A method and system for processing orders based on data analysis

Abstract

The present invention provides an order processing method and system based on data analysis, which belongs to the field of data analysis technology, and specifically includes: determining the user's proficiency in using different unmonitorable rules based on rule violation data and rule compliance data in historical data, obtaining unmonitorable rules corresponding to different unmonitorable orders, and determining the user's order violation probability on different platforms in combination with the proficiency in using different unmonitorable rules; when the platform's order violation probability meets the requirements, determining the data analysis and processing sequence of the user's feedback data on different platforms based on the order situation on different platforms, the order violation probability and the rule matching abnormality probability; when there is an abnormality in the platform's feedback data, outputting reminder information to the user, thereby ensuring the user's satisfaction with the order processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular, relates to an order processing method and system based on data analysis. Background Art

[0002] In order to increase the sales of goods, many merchants set up trial links on online platforms. Since trial links are relatively scattered, the construction of a centralized trial platform with a reward mechanism can greatly improve the conversion efficiency of trial links. Specifically, in the invention patent application CN202410269929.8 "A test method and device for issuing reward amounts in a transaction system", the order data is analyzed to screen out test users who meet the test rules, and differentiated reward measures are generated for the test users. However, the existing technical solutions have the following technical problems:

[0003] When users build trial orders through the trial platform, there may be a situation where the trial order does not match the trial rules of the platform, which makes the user unable to obtain rewards. This makes how to obtain abnormal orders in a timely and effective manner and generate targeted reminder information to users a technical problem that needs to be solved urgently.

[0004] In response to the above technical problems, the present invention provides an order processing method and system based on data analysis. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, an order processing method based on data analysis is provided.

[0007] An order processing method based on data analysis, specifically comprising:

[0008] S1 uses the analysis results of the order data to determine the matching of the user's order with the preset reward rules, and based on the matching situation, determines the rule matching abnormality probability of the user on different platforms. When the rule matching abnormality probability of the platform meets the requirements, proceed to the next step;

[0009] S2 determines the order with unmonitorable rules according to the corresponding platform of the order, and treats it as an unmonitorable order, obtains the historical data of the user on the unmonitorable rules, and determines the user's proficiency in using different unmonitorable rules based on the rule violation data and rule compliance data in the historical data;

[0010] S3 obtains the unmonitorable rules corresponding to different unmonitorable orders, and determines the order violation probability of the user on different platforms in combination with the proficiency of using different unmonitorable rules. When the order violation probability of the platform meets the requirements, proceed to the next step;

[0011] S4 determines the data analysis and processing sequence of the user's feedback data on different platforms based on the order status, order violation probability and rule matching abnormality probability on different platforms, and outputs reminder information to the user when there is an abnormality in the feedback data of the platform.

[0012] The beneficial effects of the present invention are:

[0013] 1. The unmonitorable rules corresponding to different unmonitorable orders and the proficiency of using different unmonitorable rules are used to determine the probability of users' order violations on different platforms. This allows for an assessment of users' order violation probabilities from the perspective of their violation usage data on different unmonitorable rules, ensures the screening of platforms with higher order violation probabilities, and lays the foundation for further adopting differentiated data analysis and processing of feedback data on different platforms.

[0014] 2. Based on the order situation, order violation probability and rule matching anomaly probability on different platforms, determine the order analysis and processing order of user feedback data on different platforms, taking into account both the order volume of users on different platforms and the impact of differences in order violation probability and rule matching anomaly probability on different platforms on the probability of order anomalies. This ensures the efficiency of data analysis and processing on platforms with a higher probability of order anomalies, thereby obtaining timely information on order violation situations and improving user satisfaction.

[0015] A further technical solution is that the preset reward rules are determined according to the reward rules set by different platforms and the test-collection platform, specifically including one or more of the following: specific links, link jump time, limit on the number of rewarded users for the same link, limit on the number of rewards for the same type of goods, registration status of the test-collection platform, and browsing time of goods on the test-collection platform.

[0016] A further technical solution is that the preset reward rules are reward rules that can be monitored based on the centralized testing platform.

[0017] A further technical solution is that the matching situation is determined by order data of the user's order under different preset reward rules.

[0018] A further technical solution is that the method for determining the rule matching abnormal probability is:

[0019] Using the order data of the user's order on the platform, determining the rule matching deviation between different orders on the platform and different preset reward rules, and using the rule matching deviation to determine the suspected unmatched rules in the preset reward rules;

[0020] Determining matching coefficients between different orders of the platform and preset reward rules according to the number of suspected unmatched rules, and determining suspected abnormal orders in the platform based on the matching coefficients;

[0021] Based on the proportion of the suspected abnormal orders in the number of orders of the user on the platform, the rule matching abnormality probability of the user on the platform is determined.

[0022] A further technical solution is that when the rule matching deviation between the order and the preset reward rule is not within a preset deviation range, the preset reward rule is determined to be a suspected unmatched rule.

[0023] A further technical solution is that when the matching coefficient between the order and the preset reward rule is less than a preset matching threshold, the order is determined to be a suspected abnormal order.

[0024] A further technical solution is that the method for determining the data analysis and processing order of the user's feedback data on different platforms is:

[0025] Determine the order quantities of different platforms based on the order conditions of different platforms, and determine the basic processing priority values ​​of the user's feedback data on different platforms based on the order quantities;

[0026] The order violation probabilities of different platforms are used to determine the priority value compensation amount under the order violation probabilities, and the rule matching anomaly probabilities of different platforms are used to determine the priority value compensation amount under the rule matching anomaly probabilities;

[0027] The processing priority value of the user's feedback data on different platforms is determined by the basic data analysis cycle, the priority value compensation amount under the order violation probability, and the priority value compensation amount under the rule matching exception probability, and the data analysis processing order of the user's feedback data on different platforms is determined using the processing priority value.

[0028] In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned order processing method based on data analysis.

[0029] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0032] Figure 1 It is a flow chart of an order processing method based on data analysis;

[0033] Figure 2 is a flow chart of a method for determining a rule matching anomaly probability;

[0034] Figure 3 is a flow chart of a method for determining proficiency in the use of unmonitorable rules;

[0035] Figure 4 It is a flow chart of a method for determining the probability of a user's order violation on the platform;

[0036] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0038] When general shopping platforms and trial platforms, namely, trial platforms, settle shopping rebate commissions, they may need to consider a variety of rules, such as specific links, link jump time, limit on the number of rewarded users for the same link, limit on the number of rewards for the same type of goods, registration status of the trial platform, browsing time of goods on the trial platform, etc. Once any rule does not meet the requirements, the shopping rebate commission cannot be settled.

[0039] Therefore, in order to solve the above technical problems, the present application determines the user's proficiency in using different rules by matching the user's historical orders with the rules of a specific shopping platform, and uses the proficiency in use to differentiate the rebate commission settlement data of a specific shopping platform, so that the reason for the rebate failure can be obtained at the first time to avoid user losses. Example

[0040] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, an order processing method based on data analysis is provided, which specifically includes:

[0041] S1 uses the analysis results of the order data to determine the matching of the user's order with the preset reward rules, and based on the matching situation, determines the rule matching abnormality probability of the user on different platforms. When the rule matching abnormality probability of the platform meets the requirements, proceed to the next step;

[0042] Furthermore, the preset reward rules are determined according to the reward rules set by different platforms and the test-collection platform, specifically including one or more of the following: specific links, link jump time, limit on the number of rewarded users for the same link, limit on the number of rewards for the same type of goods, registration status of the test-collection platform, and browsing time of goods on the test-collection platform.

[0043] It should be noted that the preset reward rules are reward rules that can be monitored based on the centralized testing platform.

[0044] It is understandable that the matching situation is determined by the order data of the user's order under different preset reward rules.

[0045] Specifically, it should be noted that Figure 2 As shown, the method for determining the rule matching abnormal probability is:

[0046] Using the order data of the user's order on the platform, determining the rule matching deviation between different orders on the platform and different preset reward rules, and using the rule matching deviation to determine the suspected unmatched rules in the preset reward rules;

[0047] Determining matching coefficients between different orders of the platform and preset reward rules according to the number of suspected unmatched rules, and determining suspected abnormal orders in the platform based on the matching coefficients;

[0048] Based on the proportion of the suspected abnormal orders in the number of orders of the user on the platform, the rule matching abnormality probability of the user on the platform is determined.

[0049] Furthermore, when the rule matching deviation between the order and the preset reward rule is not within a preset deviation range, the preset reward rule is determined to be a suspected unmatched rule.

[0050] It can be understood that when the matching coefficient between the order and the preset reward rule is less than the preset matching threshold, the order is determined to be a suspected abnormal order.

[0051] It should also be noted that the method for determining the rule matching anomaly probability is:

[0052] Using the order data of the user's order on the platform, determining the rule matching deviation between different orders on the platform and different preset reward rules, and using the rule matching deviation to determine the suspected unmatched rules in the preset reward rules;

[0053] Orders that are suspected of not matching the rules are taken as screening abnormal orders, and the probability of rule matching abnormality of the user on the platform is determined by comparing the proportion of the number of screening abnormal orders to the number of orders of the user on the platform.

[0054] It should be noted that the value range of the rule matching exception probability of the user on the platform is between 0 and 1. When the rule matching exception probability of the user on the platform is greater than the preset matching probability threshold, it is determined that the rule matching exception probability of the user on the platform does not meet the requirements.

[0055] It should also be noted that the method for determining the rule matching anomaly probability is:

[0056] Using the order data of the user's orders on the platform, determine the rule matching deviation between different orders on the platform and different preset reward rules, and when it is determined by using the rule matching deviation that there is no suspected unmatched rule for the orders on the platform, use the preset value to determine the rule matching abnormality probability of the user on the platform;

[0057] When it is determined by using the rule matching deviation that there is no suspected unmatched rule in the order on the platform:

[0058] Orders suspected of not matching the rules are used as screening abnormal orders. When the number of screened abnormal orders does not meet the requirement, it is determined that the rule matching abnormality probability of the user on the platform does not meet the requirement;

[0059] When the number of filtered abnormal orders meets the requirements:

[0060] Determine the matching coefficients of different abnormal screening orders and preset reward rules of the platform according to the number of suspected unmatched rules and the rule matching deviation of the suspected unmatched rules; when the average value of the matching coefficients of different abnormal screening orders and preset reward rules does not meet the requirements, it is determined that the rule matching abnormality probability of the user on the platform does not meet the requirements;

[0061] When the average value of the matching coefficients of different abnormal screening orders and the preset reward rules meets the requirements:

[0062] Determine suspected abnormal orders in the platform based on the matching coefficient, and when the number of suspected abnormal orders does not meet the requirement, determine that the rule matching abnormality probability of the user in the platform does not meet the requirement;

[0063] When the number of suspected abnormal orders meets the requirements:

[0064] Based on the number of the suspected abnormal orders and the matching coefficients of different suspected abnormal orders, the rule matching abnormality probability of the user on the platform is determined.

[0065] Furthermore, when the rule matching exception probability of the platform does not meet the requirements, the order data of the users of the platform is obtained through a preset analysis cycle, without the need to obtain the feedback data of the platform in the order of data analysis and processing.

[0066] S2 determines the order with unmonitorable rules according to the corresponding platform of the order, and treats it as an unmonitorable order, obtains the historical data of the user on the unmonitorable rules, and determines the user's proficiency in using different unmonitorable rules based on the rule violation data and rule compliance data in the historical data;

[0067] It is understandable that the unmonitorable rules are rules related only to the data of the platform, including: whether the user is a registered user of the platform, whether the user has browsed the product in advance, whether the user is on the blacklist of the platform, and the number and duration of browsing and retrieving the product in advance.

[0068] Specifically, Figure 3 As shown, the method for determining the proficiency of using the unmonitorable rules is:

[0069] Determine the user's proficiency in using different unmonitorable rules based on the rule violation data and rule compliance data in the historical data;

[0070] Determine the historical orders of the user that have violated the unmonitorable rule according to the rule violation data, and use them as the violating historical orders, and determine the violation usage assessment amount of the user in the unmonitorable rule according to the number of the violating historical orders;

[0071] Determine, based on the rule compliance data, that the user has no historical orders that violate the unmonitorable rule, and use them as rule matching historical orders, and determine the user's correct usage evaluation amount for the unmonitorable rule based on the number of rule matching historical orders;

[0072] The user's proficiency in using the unmonitorable rule is determined based on the user's correct usage evaluation amount and the illegal usage evaluation amount of the unmonitorable rule.

[0073] It can be understood that determining the user's proficiency in using the unmonitorable rule based on the user's correct use evaluation amount and illegal use evaluation amount of the unmonitorable rule specifically includes:

[0074] The average of the correct usage assessment amount and the illegal usage assessment amount is used as the user's proficiency in using the unmonitorable rule.

[0075] S3 obtains the unmonitorable rules corresponding to different unmonitorable orders, and determines the order violation probability of the user on different platforms in combination with the proficiency of using different unmonitorable rules. When the order violation probability of the platform meets the requirements, proceed to the next step;

[0076] Specifically, Figure 4 As shown, the method for determining the probability of violation of the order of the user on the platform is:

[0077] The user's order on the platform is regarded as a platform matching order, and the weight values ​​of different unmonitorable rules are determined based on the proficiency of using different unmonitorable rules corresponding to the platform matching orders, and the violation probability of different platform matching orders is determined by the sum of the weight values ​​of different unmonitorable rules;

[0078] The probability of violation of the user's order on the platform is determined based on the violation probability of matching orders on different platforms.

[0079] Furthermore, when the order violation probability of the platform does not meet the requirements, the order data of the users of the platform is obtained through a preset analysis cycle, and there is no need to obtain the feedback data of the platform according to the data analysis and processing sequence.

[0080] It should also be noted that the method for determining the probability of violation of the order of the user on the platform is:

[0081] Treat the user's orders on the platform as platform matching orders, and determine potential violation risk rules based on the proficiency of using unmonitorable rules;

[0082] The violation probabilities of matching orders on different platforms are determined according to the number of potential violation risk rules, and the violation probabilities of matching orders on different platforms are used to determine the violation probability of the user's order on the platform.

[0083] Furthermore, the potential violation risk rule is an unmonitorable rule whose usage proficiency is less than a preset proficiency.

[0084] It should also be noted that the method for determining the probability of violation of the order of the user on the platform is:

[0085] S21 obtains the number of orders placed by the user on the platform, and determines whether the number of orders placed by the user on the platform is greater than a preset number of orders. If so, proceeds to the next step; if not, proceeds to step S25;

[0086] S22 obtains the unmonitorable rules matched by the platform and uses them as unmonitorable matching rules, and determines whether the number of unmonitorable matching rules of the platform is greater than the preset number of rules. If so, it is determined that the probability of violation of the order of the user on the platform does not meet the requirement. If not, proceed to the next step;

[0087] S23 determines potential violation risk rules according to the proficiency of using different unmonitorable matching rules, and judges whether the number of the potential violation risk rules is greater than the preset number of risk rules. If so, it is determined that the probability of violation of the user's order on the platform does not meet the requirement. If not, proceed to the next step.

[0088] S24 determines the rule usage abnormality probability of the platform according to the use proficiency of different unmonitorable matching rules and the number of unmonitorable matching rules, and judges whether the rule usage abnormality probability of the platform meets the requirements. If so, proceed to the next step; if not, it is determined that the order violation probability of the user on the platform does not meet the requirements;

[0089] S25 determines the weight values ​​of different unmonitorable rules based on the proficiency in using different unmonitorable rules corresponding to platform matching orders, determines the violation probability of different platform matching orders using the sum of the weight values ​​of different unmonitorable rules, and determines the violation probability of the user's order on the platform based on the violation probability of different platform matching orders.

[0090] S4 determines the data analysis and processing sequence of the user's feedback data on different platforms based on the order status, order violation probability and rule matching abnormality probability on different platforms, and outputs reminder information to the user when there is an abnormality in the feedback data of the platform.

[0091] It should be noted that the method for determining the data analysis and processing order of the user's feedback data on different platforms is:

[0092] Determine the order quantities of different platforms based on the order conditions of different platforms, and determine the basic processing priority values ​​of the user's feedback data on different platforms based on the order quantities;

[0093] The order violation probabilities of different platforms are used to determine the priority value compensation amount under the order violation probabilities, and the rule matching anomaly probabilities of different platforms are used to determine the priority value compensation amount under the rule matching anomaly probabilities;

[0094] The processing priority value of the user's feedback data on different platforms is determined by the basic data analysis cycle, the priority value compensation amount under the order violation probability, and the priority value compensation amount under the rule matching exception probability, and the data analysis processing order of the user's feedback data on different platforms is determined using the processing priority value.

[0095] It should also be noted that the method for determining the data analysis and processing order of the user's feedback data on different platforms is:

[0096] S31 determines the order quantity of different platforms based on the order situation of different platforms, and determines the basic processing priority value of the feedback data of the user on different platforms based on the order quantity, and judges whether the basic processing priority value of the user on the platform is greater than the preset priority threshold. If so, the data analysis processing priority of the feedback data of the user on the platform is set to the first level, and the data analysis processing order of the feedback data of the user on the platform is determined by the basic processing priority value of the user on the platform. If not, proceed to the next step;

[0097] S32 determines whether the basic processing priority value of the user on the platform is within a preset priority value range, if so, proceeds to the next step, if not, proceeds to step S35;

[0098] S33 obtains the probability of violation of the order of the user on the platform, and determines whether the probability of violation of the order of the user on the platform is greater than a preset probability threshold. If so, the data analysis and processing priority of the feedback data of the user on the platform is set to the second level, and the data analysis and processing order of the feedback data of the user on the platform is determined according to the probability of violation of the order of the user on the platform. If not, proceed to the next step;

[0099] S34 obtains the rule matching anomaly probability of the user on the platform, and determines whether the rule matching anomaly probability of the user on the platform is greater than a preset probability threshold. If so, the data analysis and processing priority of the feedback data of the user on the platform is set to the second level, and the data analysis and processing order of the feedback data of the user on the platform is determined by the rule matching anomaly probability of the user on the platform. If not, proceed to the next step;

[0100] S35 sets the data analysis and processing priority of the user's feedback data on the platform to the third level, uses the order violation probability of different platforms to determine the priority value compensation amount under the order violation probability, uses the rule matching exception probability of different platforms to determine the priority value compensation amount under the rule matching exception probability, determines the processing priority value of the user's feedback data on different platforms through the basic data analysis cycle, the priority value compensation amount under the order violation probability and the priority value compensation amount under the rule matching exception probability, and uses the processing priority value to determine the data analysis and processing order of the user's feedback data on different platforms. Example

[0101] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, the above-mentioned order processing method based on data analysis is executed.

[0102] The above-mentioned order processing method based on data analysis specifically includes:

[0103] The analysis results of the order data are used to determine the matching of the user's order with the preset reward rules, and based on the matching situation, the rule matching abnormality probability of the user on different platforms is determined. When the rule matching abnormality probability of the platform meets the requirements, proceed to the next step;

[0104] Determine the order with unmonitorable rules according to the corresponding platform of the order, and treat it as an unmonitorable order, obtain the historical data of the user on the unmonitorable rules, and determine the user's proficiency in using different unmonitorable rules based on the rule violation data and rule compliance data in the historical data;

[0105] Determine the historical orders of the user that have violated the unmonitorable rule according to the rule violation data, and use them as the violating historical orders, and determine the violation usage assessment amount of the user in the unmonitorable rule according to the number of the violating historical orders;

[0106] Determine, based on the rule compliance data, that the user has no historical orders that violate the unmonitorable rule, and use them as rule matching historical orders, and determine the user's correct usage evaluation amount for the unmonitorable rule based on the number of rule matching historical orders;

[0107] Determine the user's proficiency in using the unmonitorable rule based on the user's correct usage evaluation amount and illegal usage evaluation amount of the unmonitorable rule;

[0108] Obtaining unmonitorable rules corresponding to different unmonitorable orders, and determining the order violation probability of the user on different platforms in combination with the proficiency of using different unmonitorable rules, and proceeding to the next step when the order violation probability of the platform meets the requirements;

[0109] Determine the order quantity of different platforms based on the order situation of different platforms, and determine the basic processing priority value of the feedback data of the user on different platforms based on the order quantity, use the order violation probability of different platforms to determine the priority value compensation amount under the order violation probability, and use the rule matching abnormality probability of different platforms to determine the priority value compensation amount under the rule matching abnormality probability;

[0110] The processing priority values ​​of the user's feedback data on different platforms are determined by the basic data analysis cycle, the priority value compensation amount under the order violation probability, and the priority value compensation amount under the rule matching exception probability. The data analysis and processing order of the user's feedback data on different platforms is determined by using the processing priority values. When there is an abnormality in the feedback data of the platform, a reminder message is output to the user.

[0111] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0112] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. An order processing method based on data analysis, characterized in that: Specifically include: The analysis results of the order data are used to determine the matching of the user's order with the preset reward rules, and based on the matching situation, the rule matching abnormality probability of the user on different platforms is determined. When the rule matching abnormality probability of the platform meets the requirements, proceed to the next step; Determine the order with unmonitorable rules according to the corresponding platform of the order, and treat it as an unmonitorable order, obtain the historical data of the user on the unmonitorable rules, and determine the user's proficiency in using different unmonitorable rules based on the rule violation data and rule compliance data in the historical data; Obtaining unmonitorable rules corresponding to different unmonitorable orders, and determining the order violation probability of the user on different platforms in combination with the proficiency of using different unmonitorable rules, and proceeding to the next step when the order violation probability of the platform meets the requirements; Based on the order conditions on different platforms, the probability of order violations and the probability of rule matching anomalies, determine the data analysis and processing order of the user's feedback data on different platforms, and output reminder information to the user when there is an anomaly in the feedback data of the platform; The unmonitorable rules are rules related only to the data of the platform, including: whether the user is a registered user of the platform, whether the user has browsed the product before, whether the user is on the blacklist of the platform, and the number and duration of browsing and searching the product before; The method for determining the proficiency of using the unmonitorable rules is: Determine the user's proficiency in using different unmonitorable rules based on the rule violation data and rule compliance data in the historical data; Determine the historical orders of the user that have violated the unmonitorable rule according to the rule violation data, and use them as the violating historical orders, and determine the violation usage assessment amount of the user in the unmonitorable rule according to the number of the violating historical orders; Determine, based on the rule compliance data, that the user has no historical orders that violate the unmonitorable rule, and use them as rule matching historical orders, and determine the user's correct usage evaluation amount for the unmonitorable rule based on the number of rule matching historical orders; Determine the user's proficiency in using the unmonitorable rule based on the user's correct usage evaluation amount and illegal usage evaluation amount of the unmonitorable rule; The method for determining the probability of violation of the order of the user on the platform is: The user's order on the platform is regarded as a platform matching order, and the weight values ​​of different unmonitorable rules are determined based on the proficiency of using different unmonitorable rules corresponding to the platform matching orders, and the violation probability of different platform matching orders is determined by the sum of the weight values ​​of different unmonitorable rules; The probability of violation of the user's order on the platform is determined based on the violation probability of matching orders on different platforms.

2. The order processing method based on data analysis according to claim 1, characterized in that: The preset reward rules are determined according to the reward rules set by different platforms and the test platform, and specifically include one or more of the following: specific links, link jump time, limit on the number of rewarded users for the same link, limit on the number of rewards for the same type of goods, registration status of the test platform, and browsing time of goods on the test platform.

3. The order processing method based on data analysis according to claim 2, characterized in that: The preset reward rules are reward rules that can be monitored based on the centralized testing platform.

4. The order processing method based on data analysis according to claim 1, characterized in that: The method for determining the rule matching anomaly probability is: Using the order data of the user's order on the platform, determining the rule matching deviation between different orders on the platform and different preset reward rules, and using the rule matching deviation to determine the suspected unmatched rules in the preset reward rules; Determining matching coefficients between different orders of the platform and preset reward rules according to the number of suspected unmatched rules, and determining suspected abnormal orders in the platform based on the matching coefficients; Based on the proportion of the suspected abnormal orders in the number of orders of the user on the platform, the rule matching abnormality probability of the user on the platform is determined.

5. The order processing method based on data analysis according to claim 4, characterized in that: When the rule matching deviation amount between the order and the preset reward rule is not within the preset deviation range, the preset reward rule is determined to be a suspected unmatched rule.

6. The order processing method based on data analysis according to claim 1, characterized in that: When the rule matching exception probability of the platform does not meet the requirements, the order data of the users of the platform is obtained through a preset analysis cycle, without the need to obtain the feedback data of the platform in the order of data analysis and processing.

7. The order processing method based on data analysis according to claim 1, characterized in that: When the order violation probability of the platform does not meet the requirements, the order data of the users of the platform is obtained through a preset analysis cycle, without the need to obtain the feedback data of the platform in the order of data analysis and processing.

8. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes an order processing method based on data analysis as described in any one of claims 1 to 7 when running the computer program.

Images