CN112182007A

CN112182007A - Cloud computing data processing method based on artificial intelligence and artificial intelligence platform

Info

Publication number: CN112182007A
Application number: CN202011120327.4A
Authority: CN
Inventors: 詹启新
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-10-19
Filing date: 2020-10-19
Publication date: 2021-01-05

Abstract

The data processing method and the artificial intelligence platform based on artificial intelligence cloud computing can determine the service matching data set of the cloud service configuration data based on the service data associated information and the service scene associated information of the cloud service configuration data of the cloud computing server in the obtained cloud data processing record, so that the first fusion and the second fusion of the corresponding data sets are sequentially carried out, and the service guide data set of the cloud computing server can be obtained. The service guide data set is obtained after analyzing the cloud data processing records of the cloud computing server in different service scenes, so that the deep analysis of the service processing of the cloud computing server can be realized through artificial intelligence, and the service guide data set can guide the cloud computing server to optimize service processing logic, so that the subsequent service processing efficiency of the cloud computing server can be improved, and the time consumption of same service processing or similar service processing is reduced.

Description

Cloud computing data processing method based on artificial intelligence and artificial intelligence platform

Technical Field

The embodiment of the invention relates to the technical field of artificial intelligence and cloud computing, in particular to a data processing method and an artificial intelligence platform based on artificial intelligence cloud computing.

Background

With the rapid development of Cloud Computing (Cloud Computing), Cloud processing of various services has become the mainstream. Compared with the traditional offline service processing mode, the service processing cloud terminal can eliminate the region limitation and the time limitation, so that a service requester and a service processor can flexibly perform service handling.

However, with the rapid increase of the number and types of cloud service transactions, the service processing efficiency of the cloud computing server may be difficult to meet the service requirements at the present stage, and the cloud computing server may have a problem of time consumption increase when performing service processing.

Disclosure of Invention

In view of this, the embodiment of the present invention provides a data processing method based on artificial intelligence cloud computing and an artificial intelligence platform.

The embodiment of the invention provides a data processing method based on artificial intelligence cloud computing, which is applied to an artificial intelligence platform and comprises the following steps:

acquiring n cloud data processing records of a cloud computing server; the cloud data processing record comprises a feature extraction record and a feature recombination record in a service scene, and n is a positive integer;

acquiring a service matching data set of cloud service configuration data based on service data associated information and service scene associated information of the cloud service configuration data of the cloud computing server in the cloud data processing record; performing first fusion on a service matching data set of the cloud service configuration data and a sample data set in a preset database to generate a transition data set;

acquiring multidimensional configuration data features at intervals from a data feature distribution queue of the transition data set, wherein the data feature distribution queue is a distribution queue formed by data features corresponding to the cloud service configuration data in time sequence in the transition data set;

performing second fusion on the transition data set based on the service data associated information and the service scene associated information mapped in the cloud data processing record by the multidimensional configuration data characteristics to generate a service guide data set of the cloud computing server; and sending the business guide data set to the cloud computing server so that the cloud computing server optimizes business processing logic according to the business guide data set.

Optionally, the first fusing the service matching data set of the cloud service configuration data with the sample data set in a preset database to generate a transition data set includes:

determining a first data fusion path list according to a service matching data set of the cloud service configuration data; the first data fusion path list is used for recording sequence information of fusion paths between the transition data set and cloud data processing records of the cloud computing server;

and performing first fusion on the sample data set in the preset database based on the first data fusion path list to generate the transition data set.

Optionally, the determining a first data fusion path list according to the service matching data set of the cloud service configuration data includes:

constructing a first data characteristic clustering model, wherein the first data characteristic clustering model comprises a first configuration data distribution table, a first clustering label distribution table and a first model network distribution table; the first configuration data distribution table is used for adjusting a data structure of cloud service configuration data after screening in the transition data set to meet the data structure requirement of a corresponding service matching data set, the screened cloud service configuration data refers to cloud service configuration data obtained after removing cloud service configuration data with a configuration heat value lower than a set heat value, the first clustering label distribution table is used for adjusting service indexes of the cloud service configuration data in the transition data set to meet the service requirement of the corresponding service matching data set, and the first model network distribution table is used for adjusting the data queue priority of the transition data set to enable the data queue priority to be in a level descending state;

determining the first data fusion path list meeting a preliminary fusion condition based on the business matching data set of the cloud service configuration data and the first data feature clustering model; the preliminary fusion condition comprises that the ratio of the model generalization rate and the model cluster discarding rate of the first data feature cluster model is the minimum value.

Optionally, before the constructing the first data feature clustering model, the method further includes:

based on the configuration heat record of the cloud service configuration data, mapping the cloud service configuration data in a preset heat mapping list according to a service matching data set of the cloud service configuration data; the heat calculation mode of the cloud service configuration data is the same as that of the preset heat mapping list, and the heat value is used for representing the frequency of business processing;

acquiring a mapping heat value of a configuration heat value of each group of cloud service configuration data in the preset heat mapping list;

and in response to the fact that the mapping heat value is lower than the target heat value corresponding to the preset heat mapping list, removing the cloud service configuration data corresponding to the mapping heat value to obtain the screened cloud service configuration data.

Optionally, based on the first data fusion path list, performing first fusion on the sample data set in the preset database, and generating the transition data set, including:

constructing a path incidence matrix of the first data fusion path list and a data set fusion label corresponding to each fusion path; on the premise that the first data fusion path list contains the data over-fusion packet and the data under-fusion packet through the path incidence matrix, determining label similarity coefficients between the data set fusion labels corresponding to the fusion paths under the data under-fusion grouping of the first data fusion path list and the data set fusion labels corresponding to the fusion paths under the data over-fusion grouping of the first data fusion path list according to the data set fusion labels corresponding to the fusion paths under the data under-fusion grouping of the first data fusion path list and the label weights of the data set fusion labels, adjusting a data set fusion label corresponding to a fusion path similar to the data set fusion label corresponding to the fusion path under the data under-fusion group and the data over-fusion group of the first data fusion path list to a corresponding data over-fusion group; under the condition that a data set fusion tag corresponding to a plurality of fusion paths is included in a current data under-fusion group of a first data fusion path list, determining a tag similarity coefficient between the data set fusion tags corresponding to the fusion paths in the current data under-fusion group of the first data fusion path list according to the data set fusion tag corresponding to the fusion path in the data over-fusion group of the first data fusion path list and the tag weight of the data set fusion tag, and screening the data set fusion tag corresponding to the fusion path in the current data under-fusion group according to the tag similarity coefficient between the data set fusion tags corresponding to the fusion paths; setting a label adjustment index coefficient for the labeled data set fusion label obtained by screening according to the data set fusion label corresponding to the fusion path under the data over-fusion grouping of the first data fusion path list and the label weight of the data set fusion label, and adjusting at least part of the labeled data set fusion label under the data over-fusion grouping of the first data fusion path list according to the label adjustment index coefficient;

generating a fusion label distribution list of the first data fusion path list based on the data set fusion label under the data over-fusion grouping and the data set fusion label under the data under-fusion grouping; determining a fusion weight value of each list element of the fusion label distribution list, and determining the number of the list elements with the fusion weight values smaller than or equal to a preset target weight value according to the fusion weight value of each list element; calculating the ratio of the number of the list elements to the total number of the list elements of the fusion label distribution list to obtain the weight distribution ratio of the fusion label distribution list; determining list area distribution information of the fusion label distribution list; determining list ordering information of the fusion label distribution list according to the weight distribution proportion of the fusion label distribution list and list region distribution information of the fusion label distribution list; determining a data set fusion priority corresponding to a sorting logic sequence where the list sorting information of the fusion tag distribution list is located according to a corresponding relation between a pre-stored sorting logic sequence and the data set fusion priority, and using the data set fusion priority as a data set fusion priority queue of the first data fusion path list;

sorting first data to be fused in the service matching data set through the data set fusion priority queue to obtain a first sorting sequence, and sorting second data to be fused in the sample data set through the data set fusion priority queue to obtain a second sorting sequence; and performing first fusion on each first data to be fused and one second data to be fused corresponding to each first data to be fused according to the one-to-one correspondence relationship between the sequence units in the first sequencing sequence and the second sequencing sequence to obtain the transition data set.

Optionally, the performing second fusion on the transition data set based on the service data associated information and the service scene associated information mapped in the cloud data processing record by the multidimensional configuration data feature to generate the service guidance data set of the cloud computing server includes:

acquiring a service matching data set of the multi-dimensional configuration data characteristics based on service data associated information and service scene associated information mapped by the multi-dimensional configuration data characteristics in the cloud data processing record;

determining a second data fusion path list according to the service matching data set of the multidimensional configuration data characteristics, wherein the second data fusion path list is used for recording sequence information of a fusion path between the service matching data set of the multidimensional configuration data characteristics of the cloud computing server and cloud data processing records of the cloud computing server;

and performing second fusion on the transition data set based on the second data fusion path list to generate a service guide data set of the cloud computing server.

Optionally, performing second fusion on the transition data set based on the second data fusion path list to generate a service guidance data set of the cloud computing server, including:

acquiring a dynamic sub-list set in the second data fusion path list, wherein the dynamic sub-list set is a list set comprising fusion description characteristics; dividing the dynamic sub-list set into at least two list groups according to the sequence of the feature weights of the fusion description features from large to small; detecting path optimization data included in each of the at least two list packets in parallel; detecting the fusion description characteristics according to the optimized data of each path detected in the at least two list groups to obtain a service optimized data set corresponding to the transition data set; wherein, the dividing the dynamic sub-list set into at least two list groups according to the descending order of the feature weight of the fusion description features comprises: dividing the dynamic sublist set for the first time according to the sequence of the feature weights of the fusion description features from big to small; respectively sampling list attributes for each list group obtained by dividing the list groups according to the sequence from large to small of the feature weight of the fusion description features for the first time, and counting the number of changeable list attributes included in the list attributes obtained by sampling in each list group; for the list groups with the number of the attributes of the modifiable list larger than the set number threshold, dividing the modifiable list groups for the second time according to the sequence from big to small of the feature weight of the fusion description features until the number of the attributes of the modifiable list included in the list attributes sampled in each divided list group is smaller than the set number threshold;

generating a first service optimization logic topology corresponding to the service optimization data set and a second service optimization logic topology corresponding to the transition data set, and determining a plurality of logic topology nodes with different node centrality degrees, which are respectively included in the first service optimization logic topology and the second service optimization logic topology; extracting node pointing information of the service optimization data set at any logic topology node of the first service optimization logic topology, and determining a logic topology node with the maximum node centrality in the second service optimization logic topology as a target logic topology node; mapping the node pointing information to the target logic topology node according to the dynamic distribution pointing information corresponding to the dynamic sublist set so as to obtain node mapping information corresponding to the node pointing information in the target logic topology node; waiting for a set delay after the node mapping information is determined, and then generating a logic matching path set between the service optimization data set and the transition data set based on the cosine distance between the node pointing information and the node mapping information;

acquiring a logic characteristic sequence from the target logic topology node by taking the node mapping information as reference node information, mapping the logic characteristic sequence to the logic topology node where the node pointing information is located according to the logic optimization level corresponding to the logic matching path set, so as to obtain a logic optimization sequence corresponding to the logic characteristic sequence from the logic topology node where the node pointing information is located, and determining a service logic optimization sequence of the logic optimization sequence; acquiring the node pointing information and mapping the node pointing information to a pointing path in the target logical topology node; according to the matching degree between the logic optimization sequence and logic execution parameters corresponding to a plurality of path transfer functions on the directional path, traversing and acquiring a target optimization sequence corresponding to the service logic optimization sequence in the second service optimization logic topology until the node calling heat of the logic topology node where the acquired target optimization sequence is located is consistent with the node calling heat of the service logic optimization sequence in the first service optimization logic topology, stopping acquiring the target optimization sequence in the next logic topology node, and establishing an update relation between the service logic optimization sequence and the target optimization sequence acquired last time; and performing second fusion on the transition data set and the business optimization data set based on the update pairing list of the transition data set and the business optimization data set relative to the update relationship to obtain a business guidance data set of the cloud computing server.

The embodiment of the invention also provides an artificial intelligence platform which comprises a data processing device based on artificial intelligence cloud computing, wherein the functional module of the device executes the method when in work.

The embodiment of the invention also provides an artificial intelligence platform, which comprises a processor, a communication bus and a memory; the processor and the memory communicate via the communication bus, and the processor reads the computer program from the memory and runs the computer program to perform the method described above.

The embodiment of the invention also provides a readable storage medium for a computer, wherein the readable storage medium stores a computer program, and the computer program realizes the method when running.

Compared with the prior art, the data processing method and the artificial intelligence platform based on artificial intelligence cloud computing provided by the embodiment of the invention have the following technical effects: the service matching data set of the cloud service configuration data can be determined based on the service data associated information and the service scene associated information of the cloud service configuration data of the cloud computing server in the obtained cloud data processing record, so that the first fusion and the second fusion of the corresponding data sets are sequentially carried out, and the service guide data set of the cloud computing server can be obtained. The service guide data set is obtained after analyzing the cloud data processing records of the cloud computing server in different service scenes, so that the deep analysis of the service processing of the cloud computing server can be realized through artificial intelligence, and the service guide data set can guide the cloud computing server to optimize service processing logic, so that the subsequent service processing efficiency of the cloud computing server can be improved, and the time consumption of same service processing or similar service processing is reduced.

In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic block diagram of an artificial intelligence platform according to an embodiment of the present invention.

Fig. 2 is a flowchart of a data processing method based on artificial intelligence cloud computing according to an embodiment of the present invention.

Fig. 3 is a block diagram of a data processing apparatus based on artificial intelligence cloud computing according to an embodiment of the present invention.

Fig. 4 is an architecture diagram of a data processing system based on artificial intelligence cloud computing according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

The inventor finds that the key of the technical problem of the current cloud computing server as described in the background art is that the business processing logic is not optimized properly, so that a lot of useless processing logic is added, and further the business processing time is increased.

The above prior art solutions have shortcomings which are the results of practical and careful study of the inventor, and therefore, the discovery process of the above problems and the solutions proposed by the following embodiments of the present invention to the above problems should be the contribution of the inventor to the present invention in the course of the present invention.

Based on the research, the embodiment of the invention provides a data processing method based on artificial intelligence cloud computing and an artificial intelligence platform.

FIG. 1 is a block diagram illustrating an artificial intelligence platform 10 according to an embodiment of the present invention. The artificial intelligence platform in the embodiment of the present invention may be a server with data storage, transmission, and processing functions, as shown in fig. 1, the artificial intelligence platform 10 includes: memory 11, processor 12, communication bus 13 and data processing device 20.

The memory 11, processor 12 and communication bus 13 are electrically connected, directly or indirectly, to enable the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 11 stores a data processing device 20, the data processing device 20 includes at least one software functional module which can be stored in the memory 11 in the form of software or firmware (firmware), and the processor 12 executes various functional applications and data processing by running the software programs and modules stored in the memory 11, such as the data processing device 20 in the embodiment of the present invention, so as to implement the data processing method based on artificial intelligence cloud computing in the embodiment of the present invention.

The Memory 11 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 11 is used for storing a program, and the processor 12 executes the program after receiving an execution instruction.

The processor 12 may be an integrated circuit chip having data processing capabilities. The Processor 12 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like. The various methods, steps and logic blocks disclosed in embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The communication bus 13 is used for establishing communication connection between the artificial intelligence platform and other communication terminal devices (such as a cloud computing server) through a network, and implementing transceiving operation of network signals and data. The network signal may include a wireless signal or a wired signal.

It will be appreciated that the configuration shown in FIG. 1 is merely illustrative, and that the artificial intelligence platform 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.

Fig. 2 shows a flowchart of a data processing method based on artificial intelligence cloud computing according to an embodiment of the present invention. The method steps defined by the flow related to the method are applied to an artificial intelligence platform and can be realized by the processor 12, and the method comprises the following steps S21-S24.

Step S21, n cloud data processing records of the cloud computing server are acquired.

For example, a cloud data processing record includes a feature extraction record and a feature recombination record in a business scenario, and n is a positive integer. The business scenario can be a service scenario of various different fields, such as a government enterprise service, a personal tax return service, a cloud game service, a smart grid service, a smart medical service, a blockchain payment service, a blockchain financial service, a shared hotspot smart parking service, and the like. The feature extraction record is used for representing the data features of the service data in the service scene, and the feature recombination record is used for representing the feature recombination conditions of the data features in different scenes.

Step S22, acquiring a service matching data set of the cloud service configuration data based on the service data association information and the service scene association information of the cloud service configuration data of the cloud computing server in the cloud data processing record; and performing first fusion on the service matching data set of the cloud service configuration data and the sample data set in a preset database to generate a transition data set.

For example, the cloud service configuration data is execution script data configured for the cloud computing server in advance according to business processing requirements and used for business processing. The service data association information is information of a service association identifier corresponding to the cloud service configuration data in the cloud data processing record. The service scene correlation information is information of a service scene identifier corresponding to the cloud service configuration data in the cloud data processing record. The service association identifier and the service scenario identifier may be characters, numbers or words, and are not limited herein. The service matching data set is a data set corresponding to the service execution data matched with the cloud service configuration data. The transition data set is obtained after the service matching data set and the sample data set are fused according to the service matching correlation degree.

And step S23, acquiring multidimensional configuration data characteristics at intervals from the data characteristic distribution queue of the transition data set.

For example, the data feature distribution queue refers to a distribution queue formed by data features in the transition data set corresponding to the cloud service configuration data in time sequence. The multidimensional configuration data features refer to data features on a plurality of description dimensions corresponding to the cloud computing server and are used for indicating the service processing logic and the service processing scene of the cloud computing server.

For example, the interval obtaining of the multidimensional configuration data feature from the data feature distribution queue of the transition data set further includes: determining a queue clustering area identifier of the data feature distribution queue, and acquiring multi-dimensional configuration data features according to an identifier interval corresponding to the queue clustering area identifier.

Step S24, performing second fusion on the transition data set based on the service data associated information and the service scene associated information mapped in the cloud data processing record by the multidimensional configuration data characteristics to generate a service guide data set of the cloud computing server; and sending the business guide data set to the cloud computing server so that the cloud computing server optimizes business processing logic according to the business guide data set.

For example, the service guide data set can guide the cloud computing server to perform service processing logic optimization, for example, when some services are processed, processing efficiency is improved by combining processing nodes or performing peak load shifting processing, waiting time of service processing is reduced, and flexibility of the cloud computing server in service processing is improved.

It can be understood that, through the steps S21 to S24, the service matching data set of the cloud service configuration data can be determined based on the service data association information and the service scene association information of the cloud service configuration data of the cloud computing server in the obtained cloud data processing record, so that the first fusion and the second fusion of the corresponding data sets are sequentially performed, and thus, the service guidance data set of the cloud computing server can be obtained. The service guide data set is obtained after analyzing the cloud data processing records of the cloud computing server in different service scenes, so that the deep analysis of the service processing of the cloud computing server can be realized through artificial intelligence, and the service guide data set can guide the cloud computing server to optimize service processing logic, so that the subsequent service processing efficiency of the cloud computing server can be improved, and the time consumption of same service processing or similar service processing is reduced.

In one example, in order to ensure consistency of the order of data set fusion, the first fusion of the service matching data set of the cloud service configuration data and the sample data set in the preset database, which is described in step S22, generates a transition data set, which may be implemented as described in steps S221 and S222 below.

Step S221, a first data fusion path list is determined according to the service matching data set of the cloud service configuration data.

For example, the first data fusion path list is used to record sequential information of a fusion path between the transition data set and a cloud data processing record of the cloud computing server.

Step S222, performing a first fusion on the sample data set in the preset database based on the first data fusion path list, and generating the transition data set.

By adopting the above design, the matching between the service matching data set and the sample data set can be realized according to the sequence information of the fusion path recorded in the first data fusion path list by applying the steps S221 and S222, so as to ensure the consistency of the sequence of data set fusion.

Further, on the basis of step S221, a first data fusion path list is determined according to the service matching data set of the cloud service configuration data, and further includes what is described in steps S2211 and S2212 below.

Step S2211, a first data feature clustering model is constructed.

For example, the first data feature clustering model includes a first configuration data distribution table, a first cluster label distribution table, and a first model network distribution table. The first configuration data distribution table is used for adjusting a data structure of cloud service configuration data after screening in the transition data set to meet a data structure requirement of a corresponding service matching data set, the screened cloud service configuration data refers to cloud service configuration data obtained after removing cloud service configuration data with a configuration heat value lower than a set heat value, the first clustering label distribution table is used for adjusting service indexes of the cloud service configuration data in the transition data set to meet a service requirement of the corresponding service matching data set, and the first model network distribution table is used for adjusting data queue priority of the transition data set to enable the data queue priority to be in a level descending state.

Step S2212, determining the first data fusion path list meeting the preliminary fusion condition based on the service matching data set of the cloud service configuration data and the first data feature clustering model.

For example, the preliminary fusion condition includes that a ratio between a model generalization rate and a model cluster rejection rate of the first data feature cluster model takes a minimum value.

It can be understood that, when the contents described in step S2211 and step S2212 are executed, the first data fusion path list can be determined based on the constructed first data feature clustering model, so as to ensure accurate clustering of the first data fusion path list in the data feature layer, thus avoiding the first data fusion path list from missing list units, and ensuring the integrity of the first data fusion path list.

Further, before the step of constructing the first data feature clustering model described in step S2211, the following steps (1) to (3) may also be included.

(1) And mapping the cloud service configuration data in a preset heat mapping list according to a service matching data set of the cloud service configuration data based on the configuration heat record of the cloud service configuration data.

For example, a heat calculation mode of the cloud service configuration data is the same as that of the preset heat mapping list, and the heat value is used for representing the frequency of business processing.

(2) And acquiring a mapping heat value of the configuration heat value of each group of cloud service configuration data in the preset heat mapping list.

(3) And in response to the fact that the mapping heat value is lower than the target heat value corresponding to the preset heat mapping list, removing the cloud service configuration data corresponding to the mapping heat value to obtain the screened cloud service configuration data.

When the contents described in the steps (1) to (3) are applied, the cloud service configuration data can be screened, so that the cloud service configuration data is simplified, the data set fusion rate can be improved, and the rapid generation of the business guidance data set is ensured.

In a possible embodiment, on the basis of step S222, based on the first data fusion path list, performing first fusion on the sample data set in the preset database to generate the transition data set, which may be further implemented by the following contents described in steps S2221 to S2223.

Step S2221, a path incidence matrix of the first data fusion path list and a data set fusion label corresponding to each fusion path are established; on the premise that the first data fusion path list contains the data over-fusion packet and the data under-fusion packet through the path incidence matrix, determining label similarity coefficients between the data set fusion labels corresponding to the fusion paths under the data under-fusion grouping of the first data fusion path list and the data set fusion labels corresponding to the fusion paths under the data over-fusion grouping of the first data fusion path list according to the data set fusion labels corresponding to the fusion paths under the data under-fusion grouping of the first data fusion path list and the label weights of the data set fusion labels, adjusting a data set fusion label corresponding to a fusion path similar to the data set fusion label corresponding to the fusion path under the data under-fusion group and the data over-fusion group of the first data fusion path list to a corresponding data over-fusion group; under the condition that a data set fusion tag corresponding to a plurality of fusion paths is included in a current data under-fusion group of a first data fusion path list, determining a tag similarity coefficient between the data set fusion tags corresponding to the fusion paths in the current data under-fusion group of the first data fusion path list according to the data set fusion tag corresponding to the fusion path in the data over-fusion group of the first data fusion path list and the tag weight of the data set fusion tag, and screening the data set fusion tag corresponding to the fusion path in the current data under-fusion group according to the tag similarity coefficient between the data set fusion tags corresponding to the fusion paths; and setting a label adjustment index coefficient for the labeled data set fusion label obtained by screening according to the data set fusion label corresponding to the fusion path under the data over-fusion grouping of the first data fusion path list and the label weight of the data set fusion label, and adjusting at least part of the labeled data set fusion label under the data over-fusion grouping of the first data fusion path list according to the label adjustment index coefficient.

Step S2222, a fusion tag distribution list of the first data fusion path list is generated based on the data set fusion tag under the data over-fusion grouping and the data set fusion tag under the data under-fusion grouping; determining a fusion weight value of each list element of the fusion label distribution list, and determining the number of the list elements with the fusion weight values smaller than or equal to a preset target weight value according to the fusion weight value of each list element; calculating the ratio of the number of the list elements to the total number of the list elements of the fusion label distribution list to obtain the weight distribution ratio of the fusion label distribution list; determining list area distribution information of the fusion label distribution list; determining list ordering information of the fusion label distribution list according to the weight distribution proportion of the fusion label distribution list and list region distribution information of the fusion label distribution list; and determining the data set fusion priority corresponding to the sorting logic sequence where the list sorting information of the fusion tag distribution list is located according to the corresponding relation between the pre-stored sorting logic sequence and the data set fusion priority, and using the data set fusion priority as the data set fusion priority queue of the first data fusion path list.

Step S2223, the first data to be fused in the service matching data set is sequenced through the data set fusion priority queue to obtain a first sequencing sequence, and the second data to be fused in the sample data set is sequenced through the data set fusion priority queue to obtain a second sequencing sequence; and performing first fusion on each first data to be fused and one second data to be fused corresponding to each first data to be fused according to the one-to-one correspondence relationship between the sequence units in the first sequencing sequence and the second sequencing sequence to obtain the transition data set.

It can be understood that by implementing the above steps S2221-S2223, the data set fusion tags under the data over-fusion packet and the data under-fusion packet are determined first, and then the data set fusion tags under the data over-fusion packet and the data under-fusion packet are redistributed, so that the time-efficient pairing with the first data fusion path list can be ensured. Further, a fusion tag distribution list of the first data fusion path list is generated based on the data set fusion tags under the redistributed data overfusion packet and the data underfusion packet, and a data set fusion priority queue of the first data fusion path list can be further determined, so that one-to-one corresponding fusion between the service matching data set and the sample data set can be realized through the data set fusion priority queue, and the transition data set is ensured not to be confused between the data queues.

In some examples, the second fusing of the transition data set based on the service data related information and the service scenario related information mapped in the cloud data processing record by the multidimensional configuration data feature described in step S24 to generate the service guidance data set of the cloud computing server may further include the following contents described in steps S241 to S243.

Step S241, obtaining a service matching data set of the multidimensional configuration data feature based on the service data associated information and the service scene associated information mapped in the cloud data processing record by the multidimensional configuration data feature.

Step S242, determining a second data fusion path list according to the service matching data set of the multidimensional configuration data feature, where the second data fusion path list is used to record sequential information of a fusion path between the service matching data set of the multidimensional configuration data feature of the cloud computing server and the cloud data processing record of the cloud computing server.

And step S243, performing second fusion on the transition data set based on the second data fusion path list, and generating a service guidance data set of the cloud computing server.

It can be understood that through the above steps S241 to S243, the second fusion of the transition data sets can be implemented based on the second data fusion path list, thereby ensuring accurate and reliable generation of the business guidance data sets.

In the actual application process, the inventor finds that, in order to ensure the matching degree of the business guidance data set and the execution logic of the cloud computing server and avoid failure of business logic optimization caused by incompatibility of data processing logic between the cloud computing server and the business guidance data set, the transition data set is fused for the second time based on the second data fusion path list described in step S243 to generate the business guidance data set of the cloud computing server, and further, the content described in the following steps S2431 to S2433 may be included.

Step S2431, acquiring a dynamic sublist set in the second data fusion path list, wherein the dynamic sublist set is a list set including fusion description features; dividing the dynamic sub-list set into at least two list groups according to the sequence of the feature weights of the fusion description features from large to small; detecting path optimization data included in each of the at least two list packets in parallel; and detecting the fusion description characteristics according to the optimization data of each path detected in the at least two list groups to obtain a service optimization data set corresponding to the transition data set.

For example, the dividing the dynamic sub-list set into at least two list groups according to the descending order of the feature weight of the fusion description feature includes: dividing the dynamic sublist set for the first time according to the sequence of the feature weights of the fusion description features from big to small; respectively sampling list attributes for each list group obtained by dividing the list groups according to the sequence from large to small of the feature weight of the fusion description features for the first time, and counting the number of changeable list attributes included in the list attributes obtained by sampling in each list group; and for the list groups with the number of the attributes of the modifiable list larger than the set number threshold, dividing the modifiable list groups for the second time according to the descending order of the feature weights of the fusion description features until the number of the attributes of the modifiable list included in the list attributes sampled in each divided list group is smaller than the set number threshold.

Step S2432, generating a first service optimization logic topology corresponding to the service optimization data set and a second service optimization logic topology corresponding to the transition data set, and determining a plurality of logic topology nodes with different node centrality degrees respectively included in the first service optimization logic topology and the second service optimization logic topology; extracting node pointing information of the service optimization data set at any logic topology node of the first service optimization logic topology, and determining a logic topology node with the maximum node centrality in the second service optimization logic topology as a target logic topology node; mapping the node pointing information to the target logic topology node according to the dynamic distribution pointing information corresponding to the dynamic sublist set so as to obtain node mapping information corresponding to the node pointing information in the target logic topology node; and waiting for a set delay after the node mapping information is determined, and then generating a logic matching path set between the service optimization data set and the transition data set based on the cosine distance between the node pointing information and the node mapping information.

Step S2433, taking the node mapping information as reference node information to obtain a logic characteristic sequence in the target logic topology node, mapping the logic characteristic sequence to the logic topology node where the node pointing information is located according to the logic optimization level corresponding to the logic matching path set, so as to obtain a logic optimization sequence corresponding to the logic characteristic sequence in the logic topology node where the node pointing information is located, and determining a service logic optimization sequence of the logic optimization sequence; acquiring the node pointing information and mapping the node pointing information to a pointing path in the target logical topology node; according to the matching degree between the logic optimization sequence and logic execution parameters corresponding to a plurality of path transfer functions on the directional path, traversing and acquiring a target optimization sequence corresponding to the service logic optimization sequence in the second service optimization logic topology until the node calling heat of the logic topology node where the acquired target optimization sequence is located is consistent with the node calling heat of the service logic optimization sequence in the first service optimization logic topology, stopping acquiring the target optimization sequence in the next logic topology node, and establishing an update relation between the service logic optimization sequence and the target optimization sequence acquired last time; and performing second fusion on the transition data set and the business optimization data set based on the update pairing list of the transition data set and the business optimization data set relative to the update relationship to obtain a business guidance data set of the cloud computing server.

It can be understood that, by executing the contents described in the above steps S2431 to S2433, firstly, the service optimization data set corresponding to the transition data set is determined based on the second data fusion path list, and secondly, a first service optimization logic topology corresponding to the service optimization data set and a second service optimization logic topology corresponding to the transition data set are respectively generated, so as to generate a logic matching path set between the service optimization data set and the transition data set based on the first service optimization logic topology and the second service optimization logic topology. In this way, the traversal acquisition of the target optimization sequence can be realized according to the edit matching path set, so that the update relationship between the business logic optimization sequence and the target optimization sequence is established. Therefore, the matching degree of the service guidance data set obtained by the second fusion based on the updating relation and the execution logic of the cloud computing server can be ensured, and the failure of service logic optimization caused by incompatibility of the data processing logic between the cloud computing server and the service guidance data set is avoided.

In an alternative embodiment, the acquiring a service matching data set of the cloud service configuration data based on the service data associated information and the service scenario associated information of the cloud service configuration data of the cloud computing server in the cloud data processing record as described in step S22 may further include the following steps a to d.

Step a, acquiring initial service data associated information and initial service scene associated information of initial configuration data of the cloud computing server in the cloud data processing record.

Step b, in response to the fact that the configuration key script in the initial configuration data is a service key script and the configuration key script does not have target service scene correlation information, rejecting the configuration key script; and the initial service scene associated information and the target service scene associated information have scene interaction identification.

And c, in response to the fact that the configuration key script in the initial configuration data is a non-service key script and the configuration key script does not have target service scene associated information, selecting the target script which has the shortest execution time interval with the configuration key script and the initial service scene associated information to replace the configuration key script.

And d, obtaining a service matching data set of the cloud service configuration data based on the updated configuration key script.

It can be understood that, by executing the steps a to d, the updating of the configuration key script in the initial configuration data can be realized based on the initial service data associated information and the initial service scene associated information of the initial configuration data, so that the service matching data set of the cloud service configuration data is obtained based on the updated configuration key script. Therefore, the execution matching efficiency between the service matching data set and the script file can be ensured, and the redundant data in the service matching data set can be effectively removed.

In an alternative embodiment, the acquiring of the n cloud data processing records of the cloud computing server described in step S21 may further include the following steps S211 to S214.

Step S211, obtaining m to-be-processed cloud data processing records of the cloud computing server, where m is a positive integer greater than n.

Step S212, cloud service configuration data of the cloud computing server in the feature extraction record is extracted.

Step S213, determining a service scene of the cloud computing server in the feature extraction record according to the service data association information of the cloud service configuration data of the cloud computing server in the feature extraction record.

Step S214, selecting the n cloud data processing records with the service scenes meeting the set requirements from the m cloud data processing records to be processed.

It can be understood that, by performing the above steps S211 to S214, the adaptability between the cloud data processing record and the business scenario can be ensured, so as to implement denoising of the cloud data processing record.

Based on the same inventive concept, fig. 3 shows a data processing apparatus 20 based on artificial intelligence cloud computing according to an embodiment of the present invention, where the data processing apparatus 20 includes:

the record obtaining module 21 is configured to obtain n cloud data processing records of the cloud computing server; the cloud data processing record comprises a feature extraction record and a feature recombination record in a service scene, and n is a positive integer;

the first fusion module 22 is configured to obtain a service matching data set of cloud service configuration data based on service data association information and service scenario association information of the cloud service configuration data of the cloud computing server in the cloud data processing record; performing first fusion on a service matching data set of the cloud service configuration data and a sample data set in a preset database to generate a transition data set;

a feature obtaining module 23, configured to obtain multidimensional configuration data features at intervals from a data feature distribution queue of the transition data set, where the data feature distribution queue is a distribution queue formed by data features in the transition data set corresponding to the cloud service configuration data in time sequence;

a second fusion module 24, configured to perform second fusion on the transition data set based on the service data association information and the service scene association information mapped in the cloud data processing record by the multidimensional configuration data feature, so as to generate a service guidance data set of the cloud computing server; and sending the business guide data set to the cloud computing server so that the cloud computing server optimizes business processing logic according to the business guide data set.

It is to be understood that reference is made to the description of the method embodiment shown in fig. 2 for a description of the device embodiment.

Based on the same inventive concept, fig. 4 shows an artificial intelligence based cloud computing data processing system 40 provided by an embodiment of the present invention, where the data processing system 40 may include an artificial intelligence platform 10 and a cloud computing server 30, which are in communication with each other, and the description about the data processing system 40 is as follows.

A data processing system based on artificial intelligence cloud computing comprises an artificial intelligence platform and a cloud computing server which are communicated with each other; wherein:

the artificial intelligence platform is used for:

performing second fusion on the transition data set based on the service data associated information and the service scene associated information mapped in the cloud data processing record by the multidimensional configuration data characteristics to generate a service guide data set of the cloud computing server; sending the business guide data set to the cloud computing server;

the cloud computing server is configured to: and optimizing the service processing logic according to the service guide data set.

It is to be understood that reference is made to the description of the method embodiment shown in fig. 2 for further description of the system embodiment.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an artificial intelligence platform, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data processing method based on artificial intelligence cloud computing is applied to an artificial intelligence platform, and the method comprises the following steps:

acquiring n cloud data processing records of the cloud computing server; the cloud data processing record comprises a feature extraction record and a feature recombination record in a service scene, and n is a positive integer;

2. The method of claim 1, wherein the first fusing the service matching data set of the cloud service configuration data with the sample data set in a preset database to generate a transition data set comprises:

3. The method of claim 2, wherein determining a first data fusion path list according to the traffic matching dataset of the cloud service configuration data comprises:

4. The method of claim 3, wherein before constructing the first data feature clustering model, further comprising:

5. The method according to claim 2, wherein performing a first fusion on the sample data set in the preset database based on the first data fusion path list to generate the transition data set comprises:

6. The method according to claim 1, wherein the second fusing of the transition data set based on the service data related information and the service scenario related information mapped in the cloud data processing record by the multidimensional configuration data feature to generate the service guidance data set of the cloud computing server comprises:

7. The method according to claim 6, wherein fusing the transition data set for the second time based on the second data fusion path list to generate the business guidance data set of the cloud computing server comprises:

8. An artificial intelligence platform comprising an artificial intelligence based cloud computing data processing apparatus comprising functional modules that, when operated, perform the method of any one of claims 1 to 7.

9. An artificial intelligence platform comprising a processor, a communication bus, and a memory; the processor and the memory communicate via the communication bus, the processor reading a computer program from the memory and operating to perform the method of any of claims 1-7.

10. A computer-readable storage medium, characterized in that the readable storage medium stores a computer program which, when executed, implements the method of any one of claims 1-7.