce platforms, thereby bringing extremely adverse effects to society. In the process of false transaction identification in the prior art, the e-commerce platform provider is equipped with relevant personnel to supervise the seller, thereby regulating the seller's online transaction behavior. This method consumes a lot of human resources and brings unnecessary cost expenditures to the e-commerce platform provider. Summary of the invention

[0003] In view of this, the present application provides a new technical solution that can solve the technical problem of false transactions in online transactions.

[0004] To achieve the above objectives, this application provides the following technical solutions:

[0005] According to a first aspect of the present invention, a method for identifying false transactions based on logistics data is proposed, the method comprising:

[0006] Obtaining logistics data about the transaction commodity in the online transaction, the logistics data including the logistics order number of the transaction commodity and the attribute information of the transaction commodity, wherein the logistics data is obtained through a logistics data server; the attribute information of the transaction commodity is a commodity picture of the transaction commodity;

[0007] Determining a first commodity type corresponding to the transaction commodity according to the logistics order number;

[0008] Determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity;

[0009] The determining whether the online transaction is a false transaction based on the first commodity type and the attribute information of the transaction commodity includes: determining a picture reference feature corresponding to the first commodity type in a feature model library, the feature model library storing picture reference features of transaction commodities whose sales volume reaches a set number within a set time period; and determining whether the online transaction is a false transaction based on the commodity picture and the picture reference feature.

[0010] According to a second aspect of the present invention, a device for identifying false transactions based on logistics data is provided, the device comprising:

[0011] An acquisition module is used to acquire logistics data about transaction commodities in online transactions, wherein the logistics data includes the logistics order number of the transaction commodities and the attribute information of the transaction commodities, wherein the logistics data is acquired through a logistics data server; the attribute information of the transaction commodities is a commodity picture of the transaction commodities;

[0012] A first commodity type determination module, used to determine the first commodity type corresponding to the transaction commodity according to the logistics order number obtained by the acquisition module;

[0013] A false transaction determination module, used to determine whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity;

[0014] The false transaction determination module is specifically used to: determine the image reference feature corresponding to the first commodity type in a feature model library, the feature model library storing the image reference features of transaction commodities whose sales volume reaches a set number within a set time period; determine whether the online transaction is a false transaction based on the commodity picture and the image reference feature.

[0015] According to a third aspect of the present invention, a server is provided, the server comprising:

[0016] A processor; a memory for storing instructions executable by the processor;

[0017] Wherein, the processor is used to obtain logistics data about transaction commodities in online transactions, the logistics data including the logistics order number of the transaction commodities and the attribute information of the transaction commodities, wherein the logistics data is obtained through a logistics data server; determining a first commodity type corresponding to the transaction commodity according to the logistics order number; determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity; the attribute information of the transaction commodity is a commodity image of the transaction commodity; determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity, including: determining a picture reference feature corresponding to the first commodity type in a feature model library, the feature model library storing picture reference features of transaction commodities whose sales volume reaches a set number within a set time period; determining whether the online transaction is a false transaction according to the commodity image and the picture reference feature.

[0018] It can be seen from the above technical solutions that this application identifies whether an online transaction is a false transaction based on logistics data. Since the logistics data is obtained through a third-party logistics company, the reliability of the data source can be ensured, and the seller and buyer of the online transaction can be prevented from negotiating in advance to conduct a false transaction, which prevents the seller from increasing his account credit points or commodity sales through false transactions, and ensures that the seller information displayed by the e-commerce platform is true information, providing buyers with a true reference basis when shopping online, thereby ensuring the rights and interests of buyers when shopping online. In addition, by identifying whether an online transaction is true through logistics data and transaction information, it is also possible to prohibit illegal sellers from cashing out, laundering money and other illegal activities through e-commerce platforms, making online transaction behaviors more standardized. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1A A schematic flow chart of a method for identifying false transactions based on logistics data according to an exemplary embodiment of the present invention is shown;

[0020] Figure 1B A schematic diagram showing logistics voucher information according to an exemplary embodiment of the present invention is shown;

[0021] Figure 1C A schematic diagram showing a trading commodity according to an exemplary embodiment of the present invention is shown;

[0022] Figure 2 A schematic flow chart of a method for identifying false transactions based on logistics data according to another exemplary embodiment of the present invention is shown;

[0023] Figure 3 A schematic flow chart of a method for identifying false transactions based on logistics data according to yet another exemplary embodiment of the present invention is shown;

[0024] Figure 4 A schematic diagram showing the structure of a server according to an exemplary embodiment of the present invention is shown;

[0025] Figure 5 A schematic structural diagram of a device for identifying false transactions based on logistics data according to an exemplary embodiment of the present invention is shown;

[0026] Figure 6 A schematic structural diagram of an apparatus for identifying false transactions based on logistics data according to yet another exemplary embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0029] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0030] This application identifies whether an online transaction is a false transaction through the logistics data provided by the logistics company. Since the logistics data is obtained through a third-party logistics company, the reliability of the data source can be ensured, avoiding the seller and buyer of the online transaction from agreeing in advance to conduct a false transaction, thereby stopping illegal transactions.

[0031] To further illustrate the present application, the following examples are provided:

[0032] Please refer to Figure 1A, is a flow chart of a method for identifying false transactions based on logistics data according to an exemplary embodiment of the present invention, comprising the following steps:

[0033] Step 101, obtaining logistics data about the transaction goods in the online transaction, wherein the logistics data includes the logistics order number of the online transaction and the product image of the transaction goods.

[0034] In one embodiment, the server of the e-commerce platform provider can be connected to the server of the logistics company for managing the logistics data of the transported goods through communication, and the server of the e-commerce platform provider can obtain the logistics data of the transaction goods in the online transaction from the server of the logistics company in real time or quasi-real time. In one embodiment, the commodity picture can be a color picture taken by the logistics company when the transaction goods are received, and in another embodiment, the commodity picture can be an infrared picture taken by the logistics company when the transaction goods are inspected, and the image features of the transaction goods can be determined through the color picture or the infrared picture.

[0035] Step 102: Determine the first commodity type corresponding to the transaction commodity according to the logistics order number.

[0036] In one embodiment, the commodity transaction information of this online transaction can be queried from the server of the e-commerce platform provider according to the logistics order number. Figure 1B , shows the commodity transaction information described in the embodiment of the present invention, the commodity transaction information may include the logistics order number and logistics company of the online transaction, and may also include the commodity type, commodity name, commodity weight, consignee information, consignor information, payment method and online transaction time of the transaction commodity, so that the first commodity type of the transaction commodity can be determined through the commodity transaction information. For example, Figure 1B As shown, it can be found from the server of the e-commerce platform provider based on the logistics order number that the product type of this online transaction is "smartphone" and the product name is "Apple (Apple) iPhone6 ​​Plus (A1524) 16G Silver China Mobile, China Unicom, China Telecom 4G Mobile Phone".

[0037] Step 103: Determine the second commodity type corresponding to the transaction commodity according to the commodity image.

[0038] In one embodiment, the image feature information of the commodity image can be calculated by image detection technology, and the commodity type of the transaction commodity can be determined according to the image feature information. Figure 1C , shows a schematic diagram of a transaction commodity according to an exemplary embodiment of the present invention, which uses an Apple mobile phone 10 as an example for exemplary explanation. For example, after obtaining the image feature information of the transaction commodity through image detection technology, it can be determined that the commodity type of the transaction commodity is a smart phone based on the image feature information.

[0039] Step 104: Determine whether the online transaction is a false transaction based on the first commodity type and the second commodity type.

[0040] For example, if the first commodity type corresponding to the transaction commodity is determined to be a smart phone through the above step 102, and the commodity type of the transaction commodity is determined to be a smart phone through the above step 103, the first commodity type matches the second commodity type, and it can be determined that the online transaction is a real transaction; if it is determined through the above step 102 that the first commodity type corresponding to the transaction commodity is a smart phone, but the seller sends a pack of tissues to the buyer to replace the smart phone, then the second commodity type of the online transaction can be determined to be "paper products" through the image feature information of the transaction commodity, and since "smart phone" and "paper products" do not match, it can be determined that this transaction is a false transaction.

[0041] As can be seen from the above description, the embodiment of the present invention identifies whether an online transaction is a false transaction based on logistics data. Since the logistics data is obtained through a third-party logistics company, the reliability of the data source can be ensured, thereby preventing the seller and buyer of the online transaction from negotiating in advance to conduct a false transaction, preventing the seller from increasing his account credit points or commodity sales through false transactions, ensuring that the seller information displayed by the e-commerce platform is true information, providing buyers with a true reference basis when shopping online, and ensuring the legitimate rights and interests of buyers when shopping online. In addition, by identifying whether an online transaction is true through logistics data, illegal sellers can also be prohibited from cashing out, money laundering and other illegal activities through e-commerce platforms, making online transaction behaviors more standardized.

[0042] See also Figure 2 , is a flow chart of a method for identifying false transactions based on logistics data according to another exemplary embodiment of the present invention, comprising the following steps:

[0043] Step 201, obtaining logistics data about the transaction goods in the online transaction, the logistics data including the logistics order number of the transaction goods and the product picture of the transaction goods.

[0044] For the description of step 201 , please refer to the description of step 101 above, which will not be described in detail here.

[0045] Step 202: Determine the first commodity type corresponding to the transaction commodity according to the logistics order number.

[0046] For the description of step 202, please refer to the description of step 102 above, which will not be described in detail here.

[0047] Step 203, determining the image reference features corresponding to the first commodity type in the feature model library, wherein the feature model library stores the image reference features of the transaction commodities whose sales volume reaches a set number within a set time period.

[0048] In one embodiment, a picture feature library can be set up on the server of the e-commerce platform provider to record the sales volume of any product after it goes online. When the sales volume reaches a set value within a set time period, the transaction product can be considered a hot product, and the picture reference features of the hot product and the corresponding product model can be recorded. In one embodiment, by comparing the picture feature information of the transaction product with the picture reference features stored in the picture feature library, the product model of the transaction product can be determined through the product picture, thereby more accurately identifying the transaction product.

[0049] Step 204, calculating the image feature information of the product image.

[0050] In one embodiment, the image feature information of the product image can be realized through image recognition technology. Those skilled in the art can understand that the image feature information of different products is different. For example, the image feature information of a smartphone is different from that of a daily user.

[0051] Step 205, determine whether the image feature information of the product image is consistent with the image reference feature, if consistent, execute step 206, if inconsistent, execute step 207.

[0052] Step 206: If they are consistent, the online transaction is determined to be a real transaction, and the product model of the transaction product is determined based on the image reference features.

[0053] For example, after determining that the first commodity type of the transaction commodity is a smart phone through the logistics order number, the image reference features of the smart phone are searched from the image feature library, and then the commodity model of the transaction commodity can be determined to be "Apple Mobile Phone 6 Plus".

[0054] Step 207: If they are inconsistent, the online transaction is determined to be a false transaction.

[0055] In the above Figure 1A On the basis of the beneficial technical effects of the illustrated embodiment, the embodiment of the present invention identifies whether an online transaction is a false transaction based on a product image, and can identify the product model of the transaction product through the product image, thereby achieving more accurate identification of false online transactions.

[0056] See also Figure 3 , is a flow chart of a method for identifying false transactions based on logistics data according to another exemplary embodiment of the present invention, comprising the following steps:

[0057] Step 301, obtaining logistics data about the transaction goods in the online transaction, the logistics data including the weight of the goods and the logistics order number.

[0058] The description of obtaining logistics data in step 301 can be found in the description of step 101 above, and will not be described in detail here. In one embodiment, the weight of the commodity can be the weight information of the transaction commodity weighed by the logistics company.

[0059] Step 302, determine the weight of the commodity corresponding to the transaction commodity according to the logistics order number, and determine whether the commodity weight is within the normal weight range of the transaction commodity. If the commodity weight is within the normal weight range, execute step 303; if the commodity weight exceeds the normal weight range, execute step 304.

[0060] In one embodiment, according to the above Figure 1B The weight of the transaction commodity is determined in the logistics data shown, and the normal weight range corresponding to the transaction commodity is determined. For example, the commodity type corresponding to the transaction commodity is determined to be "Apple mobile phone" through the logistics order number. If the logistics company weighs the transaction commodity at 484 grams, then 484 is within the normal weight range corresponding to the Apple mobile phone [480-10, 480+10]. Therefore, it can be determined that the online transaction is a real transaction. If the logistics company weighs the transaction commodity at 54 grams, the commodity weight has exceeded the normal weight range.

[0061] Step 303, prompting that the online transaction is a real transaction.

[0062] Step 304, calculating the percentage of the difference between the weight of the commodity exceeding the normal weight range and the normal weight range.

[0063] For example, if the logistics company weighs the transaction commodity and the weight is 54 grams, the weight of the commodity has exceeded the normal weight range. The difference in the commodity weight exceeding the normal weight range is calculated to be 480-54=426 grams, and the percentage of the difference to the normal weight range is 426 / 480=0.8875.

[0064] Step 305 , determining whether the percentage is greater than a preset threshold, if the percentage is greater than the preset threshold, executing step 306 , if the percentage is less than the preset threshold, executing step 307 .

[0065] In one embodiment, the preset threshold can be determined based on the supervision intensity of the e-commerce platform on online trading goods. When the preset threshold is larger, it means that a larger weight error is allowed. When the preset threshold is smaller, it means that a larger weight error is not allowed. Therefore, the embodiment of the present invention does not limit the specific size of the preset threshold.

[0066] Step 306: If the percentage is greater than a preset threshold, it is indicated that the online transaction is a fake transaction.

[0067] Step 307: If the percentage is less than a preset threshold, it is indicated that the online transaction is a suspected fraudulent transaction.

[0068] In this embodiment, the weight of the transaction goods is used to indicate whether the online transaction is a false transaction or a suspected false transaction, so that the supervisors of the e-commerce platform provider can classify the supervision level of online transactions. If it is a real transaction, it will be released; if it is a suspected false transaction, it will be confirmed again manually; if it is a false transaction, the online transaction will be directly delegated to the corresponding punishment department, thereby improving the supervision of online transactions by the e-commerce platform, avoiding online transaction sellers and buyers from agreeing in advance to conduct false transactions, and standardizing online transaction behaviors.

[0069] Through the above-mentioned embodiments, in the process of false transaction identification, the logistics data provided by the logistics company is used as the basis, and data such as product images and logistics voucher information of the transaction products are obtained from the server of the logistics company. The above-mentioned embodiments are used to identify various product transaction behaviors on the e-commerce platform, thereby improving the accuracy of false transaction identification.

[0070] Corresponding to the above-mentioned method for identifying false transactions based on logistics data, this application also proposes Figure 4 The schematic structural diagram of the server according to an exemplary embodiment of the present application is shown in FIG. Figure 4 At the hardware level, the server includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course may also include hardware required for other businesses. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for identifying false transactions based on logistics data at the logical level. Of course, in addition to software implementations, this application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0071] Please refer to Figure 5 In a software implementation, the device for identifying false transactions based on logistics data may include: an acquisition module 51, a first determination module 52, a second determination module 53, and a third determination module 54. Among them:

[0072] The acquisition module 51 is used to acquire the logistics data of the transaction commodity in the online transaction, and the logistics data includes the logistics order number of the transaction commodity and the commodity picture of the transaction commodity;

[0073] A first determining module 52, configured to determine a first commodity type corresponding to the transaction commodity according to the logistics order number obtained by the obtaining module 51;

[0074] A second determining module 53, configured to determine a second commodity type of the transaction commodity according to the commodity image acquired by the acquiring module 51;

[0075] The third determination module 54 is used to determine whether the online transaction is a false transaction according to the first commodity type determined by the first determination module 52 and the second commodity type determined by the second determination module 53 .

[0076] Please refer to Figure 6 , in the above Figure 5 Based on the illustrated embodiment, in one embodiment, the second determining module 53 may include:

[0077] The first calculation unit 531 is used to calculate the image feature information of the product image obtained by the acquisition module 51;

[0078] The first determining unit 532 is configured to determine the second commodity type of the transaction commodity according to the image feature information calculated by the first calculating unit 531 .

[0079] In one embodiment, the third determination module 54 may include:

[0080] A second determination unit 541, configured to determine whether the first commodity type determined by the first determination module 52 matches the second commodity type determined by the second determination module 53;

[0081] The third determination unit 542 is used to determine that the online transaction is a real transaction if the second determination unit 541 determines that there is a match; if the second determination unit 541 determines that there is no match, determine that the online transaction is a false transaction.

[0082] In one embodiment, the device may further include:

[0083] A fourth determination module 55 is used to determine in a feature model library the image reference feature corresponding to the first commodity type determined by the first determination module 52, wherein the feature model library stores image reference features of transaction commodities whose sales volume reaches a set number within a set time period;

[0084] The fifth determination module 56 is used to determine whether the product image is consistent with the image reference feature; if consistent, the product model of the transaction product is determined according to the image reference feature.

[0085] In one embodiment, the logistics data acquired by the acquisition module 51 also includes the weight of the transaction commodity, and the device may further include:

[0086] A sixth determination module 57, configured to determine whether the weight of the commodity corresponding to the transaction commodity is within a normal weight range of the transaction commodity;

[0087] The prompt module 58 is used to determine the weight of the transaction commodity according to the logistics order number, and determine whether the weight of the commodity exceeds the normal weight range determined by the sixth determination module 57 to prompt the authenticity of the online transaction.

[0088] In one embodiment, the prompt module 58 may include:

[0089] The first prompt unit 581 is used to prompt and confirm that the online transaction is a real transaction if the weight of the commodity is within the normal weight range;

[0090] The second calculation unit 582 is used to calculate the percentage of the difference between the weight of the commodity and the normal weight range if the weight of the commodity exceeds the normal weight range;

[0091] The second prompting unit 583 is used to prompt that the online transaction is a false transaction if the percentage calculated by the second calculating unit 582 is greater than a preset threshold;

[0092] The third prompting unit 584 is used to prompt that the online transaction is a suspected false transaction if the percentage calculated by the second calculating unit 582 is less than a preset threshold.

[0093] It can be seen from the above embodiments that in the process of false transaction identification, the logistics data provided by the logistics company is used as the basis, and the weight of the transaction goods and / or the scanned product images and other data are obtained from the server of the logistics company. The above data is used to identify various commodity transaction behaviors on the e-commerce platform. Since the above different logistics data can be used to identify various types of online transactions, the identification of false transactions is more comprehensive, thereby improving the accuracy of false transaction identification.

[0094] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0095] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0096] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for identifying false transactions based on logistics data, the method comprising: Obtaining logistics data about the transaction commodity in the online transaction, the logistics data including the logistics order number of the transaction commodity and the attribute information of the transaction commodity, wherein the logistics data is obtained through a logistics data server; the attribute information of the transaction commodity is a commodity picture of the transaction commodity; Determining a first commodity type corresponding to the transaction commodity according to the logistics order number; Determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity; The determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity includes: Determine a picture reference feature corresponding to the first commodity type in a feature model library, wherein the feature model library stores picture reference features of transaction commodities whose sales volume reaches a set number within a set time period; determine whether the online transaction is a false transaction based on the commodity picture and the picture reference feature.

2. According to the method of claim 1, the step of determining whether the online transaction is a false transaction based on the first commodity type and the attribute information of the transaction commodity comprises: Calculating image feature information of the product image, and determining a second product type of the transaction product according to the image feature information; Determine whether the online transaction is a false transaction according to the first commodity type and the second commodity type.

3. The method according to claim 2, wherein the step of determining whether the online transaction is a false transaction based on the first commodity type and the second commodity type comprises: determining whether the first commodity type matches the second commodity type; If they match, it is determined that the online transaction is a real transaction; If they do not match, it is determined that the online transaction is a false transaction.

4. The method according to claim 1, wherein determining whether the online transaction is a false transaction based on the product image and the image reference feature comprises: Determining whether the product image is consistent with the image reference feature; If they are consistent, it is determined that the online transaction is a real transaction; If they are inconsistent, it is determined that the online transaction is a false transaction.

5. The method according to claim 1, wherein the logistics data further includes the weight of the transaction commodity, and the method further includes: Determining a normal weight range corresponding to the transaction commodity according to the first commodity type; Determine whether the weight of the commodity is within the normal weight range of the transaction commodity; The authenticity of the online transaction is indicated based on whether the weight of the commodity exceeds the normal weight range.

6. The method according to claim 5, wherein the step of prompting the authenticity of the online transaction based on whether the weight of the commodity exceeds the normal weight range comprises: If the weight of the goods is within the normal weight range, it indicates that the online transaction is a real transaction; If the weight of the commodity exceeds the normal weight range, calculating the percentage of the difference between the weight of the commodity exceeding the normal weight range and the normal weight range; If the percentage is greater than a preset threshold, it is indicated that the online transaction is a fake transaction; If the percentage is less than the preset threshold, it is suggested that the online transaction is a suspected false transaction.

7. According to the method of claim 1, the step of determining the first commodity type corresponding to the transaction commodity according to the logistics order number comprises: Querying the commodity transaction information of the online transaction from the server of the e-commerce platform provider according to the logistics order number; The commodity transaction information at least includes the logistics order number of the online transaction and the commodity type of the transaction commodity; The commodity type included in the commodity transaction information is determined as a first commodity type corresponding to the transaction commodity.

8. A device for identifying false transactions based on logistics data, the device comprising: An acquisition module is used to acquire logistics data about transaction commodities in online transactions, wherein the logistics data includes the logistics order number of the transaction commodities and the attribute information of the transaction commodities, wherein the logistics data is acquired through a logistics data server; the attribute information of the transaction commodities is a commodity picture of the transaction commodities; A first commodity type determination module, used to determine the first commodity type corresponding to the transaction commodity according to the logistics order number obtained by the acquisition module; A false transaction determination module, used to determine whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity; The false transaction determination module is specifically used to: determine the image reference feature corresponding to the first commodity type in a feature model library, the feature model library storing the image reference features of transaction commodities whose sales volume reaches a set number within a set time period; determine whether the online transaction is a false transaction based on the commodity picture and the image reference feature.

9. A server, comprising: processor; a memory for storing instructions executable by the processor; Wherein, the processor is used to obtain logistics data about transaction commodities in online transactions, the logistics data including the logistics order number of the transaction commodities and the attribute information of the transaction commodities, wherein the logistics data is obtained through a logistics data server; determining a first commodity type corresponding to the transaction commodity according to the logistics order number; determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity; the attribute information of the transaction commodity is a commodity image of the transaction commodity; determining whether the online transaction is a false transaction according to the first commodity type and the attribute information of the transaction commodity, including: determining a picture reference feature corresponding to the first commodity type in a feature model library, the feature model library storing picture reference features of transaction commodities whose sales volume reaches a set number within a set time period; determining whether the online transaction is a false transaction according to the commodity image and the picture reference feature.

Images