Order clustering and malicious information combating method and apparatus
Order information for an order representing an electronic transaction in the distributed order system for a product or a service is received by one or more processors over a network. A unique order ID and order content based on the received order information are generated. An order vector for the order is created based on the order content. The order is added to an order cluster based on a similarity between the created order vector and a representative order vector corresponding to a representative order in the order cluster. The representative order vector corresponding to the representative order in the order cluster is analyzed to determine if the representative order is malicious. A determination is made as to whether the representative order is malicious. If the representative order is malicious, then malicious order processing is performed on the orders in the order cluster.
1. A computer-implemented method comprising:
receiving, by one or more processors and over a network, order information for an order, wherein an order is an electronic transaction that is associated with a product or a service;
generating, by the one or more processors and based on the received order information, (i) a unique order identifier (ID), and (ii) order content, wherein the unique order identifier is generated based at least on a user identifier and a product or service type;
converting, by the one or more processors, the unique order ID and the order content to a SequenceFile format;
generating, by the one or more processors and based on the converted order content, an order vector for the order;
performing, by the one or more processors, a clustering operating on the order vector to obtain an order clustering result, the order clustering result being in the SequenceFile format;
converting, by the one or more processors, the order clustering result to a text format;
determining, by the one or more processors based on the converted order clustering result,
that that a representative order in an order cluster identified in the order clustering result has been classified as malicious; and
in response to determining that the representative order in the order cluster identified in the order clustering result has been classified as malicious, halting, by one or more processor, processing of the order.
2. The method of claim 1 , wherein determining that the representative order has been classified as malicious comprises determining that remark information included in a representative order vector corresponding to the representative order includes a uniform resource locator (URL) of a website that has been identified as a phishing website.
3. The method of claim 1 , wherein determining that the representative order has been classified as malicious comprises determining that remark information included in a representative order vector corresponding to the representative order includes promotional information that has been identified as malicious.
4. The method of claim 3 , wherein the promotional information comprises promotional text or a promotional image.
5. The method of claim 1 , wherein generating the order vector comprises converting the order content to a term frequency-inverse document frequency (TF-IDF) vector.
6. The method of claim 1 , wherein the order content is generated based on an order title or remark information.
7. A non-transitory, computer-readable medium storing one or more instructions executable by one or more processors to perform operations comprising:
receiving, by the one or more processors and over a network, order information for an order, wherein an order is an electronic transaction that is associated with a product or a service;
generating, by the one or more processors and based on the received order information, (i) a unique order identifier (ID), and (ii) order content, wherein the unique order identifier is generated based at least on a user identifier and a product or service type;
converting, by the one or more processors, the unique order ID and the order content to a SequenceFile format;
generating, by the one or more processors and based on the converted order content, an order vector for the order;
performing, by the one or more processors, a clustering operating on the order vector to obtain an order clustering result, the order clustering result being in the SequenceFile format;
converting, by the one or more processors, the order clustering result to a text format;
determining, by the one or more processors based on the converted order clustering result,
that a representative order in an order cluster identified in the order clustering result has been classified as malicious; and
in response to determining that the representative order in the order cluster identified in the order clustering result has been classified as malicious, halting, by the one or more processor, processing of the order.
8. The medium of claim 7 , wherein determining that the representative order has been classified as malicious comprises determining that remark information included in a representative order vector corresponding to the representative order includes a uniform resource locator (URL) of a website that has been identified as a phishing website.
9. The medium of claim 7 , wherein determining that the representative order has been classified as malicious comprises determining that remark information included in a representative order vector corresponding to the representative order includes promotional information that has been identified as malicious.
10. The medium of claim 9 , wherein the promotional information comprises promotional text or a promotional image.
11. The medium of claim 7 , wherein generating the order vector comprises converting the order content to a term frequency-inverse document frequency (TF-IDF) vector.
12. The medium of claim 7 , wherein the order content is generated based on an order title or remark information.
13. A computer-implemented system comprising:
one or more processors; and
one or more computer memory devices interoperably coupled with the one or more processors and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more processors, perform one or more operations comprising:
receiving, by the one or more processors and over a network, order information for an order, wherein an order is an electronic transaction that is associated with a product or a service;
generating, by the one or more processors and based on the received order information, (i) a unique order identifier (ID), and (ii) order content, wherein the unique order identifier is generated based at least on a user identifier and a product or service type;
converting, by the one or more processors, the unique order ID and the order content to a SequenceFile format;
generating, by the one or more processors and based on the converted order content, an order vector for the order;
performing, by the one or more processors, a clustering operating on the order vector to obtain an order clustering result, the order clustering result being in the SequenceFile format;
converting, by the one or more processors, the order clustering result to a text format;
determining, by the one or more processors based on the converted order clustering result,
that a representative order in an order cluster identified in the order clustering result has been classified as malicious; and
in response to determining that the representative order in the order cluster identified in the order clustering result has been classified as malicious, halting, by the one or more processor, processing of the order.
14. The system of claim 13 , wherein determining that the representative order has been classified as malicious comprises determining that remark information included in a representative order vector corresponding to the representative order includes a uniform resource locator (URL) of a website that has been identified as a phishing website.
15. The system of claim 13 , wherein determining that the representative order has been classified as malicious comprises determining that remark information included in a representative order vector corresponding to the representative order includes promotional information that has been identified as malicious.
16. The system of claim 15 , wherein the promotional information comprises promotional text or a promotional image.
17. The system of claim 13 , wherein generating the order vector comprises converting the order content to a term frequency-inverse document frequency (TF-IDF) vector.
18. The system of claim 13 , wherein the order content is generated based on an order title or remark information.