Data processing method and device

Abstract

The invention discloses a data processing method and device, and relates to the technical field of computers. According to one specific embodiment, the method comprises the steps that an exception prediction result of a current time window is determined according to a trend prediction model, and the trend prediction model is obtained through training according to business exception data of each time window in a plurality of time windows; determining an abnormal actual result of the current time window; and determining an anomaly detection result of the current time window according to the anomaly prediction result and the anomaly actual result. According to the method for processing the order failure caused by the business exception based on the trend prediction model, whether the data is abnormal or not can be judged through real-time exception monitoring, so that the abnormal data can be processed in time when the data is abnormal, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data processing method and device. Background Art

[0002] In the logistics express ordering business, due to business expansion or iteration of system requirements, new scenario services will be added that require data maintenance, and old businesses also need to constantly adjust data. This data has a great impact on the business and may lead to order failures due to errors in business data maintenance.

[0003] In related technologies, business anomaly alarms are implemented by configuring business anomaly keywords or business anomaly value thresholds. However, when the call volume is large, the number of alarms will increase. If the alarms are normal business alarms, the labor cost will increase, and the business anomalies cannot be handled in a timely manner, resulting in a poor user experience. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a method and device for data processing, which implements a method for recovering order failures caused by business anomalies based on a trend prediction model. It can determine whether there are anomalies in the data through real-time anomaly monitoring, so as to realize timely processing of abnormal data when the data is abnormal, thereby improving the user experience.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a data processing method is provided, comprising:

[0006] Determine an anomaly prediction result for the current time window according to a trend prediction model; wherein the trend prediction model is trained based on the business anomaly data of each time window in a plurality of time windows;

[0007] Determine the actual results of the anomaly for the current time window;

[0008] An anomaly detection result for the current time window is determined based on the anomaly prediction result and the anomaly actual result.

[0009] Optionally, before determining the abnormality prediction result of the current time window data according to the trend prediction model, the following steps are included:

[0010] Obtain business exception data for each time window in multiple time windows;

[0011] Determine the number of business anomalies in each time window according to the business anomaly data;

[0012] The trend prediction model is trained based on the number of business anomalies in each time window.

[0013] Optionally, determining the number of business anomalies in each time window according to the business anomaly data includes:

[0014] Cleaning the abnormal business data according to preset rules to obtain cleaned abnormal business data;

[0015] The number of business anomalies is determined based on the cleaned business anomaly data.

[0016] Optionally, performing data cleaning on the business abnormality data according to preset rules includes:

[0017] Delete invalid fields in the business abnormality data and / or delete duplicate values ​​in the business abnormality data.

[0018] Optionally, the trend prediction model is trained based on the number of business anomalies in each time window, including:

[0019] Based on the number of business anomalies in each time window, the number of business anomalies in adjacent data windows is differentially processed;

[0020] The trend prediction model is trained based on the number of business anomalies after differential processing.

[0021] Optionally, determining an anomaly detection result for a current time window according to the anomaly prediction result and the anomaly actual result includes:

[0022] Determining the error between the abnormal prediction result and the actual business result;

[0023] Determining whether the error is within a preset range;

[0024] When the error is within a preset range, it is determined that the abnormality detection result is that abnormal data exists in the current time window.

[0025] Optionally, after determining that the anomaly detection result indicates that abnormal data exists in the current time window, the method further includes:

[0026] Determining a service identifier corresponding to the abnormal data;

[0027] Generate a push message corresponding to the service identifier, and send the push message to the user corresponding to the service identifier.

[0028] According to another aspect of an embodiment of the present invention, there is provided a data processing apparatus, including:

[0029] A first determination module determines an anomaly prediction result of a current time window based on a trend prediction model; wherein the trend prediction model is trained based on business anomaly data of each time window in a plurality of time windows;

[0030] The second determination module determines the actual abnormal result of the current time window;

[0031] The third determining module determines the anomaly detection result of the current time window according to the anomaly prediction result and the anomaly actual result.

[0032] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0033] one or more processors;

[0034] a storage device for storing one or more programs,

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method provided by the present invention.

[0036] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the data processing method provided by the present invention is implemented.

[0037] One embodiment of the above invention has the following advantages or beneficial effects: The data processing method first determines the anomaly prediction result for the current time window based on a trend prediction model, then compares the anomaly prediction result for the current time window with the actual anomaly result to determine the anomaly detection result for the current time window, and then determines whether to perform recovery based on the anomaly detection result. This method can monitor abnormal data in real time and report the anomaly detection results in a timely manner to enable timely processing of abnormal data when the data is abnormal; this method can also address system issues caused by abnormal business configuration, improve user experience, and provide effective protection for two-way customer expansion.

[0038] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are provided for a better understanding of the present invention and are not intended to limit the present invention.

[0040] Figure 1 is a schematic diagram of the main flow of a data processing method according to an embodiment of the present invention;

[0041] Figure 2 is a schematic diagram of the main flow of another data processing method according to an embodiment of the present invention;

[0042] Figure 3 is a schematic diagram of the main flow of another data processing method according to an embodiment of the present invention;

[0043] Figure 4is a schematic diagram of main modules of a data processing apparatus according to an embodiment of the present invention;

[0044] Figure 5 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

[0045] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following description of exemplary embodiments of the present invention is made in conjunction with the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding. These details should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0047] Figure 1 FIG. 1 is a schematic diagram of the main flow of a data processing method according to an embodiment of the present invention. Figure 1 As shown, the data processing method includes the following steps:

[0048] Step S101: determining an anomaly prediction result for the current time window based on a trend prediction model; wherein the trend prediction model is trained based on business anomaly data of each time window in a plurality of time windows;

[0049] Step S102: determining the abnormal actual result of the current time window;

[0050] Step S103: Determine the anomaly detection result of the current time window according to the anomaly prediction result and the anomaly actual result.

[0051] In an embodiment of the present invention, the data processing method can be applied to the logistics industry to detect failed orders caused by business anomalies, so as to achieve the purpose of order recovery. For example: when a collection or delivery site adds vehicles and personnel, thereby expanding the collection and delivery range, the system needs to maintain a larger map coordinate range at the system level to match the collection and delivery range. Maintenance errors may occur due to human factors, such as map coordinate range modification errors, resulting in some orders being unable to be accepted. This will prompt the system to exceed the collection and delivery range, but this error prompt makes it difficult to determine whether the address is beyond coverage during the order operation. Therefore, the data processing method of this solution can solve the problem of order failure due to business anomalies and difficulty in recovering customers.

[0052] In an embodiment of the present invention, a trend prediction model is used to predict the abnormal results of the current time window to obtain an abnormal prediction result, which can be the number of failed orders in the current time window. The trend prediction model is trained based on the business abnormality data of multiple time windows. The trend prediction model can be an ARIMA (Autoregressive Integrated Moving Average) model. The size of the current time window can be a year-on-year sliding time window size or a month-on-month sliding time window size. If the current time window is a year-on-year sliding time window, the corresponding trend prediction model can be trained based on the business data of the year-on-year sliding time window; if the current time window is a month-on-month sliding time window, the corresponding trend prediction model can be trained based on the business abnormality data of the month-on-month sliding time window.

[0053] In an embodiment of the present invention, the anomaly prediction result for the current time window may be the predicted number of business anomalies in the current time window. Determining the anomaly prediction result for the current time window based on a trend prediction model may include: inputting the current time window into the trend prediction model to obtain the anomaly prediction result for the current time window. The actual anomaly result may be the actual number of business anomalies in the current time window. Determining the actual anomaly result for the current time window may include: obtaining business anomaly data for the current time window, performing data cleaning on the business anomaly data according to preset rules, and determining the actual number of abnormal businesses in the current data window based on the cleaned business anomaly data.

[0054] In the embodiment of the present invention, Figure 2 As shown, before determining the abnormal prediction result of the current time window data according to the trend prediction model, the following steps are included:

[0055] Step S201: Acquire business exception data of each time window in multiple time windows;

[0056] Step S202: determining the number of business anomalies in each time window based on the business anomaly data;

[0057] Step S203: According to the number of business anomalies in each time window, a trend prediction model is trained.

[0058] In an embodiment of the present invention, when training a trend prediction model, the business exception data of each time window in multiple time windows is first obtained. The business exception data may include a business identifier and an exception identifier. The business identifier may be a logistics order number, and the exception identifier is used to indicate an exception response value. For example, exception response values ​​0 and -1 represent different types of failures. The exceptions may include that the current area does not support collection, the current time does not support collection, the mailed items are prohibited items and do not support mailing, etc. After obtaining the business exception data of each time window in multiple time windows, the business exception data is stored in a preset data structure. The preset data structure may be in a key-value format, or it may be a linked list or any data structure, so as to facilitate subsequent data cleaning.

[0059] Before obtaining the business anomaly data for each time window, the size of the time window, also known as a sliding window, needs to be determined. The sliding window can include a year-on-year sliding window and a quarter-on-quarter sliding window. The year-on-year sliding window can be segmented based on the number of cycles, grouped according to different sizes. The similarity of the two year-on-year segments in each group can be compared using a shape matching algorithm to obtain a group with the highest similarity within the data set. The size of the slice in this group is used as the size of the year-on-year sliding window. The quarter-on-quarter sliding window size can be determined by calculating the quarter-on-quarter growth rate between two cycles. The quarter-on-quarter growth rate is the percentage of increase or decrease between adjacent cycles. When the quarter-on-quarter growth rate of the current cycle's data volume and the previous cycle's data volume are within a preset range, the cycle can be used as the quarter-on-quarter sliding window size. The business anomaly data for each of the multiple time windows can be business anomaly data for multiple year-on-year sliding windows or business anomaly data for multiple quarter-on-quarter sliding windows.

[0060] In an embodiment of the present invention, after obtaining the business anomaly data of each time window, the amount of business anomaly data of each time window can be determined, such as the number of orders that failed to be placed in each time window, and then model training is performed based on the business anomaly data of each time window to obtain a trend prediction model.

[0061] In an embodiment of the present invention, determining the number of service anomalies in each time window based on service anomaly data includes:

[0062] Clean the business abnormal data according to the preset rules to obtain the cleaned business abnormal data;

[0063] Determine the number of business anomalies based on the cleaned business anomaly data.

[0064] In an embodiment of the present invention, for the business anomaly data in each time window, data cleaning is performed on the business anomaly data using preset rules. This may include deleting invalid fields in the business anomaly data and / or deleting duplicate values ​​in the business anomaly data, wherein invalid fields may be fields and field values ​​that are unrelated to the business anomaly. Duplicate values ​​in the business anomaly data are deleted to avoid the impact of duplicate values ​​on the number of business anomalies. Data cleaning of the business anomaly data using preset rules also includes deleting missing values ​​to avoid the impact of missing values ​​on the business anomaly data.

[0065] In an embodiment of the present invention, data cleaning is performed on the business exception data according to preset rules, and format conversion of the business exception data may also be performed, such as converting the business exception data into a JSON format.

[0066] In an embodiment of the present invention, a trend prediction model is trained based on the number of business anomalies in each time window, including:

[0067] Based on the number of business anomalies in each time window, the number of business anomalies in adjacent data windows is differentially processed;

[0068] According to the number of business anomalies after differential processing, a trend prediction model is trained.

[0069] In an embodiment of the present invention, the business anomaly data of each time window may be time series data, and differential processing may be performed on the time series data to extract a stable trend; model training is performed based on the number of business anomalies after differential processing to obtain a trend prediction model.

[0070] In the embodiment of the present invention, Figure 3 As shown, based on the anomaly prediction result and the actual anomaly result, the anomaly detection result of the current time window is determined, including:

[0071] Step S301: Determine the error between the abnormal prediction result and the actual business result;

[0072] Step S302: Determine whether the error is within a preset range; if not, execute step S303; if so, execute step S304;

[0073] Step S303: determining that the anomaly detection result indicates that abnormal data exists in the current time window;

[0074] Step S304: Determine that the abnormality detection result is that there is no abnormal data in the current time window.

[0075] In an embodiment of the present invention, the anomaly prediction result for the current time window is compared with the actual anomaly result, and the error between the two is calculated. If the error is within a preset range, the data in the current time window is not anomaly-free. If the error is not within the preset range, or is large, the data in the current time window is anomaly-free. The anomaly prediction result and the actual anomaly result for the current time window can be visualized for intuitive analysis. When the anomaly detection result indicates the presence of abnormal data in the current time window, an anomaly detection report is generated, and a notification message is generated based on the anomaly detection report to notify relevant personnel to take action. The preset range can be custom-set.

[0076] In an embodiment of the present invention, when the current time window is a year-on-year sliding time window, the trend prediction model corresponding to the year-on-year sliding time window can be used to obtain the abnormal prediction result corresponding to the year-on-year sliding time window, and then judge whether the abnormal prediction result and the abnormal actual result are within the preset range under the year-on-year sliding time window; when the current time window is a month-on-month sliding time window, the trend prediction model corresponding to the month-on-month sliding time window can be used to obtain the abnormal prediction result corresponding to the month-on-month sliding time window, and then judge whether the abnormal prediction result and the abnormal actual result are within the preset range under the month-on-month sliding time window. If the anomalies under both the year-on-year and month-on-month conditions are within the preset range, it can be determined that the abnormal detection result is that there is no abnormal data in the current time window; otherwise, it can be determined that there is abnormal data in the current time window.

[0077] In an embodiment of the present invention, after determining that the anomaly detection result indicates that abnormal data exists in the current time window, the method further includes:

[0078] Determine the business identifier corresponding to the abnormal data;

[0079] Generate a push message corresponding to the service identifier and send the push message to the user corresponding to the service identifier.

[0080] In an embodiment of the present invention, if there is abnormal data in the current time window, the business identifier corresponding to the abnormal data, such as the logistics order number, is determined, and then a push message corresponding to the business identifier is generated. The push message may include a recovery message QR code, and then the push message is sent to the user corresponding to the business identifier, so that the user can feedback the message by scanning the recovery message QR code; the push message may also include whether exclusive customer service is required to contact. If the user chooses to contact exclusive customer service, the user feedback message and the solution to the exception can be pushed to the customer service, so that the customer service can assist in recovery, such as helping the user place an order or guiding the user to place an order again, etc., thereby achieving user recovery and improving user experience.

[0081] The data processing method of the embodiment of the present invention first determines the abnormal prediction result of the current time window based on the trend prediction model, and then compares the abnormal prediction result of the current time window with the abnormal actual result to determine the abnormal detection result of the current time window, so as to determine whether to perform recovery based on the abnormal detection result. This method can monitor the abnormal data in real time and perform trend algorithm analysis, and can report the abnormal detection results in a timely manner to achieve timely processing of abnormal data. For example, when an order transaction fails due to abnormal business configuration, it can timely recover users and reduce losses. This method supplements system problems caused by abnormal business configuration, can improve user experience, and can provide effective protection for two-way customer expansion.

[0082] According to another aspect of the embodiment of the present invention, Figure 4 As shown, a data processing device 400 is provided, comprising:

[0083] A first determination module 401 determines an anomaly prediction result of a current time window based on a trend prediction model, wherein the trend prediction model is trained based on business anomaly data of each time window in a plurality of time windows;

[0084] The second determination module 402 determines the abnormal actual result of the current time window;

[0085] The third determination module 403 determines the anomaly detection result of the current time window according to the anomaly prediction result and the anomaly actual result.

[0086] In an embodiment of the present invention, the first determination module 401 is also used to: obtain business anomaly data of each time window in multiple time windows before determining the anomaly prediction result of the current time window data according to the trend prediction model; determine the number of business anomalies in each time window according to the business anomaly data; and train a trend prediction model according to the number of business anomalies in each time window.

[0087] In the embodiment of the present invention, the first determining module 401 is further configured to: clean the business anomaly data according to preset rules to obtain cleansed business anomaly data; and determine the number of business anomalies based on the cleansed business anomaly data.

[0088] In the embodiment of the present invention, the first determining module 401 is further configured to delete invalid fields in the business abnormality data and / or delete duplicate values ​​in the business abnormality data.

[0089] In an embodiment of the present invention, the first determination module 401 is further configured to: perform differential processing on the number of business anomalies in adjacent data windows according to the number of business anomalies in each time window; and train a trend prediction model based on the number of business anomalies after differential processing.

[0090] In an embodiment of the present invention, the third determination module 403 is further used to: determine the error between the abnormal prediction result and the actual business result; judge whether the error is within a preset range; if the error is within the preset range, determine that the abnormal detection result is that abnormal data exists in the current time window.

[0091] In an embodiment of the present invention, the third determination module 403 is also used to: after determining that the anomaly detection result is that abnormal data exists in the current time window, determine the business identifier corresponding to the abnormal data; generate a push message corresponding to the business identifier, and send the push message to the user corresponding to the business identifier.

[0092] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method provided by the present invention.

[0093] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the data processing method provided by the present invention is implemented.

[0094] Figure 5 An exemplary system architecture 500 is shown to which the data processing method or data processing apparatus according to the embodiment of the present invention can be applied.

[0095] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0096] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, and 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0097] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0098] Server 505 may be a server that provides various services, such as a backend management server (for example only) that supports shopping websites browsed by users using terminal devices 501, 502, and 503. The backend management server may analyze and process received data such as product information query requests, and feed back processing results (for example, target push information and product information—for example only) to the terminal device.

[0099] It should be noted that the data processing method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the data processing device is generally set in the server 505 .

[0100] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0101] Reference below Figure 6 , which shows a schematic structural diagram of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0102] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the system 600 are also stored in the RAM 603. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0103] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read therefrom can be installed into the storage section 608 as needed.

[0104] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are performed.

[0105] It should be noted that the computer-readable medium described in the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The modules described in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be provided in a processor. For example, they may be described as follows: a processor includes a first determination module, a second determination module, and a third determination module. The names of these modules do not, in some cases, limit the modules themselves. For example, the first determination module may also be described as a "module for determining an abnormality prediction result for the current time window based on a trend prediction model."

[0108] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment, or may exist independently and not be incorporated into the device. The computer-readable medium carries one or more programs. When executed by the device, the device is configured to: determine an anomaly prediction result for the current time window based on a trend prediction model, wherein the trend prediction model is trained based on business anomaly data for each of multiple time windows; determine an actual anomaly result for the current time window; and determine an anomaly detection result for the current time window based on the anomaly prediction result and the actual anomaly result.

[0109] According to the technical solution of the embodiment of the present invention, the data processing method first determines the abnormal prediction result of the current time window based on the trend prediction model, and then compares the abnormal prediction result of the current time window with the abnormal actual result to determine the abnormal detection result of the current time window, so as to determine whether to recover based on the abnormal detection result. This method can monitor the abnormal data in real time and perform trend algorithm analysis, and can report the abnormal detection results in time to achieve timely processing of abnormal data. For example, when an order transaction fails due to abnormal business configuration, it can recover users in time and reduce losses. This method supplements the system problems caused by abnormal business configuration, can improve user experience, and can provide effective protection for two-way expansion of customers.

[0110] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A data processing method, characterized in that: include: Determine an anomaly prediction result for the current time window according to a trend prediction model; wherein the trend prediction model is trained based on the business anomaly data of each time window in a plurality of time windows; Determining an abnormal actual result for the current time window; An anomaly detection result for the current time window is determined based on the anomaly prediction result and the anomaly actual result.

2. The method according to claim 1, characterized in that Before determining the abnormal prediction results of the current time window data based on the trend prediction model, the following steps are included: Obtain business exception data for each time window in multiple time windows; Determine the number of business anomalies in each time window according to the business anomaly data; The trend prediction model is trained based on the number of business anomalies in each time window.

3. The method according to claim 2, characterized in that Determining the number of business anomalies in each time window according to the business anomaly data includes: Cleaning the abnormal business data according to preset rules to obtain cleaned abnormal business data; The number of business anomalies is determined based on the cleaned business anomaly data.

4. The method according to claim 3, characterized in that Clean the abnormal business data according to preset rules, including: Delete invalid fields in the business abnormality data and / or delete duplicate values ​​in the business abnormality data.

5. The method according to claim 3, characterized in that The trend prediction model is trained based on the number of business anomalies in each time window, including: Based on the number of business anomalies in each time window, the number of business anomalies in adjacent data windows is differentially processed; The trend prediction model is trained based on the number of business anomalies after differential processing.

6. The method according to claim 1, characterized in that Determining an anomaly detection result for the current time window according to the anomaly prediction result and the anomaly actual result includes: Determining the error between the abnormal prediction result and the actual business result; Determining whether the error is within a preset range; When the error is within a preset range, it is determined that the abnormality detection result is that abnormal data exists in the current time window.

7. The method according to claim 1, characterized in that After determining that the anomaly detection result indicates that abnormal data exists in the current time window, the method further includes: Determining a service identifier corresponding to the abnormal data; Generate a push message corresponding to the service identifier, and send the push message to the user corresponding to the service identifier.

8. A data processing device, characterized in that: include: A first determination module determines an anomaly prediction result of a current time window based on a trend prediction model; wherein the trend prediction model is trained based on business anomaly data of each time window in a plurality of time windows; A second determination module determines the abnormal actual result of the current time window; The third determining module determines the anomaly detection result of the current time window according to the anomaly prediction result and the anomaly actual result.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images