Transaction link decision method, device, equipment and computer-readable storage medium

Abstract

The present invention discloses a transaction link decision method, device, equipment and computer-readable storage medium, the method comprising the following steps: extracting characteristic observation values ​​from raw data, normalizing the characteristic observation values, and obtaining normalized values ​​corresponding to the characteristic observation values; obtaining characteristic parameters corresponding to the characteristic observation values ​​issued by a global computing center; and intelligently selecting a transaction link according to the characteristic observation values, the normalized values ​​and the characteristic parameters. The present invention realizes automatic selection of a transaction link by evaluating the correctness or excellence of existing behaviors through more fine-grained transaction link decision making.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a transaction link decision method, device, equipment and computer-readable storage medium. Background Art

[0002] With the development of computer technology, more and more technologies (big data, distributed, blockchain, artificial intelligence, etc.) are being applied in the financial field. The traditional financial industry is gradually transforming to financial technology (Fintech). However, due to the security and real-time requirements of the financial industry, higher requirements are also placed on technology.

[0003] Currently, SaaS (Software-as-a-Service) services mainly provide two technologies. One is hosted SaaS, also known as public cloud, which means that all hardware and data storage are located on cloud services, and users choose to pay for content according to their needs. The other is local SaaS, which means self-built private cloud, data is stored locally, and all hardware and software are installed and controlled within the user's business scope. Hosted SaaS can provide low maintenance costs and attractive services to users, allowing customers to focus more on core services. Local deployment has a higher security factor, and customers have greater autonomy and are no longer restricted by cloud vendors. In order to achieve the transition between local deployment and full cloudification, there is a hybrid cloud model that allows customers to take advantage of the security of local deployment and obtain part of the computing and storage resources of the public cloud, thereby obtaining a better combination of benefits.

[0004] Although the hybrid cloud model has considered combining local deployment with SaaS deployment, the existing hybrid cloud model deployment strategy is simple. It only considers statically placing private modules locally and public access entrances in the public cloud, or simply using the public cloud as data disaster recovery storage. The functions of the two are completely isolated. The extensive strategy cannot achieve fine management, and cannot automatically select transaction links by evaluating the correctness or quality of existing behaviors during system operation. Local differentiated needs cannot be met, which greatly affects the user experience. Summary of the invention

[0005] The main purpose of the present invention is to provide a transaction link decision method, device, equipment and computer-readable storage medium, aiming to automatically select a transaction link by evaluating the correctness or excellence of existing behaviors.

[0006] To achieve the above object, the present invention provides a transaction link decision method, which comprises the following steps:

[0007] Extracting characteristic observation values ​​from the original data, and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values;

[0008] Obtaining characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center;

[0009] A transaction link is intelligently selected according to the characteristic observation value, the normalized value and the characteristic parameter.

[0010] Optionally, the characteristic observation values ​​include performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values, and the step of extracting the characteristic observation values ​​from the original data and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values ​​includes:

[0011] Extracting performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values ​​from the original data;

[0012] Calculate the average value and standard deviation of the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value;

[0013] The differences between the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value and the average value are calculated respectively, and then the differences are divided by the standard deviation respectively to obtain normalized values ​​corresponding to the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value one by one.

[0014] Optionally, the characteristic observation value further includes a security characteristic value and an extended characteristic value, the characteristic parameter corresponding to the security characteristic value is a security threshold, and the characteristic parameter corresponding to the extended characteristic value is an extended threshold, and the step of obtaining the characteristic parameter corresponding to the characteristic observation value issued by the global computing center includes:

[0015] The performance weight of the performance characteristic value, the capacity weight of the capacity characteristic value, the network weight of the network characteristic value and the cost weight of the cost characteristic value, as well as the security threshold of the security characteristic value and the extension threshold of the extension characteristic value issued by the global computing center are obtained.

[0016] Optionally, the step of intelligently selecting a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter includes:

[0017] Determining whether the security feature value is greater than a security threshold and / or whether the extended feature value is greater than an extended threshold;

[0018] If the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, a local service link is selected.

[0019] Optionally, the characteristic parameter further includes a decision threshold value, and after the step of determining whether the security characteristic value is greater than a security threshold value and / or whether the extended characteristic value is greater than an extended threshold value, the step further includes:

[0020] If the security feature value is less than or equal to the security threshold, and the extended feature value is less than or equal to the extended threshold, the transaction factor is calculated according to a preset calculation rule;

[0021] Determining whether the transaction factor is greater than or equal to the decision threshold;

[0022] If the transaction factor is greater than or equal to the decision threshold, selecting a local service link;

[0023] If the transaction factor is less than the decision threshold, the Software as a Service (SaaS) link is selected.

[0024] Optionally, the step of calculating the transaction factor according to a preset calculation rule includes:

[0025] Calculate the product of the normalized value of the capacity characteristic value and the capacity weight, and calculate the product of 1 minus the normalized value of the network characteristic value and the network weight, and add the two products to get the positive value;

[0026] Calculate the product of the normalized value of the cost feature value and the cost weight, and calculate the product of 1 minus the normalized value of the performance feature value and the performance weight, and add the two products to get the negative value;

[0027] The transaction factor is obtained by subtracting the negative value from the positive value.

[0028] Optionally, after the step of intelligently selecting a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter, the step further includes:

[0029] Send the characteristic observation value, transaction factor and the decision result of this transaction link to the global computing center, so that the global computing center can calculate new characteristic parameters based on the characteristic observation value, transaction factor and the decision result of this transaction link and provide feedback;

[0030] The new characteristic parameters are received, and a next transaction link decision is made according to the new characteristic parameters.

[0031] Optionally, the security characteristic value includes a data isolation level and an algorithm isolation level, and the extended characteristic value includes a newly added data amount and a newly added method amount.

[0032] Optionally, the performance characteristic values ​​include average response time and query rate per second, the capacity characteristic values ​​include the number of idle CPU cores and idle storage space, the network characteristic values ​​include network accessibility and network bandwidth, and the cost characteristic values ​​include the comprehensive cost per transaction and the disaster recovery level.

[0033] Furthermore, in order to achieve the above-mentioned object, the present invention also provides a transaction link decision device, the transaction link decision device comprising:

[0034] A normalization module is used to extract characteristic observation values ​​from the original data, and perform normalization processing on the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values;

[0035] An acquisition module, used for acquiring characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center;

[0036] A selection module is used to intelligently select a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter.

[0037] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a transaction link decision device, which includes a memory, a processor, and a transaction link decision program stored in the memory and executable on the processor, and the transaction link decision program, when executed by the processor, implements the steps of the transaction link decision method as described above.

[0038] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a transaction link decision program is stored, and when the transaction link decision program is executed by a processor, the steps of the transaction link decision method described above are implemented.

[0039] The present invention extracts characteristic observation values ​​from raw data, normalizes the characteristic observation values, obtains normalized values ​​corresponding to the characteristic observation values, obtains characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center, and intelligently selects transaction links according to the characteristic observation values, the normalized values, and the characteristic parameters. The present invention realizes automatic selection of transaction links by evaluating the correctness or excellence of existing behaviors through more fine-grained transaction link decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a structural diagram of the device hardware operating environment involved in the transaction link decision device embodiment of the present invention;

[0041] Figure 2 It is a flowchart of the first embodiment of the transaction link decision method of the present invention;

[0042] Figure 3 Schematic diagram of the functional modules of the transaction link decision device of the present invention.

[0043] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0045] It should be noted that the existing hybrid cloud model has taken into account the combination of local deployment and SaaS deployment, but the existing hybrid cloud model deployment strategy is simple, which only considers statically placing private modules locally and public access entrances in the public cloud, or simply using the public cloud as data disaster recovery storage. The functions of the two are completely isolated, and the extensive strategy cannot achieve fine management. It cannot automatically select transaction links by evaluating the correctness or quality of existing behaviors during system operation. Local differentiated needs cannot be met, which greatly affects the user experience.

[0046] Based on the above-mentioned defects, the present invention provides a transaction link decision device, referring to Figure 1 , Figure 1 It is a structural diagram of the device hardware operating environment involved in the transaction link decision device embodiment of the present invention.

[0047] like Figure 1 As shown, the transaction link decision device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The hardware structure of the transaction link decision device shown in the figure does not constitute a limitation on the transaction link decision device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0049] like Figure 1As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a transaction link decision program. The operating system is a program for managing and controlling the transaction link decision device and software resources, and supports the operation of the network communication module, the user interface module, the transaction link decision program, and other programs or software; the network communication module is used to manage and control the network interface 1004; and the user interface module is used to manage and control the user interface 1003.

[0050] exist Figure 1 In the hardware structure of the transaction link decision device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the transaction link decision program stored in the memory 1005 and perform the following operations:

[0051] Extracting characteristic observation values ​​from the original data, and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values;

[0052] Obtaining characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center;

[0053] A transaction link is intelligently selected according to the characteristic observation value, the normalized value and the characteristic parameter.

[0054] Furthermore, the characteristic observation values ​​include performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values, and the step of extracting the characteristic observation values ​​from the original data and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values ​​includes:

[0055] Extracting performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values ​​from the original data;

[0056] Calculate the average value and standard deviation of the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value;

[0057] The differences between the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value and the average value are calculated respectively, and then the differences are divided by the standard deviation respectively to obtain normalized values ​​corresponding to the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value one by one.

[0058] Furthermore, the characteristic observation value also includes a security characteristic value and an extended characteristic value, the characteristic parameter corresponding to the security characteristic value is a security threshold, and the characteristic parameter corresponding to the extended characteristic value is an extended threshold, and the step of obtaining the characteristic parameter corresponding to the characteristic observation value issued by the global computing center includes:

[0059] The performance weight of the performance characteristic value, the capacity weight of the capacity characteristic value, the network weight of the network characteristic value and the cost weight of the cost characteristic value, as well as the security threshold of the security characteristic value and the extension threshold of the extension characteristic value issued by the global computing center are obtained.

[0060] Furthermore, the step of intelligently selecting a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter includes:

[0061] Determining whether the security feature value is greater than a security threshold and / or whether the extended feature value is greater than an extended threshold;

[0062] If the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, a local service link is selected.

[0063] Further, the characteristic parameter also includes a decision threshold value. After the step of determining whether the security characteristic value is greater than the security threshold value and / or whether the extended characteristic value is greater than the extended threshold value, the processor 1001 is further configured to call a transaction link decision program stored in the memory 1005, and perform the following operations:

[0064] If the security feature value is less than or equal to the security threshold, and the extended feature value is less than or equal to the extended threshold, the transaction factor is calculated according to a preset calculation rule;

[0065] Determining whether the transaction factor is greater than or equal to the decision threshold;

[0066] If the transaction factor is greater than or equal to the decision threshold, selecting a local service link;

[0067] If the transaction factor is less than the decision threshold, the Software as a Service (SaaS) link is selected.

[0068] Furthermore, the step of calculating the transaction factor according to the preset calculation rules includes:

[0069] Calculate the product of the normalized value of the capacity characteristic value and the capacity weight, and calculate the product of 1 minus the normalized value of the network characteristic value and the network weight, and add the two products to get the positive value;

[0070] Calculate the product of the normalized value of the cost feature value and the cost weight, and calculate the product of 1 minus the normalized value of the performance feature value and the performance weight, and add the two products to get the negative value;

[0071] The transaction factor is obtained by subtracting the negative value from the positive value.

[0072] Further, after the step of intelligently selecting a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter, the processor 1001 is further configured to call a transaction link decision program stored in the memory 1005, and perform the following operations:

[0073] Send the characteristic observation value, transaction factor and the decision result of this transaction link to the global computing center, so that the global computing center can calculate new characteristic parameters based on the characteristic observation value, transaction factor and the decision result of this transaction link and provide feedback;

[0074] The new characteristic parameters are received, and a next transaction link decision is made according to the new characteristic parameters.

[0075] Furthermore, the security characteristic value includes a data isolation level and an algorithm isolation level, and the extended characteristic value includes a newly added data amount and a newly added method amount.

[0076] Furthermore, the performance characteristic values ​​include average response time and query rate per second, the capacity characteristic values ​​include the number of idle CPU cores and idle storage space, the network characteristic values ​​include network accessibility and network bandwidth, and the cost characteristic values ​​include the comprehensive cost per transaction and the disaster recovery level.

[0077] The specific implementation of the transaction link decision device of the present invention is basically the same as the various embodiments of the transaction link decision method described below, and will not be repeated here.

[0078] The present invention also provides a transaction link decision method.

[0079] SaaS (Software-as-a-Service) is a model for providing software through the Internet. Manufacturers deploy application software on their own servers. Customers can order the required application software services from manufacturers through the Internet according to their actual needs, pay the manufacturer according to the amount of services ordered and the length of time, and obtain the services provided by the manufacturer through the Internet. Users no longer need to purchase software, but instead rent Internet-based software from providers to manage business activities, and there is no need to maintain the software. Service providers will fully manage and maintain the software. While providing Internet applications to customers, software manufacturers also provide offline operation of the software and local data storage, allowing users to use the software and services they ordered anytime and anywhere. For many small businesses, SaaS is the best way to adopt advanced technology. It eliminates the need for enterprises to purchase, build and maintain infrastructure and applications.

[0080] The embodiment of the present invention provides an embodiment of the transaction link decision method. It should be noted that although the logical order is shown in the flow chart, in some cases, the steps shown or described may be executed in a different order from that shown here.

[0081] In each embodiment of the transaction link decision method, for the sake of convenience, the execution subject is omitted to illustrate each embodiment. Figure 2 , Figure 2 This is a flow chart of the first embodiment of the transaction link decision method of the present invention. The transaction link decision method includes:

[0082] Step S1, extracting characteristic observation values ​​from original data, and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values;

[0083] The existing hybrid cloud model deployment strategy is simple, only considering statically placing private modules locally and public access entrances in the public cloud, or simply using the public cloud as data disaster recovery storage. The functions of the two are completely isolated, and the extensive strategy cannot achieve fine management. It cannot automatically select transaction links by evaluating the correctness or quality of existing behaviors during system operation. Local differentiated needs cannot be met, which greatly affects the user experience.

[0084] In order to solve the technical problem that the existing technology does not support automatic selection of transaction links by evaluating the correctness or excellence of existing behaviors, in this embodiment, the local decision center analyzes the characteristic factors affecting the transaction links in the original data to obtain characteristic observation values ​​of different characteristics. The original data includes but is not limited to local historical data, industry historical data and other data that are helpful for transaction link selection.

[0085] After obtaining the feature observations of different features, since the feature observations of different feature dimensions often have different dimensions and dimensional units, this situation will affect the results of data analysis. In order to eliminate the dimensional influence between different features, the feature observations need to be normalized to solve the comparability between different features and make each feature observation value at the same order of magnitude.

[0086] Step S2, obtaining characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center;

[0087] In this embodiment, after the local decision center obtains the feature observation values ​​of different features from the original data and normalizes them, in order to select a transaction link based on the feature observation values, it is also necessary to obtain the feature parameters corresponding to the feature observation values ​​issued by the global computing center. Each feature observation value has a corresponding feature parameter.

[0088] Step S3, intelligently selecting a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter.

[0089] Specifically, determine whether the security feature value is greater than the security threshold and / or whether the extended feature value is greater than the extended threshold; if the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, select the local service link; if the security feature value is less than or equal to the security threshold, and the extended feature value is less than or equal to the extended threshold, calculate the transaction factor according to the preset calculation rules; determine whether the transaction factor is greater than or equal to the decision critical value; if the transaction factor is greater than or equal to the decision critical value, select the local service link; if the transaction factor is less than the decision critical value, select the Software as a Service SaaS link.

[0090] This embodiment extracts characteristic observation values ​​from raw data, normalizes the characteristic observation values, obtains normalized values ​​corresponding to the characteristic observation values, obtains characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center, and intelligently selects transaction links based on the characteristic observation values, the normalized values, and the characteristic parameters. This achieves automatic selection of transaction links by evaluating the correctness or excellence of existing behaviors.

[0091] Furthermore, a second embodiment of the transaction link decision method of the present invention is proposed, wherein the characteristic observation values ​​include performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values, and the above step S1 includes:

[0092] Step S11, extracting performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values ​​from the original data;

[0093] In this embodiment, the local decision center analyzes the characteristic factors affecting the transaction link in the original data to obtain characteristic observation values ​​of different characteristics. In addition, the original data includes but is not limited to local historical data, industry historical data and other data that are helpful for transaction link selection.

[0094] Among them, the characteristic observation values ​​include performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values. Performance characteristics refer to the performance evaluation indicators of transactions, which mainly refer to online transaction indicators. The response time of each transaction and the total number of concurrent transactions that can be processed have a significant impact on customer experience. Different levels of standards correspond to different choices. The larger the performance characteristic value, the more inclined to choose the local link; capacity characteristics refer to the capacity planning provided by the system for the service. The computing resources and storage resources of the local system are limited. If a transaction consumes small resources and has high performance requirements, it tends to call the local service directly, otherwise it needs to call the external interface; network characteristics refer to the network overhead of local services and remote services, which is an important reference factor for service planning. The larger the network characteristic value, the more inclined to choose the SaaS link; cost characteristics can reflect the current objective cost evaluation. The height of the threshold directly affects the routing strategy of the transaction. A large number of local calls will bring higher local maintenance costs, but higher security.

[0095] Step S12, calculating the average value and standard deviation of the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value;

[0096] This embodiment uses the Z-score method to normalize the characteristic observation value. This method obtains the normalized value corresponding to the actual observation value by dividing the difference between the actual observation value (i.e., the characteristic observation value) and the average by the standard deviation. First, the average value and standard deviation of the performance characteristic value, capacity characteristic value, network characteristic value, and cost characteristic value need to be calculated.

[0097] To help understand, here is an example: if the performance characteristic value is O, the capacity characteristic value is P, the network characteristic value is Q, and the cost characteristic value is R, then the average μ = (O + P + Q + R) / 4, and the standard deviation

[0098]

[0099] Step S13, respectively calculating the differences between the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value and the average value, and then dividing the differences by the standard deviation to obtain normalized values ​​corresponding to the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value.

[0100] In this embodiment, the specific formula for calculating the normalized value is as follows:

[0101]

[0102] Where x is the characteristic observation value; μ is the average of the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value; σ is the standard deviation of the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value; x ’ is the normalized value corresponding to each feature observation.

[0103] Furthermore, the characteristic observation value further includes a security characteristic value and an extended characteristic value, the characteristic parameter corresponding to the security characteristic value is a security threshold, and the characteristic parameter corresponding to the extended characteristic value is an extended threshold, and the above step S2 includes:

[0104] Step S21, obtaining the performance weight of the performance characteristic value, the capacity weight of the capacity characteristic value, the network weight of the network characteristic value and the cost weight of the cost characteristic value, as well as the security threshold of the security characteristic value and the extension threshold of the extension characteristic value issued by the global computing center.

[0105] In this embodiment, the characteristic observation value also includes a security characteristic value and an extended characteristic value. The characteristic parameter corresponding to the security characteristic value is the security threshold, and the characteristic parameter corresponding to the extended characteristic value is the extended threshold. Among them, the security characteristic refers to the different requirements of customers for security levels. The better the isolation, the safer it is. In areas with high privacy data protection such as finance, some modules are usually deployed internally by the institution; the extended characteristic refers to the degree of local differentiation of the customer. The more field customization, the more local calls can improve iteration efficiency, and the more convenient it is for data integration and flexible allocation of resources.

[0106] After completing the decision of each transaction link, the local decision center will upload the relevant information of this decision to the global computing center. After receiving the relevant information of the most recent transaction link decision, the global computing center can adjust the feature parameters used in the most recent transaction link decision based on the relevant information of the historical transaction link decision through its own machine learning algorithm to use as the feature parameters used in the next transaction link decision. The operation and maintenance personnel can also adjust the feature parameters used in the most recent transaction link decision through the global computing center to use as the feature parameters used in the next transaction link decision. Among them, the relevant information includes but is not limited to the feature observation value, transaction factor, the decision result of this transaction link, and the feature parameters used in this transaction link decision, which are not specifically limited in this embodiment.

[0107] This embodiment normalizes the feature observation values ​​of different features after obtaining them, thereby eliminating the dimensional influence between different features, solving the comparability between different features, making each feature observation value at the same order of magnitude, and laying the foundation for intelligent decision-making in the transaction link.

[0108] Furthermore, a third embodiment of the transaction link decision method of the present invention is proposed, wherein the above step S3 includes:

[0109] Step S31, determining whether the security feature value is greater than a security threshold and / or whether the extended feature value is greater than an extended threshold;

[0110] Step S32: If the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, a local service link is selected.

[0111] In this embodiment, after completing the normalization processing of the characteristic observation value, it is first determined whether at least one of the security characteristic value and the extended characteristic value is greater than the corresponding threshold value, that is, whether the security characteristic value is greater than the security threshold value and / or whether the extended characteristic value is greater than the extended threshold value. Since the local service has a higher security factor and the customer has greater autonomy, and the security characteristic value represents the customer's requirements for the security level, the higher the security level, the larger the security characteristic value, and the more inclined to use local services, and the extended characteristic value represents the user's requirements for customization, the more requirements, the larger the extended characteristic value, and the more inclined to use local services, so when one or both of the security characteristic value and the extended characteristic value are greater than the corresponding threshold value, the local service link is selected.

[0112] Furthermore, the characteristic parameter also includes a decision threshold value. After the above step S31, the following step is further included:

[0113] Step S33, if the security feature value is less than or equal to the security threshold, and the extended feature value is less than or equal to the extended threshold, then calculating the transaction factor according to a preset calculation rule;

[0114] In this embodiment, if the security feature value and the extended feature value are both less than or equal to the corresponding threshold value, further analysis is required. First, the transaction factor needs to be calculated according to a preset calculation rule.

[0115] Specifically, the step of calculating the transaction factor according to the preset calculation rules includes:

[0116] Calculate the product of the normalized value of the capacity characteristic value and the capacity weight, and calculate the product of 1 minus the normalized value of the network characteristic value and the network weight, and add the two products to get a positive value; calculate the product of the normalized value of the cost characteristic value and the cost weight, and calculate the product of 1 minus the normalized value of the performance characteristic value and the performance weight, and add the two products to get a negative value; subtract the negative value from the positive value to get the transaction factor. Among them, the positive value quantifies the local comprehensive service processing capacity, and the negative value quantifies the interference effect on the local service, that is, the interference effect on the local service will offset the local decision-making tendency, so the larger the transaction factor value, the more inclined to choose local services, and the smaller the transaction factor value, the more inclined to choose SaaS services.

[0117] To assist understanding, an example is given below: Assume that the normalized value of the performance characteristic value is 0 ’ , the performance weight is U, and the normalized value of the capacity characteristic value is P ’ , the capacity weight is V, and the normalized value of the network characteristic value is Q ’ , the network weight is W, and the normalized value of the cost feature value is R ’ , the cost weight is X, then the transaction factor factor = P ’ *V+(1-Q ’ )*W-(1-O ’ )*UR ’ *X.

[0118] Step S34, determining whether the transaction factor is greater than or equal to the decision threshold;

[0119] Step S35, if the transaction factor is greater than or equal to the decision threshold, selecting a local service link;

[0120] Step S36: If the transaction factor is less than the decision threshold, a Software as a Service (SaaS) link is selected.

[0121] In this embodiment, the characteristic parameters also include a decision critical value, which represents the critical value of the decision tendency of the local service. The decision critical value can be customized by the user of this transaction according to the confidentiality level of the transaction data. For example, if the confidentiality level of this transaction is high, the user can set the decision critical value higher. If the confidentiality level is low, the user can set the decision critical value lower. The decision critical value can also be obtained by taking the average value of historical decision critical values ​​of historical transaction link decisions by the global computing center. This embodiment does not impose specific restrictions on the setting of the decision critical value.

[0122] After calculating the transaction factor, determine whether the transaction factor is greater than or equal to the decision critical value. Since the larger the transaction factor value, the more inclined to choose local services, and the smaller the transaction factor value, the more inclined to choose SaaS services, if the transaction factor is greater than or equal to the decision critical value, the local service link is selected; if the transaction factor is less than the decision critical value, the software as a service SaaS link is selected.

[0123] Furthermore, after the above step S3, the following steps are also included:

[0124] Step S41, sending the characteristic observation value, transaction factor and the decision result of the transaction link to the global computing center, so that the global computing center can calculate new characteristic parameters based on the characteristic observation value, transaction factor and the decision result of the transaction link and provide feedback;

[0125] Step S42, receiving the new characteristic parameters, and making a next transaction link decision based on the new characteristic parameters.

[0126] The link decision strategy of the existing hybrid cloud model cannot be updated. As time goes by, the internal access volume accumulates and the external data source fluctuates, the initial decision is likely to become invalid. If the strategy cannot be updated as the environment changes, it will lead to unreasonable resource distribution, performance bottlenecks, and reduced stability.

[0127] To solve this problem, in this embodiment, the local decision center will upload the relevant information of this decision to the global computing center after completing the decision of each transaction link. After receiving the relevant information of the most recent transaction link decision, the global computing center can adjust the feature parameters used in the most recent transaction link decision according to the relevant information of the historical transaction link decision through its own machine learning algorithm, so as to use them as the feature parameters used in the next transaction link decision. Alternatively, the operation and maintenance personnel can adjust the feature parameters used in the most recent transaction link decision through the global computing center, so as to use them as the feature parameters used in the next transaction link decision. Among them, the relevant information includes but is not limited to the feature observation value, the transaction factor, the decision result of this transaction link, and the feature parameters used in this transaction link decision, which are not specifically limited in this embodiment.

[0128] Furthermore, the performance characteristic values ​​include average response time and query rate per second, the capacity characteristic values ​​include the number of idle CPU cores and idle storage space, the network characteristic values ​​include network accessibility and network bandwidth, the cost characteristic values ​​include the comprehensive cost per transaction and the disaster recovery level, the security characteristic values ​​include the data isolation level and the algorithm isolation level, and the extension characteristic values ​​include the amount of new data and the amount of new methods.

[0129] In this embodiment, by judging whether the security feature value is greater than the security threshold and / or whether the extended feature value is greater than the extended threshold; if the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, the local service link is selected; if the security feature value is less than or equal to the security threshold, and the extended feature value is less than or equal to the extended threshold, it is judged whether the transaction factor is greater than or equal to the decision critical value; if the transaction factor is greater than or equal to the decision critical value, the local service link is selected; if the transaction factor is less than the decision critical value, the software as a service SaaS link is selected. Refined management of the local service end is achieved. The global computing center also updates the characteristic parameters of the local decision center according to the relevant information of the historical transaction link decision, thereby achieving the transaction link decision strategy to be adjusted accordingly with environmental changes.

[0130] The present invention also provides a transaction link decision device.

[0131] Reference Figure 3 , Figure 3 This is a functional module diagram of the first embodiment of the transaction link decision device of the present invention, and the transaction link decision device includes:

[0132] A normalization module 10 is used to extract characteristic observation values ​​from the original data, and perform normalization processing on the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values;

[0133] An acquisition module 20, used to acquire characteristic parameters corresponding to the characteristic observation values ​​issued by a global computing center;

[0134] The selection module 30 is used to intelligently select a transaction link according to the characteristic observation value, the normalized value and the characteristic parameter.

[0135] The specific implementation of the transaction link decision device of the present invention is basically the same as the various embodiments of the transaction link decision method described above, and will not be described in detail here.

[0136] In addition, an embodiment of the present invention further provides a computer-readable storage medium.

[0137] A transaction link decision program is stored on a computer-readable storage medium, and when the transaction link decision program is executed by a processor, the steps of the transaction link decision method described above are implemented.

[0138] The specific implementation of the computer-readable storage medium of the present invention is basically the same as the various embodiments of the transaction link decision method described above, and will not be described in detail here.

[0139] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims. All equivalent structures or equivalent process changes made using the contents of the specification and drawings of the present invention, or directly or indirectly used in other related technical fields, are protected by the present invention.

Claims

1. A transaction link decision method, characterized in that: The transaction link decision method comprises the following steps: Extracting characteristic observation values ​​from the original data, and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values, wherein the characteristic observation values ​​include performance characteristic values, capacity characteristic values, network characteristic values, security characteristic values, extension characteristic values, decision threshold values, and cost characteristic values; the performance characteristic values ​​include average response time and query rate per second; the capacity characteristic values ​​include idle CPU cores and idle storage space; the network characteristic values ​​include network reachability and network bandwidth; and the cost characteristic values ​​include comprehensive cost per transaction and disaster recovery level; Acquire a characteristic parameter corresponding to the characteristic observation value issued by a global computing center, wherein the characteristic parameter corresponding to the safety characteristic value is a safety threshold, and the characteristic parameter corresponding to the extended characteristic value is an extended threshold; Determining whether the security feature value is greater than a security threshold and / or whether the extended feature value is greater than an extended threshold; If the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, selecting a local service link; If the safety characteristic value is less than or equal to the safety threshold, and the extended characteristic value is less than or equal to the extended threshold, the product of the normalized value of the capacity characteristic value and the capacity weight is calculated, and the product of 1 minus the normalized value of the network characteristic value and the network weight is calculated, and the products of the two are added to obtain a positive value; Calculate the product of the normalized value of the cost feature value and the cost weight, and calculate the product of 1 minus the normalized value of the performance feature value and the performance weight, and add the two products to get the negative value; Subtracting the negative value from the positive value to obtain a transaction factor; Determining whether the transaction factor is greater than or equal to the decision threshold; If the transaction factor is greater than or equal to the decision threshold, selecting a local service link; If the transaction factor is less than the decision threshold, the Software as a Service (SaaS) link is selected.

2. The transaction link decision method according to claim 1, characterized in that: The step of extracting characteristic observation values ​​from the original data and normalizing the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values ​​comprises: Extracting performance characteristic values, capacity characteristic values, network characteristic values ​​and cost characteristic values ​​from the original data; Calculate the average value and standard deviation of the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value; The differences between the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value and the average value are calculated respectively, and then the differences are divided by the standard deviation respectively to obtain normalized values ​​corresponding to the performance characteristic value, capacity characteristic value, network characteristic value and cost characteristic value one by one.

3. The transaction link decision method according to claim 2, characterized in that: The step of obtaining the characteristic parameters corresponding to the characteristic observation values ​​issued by the global computing center comprises: The performance weight of the performance characteristic value, the capacity weight of the capacity characteristic value, the network weight of the network characteristic value and the cost weight of the cost characteristic value, as well as the security threshold of the security characteristic value and the extension threshold of the extension characteristic value issued by the global computing center are obtained.

4. The transaction link decision method according to claim 3, characterized in that: After selecting the transaction link, it also includes: Send the characteristic observation value, transaction factor and the decision result of this transaction link to the global computing center, so that the global computing center can calculate new characteristic parameters based on the characteristic observation value, transaction factor and the decision result of this transaction link and provide feedback; The new characteristic parameters are received, and a next transaction link decision is made according to the new characteristic parameters.

5. The transaction link decision method according to claim 3, characterized in that: The security characteristic value includes a data isolation level and an algorithm isolation level, and the extended characteristic value includes a newly added data amount and a newly added method amount.

6. A transaction link decision device, characterized in that: The transaction link decision device comprises: A normalization module is used to extract characteristic observation values ​​from the original data, and normalize the characteristic observation values ​​to obtain normalized values ​​corresponding to the characteristic observation values, wherein the characteristic observation values ​​include performance characteristic values, capacity characteristic values, network characteristic values, security characteristic values, extension characteristic values, decision threshold values, and cost characteristic values. The performance characteristic values ​​include average response time and query rate per second, the capacity characteristic values ​​include idle CPU cores and idle storage space, the network characteristic values ​​include network reachability and network bandwidth, and the cost characteristic values ​​include comprehensive cost per transaction and disaster recovery level; An acquisition module is used to acquire a characteristic parameter corresponding to the characteristic observation value issued by a global computing center, wherein the characteristic parameter corresponding to the safety characteristic value is a safety threshold, and the characteristic parameter corresponding to the extended characteristic value is an extended threshold; A selection module is used to determine whether the security feature value is greater than a security threshold and / or whether the extended feature value is greater than an extended threshold; if the security feature value is greater than the security threshold and / or the extended feature value is greater than the extended threshold, a local service link is selected; if the security feature value is less than or equal to the security threshold, and the extended feature value is less than or equal to the extended threshold, the product of the normalized value of the capacity feature value and the capacity weight is calculated, and the product of 1 minus the normalized value of the network feature value and the network weight is calculated, and the products of the two are added to obtain a positive value; the product of the normalized value of the cost feature value and the cost weight is calculated, and the product of 1 minus the normalized value of the performance feature value and the performance weight is calculated, and the products of the two are added to obtain a negative value; the transaction factor is obtained by subtracting the negative value from the positive value; it is determined whether the transaction factor is greater than or equal to the decision critical value; if the transaction factor is greater than or equal to the decision critical value, a local service link is selected; if the transaction factor is less than the decision critical value, a software as a service SaaS link is selected.

7. A transaction link decision device, characterized in that: The transaction link decision device includes a memory, a processor, and a transaction link decision program stored in the memory and executable on the processor. When the transaction link decision program is executed by the processor, the steps of the transaction link decision method as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a transaction link decision program, and when the transaction link decision program is executed by the processor, the steps of the transaction link decision method according to any one of claims 1 to 5 are implemented.

Images