A cloud bill splitting method based on machine learning

Abstract

The present invention discloses a cloud bill splitting method based on machine learning, and relates to the technical field of splitting accounts. The method comprises obtaining a cloud bill; for a first billing detail in the cloud bill whose granularity corresponding to a resource instance usage object is less than or equal to a billing granularity, determining a first resource instance usage object corresponding thereto and having the same granularity as the billing granularity; for a second billing detail whose granularity corresponding to a resource instance usage object is greater than the billing granularity, analyzing and identifying at least one second resource instance usage object corresponding thereto and having the same granularity as the billing granularity and its cost sharing ratio; performing splitting calculation based on the unit price of each resource instance, the resource instance ID corresponding to each first and second billing detail, the resource instance usage, the first and second resource instance usage objects, and the cost sharing ratio, and obtaining the to-be-paid expenses of multiple target resource instance usage objects. The method disclosed in the present invention can reduce the workload of splitting cloud bills and reduce splitting errors.

Description

Technical Field

[0001] The present invention belongs to the technical field of account splitting, and in particular relates to a cloud bill splitting method based on machine learning. Background Art

[0002] As companies move to the cloud one after another, the advantages of cloud computing resources such as pay-as-you-go and elastic expansion have brought great convenience to companies. However, the ensuing cloud bill problem has gradually surfaced.

[0003] Cloud billing is mostly done on an enterprise basis, that is, the cloud bill of the enterprise in the previous settlement cycle is directly pulled, and the total bill of the enterprise is calculated based on the resource instance usage and the unit price of each bill detail in the cloud bill. For some enterprises, multiple objects may pay separately according to their own resource instance usage, such as separate billing between different departments of the same enterprise or different groups of the same department. Therefore, for some enterprises, cloud bills need to be split. In the prior art, cloud bill splitting of enterprises is mostly done manually by relevant personnel, and financial settlement is performed based on the results of manual splitting. However, this method requires a lot of manpower, and due to the cumbersome content of cloud bills, it is easy to cause splitting errors, which brings great inconvenience to the cloud bill splitter.

[0004] Therefore, how to provide an effective solution to reduce the workload of cloud bill splitting and reduce splitting errors has become a difficult problem that needs to be solved urgently in the existing technology. Summary of the invention

[0005] The purpose of the present invention is to provide a cloud bill splitting method based on machine learning to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a cloud bill splitting method based on machine learning, comprising:

[0008] Obtain the cloud bill of the enterprise in the previous settlement cycle, wherein the cloud bill includes multiple bill details, each of which includes a resource instance ID, resource instance usage, resource instance usage object, and resource instance cost sharing description;

[0009] For a first billing detail whose granularity corresponding to a resource instance usage object in the multiple billing details is less than or equal to a billing granularity, based on an object ownership relationship and the resource instance usage object in the first billing detail, determining a first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity;

[0010] For a second billing detail whose granularity corresponding to a resource instance usage object in the multiple billing details is greater than the billing granularity, analyzing and identifying the resource instance cost sharing description of the second billing detail through a pre-trained machine learning model, obtaining at least one second resource instance usage object corresponding to the resource instance sharing description and having the same granularity as the billing granularity, and a cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object;

[0011] Based on the unit price of each resource instance, the resource instance ID corresponding to each first billing detail, the resource instance usage and the first resource instance usage object, and the resource instance ID corresponding to each second billing detail, the resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object, the account splitting calculation is performed to obtain the to-be-paid fees corresponding to the multiple target resource instance usage objects;

[0012] The multiple target resource instance usage objects include a first resource instance usage object corresponding to the first billing detail and a second resource instance usage object corresponding to the second billing detail.

[0013] Based on the above disclosed content, the present invention obtains the cloud bill of the enterprise in the previous settlement cycle, where the cloud bill includes multiple bill details, each bill detail including a resource instance ID, resource instance usage, resource instance usage object, and resource instance cost sharing description; for a first bill detail in which the granularity corresponding to the resource instance usage object in the multiple bill details is less than or equal to the billing granularity, based on the object ownership relationship and the resource instance usage object in the first bill detail, determine the first resource instance usage object corresponding to the first bill detail and having the same granularity as the billing granularity; for a second bill detail in which the granularity corresponding to the resource instance usage object in the multiple bill details is greater than the billing granularity, use a pre-trained machine learning model to train the second bill detail. The detailed resource instance cost sharing description is analyzed and identified to obtain at least one second resource instance usage object corresponding to the resource instance sharing description and with the same granularity as the billing granularity, and the cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object; based on the unit price of each type of resource instance, the resource instance ID, resource instance usage and first resource instance usage object corresponding to each first billing detail, and the resource instance ID, resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object corresponding to each second billing detail, account sharing calculation is performed to obtain the to-be-paid fees corresponding to multiple target resource instance usage objects. In this way, for resource instance usage objects in the billing details whose granularity is less than or equal to the billing granularity, the first resource instance usage object whose granularity corresponding to the billing details is the same as the billing granularity can be determined; for resource instance usage objects in the billing details whose granularity is greater than the billing granularity, at least one second resource instance usage object whose granularity corresponding to the billing details is the same as the billing granularity and the cost sharing ratio corresponding to each second resource instance usage object can be determined, thereby splitting the granularity of the resource instance usage objects in the billing details into a granularity consistent with the billing granularity, and then the payment fee of the source instance usage object can be very conveniently calculated. In this process, there is no need for manual account splitting and settlement, which reduces the workload of cloud bill account splitting and can also reduce account splitting errors caused by the cumbersome content of the cloud bill.

[0014] In a possible design, based on the object ownership relationship and the resource instance usage object in the first bill detail, determining the first resource instance usage object corresponding to the first bill detail and having the same granularity as the billing granularity includes:

[0015] If the granularity of the resource instance usage object corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail;

[0016] If the granularity of the resource instance usage object corresponding to the first billing detail is smaller than the billing granularity, searching for the parent resource instance usage object of the resource instance usage object corresponding to the first billing detail based on the object ownership relationship, and updating the found parent resource instance usage object to the resource instance usage object corresponding to the first billing detail;

[0017] If the granularity of the resource instance usage object currently and most recently corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object currently and most recently corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail;

[0018] If the granularity of the resource instance usage object to which the first billing detail currently corresponds is smaller than the billing granularity, the parent-level resource instance usage object of the resource instance usage object to which the first billing detail currently corresponds is re-searched based on the object ownership relationship, and the parent-level resource instance usage object found is updated to the resource instance usage object corresponding to the first billing detail, until the granularity of the resource instance usage object to which the first billing detail currently corresponds is equal to the billing granularity, in which case the resource instance usage object to which the first billing detail currently corresponds is used as the first resource instance usage object corresponding to the first billing detail.

[0019] In one possible design, if the resource instance cost sharing description of the second billing details is analyzed and identified, and the granularity corresponding to any resource instance usage object obtained is smaller than the billing granularity, then the parent resource instance usage object of any resource instance usage object and with a granularity equal to the billing granularity is used as a second resource instance usage object.

[0020] In one possible design, the machine learning model is a semantic recognition model based on NLP or a convolutional neural network model, and the convolutional neural network model is trained with a sample resource instance cost sharing description as input, at least one sample resource instance usage object corresponding to the sample resource instance cost sharing description, and the cost sharing ratio corresponding to each sample resource instance usage object in at least one sample resource instance usage object as output.

[0021] In one possible design, the method further includes:

[0022] The to-be-paid fees corresponding to each target resource instance user object are sent to the corresponding target resource instance user object.

[0023] In one possible design, the resource instance is a cloud computing resource.

[0024] In a possible design, the resource instance using object is the name of the object using the resource instance or the ID of the object using the resource instance.

[0025] In a second aspect, the present invention provides a cloud bill splitting device based on machine learning, comprising:

[0026] An acquisition unit is used to acquire a cloud bill of the enterprise in the previous settlement cycle, wherein the cloud bill includes multiple bill details, each of which includes a resource instance ID, a resource instance usage, a resource instance usage object, and a resource instance cost sharing description;

[0027] a determining unit configured to determine, for a first billing detail whose granularity corresponding to the resource instance usage object in the plurality of billing details is less than or equal to the billing granularity, a first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity based on an object ownership relationship and the resource instance usage object in the first billing detail;

[0028] an analysis and identification unit for analyzing and identifying, for a second billing detail in which a granularity corresponding to a resource instance usage object in the multiple billing details is greater than a billing granularity, a resource instance cost sharing description of the second billing detail by a pre-trained machine learning model, to obtain at least one second resource instance usage object corresponding to the resource instance sharing description and having the same granularity as the billing granularity, and a cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object;

[0029] A split-account calculation unit is used to perform split-account calculation based on the unit price of each resource instance, the resource instance ID corresponding to each first billing detail, the resource instance usage and the first resource instance usage object, and the resource instance ID corresponding to each second billing detail, the resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object, so as to obtain the to-be-paid fees corresponding to the multiple target resource instance usage objects;

[0030] The multiple target resource instance usage objects include a first resource instance usage object corresponding to the first billing detail and a second resource instance usage object corresponding to the second billing detail.

[0031] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the cloud bill splitting method based on machine learning as described in the first aspect or any possible design of the first aspect.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, executes the cloud bill splitting method based on machine learning as described in the first aspect or any possible design of the first aspect.

[0033] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the cloud bill splitting method based on machine learning as described in the first aspect or any possible design of the first aspect.

[0034] Beneficial effects:

[0035] The cloud bill splitting method based on machine learning provided by the present invention can determine, for resource instance usage objects with a granularity less than or equal to the billing granularity in the billing details, a first resource instance usage object with a granularity corresponding to the billing details and the same billing granularity; for resource instance usage objects with a granularity greater than the billing granularity in the billing details, at least one second resource instance usage object with a granularity corresponding to the billing details and the same billing granularity and a cost sharing ratio corresponding to each second resource instance usage object can be determined, thereby splitting the granularity of the resource instance usage objects in the billing details into a granularity consistent with the billing granularity, and then conveniently calculating the payment fee of the source instance usage object. In this process, no manual account splitting and settlement is required, which reduces the workload of cloud bill splitting. At the same time, it can reduce account splitting errors caused by the cumbersome content of the cloud bill, which is convenient for practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a cloud bill splitting method based on machine learning provided in an embodiment of the present application;

[0037] Figure 2 A schematic block diagram of a cloud bill splitting device based on machine learning provided in an embodiment of the present application;

[0038] Figure 3 A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0040] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0041] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0042] In order to facilitate cloud bill splitting, an embodiment of the present application provides a cloud bill splitting method based on machine learning. The cloud bill splitting method based on machine learning can reduce the workload of cloud bill splitting and reduce splitting errors.

[0043] The cloud bill splitting method based on machine learning provided in the embodiment of the present application can be applied to a server on the enterprise side or a terminal device on the enterprise side for splitting accounts. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0044] The following is a detailed description of the cloud bill splitting method based on machine learning provided in an embodiment of the present application.

[0045] like Figure 1 As shown, it is a flowchart of the cloud bill splitting method based on machine learning provided in the first aspect of the embodiment of the present application. The cloud bill splitting method based on machine learning may include but is not limited to the following steps S101-S104.

[0046] Step S101. Obtain the cloud bill of the enterprise in the previous settlement cycle.

[0047] The cloud bill includes multiple bill details, each of which includes a resource instance ID (Identity document), resource instance usage, resource instance usage objects, and resource instance cost sharing instructions.

[0048] Resource instances may be, but are not limited to, cloud computing resources such as computing resources, network resources, storage resources, application software resources, and / or big data analysis tool resources. Resource instance users may be, but are not limited to, the name of the object using the resource instance or the ID of the object using the resource instance, such as the name or ID of the division company using the resource instance, the name or ID of the department using the resource instance, the name or ID of the department group using the resource instance, etc. Resource instance cost sharing description may be used to describe multiple resource instance users using the same resource instance and the cost sharing ratio of the multiple resource instance users.

[0049] Step S102. For a first billing detail in which the granularity corresponding to the resource instance usage object in multiple billing details is less than or equal to the billing granularity, based on the object ownership relationship and the resource instance usage object in the first billing detail, determine the first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity.

[0050] The billing granularity may refer to the unit of division of the billing object when splitting the cloud bill. For example, if the billing granularity is department, the bill is split by department (i.e., the usage fee of cloud computing resources is calculated by department).

[0051] Specifically, if the granularity of the resource instance usage object corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail. For example, if the resource instance usage object in a billing detail a is department A1, and the billing granularity is department, then the resource instance usage object corresponding to the billing detail a can be (department A1) as the first resource instance usage object corresponding to the billing detail a.

[0052] If the granularity of the resource instance usage object corresponding to the first billing detail is smaller than the billing granularity, the upper-level resource instance usage object of the resource instance usage object corresponding to the first billing detail is searched based on the object ownership relationship, and the found upper-level resource instance usage object is updated to the resource instance usage object corresponding to the first billing detail. The object ownership relationship may be the ownership relationship between subsidiaries, departments, and department groups in an enterprise.

[0053] For example, if the resource instance usage object corresponding to a billing detail b is department group B2, and the billing granularity is department, then the parent resource instance usage object department B1 of the resource instance usage object B2 corresponding to billing detail b can be found based on the object ownership relationship, and then the parent resource instance usage object (department B1) can be updated to the resource instance usage object corresponding to billing detail b.

[0054] If the granularity of the resource instance usage object currently corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object currently corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail. Still based on the above example, after the update, the resource instance usage object currently corresponding to billing detail b is department B1, and the billing granularity is also department, then department B1 is finally used as the first resource instance usage object corresponding to billing detail b.

[0055] If the granularity of the resource instance usage object currently corresponding to the first billing detail is still smaller than the billing granularity, the parent resource instance usage object of the resource instance usage object currently corresponding to the first billing detail can be re-searched based on the object ownership relationship, and the parent resource instance usage object found can be updated to the resource instance usage object corresponding to the first billing detail, until the granularity of the resource instance usage object currently corresponding to the first billing detail is equal to the billing granularity, and the resource instance usage object currently corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail.

[0056] In this way, for the first bill detail whose corresponding granularity of the resource instance usage object is less than or equal to the billing granularity, the granularity of its resource instance usage object can be updated to be consistent with the billing granularity, that is, the division unit of the resource instance usage object in the bill detail is consistent with the division unit during billing, thereby facilitating subsequent cloud bill splitting.

[0057] Step S103. For a second billing detail in which the granularity corresponding to the resource instance usage object in multiple billing details is greater than the billing granularity, the resource instance cost sharing description of the second billing detail is analyzed and identified through a pre-trained machine learning model to obtain at least one second resource instance usage object corresponding to the resource instance sharing description and having the same granularity as the billing granularity and the cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object.

[0058] In the embodiment of the present application, a machine learning model for analyzing and identifying resource instance cost sharing instructions is pre-trained. The machine learning model may be, but is not limited to, a semantic recognition model based on natural language processing (Natural Language Processing, NLP) or a convolutional neural network (Convolutional Neural Networks, CNN) model, etc., which is not specifically limited in the embodiment of the present application. When the machine learning model is a convolutional neural network, the convolutional neural network model can be trained with a sample resource instance cost sharing instruction as input, at least one sample resource instance usage object corresponding to the sample resource instance cost sharing instruction, and the cost sharing ratio corresponding to each sample resource instance usage object in at least one sample resource instance usage object as output.

[0059] For example, if the billing granularity is department, and the resource instance user in a billing detail c is branch company C, then the granularity corresponding to the resource instance user C in the billing detail c is greater than the billing granularity. In this case, the pre-trained machine learning model can be used to analyze and identify the cost allocation description of the resource instance in billing detail c. Assuming that the cost allocation description of the resource instance in billing detail c is "the cost of resource instance x is evenly allocated to department C1 and department C2", after analysis and identification, a total of two resource instance users, namely the second resource instance user C1 and the second resource instance user C2, can be obtained, and the cost allocation ratios corresponding to the two resource instance users are both 50%.

[0060] In one or more embodiments, if the resource instance cost sharing description of the second billing details is analyzed and identified, and the granularity corresponding to any resource instance usage object obtained is smaller than the billing granularity, then the parent resource instance usage object of any resource instance usage object and whose granularity is equal to the billing granularity can be used as a second resource instance usage object.

[0061] In this way, for the second billing details whose corresponding granularity of the resource instance usage object is larger than the billing granularity, it can be divided into at least one second resource instance usage object whose granularity is consistent with the billing granularity, so that the division unit of the resource instance usage object in the billing details is consistent with the division unit during billing. At the same time, the cost sharing ratio corresponding to each second resource instance usage object in at least one second resource instance usage object can be analyzed, which is convenient for subsequent cloud bill splitting.

[0062] Step S104. Based on the unit price of each type of resource instance, the resource instance ID corresponding to each first billing detail, the resource instance usage and the first resource instance usage object, as well as the resource instance ID corresponding to each second billing detail, the resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object, account sharing calculation is performed to obtain the unpaid fees corresponding to multiple target resource instance usage objects.

[0063] Among them, multiple target resource instance usage objects include a first resource instance usage object corresponding to a first bill detail and a second resource instance usage object corresponding to a second bill detail. The unit price of each type of resource instance can be known data given by the cloud computing resource provider. The to-be-paid fee corresponding to any target resource instance usage object is the unit price of any target resource instance * the usage of any target resource instance, or the unit price of any target resource instance * the usage of any target resource instance * the cost sharing ratio corresponding to any target resource instance usage object, which is not repeated in the embodiments of the present application.

[0064] In one or more embodiments, after obtaining the unpaid fees corresponding to multiple target resource instance usage objects, the unpaid fees corresponding to each target resource instance usage object can also be sent to the corresponding target resource instance usage object so that each resource instance usage object can pay and settle the fees.

[0065] In summary, the cloud bill splitting method based on machine learning provided by the present invention obtains the cloud bill of the enterprise in the previous settlement cycle, where the cloud bill includes multiple bill details, each bill detail includes a resource instance ID, resource instance usage, resource instance usage object, and resource instance cost sharing description; for a first bill detail in which the granularity corresponding to the resource instance usage object in the multiple bill details is less than or equal to the billing granularity, based on the object ownership relationship and the resource instance usage object in the first bill detail, a first resource instance usage object corresponding to the first bill detail and having the same granularity as the billing granularity is determined; for a second bill detail in which the granularity corresponding to the resource instance usage object in the multiple bill details is greater than the billing granularity, a pre-trained machine learning model is used to The resource instance cost sharing description of the second billing detail is analyzed and identified to obtain at least one second resource instance usage object corresponding to the resource instance sharing description and with the same granularity as the billing granularity, and the cost sharing ratio corresponding to each second resource instance usage object in at least one second resource instance usage object; based on the unit price of each type of resource instance, the resource instance ID, resource instance usage and first resource instance usage object corresponding to each first billing detail, as well as the resource instance ID, resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object corresponding to each second billing detail, account sharing calculation is performed to obtain the unpaid fees corresponding to multiple target resource instance usage objects. In this way, for resource instance usage objects in the billing details whose granularity is less than or equal to the billing granularity, the first resource instance usage object whose granularity corresponding to the billing details is the same as the billing granularity can be determined; for resource instance usage objects in the billing details whose granularity is greater than the billing granularity, at least one second resource instance usage object whose granularity corresponding to the billing details is the same as the billing granularity and the cost sharing ratio corresponding to each second resource instance usage object can be determined, thereby splitting the granularity of the resource instance usage objects in the billing details into a granularity consistent with the billing granularity, that is, the division unit of the resource instance usage objects in the billing details is consistent with the division unit during account splitting, and thus the payment fee of the source instance usage object can be very conveniently calculated. In this process, there is no need for manual account splitting and settlement, which reduces the workload of cloud bill account splitting. At the same time, it can reduce account splitting errors caused by the cumbersome content of the cloud bill, which is convenient for practical application and promotion.

[0066] See also Figure 2 The second aspect of the embodiment of the present application provides a cloud bill splitting device based on machine learning, and the cloud bill splitting based on machine learning includes:

[0067] An acquisition unit is used to acquire a cloud bill of the enterprise in the previous settlement cycle, wherein the cloud bill includes multiple bill details, each of which includes a resource instance ID, a resource instance usage, a resource instance usage object, and a resource instance cost sharing description;

[0068] a determining unit configured to determine, for a first billing detail whose granularity corresponding to the resource instance usage object in the plurality of billing details is less than or equal to the billing granularity, a first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity based on an object ownership relationship and the resource instance usage object in the first billing detail;

[0069] an analysis and identification unit for analyzing and identifying, for a second billing detail in which a granularity corresponding to a resource instance usage object in the multiple billing details is greater than a billing granularity, a resource instance cost sharing description of the second billing detail by a pre-trained machine learning model, to obtain at least one second resource instance usage object corresponding to the resource instance sharing description and having the same granularity as the billing granularity, and a cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object;

[0070] A split-account calculation unit is used to perform split-account calculation based on the unit price of each resource instance, the resource instance ID corresponding to each first billing detail, the resource instance usage and the first resource instance usage object, and the resource instance ID corresponding to each second billing detail, the resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object, so as to obtain the to-be-paid fees corresponding to the multiple target resource instance usage objects;

[0071] The multiple target resource instance usage objects include a first resource instance usage object corresponding to the first billing detail and a second resource instance usage object corresponding to the second billing detail.

[0072] The working process, working details and technical effects of the cloud bill splitting device based on machine learning provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be repeated here.

[0073] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the cloud bill splitting method based on machine learning as described in the first aspect of the embodiment.

[0074] For specific examples, the memory may include but is not limited to random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may be but is not limited to a microprocessor of the STM32F105 series, an ARM (Advanced RISC-Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may be but is not limited to a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0075] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions for the cloud bill splitting method based on machine learning as described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the cloud bill splitting method based on machine learning as described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0076] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the cloud bill splitting method based on machine learning as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0077] It should be understood that certain details are provided in the following description to facilitate a complete understanding of the example embodiments. However, it should be understood by those of ordinary skill in the art that the example embodiments can be implemented without these certain details. For example, the system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other examples, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0078] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cloud bill splitting method based on machine learning, characterized in that: include: Obtain the cloud bill of the enterprise in the previous settlement cycle, wherein the cloud bill includes multiple bill details, each of which includes a resource instance ID, resource instance usage, resource instance usage object, and resource instance cost sharing description; For a first billing detail whose granularity corresponding to a resource instance usage object in the multiple billing details is less than or equal to a billing granularity, based on an object ownership relationship and the resource instance usage object in the first billing detail, determining a first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity; For a second billing detail whose granularity corresponding to a resource instance usage object in the multiple billing details is greater than the billing granularity, analyzing and identifying the resource instance cost sharing description of the second billing detail through a pre-trained machine learning model, obtaining at least one second resource instance usage object corresponding to the resource instance sharing description and having the same granularity as the billing granularity, and a cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object; Based on the unit price of each resource instance, the resource instance ID corresponding to each first billing detail, the resource instance usage and the first resource instance usage object, and the resource instance ID corresponding to each second billing detail, the resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object, the account splitting calculation is performed to obtain the to-be-paid fees corresponding to the multiple target resource instance usage objects; The multiple target resource instance usage objects include a first resource instance usage object corresponding to the first billing detail and a second resource instance usage object corresponding to the second billing detail; Determining, based on the object ownership relationship and the resource instance usage object in the first bill detail, a first resource instance usage object corresponding to the first bill detail and having the same granularity as the billing granularity, includes: If the granularity of the resource instance usage object corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail; If the granularity of the resource instance usage object corresponding to the first billing detail is smaller than the billing granularity, searching for the parent resource instance usage object of the resource instance usage object corresponding to the first billing detail based on the object ownership relationship, and updating the found parent resource instance usage object to the resource instance usage object corresponding to the first billing detail; If the granularity of the resource instance usage object currently and most recently corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object currently and most recently corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail; If the granularity of the resource instance usage object to which the first billing detail currently corresponds is smaller than the billing granularity, the parent-level resource instance usage object of the resource instance usage object to which the first billing detail currently corresponds is re-searched based on the object ownership relationship, and the parent-level resource instance usage object found is updated to the resource instance usage object corresponding to the first billing detail, until the granularity of the resource instance usage object to which the first billing detail currently corresponds is equal to the billing granularity, in which case the resource instance usage object to which the first billing detail currently corresponds is used as the first resource instance usage object corresponding to the first billing detail.

2. The cloud bill splitting method based on machine learning according to claim 1, characterized in that: If the resource instance cost sharing description of the second billing details is analyzed and identified, and the granularity corresponding to any resource instance usage object obtained is smaller than the billing granularity, then the parent resource instance usage object of any resource instance usage object and with a granularity equal to the billing granularity will be used as a second resource instance usage object.

3. The cloud bill splitting method based on machine learning according to claim 1, characterized in that: The machine learning model is a semantic recognition model based on NLP or a convolutional neural network model, and the convolutional neural network model is trained with a sample resource instance cost sharing description as input, at least one sample resource instance usage object corresponding to the sample resource instance cost sharing description, and the cost sharing ratio corresponding to each sample resource instance usage object in at least one sample resource instance usage object as output.

4. The cloud bill splitting method based on machine learning according to claim 1, characterized in that: The method further comprises: The to-be-paid fees corresponding to each target resource instance user object are sent to the corresponding target resource instance user object.

5. The cloud bill splitting method based on machine learning according to claim 1, characterized in that: The resource instance is a cloud computing resource.

6. The cloud bill splitting method based on machine learning according to claim 1, characterized in that: The resource instance using object is the name of the object using the resource instance or the ID of the object using the resource instance.

7. A cloud bill splitting device based on machine learning, characterized in that: include: An acquisition unit is used to acquire a cloud bill of the enterprise in the previous settlement cycle, wherein the cloud bill includes multiple bill details, each of which includes a resource instance ID, a resource instance usage, a resource instance usage object, and a resource instance cost sharing description; a determining unit configured to determine, for a first billing detail whose granularity corresponding to the resource instance usage object in the plurality of billing details is less than or equal to the billing granularity, a first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity based on an object ownership relationship and the resource instance usage object in the first billing detail; an analysis and identification unit for analyzing and identifying, for a second billing detail in which a granularity corresponding to a resource instance usage object in the multiple billing details is greater than a billing granularity, a resource instance cost sharing description of the second billing detail by a pre-trained machine learning model, to obtain at least one second resource instance usage object corresponding to the resource instance sharing description and having the same granularity as the billing granularity, and a cost sharing ratio corresponding to each second resource instance usage object in the at least one second resource instance usage object; A split-account calculation unit is used to perform split-account calculation based on the unit price of each resource instance, the resource instance ID corresponding to each first billing detail, the resource instance usage and the first resource instance usage object, and the resource instance ID corresponding to each second billing detail, the resource instance usage, at least one second resource instance usage object and the cost sharing ratio corresponding to each second resource instance usage object, so as to obtain the to-be-paid fees corresponding to the multiple target resource instance usage objects; The multiple target resource instance usage objects include a first resource instance usage object corresponding to the first billing detail and a second resource instance usage object corresponding to the second billing detail; When the determining unit is used to determine the first resource instance usage object corresponding to the first billing detail and having the same granularity as the billing granularity based on the object ownership relationship and the resource instance usage object in the first billing detail, the determining unit is specifically used to: If the granularity of the resource instance usage object corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail; If the granularity of the resource instance usage object corresponding to the first billing detail is smaller than the billing granularity, searching for the parent resource instance usage object of the resource instance usage object corresponding to the first billing detail based on the object ownership relationship, and updating the found parent resource instance usage object to the resource instance usage object corresponding to the first billing detail; If the granularity of the resource instance usage object currently and most recently corresponding to the first billing detail is equal to the billing granularity, the resource instance usage object currently and most recently corresponding to the first billing detail is used as the first resource instance usage object corresponding to the first billing detail; If the granularity of the resource instance usage object to which the first billing detail currently corresponds is smaller than the billing granularity, the parent-level resource instance usage object of the resource instance usage object to which the first billing detail currently corresponds is re-searched based on the object ownership relationship, and the parent-level resource instance usage object found is updated to the resource instance usage object corresponding to the first billing detail, until the granularity of the resource instance usage object to which the first billing detail currently corresponds is equal to the billing granularity, in which case the resource instance usage object to which the first billing detail currently corresponds is used as the first resource instance usage object corresponding to the first billing detail.

8. An electronic device, characterized in that: It includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the cloud bill splitting method based on machine learning as described in any one of claims 1 to 6.

9. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the cloud bill splitting method based on machine learning is implemented as described in any one of claims 1 to 6.

Images