Early warning method and device, electronic equipment and readable storage medium

Abstract

The present disclosure provides a pre-warning method and device, electronic equipment and readable storage medium, relating to the technical field of artificial intelligence such as cloud service, big data and deep learning. The pre-warning method comprises: determining a target cloud product, and obtaining predicted resource consumption of the target cloud product at a future target time; obtaining target available resources of the target cloud product at the future target time according to product information of the target cloud product and the future target time; and generating a pre-warning result corresponding to the target cloud product according to the target available resources and the predicted resource consumption. The present disclosure achieves the purpose of automatically warning the cloud product used by the user, and improves the accuracy when warning the cloud product.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, in particular to the technical field of artificial intelligence such as cloud computing, big data, deep learning, and the like, and provides a pre-warning method and device, an electronic device, and a readable storage medium. BACKGROUND

[0002] Cloud products usually have two delivery modes, one is prepayment, and the other is postpayment. When using the postpayment payment mode, the asset balance of a user has a great influence on whether the cloud product can be normally used. If the asset balance of the user is small, it will lead to a charge failure, which seriously affects the normal use of the cloud product by the user; if the asset balance of the user is large, it will affect the use or planning of the user's funds. SUMMARY

[0003] According to a first aspect of the present disclosure, a pre-warning method is provided, comprising: determining a target cloud product, and obtaining a predicted resource consumption of the target cloud product at a future target time; according to product information of the target cloud product and the future target time, obtaining a target available resource of the target cloud product at the future target time; and according to the target available resource and the predicted resource consumption, generating a pre-warning result corresponding to the target cloud product.

[0004] According to a second aspect of the present disclosure, a pre-warning device is provided, comprising: a prediction unit configured to determine a target cloud product, and obtain a predicted resource consumption of the target cloud product at a future target time; a processing unit configured to, according to product information of the target cloud product and the future target time, obtain a target available resource of the target cloud product at the future target time; and a pre-warning unit configured to, according to the target available resource and the predicted resource consumption, generate a pre-warning result corresponding to the target cloud product.

[0005] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0006] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the method described above.

[0007] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method described above.

[0008] From the above technical solutions, it can be seen that the present disclosure can achieve the purpose of automatically warning the cloud product used by the user, and by combining the product information of the target cloud product and the future target time, the target available resources can be more accurately obtained, thereby improving the accuracy when warning the cloud product.

[0009] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme and do not constitute a limitation on the present disclosure. Among them:

[0011] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure;

[0012] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure;

[0014] Figure 4 is a schematic diagram according to the fourth embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram according to the fifth embodiment of the present disclosure;

[0016] Figure 6 is a schematic diagram according to the sixth embodiment of the present disclosure;

[0017] Figure 7 is a block diagram of an electronic device for implementing the warning method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, the description below omits the description of well-known functions and mechanisms.

[0019] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure. As Figure 1 shown, the warning method of the present embodiment specifically includes the following steps:

[0020] S101, determine a target cloud product, and obtain predicted resource consumption of the target cloud product at a future target time;

[0021] S102, obtain target available resources of the target cloud product at the future target time according to product information of the target cloud product and the future target time;

[0022] S103, generate a warning result corresponding to the target cloud product according to the target available resources and the predicted resource consumption.

[0023] The warning method of the embodiment first determines a target cloud product, and obtains predicted resource consumption of the target cloud product at a future target time, then obtains target available resources of the target cloud product at the future target time according to product information of the target cloud product and the future target time, and finally generates a warning result corresponding to the target cloud product according to the target available resources and the predicted resource consumption. The embodiment can achieve the purpose of automatically warning the cloud product used by the user, and can more accurately obtain the target available resources by combining the product information of the target cloud product and the future target time, thereby improving the accuracy when warning the cloud product.

[0024] When the embodiment performs S101 to determine the target cloud product, an optional implementation manner that can be adopted is: obtaining at least one cloud product corresponding to the target account; obtaining a priority of the at least one cloud product; and taking the cloud product with a priority meeting a requirement as the target cloud product.

[0025] The at least one cloud product obtained by the embodiment performing S101 is a cloud product used by a target user corresponding to the target account on a cloud platform.

[0026] It can be understood that the resource in the embodiment can be currency, or other specific real resources or virtual resources, which are not limited by the embodiment. For example, the resource consumption in the embodiment can be a consumption amount required for using the cloud product, and correspondingly, the available resource can be an asset in the target account.

[0027] When the embodiment performs S101 to obtain the priority of the at least one cloud product, an optional implementation manner that can be adopted is: obtaining historical resource data activity corresponding to each cloud product; and determining the cloud product corresponding to higher historical resource data activity as the cloud product with a higher corresponding priority.

[0028] Optionally, for any cloud product, the average historical resource data activity of all accounts corresponding to the cloud product is obtained, and the average historical resource data activity is taken as the historical resource data activity, wherein the average historical resource data activity is the sum of the historical resource data activities of the accounts corresponding to the cloud product divided by the number of the accounts, and the all accounts refer to the accounts that have existed historically corresponding to the cloud product.

[0029] Alternatively, for any cloud product, the historical resource data activity of the account corresponding to the cloud product is obtained, and the historical resource data activity of the account corresponding to the cloud product is taken as the historical resource data activity corresponding to the cloud product.

[0030] In the embodiment, the historical resource data activity corresponding to each cloud product obtained in S101 can be preset, that is, the embodiment can preset the priority of each cloud product.

[0031] In the embodiment, when S101 is performed, the historical resource data activity of each cloud product can also be obtained according to the information such as the resource consumption speed, resource replenishment frequency and resource replenishment amount of each cloud product in the historical time, for example, the faster the resource consumption speed, the higher the historical resource data activity, the higher the resource replenishment frequency, the higher the historical resource data activity, and the larger the resource replenishment amount, the higher the historical resource data activity.

[0032] In the embodiment, when S101 is performed, the cloud product with the priority meeting the requirement is taken as the target cloud product, and each cloud product can be sequentially taken as the target cloud product in the order from high to low priority, so that only one cloud product is warned in one pre-warning process, and the higher the priority of the target cloud product, the more important the target cloud product, and thus the target cloud product with a higher importance is preferentially warned.

[0033] Correspondingly, after the pre-warning of the current target cloud product is completed, the next target cloud product is determined in the same way, and the pre-warning of the target cloud product is performed, so that the pre-warning results corresponding to each target cloud product are sequentially generated.

[0034] In addition, in the embodiment, when S101 is performed, one cloud product randomly selected from the cloud products can also be taken as the target cloud product, so that after the pre-warning of the current target cloud product is completed, other cloud products are randomly selected for pre-warning.

[0035] In the embodiment, after S101 is performed to determine the target cloud product, the predicted resource consumption of the target cloud product at a future target time is obtained.

[0036] In the execution of S101, the embodiment first determines a future target time, and then acquires the predicted resource consumption of the target cloud product at the future target time; the future target time in the embodiment can be a future time point or a future time period; the number of future target times can be one or multiple.

[0037] In the execution of S101 to determine the future target time, the embodiment can take the time input by the input end or the time selected by the input end as the future target time; or take a time that is a preset time interval away from the current time as the future target time, for example, the current time is March 28, and the preset time interval is 1 day, then the embodiment takes March 29 as the future target time.

[0038] In the execution of S101 to acquire the predicted resource consumption of the target cloud product at the future target time, the embodiment can take the average value of the historical resource consumption of the target cloud product within a preset number of days before the future target time as the predicted resource consumption.

[0039] It can be understood that if the embodiment determines multiple future target times, for example, the time in the next week, the embodiment will obtain the predicted resource consumption of the target cloud product corresponding to each future target time respectively in the execution of S101.

[0040] After the execution of S101 to acquire the predicted resource consumption of the target cloud product at the future target time, the embodiment executes S102 to acquire the target available resource of the target cloud product at the future target time according to the product information of the target cloud product and the future target time.

[0041] Since the target account of the target user contains multiple types of resources, such as cash, coupons, and points, and different types of resources usually correspond to different use conditions, for example, the coupons have product type or use time restrictions, the embodiment needs to filter the resources in the target account according to the product information of the target cloud product and the future target time, so as to improve the accuracy of the acquired target available resource.

[0042] Specifically, in the execution of S102 to acquire the target available resource of the target cloud product at the future target time according to the product information of the target cloud product and the future target time, the optional implementation manner that can be adopted by the embodiment is: acquiring the current available resource of the target account; selecting a resource that meets a preset condition from the current available resource as the target available resource, the resource that meets the preset condition includes: the product information applicable to the resource includes the product information of the target cloud product, and the resource meets the availability requirement at the future target time; in the embodiment, the product information of the target cloud product can be the name of the target cloud product, the type of the target cloud product, and the like.

[0043] For example, if the resource list R of the current available resources obtained by the embodiment is {cash 1, coupon 1, coupon 2, points 1}, if the target cloud product is cloud product 1, and the future target time is Tuesday, if the product type of the coupon 1 is limited to cloud product 2, and the available time of the points 1 is the weekend, then the resource list R' of the target available resources obtained by the embodiment executing S102 is {cash 1, coupon 2}.

[0044] Since the embodiment involves pre-warning multiple cloud products, considering that after a pre-warning, the user resources in the target account will be at least partially occupied, the embodiment proposes to obtain the available resources in the target account corresponding to different times according to the number of currently generated pre-warning results, so as to improve the accuracy of obtaining the current available resources.

[0045] The optional implementation manner that can be adopted by the embodiment when executing S102 to obtain the current available resources of the target account is: obtaining the number of currently generated pre-warning results; obtaining the current available resources of the target account according to the number of generated pre-warning results.

[0046] For example, if it is the first pre-warning, the current available assets obtained by the embodiment executing S102 are all the resources of the target account; if it is not the first pre-warning, the current available resources obtained by the embodiment executing S102 are the subtraction result between the current available assets obtained in the previous pre-warning and the predicted resource consumption obtained in the previous pre-warning.

[0047] That is, the embodiment filters the target available resources from the current available resources of the target account according to the product information of the target cloud product and the future target time, avoids errors in obtaining the target available resources, and improves the accuracy of the obtained target available resources.

[0048] When executing S102 to obtain the current available resources of the target account according to the number of generated pre-warning results, the embodiment can also sort the obtained current available resources according to at least one of the priority of the resource category, the available time of the resource, and the numerical size of the resource; wherein the priority of the resource category can be that the coupon is the first priority, the points are the second priority, and the cash is the third priority, and the assets with higher priority are deducted first.

[0049] When executing S102 to select the resources meeting the preset conditions from the current available resources as the target available resources, the embodiment can also combine the limit of resource use, such as the daily limit, the weekly limit, or the single product limit, and select the resources that do not exceed the limit from the resources that can be used by the target cloud product at the future target time as the target available resources, so as to further improve the accuracy of the obtained target available resources.

[0050] For example, if the current early warning is the first early warning, if the target cloud product can use the resource of 100 yuan in the future target time, if the single product limit of the coupon 2 is 40 yuan, the resource list R' of the target available resource obtained by the embodiment executing S102 is {cash 1, 40 yuan in the coupon 2}.

[0051] After the embodiment executing S102 obtains the target available resource of the target cloud product at the future target time, S103 is executed to generate the early warning result corresponding to the target cloud product according to the target available resource and the predicted resource consumption.

[0052] When the embodiment executing S103 generates the early warning result corresponding to the target cloud product according to the target available resource and the predicted resource consumption, an optional implementation manner that can be adopted is that the early warning result corresponding to the target cloud product is generated in the case that the target available resource is less than or equal to the predicted resource consumption.

[0053] The embodiment executing S103 determines that the target available resource is greater than the predicted resource consumption, which means that the assets in the target account of the target user are relatively abundant, so that the early warning result does not need to be generated.

[0054] After the embodiment executing S103 generates the early warning result corresponding to the target cloud product, an output early warning result operation can also be executed, that is, the early warning result is sent to the target user.

[0055] When the embodiment executing S103 outputs the early warning result, an optional implementation manner that can be adopted is that a notification mode corresponding to the priority of the target cloud product is obtained; the early warning result is output by using the notification mode corresponding to the priority, so as to improve the intelligence of the notification.

[0056] For example, if the priority of the target cloud product obtained by the embodiment is priority 1, if the sending mode corresponding to the priority 1 is telephone notification or using a high notification frequency (for example, once every minute or multiple times every hour), the early warning result is output by using the above sending mode.

[0057] The embodiment can further set a termination condition, for example, after the target user completes resource replenishment or the target user clicks a specific button, the output of the early warning result is stopped.

[0058] After the embodiment executing S103 generates the early warning result corresponding to the target cloud product, it can be switched to executing step S101 to determine the target cloud product, and this continues until the early warning of all cloud products corresponding to the target account is completed.

[0059] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure. As Figure 2As shown, when performing S101, the embodiment specifically includes the following steps:

[0060] S201, acquiring first feature data of the target cloud product corresponding to a historical time;

[0061] S202, training a neural network model according to the first feature data, to obtain a resource consumption prediction model corresponding to the target cloud product;

[0062] S203, inputting second feature data of the target cloud product corresponding to the future target time into the resource consumption prediction model, and taking an output result of the resource consumption prediction model as the predicted resource consumption.

[0063] That is, the embodiment trains a resource consumption prediction model according to historical data corresponding to the target cloud product, and then uses the resource consumption prediction model to obtain the predicted resource consumption of the target cloud product at the future target time. Different target cloud products correspond to different resource consumption prediction models, which can improve the accuracy of the obtained predicted resource consumption.

[0064] When performing S201, the embodiment first determines a historical time, and then acquires first feature data of the target cloud product corresponding to the historical time. The first feature data includes historical resource consumption of the target cloud product at the historical time. The historical time in the embodiment can be a time point or a time period.

[0065] The first feature data of the target cloud product corresponding to the historical time acquired by the embodiment when performing S201 includes at least one of user feature data, product feature data, and consumption feature data corresponding to the historical time. The embodiment pre-stores feature data corresponding to different times in the server, so that the feature data can be acquired according to the determined historical time. The acquired feature data is a numerical value corresponding to different features.

[0066] The user feature data corresponding to the historical time acquired by the embodiment when performing S201 can include at least one of the following data: whether the user is real-name (for example, 1 for yes and 0 for no), real-name authentication type of the user (for example, 0 for no authentication, 1 for personal authentication, 2 for organization authentication, 3 for enterprise authentication, etc.), first-level industry classification of the user (numerical mapping according to national economic industry classification and code), second-level industry classification of the user (numerical mapping according to national economic industry classification and code), VIP level (for example, 0 for ordinary user, 1 for VIP, and 2 for VVIP), user type (for example, 0 for self-registration, 1 for business opportunity mining, 2 for project cooperation, and 3 for group relationship), and account validity duration of the user.

[0067] The product feature data corresponding to the historical time obtained by the embodiment in S201 can include at least one of the following data: a basic configuration price of the product corresponding to the minimum time unit, whether the product is on promotion (for example, 1 for yes and 0 for no), a price difference of the product (for example, a unit price difference between the same day or the same period), a use time of the product, a total consumption of the product, a difference between the price set by the user and the basic configuration price, and the like.

[0068] The consumption feature data corresponding to the historical time obtained by the embodiment in S201 can include at least one of the following data: resource consumption of the user in the historical time, resource consumption of the user in the historical time yesterday, daily resource consumption of the user in the historical time last week, daily resource consumption of the user in the historical time last month, daily resource consumption of the total consumption of the user, day of the week of the historical time (for example, 1-7 for Monday to Sunday in turn), month of the historical time (for example, 1-12 for January to December in turn), and date of the historical time (for example, 1-31 for January 1st to January 31st in turn).

[0069] If the first feature data obtained by the embodiment in S201 is different features, the embodiment in S201 can convert the values corresponding to the features obtained by the conversion according to different features and their corresponding value conversion modes, and take the converted values as the first feature data.

[0070] The optional implementation manner that can be used by the embodiment in S202 to train the neural network model according to the first feature data to obtain the resource consumption prediction model corresponding to the target cloud product is as follows: input the first feature data into the neural network model to obtain the predicted resource consumption output by the neural network model; calculate the loss function value according to the historical resource consumption and the predicted resource consumption; adjust the parameters of the neural network model according to the calculated loss function value until the neural network model converges, and obtain the resource consumption prediction model.

[0071] It can be understood that the neural network model in the embodiment can be a regression model, and different feature data corresponds to different parameters in the regression model, so the training process of the regression model is the process of adjusting the parameters corresponding to different feature data.

[0072] The embodiment in S203 first obtains the second feature data corresponding to the future target time of the target cloud product (the obtaining manner of the second feature data is the same as that of the first feature data, except that the second feature data does not include the resource consumption of the future target time), and then inputs the obtained second feature data into the resource consumption prediction model, which can output the predicted resource consumption corresponding to the future target time.

[0073] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure. Figure 3The flowchart of training the resource consumption prediction model corresponding to different target cloud products is shown in this embodiment: in Figure 3 different feature modules are used to obtain different feature data; if the obtained feature data is a feature, the obtained feature is converted into a numerical value by a data preprocessing module, and the conversion result is taken as first feature data, i.e., a data set, different cloud products correspond to different data sets; according to the data sets corresponding to different cloud products, resource consumption prediction models corresponding to different cloud products are respectively trained on a machine learning regression model training platform, and the neural network model used for training is a regression model.

[0074] Figure 4 is a schematic diagram according to the fourth embodiment of the present disclosure. Figure 4 The flowchart of this embodiment when warning the product x is shown: a warning configuration module is used to obtain the resource consumption prediction model N corresponding to the product x from the machine learning model training platform; the machine learning model training platform is used to train the resource consumption model N corresponding to the product x, the resource consumption model N is a regression model, and the predicted resource consumption of the product x at the future target time is obtained using the obtained resource consumption prediction model N; a user resource module is used to obtain the current available resources of the target account, obtain the target available resources of the product x, and perform resource matching on the target available resources and the predicted resource consumption, and obtain a warning result according to the matching result; a message notification module is used to obtain the warning notification configuration from the warning configuration module to perform message notification, specifically, the target user is notified according to the preconfigured notification frequency and notification mechanism.

[0075] Figure 5 is a schematic diagram according to the fifth embodiment of the present disclosure. Figure 5 The flowchart of this embodiment when warning multiple target cloud products is shown, and one target cloud product is warned by a multi-dimensional matching method; the first dimension is the product, which determines the target cloud product; the second dimension is the resource category, which is used to obtain the current available resources R of the target account corresponding to different resource categories; the third dimension is the resource verification, which is used to obtain the target available resources R' of the target cloud product at the future target time; the fourth dimension is the resource matching, which is used to match the target available resources with the predicted resource consumption; after the warning of the target cloud product x is completed, the next target cloud product y is continued to be warned.

[0076] Figure 6 is a schematic diagram according to the sixth embodiment of the present disclosure. As shown in Figure 6 The warning device 600 of this embodiment includes:

[0077] a prediction unit 601, configured to determine a target cloud product and obtain predicted resource consumption of the target cloud product at a future target time;

[0078] The processing unit 602 is configured to acquire target available resources of the target cloud product at the future target time according to product information of the target cloud product and the future target time.

[0079] The early warning unit 603 is configured to generate an early warning result corresponding to the target cloud product according to the target available resources and the predicted resource consumption.

[0080] In the process of determining the target cloud product, the prediction unit 601 can adopt an optional implementation manner: acquiring at least one cloud product corresponding to the target account; acquiring a priority of the at least one cloud product; and taking the cloud product with a priority meeting a requirement as the target cloud product.

[0081] The at least one cloud product corresponding to the target account acquired by the prediction unit 601 is a cloud product used by a target user corresponding to the target account on a cloud platform.

[0082] In the process of acquiring the priority of the at least one cloud product, the prediction unit 601 can adopt an optional implementation manner: acquiring historical resource data activity degrees corresponding to each cloud product; and taking the cloud product corresponding to a higher historical resource data activity degree as the cloud product corresponding to a higher priority.

[0083] Optionally, for any cloud product, the prediction unit 601 acquires an average historical resource data activity degree of all accounts corresponding to the cloud product, and takes the average historical resource data activity degree as the historical resource data activity degree, where the average historical resource data activity degree is a sum of historical resource data activity degrees of each account corresponding to the cloud product divided by the number of accounts, and the all accounts refer to accounts that have historically existed and correspond to the cloud product.

[0084] Alternatively, for any cloud product, the prediction unit 601 acquires a historical resource data activity degree of the account corresponding to the cloud product, and takes the historical resource data activity degree of the account corresponding to the cloud product as the historical resource data activity degree corresponding to the cloud product.

[0085] The historical resource data activity degrees corresponding to each cloud product acquired by the prediction unit 601 can be preset, that is, the priority of each cloud product is preset in this embodiment.

[0086] The prediction unit 601 can also acquire the historical resource data activity degrees of each cloud product according to information such as a resource consumption speed, a resource replenishment frequency, and a resource replenishment amount of each cloud product at a historical time, for example, the faster the resource consumption speed, the higher the historical resource data activity degree, the higher the resource replenishment frequency, the higher the historical resource data activity degree, and the larger the resource replenishment amount, the higher the historical resource data activity degree.

[0087] When the prediction unit 601 takes the cloud product meeting the priority requirement as the target cloud product, the prediction unit 601 can take each cloud product as the target cloud product in turn according to the order from high to low of the priority, so that the prediction unit 601 only gives a warning to one cloud product in one early warning process. The higher the priority of the target cloud product is, the more important the target cloud product is, and thus the prediction unit 601 gives a warning to the target cloud product with a higher importance in priority.

[0088] Correspondingly, after the early warning to the current target cloud product is completed, the prediction unit 601 determines the next target cloud product in the same manner and gives a warning to the target cloud product, so as to generate the early warning result corresponding to each target cloud product in turn.

[0089] In addition, when determining the target cloud product, the prediction unit 601 can also randomly select one cloud product from the cloud products as the target cloud product, so as to randomly select other cloud products for early warning after the early warning to the current target cloud product is completed.

[0090] After determining the target cloud product, the prediction unit 601 obtains the predicted resource consumption of the target cloud product at a future target time.

[0091] The prediction unit 601 first determines the future target time and then obtains the predicted resource consumption of the target cloud product at the future target time. The future target time in this embodiment can be a time point or a time period. The number of future target times can be one or more.

[0092] When determining the future target time, the prediction unit 601 can take the time input by the input end or the time selected by the input end as the future target time, or take the time with a preset time interval from the current time as the future target time.

[0093] When obtaining the predicted resource consumption of the target cloud product at the future target time, the prediction unit 601 can take the average value of the historical resource consumption of the target cloud product within a preset number of days before the future target time as the predicted resource consumption.

[0094] When obtaining the predicted resource consumption of the target cloud product at the future target time, the prediction unit 601 can also use the following manner: obtaining first feature data corresponding to a historical time of the target cloud product; training a neural network model according to the first feature data to obtain a resource consumption prediction model corresponding to the target cloud product; inputting second feature data corresponding to the future target time of the target cloud product into the resource consumption prediction model, and taking the output result of the resource consumption prediction model as the predicted resource consumption.

[0095] That is, the prediction unit 601 trains a resource consumption prediction model according to historical data of a corresponding target cloud product, and then uses the resource consumption prediction model to obtain a predicted resource consumption of the target cloud product at a future target time, and different target cloud products correspond to different resource consumption prediction models, which can improve the accuracy of the obtained predicted resource consumption.

[0096] The prediction unit 601 first determines a historical time, and then obtains first feature data of the target cloud product corresponding to the historical time, the first feature data including historical resource consumption of the target cloud product at the historical time; wherein the historical time in this embodiment can be a time point or a time period.

[0097] The first feature data of the target cloud product corresponding to the historical time obtained by the prediction unit 601 includes at least one of user feature data, product feature data and consumption feature data corresponding to the historical time; this embodiment will pre-store feature data corresponding to different times in the server, so that the feature data can be obtained according to the determined historical time, and the obtained feature data is a numerical value corresponding to different features.

[0098] If the first feature data obtained by the prediction unit 601 is different features, the prediction unit 601 can convert the numerical value corresponding to the feature obtained by conversion according to different features and their corresponding numerical value conversion mode, as the first feature data.

[0099] When the prediction unit 601 trains a neural network model according to the first feature data to obtain a resource consumption prediction model corresponding to the target cloud product, an optional implementation manner that can be used by the prediction unit 601 is: inputting the first feature data into the neural network model to obtain a predicted resource consumption output by the neural network model; calculating a loss function value according to the historical resource consumption and the predicted resource consumption; adjusting parameters of the neural network model according to the calculated loss function value until the neural network model converges, and obtaining the resource consumption prediction model.

[0100] The prediction unit 601 first obtains second feature data of the target cloud product corresponding to the future target time (the obtaining manner of the second feature data is the same as that of the first feature data, except that the second feature data does not include resource consumption of the future target time), and then inputs the obtained second feature data into the resource consumption prediction model, which can output a predicted resource consumption corresponding to the future target time.

[0101] It can be understood that if the prediction unit 601 determines multiple future target times, for example, a week in the future, the prediction unit 601 will obtain a predicted resource consumption of the target cloud product corresponding to each future target time.

[0102] After the prediction unit 601 obtains the predicted resource consumption of the target cloud product at the future target time, the processing unit 602 obtains the target available resource of the target cloud product at the future target time according to the product information of the target cloud product and the future target time.

[0103] When the processing unit 602 obtains the target available resource of the target cloud product at the future target time according to the product information of the target cloud product and the future target time, an optional implementation manner that can be adopted by the processing unit 602 is as follows: obtaining the current available resource of the target account; selecting a resource meeting a preset condition from the current available resource as the target available resource, wherein the resource meeting the preset condition includes that the product information applicable to the resource includes the product information of the target cloud product, and the resource meets the availability requirement at the future target time; in this embodiment, the product information of the target cloud product can be the name of the target cloud product, the type of the target cloud product, and the like.

[0104] Since the embodiment can involve the pre-warning of multiple cloud products, and after a pre-warning, the user resource in the target account is at least partially occupied, the processing unit 602 needs to obtain the available resource in the target account corresponding to different times according to the number of times of the pre-warning result that has been generated.

[0105] When the processing unit 602 obtains the current available resource of the target account, an optional implementation manner that can be adopted by the processing unit 602 is as follows: obtaining the number of times of the pre-warning result that has been generated; obtaining the current available resource of the target account according to the number of times of the pre-warning result that has been generated.

[0106] That is, the processing unit 602 selects the target available resource from the current available resource of the target account according to the product information of the target cloud product and the future target time, avoids errors in obtaining the target available resource, and improves the accuracy of the obtained target available resource.

[0107] When the processing unit 602 obtains the current available resource of the target account according to the number of times of the pre-warning result that has been generated, the processing unit 602 can also sort the obtained current available resource according to at least one of the priority of the resource category, the available time of the resource, and the numerical size of the resource; wherein the priority of the resource category can be that the coupon is the first priority, the points return is the second priority, and the cash is the third priority, and the assets with higher priority are deducted first.

[0108] When the processing unit 602 selects the resource meeting the preset condition from the current available resource as the target available resource, the processing unit 602 can also combine the limit of the resource usage, such as the daily limit, the weekly limit, or the single product limit, and select the resource that does not exceed the limit from the resource that can be used by the target cloud product at the future target time as the target available resource, so as to further improve the accuracy of the obtained target available resource.

[0109] After the processing unit 602 obtains the target available resource of the target cloud product at the future target time, the pre-warning unit 603 generates a pre-warning result of the corresponding target cloud product according to the target available resource and the predicted resource consumption.

[0110] When generating the pre-warning result of the corresponding target cloud product according to the target available resource and the predicted resource consumption, the pre-warning unit 603 can adopt an optional implementation manner that: in a case where it is determined that the target available resource is less than or equal to the predicted resource consumption, the pre-warning result of the corresponding target cloud product is generated.

[0111] If the pre-warning unit 603 determines that the target available resource is greater than the predicted resource consumption, it means that the assets in the target account of the target user are relatively abundant, and thus there is no need to generate the pre-warning result.

[0112] After generating the pre-warning result of the corresponding target cloud product, the pre-warning unit 603 can further perform an output pre-warning result operation, that is, sending the pre-warning result to the target user.

[0113] When outputting the pre-warning result, the pre-warning unit 603 can adopt an optional implementation manner that: obtaining a notification mode corresponding to the priority of the target cloud product; and outputting the pre-warning result by using the notification mode corresponding to the priority, so as to improve the intelligence of the notification.

[0114] The pre-warning unit 603 can further set a termination condition, for example, after the target user completes resource replenishment or the target user clicks a specific button, the output of the pre-warning result is stopped.

[0115] After generating the pre-warning result of the corresponding target cloud product, the pre-warning unit 603 can turn to the prediction unit 601 to determine the target cloud product, and continuously perform the above operations until the pre-warning of all cloud products corresponding to the target account is completed.

[0116] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0117] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0118] As Figure 7FIG. 1 illustrates a block diagram of an electronic device according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown in FIG. 1, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0119] As shown in FIG. 7, the device 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded into a random access memory (RAM) 703 from a storage unit 708. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704. Figure 7

[0120] Various components in the device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, a speaker, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0121] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs various methods and processes described above, such as the early warning method. For example, in some embodiments, the early warning method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 708.

[0122] ​In some embodiments, portions or all of the computer program can be loaded onto the apparatus 700 via the ROM 702 and / or the communications unit 709. When the computer program is loaded onto the RAM 703 and executed by the computer unit 701, one or more steps of the early warning method described above can be performed. Alternatively, in other embodiments, the computer unit 701 can be configured, by any suitable means (for example, by means of firmware), to perform the early warning method.

[0123] Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0124] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general or special purpose computer, special purpose computer, or other programmable processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0125] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0126] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0127] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0128] The computer system can include clients and servers. This relationship can be. remote, where each server is stored on a remote computer from a client. The clients and the servers can be connected through a communication network. The relationship can be a client-server relationship over a network. A server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of large management difficulty and weak business scalability in traditional physical hosts and VPS services (Virtual Private Server, or VPS for short). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0129] It should be understood that the steps shown above can be reordered, added to, or deleted from. For example, the steps described in the present disclosure can be executed in parallel, in sequence, or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

[0130] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An early warning method, comprising: Identify the target cloud product; Obtain the first feature data of the target cloud product corresponding to the historical time. Based on the first feature data, a neural network model is trained to obtain a resource consumption prediction model corresponding to the target cloud product; The second feature data of the target cloud product corresponding to the future target time is input into the resource consumption prediction model, and the output of the resource consumption prediction model is used as the predicted resource consumption of the target cloud product at the future target time. The number of times a warning result has been generated is obtained, and the current available resources of the target account are obtained based on the number of times. The target account is the account corresponding to the target cloud product, and the current available resources include resources of various categories. Select resources that meet preset conditions from the currently available resources as the target available resources for the target cloud product at the target future time. The resources that meet the preset conditions include: the product information applicable to the resource includes the product information of the target cloud product, and the resource meets the availability requirements at the target future time. Based on the target available resources and the predicted resource consumption at the corresponding future target time, an early warning result is generated for the target cloud product.

2. The method according to claim 1, wherein, The identified target cloud products include: Obtain at least one cloud product corresponding to the target account; Obtain the priority of the at least one cloud product; Cloud products that meet the priority requirements will be selected as the target cloud products.

3. The method according to any one of claims 1-2, wherein, The step of generating a warning result corresponding to the target cloud product based on the target available resources and the predicted resource consumption includes: If the target available resources are determined to be less than or equal to the predicted resource consumption, an early warning result corresponding to the target cloud product is generated.

4. The method according to any one of claims 1-3, further comprising: After generating the warning result corresponding to the target cloud product, obtain the notification method corresponding to the priority of the target cloud product; The warning result is output using the notification method corresponding to the priority.

5. The method according to claim 2, wherein obtaining the priority of the at least one cloud product includes: Obtain historical resource activity data for each corresponding cloud product; The cloud products with higher historical resource data activity levels are assigned higher priority.

6. The method according to claim 2, wherein selecting cloud products that meet the priority requirements as the target cloud products includes: In descending order of priority, each cloud product is selected as the target cloud product. The generation of early warning results corresponding to the target cloud product includes: The system generates warning results for each target cloud product in sequence.

7. A warning device, comprising: Prediction unit, used to determine target cloud product. The prediction unit is also used to obtain the first feature data of the target cloud product corresponding to the historical time. Based on the first feature data, a neural network model is trained to obtain a resource consumption prediction model corresponding to the target cloud product; The second feature data of the target cloud product corresponding to the future target time is input into the resource consumption prediction model, and the output of the resource consumption prediction model is used as the predicted resource consumption of the target cloud product at the future target time. The processing unit is used to obtain the number of times the current warning result has been generated, and to obtain the current available resources of the target account based on the number of times. The target account is the account corresponding to the target cloud product, and the current available resources include resources of various categories. Select resources that meet preset conditions from the currently available resources as the target available resources for the target cloud product at the target future time. The resources that meet the preset conditions include: the product information applicable to the resource includes the product information of the target cloud product, and the resource meets the availability requirements at the target future time. The early warning unit is used to generate an early warning result for the target cloud product based on the target available resources and the predicted resource consumption at the target future time.

8. The apparatus according to claim 7, wherein, When determining the target cloud product, the prediction unit specifically performs the following: Obtain at least one cloud product corresponding to the target account; Obtain the priority of the at least one cloud product; Cloud products that meet the priority requirements will be selected as the target cloud products.

9. The apparatus according to any one of claims 7-8, wherein, When the early warning unit generates an early warning result corresponding to the target cloud product based on the target available resources and the predicted resource consumption, it specifically performs the following: If the target available resources are determined to be less than or equal to the predicted resource consumption, an early warning result corresponding to the target cloud product is generated.

10. The apparatus according to any one of claims 7-9, wherein, The early warning unit is also used to perform... After generating the warning result corresponding to the target cloud product, obtain the notification method corresponding to the priority of the target cloud product; The warning result is output using the notification method corresponding to the priority.

11. The apparatus according to claim 8, wherein when the prediction unit obtains the priority of the at least one cloud product, it specifically performs the following: Obtain historical resource activity data corresponding to each cloud product; The cloud products with higher historical resource data activity levels are assigned higher priority.

12. The apparatus according to claim 8, wherein when the prediction unit selects a cloud product that meets the priority requirement as the target cloud product, it specifically performs the following: In descending order of priority, each cloud product is selected as the target cloud product. The generation of early warning results corresponding to the target cloud product includes: The system generates warning results for each target cloud product in sequence.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images