Order exception determination method, apparatus, device, and medium

Abstract

The application discloses an order exception determination method and device, equipment and medium, and relates to the technical field of computers. The method comprises the following steps: acquiring pre-configured transaction characteristics corresponding to each transaction link and to-be-diagnosed transaction data; diagnosing the to-be-diagnosed transaction data based on the transaction characteristics, so as to diagnose an order exception reason corresponding to an abnormal order in the to-be-diagnosed transaction data; determining a target data table corresponding to the transaction type of the to-be-diagnosed transaction data from a preset data warehouse, and sending the order exception reason and order characteristic information corresponding to the abnormal order to the target data table for storage; and when a query request containing target order characteristic information is acquired, querying the target data table by using the target order characteristic information in the query request, so as to obtain a target order exception reason corresponding to the target order characteristic information. Through the above method, the accuracy of the determined order exception reason can be improved, and the cost required for determining the order exception reason can be reduced.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, equipment, and medium for determining order anomalies. Background Technology

[0002] With the development of computer technology, many businesses, systems, and computer programs are becoming increasingly large and complex. When it is necessary to determine which one or more stages of a particular abnormal data error occurred and the detailed cause of the error, existing technologies need to be applied across various business models and numerous stages. This is costly and challenging, and business processes can change at any time, with actual business scenarios differing from pre-designed ideal scenarios. Furthermore, existing technologies, which rely on ideal business scenarios to determine the cause of abnormal data generated in actual business scenarios, are likely to be incompatible. For example, when determining the cause of an order's anomaly, the actual business scenario involves numerous stages and a massive amount of data. The actual order generation scenario may also differ from the ideal one. Therefore, existing technologies for determining the cause of order anomalies are extremely costly, and the accuracy of the determined causes is low.

[0003] In summary, improving the accuracy of identifying the causes of order anomalies and reducing the cost required to do so are problems that need to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method, apparatus, device, and medium for determining order anomalies, which can improve the accuracy of identifying the causes of order anomalies and reduce the cost required for determining the causes of order anomalies. The specific solution is as follows:

[0005] Firstly, this application discloses a method for determining order anomalies, including:

[0006] Obtain the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage;

[0007] Based on the transaction characteristics, the transaction data to be diagnosed is diagnosed to identify the reasons for the abnormal orders in the transaction data to be diagnosed.

[0008] The target data table corresponding to the transaction type of the transaction data to be diagnosed is determined from the preset data warehouse, and the order anomaly cause and the order feature information corresponding to the abnormal order are sent to the target data table for storage.

[0009] When a query request containing target order feature information is received, the target data table is queried using the target order feature information in the query request to obtain the target order anomaly cause corresponding to the target order feature information.

[0010] Optionally, the step of diagnosing the transaction data to be diagnosed based on the transaction characteristics to diagnose the reasons for order anomalies corresponding to abnormal orders in the transaction data to be diagnosed includes:

[0011] Based on the transaction characteristics, and using the Apache Spark computing engine to perform offline diagnosis on the transaction data to be diagnosed, the cause of the abnormal order in the transaction data to be diagnosed is determined.

[0012] Optionally, the step of diagnosing the transaction data to be diagnosed based on the transaction characteristics to diagnose the reasons for order anomalies corresponding to abnormal orders in the transaction data to be diagnosed includes:

[0013] Abnormal transaction data is obtained based on preset matching conditions and the transaction characteristics, and the corresponding abnormal orders are obtained using the abnormal transaction data. Then, the cause of the abnormality of the order corresponding to the abnormal order is diagnosed.

[0014] Optionally, obtaining abnormal transaction data based on preset matching conditions and the transaction characteristics includes:

[0015] The transaction features are matched with the transaction data to be diagnosed based on preset matching conditions, and the transaction data to be diagnosed that does not meet the preset matching conditions are filtered out to obtain abnormal transaction data.

[0016] Optionally, the step of determining the target data table corresponding to the transaction type of the transaction data to be diagnosed from the preset data warehouse, and sending the order anomaly reason and the order feature information corresponding to the anomaly order to the target data table for storage includes:

[0017] Extract the order anomaly cause and the order feature information corresponding to the abnormal order from the ODS table of the preset data warehouse, determine the target data table corresponding to the transaction type of the transaction data to be diagnosed, and then send the order anomaly cause and the order feature information corresponding to the abnormal order to the target data table for storage.

[0018] Create a presentation layer that includes a query request retrieval interface, so that a query request containing target order feature information can be obtained through the query request retrieval interface.

[0019] Optionally, the method for determining order anomalies further includes:

[0020] Determine the mapping relationship between the cause of the order anomaly and the order feature information corresponding to the anomaly order;

[0021] The mapping relationship is used to save the order anomaly cause and the order feature information corresponding to the anomaly order to the ODS table of the preset data warehouse.

[0022] Optionally, the step of querying the target data table using the target order feature information in the query request to obtain the target order anomaly reason corresponding to the target order feature information includes:

[0023] The IData big data platform is used to query the target order anomaly cause corresponding to the target order feature information in the query request in the target data table.

[0024] Secondly, this application discloses an order anomaly determination device, comprising:

[0025] The data acquisition module is used to acquire the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage.

[0026] The anomaly cause diagnosis module is used to diagnose the transaction data to be diagnosed based on the transaction characteristics, so as to diagnose the order anomaly cause corresponding to the abnormal order in the transaction data to be diagnosed;

[0027] The abnormality cause storage module is used to determine the target data table corresponding to the transaction type of the transaction data to be diagnosed from the preset data warehouse, and send the order abnormality cause and the order feature information corresponding to the abnormal order to the target data table for storage.

[0028] The anomaly cause query module is used to query the target data table using the target order feature information in the query request when a query request containing target order feature information is received, so as to obtain the anomaly cause of the target order corresponding to the target order feature information.

[0029] Thirdly, this application discloses an electronic device, including:

[0030] Memory, used to store computer programs;

[0031] A processor is configured to execute the computer program to implement the steps of the aforementioned disclosed method for determining order anomalies.

[0032] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed method for determining order anomalies.

[0033] As can be seen, the process involves acquiring pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage; diagnosing the transaction data based on the transaction characteristics to identify the cause of abnormal orders in the transaction data; determining a target data table from a preset data warehouse that corresponds to the transaction type of the transaction data to be diagnosed, and sending the cause of abnormal orders and the order characteristic information corresponding to the abnormal orders to the target data table for storage; and when a query request containing target order characteristic information is received, querying the target data table using the target order characteristic information in the query request to obtain the cause of abnormality of the target orders corresponding to the target order characteristic information. Therefore, this application diagnoses the transaction data to be diagnosed based on transaction characteristics at each transaction stage, and saves the diagnosed order anomaly reasons and corresponding order characteristic information in the target data table in the preset data warehouse. Therefore, when a query request containing target order characteristic information is obtained, the target data table can be queried using the target order characteristic information in the query request, and then the specific reason for the anomaly of the target order characteristic information in a specific transaction stage can be obtained. There is no need to use complex algorithms to reverse-engineer the order anomaly reasons, which reduces the cost required to determine the order anomaly reasons. Moreover, the determined order anomaly reasons are saved in the actual business scenario, and the accuracy is higher. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0035] Figure 1 The method for determining order anomalies disclosed in this application lacks a flowchart;

[0036] Figure 2 The specific method for determining order anomalies disclosed in this application lacks a flowchart;

[0037] Figure 3 This is a schematic diagram illustrating a specific method for determining the cause of order anomalies disclosed in this application;

[0038] Figure 4 This is a schematic diagram of the structure of an order anomaly determination device disclosed in this application;

[0039] Figure 5 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0040] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0041] With the development of computer technology, many businesses, systems, and computer programs are becoming increasingly large and complex. When it is necessary to determine which one or more stages of a particular abnormal data error occurred and the detailed cause of the error, existing technologies need to be applied across various business models and numerous stages. This is costly and challenging, and business processes can change at any time, with actual business scenarios differing from pre-designed ideal scenarios. Furthermore, existing technologies, which rely on ideal business scenarios to determine the cause of abnormal data generated in actual business scenarios, are likely to be incompatible. For example, when determining the cause of an order's anomaly, the actual business scenario involves numerous stages and a massive amount of data. The actual order generation scenario may also differ from the ideal one. Therefore, existing technologies for determining the cause of order anomalies are extremely costly, and the accuracy of the determined causes is low.

[0042] In summary, improving the accuracy of identifying the causes of order anomalies and reducing the cost required to do so are problems that need to be solved in this field.

[0043] Therefore, this application provides a solution for determining order anomalies, which can improve the accuracy of identifying the causes of order anomalies and reduce the cost required to determine the causes of order anomalies.

[0044] See Figure 1 As shown in the figure, this application discloses a method for determining order anomalies, including:

[0045] Step S11: Obtain the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage.

[0046] In this embodiment, based on the actual business scenario, each corresponding transaction stage is pre-configured, and transaction feature information and transaction data to be diagnosed for each stage are obtained. Since the Apache Spark computing engine is better suited for data mining and machine learning algorithms that require iterative MapReduce, transaction feature information and transaction data to be diagnosed can be obtained through the Apache Spark computing engine. For example, in the actual business scenario of order transactions, the Apache Spark computing engine can be used to pull the data to be diagnosed within a preset time period. This data can include transaction-related data such as order-related information, product-related information, project-related information, and agreement-related information. Then, the Apache Spark computing engine is used to obtain the business integration configuration and strategy configuration. The business integration configuration can be used to determine the businesses that require commission extraction and the billing time. The strategy configuration can include the business charging standard and charging method, etc.

[0047] Step S12: Diagnose the transaction data to be diagnosed based on the transaction characteristics to diagnose the reasons for the abnormal orders in the transaction data to be diagnosed.

[0048] In this embodiment, the step of diagnosing the transaction data to be diagnosed based on the transaction characteristics to diagnose the order anomaly cause corresponding to the abnormal order in the transaction data to be diagnosed includes: based on the transaction characteristics, and using the Apache Spark computing engine to perform offline diagnosis on the transaction data to be diagnosed to diagnose the order anomaly cause corresponding to the abnormal order in the transaction data to be diagnosed.

[0049] In this embodiment, the step of diagnosing the transaction data to be diagnosed based on the transaction features to diagnose the order abnormality cause corresponding to the abnormal order in the transaction data to be diagnosed specifically includes: obtaining abnormal transaction data based on preset matching conditions and the transaction features, obtaining the corresponding abnormal order using the abnormal transaction data, and then diagnosing the order abnormality cause corresponding to the abnormal order.

[0050] In this embodiment, obtaining abnormal transaction data based on preset matching conditions and the transaction features specifically includes: matching the transaction features with the transaction data to be diagnosed based on preset matching conditions, and filtering out the transaction data to be diagnosed that does not meet the preset matching conditions to obtain abnormal transaction data.

[0051] In this embodiment, for example, the transaction features are business integration configuration and strategy configuration. Therefore, based on preset matching conditions, the transaction data to be diagnosed is matched with the business integration configuration. Transaction data that does not meet the preset matching conditions, i.e., transaction data that cannot be matched with the business integration configuration, is selected as the first abnormal transaction data. The corresponding first abnormal order is obtained using the first abnormal transaction data, and then the cause of the first abnormal order is analyzed and diagnosed. The cause of the first abnormal order can be recorded in the ODS table in the preset data warehouse. Based on the preset matching conditions, the transaction data to be diagnosed is matched with the strategy configuration level by level. The matching data is recorded, and the transaction data that does not meet the preset matching conditions, i.e., transaction data that cannot be matched with the strategy configuration, is selected as the second abnormal transaction data. The corresponding second abnormal order is obtained using the second abnormal transaction data, and then the cause of the second abnormal order is analyzed and diagnosed. The cause of the second abnormal order can be recorded in the ODS table in the preset data warehouse.

[0052] Step S13: Determine the target data table corresponding to the transaction type of the transaction data to be diagnosed from the preset data warehouse, and send the order anomaly cause and the order feature information corresponding to the anomaly order to the target data table for storage.

[0053] In this embodiment, it is understood that the reasons for abnormal orders corresponding to each transaction stage are summarized. This can be done by classifying and summarizing based on order type, order quantity, etc., or by summarizing based on the type of abnormal order reason. Furthermore, the corresponding order feature information needs to be processed accordingly during the summarization process so that subsequent queries can be performed based on the order feature information, making it simpler, more convenient, and greatly improving query efficiency.

[0054] Step S14: When a query request containing target order feature information is obtained, the target data table is queried using the target order feature information in the query request to obtain the target order anomaly cause corresponding to the target order feature information.

[0055] In this embodiment, when a query request containing target order feature information is obtained, the IData big data platform can be used to query the order anomaly cause corresponding to the target order feature information. This eliminates the need for a large investment of manpower and time; the order anomaly cause can be analyzed with just one target order feature information.

[0056] As can be seen, the process involves acquiring pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage; diagnosing the transaction data based on the transaction characteristics to identify the cause of abnormal orders in the transaction data; determining a target data table from a preset data warehouse that corresponds to the transaction type of the transaction data to be diagnosed, and sending the cause of abnormal orders and the order characteristic information corresponding to the abnormal orders to the target data table for storage; and when a query request containing target order characteristic information is received, querying the target data table using the target order characteristic information in the query request to obtain the cause of abnormality of the target orders corresponding to the target order characteristic information. Therefore, this application diagnoses the transaction data to be diagnosed based on transaction characteristics at each transaction stage, and saves the diagnosed order anomaly reasons and corresponding order characteristic information in the target data table in the preset data warehouse. Therefore, when a query request containing target order characteristic information is obtained, the target data table can be queried using the target order characteristic information in the query request, and then the specific reason for the anomaly of the target order characteristic information in a specific transaction stage can be obtained. There is no need to use complex algorithms to reverse-engineer the order anomaly reasons, which reduces the cost required to determine the order anomaly reasons. Moreover, the determined order anomaly reasons are saved in the actual business scenario, and the accuracy is higher.

[0057] See Figure 2 As shown in the figure, this application discloses a specific method for determining order anomalies, including:

[0058] Step S21: Obtain the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage.

[0059] Step S22: Diagnose the transaction data to be diagnosed based on the transaction characteristics to diagnose the reasons for the abnormal orders in the transaction data to be diagnosed.

[0060] In this embodiment, for example, the actual business scenario is an order transaction. Order transactions involve various transaction stages. For instance, in the expected fee transaction stage, the first commission amount for each product line of each transaction order in the transaction data to be diagnosed is calculated based on the strategy configuration, and the second commission amount for each transaction order is obtained based on the first commission amount for each product line. Based on the transaction order and the second commission amount, transaction orders for which the second commission amount was not calculated are filtered out. An asynchronous thread script is used to analyze the third order anomaly cause for this transaction order. The third order anomaly cause may be: 1) mismatch in product category or activity tag configuration; 2) incomplete configuration of the charging standard; or 3) incorrect configuration of the fee type. In the reversal transaction stage, reversal order data is obtained, and products in the reversal order data that meet the preset reversal conditions are identified. Then, the reversal amount for these products is calculated to obtain a reversal record. An asynchronous thread is used to analyze whether the reversal amount in the reversal record is normal with the corresponding reversal order data to obtain an abnormal reversal record. A fourth order anomaly cause is generated based on this abnormal reversal record. In the billing transaction stage, transaction orders in the transaction data to be diagnosed are merged based on supplier and date information. For example, transaction orders with the same supplier information are merged to obtain billing orders, and transaction orders with the same date information are also merged to obtain billing orders. Then, transaction orders that cannot be merged are identified as abnormal orders, and the data corresponding to abnormal orders is abnormal transaction data. Based on the abnormal orders, the corresponding fifth order abnormality reason is analyzed. In the payment date information calculation transaction stage, the latest payment date for each billing order is calculated to construct a complete invoice. Then, the current period's complete invoice is generated, and billing orders with incorrect latest payment date calculations are filtered out. The sixth order abnormality reason for billing orders with incorrect latest payment date calculations is analyzed.

[0061] Step S23: Extract the order anomaly cause and the order feature information corresponding to the abnormal order from the ODS table of the preset data warehouse, determine the target data table corresponding to the transaction type of the transaction data to be diagnosed, and then send the order anomaly cause and the order feature information corresponding to the abnormal order to the target data table for storage.

[0062] In this embodiment, the method further includes: determining the mapping relationship between the order anomaly cause and the order feature information corresponding to the abnormal order; and using the mapping relationship to save the order anomaly cause and the order feature information corresponding to the abnormal order to the ODS table of the preset data warehouse.

[0063] Step S24: Create a presentation layer containing a query request retrieval interface, so that a query request containing target order feature information can be obtained through the query request retrieval interface.

[0064] In this embodiment, a presentation layer is created that includes a query request retrieval interface, which provides a presentation layer for users, making it more convenient, faster, and more intuitive for users to query the reasons for order anomalies, thus greatly improving the user experience.

[0065] Step S25: When a query request containing target order feature information is obtained, the IData big data platform is used to query the target data table to find the abnormal reason of the target order corresponding to the target order feature information in the query request.

[0066] In this embodiment, for example Figure 3 The diagram illustrates a specific method for determining the cause of order anomalies. The user (Actor) inputs target order characteristic information, such as the order number, into a web (World Wide Web) interface. Based on the IData big data platform, the system retrieves pre-defined diagnostic points from a pre-built data warehouse, generated using the Apache Spark computing engine based on the data to be diagnosed and transaction characteristics of the target application. This allows the system to identify the corresponding cause of the target order anomaly and display it on the web interface for subsequent processing by the user. The diagnostic points are recorded at each stage of the transaction if an order anomaly is identified. This method of retrieving the cause of the target order anomaly based on its characteristic information significantly improves speed and work efficiency.

[0067] Therefore, this application does not require a large amount of computing resources and is applicable to a variety of business scenarios. It makes the query of the cause of order anomalies reliable, solves the problem of not knowing where to start in querying the cause, greatly improves the speed of determining the cause of the anomaly, is simple to operate, and significantly improves the user experience.

[0068] See Figure 4 As shown in the figure, this application discloses an order anomaly determination device, including:

[0069] The data acquisition module 11 is used to acquire the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage.

[0070] The anomaly cause diagnosis module 12 is used to diagnose the transaction data to be diagnosed based on the transaction characteristics, so as to diagnose the order anomaly cause corresponding to the abnormal order in the transaction data to be diagnosed;

[0071] The anomaly cause storage module 13 is used to determine the target data table corresponding to the transaction type of the transaction data to be diagnosed from the preset data warehouse, and send the order anomaly cause and the order feature information corresponding to the anomaly order to the target data table for storage.

[0072] The anomaly cause query module 14 is used to query the target data table using the target order feature information in the query request when a query request containing target order feature information is obtained, so as to obtain the target order anomaly cause corresponding to the target order feature information.

[0073] As can be seen, the process involves acquiring pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage; diagnosing the transaction data based on the transaction characteristics to identify the cause of abnormal orders in the transaction data; determining a target data table from a preset data warehouse that corresponds to the transaction type of the transaction data to be diagnosed, and sending the cause of abnormal orders and the order characteristic information corresponding to the abnormal orders to the target data table for storage; and when a query request containing target order characteristic information is received, querying the target data table using the target order characteristic information in the query request to obtain the cause of abnormality of the target orders corresponding to the target order characteristic information. Therefore, this application diagnoses the transaction data to be diagnosed based on transaction characteristics at each transaction stage, and saves the diagnosed order anomaly reasons and corresponding order characteristic information in the target data table in the preset data warehouse. Therefore, when a query request containing target order characteristic information is obtained, the target data table can be queried using the target order characteristic information in the query request, and then the specific reason for the anomaly of the target order characteristic information in a specific transaction stage can be obtained. There is no need to use complex algorithms to reverse-engineer the order anomaly reasons, which reduces the cost required to determine the order anomaly reasons. Moreover, the determined order anomaly reasons are saved in the actual business scenario, and the accuracy is higher.

[0074] In some specific embodiments, the anomaly cause diagnosis module 12 includes:

[0075] The first diagnostic unit is used to perform offline diagnostics on the transaction data to be diagnosed based on the transaction characteristics and using the Apache Spark computing engine to diagnose the reasons for the abnormal orders in the transaction data to be diagnosed.

[0076] In some specific embodiments, the anomaly cause diagnosis module 12 includes:

[0077] The second diagnostic unit is used to obtain abnormal transaction data based on preset matching conditions and the transaction characteristics, obtain the corresponding abnormal orders using the abnormal transaction data, and then diagnose the order abnormality cause corresponding to the abnormal order.

[0078] In some specific embodiments, the second diagnostic unit includes:

[0079] An abnormal transaction data filtering unit is used to match the transaction features with the transaction data to be diagnosed based on preset matching conditions, and filter out the transaction data to be diagnosed that does not meet the preset matching conditions, so as to obtain abnormal transaction data.

[0080] In some specific embodiments, the anomaly cause storage module 13 includes:

[0081] The first storage unit is used to extract the order anomaly cause and the order feature information corresponding to the abnormal order from the ODS table of the preset data warehouse, determine the target data table corresponding to the transaction type of the transaction data to be diagnosed, and then send the order anomaly cause and the order feature information corresponding to the abnormal order to the target data table for storage.

[0082] The query request acquisition unit is used to create a presentation layer containing a query request acquisition interface, so as to obtain a query request containing target order feature information through the query request acquisition interface.

[0083] In some specific embodiments, the order anomaly determination device further includes:

[0084] The first storage unit is used to determine the mapping relationship between the order anomaly cause and the order feature information corresponding to the anomaly order; and to use the mapping relationship to save the order anomaly cause and the order feature information corresponding to the anomaly order to the ODS table of the preset data warehouse.

[0085] In some specific embodiments, the anomaly cause query module 14 includes:

[0086] The query unit is used to use the IData big data platform to query the target order anomaly reasons corresponding to the target order feature information in the query request in the target data table.

[0087] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the order anomaly determination method performed by the electronic device as disclosed in any of the foregoing embodiments.

[0088] In this embodiment, the power supply 23 is used to provide operating voltage for various hardware devices on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0089] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0090] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0091] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the order anomaly determination method executed by the electronic device as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0092] Furthermore, embodiments of this application also disclose a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the method steps executed during the order exception determination method disclosed in any of the foregoing embodiments.

[0093] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0094] The above provides a detailed description of the order anomaly determination method, apparatus, device, and medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for determining order anomalies, characterized in that, include: Obtain the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage; Based on the transaction characteristics, the transaction data to be diagnosed is diagnosed to identify the reasons for the abnormal orders in the transaction data to be diagnosed. The target data table corresponding to the transaction type of the transaction data to be diagnosed is determined from the preset data warehouse, and the order anomaly cause and the order feature information corresponding to the abnormal order are sent to the target data table for storage. When a query request containing target order feature information is obtained, the target data table is queried using the target order feature information in the query request to obtain the target order anomaly cause corresponding to the target order feature information; The step of querying the target data table using the target order feature information in the query request to obtain the target order anomaly reason corresponding to the target order feature information includes: Use the IData big data platform to query the target order anomaly reasons in the target data table that correspond to the target order feature information in the query request; The method for determining order anomalies also includes: The Apache Spark computing engine is used to perform offline diagnosis based on the transaction data to be diagnosed in the target program and the transaction characteristics. Diagnostic points are set at each transaction stage. If an abnormal order is diagnosed, the corresponding order abnormality reason is recorded through the diagnostic points and saved to the preset data warehouse. The step of determining the target data table corresponding to the transaction type of the transaction data to be diagnosed from the preset data warehouse, and sending the order anomaly cause and the order feature information corresponding to the anomaly order to the target data table for storage includes: Extract the order anomaly cause and the corresponding order feature information from the ODS table of the preset data warehouse, determine the target data table corresponding to the transaction type of the transaction data to be diagnosed, and then send the order anomaly cause and the corresponding order feature information to the target data table for storage; create a presentation layer containing a query request retrieval interface so that a query request containing the target order feature information can be obtained through the query request retrieval interface.

2. The order anomaly determination method according to claim 1, characterized in that, The step of diagnosing the transaction data to be diagnosed based on the transaction characteristics, in order to diagnose the reasons for the abnormal orders in the transaction data to be diagnosed, includes: Based on the transaction characteristics, and using the Apache Spark computing engine to perform offline diagnosis on the transaction data to be diagnosed, the cause of the abnormal order in the transaction data to be diagnosed is determined.

3. The order anomaly determination method according to claim 1, characterized in that, The step of diagnosing the transaction data to be diagnosed based on the transaction characteristics, in order to diagnose the reasons for the abnormal orders in the transaction data to be diagnosed, includes: Abnormal transaction data is obtained based on preset matching conditions and the transaction characteristics, and the corresponding abnormal orders are obtained using the abnormal transaction data. Then, the cause of the abnormality of the order corresponding to the abnormal order is diagnosed.

4. The order anomaly determination method according to claim 3, characterized in that, The process of obtaining abnormal transaction data based on preset matching conditions and transaction characteristics includes: The transaction features are matched with the transaction data to be diagnosed based on preset matching conditions, and the transaction data to be diagnosed that does not meet the preset matching conditions are filtered out to obtain abnormal transaction data.

5. The method for determining order anomalies according to claim 1, characterized in that, Also includes: Determine the mapping relationship between the cause of the order anomaly and the order feature information corresponding to the anomaly order; The mapping relationship is used to save the order anomaly cause and the order feature information corresponding to the anomaly order to the ODS table of the preset data warehouse.

6. An order anomaly determination device, characterized in that, The steps for implementing the order anomaly determination method as described in any one of claims 1 to 5 include: The data acquisition module is used to acquire the pre-configured transaction characteristics and transaction data to be diagnosed for each transaction stage. The anomaly cause diagnosis module is used to diagnose the transaction data to be diagnosed based on the transaction characteristics, so as to diagnose the order anomaly cause corresponding to the abnormal order in the transaction data to be diagnosed; The anomaly cause storage module is used to determine the target data table corresponding to the transaction type of the transaction data to be diagnosed from the preset data warehouse, and send the order anomaly cause and the order feature information corresponding to the anomaly order to the target data table for storage. The anomaly cause query module is used to query the target data table using the target order feature information in the query request when a query request containing target order feature information is received, so as to obtain the anomaly cause of the target order corresponding to the target order feature information.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the order anomaly determination method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the order anomaly determination method as described in any one of claims 1 to 5.

Images