Data supplementing method, device and equipment and storage medium

Abstract

A data supplementing method, device and equipment and storage medium are related to the technical field of data processing. The method can be applied to various scenes with data supplementing, including but not limited to map, traffic, Internet of Vehicles and the like. The method comprises: obtaining task characteristic information of n time intervals; determining state probabilities corresponding to the n time intervals respectively according to task data volumes of the n time intervals to obtain a first state probability sequence; determining supplementing probability information corresponding to a first time interval located after the n time intervals according to the first state probability sequence and the task characteristic information of the n time intervals; and performing data supplementing on a data calculation task in the first time interval according to the supplementing probability information corresponding to the first time interval. The method realizes automatic detection of whether the data calculation task needs data supplementing, and avoids idle time and processing resources caused by data storage abnormalities of the data calculation task.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of data processing, and in particular, relate to a data supplement recording method and device, equipment and a storage medium. BACKGROUND

[0002] In the execution process of a data computing task, when data loss occurs due to system scheduling, other factors in the data collection process or human factors, etc., large-scale data supplement recording is required.

[0003] The related art provides a data supplement recording method, which can supplement record data in parallel according to a time period. That is, a fixed supplement recording period and supplement recording method are set, and the data computing task is detected and supplemented recorded in parallel.

[0004] However, the above method needs to supplement record data in the same time interval, which is easy to cause congestion in the time interval. SUMMARY

[0005] Embodiments of the present application provide a data supplement recording method, device, equipment and storage medium. The technical solutions provided by the embodiments of the present application are as follows.

[0006] According to an aspect of the embodiments of the present application, a data supplement recording method is provided, which comprises:

[0007] obtaining task characteristic information of n time intervals; wherein the task characteristic information of the i-th time interval in the n time intervals is used to indicate the characteristics of each data computing task in the i-th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n;

[0008] determining the state probability corresponding to each of the n time intervals according to the task data volume of the n time intervals, to obtain a first state probability sequence; wherein the task data volume of the i-th time interval is used to indicate the data volume of each data computing task in the i-th time interval; and the state probability corresponding to the i-th time interval is used to indicate the number of data computing tasks in the i-th time interval that need to be supplemented recorded, and the proportion of the number in the total number of data computing tasks in the i-th time interval;

[0009] determining the supplement recording probability information corresponding to a first time interval after the n time intervals according to the first state probability sequence and the task characteristic information of the n time intervals; wherein the supplement recording probability information corresponding to the first time interval is used to indicate the probability of each data computing task in the first time interval needing to be supplemented recorded;

[0010] According to the supplement probability information corresponding to the first time interval, data supplement is performed on the data calculation task in the first time interval.

[0011] According to an aspect of an embodiment of the present application, a data supplement method is provided, which comprises:

[0012] Receiving supplement confirmation information sent by a server, the supplement confirmation information being used for requesting confirmation of whether to perform data supplement on at least one candidate data calculation task in a first time interval; wherein the at least one candidate data calculation task is determined according to supplement probability information corresponding to the first time interval, and the supplement probability information corresponding to the first time interval is used for indicating the probability of each data calculation task in the first time interval needing data supplement;

[0013] Displaying supplement reminding information, the supplement reminding information being used for displaying supplement prompts for the at least one candidate data calculation task;

[0014] In response to an operation on the supplement reminding information, sending feedback information to the server, the feedback information being used for indicating a target data calculation task needing data supplement, which is determined from the at least one candidate data calculation task.

[0015] According to an aspect of an embodiment of the present application, a data supplement device is provided, which comprises:

[0016] An acquisition module, configured to acquire task characteristic information of n time intervals; wherein the task characteristic information of an i th time interval in the n time intervals is used for indicating the characteristics of each data calculation task in the i th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n;

[0017] A first determination module, configured to determine the state probability corresponding to each of the n time intervals according to the task data volume of the n time intervals, to obtain a first state probability sequence; wherein the task data volume of the i th time interval is used for indicating the data volume of each data calculation task in the i th time interval; and the state probability corresponding to the i th time interval is used for indicating the proportion of the number of data calculation tasks needing data supplement in the i th time interval to the total number of data calculation tasks in the i th time interval.

[0018] A second determination module, configured to determine supplement probability information corresponding to a first time interval located after the n time intervals according to the first state probability sequence and the task characteristic information of the n time intervals; wherein the supplement probability information corresponding to the first time interval is used for indicating the probability of each data calculation task in the first time interval needing data supplement.

[0019] The supplement module is configured to perform data supplement on the data calculation task in the first time interval according to the supplement probability information corresponding to the first time interval.

[0020] According to an aspect of an embodiment of the present application, a data supplement device is provided, and the device comprises:

[0021] The receiving module is configured to receive supplement confirmation information sent by the server, wherein the supplement confirmation information is used to request confirmation of whether to perform data supplement on at least one candidate data calculation task in a first time interval; wherein the at least one candidate data calculation task is determined according to supplement probability information corresponding to the first time interval, and the supplement probability information corresponding to the first time interval is used to indicate a probability of needing to perform data supplement on each data calculation task in the first time interval.

[0022] The display module is configured to display supplement reminder information, wherein the supplement reminder information is used to show a supplement prompt for the at least one candidate data calculation task.

[0023] The sending module is configured to send feedback information to the server in response to an operation on the supplement reminder information, wherein the feedback information is used to indicate a target data calculation task needing to perform data supplement, which is determined from the at least one candidate data calculation task.

[0024] According to an aspect of an embodiment of the present application, a computer device is provided, and the computer device comprises a processor and a memory, wherein the memory stores a computer program, the computer program is loaded and executed by the processor to implement the above-mentioned data supplement method.

[0025] According to an aspect of an embodiment of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, wherein the computer program is loaded and executed by a processor to implement the above-mentioned data supplement method.

[0026] According to an aspect of an embodiment of the present application, a computer program product is provided, and the computer program product comprises a computer program stored in a computer readable storage medium. A processor of a computer device reads the computer program from the computer readable storage medium, and the processor executes the computer program, so that the computer device executes the above-mentioned data supplement method.

[0027] The technical solution provided by the embodiments of the present application can bring the following beneficial effects:

[0028] The task feature information and the first state probability sequence of the data calculation task are calculated through each data of n time intervals, the first time interval corresponding supplement record probability information is determined, and the data calculation task in the first time interval is supplemented according to the first time interval corresponding supplement record probability information. The automatic detection of whether the data calculation task needs data supplement is realized, and the time and processing resources of the time interval where the data calculation task is located are idle due to the data storage exception of the data calculation task. It is not necessary to detect and supplement the data of the data calculation task in the fixed time interval, and congestion is avoided due to too many data calculation tasks needing data supplement in a certain time resource. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0030] Figure 1 is a schematic diagram of a scheme implementation environment provided by an embodiment of the present application;

[0031] Figure 2 is a flowchart of a data supplement method provided by an embodiment of the present application;

[0032] Figure 3 is a schematic diagram of the relationship between the first time interval and n time intervals provided by an embodiment of the present application;

[0033] Figure 4 is a flowchart of a data supplement method provided by another embodiment of the present application;

[0034] Figure 5 is a flowchart of a probability prediction model training method provided by an embodiment of the present application;

[0035] Figure 6 is a schematic diagram of the relationship between the target training sample and m historical time intervals provided by an embodiment of the present application;

[0036] Figure 7 is a flowchart of a data supplement method provided by another embodiment of the present application;

[0037] Figure 8 is a schematic diagram of confirmation reminding information provided by an embodiment of the present application;

[0038] Figure 9 is a block diagram of a data supplement device provided by an embodiment of the present application;

[0039] Figure 10 is a block diagram of a data supplementary recording device provided by another embodiment of the present application;

[0040] Figure 11 is a block diagram of a data supplementary recording device provided by another embodiment of the present application;

[0041] Figure 12 This is a structural block diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0043] Please refer to Figure 1 , which shows a schematic diagram of a solution implementation environment provided by an embodiment of the present application. The solution implementation environment can be implemented as a system architecture for data supplementation. The solution implementation environment may include: a terminal device 100 and a server 200.

[0044] The terminal device 100 includes but is not limited to mobile phones, tablet computers, wearable devices, PCs (Personal Computers), vehicle-mounted terminal devices, intelligent voice interaction devices, smart home appliances, aircraft and other electronic devices. A client that runs a target application can be installed in the terminal device 100. The target application can be a data processing application, such as a data entry application, a data storage application, etc., or other applications that provide data supplementary recording functions, such as game applications, social applications, navigation applications, vehicle-mounted information service applications, etc. This application does not limit this. In addition, this application does not limit the form of the target application, including but not limited to App (Application, application), mini-programs, etc. installed in the terminal device 100, and can also be in the form of a web page.

[0045] The server 200 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The server 200 may be a background server of the target application, used to provide background services for the client of the target application.

[0046] The terminal device 100 and the server 200 can communicate with each other via a network, such as a wired or wireless network.

[0047] The data supplementation method provided in the embodiment of the present application can be performed by a computer device, which refers to an electronic device with data calculation, processing and storage capabilities. Figure 1The terminal device 100 can execute the data supplement method (e.g., a client of a target application installed and running in the terminal device 100 executes the data supplement method), the server 200 can execute the data supplement method, or the terminal device 100 and the server 200 can execute the data supplement method in cooperation. The server 200 can train the probability prediction model, and the trained probability prediction model can be configured in the terminal device 100 to execute the data supplement method.

[0048] The embodiments of the present application can be applied to various scenarios, including but not limited to data supplement, data recovery, and the like. For ease of illustration, in the following method embodiments, only the computer device as the subject of each step of the data supplement method is introduced and described.

[0049] Please refer to Figure 2 which shows a flowchart of a data supplement method provided by an embodiment of the present application. The method can include at least one of the following steps 210-240.

[0050] At step 210, task feature information of n time intervals is obtained; wherein the task feature information of an i-th time interval in the n time intervals is used to indicate the features of each data calculation task in the i-th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n.

[0051] In some embodiments, the task feature information includes at least one of the following: feature information of a log data file corresponding to the data calculation task, feature information of an upstream and downstream associated task of the data calculation task.

[0052] The log data file refers to a data file used to save the task data of the data calculation task. The upstream and downstream associated task refers to a data calculation task that is located in a time interval before the time interval of the data calculation task and / or a time interval after the time interval of the data calculation task, and has an association with the data calculation task.

[0053] In some embodiments, the feature information of the log data file corresponding to the data calculation task includes at least one of the following: collection time, storage time, storage duration, storage completion time, number of independent visitors, click volume, storage volume, and scheduling failure rate of the log data file.

[0054] The collection time of the log data file refers to a time point at which the device collects log data and generates a log data file. The warehousing time refers to a time point at which the data computing task starts data collection. The warehousing duration refers to a duration from the start of data collection of the data computing task to the completion of data collection. The warehousing completion time refers to a time point at which the data computing task completes data collection. The number of independent visitors refers to the number of independent visitors accessing in a time interval of the data computing task. The number of visitors can refer to a device or an IP (Internet Protocol) address. The number of clicks refers to the number of pages browsed by each independent visitor. The storage amount refers to the storage amount of data collected by the data computing task. The scheduling failure rate refers to a probability of scheduling failure of the data computing task in the time interval.

[0055] In some embodiments, the feature information of the upstream and downstream associated tasks of the data computing task includes at least one of a completion time, a scheduling frequency, a start time, an end time, and a scheduling failure rate of the upstream and downstream associated tasks.

[0056] The completion time of the upstream and downstream associated tasks refers to a time point at which the upstream and downstream associated tasks complete data computation. The scheduling frequency refers to a frequency of scheduling the upstream and downstream associated tasks. The start time refers to a time point at which the upstream and downstream associated tasks start data collection. The end time refers to a time point at which the upstream and downstream associated tasks complete data collection. The scheduling failure rate refers to a probability of scheduling failure of the upstream and downstream associated tasks in the time interval.

[0057] In step 220, a state probability corresponding to each of the n time intervals is determined according to the task data amount of the n time intervals, to obtain a first state probability sequence. The task data amount of the i-th time interval is used to indicate the data amount of each data computing task in the i-th time interval. The state probability corresponding to the i-th time interval is used to indicate the number of data computing tasks that need to be data-reconciled in the i-th time interval, and the proportion of the number of data computing tasks that need to be data-reconciled in the total number of data computing tasks in the i-th time interval.

[0058] The task data amount refers to the data amount of task data used for the data computing task, and the task data can be saved in a log data file.

[0059] Exemplarily, the current time interval is denoted as T, the i-th time interval is denoted as T-i+1, and each time interval contains 5 data calculation tasks. The task data amount of the i-th time interval is used to indicate the data amount of each of the 5 data calculation tasks in the T-i+1 time interval. The state probability corresponding to the i-th time interval is used to indicate the number of data calculation tasks that need to be data-reposted in the 5 data calculation tasks, accounting for the proportion of the 5 data calculation tasks. For example, the number of data calculation tasks that need to be data-reposted in the T-i+1 time interval is 3, and the state probability corresponding to the i-th time interval is 60%.

[0060] In some embodiments, for the i-th time interval, the label information of each data calculation task in the i-th time interval is determined according to the task data amount of the i-th time interval; the number of data calculation tasks that need to be data-reposted in the i-th time interval is determined according to the label information of each data calculation task in the i-th time interval, accounting for the proportion of the total number of data calculation tasks in the i-th time interval, to obtain the state probability corresponding to the i-th time interval; and the first state probability sequence is obtained according to the state probabilities corresponding to the n time intervals.

[0061] The label information is used to indicate whether the data calculation task needs to be data-reposted or not. Exemplarily, the label information of "1" indicates that the data calculation task needs to be data-reposted, and the label information of "0" indicates that the data calculation task does not need to be data-reposted.

[0062] Exemplarily, the label information of each data calculation task in the i-th time interval is denoted as {1, 1, 0, 0, 0}, where 1 represents that the data calculation task needs to be data-reposted, and 0 represents that the data calculation task does not need to be data-reposted. Then the state probability corresponding to the i-th time interval can be obtained as 40%.

[0063] Exemplarily, the state probabilities corresponding to the 5 time intervals are 0, 40%, 10%, 0, and 20% respectively, and the first state probability sequence {0, 40%, 10%, 0, 20%} is obtained.

[0064] In some embodiments, for the i-th time interval, the label information of each data calculation task in the i-th time interval is determined according to the task data amount of the i-th time interval and the reference task data amount.

[0065] The reference task data amount refers to the reference data amount of the task data for the data calculation task.

[0066] In some embodiments, the label information of each data calculation task in the i-th time interval is determined according to the size relationship between the task data amount of the i-th time interval and the reference task data amount.

[0067] Exemplarily, for each data computing task in the i-th time interval, if the task data amount of the data computing task in the i-th time interval is less than the reference task data amount of the data computing task, it is determined that the label information of the data computing task is that data supplement is needed.

[0068] In some embodiments, according to the difference ratio between the task data amount of the i-th time interval and the reference task data amount, the label information of each data computing task in the i-th time interval is determined.

[0069] Exemplarily, for each data computing task in the i-th time interval, if the difference between the task data amount of the data computing task in the i-th time interval and the reference task data amount of the data computing task accounts for more than or equal to a first threshold value of the reference task data amount of the data computing task, it is determined that the label information of the data computing task is that data supplement is needed.

[0070] For example, the first threshold value is 5%, and for each data computing task in the i-th time interval, if the difference between the task data amount of the data computing task in the i-th time interval and the reference task data amount of the data computing task accounts for more than or equal to 5% of the reference task data amount of the data computing task, it is determined that the label information of the data computing task is that data supplement is needed. Compared with using the difference method to determine whether the data computing task needs data supplement, using the difference ratio method to determine whether the data computing task needs data supplement can be suitable for data computing tasks of different data amounts, without setting a corresponding difference value according to the data amount of each data computing task.

[0071] In step 230, according to the first state probability sequence and the task feature information of the n time intervals, supplement probability information corresponding to a first time interval located after the n time intervals is determined; wherein the supplement probability information corresponding to the first time interval is used to indicate the probability that each data computing task in the first time interval needs data supplement.

[0072] The first time interval is located after the n time intervals. Exemplarily, the relationship between the first time interval and the n time intervals on the time axis is as shown in Figure 3 , wherein the region between two adjacent short line segments on the time axis t is a time interval, the first time interval 310 is located after the n time intervals 320, and they are adjacent time intervals, that is, there is no other time interval between the first time interval 310 and the n time intervals 320.

[0073] In some embodiments, the probability prediction model is used to determine, according to the first state probability sequence and the task feature information of the n time intervals, the data supplement probability information corresponding to the first time interval after the n time intervals.

[0074] The probability prediction model refers to a neural network model used to process the first state probability sequence and the task feature information of the n time intervals to obtain the data supplement probability information corresponding to the first time interval.

[0075] Optionally, the probability prediction model can be an LSTM (Long Short Term Memory) network, an RNN (Recurrent Neural Network), or a recurrent neural network, which is not limited in the present application.

[0076] At step 240, the data supplement is performed on the data calculation task in the first time interval according to the data supplement probability information corresponding to the first time interval.

[0077] In some embodiments, the data supplement is performed on the data calculation task in need of data supplement according to the probability of data supplement of each data calculation task in the first time interval.

[0078] For example, for each data calculation task in the first time interval, if the data supplement probability of the data calculation task is greater than the second threshold, the data supplement is performed on the data calculation task.

[0079] For example, the second threshold is 0.5, and for each data calculation task in the first time interval, if the data supplement probability of the data calculation task is greater than 0.5, the data supplement is performed on the data calculation task.

[0080] The technical scheme provided by the embodiments of the present application determines the data supplement probability information corresponding to the first time interval through the task feature information of each data calculation task in the n time intervals and the first state probability sequence, and performs the data supplement on the data calculation task in the first time interval according to the data supplement probability information corresponding to the first time interval. The automatic detection of whether the data calculation task needs data supplement is realized, and the time and processing resources of the time interval in which the data calculation task is located are prevented from being idle due to the data storage exception of the data calculation task. The detection and data supplement of the data calculation task in the fixed time interval are not needed, and the congestion of the time resource caused by too many data calculation tasks in need of data supplement is avoided.

[0081] Please refer to Figure 4 which shows a flowchart of the data supplement method provided by an embodiment of the present application. The method can include at least one of the steps 410-490.

[0082] Step 410, obtaining task characteristic information of n time intervals.

[0083] Exemplarily, the n time intervals are denoted as {T-n+1, ···, T}, and the task characteristic information X of the n time intervals {T-n+1, ···, T} is obtained. T denoted as X T ={x T-n+1 , ···, x T}.

[0084] Step 430, for the i-th time interval, determining the label information of each data computing task in the i-th time interval according to the task data amount of the i-th time interval and the reference task data amount.

[0085] In some embodiments, for each data computing task in the i-th time interval, if the task data amount of the data computing task in the i-th time interval satisfies a first condition, the label information of the data computing task is determined as needing data supplement; if the task data amount of the data computing task in the i-th time interval does not satisfy the first condition, the label information of the data computing task is determined as not needing data supplement.

[0086] In some embodiments, the first condition comprises that the task data amount of the data computing task in the i-th time interval is less than the reference task data amount of the data computing task, and the difference between the task data amount of the data computing task in the i-th time interval and the reference task data amount of the data computing task is greater than or equal to a first threshold.

[0087] Exemplarily, the reference task data amount is 100MB, the first threshold is 5%, if the task data amount of the data computing task in the i-th time interval is 94MB, the first condition is satisfied, and the label information of the data computing task is determined as needing data supplement; if the task data amount of the data computing task in the i-th time interval is 101MB, the first condition is not satisfied, and the label information of the data computing task is determined as not needing data supplement.

[0088] In some embodiments, the label information can be represented by one bit. For example, the label information needing data supplement is denoted as 1, and the label information not needing data supplement is denoted as 0.

[0089] Exemplarily, the label information of the n time intervals is denoted as Y={Y T-n+1 , ···, Y T}.

[0090] In some embodiments, before step 430, step 420 is also included, for each data computing task in the i-th time interval, determining the reference task data volume of the data computing task based on the task data volume of the data computing task in at least one reference time interval; wherein the reference time interval is located before the i-th time interval.

[0091] Exemplarily, the reference task data volume of the data computing task is determined based on the average value of the task data volume of the data computing task in at least one reference time interval. For example, the k time intervals before the i-th time interval are taken as k reference time intervals, and the task data volume of the data computing task in the above k reference time intervals is recorded as {a1, ···, a k}, calculate the average value of the task data volume in the above k reference time intervals based on the data (a1+···+a k ) / k, determine the reference task data volume of the data calculation task. For example, the average value of the task data volume of the data calculation task in the above k reference time intervals (a1+···+a k ) / k is determined as the reference task data volume of the data calculation task. k is an integer greater than 0. This application does not limit the value of k. For example, k is n / 2.

[0092] In some embodiments, n / 2 is not an integer, and the value of k can be an integer digit of n / 2, or an integer digit of n / 2 plus 1, and this application does not limit this. For example, if n=9, then n / 2=4.5, and the value of k can be 4 or 5, and this application does not limit this.

[0093] Step 440, based on the label information of each data computing task in the i-th time interval, determine the number of data computing tasks that need to be supplemented in the i-th time interval, and the proportion of the number of data computing tasks in the i-th time interval to the total number of data computing tasks in the i-th time interval, and obtain the state probability corresponding to the i-th time interval.

[0094] In some embodiments, the state probability corresponding to the i-th time interval includes the number of data computing tasks that need to be supplemented in the i-th time interval, the proportion of the total number of data computing tasks in the i-th time interval, and the number of data computing tasks that do not need to be supplemented in the i-th time interval, the proportion of the total number of data computing tasks in the i-th time interval.

[0095] For example, the state probability corresponding to the i-th time interval includes the number of data computing tasks that need to be supplemented in the i-th time interval, and the ratio of the number of data computing tasks in the i-th time interval to the total number of data computing tasks in the i-th time interval, denoted as f T-iand the proportion of the number of data calculation tasks that do not need to be supplemented in the i th time interval to the total number of data calculation tasks in the i th time interval is denoted as 1-f T-i .

[0096] In step 450, a first state probability sequence is obtained according to the state probabilities corresponding to the n time intervals respectively.

[0097] In step 460, according to the first state probability sequence and the task feature information of the n time intervals, the supplement probability information corresponding to the first time interval after the n time intervals is determined.

[0098] In some embodiments, the task feature information of the n time intervals is processed by a probability prediction model to obtain hidden layer feature information of the probability prediction model; and based on the hidden layer feature information and the first state probability sequence, the supplement probability information corresponding to the first time interval is obtained.

[0099] In some embodiments, the probability prediction model is an RNN model. Illustratively, the probability prediction model is a state transition RNN model. For example, the task feature information of the n time intervals is processed by using the following formula.

[0100] h T+1 =σ h (W h X T +U h h T +b h )

[0101] Wherein, h T+1 represents an output vector, which is the hidden layer feature information; σ h is an activation function; X T represents an input vector, which is the task feature information of the n time intervals; W h and U h represent parameter matrices; and b h is a parameter vector.

[0102] For example, the hidden layer feature information and the first state probability sequence are processed by using the following formula to obtain the supplement probability information corresponding to the first time interval.

[0103] P(y T+1 =1|h T+1 ,y t )=f T ·σ y (W y h T+1 +b y )+(1-f T )·σ y (W yh T+1 +b y )

[0104] wherein P represents an output vector, is the supplement recording probability information corresponding to a first time interval, and the first time interval is a T+1th time interval; f T is the number of data calculation tasks that need to be supplemented in the first state probability sequence, and accounts for a proportion of the total number of data calculation tasks in the i th time interval; σ y is an activation function; W y represents a parameter matrix; b y is a parameter vector; 1-f T is the number of data calculation tasks that do not need to be supplemented in the first state probability sequence, and accounts for a proportion of the total number of data calculation tasks in the i th time interval.

[0105] In some embodiments, the activation function can adopt a tanh function, or a ReLU function, or a sigmoid function, which is not limited in the present application. σ h and σ y may adopt the same activation function, or different activation functions, which is not limited in the present application. For example, σ h adopts a tanh function, and σ y adopts a sigmoid function.

[0106] Step 470, determining at least one candidate data calculation task according to the probability that each data calculation task in the first time interval needs to be supplemented.

[0107] The candidate data calculation task refers to a data calculation task that meets the condition of sending the supplement confirmation information.

[0108] In some embodiments, for each data calculation task in the first time interval, if the data calculation task meets a second condition, the data calculation task is determined as the candidate data calculation task.

[0109] In some embodiments, the second condition includes that the probability that the data calculation task needs to be supplemented is greater than a second threshold.

[0110] Exemplarily, the second threshold is 0.5, and for each data calculation task in the first time interval, if the probability that the data calculation task needs to be supplemented is greater than 0.5, the data calculation task is determined as the candidate data calculation task.

[0111] Step 480, sending the supplement confirmation information to the target user equipment, and the supplement confirmation information is used to request to confirm whether to supplement the candidate data calculation task.

[0112] In some embodiments, one piece of the supplement record confirmation information can correspond to one candidate data calculation task, or can correspond to multiple candidate data calculation tasks, which is not limited in the present application. In one example, if five candidate data calculation tasks are determined, five pieces of supplement record confirmation information are sent to the target user equipment, each piece of the supplement record confirmation information corresponding to one candidate data calculation task, and used for requesting confirmation of whether to perform data supplement record on the candidate data calculation task corresponding to the supplement record confirmation information. In another example, if five candidate data calculation tasks are determined, one piece of supplement record confirmation information is sent to the target user equipment, the piece of supplement record confirmation information corresponding to the five candidate data calculation tasks, and used for requesting confirmation of whether to perform data supplement record on the five candidate data calculation tasks.

[0113] In step 490, the target data calculation task that needs to perform data supplement record is determined according to the feedback information for the supplement record confirmation information, and data supplement record is performed on the target data calculation task.

[0114] In some embodiments, one piece of supplement record confirmation information corresponds to one candidate data calculation task, if the feedback information for the supplement record confirmation information is confirmation of supplement record, the candidate data calculation task is taken as the target data calculation task, and data supplement record is performed on the target data calculation task.

[0115] In some embodiments, one piece of supplement record confirmation information corresponds to multiple candidate data calculation tasks, then the target data calculation task that needs to perform data supplement record is determined according to the feedback information for each candidate data calculation task in the feedback information for the supplement record confirmation information, and data supplement record is performed on the target data calculation task.

[0116] Exemplarily, one piece of supplement record confirmation information corresponds to five candidate data calculation tasks, which are R1, R2, R3, R4 and R5 respectively, the feedback information for R1, R2, R3 and R4 in the feedback information is confirmation of supplement record, and the feedback information for R5 is cancellation of supplement record, then R1, R2, R3 and R4 are taken as the target data calculation tasks, and data supplement record is performed on R1, R2, R3 and R4.

[0117] The technical scheme provided by the embodiments of the present application determines the label information of each data calculation task through the task data quantity and the reference task data quantity, determines the first state probability sequence according to the label information, and then obtains the supplement recording probability information corresponding to the first time interval through the probability prediction model according to the first state probability sequence and the task feature information of the n time intervals. The principle of state transition is applied, the time sequence information is considered, and the accuracy of the supplement recording probability information corresponding to the first time interval is ensured. In addition, the supplement recording confirmation information is sent to the target user equipment, the target data calculation task that needs to be supplemented and recorded is determined according to the feedback information of the supplement recording confirmation information, and the accuracy of determining the target data calculation task that needs to be supplemented and recorded is further improved.

[0118] Please refer to Figure 5 which shows a flowchart of a training method of a probability prediction model provided by an embodiment of the present application. The method can include at least one of the following steps 510-530.

[0119] Step 510, obtain the task feature information and the task label information of m historical time intervals; wherein the task feature information of the jth historical time interval in the m historical time intervals is used to indicate the features of each data calculation task in the jth historical time interval; the task label information of the jth historical time interval includes the label information of each data calculation task in the jth historical time interval, and the label information is used to indicate whether the data calculation task needs to be supplemented and recorded or not, m is an integer greater than 1, and j is a positive integer less than or equal to m.

[0120] In some embodiments, the task feature information of the m historical time intervals is obtained, and for the jth time interval, the label information of each data calculation task in the jth time interval is determined according to the task data quantity and the reference task data quantity of the jth time interval. The label information of each data calculation task in the jth time interval is matched with the task feature information of each data calculation task in the jth time interval to determine the task label information of each data calculation task in the jth time interval.

[0121] In some embodiments, the label information of each data calculation task in the jth time interval is matched with the task feature information of each data calculation task in the jth time interval to determine the task label information of each data calculation task in the jth time interval according to the identification information of the data calculation task.

[0122] In some embodiments, the identification information of the data calculation task can include the task ID (Identity Document, identity code) of the data calculation task, or can include the file ID of the log data file corresponding to the data calculation task, which is not limited by the present application.

[0123] In step 520, a training sample set of the probability prediction model is constructed based on the task feature information and the task label information of the m historical time intervals.

[0124] As shown in the example of FIG. 6, the sample data of a target training sample in the training sample set 600 includes the task feature information of the n historical time intervals before the target historical time interval 610 in the m historical time intervals 620. Figure 6

[0125] In step 530, the training sample set is used to train the probability prediction model.

[0126] In some embodiments, the training sample set is divided into a training sample subset and a test sample subset according to a certain proportion, the training sample subset is used to train the probability prediction model, and the test sample subset is used to test the probability prediction model.

[0127] The proportion of the training sample subset and the test sample subset is not limited in the present application. For example, the training sample set is divided into the training sample subset and the test sample subset according to a proportion of 8:2.

[0128] The training samples in the training sample subset can be continuous time intervals or discontinuous time intervals, which are not limited in the present application. For example, 4 / 5 of the training samples in the training sample set are randomly selected to form the training sample subset.

[0129] In some embodiments, the training sample set is used to train the probability prediction model through a loss function. The specific loss function is not limited in the present application.

[0130] It should be noted that the contents not described in detail in the present embodiment can refer to the same concept as the above-described data recording method, and both belong to the same concept, which will not be described herein again.

[0131] The technical scheme provided in the embodiments of the present application trains the probability prediction model by constructing a training sample set, adjusts the parameters of the probability prediction model, and improves the accuracy of the probability prediction model.

[0132] Please refer to Figure 7 ​, which shows a flow chart of a data supplementation method provided by an embodiment of the present application. The method can be executed by a terminal device or by the terminal device and a server interacting. The method can include at least one of the following steps 710 to 730.

[0133] Step 710: Receive the supplementary recording confirmation information sent by the server, where the supplementary recording confirmation information is used to request confirmation of whether to perform data supplementary recording on at least one candidate data computing task within the first time interval; wherein, the at least one candidate data computing task is determined based on the supplementary recording probability information corresponding to the first time interval, and the supplementary recording probability information corresponding to the first time interval is used to indicate the probability that each data computing task within the first time interval needs to perform data supplementary recording.

[0134] Step 720: Display supplementary recording reminder information, where the supplementary recording reminder information is used to display a supplementary recording reminder for at least one candidate data computing task.

[0135] In some embodiments, the supplementary recording reminder information includes at least one of the following: identification information of the candidate data computing task; name information of the candidate data computing task; the time interval to which the candidate data computing task belongs; and the difference ratio between the task data volume of the candidate data computing task and the reference task data volume.

[0136] For example, Figure 8 As shown, the supplementary recording confirmation information 800 includes: the identification information (task ID) 810 of the candidate data calculation task, the name information (task name) 820 of the candidate data calculation task, the time interval (time partition) 830 to which the candidate data calculation task belongs, the difference ratio (data status) 840 between the task data volume of the candidate data calculation task and the reference task data volume, as well as the supplementary recording control 850 and the cancel control 860.

[0137] Step 730: In response to the operation on the supplementary recording reminder information, feedback information is sent to the server, where the feedback information is used to indicate the target data computing task that needs to be supplemented with data from at least one candidate data computing task.

[0138] It should be noted that the content not described in detail in this embodiment can refer to the same concept as the above-mentioned data supplement method. The two belong to the same concept and will not be repeated in this application.

[0139] The technical solution provided in the embodiment of the present application realizes the control and intervention of target data calculation tasks that require data supplementation by displaying supplementary recording reminder information and sending feedback information to the server based on the operation in response to the supplementary recording reminder information, thereby improving the accuracy of confirming target data calculation tasks that require data supplementation.

[0140] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, refer to the method embodiments of the present application.

[0141] Please refer to Figure 9 , which shows a block diagram of a data supplementing apparatus provided by an embodiment of the present application. The apparatus has the functions of implementing the above data supplementing method, which can be implemented by hardware or corresponding software executed by hardware. The apparatus can be a computer device or be arranged in a computer device. The apparatus 900 can include an acquisition module 910, a first determination module 920, a second determination module 930 and a supplementing module 940.

[0142] The acquisition module 910 is configured to acquire task characteristic information of n time intervals. The task characteristic information of an i th time interval in the n time intervals is used to indicate characteristics of each data calculation task in the i th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n.

[0143] The first determination module 920 is configured to determine state probabilities corresponding to the n time intervals respectively according to task data amounts of the n time intervals, to obtain a first state probability sequence. The task data amount of the i th time interval is used to indicate data amounts of each data calculation task in the i th time interval. The state probability corresponding to the i th time interval is used to indicate a proportion of a number of data calculation tasks requiring data supplementing in the i th time interval to a total number of data calculation tasks in the i th time interval.

[0144] The second determination module 930 is configured to determine supplementing probability information corresponding to a first time interval located after the n time intervals according to the first state probability sequence and the task characteristic information of the n time intervals. The supplementing probability information corresponding to the first time interval is used to indicate probabilities of each data calculation task in the first time interval requiring data supplementing.

[0145] The supplementing module 940 is configured to perform data supplementing on data calculation tasks in the first time interval according to the supplementing probability information corresponding to the first time interval.

[0146] In some embodiments, as shown in Figure 10 , the first determination module 920 includes a first determination unit 921, a second determination unit 922 and an obtaining unit 923.

[0147] The first determining unit 921 is configured to determine, for the ith time interval, label information of each data calculation task in the ith time interval according to the task data volume of the ith time interval and the reference task data volume, the label information being used to indicate whether the data calculation task needs data supplement or not.

[0148] The second determining unit 922 is configured to determine, according to the label information of each data calculation task in the ith time interval, a proportion of a quantity of data calculation tasks that need data supplement in the ith time interval to a total quantity of data calculation tasks in the ith time interval, to obtain a state probability corresponding to the ith time interval.

[0149] The obtaining unit 923 is configured to obtain the first state probability sequence according to the state probabilities corresponding to the n time intervals respectively.

[0150] In some embodiments, the first determining unit 921 is configured to, for each data calculation task in the ith time interval, determine the label information of the data calculation task as needing data supplement, if the task data volume of the data calculation task in the ith time interval satisfies a first condition; and determine the label information of the data calculation task as not needing data supplement, if the task data volume of the data calculation task in the ith time interval does not satisfy the first condition; wherein the first condition comprises that the task data volume of the data calculation task in the ith time interval is less than the reference task data volume of the data calculation task, and a difference proportion between the task data volume of the data calculation task in the ith time interval and the reference task data volume of the data calculation task is greater than or equal to a first threshold.

[0151] In some embodiments, as shown in Figure 10 The first determining module 920 further includes a third determining unit 924.

[0152] The third determining unit 924 is configured to, for each data calculation task in the ith time interval, determine the reference task data volume of the data calculation task according to the task data volume of the data calculation task in at least one reference time interval; wherein the reference time interval is located before the ith time interval.

[0153] In some embodiments, the second determining module 930 is configured to process the task feature information of the n time intervals by a probability prediction model to obtain hidden layer feature information of the probability prediction model; and obtain the supplement probability information corresponding to the first time interval based on the hidden layer feature information and the first state probability sequence.

[0154] In some embodiments, the training process of the probability prediction model is as follows: obtaining task feature information and task label information of m historical time intervals; the task feature information of the jth historical time interval in the m historical time intervals is used to indicate the characteristics of each data computing task in the jth historical time interval; the task label information of the jth historical time interval includes the label information of each data computing task in the jth historical time interval, and the label information is used to indicate whether the data computing task needs or does not need data supplement, m is an integer greater than 1, and j is a positive integer less than or equal to m; based on the task feature information and the task label information of the m historical time intervals, a training sample set of the probability prediction model is constructed; wherein the sample data of the target training sample in the training sample set includes the task feature information of the n historical time intervals before the target historical time interval in the m historical time intervals; the label data of the target training sample includes the task label information of the target historical time interval; the training sample set is used to train the probability prediction model.

[0155] In some embodiments, the supplement module 940 is configured to determine at least one candidate data computing task according to the probability of each data computing task in the first time interval needing data supplement, send supplement confirmation information to a target user device, the supplement confirmation information being used to request confirmation of whether to supplement the candidate data computing task, and determine a target data computing task needing data supplement according to feedback information for the supplement confirmation information and supplement the target data computing task.

[0156] In some embodiments, the task feature information includes at least one of the following: feature information of a log data file corresponding to the data computing task, including at least one of the following: collection time, storage time, storage duration, storage completion time, number of independent visitors, click volume, storage volume, and scheduling failure rate of the log data file; feature information of upstream and downstream associated tasks of the data computing task, including at least one of the following: completion time, scheduling frequency, start time, end time, and scheduling failure rate of the upstream and downstream associated tasks.

[0157] The technical scheme provided by the embodiment of the application determines the data supplement probability information corresponding to the first time interval according to the task feature information and the first state probability sequence of each data calculation task in the n time intervals, and performs data supplement on the data calculation task in the first time interval according to the data supplement probability information corresponding to the first time interval. The automatic detection of whether the data calculation task needs data supplement is realized, and the time and processing resources of the time interval in which the data calculation task is located are prevented from being idle due to data storage abnormity of the data calculation task. The data calculation task does not need to be detected and supplemented in a fixed time interval, and congestion in a certain time resource due to too many data calculation tasks that need data supplement is avoided.

[0158] Please refer to Figure 11 which shows a block diagram of a data supplement device provided by an embodiment of the application. The device has the functions of implementing the above-mentioned data supplement method, which can be implemented by hardware or corresponding software executed by hardware. The device can be a computer device or can be arranged in a computer device. The device 1100 can include a receiving module 1110, a display module 1120, and a sending module 1130.

[0159] The receiving module 1110 is configured to receive data supplement confirmation information sent by a server, the data supplement confirmation information being used to request confirmation of whether to perform data supplement on at least one candidate data calculation task in a first time interval; wherein the at least one candidate data calculation task is determined according to data supplement probability information corresponding to the first time interval, and the data supplement probability information corresponding to the first time interval is used to indicate the probability that each data calculation task in the first time interval needs data supplement.

[0160] The display module 1120 is configured to display data supplement reminder information, the data supplement reminder information being used to show a supplement prompt for the at least one candidate data calculation task.

[0161] The sending module 1130 is configured to send feedback information to the server in response to an operation on the data supplement reminder information, the feedback information being used to indicate a target data calculation task that needs data supplement and is determined from the at least one candidate data calculation task.

[0162] In some embodiments, the data supplement reminder information includes at least one of the following: identification information of the candidate data calculation task; name information of the candidate data calculation task; a time interval to which the candidate data calculation task belongs; and a difference ratio between a task data amount of the candidate data calculation task and a reference task data amount.

[0163] The technical scheme provided by the embodiments of the present application displays the supplement recording reminding information, sends feedback information to the server according to the operation on the supplement recording reminding information, and realizes the controllability and the intervention of the target data calculation task that needs to be supplemented, thereby improving the accuracy of confirming the target data calculation task that needs to be supplemented.

[0164] It should be noted that the device provided by the above embodiments is only exemplified by the division of the above functional modules in realizing its functions, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the device and method embodiments provided by the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0165] Please refer to Figure 12 which shows a structural schematic diagram of a computer device provided by an embodiment of the present application. The computer device can be any electronic device with data calculation, processing and storage functions. The computer device can be used to implement the data supplement recording method provided in the above embodiments. Specifically:

[0166] The computer device 1200 includes a central processing unit (such as CPU (Central Processing Unit), GPU (Graphics Processing Unit) and FPGA (Field Programmable Gate Array)) 1201, a system memory 1204 including a RAM (Random-Access Memory) 1202 and a ROM (Read-Only Memory) 1203, and a system bus 1205 connecting the system memory 1204 and the central processing unit 1201. The computer device 1200 also includes a basic input / output system (Input Output System, I / O system) 1206 to help transfer information between various devices in the server, and a mass storage device 1207 for storing an operating system 1213, application programs 1214 and other program modules 1215.

[0167] In some embodiments, the basic input / output system 1206 includes the display 1208 to display information and input devices 1209 such as a mouse, keyboard, etc. for inputting information. In one embodiment, the display 1208 and input devices 1209 are connected to the central processing unit 1201 through input / output controllers 1210 connected to the system bus 1205. The basic input / output system 1206 can also include input / output controllers 1210 for receiving and processing input from a number of other devices, including a keyboard, mouse, or electronic stylus. Similarly, input / output controllers 1210 provide output to a display screen, printer, or other type of output device.

[0168] The mass storage device 1207 is connected to the central processing unit 1201 through a mass storage controller (not shown), which is connected to the system bus 1205. The mass storage device 1207 and its associated computer readable media provide nonvolatile storage for the computer device 1200. That is, the mass storage device 1207 can include a computer readable medium (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0169] Without loss of generality, the computer readable media can include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other solid state memory technology, CD-ROM, DVD (Digital Video Disc), R-DVD (Blu-ray Disc), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. It should be understood by those skilled in the art that computer storage media can not be limited to the above-mentioned several types. The system memory 1204 and the mass storage device 1207 mentioned above can be collectively referred to as memory.

[0170] According to the embodiments of the present application, the computer device 1200 can also run on a remote computer connected to a network, such as the Internet. That is, the computer device 1200 can be connected to a network 1212 through a network interface unit 1211 connected to the system bus 1205, or can be connected to other types of networks or remote computer systems (not shown) using the network interface unit 1211.

[0171] The memory stores a computer program, which is loaded and executed by the processor to implement the above-mentioned data supplement method.

[0172] In an exemplary embodiment, a computer readable storage medium is also provided, which stores a computer program, which is loaded and executed by a processor to implement the above-mentioned data supplement method.

[0173] Optionally, the computer readable storage medium can include ROM (Read-Only Memory), RAM (Random-Access Memory), SSD (Solid State Drives), optical disc, etc. Among them, the random access memory can include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0174] In an exemplary embodiment, a computer program product is also provided, which includes a computer program stored in a computer readable storage medium, and a processor reads and executes the computer program from the computer readable storage medium to implement the above-mentioned data supplement method.

[0175] It should be understood that "multiple" referred to herein means two or more. "And / or", which describes the association relationship of the associated objects, means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents that the associated objects before and after it are in an "or" relationship.

[0176] The above only describes exemplary embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data entry method, characterized by, The method comprises: obtaining task characteristic information of n time intervals; wherein the task characteristic information of an i-th time interval in the n time intervals is used for indicating characteristics of each data calculation task in the i-th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n; determining state probabilities corresponding to the n time intervals respectively according to task data amounts of the n time intervals, to obtain a first state probability sequence; wherein the task data amount of the i-th time interval is used for indicating data amounts of each data calculation task in the i-th time interval; and the state probability corresponding to the i-th time interval is used for indicating a proportion of a number of data calculation tasks needing data re-entry in the i-th time interval to a total number of data calculation tasks in the i-th time interval; determining re-entry probability information corresponding to a first time interval located after the n time intervals according to the first state probability sequence and the task characteristic information of the n time intervals; wherein the re-entry probability information corresponding to the first time interval is used for indicating probabilities of each data calculation task in the first time interval needing data re-entry; performing data re-entry on the data calculation tasks in the first time interval according to the re-entry probability information corresponding to the first time interval.

2. The method of claim 1, wherein, The determining of the state probabilities corresponding to the n time intervals respectively according to the task data amounts of the n time intervals, to obtain the first state probability sequence, comprises: for the i-th time interval, determining label information of each data calculation task in the i-th time interval according to the task data amount of the i-th time interval and a reference task data amount, the label information being used for indicating whether the data calculation task needs data re-entry or not; determining, according to the label information of each data calculation task in the i-th time interval, a proportion of a number of data calculation tasks needing data re-entry in the i-th time interval to a total number of data calculation tasks in the i-th time interval, to obtain the state probability corresponding to the i-th time interval; obtaining the first state probability sequence according to the state probabilities corresponding to the n time intervals respectively.

3. The method of claim 2, wherein, The determining of the label information of each data calculation task in the i-th time interval according to the task data amount of the i-th time interval and the reference task data amount, comprises: for each data calculation task in the i-th time interval, if a task data amount of the data calculation task in the i-th time interval satisfies a first condition, determining that the label information of the data calculation task is data re-entry needed; if the task data amount of the data calculation task in the i-th time interval does not satisfy the first condition, determining that the label information of the data calculation task is data re-entry not needed. The first condition comprises that a task data amount of the data computing task in the i th time interval is less than a reference task data amount of the data computing task, and a difference ratio between the task data amount and the reference task data amount is greater than or equal to a first threshold.

4. The method of claim 2, wherein, The method further comprises: For each data computing task in the i th time interval, determining a reference task data amount of the data computing task according to a task data amount of the data computing task in at least one reference time interval, wherein the reference time interval is located before the i th time interval.

5. The method of claim 1, wherein, The determination of the supplement recording probability information corresponding to the first time interval located after the n time intervals according to the first state probability sequence and the task characteristic information of the n time intervals comprises: processing the task characteristic information of the n time intervals by a probability prediction model to obtain hidden layer characteristic information of the probability prediction model; obtaining the supplement recording probability information corresponding to the first time interval based on the hidden layer characteristic information and the first state probability sequence.

6. The method of claim 5, wherein, The training process of the probability prediction model is as follows: obtaining m historical time interval task characteristic information and task label information; wherein the task characteristic information of the j th historical time interval in the m historical time intervals is used to indicate the characteristics of each data computing task in the j th historical time interval; the task label information of the j th historical time interval comprises the label information of each data computing task in the j th historical time interval, and the label information is used to indicate whether the data computing task needs or does not need data supplement recording, m is an integer greater than 1, and j is a positive integer less than or equal to m; constructing a training sample set of the probability prediction model based on the m historical time interval task characteristic information and the task label information; wherein the sample data of a target training sample in the training sample set comprises the task characteristic information of n historical time intervals located before a target historical time interval in the m historical time intervals; the label data of the target training sample comprises the task label information of the target historical time interval; training the probability prediction model by using the training sample set.

7. The method of claim 1, wherein, The data supplement recording of the data computing task in the first time interval according to the supplement recording probability information corresponding to the first time interval comprises: determining at least one candidate data computing task according to the probability of each data computing task in the first time interval needing data supplement recording; sending supplement recording confirmation information to a target user equipment, wherein the supplement recording confirmation information is used to request confirmation of whether to perform data supplement recording on the candidate data computing task; determining a target data computing task needing data supplement recording according to feedback information for the supplement recording confirmation information, and performing data supplement recording on the target data computing task.

8. The method of claim 1, wherein, The task characteristic information comprises at least one of the following: The feature information of a log data file corresponding to the data computing task includes at least one of collection time, warehousing time, warehousing duration, warehousing completion time, independent visitor quantity, click volume, storage volume, and scheduling failure rate of the log data file; The feature information of an upstream or downstream associated task of the data computing task includes at least one of completion time, scheduling frequency, start time, end time, and scheduling failure rate of the upstream or downstream associated task.

9. A data entry method, characterized by, The method comprises: receiving the server sent supplement record confirmation information, the supplement record confirmation information is used to request to confirm whether to supplement record at least one candidate data computing task in the first time interval; wherein the at least one candidate data computing task is determined according to the supplement record probability information corresponding to the first time interval, the supplement record probability information corresponding to the first time interval is used to indicate the probability that each data computing task in the first time interval needs to be supplemented and recorded, the supplement record probability information is determined based on the first state probability sequence and the task feature information of n time intervals, the task feature information of the i th time interval in the n time intervals is used to indicate the characteristics of each data computing task in the i th time interval, the first state probability sequence includes the state probability corresponding to the n time intervals respectively, the state probability corresponding to the i th time interval is used to indicate the number of data computing tasks that need to be supplemented and recorded in the i th time interval, the proportion of the total number of data computing tasks in the i th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n; displaying supplement record reminding information, the supplement record reminding information is used to show the supplement record prompt for the at least one candidate data computing task; in response to the operation of the supplement record reminding information, the server sends feedback information, the feedback information is used to indicate the target data computing task that needs to be supplemented and recorded from the at least one candidate data computing task.

10. The method of claim 9, wherein, The supplement record reminding information includes at least one of the following: The identification information of the candidate data computing task; The name information of the candidate data computing task; The time interval to which the candidate data computing task belongs; The difference ratio between the task data volume of the candidate data computing task and the reference task data volume.

11. A data entry device, comprising: The device comprises: an acquisition module for acquiring task feature information of n time intervals; wherein the task feature information of the i th time interval in the n time intervals is used to indicate the characteristics of each data computing task in the i th time interval, n is an integer greater than 1, and i is a positive integer less than or equal to n; The first determining module is configured to determine state probabilities corresponding to the n time intervals respectively according to the task data volumes of the n time intervals, to obtain a first state probability sequence; wherein the task data volume of the ith time interval is used to indicate data volumes of respective data calculation tasks in the ith time interval; and the state probability corresponding to the ith time interval is used to indicate a proportion of a number of data calculation tasks that need to be data-reconciled in the ith time interval to a total number of data calculation tasks in the ith time interval. The second determining module is configured to determine reconciliation probability information corresponding to a first time interval located after the n time intervals according to the first state probability sequence and task characteristic information of the n time intervals; wherein the reconciliation probability information corresponding to the first time interval is used to indicate probabilities of respective data calculation tasks in the first time interval needing to be data-reconciled. The reconciliation module is configured to perform data reconciliation on data calculation tasks in the first time interval according to the reconciliation probability information corresponding to the first time interval.

12. A data entry device, comprising: The apparatus comprises: The receiving module is configured to receive reconciliation confirmation information sent by a server, the reconciliation confirmation information being used to request confirmation of whether to perform data reconciliation on at least one candidate data calculation task in a first time interval; wherein the at least one candidate data calculation task is determined according to reconciliation probability information corresponding to the first time interval, the reconciliation probability information corresponding to the first time interval being used to indicate probabilities of respective data calculation tasks in the first time interval needing to be data-reconciled, the reconciliation probability information being determined based on a first state probability sequence and task characteristic information of n time intervals, task characteristic information of an ith time interval in the n time intervals being used to indicate characteristics of respective data calculation tasks in the ith time interval, the first state probability sequence comprising state probabilities corresponding to the n time intervals respectively, the state probability corresponding to the ith time interval being used to indicate a proportion of a number of data calculation tasks that need to be data-reconciled in the ith time interval to a total number of data calculation tasks in the ith time interval, n being an integer greater than 1, and i being a positive integer less than or equal to n; The display module is configured to display reconciliation reminding information, the reconciliation reminding information being used to show reconciliation prompts for the at least one candidate data calculation task; The sending module is configured to send feedback information to the server in response to an operation on the reconciliation reminding information, the feedback information being used to indicate a target data calculation task that needs to be data-reconciled and is determined from the at least one candidate data calculation task.

13. A computer device, comprising: The computer device comprises a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the data reconciliation method according to any one of claims 1 to 8, or to implement the data reconciliation method according to any one of claims 9 to 10.

14. A computer-readable storage medium, characterized in that, The computer program is stored in the computer readable storage medium and is loaded and executed by the processor to implement the data supplementing method according to any one of claims 1 to 8, or to implement the data supplementing method according to any one of claims 9 to 10.

15. A computer program product, characterised in that, The computer program product comprises a computer program stored in a computer readable storage medium, and the processor reads and executes the computer program from the computer readable storage medium to implement the data supplementing method according to any one of claims 1 to 8, or to implement the data supplementing method according to any one of claims 9 to 10.

Images