Object prediction method, device and equipment

Abstract

The invention provides an object prediction method, device and equipment, and the method can comprise the steps: obtaining the historical connection information of a target object, the historical connection information comprises a plurality of historical time periods, and the historical connection frequency of the target object in each historical time period; determining at least one statistical period, and determining connection average information and connection difference information corresponding to each statistical period according to the historical connection information to obtain at least one piece of connection average information and at least one piece of connection difference information; and processing the at least one piece of connection average information and the at least one piece of connection difference information through a preset model, and determining a target connection behavior of the target object in the target time period. And the accuracy of predicting the target connection behavior is improved.

Description

Technical Field

[0001] The present application relates to the field of big data, and in particular to an object prediction method, device and equipment. Background Art

[0002] When cloud service providers provide cloud products (e.g., virtual machines) to users, they can predict users' usage and connection behavior of cloud products so as to schedule cloud products in a timely manner and provide cloud product services to users.

[0003] In the related art, multiple historical connection times of a cloud product within a historical duration can be determined, and based on the multiple historical connection times, the target connection behavior of the cloud product in the target period can be predicted. However, in the above method, the target connection behavior is strongly correlated with the set historical duration. When the historical duration is long, it is impossible to take into account the rapid change trend of users' use of cloud products in the recent period; when the historical duration is short, it is easy to cause the noise resistance of the target connection behavior to weaken.

[0004] From the above, we can see that the accuracy of predicting target connection behavior in the correlation method is poor. Summary of the invention

[0005] Multiple aspects of the present application provide an object prediction method, apparatus and device to improve the accuracy of predicting target connection behavior.

[0006] In a first aspect, an embodiment of the present application provides an object prediction method, comprising:

[0007] Acquire historical connection information of the target object, wherein the historical connection information includes multiple historical time periods and the number of historical connections of the target object in each historical time period;

[0008] Determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period according to the historical connection information, to obtain at least one connection average information and at least one connection difference information;

[0009] The at least one connection average information and the at least one connection difference information are processed through a preset model to determine a target connection behavior of the target object in a target time period.

[0010] In a possible implementation manner, for any statistical period, determining the connection average information and the connection difference information corresponding to the statistical period according to the historical connection information includes:

[0011] According to the statistical period and the historical time period corresponding to each historical connection number in the historical connection information, grouping multiple historical connection numbers in the historical connection information to obtain at least one first connection number set;

[0012] The connection average information and the connection difference information are determined according to the multiple first connection number sets.

[0013] In a possible implementation manner, determining the connection average information according to the multiple first connection number sets includes:

[0014] For any first connection number set, according to the historical time period corresponding to each historical connection number in the first connection number set, multiple historical connection times in the first connection number set are grouped to obtain multiple second connection number sets, and the historical time period corresponding to each historical connection number in the second connection number set is: the same time period in multiple sub-periods within the statistical period;

[0015] The connection average information is determined according to a plurality of second connection number sets in each first connection number set.

[0016] In a possible implementation, determining the connection average information according to multiple second connection number sets in each first connection number set includes:

[0017] For any first connection number set, an average value of a plurality of historical connection numbers in each second connection number set included in the first connection number set is determined as the average connection number corresponding to each second connection number set, to obtain a plurality of average connection numbers;

[0018] Determine, according to the multiple average connection times, initial connection average information corresponding to the first connection number set;

[0019] Generate a connection number matrix according to the initial connection average information corresponding to each first connection number set, wherein the connection number matrix includes the initial connection average information corresponding to each first connection number set;

[0020] The connection times matrix is ​​determined as the connection average information.

[0021] In a possible implementation, determining the connection difference information according to the multiple first connection number sets includes:

[0022] For any first connection number set, a plurality of historical connection numbers in the first connection number set are grouped according to the characteristics of the historical time period to obtain a third connection number set and a fourth connection number set;

[0023] Determine, according to the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set;

[0024] The connection difference information is determined according to the connection number ratio corresponding to each first connection number set.

[0025] In a possible implementation, determining, according to the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set includes:

[0026] For any first connection count set, the sum of each historical connection count in the third connection count set is determined as the first total historical connection count;

[0027] Determine the sum of each historical connection count in the fourth connection count set as the second total historical connection count;

[0028] A ratio of the first total historical connection times to the second total historical connection times is determined as the connection times ratio.

[0029] In a possible implementation, the method further includes:

[0030] Acquire at least one historical connection prediction behavior corresponding to the target object, and an actual connection behavior corresponding to each historical connection prediction behavior, wherein the at least one historical connection prediction behavior is obtained by historically predicting the target object through the preset model;

[0031] The confidence level of the connection behavior prediction of the target object by the preset model is determined according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior.

[0032] In a possible implementation, determining, according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, a confidence level of the connection behavior prediction of the target object by the preset model includes:

[0033] Determining a first accuracy of the preset model for estimating the target object according to the at least one historical connection estimation behavior and the actual connection behavior corresponding to each historical connection estimation behavior;

[0034] Determining an overall accuracy based on a second accuracy of each of the multiple reference objects estimated by the preset model;

[0035] A confidence level corresponding to the target object is determined according to the first accuracy and the overall accuracy.

[0036] In a possible implementation, determining a first accuracy of the preset model for estimating the target object according to the at least one historical connection estimation behavior and an actual connection behavior corresponding to each historical connection estimation behavior includes:

[0037] determining a first quantity of at least one historical connection estimated behavior;

[0038] Determine, according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, a second number of the historical connection prediction behaviors being consistent with the corresponding actual connection behaviors;

[0039] A ratio of the second number to the first number is determined as a first accuracy.

[0040] In a second aspect, an embodiment of the present application provides an object prediction device, including: a first acquisition module, a first determination module and a processing module, wherein:

[0041] The first acquisition module is used to acquire historical connection information of the target object, wherein the historical connection information includes multiple historical time periods and the number of historical connections of the target object in each historical time period;

[0042] The first determination module is used to determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period according to the historical connection information, to obtain at least one connection average information and at least one connection difference information;

[0043] The processing module is used to process the at least one connection average information and the at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period.

[0044] In a possible implementation manner, for any statistical period, the first determining module is specifically configured to:

[0045] According to the statistical period and the historical time period corresponding to each historical connection number in the historical connection information, grouping multiple historical connection numbers in the historical connection information to obtain at least one first connection number set;

[0046] The connection average information and the connection difference information are determined according to the multiple first connection number sets.

[0047] In a possible implementation manner, the first determining module is specifically configured to:

[0048] For any first connection number set, according to the historical time period corresponding to each historical connection number in the first connection number set, multiple historical connection times in the first connection number set are grouped to obtain multiple second connection number sets, and the historical time period corresponding to each historical connection number in the second connection number set is: the same time period in multiple sub-periods within the statistical period;

[0049] The connection average information is determined according to a plurality of second connection number sets in each first connection number set.

[0050] In a possible implementation manner, the first determining module is specifically configured to:

[0051] For any first connection number set, an average value of a plurality of historical connection numbers in each second connection number set included in the first connection number set is determined as the average connection number corresponding to each second connection number set, to obtain a plurality of average connection numbers;

[0052] Determine, according to the multiple average connection times, initial connection average information corresponding to the first connection number set;

[0053] Generate a connection number matrix according to the initial connection average information corresponding to each first connection number set, wherein the connection number matrix includes the initial connection average information corresponding to each first connection number set;

[0054] The connection times matrix is ​​determined as the connection average information.

[0055] In a possible implementation manner, the first determining module is specifically configured to:

[0056] For any first connection number set, a plurality of historical connection numbers in the first connection number set are grouped according to the characteristics of the historical time period to obtain a third connection number set and a fourth connection number set;

[0057] Determine, according to the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set;

[0058] The connection difference information is determined according to the connection number ratio corresponding to each first connection number set.

[0059] In a possible implementation manner, the first determining module is specifically configured to:

[0060] For any first connection count set, the sum of each historical connection count in the third connection count set is determined as the first total historical connection count;

[0061] Determine the sum of each historical connection count in the fourth connection count set as the second total historical connection count;

[0062] A ratio of the first total historical connection times to the second total historical connection times is determined as the connection times ratio.

[0063] In a possible implementation manner, the device further includes: a second acquisition module and a second determination module, wherein:

[0064] The second acquisition module is used to acquire at least one historical connection prediction behavior corresponding to the target object and an actual connection behavior corresponding to each historical connection prediction behavior, wherein the at least one historical connection prediction behavior is obtained by historically predicting the target object through the preset model;

[0065] The second determination module is used to determine the confidence of the preset model in predicting the connection behavior of the target object based on the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior.

[0066] In a possible implementation manner, the second determining module is specifically configured to:

[0067] Determining a first accuracy of the preset model for estimating the target object according to the at least one historical connection estimation behavior and the actual connection behavior corresponding to each historical connection estimation behavior;

[0068] Determining an overall accuracy based on a second accuracy of each of the multiple reference objects estimated by the preset model;

[0069] A confidence level corresponding to the target object is determined according to the first accuracy and the overall accuracy.

[0070] In a possible implementation manner, the second determining module is specifically configured to:

[0071] determining a first quantity of at least one historical connection estimated behavior;

[0072] Determine, according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, a second number of the historical connection prediction behaviors being consistent with the corresponding actual connection behaviors;

[0073] A ratio of the second number to the first number is determined as a first accuracy.

[0074] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor;

[0075] The memory stores computer-executable instructions;

[0076] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method described in any one of the first aspects.

[0077] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in any one of the first aspects.

[0078] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method shown in any one of the first aspects.

[0079] The embodiments of the present application provide an object prediction method, apparatus, and device. The electronic device can obtain historical connection information of the target object, determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period based on the historical connection information, and obtain at least one connection average information and at least one connection difference information. The electronic device can process at least one connection average information and at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period. Since the target connection behavior can be comprehensively predicted not only based on the connection average information corresponding to different statistical periods, but also based on the connection difference information corresponding to different statistical periods, the accuracy of predicting the target connection behavior is improved compared to directly predicting the target connection behavior based on the connection average information within the historical time period. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0081] Figure 1 A schematic diagram of a scenario provided for an exemplary embodiment of the present application;

[0082] Figure 2 A flowchart of an object prediction method provided for an exemplary embodiment of the present application;

[0083] Figure 3 A flowchart of another object prediction method provided for an exemplary embodiment of the present application;

[0084] Figure 4 A schematic diagram of a process of an object prediction method provided in an embodiment of the present application;

[0085] Figure 5 A schematic diagram of the structure of an object prediction device is provided for an embodiment of the present application;

[0086] Figure 6 A schematic diagram of the structure of another object prediction device provided in an embodiment of the present application;

[0087] Figure 7 A schematic structural diagram of an electronic device provided for an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0089] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. 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 making creative work are within the scope of protection of the present application.

[0090] Figure 1 A schematic diagram of a scenario provided for an exemplary embodiment of the present application. Figure 1 For any target object, the historical connection information of the target object within the historical time period can be determined. The historical connection information can include multiple historical time periods and the number of historical connections corresponding to each historical time period. The target connection behavior of the target object in the target time period can be predicted based on the number of historical connections.

[0091] For example, if the target object is virtual machine 1 and the historical duration is 2023.8.1-2023.9.30, the historical connection information of virtual machine 1 between 2023.8.1-2023.9.30 can be determined, and the historical connection information can include historical connection number 1 corresponding to historical period 1, historical connection number 2 corresponding to historical period 2, ..., historical connection number n corresponding to historical period n. If the target period is 2023.10.2, the target connection behavior of virtual machine 1 on 2023.10.2 can be predicted based on the historical connection information.

[0092] In the related art, multiple historical connection times of a cloud product within a historical duration can be determined, and based on the multiple historical connection times, the target connection behavior of the cloud product in the target time period can be predicted. However, in the above method, the target connection behavior is strongly correlated with the set historical duration. When the historical duration is long, it is impossible to take into account the rapid changes in the user's use of cloud products in the recent period; when the historical duration is short, it is easy to cause the noise resistance of the target connection behavior to become weak. From the above, it can be seen that the accuracy of predicting the target connection behavior in the related method is poor.

[0093] In the embodiment of the present application, at least one statistical period can be determined, and the connection average information and connection difference information corresponding to each statistical period can be determined based on the historical connection information of the target object, and then at least one connection average information and connection difference information can be processed by a preset model to predict the target connection behavior of the target object in the target period. Since the target connection behavior can be comprehensively predicted not only based on the connection average information corresponding to different statistical periods, but also based on the connection difference information corresponding to different statistical periods, compared with directly predicting the target connection behavior based on the connection average information within the historical duration, the accuracy of predicting the target connection behavior is improved.

[0094] The technical solutions shown in the present application are described in detail below through specific embodiments. It should be noted that the following embodiments can exist independently or in combination with each other, and the same or similar contents will not be described repeatedly in different embodiments.

[0095] Figure 2 A flowchart of an object prediction method provided for an exemplary embodiment of the present application. Figure 2 , the method may include:

[0096] S201: Obtain historical connection information of a target object.

[0097] The execution subject of the embodiment of the present application may be an electronic device, or an object prediction device set in the electronic device. The object prediction device may be implemented by software, or by a combination of software and hardware. The object prediction device may be a processor in the electronic device. For ease of understanding, the following description is made by taking the execution subject as an electronic device as an example.

[0098] The target object may be a cloud product. For example, the target object may be a virtual machine.

[0099] The historical connection information may include multiple historical time periods and the number of historical connections of the target object in each historical time period.

[0100] For example, if the target object is virtual machine 1, and if the historical duration is 2023.8.1-2023.9.30, which includes multiple historical periods, the multiple historical periods are each hour between 2023.8.1-2023.9.30. Then the historical connection information may include the historical connection count of virtual machine 1 per hour between 2023.8.1-2023.9.30, as shown in Table 1:

[0101] Table 1

[0102]

[0103] The electronic device may collect the historical connection times of the target object in each historical period within the historical time period to obtain the historical connection information.

[0104] S202: Determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period according to the historical connection information, to obtain at least one connection average information and at least one connection difference information.

[0105] At least one statistical period may be preset manually. For example, two statistical periods may be preset, the first statistical period may be 31 days, and the second statistical period may be 7 days.

[0106] In an optional embodiment, for any statistical period, the connection average information and connection difference information corresponding to the statistical period can be determined according to the historical connection information in the following manner: according to the statistical period and the historical time period corresponding to each historical connection number in the historical connection information, multiple historical connection times in the historical connection information are grouped to obtain at least one first connection number set; based on the multiple first connection number sets, the connection average information and connection difference information are determined.

[0107] The first connection count set may include historical connection counts corresponding to multiple historical time periods within a statistical period.

[0108] For any statistical period, multiple statistical periods can be determined based on multiple historical time periods, and then multiple historical connection times can be grouped and processed according to the multiple statistical periods. The historical connection times corresponding to multiple historical time periods within any statistical period can be divided into a first connection number set to obtain multiple first connection number sets, and each statistical period can correspond to a first connection number set.

[0109] For example, if the historical connection information is as shown in Table 1, including the historical connection times per hour from 2023.8.1 to 2023.9.30, if there are two statistical periods, namely, a 7-day statistical period and a 30-day statistical period, then for the 7-day statistical period, 9 statistical periods can be determined according to multiple historical time periods, and each statistical period can include multiple historical time periods. The 168 historical connection times corresponding to 7*24=168 historical time periods in each statistical period can be divided into a first connection number set. Since there are 9 statistical periods, 9 first connection number sets can be determined, namely, first connection number set 1-1, first connection number set 1-2, ..., first connection number set 1-9, wherein each of the first connection number sets 1-1 to the first connection number set 1-8 can include 168 historical connection times, and the first connection number set 1-9 can include 120 historical connection times.

[0110] Similarly, for a 31-day statistical period, two statistical periods can be determined based on multiple historical periods, and statistical period 1 can include 31*24=744 historical periods between 2023.8.1-2023.8.31, and statistical period 2 can include 30*24=720 historical periods between 2023.9.1-2023.9.30. The 744 historical connection times corresponding to the 744 historical periods in statistical period 1 can be divided into a first connection number set 2-1, and the 720 historical connection times corresponding to the 720 historical periods in statistical period 2 can be divided into a first connection number set 2-2.

[0111] After determining a plurality of first connection number sets, connection average information and connection difference information may be determined according to the plurality of first connection number sets.

[0112] Optionally, the average connection information may be represented by a matrix. The average connection information may include 24 average connection times corresponding to each first connection times set. The 24 average connection times are the average connection times corresponding to each hour in the first connection times set.

[0113] The connection difference information may be represented by a one-dimensional vector. The connection difference information may include connection number ratios corresponding to multiple first connection number sets. The connection number ratio may be a ratio of the sum of each historical connection number in multiple working days in the first connection number set to the sum of each historical connection number in multiple non-working days.

[0114] For example, if there are 9 first connection number sets corresponding to a 7-day statistical period, 24 average connection numbers corresponding to the 9 first connection number sets can be determined, and 9*24=216 average connection numbers are obtained. Assume that the 216 average connection numbers are as shown in Table 2:

[0115] Table 2

[0116]

[0117] Then, the connection average information 1 corresponding to the 7-day statistical period can be determined based on the 216 average connection times. The connection average information 1 can be represented by the following matrix A:

[0118]

[0119] The matrix may include 24 rows and 9 columns, and each column includes 24 average connection times corresponding to a first connection number set.

[0120] The connection number ratios corresponding to the nine first connection number sets can be determined to obtain nine connection number ratios. Assuming that the nine connection number ratios are 1.5, 0.6, 1.3, 2.1, 1.7, 0.9, 1.1, 2.0, and 0.4, the connection difference information 1 corresponding to the 7-day statistical period can be determined to be (1.5, 0.6, 1.3, 2.1, 1.7, 0.9, 1.1, 2.0, and 0.4) according to the nine connection number ratios.

[0121] Similarly, for a 31-day statistical period, if there are two first connection number sets corresponding to the 31-day statistical period, 24 average connection numbers corresponding to the two first connection number sets can be determined respectively, and 2*24=48 average connection numbers are obtained. Assume that the 48 average connection numbers are as shown in Table 3:

[0122] Table 3

[0123]

[0124]

[0125] Then, the average connection information 2 corresponding to the 31-day statistical period can be determined based on the 48 average connection times. The average connection information 2 can be represented by the following matrix B:

[0126]

[0127] The matrix may include 24 rows and 2 columns, wherein the first column includes 24 average connection times corresponding to the first connection time set 2-1; and the second column includes 24 average connection times corresponding to the first connection time set 2-2.

[0128] The connection number ratios corresponding to the two first connection number sets can be determined to obtain two connection number ratios. Assuming that the two connection number ratios are 1.3 and 0.6 respectively, the connection difference information 2 corresponding to the 31-day statistical period can be determined to be (1.3, 0.6) based on the two connection number ratios.

[0129] S203: Process at least one piece of connection average information and at least one piece of connection difference information through a preset model to determine a target connection behavior of the target object in a target time period.

[0130] Optionally, the preset model may be a Light Gradient Boosting Machine (LightGBM) model.

[0131] The target connection behavior includes connection or disconnection, where "1" can be used to indicate connection, and "0" can be used to indicate disconnection.

[0132] For example, if the 7-day statistical period corresponds to the connection average information 1 as shown in matrix A, the connection difference information 1 is (1.5, 0.6, 1.3, 2.1, 1.7, 0.9, 1.1, 2.0, 0.4); the 31-day statistical period corresponds to the connection average information 2 as shown in matrix B, and the connection difference information 2 is (1.3, 0.6). If the preset model is the LightGBM model and the target period is 2023.10.1, the connection average information 1, the connection difference information 1, the connection average information 2, and the connection difference information 2 can be processed by the LightGBM model to determine the target connection behavior 1 of virtual machine 1 on 2023.10.1. Assume that the target connection behavior 1 is determined to be "connected".

[0133] In an embodiment of the present application, the electronic device can obtain the historical connection information of the target object, determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period based on the historical connection information, and obtain at least one connection average information and at least one connection difference information. The electronic device can process at least one connection average information and at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period. Since the target connection behavior can be comprehensively predicted not only based on the connection average information corresponding to different statistical periods, but also based on the connection difference information corresponding to different statistical periods, compared with directly predicting the target connection behavior based on the connection average information within the historical time period, the accuracy of predicting the target connection behavior is improved.

[0134] Below, in Figure 2 Based on the embodiment shown, combined Figure 3 , the above object prediction method is explained in detail.

[0135] Figure 3 This is a flowchart of another object prediction method provided in an embodiment of the present application. Figure 3 , the method may include:

[0136] S301: Obtain historical connection information of a target object.

[0137] It should be noted that the execution process of step S301 can refer to the execution process of step S201, which will not be repeated here.

[0138] S302: Determine at least one statistical period.

[0139] For example, the electronic device may determine two statistical periods, the first statistical period may be 31 days, and the second statistical period may be 7 days.

[0140] S303: For any statistical period, group multiple historical connection times in the historical connection information according to the statistical period and the historical time period corresponding to each historical connection time in the historical connection information to obtain multiple first connection time sets.

[0141] For example, if there are two statistical cycles, namely, a 7-day statistical cycle and a 31-day statistical cycle, and if the historical connection information is as shown in Table 1, the 1464 historical connection times in the historical connection information can be grouped according to the 7-day statistical cycle and the historical time period corresponding to each historical connection number in the historical connection information, and 9 first connection number sets corresponding to the 7-day statistical cycle are obtained, as shown in Table 4:

[0142] Table 4

[0143]

[0144] As shown in Table 4, each statistical period includes multiple historical periods. For example, statistical period 1-1 may include multiple historical periods, which are 24 hours per day from 2023.8.1 to 2023.8.7, for a total of 168 historical periods.

[0145] For any statistical period, the historical connection times corresponding to the multiple historical time periods in the statistical period can be divided into a first connection times set. As shown in Table 4, the statistical period 1-1 includes 168 historical time periods, and the historical connection times corresponding to the 168 historical time periods can be divided into the first connection times set 1-1, and the first connection times set 1-1 can include the historical connection times corresponding to the 168 historical time periods; similarly, the first connection times set 1-2 corresponding to the statistical period 1-2, ..., and the first connection times set 1-9 corresponding to the statistical period 1-9 can be determined respectively.

[0146] For a statistical period of 31 days, the 1464 historical connection times in the historical connection information can be grouped according to the statistical period of 31 days and the historical time period corresponding to each historical connection time in the historical connection information to obtain two first connection time sets corresponding to the statistical period of 31 days, as shown in Table 5:

[0147] Table 5

[0148]

[0149] As shown in Table 5, the statistical period 2-1 may include 744 historical time periods, and the statistical period 2-2 may include 720 historical time periods. For the statistical period 2-1, the 744 historical connection times corresponding to the 744 historical time periods included in the statistical period may be divided into a first connection times set 2-1; the 720 historical connection times corresponding to the 720 historical time periods included in the statistical period 2-2 may be divided into a first connection times set 2-2.

[0150] S304: Determine average connection information according to multiple first connection number sets.

[0151] In an optional embodiment, the connection average information can be determined based on multiple first connection number sets in the following manner: for any first connection number set, multiple historical connection numbers in the first connection number set are grouped according to the historical time periods corresponding to each historical connection number in the first connection number set to obtain multiple second connection number sets; the connection average information is determined based on the multiple second connection number sets in each first connection number set.

[0152] The historical time period corresponding to each historical connection count in the second connection count set is: the same time period in multiple sub-periods within the statistical period. For example, if the statistical period is 7 days, the sub-period can be 1 day. A statistical period can include 7 sub-periods, and each sub-period can include 24 historical time periods, namely 0:00-1:00, 1:00-2:00, ..., 23:00-0:00. For example, the historical time period corresponding to each historical connection count in the second connection count set 1 can be the same time period 0:00-1:00 in the 7 sub-periods.

[0153] For example, for a statistical period of 7 days, Table 4 includes 9 first connection number sets, namely, first connection number set 1-1, ..., first connection number set 1-9. If the sub-period is 1 day, for the first connection number set 1-1, the first connection number set 1-1 includes 24 hours of each day from 2023.8.1 to 2023.8.7, then in the first connection number set, the historical connection times corresponding to 0:00-1:00 in the 7 sub-periods from 2023.8.1 to 2023.8.7, that is, the 7 historical time periods 0:00-1:00, can be divided into the second connection number set 1-1; 2023 can be divided into the second connection number set 1-2. 1:00-2:00 included in the 7 sub-periods from 2023.8.1 to 2023.8.7, that is, the historical connection times corresponding to the 7 historical time periods from 1:00-2:00 are divided into second connection times sets 1-2; ...; 23:00-0:00 included in the 7 sub-periods from 2023.8.1 to 2023.8.7, that is, the historical connection times corresponding to the 7 historical time periods from 23:00-0:00 are divided into second connection times sets 1-24. The first connection times set may include 24 second connection times sets, and each second connection times set may include 7 historical connection times.

[0154] In an optional embodiment, the connection average information can be determined based on multiple second connection number sets in each first connection number set in the following manner: for any first connection number set, the average value of multiple historical connection times in each second connection number set included in the first connection number set is determined as the average connection number corresponding to each second connection number set, and multiple average connection times corresponding to the first connection number set are obtained; based on the multiple average connection times, initial connection average information corresponding to the first connection number set is determined; based on the initial connection average information corresponding to each first connection number set, a connection number matrix is ​​generated; and the connection number matrix is ​​determined as the connection average information.

[0155] The initial connection average information can be represented by a one-dimensional column vector.

[0156] For any second connection number set, multiple historical connection numbers included in the second connection number set can be determined, and an average value of the multiple historical connection numbers can be determined, and the average value is determined as the average connection number corresponding to the second connection number set.

[0157] For example, for a statistical period of 7 days, Table 4 includes 9 first connection number sets, namely, first connection number set 1-1, ..., first connection number set 1-9. For the first connection number set 1-1, the first connection number set 1-1 includes 24 second connection number sets, each of which may include 7 historical connection numbers, and then the average connection numbers corresponding to the 24 second connection number sets can be determined to obtain 24 average connection numbers. Assuming that the 24 average connection numbers are 1, 2, ..., 2, respectively, the initial connection average information 1-1 corresponding to the first connection number set 1-1 can be determined based on the 24 average connection numbers. The initial connection average information 1-1 can be expressed as: (1, 2, ..., 2) T .

[0158] Similarly, the initial connection average information 1-2 corresponding to the first connection number set 1-2 can be determined; ...; the initial connection average information 1-9 corresponding to the first connection number set 1-9 can be determined, and 9 initial connection average information can be obtained.

[0159] Optionally, after obtaining multiple pieces of initial connection average information, the multiple pieces of initial connection average information may be combined to generate a connection number matrix. The connection number matrix may include initial connection average information corresponding to each first connection number set.

[0160] For example, there are 9 initial connection average information, namely (1, 2, ..., 2) T 、(2,1,……,3) T , …, (1, 2, …, 3) T , the 9 initial connection average information can be combined to generate the connection number matrix 1, which can be represented by matrix A as follows:

[0161]

[0162] Then the connection times matrix 1 may be determined as the connection average information 1 corresponding to the 7-day statistical period.

[0163] Similarly, for a statistical period of 31 days, Table 5 includes two first connection number sets, namely, first connection number set 2-1 and first connection number set 2-2. For the first connection number set 2-1, the first connection number set 2-1 includes 24 hours every day from 2023.8.1 to 2023.8.31. Then, in the first connection number set 2-1, the historical connection times corresponding to 0:00-1:00 respectively included in 2023.8.1-2023.8.31, that is, the historical connection times corresponding to 0:00-1:00 in 31 historical time periods can be divided into the second connection number set 2-1; the historical connection times corresponding to 1:00-2:00 respectively included in 2023.8.1-2023.8.31, that is, the historical connection times corresponding to 1:00-2:00 in 31 historical time periods can be divided into the second connection number set 2-2; ...; the historical connection times corresponding to 23:00-0:00 respectively included in 2023.8.1-2023.8.31, that is, the historical connection times corresponding to 23:00-0:00 in 31 historical time periods can be divided into the second connection number set 2-24. The first connection count set 2-1 may include 24 second connection count sets, and each second connection count set may include 31 historical connection counts. The average connection counts corresponding to the 24 second connection count sets in the first connection count set 2-1 may be determined to obtain 24 average connection counts. Assuming that the 24 average connection counts are 2, 1, ..., 3, respectively, the initial connection average information 2-1 corresponding to the first connection count set 2-1 may be determined based on the 24 spliced ​​connection counts. The initial connection average information 2-1 may be expressed as: (2, 1, ..., 3) T Similarly, the initial connection average information 2-2 corresponding to the first connection number set 2-2 can be determined. Assume that the initial connection average information 2-2 is (3, 2, ..., 2) T Then the initial connection average information 2-1 and the initial connection average information 2-2 can be combined to generate a connection number matrix 2, which can be represented by the following matrix B:

[0164]

[0165] Then the connection times matrix 2 may be determined as the connection average information 2 corresponding to the statistical period of 31 days.

[0166] S305: Determine connection difference information according to multiple first connection number sets.

[0167] In an optional embodiment, connection difference information can be determined based on multiple first connection number sets in the following manner: for any first connection number set, multiple historical connection numbers in the first connection number set are grouped according to historical time period characteristics to obtain a third connection number set and a fourth connection number set; based on the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set is determined; based on the connection number ratio corresponding to each first connection number set, connection difference information is determined.

[0168] The historical period characteristic refers to whether the historical period is located on a working day or a non-working day.

[0169] The third connection number set may include historical connection numbers corresponding to multiple historical time periods on working days. The fourth connection number set may include historical connection numbers corresponding to multiple historical time periods on non-working days.

[0170] The connection number ratio may be a ratio of the sum of each historical connection number in the third connection number set to the sum of each historical connection number in the fourth connection number set.

[0171] For example, for a statistical period of 7 days, Table 4 includes 9 first connection number sets, namely, first connection number set 1-1, ..., first connection number set 1-9. For the first connection number set 1-1, the first connection number set 1-1 includes 24 hours each day from 2023.8.1 to 2023.8.7. Assuming that 2023.8.1 to 2023.8.5 are working days and 2023.8.6 to 2023.8.7 are non-working days, then according to the characteristics of the historical period, the historical connection times corresponding to the 24 hours respectively included in 2023.8.1 to 2023.8.5 in the first connection number set can be divided into a third connection number set 1-1, and the historical connection times corresponding to the 24 hours respectively included in 2023.8.6 to 2023.8.7 can be divided into a fourth connection number set 1-1. The third connection number set 1-1 can include 5*24=120 historical connection times, and the fourth connection number set can include 2*24=48 historical connection times.

[0172] Optionally, the connection number ratio corresponding to each first connection number set can be determined according to the third connection number set and the fourth connection number set corresponding to each first connection number set in the following manner: for any first connection number set, the sum of each historical connection number in the third connection number set is determined as the first historical total connection number; the sum of each historical connection number in the fourth connection number set is determined as the second historical total connection number; the ratio of the first historical total connection number to the second historical total connection number is determined as the connection number ratio.

[0173] For example, for the third connection number set 1-1 and the fourth connection number set 1-1 corresponding to the first connection number set 1-1, since the third connection number set 1-1 includes 120 historical connection times, the sum of the 120 historical connection times can be determined as the first historical total connection number 1-1, assuming that the first historical total connection number 1-1 is 237. Since the fourth connection number set includes 48 historical connection times, the sum of the 48 historical connection times can be determined as the second historical total connection number 1-1, assuming that the second historical total connection number 1-1 is 158, it can be determined that the ratio of the first historical total connection number 1-1 to the second historical total connection number 1-1 is 237 / 158=1.5, and the ratio 1.5 can be determined as the connection number ratio 1-1 corresponding to the first connection number set 1-1.

[0174] Similarly, the connection number ratios 1-2, ..., and the connection number ratios 1-9 corresponding to the first connection number set 1-9 can be determined to obtain 9 connection number ratios. Assume that the 9 connection number ratios are 1.5, 0.6, 1.3, 2.1, 1.7, 0.9, 1.1, 2.0, and 0.4, respectively.

[0175] Optionally, after determining multiple connection times ratios, connection difference information can be determined according to the multiple connection times ratios. For example, if there are 9 connection times ratios, which are 1.5, 0.6, 1.3, 2.1, 1.7, 0.9, 1.1, 2.0, and 0.4, then the connection difference information 1 corresponding to the 7-day statistical period can be determined according to the 9 connection times ratios to be (1.5, 0.6, 1.3, 2.1, 1.7, 0.9, 1.1, 2.0, 0.4).

[0176] Similarly, for the 31-day statistical period, assuming that it can be determined that the connection number ratio corresponding to the first connection number set 2-1 in Table 5 is 1.3, and the connection number ratio corresponding to the first connection number set 2-2 is 0.6, then based on the two connection number ratios, it can be determined that the connection difference information 2 corresponding to the 31-day statistical period is (1.3, 0.6).

[0177] S306: Process at least one piece of connection average information and at least one piece of connection difference information through a preset model to determine a target connection behavior of the target object in a target period of time.

[0178] It should be noted that the execution process of step S306 can refer to step S203, which will not be described again here.

[0179] S307: Obtain at least one historical connection prediction behavior corresponding to the target object, and an actual connection behavior corresponding to each historical connection prediction behavior.

[0180] At least one historical connection prediction behavior is obtained by performing historical prediction on the target object through a preset model.

[0181] For example, the electronic device can obtain 24 historical connection estimated behaviors corresponding to 24 hours in 2023.10.1 for virtual machine 1 predicted by a preset model, and can obtain the actual connection behaviors corresponding to 24 hours in 2023.10.1 for virtual machine 1, as shown in Table 6:

[0182] Table 6

[0183] 2023.10.1 0:00-1:00 1:00-2:00 2:00-3:00 …… 23:00-0:00 Historical connection prediction behavior 1 0 0 …… 1 Actual connection behavior 1 1 0 …… 1

[0184] S308: Determine the confidence level of the connection behavior prediction of the target object by the preset model according to at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior.

[0185] In an optional embodiment, the confidence of the preset model in predicting the connection behavior of the target object can be determined in the following manner based on at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior: determine a first accuracy of the preset model's prediction of the target object based on at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior; determine the overall accuracy based on a second accuracy of the preset model's prediction of each reference object among multiple reference objects; and determine the confidence corresponding to the target object based on the first accuracy and the overall accuracy.

[0186] The reference object and the target object are objects of the same type. For example, if the target object is a virtual machine, the reference object is also a virtual machine.

[0187] Optionally, the first accuracy of the preset model's estimation of the target object can be determined based on at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior in the following manner: determining a first quantity of at least one historical connection prediction behavior; determining a second quantity of historical connection prediction behaviors that are consistent with the corresponding actual connection behaviors based on at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior; and determining the ratio of the second quantity to the first quantity as the first accuracy.

[0188] For example, if the first number of at least one historical connection prediction behavior is 24, and among the 24 historical connection prediction behaviors, the second number of historical connection prediction behaviors that are consistent with the corresponding actual connection behaviors is 20, then the ratio of the second number to the first number, 20 / 24=83%, can be determined as the first accuracy.

[0189] Optionally, the electronic device may obtain the second accuracy of each reference object estimated by the preset model for multiple reference objects, obtain multiple second accuracies, and determine the average of the multiple second accuracies as the overall accuracy. For example, if there are 10 virtual machines, and the second accuracy estimated by the preset model for each virtual machine is 80%, 83%, 81%, 90%, 89%, 87%, 93%, 83%, 89%, 81% respectively, then the average of the 10 second accuracies may be determined to be 85.6%, and the average of 85.6% may be determined as the overall accuracy.

[0190] Optionally, a deviation ratio between the first accuracy and the overall accuracy may be determined, and then the confidence level of the prediction of the target object may be determined based on the deviation ratio and a preset mapping relationship.

[0191] Optionally, the preset mapping relationship may be a preset mapping algorithm or a preset mapping table. The deviation ratio is calculated and processed by the preset mapping algorithm to obtain the confidence corresponding to the deviation ratio; the preset mapping table may include multiple deviation ratios and the confidence corresponding to each deviation ratio, and the confidence corresponding to the deviation ratio may be determined in the preset mapping table.

[0192] For example, if the overall accuracy is 85.6% and the first accuracy is 83%, the deviation ratio between the first accuracy and the overall accuracy is determined to be 83% / 85.6%=0.97. Assuming that the preset mapping relationship is a preset mapping table, the confidence corresponding to the deviation ratio of 0.97 can be determined in the preset mapping table. Assuming the confidence is 90%, it can be determined that the confidence of the preset model in predicting the target object is 90%.

[0193] Optionally, a confidence threshold corresponding to the confidence level may be set. When the confidence level is greater than or equal to the confidence threshold, it indicates that the preset model predicts the target connection behavior of the target object with greater accuracy; when the confidence level is less than the confidence threshold, it indicates that the preset model predicts the target connection behavior of the target object with less accuracy.

[0194] Through the technical solution of this application, the LightGBM model provides good target connection behavior prediction capabilities, especially when the characteristics of the target connection behavior of the object have significant periodicity or trend, it will show obvious advantages and improve the accuracy of predicting the target connection behavior. In addition, the confidence setting rules take into account the historical connection behavior, adapt to the distribution of different connection behaviors to a certain extent, and improve the quality of the confidence of predicting the target connection behavior; and because this solution takes into account the average connection information and the connection difference information, it can improve the recall rate of predicting the target connection behavior.

[0195] In an embodiment of the present application, the electronic device can obtain historical connection information of the target object and determine at least one statistical period. For any statistical period, the electronic device can group multiple historical connection times in the historical connection information according to the statistical period and the historical time period corresponding to each historical connection time in the historical connection information to obtain multiple first connection time sets, and can determine the connection average information according to the multiple first connection time sets, and can also determine the connection difference information according to the multiple first connection time sets. The electronic device can process at least one connection average information and at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period. The electronic device can also obtain at least one historical connection estimated behavior of the target object through the preset model, and the actual connection behavior corresponding to each historical connection estimated behavior, and determine the confidence of the preset model in predicting the connection behavior of the target object according to at least one historical connection estimated behavior and the actual connection behavior corresponding to each historical connection estimated behavior. Since the target connection behavior can be comprehensively predicted not only according to the connection average information corresponding to different statistical periods, but also according to the connection difference information corresponding to different statistical periods, the accuracy of predicting the target connection behavior is improved compared with directly predicting the target connection behavior according to the connection average information within the historical duration.

[0196] Next, based on any of the above embodiments, Figure 4 , the above object prediction method is further explained through specific examples.

[0197] Figure 4 A schematic diagram of the process of an object prediction method provided in an embodiment of the present application. Figure 4The electronic device can obtain the historical connection information of the target object within the historical time period, and the historical connection information can include 1464 historical time periods and the number of historical connections corresponding to each historical time period.

[0198] The electronic device can determine two statistical cycles and can group multiple historical connection times in the historical connection information according to the first statistical cycle and the historical time period corresponding to each historical connection time in the historical connection information to obtain 9 first connection time sets.

[0199] For any first connection number set, the electronic device can determine the initial connection average information corresponding to the first connection number set and the connection number ratio based on the multiple historical connection numbers included in the first connection number set. Specifically, the first connection number set can be grouped to obtain 24 second connection number sets corresponding to the first connection number set, and each second connection number set can include 7 historical connection numbers. The average values ​​of the multiple historical connection numbers respectively included in the 24 second connection number sets can be determined as the average connection numbers corresponding to the 24 second connection number sets, respectively, to obtain 24 average connection numbers corresponding to the first connection number set, and then the initial connection average information corresponding to the first connection number set can be determined based on the 24 average connection numbers. Then the electronic device can obtain 9 initial connection average information.

[0200] Specifically, the electronic device may group multiple historical connection times in the first connection number set according to the characteristics of the historical period, obtain a third connection number set and a fourth connection number set, and determine the ratio of the first historical total connection number corresponding to the third connection number set to the second historical total connection number corresponding to the fourth connection number set as the connection number ratio corresponding to the first connection number set. Then, the electronic device may obtain 9 connection number ratios.

[0201] The electronic device can combine and process the 9 initial connection average information to generate a connection number matrix 1, and can use the connection number matrix 1 as the connection average information 1 corresponding to the first statistical period; the 9 connection number ratios can be combined and processed to generate connection difference information 1.

[0202] Similarly, for the second statistical period, multiple historical connection times in the historical connection information may be grouped according to the second statistical period and the historical time periods corresponding to each historical connection time in the historical connection information to obtain two first connection time sets.

[0203] For any first connection number set, the electronic device can determine the initial connection average information and the connection number ratio corresponding to the first connection number set according to the multiple historical connection numbers included in the first connection number set. The electronic device can obtain 2 initial connection average information and 2 connection number ratios, and then can determine the arrangement order of the 2 first connection number sets according to the historical time periods corresponding to the 2 first connection number sets, and then can combine the 2 initial connection average information to generate a connection number matrix 2, and the connection number matrix 2 can be used as the connection average information 2 corresponding to the 30-day statistical period; the 2 connection number ratios can be combined to generate connection difference information 2.

[0204] The electronic device can process the connection average information 1, the connection difference information 1, the connection average information 2, and the connection difference information 2 through a preset model to obtain the target connection behavior of the target object in the target time period.

[0205] Optionally, the electronic device may also obtain at least one historical connection prediction behavior corresponding to the target object, and the actual connection behavior corresponding to each historical connection prediction behavior. The electronic device may determine a first accuracy based on at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, and determine an overall accuracy based on the second accuracy of multiple reference objects, and then determine the confidence corresponding to the target object based on the first accuracy and the overall accuracy. The confidence may be used to measure the reliability of the preset model in predicting the target connection behavior of the target object.

[0206] In an embodiment of the present application, the electronic device can obtain historical connection information of the target object and determine at least one statistical period. For any statistical period, the electronic device can group multiple historical connection times in the historical connection information according to the statistical period and the historical time period corresponding to each historical connection time in the historical connection information to obtain multiple first connection time sets, and can determine the connection average information according to the multiple first connection time sets, and can also determine the connection difference information according to the multiple first connection time sets. The electronic device can process at least one connection average information and at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period. The electronic device can also obtain at least one historical connection estimated behavior corresponding to the target object and the actual connection behavior corresponding to each historical connection estimated behavior, and determine the confidence of the preset model in predicting the connection behavior of the target object according to at least one historical connection estimated behavior and the actual connection behavior corresponding to each historical connection estimated behavior. Since the target connection behavior can be comprehensively predicted not only according to the connection average information corresponding to different statistical periods, but also according to the connection difference information corresponding to different statistical periods, the accuracy of predicting the target connection behavior is improved compared with directly predicting the target connection behavior according to the connection average information within the historical duration.

[0207] Figure 5 The present invention provides a schematic diagram of the structure of an object prediction device. Figure 5 The object prediction device 10 includes: a first acquisition module 11, a first determination module 12 and a processing module 13, wherein:

[0208] The first acquisition module 11 is used to acquire historical connection information of the target object, wherein the historical connection information includes multiple historical time periods and the number of historical connections of the target object in each historical time period;

[0209] The first determining module 12 is used to determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period according to the historical connection information, to obtain at least one connection average information and at least one connection difference information;

[0210] The processing module 13 is used to process the at least one connection average information and the at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period.

[0211] The object prediction device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0212] In a possible implementation manner, for any statistical period, the first determining module 12 is specifically configured to:

[0213] According to the statistical period and the historical time period corresponding to each historical connection number in the historical connection information, grouping multiple historical connection numbers in the historical connection information to obtain at least one first connection number set;

[0214] The connection average information and the connection difference information are determined according to the multiple first connection number sets.

[0215] In a possible implementation manner, the first determining module 12 is specifically configured to:

[0216] For any first connection number set, according to the historical time period corresponding to each historical connection number in the first connection number set, multiple historical connection times in the first connection number set are grouped to obtain multiple second connection number sets, and the historical time period corresponding to each historical connection number in the second connection number set is: the same time period in multiple sub-periods within the statistical period;

[0217] The connection average information is determined according to a plurality of second connection number sets in each first connection number set.

[0218] In a possible implementation manner, the first determining module 12 is specifically configured to:

[0219] For any first connection number set, an average value of a plurality of historical connection numbers in each second connection number set included in the first connection number set is determined as the average connection number corresponding to each second connection number set, to obtain a plurality of average connection numbers;

[0220] Determine, according to the multiple average connection times, initial connection average information corresponding to the first connection number set;

[0221] Generate a connection number matrix according to the initial connection average information corresponding to each first connection number set, wherein the connection number matrix includes the initial connection average information corresponding to each first connection number set;

[0222] The connection times matrix is ​​determined as the connection average information.

[0223] In a possible implementation manner, the first determining module 12 is specifically configured to:

[0224] For any first connection number set, a plurality of historical connection numbers in the first connection number set are grouped according to the characteristics of the historical time period to obtain a third connection number set and a fourth connection number set;

[0225] Determine, according to the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set;

[0226] The connection difference information is determined according to the connection number ratio corresponding to each first connection number set.

[0227] In a possible implementation manner, the first determining module 12 is specifically configured to:

[0228] For any first connection count set, the sum of each historical connection count in the third connection count set is determined as the first total historical connection count;

[0229] Determine the sum of each historical connection count in the fourth connection count set as the second total historical connection count;

[0230] A ratio of the first total historical connection times to the second total historical connection times is determined as the connection times ratio.

[0231] The object prediction device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0232] Figure 6 This is a schematic diagram of the structure of another object prediction device provided in an embodiment of the present application. Figure 6 ,exist Figure 5 Based on the embodiment shown, the object prediction device 10 further includes a second acquisition module 14 and a second determination module 15, wherein:

[0233] The second acquisition module 14 is used to acquire at least one historical connection prediction behavior corresponding to the target object and an actual connection behavior corresponding to each historical connection prediction behavior, wherein the at least one historical connection prediction behavior is obtained by historically predicting the target object through the preset model;

[0234] The second determination module 15 is used to determine the confidence of the connection behavior prediction of the target object by the preset model according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior.

[0235] The object prediction device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0236] In a possible implementation manner, the second determining module 15 is specifically configured to:

[0237] Determining a first accuracy of the preset model for estimating the target object according to the at least one historical connection estimation behavior and the actual connection behavior corresponding to each historical connection estimation behavior;

[0238] Determining an overall accuracy based on a second accuracy of each of the multiple reference objects estimated by the preset model;

[0239] A confidence level corresponding to the target object is determined according to the first accuracy and the overall accuracy.

[0240] In a possible implementation manner, the second determining module 15 is specifically configured to:

[0241] determining a first quantity of at least one historical connection estimated behavior;

[0242] Determine, according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, a second number of the historical connection prediction behaviors being consistent with the corresponding actual connection behaviors;

[0243] A ratio of the second number to the first number is determined as a first accuracy.

[0244] The object prediction device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0245] The exemplary embodiment of the present application provides a structural diagram of an electronic device, see Figure 7 The electronic device 20 may include a processor 21 and a memory 22. Exemplarily, the processor 21 and the memory 22 are interconnected via a bus 23.

[0246] The memory 22 stores computer-executable instructions;

[0247] The processor 21 executes the computer-executable instructions stored in the memory 22, so that the processor 21 performs the object prediction method shown in the above method embodiment.

[0248] Accordingly, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the object prediction method described in the above method embodiment.

[0249] Accordingly, an embodiment of the present application may also provide a computer program product, including a computer program, which, when executed by a processor, can implement the object prediction method shown in the above method embodiment.

[0250] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0251] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0252] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0253] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0254] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0255] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0256] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0257] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0258] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An object prediction method, It is characterized in that include: Acquire historical connection information of the target object, wherein the historical connection information includes multiple historical time periods and the number of historical connections of the target object in each historical time period; Determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period according to the historical connection information, to obtain at least one connection average information and at least one connection difference information; The at least one connection average information and the at least one connection difference information are processed through a preset model to determine a target connection behavior of the target object in a target time period.

2. The method according to claim 1, It is characterized in that For any statistical period; according to the historical connection information, determining the connection average information and connection difference information corresponding to the statistical period, including: According to the statistical period and the historical time period corresponding to each historical connection number in the historical connection information, grouping multiple historical connection numbers in the historical connection information to obtain at least one first connection number set; The connection average information and the connection difference information are determined according to the multiple first connection number sets.

3. The method according to claim 2, It is characterized in that Determining the connection average information according to the multiple first connection number sets includes: For any first connection number set, according to the historical time period corresponding to each historical connection number in the first connection number set, multiple historical connection times in the first connection number set are grouped and processed to obtain multiple second connection number sets, and the historical time period corresponding to each historical connection number in the second connection number set is: the same time period in multiple sub-periods within the statistical period; The connection average information is determined according to a plurality of second connection number sets in each first connection number set.

4. The method according to claim 3, It is characterized in that Determining the connection average information according to the plurality of second connection number sets in each first connection number set includes: For any first connection number set, an average value of a plurality of historical connection numbers in each second connection number set included in the first connection number set is determined as the average connection number corresponding to each second connection number set, to obtain a plurality of average connection numbers; Determine, according to the multiple average connection times, initial connection average information corresponding to the first connection number set; Generate a connection number matrix according to the initial connection average information corresponding to each first connection number set, wherein the connection number matrix includes the initial connection average information corresponding to each first connection number set; The connection times matrix is ​​determined as the connection average information.

5. The method according to claim 2, It is characterized in that Determining the connection difference information according to the multiple first connection number sets includes: For any first connection number set, a plurality of historical connection numbers in the first connection number set are grouped according to the characteristics of the historical time period to obtain a third connection number set and a fourth connection number set; Determine, according to the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set; The connection difference information is determined according to the connection number ratio corresponding to each first connection number set.

6. The method according to claim 5, It is characterized in that Determining, according to the third connection number set and the fourth connection number set corresponding to each first connection number set, a connection number ratio corresponding to each first connection number set, comprising: For any first connection count set, the sum of each historical connection count in the third connection count set is determined as the first total historical connection count; Determine the sum of each historical connection count in the fourth connection count set as the second total historical connection count; A ratio of the first total historical connection times to the second total historical connection times is determined as the connection times ratio.

7. The method according to any one of claims 1 to 6, It is characterized in that The method further comprises: Acquire at least one historical connection prediction behavior corresponding to the target object, and an actual connection behavior corresponding to each historical connection prediction behavior, wherein the at least one historical connection prediction behavior is obtained by historically predicting the target object through the preset model; The confidence level of the connection behavior prediction of the target object by the preset model is determined according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior.

8. The method according to claim 7, It is characterized in that Determining, according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, the confidence of the connection behavior prediction of the target object by the preset model, including: Determining a first accuracy of the preset model for estimating the target object according to the at least one historical connection estimation behavior and the actual connection behavior corresponding to each historical connection estimation behavior; Determining an overall accuracy based on a second accuracy of each of the multiple reference objects estimated by the preset model; A confidence level corresponding to the target object is determined according to the first accuracy and the overall accuracy.

9. The method according to claim 8, It is characterized in that Determining a first accuracy of the preset model for estimating the target object according to the at least one historical connection estimation behavior and the actual connection behavior corresponding to each historical connection estimation behavior includes: determining a first quantity of at least one historical connection estimated behavior; Determine, according to the at least one historical connection prediction behavior and the actual connection behavior corresponding to each historical connection prediction behavior, a second number of the historical connection prediction behaviors being consistent with the corresponding actual connection behaviors; A ratio of the second number to the first number is determined as a first accuracy.

10. An object prediction device, It is characterized in that include: A first acquisition module, a first determination module, and a processing module, wherein: The first acquisition module is used to acquire historical connection information of the target object, wherein the historical connection information includes multiple historical time periods and the number of historical connections of the target object in each historical time period; The first determination module is used to determine at least one statistical period, and determine the connection average information and connection difference information corresponding to each statistical period according to the historical connection information, to obtain at least one connection average information and at least one connection difference information; The processing module is used to process the at least one connection average information and the at least one connection difference information through a preset model to determine the target connection behavior of the target object in the target time period.

11. An electronic device, It is characterized in that include: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the electronic device to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images