A method and device for determining target event data

Abstract

The present application relates to a method and device for determining target time data, wherein the method comprises: obtaining first event data of the target event in the first sub-time period within a reference time period; determining third event data of the target event in the second sub-time period based on second event data of a similar event of the target event in the second sub-time period within the reference time period, and determining the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period; determining target event data of the target event in the target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period. The present application solves the technical problem of low accuracy in predicting business trends based on historical event data.

Description

Technical Field

[0001] The present application relates to the field of data mining research, and in particular to a method and device for determining target event data. Background Art

[0002] With the development of the Internet, more and more businesses can be realized through the network. In many business scenarios, it is necessary to accumulate and analyze the business operations of users in order to predict and predict the future business tendencies of users. For example, the click-through rate of an advertisement in a future time period can be predicted based on the user's browsing of an advertisement. Related technologies predict the user's business tendencies through the deep learning method of time series. However, in actual use, some data will be missing, resulting in discontinuous time series data, which will lead to inaccurate prediction data.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The present application provides a method and device for determining target event data, so as to at least solve the technical problem of low accuracy in predicting business trends based on historical event data in related technologies.

[0005] According to one aspect of an embodiment of the present application, a method for determining target event data is provided, comprising: acquiring first event data of a first sub-time period of the target event within a reference time period; determining third event data of the target event in a second sub-time period of the reference time period based on second event data of a similar event of the target event in the second sub-time period of the reference time period, and determining the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period; determining target event data of the target event within a target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period.

[0006] Optionally, determining the third event data of the target event in the second sub-time period based on the second event data of the similar event of the target event in the second sub-time period within the reference time period includes: performing targeted processing on the second event data according to a predetermined rule to obtain processed fourth event data; and determining the fourth event data as the third event data of the target event in the second sub-time period.

[0007] Optionally, performing the target processing on the second event data according to the predetermined rule to obtain the processed fourth event data includes: determining the event data ratio between the target event and the similar event in the first sub-time period; performing the target processing on the second event data based on the event data ratio to obtain the processed fourth event data, wherein the ratio of the second event data to the fourth event data is equal to the event data ratio.

[0008] Optionally, performing the target processing on the second event data according to the predetermined rule to obtain the fourth event data includes: determining each target sub-timestamp of the second sub-time period; confirming the first timestamp event data of the similar event within each target sub-timestamp, wherein the second event data includes the first timestamp event data; performing the target processing on the first timestamp event data according to the predetermined rule to obtain the corresponding second timestamp event data of the target event within each target sub-timestamp, wherein the fourth event data includes the second timestamp event data.

[0009] Optionally, based on the second event data of the second sub-time period within the reference time period of the similar event of the target event, it is determined that the target event is before the third event data of the second sub-time period, and the method also includes: obtaining the target event feature of the target event; determining the similar event with the greatest similarity to the target event feature in an event database, wherein the event database stores event data and event features of each event in each historical time period.

[0010] Optionally, obtaining the target event characteristics of the target event includes: obtaining initial attribute information of multiple dimensions of the target event; and determining the target event characteristics of the target event based on the multiple initial attribute information.

[0011] Optionally, determining the target event characteristics of the target event based on multiple initial attribute information includes: normalizing each initial attribute information to obtain target attribute information; and determining the target event characteristics of the target event based on the target attribute information of each dimension and corresponding weight information.

[0012] According to another aspect of an embodiment of the present application, a device for determining target event data is also provided, including: a first acquisition module, used to acquire first event data of the target event in a first sub-time period within a reference time period; a first determination module, used to determine third event data of the target event in a second sub-time period within the reference time period based on second event data of a similar event of the target event in a second sub-time period within the reference time period, and determine the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period; a second determination module, used to determine the target event data of the target event within a target time period based on the reference event data, wherein the start time of the target time period is later than the end time of the reference time period.

[0013] According to another aspect of an embodiment of the present application, a storage medium is further provided, which includes a stored program, and the above method is executed when the program is run.

[0014] According to another aspect of an embodiment of the present application, an electronic device is further provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above method through the computer program.

[0015] In an embodiment of the present application, the method adopts the method of obtaining first event data of a first sub-time period of the target event within a reference time period; determining third event data of the target event in the second sub-time period based on second event data of a similar event of the target event in the second sub-time period within the reference time period, and determining the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period; determining target event data of the target event in the target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period, by obtaining second event data of a similar event of the target event in the second sub-time period, and determining the target event in the second sub-time period according to the second event data of the similar event. The third event data of the target event in the first sub-time period within the reference time period is obtained, thereby determining the continuous reference event data of the target event in the reference time period according to the first event data of the target event in the first sub-time period within the reference time period and the third event data of the target event in the second sub-time period, and determining the target event data of the target event in the future target time period according to the reference event data, thereby achieving the purpose of determining the third event data of the target event in the second sub-time period according to the second data of a similar event in the second sub-time period, instead of ignoring or randomly assigning values ​​to discontinuous data in the related art, thereby achieving the technical effect of improving the accuracy of predicting business trends based on historical event data, and further solving the technical problem of low accuracy in predicting business trends based on historical event data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 is a schematic diagram of a hardware environment of a method for determining target event data according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of an optional method for determining target event data according to an embodiment of the present application;

[0020] Figure 3 is an optional event data prediction flow chart according to an embodiment of the present application;

[0021] Figure 4is a schematic diagram of an optional device for determining target event data according to an embodiment of the present application;

[0022] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to one aspect of an embodiment of the present application, a method embodiment for determining target event data is provided.

[0026] Optionally, in this embodiment, the above target event data determination method can be applied to Figure 1 The hardware environment shown is composed of a terminal 101 and a server 103. Figure 1 is a schematic diagram of the hardware environment of the method for determining target event data according to an embodiment of the present application, such as Figure 1As shown, server 103 is connected to terminal 101 via a network, and can be used to provide services for the terminal or the client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for server 103. The above network includes but is not limited to: wide area network, metropolitan area network or local area network, and terminal 101 is not limited to PC, mobile phone, tablet computer, etc. The method for determining the target event data of the embodiment of the present application can be executed by server 103, or by terminal 101, or by server 103 and terminal 101. Among them, the method for determining the target event data of the embodiment of the present application executed by terminal 101 can also be executed by the client installed thereon.

[0027] Figure 2 is a flowchart of an optional method for determining target event data according to an embodiment of the present application. Figure 2 As shown, the method may include the following steps:

[0028] Step S202, obtaining first event data of the target event in the first sub-time period within the reference time period;

[0029] Step S204, determining third event data of the target event in the second sub-time period within the reference time period based on second event data of a similar event of the target event, and determining the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period;

[0030] Step S206: determining target event data of the target event within a target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period.

[0031] Through the above steps S202 to S206, by obtaining the second event data of a similar event of the target event in the second sub-time period, the third event data of the target event in the second sub-time period is determined according to the second event data of the similar event, thereby determining the continuous reference event data of the target event in the reference time period according to the first event data of the first sub-time period of the target event in the reference time period, and determining the target event data of the target event in the future target time period according to the reference event data, thereby achieving the purpose of determining the third event data of the target event in the second sub-time period according to the second data of the similar event in the second sub-time period, instead of ignoring or randomly assigning values ​​to discontinuous data in the related art, thereby achieving the technical effect of improving the accuracy of predicting business trends based on historical event data, and further solving the technical problem of low accuracy in predicting business trends based on historical event data.

[0032] In the technical solution provided in step S202, the target event may include, but is not limited to, the click rate of a certain product, the number of views of a certain advertisement, and the like.

[0033] Optionally, in this embodiment, the reference time period is a historical time period, and the length of the reference time period is not limited, for example, it can be 10 minutes, 20 minutes, 1 hour, etc.

[0034] The first event data of the target event in the first time period may be sent by other devices or obtained by detecting and calculating the target event itself. For example, when the target event is the click-through rate of a certain advertisement, the first event data is the click-through rate value of the advertisement in the first time period. The click-through rate value may be the result of statistics and calculation obtained from other advertising platforms, or it may be the result of each advertisement click event obtained from the advertising platform and calculated for each event. This solution does not limit this.

[0035] In the technical solution provided in step S204, similar events to the target event may be events with similar characteristic attributes to the target event. For example, when the target event is the click-through rate of a certain advertising video, similar events may be advertisements with similar characteristics to the advertisement (such as similar product attributes in the advertisement, etc.).

[0036] Optionally, in this embodiment, the method for determining the third event data of the target event in the second sub-time period based on the second event data of the similar event in the second sub-time period within the reference time period may be to directly determine the second event data as the third event data of the target event in the second sub-time period, or may be to adjust the second event data based on the ratio of the event data of the similar event and the target event in other time periods, and determine the adjusted second event data as the third event data of the target event in the second sub-time period, and this scheme is not limited to this.

[0037] Optionally, in the present example, there may or may not be an intersection between the first sub-time period and the second sub-time period. For example, the reference time period is 10:00-11:00 a.m. on a certain day in history, the first sub-time period is 10:30-11:00 a.m. on that day, and the second sub-time period may be 10:00-10:30, 10:00-10:35, 10:00-10:50, and so on.

[0038] In the technical solution provided in step S206, the target event data of the target event within the target time period is determined based on the reference event data, which can be but is not limited to being determined by a model or mathematical formula, etc. This solution does not limit this. For example, through a pre-trained Transformer network model, the time data within a reference time period is input into the Transformer network model, and the target event data value of the target event is output.

[0039] As an optional embodiment, determining the third event data of the target event in the second sub-time period based on the second event data of the similar event of the target event in the second sub-time period within the reference time period includes:

[0040] S11, performing target processing on the second event data according to a predetermined rule to obtain processed fourth event data;

[0041] S12: Determine the fourth event data as the third event data of the target event in the second sub-time period.

[0042] Optionally, in this embodiment, the predetermined rule may be pre-set by a device developer, or may be sent by other functional terminal devices.

[0043] Optionally, in this embodiment, the method for performing target processing on the second event data according to preset rules may be to process the numerical value of the second event data, or to adjust the order of the second event data in the second sub-time period, or to adjust the numerical value of the second event data and the order of the second event data in the second sub-time period at the same time, and this scheme is not limited to this.

[0044] Through the above steps, by performing target processing on the second event and using the processed fourth event as the third event data of the target event in the second sub-time period, the accuracy of the third event data of the determined target event in the second sub-time period is improved.

[0045] As an optional embodiment, performing the target processing on the second event data according to the predetermined rule to obtain the processed fourth event data includes:

[0046] S21, determining the event data ratio between the target event and the similar event in the first sub-time period;

[0047] S22, performing the target processing on the second event data based on the event data ratio to obtain the processed fourth event data, wherein the ratio of the second event data to the fourth event data is equal to the event data ratio.

[0048] Optionally, in this embodiment, determining the time data ratio of the target event and similar events in the first sub-time period can be by comparing the event data at each corresponding timestamp in the first sub-time period, calculating the event data ratio of the target event and similar events at each timestamp, or it can be by comparing the overall event data of the target event and similar events in the first sub-time period to obtain the overall event data ratio.

[0049] Optionally, in this embodiment, processing the second event data according to the event data ratio may be scaling the value of the second event data according to the event data ratio. For example, the second event data is 80, and the event data ratio of similar events and target events in the first sub-time period is 2:1. Then, the event data value of the similar event is twice the event data value of the target event at the corresponding time. Therefore, it is necessary to scale down the value of the second event data. The fourth event data obtained after processing is 40, and the ratio of the second event data to the fourth event data is 2:1.

[0050] Through the above steps, by comparing the event data ratio of the target event data and the similar event data in the first sub-time period, and processing the second event data in the second sub-time period according to the event data ratio, the fourth event data obtained after the target processing is used as the third event data of the target event in the second sub-time period, thereby improving the accuracy and reliability of the third event data of the target event in the second sub-time period.

[0051] As an optional embodiment, performing the target processing on the second event data according to the predetermined rule to obtain the fourth event data includes:

[0052] S31, determining each target sub-time stamp of the second sub-time period;

[0053] S32, confirming the first timestamp event data of the similar event in each of the target sub-time stamps, wherein the second event data includes the first timestamp event data;

[0054] S33, performing the target processing on the first timestamp event data according to the predetermined rule to obtain corresponding second timestamp event data of the target event in each of the target sub-timestamps, wherein the fourth event data includes the second timestamp event data.

[0055] Optionally, in this embodiment, the target sub-timestamps are the time points constituting the second sub-time period, and each target sub-timestamp corresponds to a timestamp event data.

[0056] Optionally, in this embodiment, the first timestamp event data of a similar event at a target sub-timestamp is determined as the second timestamp event data of the target event at a corresponding target sub-timestamp, so that the determined fourth event data is closer to the true value, providing a more accurate data reference for the prediction of target event data in subsequent target time periods.

[0057] As an optional embodiment, determining that the target event is before the third event data of the second sub-time period within the reference time period based on the second event data of the similar event of the target event, the method further includes:

[0058] S41, obtaining target event features of the target event;

[0059] S42, determining the similar event with the greatest similarity to the target event feature in an event database, wherein the event database stores event data and event features of each event in each historical time period.

[0060] Optionally, in this embodiment, the target event feature may be a feature of each dimension of the target event, or may be a total event feature value of the target event obtained by fusing the features of each dimension of the target event.

[0061] Through the above steps, by setting up an event database, the historical event data and time data values ​​are stored in the event database accordingly. When in use, the similarity of event features can be used to search for similar events with the greatest similarity for the target event in the event feature database, thereby achieving the purpose of efficiently and quickly determining similar events to the target event.

[0062] As an optional embodiment, acquiring the target event feature of the target event includes:

[0063] S51, obtaining initial attribute information of multiple dimensions of the target event;

[0064] S52: Determine the target event feature of the target event based on the multiple initial attribute information.

[0065] Optionally, in this embodiment, the initial attribute information of each dimension of the target event may include, but is not limited to, attribute information of dimensions such as appearance, size, function, and target audience of the target event.

[0066] Optionally, the method for determining the target event feature of the target event based on multiple initial attribute information may include, but is not limited to, fusing the multiple initial attribute information to obtain fused event features, and determining the fused event features as the target event features.

[0067] As an optional embodiment, determining the target event feature of the target event based on the multiple initial attribute information includes:

[0068] S61, normalizing each of the initial attribute information to obtain target attribute information;

[0069] S62: Determine the target event feature of the target event based on the target attribute information of each dimension and the corresponding weight information.

[0070] Optionally, in this embodiment, the dimensions of the initial attribute information are different, and thus the units are also different. Through normalization processing, the initial attribute information of each dimension is distributed into the interval (0, 1), so that the initial attribute information of different dimensions is comparable.

[0071] Optionally, in this example, the fused target event features of the target event are calculated according to different weights for the target attribute information of each dimension. The method for weighting the target attribute information may be subjective weighting or determined by an objective weighting method, and this scheme does not limit this.

[0072] Through the above steps, the initial attribute information is normalized to make the target attribute information of each dimension comparable after processing, and the target attribute information is weighted. The target attribute information of each dimension is calculated according to the weight to obtain the target event characteristics, thereby improving the scientificity and reliability of determining the target event characteristics.

[0073] Figure 3is an optional event data prediction flow chart according to an embodiment of the present application, the method is applied to predict the click rate of a certain advertisement in a certain time period in the future, such as Figure 3 As shown:

[0074] S301, collecting data information of the target advertisement on the delivery platform, including the advertisement material image (which can be a frame of image randomly extracted from the target advertisement), the advertisement text title, the advertisement material delivery media, the click information within the target time period, etc.; pre-processing the acquired data of the target advertisement, for example, in order to facilitate feature extraction, up- and down-sampling processing is performed on the acquired advertisement material image, and the advertisement material image is unified into a size of 224×224×3, and the advertisement text title is first segmented using Chinese word segmentation tools such as Jieba word segmentation, and then stop words and low-frequency words are removed, and the initial click rate of the advertisement is obtained by calculating the ratio of the click information of the advertisement within the target time period to the number of advertisement exposures. Since the value of the initial click rate is usually very small and has a long-tail distribution, in order to facilitate subsequent calculations, the initial click rate needs to be transformed for use in model calculations, so it is necessary to add 1 to the initial click rate and then take the logarithm to finally obtain the processed click rate.

[0075] S302, the input advertising data information is not suitable for direct advertising feature fusion, and advertising feature extraction must be performed first to map various data into a continuous vector space. For example, for advertising material images, the VGGNet16 model pre-trained on the large data set ImageNet is used for feature extraction, and the output of the last layer (pooling layer) is taken as the feature. For text title features, the text title data is encoded using one-hot encoding and the word2vec model to obtain text title features. For the media where the advertising material is placed, one-hot encoding is used to obtain media list features; the processed features of each dimension are fused to obtain the fused target advertising features.

[0076] S303, using the Euclidean distance calculation formula to calculate similar advertisements in a preset advertisement material database that have the highest similarity with the target advertisement.

[0077] S304, determine the missing time period corresponding to the missing value of the click rate sequence of the target advertisement, extract the click rate data of similar advertisements in the missing time period from the advertisement material database, supplement the missing value of the click rate sequence of the target advertisement material number in the missing time period, and obtain a complete click rate time series within the target time period of the target advertisement.

[0078] S305, inputting the complete click-through rate time series into the trained Transformer network model, thereby predicting the click-through rate information of the advertisement in a certain time period in the future and obtaining the final prediction result.

[0079] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for enabling an electronic device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0081] According to another aspect of an embodiment of the present application, a device for determining target event data for implementing the above-mentioned method for determining target event data is also provided. Figure 4 is a schematic diagram of an optional device for determining target event data according to an embodiment of the present application, such as Figure 4 As shown, the device may include:

[0082] A first acquisition module 42, configured to acquire first event data of a first sub-time period of the target event within a reference time period;

[0083] A first determining module 44 is configured to determine third event data of the target event in the second sub-time period within the reference time period based on second event data of a similar event of the target event in the second sub-time period, and determine the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period;

[0084] The second determining module 46 is configured to determine target event data of the target event within a target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period.

[0085] It should be noted that the first acquisition module 42 in this embodiment can be used to execute step S202 in the embodiment of the present application, the first determination module 44 in this embodiment can be used to execute step S204 in the embodiment of the present application, and the second determination module 46 in this embodiment can be used to execute step S206 in the embodiment of the present application.

[0086] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware.

[0087] Through the above modules, the technical problem of low accuracy in predicting business trends based on historical event data can be solved, thereby achieving the technical effect of improving the accuracy of predicting business trends based on historical event data.

[0088] As an optional embodiment, the first determination module includes: a processing unit, used to perform target processing on the second event data according to a predetermined rule to obtain processed fourth event data; a first determination unit, used to determine the fourth event data as the third event data of the target event in the second sub-time period.

[0089] As an optional embodiment, the processing unit is used to: determine the event data ratio of the target event and the similar event in the first sub-time period; perform the target processing on the second event data based on the event data ratio to obtain the processed fourth event data, wherein the ratio of the second event data to the fourth event data is equal to the event data ratio.

[0090] As an optional embodiment, the processing unit is used to: determine each target sub-timestamp of the second sub-time period; confirm the first timestamp event data of the similar event in each of the target sub-timestamps, wherein the second event data includes the first timestamp event data; perform the target processing on the first timestamp event data according to the predetermined rule to obtain the corresponding second timestamp event data of the target event in each of the target sub-timestamps, wherein the fourth event data includes the second timestamp event data.

[0091] As an optional embodiment, the device also includes: a second acquisition module, used to determine that the target event is before the third event data of the second sub-time period within the reference time period based on the second event data of the similar event of the target event in the second sub-time period within the reference time period, and obtain the target event characteristics of the target event; a third determination unit, used to determine the similar event with the greatest similarity to the target event characteristics in an event database, wherein the event database stores event data and event characteristics of each event in each historical time period accordingly.

[0092] As an optional embodiment, the second acquisition module includes: an acquisition unit, used to acquire initial attribute information of multiple dimensions of the target event; and a second determination unit, used to determine the target event characteristics of the target event based on the multiple initial attribute information.

[0093] As an optional embodiment, the second determination unit is used to: normalize each of the initial attribute information to obtain target attribute information; and determine the target event characteristics of the target event based on the target attribute information of each dimension and the corresponding weight information.

[0094] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0095] According to another aspect of an embodiment of the present application, an electronic device for implementing the above-mentioned method for determining target event data is also provided.

[0096] Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application, such as Figure 5 As shown, the electronic device may include: one or more (only one is shown in the figure) processors 501, a memory 503, and a transmission device 505, such as Figure 5 As shown, the electronic device may further include an input / output device 507 .

[0097] Wherein, memory 503 can be used for storing software program and module, such as the program instruction / module corresponding to the determination method and device of target event data in the embodiment of the present application, processor 501 performs various functional applications and data processing by running the software program and module stored in memory 503, i.e., realizes the determination method of above-mentioned target event data. Memory 503 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory or other non-volatile solid-state memory. In some instances, memory 503 may further include a memory remotely arranged relative to processor 501, and these remote memories may be connected to electronic devices via a network. Examples of the above-mentioned network include but are not limited to the Internet, intranet, local area network, mobile communication network and combinations thereof.

[0098] The above-mentioned transmission device 505 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. The above-mentioned network specific examples may include wired networks and wireless networks. In one example, the transmission device 505 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 505 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0099] Specifically, the memory 503 is used to store application programs.

[0100] The processor 501 can call the application stored in the memory 503 through the transmission device 505 to perform the following steps: obtain the first event data of the target event in the first sub-time period within the reference time period; determine the third event data of the target event in the second sub-time period within the reference time period based on the second event data of a similar event of the target event in the second sub-time period, and determine the first event data and the third event data as the reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period; determine the target event data of the target event in the target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period.

[0101] By adopting the embodiment of the present application, a method and device for determining target event data are provided. By acquiring the second event data of a similar event of the target event in the second sub-time period, the third event data of the target event in the second sub-time period is determined according to the second event data of the similar event, thereby determining the continuous reference event data of the target event in the reference time period according to the acquired first event data of the target event in the first sub-time period in the reference time period, and the determined third event data of the target event in the second sub-time period, and determining the target event data of the target event in the future target time period according to the reference event data, the purpose of determining the third event data of the target event in the second sub-time period according to the second data of the similar event in the second sub-time period is achieved, instead of ignoring or randomly assigning values ​​to discontinuous data in the related art, thereby achieving the technical effect of improving the accuracy of predicting business trends based on historical event data, and thus solving the technical problem of low accuracy of predicting business trends based on historical event data.

[0102] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0103] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other electronic devices. Figure 5 The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations shown.

[0104] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the electronic device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0105] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the method for determining target event data.

[0106] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0107] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: obtaining first event data of the target event in the first sub-time period within a reference time period; determining third event data of the target event in the second sub-time period within the reference time period based on second event data of a similar event of the target event in the second sub-time period within the reference time period, and determining the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period; determining target event data of the target event within a target time period based on the reference event data, wherein the start time of the target time period is later than the end time of the reference time period.

[0108] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0109] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0110] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0111] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0112] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining target event data, characterized in that: include: Acquire first event data of the target event in a first sub-time period within a reference time period; Determine the third event data of the target event in the second sub-time period based on the second event data of a similar event of the target event in the second sub-time period within the reference time period, and determine the first event data and the third event data as the reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period, and the second sub-time period is a missing time period corresponding to a missing value of a click rate sequence of a target advertisement; Determining target event data of the target event within a target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period; Wherein, determining the third event data of the target event in the second sub-time period based on the second event data of the similar event of the target event in the second sub-time period within the reference time period comprises: performing target processing on the second event data according to a predetermined rule to obtain processed fourth event data; determining the fourth event data as the third event data of the target event in the second sub-time period; Wherein, performing the target processing on the second event data according to the predetermined rule to obtain the processed fourth event data includes: determining the event data ratio of the target event and the similar event in the first sub-time period; performing the target processing on the second event data based on the event data ratio to obtain the processed fourth event data, wherein the ratio of the second event data to the fourth event data is equal to the event data ratio; or, determining each target sub-time stamp of the second sub-time period; determining the first timestamp event data of the similar event within each target sub-time stamp, wherein the second event data includes the first timestamp event data; performing the target processing on the first timestamp event data according to the predetermined rule to obtain the second timestamp event data of the target event within each target sub-time stamp, wherein the fourth event data includes the second timestamp event data; The target processing of the first timestamp event data according to the predetermined rule includes: determining the first timestamp event data of the similar event at the target sub-timestamp as the second timestamp event data of the target event at the corresponding target sub-timestamp.

2. The method according to claim 1, characterized in that Determining that the target event is before the third event data of the second sub-time period within the reference time period based on the second event data of the second sub-time period of the similar event to the target event, the method further includes: Acquire target event features of the target event; The similar event having the greatest similarity to the target event feature is determined in an event database, wherein the event database stores event data and event features of each event in each historical time period.

3. The method according to claim 2, characterized in that Acquiring the target event feature of the target event includes: Acquire initial attribute information of multiple dimensions of the target event; The target event feature of the target event is determined based on a plurality of the initial attribute information.

4. The method according to claim 3, characterized in that Determining the target event feature of the target event based on the plurality of initial attribute information includes: Normalizing each of the initial attribute information to obtain target attribute information; The target event feature of the target event is determined based on the target attribute information of each dimension and the corresponding weight information.

5. A device for determining target event data, characterized in that: include: A first acquisition module, used to acquire first event data of the target event in a first sub-time period within a reference time period; A first determination module is configured to determine third event data of the target event in a second sub-time period within the reference time period based on second event data of a similar event of the target event in a second sub-time period within the reference time period, and determine the first event data and the third event data as reference event data of the target event in the reference time period, wherein the reference time period includes the first sub-time period and the second sub-time period, and the second sub-time period is a missing time period corresponding to a missing value of a click rate sequence of a target advertisement; A second determining module, configured to determine target event data of the target event within a target time period according to the reference event data, wherein the start time of the target time period is later than the end time of the reference time period; The first determination module includes: a processing unit, configured to perform target processing on the second event data according to a predetermined rule to obtain processed fourth event data; a first determination unit, configured to determine the fourth event data as the third event data of the target event in the second sub-time period; Wherein, performing the target processing on the second event data according to the predetermined rule to obtain the processed fourth event data includes: determining the event data ratio of the target event and the similar event in the first sub-time period; performing the target processing on the second event data based on the event data ratio to obtain the processed fourth event data, wherein the ratio of the second event data to the fourth event data is equal to the event data ratio; or, determining each target sub-time stamp of the second sub-time period; determining the first timestamp event data of the similar event within each target sub-time stamp, wherein the second event data includes the first timestamp event data; performing the target processing on the first timestamp event data according to the predetermined rule to obtain the second timestamp event data of the target event within each target sub-time stamp, wherein the fourth event data includes the second timestamp event data; The target processing of the first timestamp event data according to the predetermined rule includes: determining the first timestamp event data of the similar event at the target sub-timestamp as the second timestamp event data of the target event at the corresponding target sub-timestamp.

6. A storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 4 when executed.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes the method described in any one of claims 1 to 4 through the computer program.

Images