Bank application offline time prediction method and device, equipment and storage medium

Abstract

The invention relates to the technical field of financial science and technology and deep learning, and discloses a bank application offline time prediction method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining the effective access duration of a target application in each unit time in the past, and inputting the effective access duration into a first time series prediction model; the predicted access duration of the target application in each unit time in the future is obtained, and the date corresponding to the predicted access duration smaller than the access duration threshold value serves as the offline time of the target application. Visibly, the offline time of the target application can be predicted in advance based on the effective access duration of the target application in each unit time in the past through the first time sequence prediction model, so that offline evaluation on the target application can be started in advance, and compared with the prior art, the method can achieve the purpose of improving the application offline efficiency.

Description

Technical Field

[0001] The present invention relates to the fields of financial technology and deep learning technology, and in particular to a method, device, computer equipment and storage medium for predicting offline time of bank applications. Background Art With the continuous development of the times, the number of bank applications is increasing day by day, such as mobile banking apps, auto insurance apps, etc. The use of a large number of applications not only releases the bank's human resources, but also brings users a better service experience. Then, in the development process of various applications, it is necessary to prevent the emergence of zombie applications, which will occupy a lot of development and operation and maintenance manpower costs, as well as server and other resource costs.

[0002] Therefore, when zombie applications are found, it is necessary to initiate a shutdown process for the zombie applications in a timely manner to save manpower and resource costs.

[0003] At present, only when the bank application reaches the day of going offline can it be manually determined whether the bank application needs to be offline. After determining that the bank application needs to be offline, the bank application is evaluated for offline, and after determining that the bank application can be offline, the offline process is executed for the bank application. Therefore, when the bank application is evaluated for offline, the bank application still needs to continue to occupy manpower and resource costs, resulting in low offline efficiency of the bank application. Summary of the invention

[0004] The embodiment of the present invention provides a method, device, computer equipment and storage medium for predicting offline time of bank applications, so as to solve the problem of low offline efficiency of bank applications.

[0005] A method for predicting offline time of bank applications, the method comprising: Acquire historical access data of the target application, wherein the historical access data includes the effective access duration of the target application in each unit time in the past; Inputting the effective access duration into a first time series prediction model to obtain a predicted access duration of the target application in each unit time in the future; Determining whether the predicted access duration is less than a preset access duration threshold; If the predicted access duration is less than the access duration threshold, the date corresponding to the predicted access duration is determined as the offline time of the target application.

[0006] In the above method, optionally, the historical access data also includes the number of valid accesses to the target application in each unit time in the past; After acquiring the historical access data of the target application, the method further includes: Inputting the effective access quantity into a second time series prediction model to obtain the predicted access quantity of the target application in each unit time in the future; Determining whether the predicted number of visits is less than a preset number of visits threshold; If the predicted number of visits is less than the number of visits threshold, the date corresponding to the predicted number of visits is determined as the offline time.

[0007] The above method may optionally be characterized in that, after determining that the date corresponding to the predicted access duration is the offline time of the target application, the method further comprises: Performing an offline evaluation on the target application to determine whether the target application meets a preset offline condition; If the target application meets the offline condition, an offline process is executed for the target application.

[0008] In the above method, optionally, the offline evaluation includes: evaluating from one or more angles including security evaluation, reliability evaluation, performance evaluation, user experience evaluation, compliance evaluation, and commercial benefit evaluation.

[0009] In the above method, optionally, the offline process includes: application data backup, application domain name release, application data cleanup, and application user notification.

[0010] The above method, optionally, before performing offline evaluation on the target application to determine whether the target application meets a preset offline condition, the method further includes: Obtain the current time, and calculate the time difference between the offline time and the current time; If the time difference is less than a preset difference threshold, the target step is executed: an offline evaluation is performed on the target application to determine whether the target application meets a preset offline condition.

[0011] In the above method, optionally, the first time series prediction model is trained in the following manner: Obtain the historical access data before the offline application is offline; The historical access data is input into a basic time series prediction model for iterative training, so as to obtain the first time series prediction model when the basic time series prediction model reaches a preset training end condition.

[0012] A bank application offline time prediction device, comprising: A data acquisition module, used to acquire historical access data of a target application, wherein the historical access data includes the effective access duration of the target application in each unit time in the past; A first prediction module, used for inputting the effective access duration into a first time series prediction model to obtain a predicted access duration of the target application in each unit time in the future; A first judgment module, used to judge whether the predicted access duration is less than a preset access duration threshold; The first determination module is used to determine the date corresponding to the predicted access duration as the offline time of the target application when the predicted access duration is less than the access duration threshold.

[0013] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the above-mentioned methods for predicting offline time of bank applications when executing the computer program.

[0014] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting the offline time of a bank application described in any one of the above is implemented.

[0015] The above-mentioned bank application offline time prediction method, device, computer equipment and storage medium obtain the effective access time of the target application in each unit time in the past, input the effective access time into the first time series prediction model, obtain the predicted access time of the target application in each unit time in the future, and use the date corresponding to the predicted access time less than the access time threshold as the offline time of the target application. It can be seen that in this embodiment, the offline time of the target application can be predicted in advance based on the effective access time of the target application in each unit time in the past through the first time series prediction model. Therefore, the offline evaluation of the target application can be started in advance, and compared with the existing technology, the purpose of improving the offline efficiency of the application can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0017] Figure 1 This is a flow chart of an implementation of a method for predicting offline time of bank applications in one embodiment of the present invention; Figure 2 It is another implementation flow chart of the method for predicting offline time of bank applications in one embodiment of the present invention; Figure 3 It is another implementation flow chart of the method for predicting offline time of bank applications in one embodiment of the present invention; Figure 4 It is another implementation flow chart of the method for predicting offline time of bank applications in one embodiment of the present invention; Figure 5 This is a partial implementation flow chart of a method for predicting offline time of bank applications in one embodiment of the present invention; Figure 6 It is a structural schematic diagram of a device for predicting offline time of bank applications in one embodiment of the present invention; Figure 7 It is a schematic diagram of the structure of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0020] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0021] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0022] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0023] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0024] The present invention discloses a method, device, computer equipment and storage medium for predicting the offline time of a bank application. The method obtains the effective access time of the target application in each unit time in the past, inputs the effective access time into a first time series prediction model, obtains the predicted access time of the target application in each unit time in the future, and uses the date corresponding to the predicted access time less than the access time threshold as the offline time of the target application. It can be seen that in this embodiment, the offline time of the target application can be predicted in advance based on the effective access time of the target application in each unit time in the past through the first time series prediction model. Therefore, the offline evaluation of the target application can be started in advance, and compared with the prior art, the purpose of improving the offline efficiency of the application can be achieved. The following is an explanation through a specific embodiment.

[0025] In one embodiment, if Figure 1 As shown, a method for predicting offline time of bank applications is provided. The method is applicable to electronic devices with data processing capabilities, such as mobile phones, tablet computers, laptop computers, computers or servers. The method in this embodiment specifically includes the following steps: S101: Acquire historical access data of a target application, where the historical access data includes the effective access duration of the target application in each unit time in the past.

[0026] The unit time includes but is not limited to one day, one week or one month.

[0027] In a specific implementation, this embodiment can obtain the effective access time in each unit time since the target application was launched, or the effective access time in each unit time of the target application in the past period of time. Among them, the effective access time refers to the time the user opens the target application when the user has effective interaction in the target application after opening the target application, or the time the user handles effective business in the target application. This embodiment does not limit the conditions for limiting the effective access time. It should be noted that multiple users may open the target application within a unit time. In this case, the effective access duration within the unit time is the sum of the effective access durations of all users.

[0028] S102: Input the effective access duration into the first time series prediction model to obtain the predicted access duration of the target application in each unit time in the future.

[0029] In a specific implementation, the first time series prediction model provided by this embodiment includes but is not limited to an XGBoost model. The effective access time is input into the XGBoost model. The XGBoost model can predict the predicted access time in the next unit time based on the effective access time in different unit times, and then predict the predicted access time in the next unit time based on the predicted access time and the effective access time, and so on, to predict the predicted access time of the target application in each unit time in the future.

[0030] S103: Determine whether the predicted access duration is less than a preset access duration threshold.

[0031] If the predicted access time is less than the preset access time threshold, the date corresponding to the predicted access time is determined as the offline time of the target application, and there is no need to predict the predicted access time of the target application per unit time after that through the first time series prediction model; if the predicted access time is greater than or equal to the preset access time threshold, the predicted access time of the target application per unit time after that continues to be predicted through the first time series prediction model until the predicted access time is less than the preset access time threshold, and the date corresponding to the predicted access time is determined as the offline time of the target application.

[0032] S104: If the predicted access duration is less than the access duration threshold, determine the date corresponding to the predicted access duration as the offline time of the target application.

[0033] It is understandable that if the predicted access time is less than the access time threshold, it means that there are almost no users currently accessing the target application effectively, and the target application cannot provide corresponding services to users. Therefore, the target application has lost its value of existence and it is time for the target application to go offline.

[0034] In a specific implementation, in this embodiment, after the offline time of the target application is predicted by the first time series prediction model, the offline evaluation of the target application can be performed in advance, and then after determining that the target application can be offline, the offline process of the target application is executed on time when the predicted offline time is reached.

[0035] In summary, a method for predicting the offline time of a bank application disclosed in this embodiment obtains the effective access time of the target application in each unit time in the past, and inputs the effective access time into the first time series prediction model to obtain the predicted access time of the target application in each unit time in the future, and takes the date corresponding to the predicted access time less than the access time threshold as the offline time of the target application. It can be seen that in this embodiment, the offline time of the target application can be predicted in advance based on the effective access time of the target application in each unit time in the past through the first time series prediction model, so the offline evaluation of the target application can be started in advance, and compared with the existing technology, the purpose of improving the offline efficiency of the application can be achieved.

[0036] based on Figure 1 In the specific implementation, this embodiment further includes the following steps after step S101: Figure 2 As shown: S105: Input the number of valid visits into the second time series prediction model to obtain the predicted number of visits of the target application in each unit time in the future.

[0037] In a specific implementation, the second time series prediction model provided in this embodiment includes but is not limited to the XGBoost model. The number of valid accesses is input into the XGBoost model. The XGBoost model can predict the predicted number of accesses in the next unit time based on the number of valid accesses in different unit times, and then predict the predicted number of accesses in the next unit time based on the predicted number of accesses and the number of valid accesses, and so on, to predict the predicted number of accesses in each unit time of the target application in the future.

[0038] S106: Determine whether the predicted number of visits is less than a preset number of visits threshold.

[0039] If the predicted number of visits is less than the preset number of visits threshold, the date corresponding to the predicted number of visits is determined to be the offline time of the target application, and there is no need to predict the predicted number of visits to the target application per unit time after that through the first time series prediction model; if the predicted number of visits is greater than or equal to the preset number of visits threshold, the predicted number of visits to the target application per unit time after that continues to be predicted through the first time series prediction model until the predicted number of visits is less than the preset number of visits threshold, and the date corresponding to the predicted number of visits is determined to be the offline time of the target application.

[0040] S107: If the predicted number of visits is less than the threshold value of the number of visits, determine the date corresponding to the predicted number of visits as the offline time of the target application.

[0041] If the predicted number of visits is less than the visit number threshold, it means that the target application currently has almost no users visiting it, and the target application cannot provide corresponding services to users. Therefore, the target application has lost its value of existence, and it is time for the target application to go offline.

[0042] It should be noted that the first time series prediction model and the second time series prediction model in this embodiment can be the same model, or the first time series prediction model and the second time series prediction model can also be different models. When the first time series prediction model and the second time series prediction model are the same time series prediction model, the effective access number and effective access duration of the target application in each unit time in the past can be simultaneously input into the time series prediction model to obtain the predicted access duration and predicted access number in each unit time in the future.

[0043] In one embodiment, in this embodiment, when the predicted number of visits within the same unit time is less than the access number threshold, and the predicted access duration is less than the access duration threshold, the date corresponding to the unit time is determined as the offline time of the target application; when the predicted number of visits within the same unit time is greater than or equal to the access number threshold, and / or the predicted access duration is greater than or equal to the access duration threshold, the predicted access duration and predicted number of visits of the target application in the next unit time are continued to be predicted.

[0044] In another embodiment, in this embodiment, when the predicted number of visits within the same unit time is less than the access number threshold, or the predicted access duration is less than the access duration threshold, the date corresponding to the unit time can be determined as the offline time of the target application; when the predicted number of visits within the same unit time is greater than or equal to the access number threshold, and the predicted access duration is greater than or equal to the access duration threshold, the predicted access duration and predicted number of visits of the target application in the next unit time will continue to be predicted.

[0045] In summary, in this embodiment, the number of valid accesses to the target application in each unit time in the past is obtained, and the valid accesses are input into the second time series prediction model to obtain the predicted number of accesses to the target application in each unit time in the future, and the date corresponding to the predicted number of accesses less than the access number threshold is used as the offline time of the target application. It can be seen that in this embodiment, the offline time of the target application can be predicted in advance based on the number of valid accesses to the target application in each unit time in the past through the second time series prediction model. Therefore, the offline evaluation of the target application can be started in advance, and compared with the existing technology, the purpose of improving the offline efficiency of the application can be achieved.

[0046] based on Figure 1In the specific implementation, after determining the date corresponding to the predicted access duration as the offline time of the target application, this embodiment may also include the following steps: Figure 3 As shown: S108: Perform offline evaluation on the target application to determine whether the target application meets a preset offline condition.

[0047] After completing the offline evaluation of the target application, if the target application meets the offline requirements, it is determined that the target application meets the offline conditions; if the target application does not meet the offline requirements, it is determined that the target application does not meet the offline conditions.

[0048] In a specific implementation, the offline evaluation in this embodiment includes, but is not limited to, evaluating the target application from one or more angles including security evaluation, reliability evaluation, performance evaluation, user experience evaluation, compliance evaluation, and commercial benefit evaluation.

[0049] In one embodiment, the security assessment includes: assessing whether the target application has vulnerabilities and threats, for example, assessing whether the target application has known security vulnerabilities and whether these vulnerabilities have been fixed; assessing whether new security threats may be exposed during the target application's offline process; checking whether the data stored and processed by the target application has been properly protected and whether the data will be leaked or damaged during the offline process; and analyzing whether there are potential security risks left after the target application goes offline, such as uncleaned temporary files, unclosed ports, etc.

[0050] In one embodiment, the reliability assessment includes: evaluating whether the current running status of the application is stable and whether there are frequent crashes or failures; analyzing the dependencies of the application with other systems or services and whether going offline will affect the normal operation of these dependent systems; and checking whether there is an effective backup and recovery mechanism to deal with unexpected situations that may occur during the offline process.

[0051] S109: If the target application meets the offline condition, execute the offline process for the target application.

[0052] If the target application meets the offline conditions, it means that the offline of the target application will hardly have a big impact on the users and the bank itself, and the offline process can be started for the target application. If the target application does not meet the offline conditions, it means that there is still a strong bond between the bank or user and the target application, and the user or bank cannot directly leave the target application. Therefore, the offline process cannot be executed for the target application for the time being.

[0053] In a specific implementation, the offline process of the target application in this embodiment includes: application data backup, application domain name release, application data cleanup, and application user notification.

[0054] In summary, in this embodiment, offline evaluation is performed on the target application that is about to be taken offline, so as to explore the potential commercial value or user dependence between the target application and the user, avoid the target application being taken offline directly according to the offline time and have a greater impact on the bank, and is conducive to improving the rationality and security of the target application being taken offline.

[0055] based on Figure 3 In the specific implementation, before step S108, the method in this embodiment further includes the following steps: Figure 4 As shown: S110: Obtain the current time, and calculate the time difference between the offline time and the current time.

[0056] If the time difference is less than the preset difference threshold, the target step is executed: an offline evaluation is performed on the target application to determine whether the target application meets the preset offline condition.

[0057] The current time is the date of the predicted offline time of the target application.

[0058] In a specific implementation, in this embodiment, the offline time can be subtracted from the current time to obtain the time difference. For example, if the current time is January 1, and the predicted offline time of the target application is January 30, then the time difference between the offline time and the current time is 29 days.

[0059] If the time difference is less than the preset difference threshold, it means that the current time is close to the offline time of the target application, and the offline evaluation of the target application can be started; if the time difference is greater than the preset difference threshold, it means that the current time is still far from the offline time of the target application, and the offline evaluation of the target application can be started when the waiting time difference is greater than or equal to the difference threshold.

[0060] To sum up, in this embodiment, by calculating the time difference between the offline time and the current time, it is possible to avoid performing offline evaluation on the target application too early, resulting in a decrease in the accuracy of the offline evaluation, and to avoid performing offline evaluation on the target application too late, resulting in the target application reaching the offline time but the offline evaluation has not yet ended, resulting in a decrease in the offline efficiency of the target application.

[0061] In a specific implementation, the first time series prediction model in this embodiment is trained in the following manner: Figure 5 As shown: S501: Acquire historical access data of the offline application before it goes offline.

[0062] In this embodiment, the effective access duration of each unit time before the offline application is offline can be obtained, or the effective access duration of each unit time within a certain period of time before the offline application is offline can be obtained. For example, the effective access duration of each day within six months before the offline application is offline, or the effective access duration of each week within one year before the offline application is offline.

[0063] S502: Inputting historical access data into a basic time series prediction model for iterative training, so as to obtain a first time series prediction model when the basic time series prediction model reaches a preset training end condition.

[0064] In one embodiment, the training end condition in this embodiment is that after the basic time series prediction model completes the training of a preset first number of iterations based on historical access data, the basic time series prediction model is determined to be the first time series prediction model.

[0065] In another embodiment, in this embodiment, historical access data can be used as a training set and a test set, and the test set is input into the basic time series prediction model for iterative training. After each iterative training of the basic time series prediction model, the test set is input into the basic time series prediction model for testing. When the accuracy of the basic time series prediction model is higher than 90%, the basic time series prediction model is determined to be the first time series prediction model.

[0066] The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0067] In one embodiment, if Figure 6 As shown, a bank application offline time prediction device is provided, which corresponds to the bank application offline time prediction method in the above embodiment. The bank application offline time prediction device includes a data acquisition module, a model prediction module, a first judgment module and a first determination module. Each functional module is described in detail as follows: The data acquisition module 601 is used to acquire the historical access data of the target application, where the historical access data includes the effective access duration of the target application in each unit time in the past; The first prediction module 602 is used to input the effective access duration into the first time series prediction model to obtain the predicted access duration of the target application in each unit time in the future; The first judgment module 603 is used to judge whether the predicted access time is less than a preset access time threshold; The first determination module 604 is configured to determine, when the predicted access duration is less than the access duration threshold, a date corresponding to the predicted access duration as the offline time of the target application.

[0068] In one embodiment, the historical access data also includes the number of valid accesses of the target application in each unit time in the past; This embodiment also includes: A second prediction module is used to input the number of valid visits into a second time series prediction model to obtain the predicted number of visits to the target application per unit time in the future; A second judgment module is used to judge whether the predicted access quantity is less than a preset access quantity threshold; The second determination module is used to determine the date corresponding to the predicted number of visits as the offline time when the predicted number of visits is less than the threshold value of the number of visits.

[0069] In one embodiment, the present embodiment also includes: The offline evaluation module is used to perform offline evaluation on the target application to determine whether the target application meets the preset offline conditions; The offline execution module is used to execute the offline process for the target application when the target application meets the offline condition.

[0070] In one embodiment, the offline evaluation includes: safety evaluation, reliability evaluation, performance evaluation, user experience evaluation, compliance evaluation, and commercial benefit evaluation from one or more perspectives.

[0071] In one embodiment, it is characterized in that the offline process includes: application data backup, application domain name release, application data cleanup, and application user notification.

[0072] In one embodiment, the present embodiment also includes: The time calculation module is used to obtain the current time and calculate the time difference between the offline time and the current time; The return execution module is used to execute the target step when the time difference is less than the preset difference threshold: perform an offline evaluation on the target application to determine whether the target application meets the preset offline condition.

[0073] In one embodiment, the first time series prediction model is trained in the following manner: Get the historical access data of the offline application before it went offline; The historical access data is input into the basic time series prediction model for iterative training, so as to obtain a first time series prediction model when the basic time series prediction model reaches a preset training end condition.

[0074] The specific definition of the bank application offline time prediction device can be found in the definition of the bank application offline time prediction method mentioned above, which will not be repeated here. Each module in the above-mentioned bank application offline time prediction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0075] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the offline time of a bank application is implemented.

[0076] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the bank application offline time prediction method in the above embodiment is implemented.

[0077] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the bank application offline time prediction method in the above embodiment is implemented. Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0078] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0079] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for predicting offline time of bank applications, characterized in that: The method comprises: Acquire historical access data of the target application, wherein the historical access data includes the effective access duration of the target application in each unit time in the past; Inputting the effective access duration into a first time series prediction model to obtain a predicted access duration of the target application in each unit time in the future; Determining whether the predicted access duration is less than a preset access duration threshold; If the predicted access duration is less than the access duration threshold, the date corresponding to the predicted access duration is determined as the offline time of the target application.

2. The method for predicting offline time of bank applications according to claim 1, characterized in that: The historical access data also includes the number of valid accesses to the target application in each unit time in the past; After acquiring the historical access data of the target application, the method further includes: Inputting the effective access quantity into a second time series prediction model to obtain the predicted access quantity of the target application in each unit time in the future; Determining whether the predicted number of visits is less than a preset number of visits threshold; If the predicted number of visits is less than the number of visits threshold, the date corresponding to the predicted number of visits is determined as the offline time.

3. The method for predicting offline time of bank applications according to any one of claims 1 or 2, characterized in that: After determining that the date corresponding to the predicted access duration is the offline time of the target application, the method further includes: Performing an offline evaluation on the target application to determine whether the target application meets a preset offline condition; If the target application meets the offline condition, an offline process is executed for the target application.

4. The method for predicting offline time of bank applications according to claim 3, characterized in that: The offline evaluation includes: safety evaluation, reliability evaluation, performance evaluation, user experience evaluation, compliance evaluation, and commercial benefit evaluation from one or more angles.

5. The method for predicting offline time of bank applications according to claim 3, characterized in that: The offline process includes: application data backup, application domain name release, application data cleanup, and application user notification.

6. The method for predicting offline time of bank applications according to claim 3, characterized in that: Before performing offline evaluation on the target application to determine whether the target application meets a preset offline condition, the method further includes: Obtain the current time, and calculate the time difference between the offline time and the current time; If the time difference is less than a preset difference threshold, the target step is executed: an offline evaluation is performed on the target application to determine whether the target application meets a preset offline condition.

7. The method for predicting offline time of bank applications according to claim 1, characterized in that: The first time series prediction model is trained in the following way: Obtain the historical access data before the offline application is offline; The historical access data is input into a basic time series prediction model for iterative training, so as to obtain the first time series prediction model when the basic time series prediction model reaches a preset training end condition.

8. A bank application offline time prediction device, characterized in that: include: A data acquisition module, used to acquire historical access data of a target application, wherein the historical access data includes the effective access duration of the target application in each unit time in the past; A first prediction module, used for inputting the effective access duration into a first time series prediction model to obtain a predicted access duration of the target application in each unit time in the future; A first judgment module, used to judge whether the predicted access duration is less than a preset access duration threshold; The first determination module is used to determine, when the predicted access duration is less than the access duration threshold, a date corresponding to the predicted access duration as an offline time of the target application.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the bank application offline time prediction method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the bank application offline time prediction method described in any one of claims 1 to 7 is implemented.

Images