CN114281553A - Business processing method and system and cloud platform - Google Patents
Business processing method and system and cloud platform Download PDFInfo
- Publication number
- CN114281553A CN114281553A CN202210218507.9A CN202210218507A CN114281553A CN 114281553 A CN114281553 A CN 114281553A CN 202210218507 A CN202210218507 A CN 202210218507A CN 114281553 A CN114281553 A CN 114281553A
- Authority
- CN
- China
- Prior art keywords
- determining
- event
- service data
- array
- business
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The service processing method, the system and the cloud platform provided by the embodiment of the invention can determine the corresponding service data set to be called when a service processing application is received, further perform data association analysis on each group of service data to be called to obtain the corresponding associated service data set, can combine different associated service data sets to perform targeted data calling processing, and avoid the problem that part of the associated service data sets are changed when the service data sets to be called are directly called, so that the subsequent services cannot be normally handled due to the fact that part of the associated service data sets are changed. And performing service data calling processing according to the associated service data set, wherein the current use state and the modified use state of the associated service data set can be considered, so that the precision and the reliability of the acquired service data set to be called when the service processing application is processed are ensured, and the normal use of the associated service data set corresponding to the service data set to be called when the service processing application is completed can also be ensured.
Description
Technical Field
The invention relates to the technical field of business processing, in particular to a business processing method, a business processing system and a cloud platform.
Background
Most of the current business handling processes involve interactive businesses among multiple data sources, related technologies generally call business data in corresponding data sources directly according to business requirements while ignoring data relevance among different data sources, and in the business data calling process, if data change exists, the related business data may be affected, so that normal handling of subsequent businesses is affected. Therefore, a more optimized service data calling technique is needed to avoid the above problems.
Disclosure of Invention
In order to solve the technical problems in the related art, the invention provides a service processing method, a service processing system and a cloud platform.
In a first aspect, an embodiment of the present invention provides a service processing method, which is applied to a service processing cloud platform, where the service processing cloud platform is in communication connection with a digital service terminal, and the method includes:
responding to a service processing application initiated by the digital service terminal, and determining a service data set to be called corresponding to the service processing application;
determining an associated service data set corresponding to each group of service data to be called aiming at each group of service data to be called in the service data set to be called;
and calling the service data according to the associated service data set corresponding to each group of the service data to be called.
Under some design ideas which can be independently implemented, the determining an associated service data set corresponding to each group of service data to be called includes:
identifying the service theme of each group of calling service data;
and determining an associated service data set matched with the service theme from a preset service database.
Under some design ideas which can be independently implemented, the determining, from a preset business database, an associated business data set matching the business topic includes:
determining a business event handling record set which has upstream and downstream relation with the business theme; the business event handling record set comprises at least one group of business event handling records with a precedence relationship;
determining an exception event transaction record set via the transaction event transaction record set; the abnormal event handling record set comprises at least one group of abnormal event handling records with a precedence relationship;
according to the business event handling record set, determining a business event significant content set through a first significant content mining subnet covered by a preset GCN network; wherein the set of business event salient content comprises at least one business event salient content;
according to the abnormal event handling record set, determining an abnormal event significant content set through a second significant content mining subnet covered by the preset GCN network; wherein the set of exceptional significant content comprises at least one exceptional significant content;
determining semantic description values matched with the business event handling records through semantic parsing subnets covered by the preset GCN according to the business event significant content set and the abnormal event significant content set;
determining a subject feature value of the set of business event transaction records via the semantic description value; and determining a related service data set from the preset service database according to the theme characteristic value.
Under some design ideas which can be independently implemented, the determining, according to the significant content set of the business event and the significant content set of the abnormal event, semantic description values which are matched with the business event handling record set through a semantic parsing subnet covered by the preset GCN network includes:
determining at least one first description array through a first scene tendency model covered by the preset GCN according to the service event significant content set; wherein each first description array corresponds to a service event salient content;
determining at least one second description array through a second scene trend model covered by the preset GCN according to the abnormal event significant content set; wherein each second description array corresponds to a significant content of an exceptional event;
performing a connecting operation on the at least one first description array and the at least one second description array to obtain at least one target description array; each target description array covers a first description array and a second description array;
and determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN according to the at least one target description array.
Under some design considerations which can be independently implemented, the determining, by the first scene trend model covered by the preset GCN network, at least one first description array according to the significant content set of the business event includes:
for each set of traffic event salient content in the set of traffic event salient content, determining a first local downsampling salient content by a local downsampling unit covered by the first scene trending model; wherein the first scene trending model matches the pre-set GCN network;
for each group of the business event salient content in the business event salient content set, determining a first global down-sampling salient content through a global down-sampling unit covered by the first scene trending model;
for each group of the business event salient contents in the business event salient content set, determining a first multi-modal salient content through a feature optimization unit covered by the first scene tendency model according to the first local downsampled salient content and the first global downsampled salient content;
for each group of the business event salient contents in the business event salient content set, determining a first description array through a first global down-sampling unit covered by the first scene tendency model according to the first multi-modal salient contents and the business event salient contents.
Under some design considerations which can be independently implemented, the determining, by a second scene trend model covered by the preset GCN network, at least one second description array according to the exceptional significant content set includes:
for each set of exceptional salient content in the set of exceptional salient content, determining a second locally downsampled salient content by a locally downsampling unit covered by the second scene trending model; wherein the second scene trending model matches the pre-set GCN network;
for each set of exceptional salient content in the set of exceptional salient content, determining a second globally downsampled salient content by a global downsampling unit covered by the second scene trending model;
for each group of the abnormal event salient contents in the abnormal event salient content set, determining a second multi-modal salient content through a feature optimization unit covered by the second scene tendency model according to the second local downsampling salient content and the second global downsampling salient content;
for each group of the abnormal event salient content in the abnormal event salient content set, determining a second description array through a second global down-sampling unit covered by the second scene trend model according to the second multi-modal salient content and the abnormal event salient content.
Under some independently implementable design ideas, the target description array is multiple; the determining, according to the at least one target description array, the semantic description value matched with the service event handling record set through the semantic parsing subnet covered by the preset GCN network includes:
determining a multi-modal description array through a sequence tendency model covered by the preset GCN network according to the at least one target description array; wherein the multimodal descriptor array is determined via the at least one target descriptor array and at least one priority index, each target descriptor array corresponding to a priority index;
and determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN according to the multi-modal description array.
Under some independently implementable design considerations, the determining a multi-modal array of descriptions from the at least one array of target descriptions through an order-inclined model covered by the predetermined GCN network comprises:
determining at least one first local description array through a first local model covered by the sequential tendency model according to the at least one target description array; wherein the sequential trending model matches the pre-set GCN network;
determining at least one second local description array through a second local model covered by the sequence tendency model according to the at least one first local description array;
determining at least one priority index via the at least one second local description array; wherein each priority index corresponds to a target description array;
determining the multimodal description array via the at least one target description array and at least one priority index.
Under some design ideas which can be independently implemented, the number of the first description arrays is multiple; the determining, according to the significant content set of the business event and the significant content set of the abnormal event, the semantic description value matched with the business event transaction record through the semantic parsing subnet covered by the preset GCN network includes:
determining at least one first description array through a first global down-sampling unit covered by the preset GCN network according to the service event significant content set; wherein each first description array corresponds to a service event salient content;
determining at least one second description array through a second global down-sampling unit covered by the preset GCN according to the abnormal event significant content set; wherein each second description array corresponds to a significant content of an exceptional event;
performing a connecting operation on the at least one first description array and the at least one second description array to obtain at least one target description array; each target description array covers a first description array and a second description array;
determining a multi-modal description array through a sequence tendency model covered by the preset GCN network according to the at least one target description array; wherein the multimodal descriptor array is determined via the at least one target descriptor array and at least one priority index, each target descriptor array corresponding to a priority index;
and determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN according to the multi-modal description array.
Under some independently implementable design considerations, the determining a set of exception event transaction records via the set of business event transaction records includes:
for each group of business event handling records in the business event handling record set, determining first abnormal event distribution, second abnormal event distribution and third abnormal event distribution through a handling record optimization network;
and generating abnormal event handling records matched with each group of business event handling records through the first abnormal event distribution, the second abnormal event distribution and the third abnormal event distribution matched with each group of business event handling records.
In a second aspect, the present invention further provides a service processing system, including a service processing cloud platform and a digital service terminal, which are in communication connection with each other in advance; the digital service terminal is used for initiating a service processing application to the service processing cloud platform; the digital service terminal is used for responding to a service processing application initiated by the digital service terminal and determining a service data set to be called corresponding to the service processing application; determining an associated service data set corresponding to each group of service data to be called aiming at each group of service data to be called in the service data set to be called; and calling the service data according to the associated service data set corresponding to each group of the service data to be called.
In a third aspect, the present invention further provides a service processing cloud platform, including a processor and a memory; the processor is connected with the memory in communication, and the processor is used for reading the computer program from the memory and executing the computer program to realize the method.
The method and the device can determine the corresponding service data sets to be called when a service processing application is received, and further perform data association analysis on each group of service data to be called to obtain the corresponding associated service data sets, so that different associated service data sets can be combined to perform targeted data calling processing, the problem that part of the associated service data sets are changed when the service data sets to be called are directly called is solved, and further follow-up evasive services cannot be normally handled due to the fact that part of the associated service data sets are changed. It can be understood that, the service data calling processing is performed according to the associated service data set, and the current use state and the modified use state of the associated service data set can be considered, so that the precision and the reliability of the acquired service data set to be called when the service processing application is processed are ensured, and the normal use of the associated service data set corresponding to the service data set to be called when the service processing application is completed can also be ensured.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic diagram of a hardware structure of a service processing cloud platform according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a service processing method according to an embodiment of the present invention.
Fig. 3 is a schematic communication architecture diagram of an application environment of a service processing method according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method provided by the embodiment of the invention can be executed in a service processing cloud platform, computer equipment or a similar operation device. Taking an operation on a service processing cloud platform as an example, fig. 1 is a hardware structure block diagram of a service processing cloud platform implementing a service processing method according to an embodiment of the present invention. As shown in fig. 1, the business processing cloud platform 10 may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally, the business processing cloud platform may further include a transmission device 106 for communication functions. It can be understood by those of ordinary skill in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the business processing cloud platform. For example, business process cloud 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 memory 104 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a service processing method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which may be connected to business processing cloud platform 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the service processing cloud platform 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
Based on this, please refer to fig. 2, fig. 2 is a schematic flowchart of a service processing method according to an embodiment of the present invention, where the method is applied to a service processing cloud platform communicatively connected to a digital service terminal, and may further include the following technical solutions.
Step 21, responding to the service processing application initiated by the digital service terminal, and determining a service data set to be called corresponding to the service processing application.
In the embodiment of the present invention, the digital service terminal may be a banking service terminal, an office service terminal, or an educational service terminal, but is not limited thereto. The service processing application initiated by the digital service terminal can be different types of applications such as text application, voice application and the like. The service processing cloud platform can analyze the service processing application after receiving the service processing application, so as to obtain service data required by the service processing application, namely a service data set to be called.
And step 22, determining an associated service data set corresponding to each group of service data to be called aiming at each group of service data to be called in the service data set to be called.
In the embodiment of the present invention, a data source corresponding to each group of to-be-called service data in the to-be-called service data set may be associated with other data sources, and for convenience of description, it is described by taking an example that there is no intersection between an associated service data set corresponding to each group of to-be-called service data and a to-be-called service data set. It can be understood that, by determining the associated service data set corresponding to each group of service data to be invoked, reference can be provided for subsequent data invocation, thereby avoiding negative effects caused by "moving the whole body by pulling" service data modification.
Under some design considerations that can be implemented independently, the determining of the associated service data set corresponding to each set of service data to be called, which is described in step 22, may include the technical solutions described in step 221 and step 222.
And step 221, identifying the service theme of each group of calling service data.
For example, when the service data to be called is text data, the service theme of the calling service data can be analyzed and summarized through a natural language processing technology. For example, the business topic may be "identity information modification", "office progress update", or the like.
Step 222, determining an associated service data set matched with the service theme from a preset service database.
In the embodiment of the invention, the preset service database stores service data sets of different data sources, and for the convenience of understanding, it is assumed that no intersection exists between the service data stored in the preset service database and the service data set to be called. In this way, through step 221 and step 222, the associated business data set can be precisely located by the business topic.
In some possible embodiments, the step 222 of determining the associated service data set matching the service topic from the preset service database may include the technical solutions described in the steps 2221 to 2226.
Step 2221, determining a business event handling record set which has upstream and downstream connection with the business theme; the business event handling record set comprises at least one group of business event handling records with a precedence relationship.
For example, the upstream and downstream contact may be a presence service association (such as a service category association or a service content association).
Step 2222, determining an abnormal event handling record set through the service event handling record set; the abnormal event handling record set comprises at least one group of abnormal event handling records with a precedence relationship.
For example, the existence of precedence relationships may be understood as sequential.
It will be appreciated that in some possible embodiments, the determination of the set of exception event transaction records via the set of business event transaction records described in step 2222 may include the following: for each group of business event handling records in the business event handling record set, determining first abnormal event distribution, second abnormal event distribution and third abnormal event distribution through a handling record optimization network; and generating abnormal event handling records matched with each group of business event handling records through the first abnormal event distribution, the second abnormal event distribution and the third abnormal event distribution matched with each group of business event handling records. In this way, the integrity of the exception event transaction record can be ensured.
Step 2223, determining a significant content set of the service event through a first significant content mining subnet covered by a preset GCN network according to the service event handling record set; wherein the set of business event salient content includes at least one business event salient content.
For example, the predetermined GCN network may be trained according to a related training method, and the salient content mining subnet may be understood as a feature mining layer.
Step 2224, determining a significant content set of the abnormal event through a second significant content mining subnet covered by the preset GCN network according to the abnormal event handling record set; wherein the set of exceptional significant content comprises at least one exceptional significant content.
Step 2225, determining semantic description values matched with the business event transaction records through the semantic parsing sub-networks covered by the preset GCN network according to the business event significant content set and the abnormal event significant content set.
For example, a semantic parsing subnet may be understood as a classification layer and a semantic description value may be understood as a classification value.
In some possible implementations, the determining semantic description values matching the service event transaction record set according to the service event significant content set and the abnormal event significant content set in step 2225 through the semantic parsing sub-network covered by the preset GCN network may include the technical solutions described in steps 22251 to 22254.
Step 22251, determining at least one first description array through the first scene tendency model covered by the preset GCN network according to the significant content set of the service event; wherein each first description array corresponds to a business event salient content.
For example, the scene trending model may be a spatial attention network and the description array may be a feature vector. Based on this, in some possible embodiments, the determining at least one first description array according to the significant content set of the service event through the first scene trending model covered by the predetermined GCN network in step 22251 may include the following: for each set of traffic event salient content in the set of traffic event salient content, determining a first local downsampling salient content by a local downsampling unit covered by the first scene trending model; wherein the first scene trending model matches the pre-set GCN network; for each group of the business event salient content in the business event salient content set, determining a first global down-sampling salient content through a global down-sampling unit covered by the first scene trending model; for each group of the business event salient contents in the business event salient content set, determining a first multi-modal salient content through a feature optimization unit covered by the first scene tendency model according to the first local downsampled salient content and the first global downsampled salient content; for each group of the business event salient contents in the business event salient content set, determining a first description array through a first global down-sampling unit covered by the first scene tendency model according to the first multi-modal salient contents and the business event salient contents.
For example, local downsampling may be understood as maximum pooling processing, and global downsampling may be understood as average pooling processing, so that the simplification of the first description array may be realized as much as possible while the integrity of the first description array is guaranteed.
Step 22252, determining at least one second description array through a second scene trend model covered by the preset GCN network according to the abnormal event significant content set; wherein each second descriptor array corresponds to a significant content of the exception event.
In some possible embodiments, the determining at least one second description array according to the exceptional significant content set by the second scenario-oriented model covered by the predetermined GCN network, as described in step 22252, may include the following: for each set of exceptional salient content in the set of exceptional salient content, determining a second locally downsampled salient content by a locally downsampling unit covered by the second scene trending model; wherein the second scene trending model matches the pre-set GCN network; for each set of exceptional salient content in the set of exceptional salient content, determining a second globally downsampled salient content by a global downsampling unit covered by the second scene trending model; for each group of the abnormal event salient contents in the abnormal event salient content set, determining a second multi-modal salient content through a feature optimization unit covered by the second scene tendency model according to the second local downsampling salient content and the second global downsampling salient content; for each group of the abnormal event salient content in the abnormal event salient content set, determining a second description array through a second global down-sampling unit covered by the second scene trend model according to the second multi-modal salient content and the abnormal event salient content. By the design, the simplification of the second description array can be realized as far as possible on the premise of ensuring the integrity of the second description array.
Step 22253, performing join operation on the at least one first description array and the at least one second description array to obtain at least one target description array; each target description array covers a first description array and a second description array.
Step 22254, determining semantic description values matched with the service event handling record set through the semantic parsing sub-network covered by the preset GCN network according to the at least one target description array.
By means of the design, the semantic description values can be accurately determined and the reliability of the semantic description values can be guaranteed as far as possible by applying the steps 22251-22254.
In some examples, the target description array is plural, and based on this, the determining semantic description values matching the business event transaction record set through the semantic parsing sub-network covered by the preset GCN network according to the at least one target description array described in step 22254 may include the following: determining a multi-modal description array through a sequence tendency model covered by the preset GCN network according to the at least one target description array; wherein the multimodal descriptor array is determined via the at least one target descriptor array and at least one priority index, each target descriptor array corresponding to a priority index; and determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN according to the multi-modal description array.
The priority index can be understood as a timing index or a timing weight, for example. In this way, the timeliness of the semantic description values can be ensured.
In some further embodiments, the determining a multi-modal array of descriptions through the order trend model covered by the predetermined GCN network according to the at least one array of objective descriptions may include: determining at least one first local description array through a first local model covered by the sequential tendency model according to the at least one target description array; wherein the sequential trending model matches the pre-set GCN network; determining at least one second local description array through a second local model covered by the sequence tendency model according to the at least one first local description array; determining at least one priority index via the at least one second local description array; wherein each priority index corresponds to a target description array; determining the multimodal description array via the at least one target description array and at least one priority index. For example, the multi-modal descriptor array can be understood as a fusion feature, and the design can avoid the missing of the multi-modal descriptor array.
In other possible embodiments, the number of the first description arrays is multiple, and based on this, the determining, according to the significant content set of the business event and the significant content set of the abnormal event, semantic description values matching the business event transaction records through the semantic parsing subnet covered by the preset GCN network described in step 2225 may include the following: determining at least one first description array through a first global down-sampling unit covered by the preset GCN network according to the service event significant content set; wherein each first description array corresponds to a service event salient content; determining at least one second description array through a second global down-sampling unit covered by the preset GCN according to the abnormal event significant content set; wherein each second description array corresponds to a significant content of an exceptional event; performing a connecting operation on the at least one first description array and the at least one second description array to obtain at least one target description array; each target description array covers a first description array and a second description array; determining a multi-modal description array through a sequence tendency model covered by the preset GCN network according to the at least one target description array; wherein the multimodal descriptor array is determined via the at least one target descriptor array and at least one priority index, each target descriptor array corresponding to a priority index; and determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN according to the multi-modal description array.
Step 2226, determining a subject feature value of the business event transaction record set through the semantic description value; and determining a related service data set from the preset service database according to the theme characteristic value.
In actual application, a set characteristic value interval in which the subject characteristic value falls can be determined, and then a service data set corresponding to a target characteristic value in the set characteristic value interval is determined as an associated service data set, so that the integrity of the obtained associated service data set is guaranteed.
It can be understood that, based on steps 2221-2226, a business event handling record set of a business topic can be subjected to targeted analysis in combination with an artificial intelligence model, so that a topic characteristic value of the business event handling record set is determined according to a thought of characteristic analysis, and thus, a related business data set can be completely positioned according to a preset characteristic value interval, and omission of the determined related business data set is avoided.
And step 23, carrying out service data calling processing according to the associated service data set corresponding to each group of service data to be called.
In some possible embodiments, when the service data is called according to the associated service data set, the current use state and the modified use state of the associated service data set may be considered, so as to ensure the accuracy and the reliability of the acquired service data set to be called when the service processing application is processed, and simultaneously ensure the normal use of the associated service data set corresponding to the service data set to be called when the service processing application is completed.
For example, for a group of the service data to be called data1, the associated service data set is in _ data1, if the current usage status of the associated service data set in _ data1 is "unused" and the modification remark of the associated service data set in _ data1 is "modifiable", the modification can be directly performed if needed during the process of calling the service data to be called data 1. For another example, if the associated service data set of the service data to be called data2 is in _ data2 and the modification remark of the associated service data set in _ data2 is "non-modifiable", the modification cannot be made at will if it is needed during the process of calling the service data to be called data 2.
In summary, when the method is applied to steps 21 to 23, the corresponding service data sets to be called can be determined when a service processing application is received, and then data association analysis is performed on each group of service data to be called to obtain the corresponding associated service data sets, so that targeted data calling processing can be performed in combination with different associated service data sets, the problem that part of the associated service data sets are changed when the service data sets to be called are directly called is avoided, and further the problem that subsequent services cannot be normally handled due to the fact that part of the associated service data sets are changed is avoided. It can be understood that, the service data calling processing is performed according to the associated service data set, and the current use state and the modified use state of the associated service data set can be considered, so that the precision and the reliability of the acquired service data set to be called when the service processing application is processed are ensured, and the normal use of the associated service data set corresponding to the service data set to be called when the service processing application is completed can also be ensured.
Based on the same or similar inventive concepts, an architecture schematic diagram of an application environment 30 of a service processing method is also provided, which includes a service processing cloud platform 10 and a digital service terminal 20 that communicate with each other, and the service processing cloud platform 10 and the digital service terminal 20 implement or partially implement the technical solutions described in the above method embodiments when running. Further, the digital service terminal is used for initiating a service processing application to the service processing cloud platform. The digital service terminal is used for responding to a service processing application initiated by the digital service terminal and determining a service data set to be called corresponding to the service processing application; determining an associated service data set corresponding to each group of service data to be called aiming at each group of service data to be called in the service data set to be called; and calling the service data according to the associated service data set corresponding to each group of the service data to be called.
Further, a readable storage medium is provided, on which a program is stored, which when executed by a processor implements the method described above.
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 or a part thereof, which essentially contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a media service server 10, or a network device) to execute 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 (10)
1. A service processing method is applied to a service processing cloud platform, wherein the service processing cloud platform is in communication connection with a digital service terminal, and the method comprises the following steps:
responding to a service processing application initiated by the digital service terminal, and determining a service data set to be called corresponding to the service processing application;
determining an associated service data set corresponding to each group of service data to be called aiming at each group of service data to be called in the service data set to be called;
and calling the service data according to the associated service data set corresponding to each group of the service data to be called.
2. The method according to claim 1, wherein the determining an associated service data set corresponding to each group of service data to be called includes:
identifying a service theme of each group of calling service data;
and determining an associated service data set matched with the service theme from a preset service database.
3. The method of claim 2, wherein the determining the associated business data set matching the business topic from a preset business database comprises:
determining a business event handling record set which has upstream and downstream relation with the business theme; the business event handling record set comprises at least one group of business event handling records with a precedence relationship;
determining an exception event transaction record set via the transaction event transaction record set; the abnormal event handling record set comprises at least one group of abnormal event handling records with a precedence relationship;
according to the business event handling record set, determining a business event significant content set through a first significant content mining subnet covered by a preset GCN network; wherein the set of business event salient content comprises at least one business event salient content;
according to the abnormal event handling record set, determining an abnormal event significant content set through a second significant content mining subnet covered by the preset GCN network; wherein the set of exceptional significant content comprises at least one exceptional significant content;
determining semantic description values matched with the business event handling records through semantic parsing subnets covered by the preset GCN according to the business event significant content set and the abnormal event significant content set;
determining a subject feature value of the set of business event transaction records via the semantic description value; and determining a related service data set from the preset service database according to the theme characteristic value.
4. The method of claim 3, wherein the determining semantic description values matching the set of business event transaction records according to the set of business event salient contents and the set of exceptional event salient contents through a semantic parsing subnet covered by the predetermined GCN network comprises:
determining at least one first description array through a first scene tendency model covered by the preset GCN according to the service event significant content set; wherein each first description array corresponds to a service event salient content;
determining at least one second description array through a second scene trend model covered by the preset GCN according to the abnormal event significant content set; wherein each second description array corresponds to a significant content of an exceptional event;
performing a connecting operation on the at least one first description array and the at least one second description array to obtain at least one target description array; each target description array covers a first description array and a second description array;
and determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN according to the at least one target description array.
5. The method of claim 4, wherein the determining at least one first description array according to the significant content set of the business event through a first scene trending model covered by the predetermined GCN network comprises:
for each set of traffic event salient content in the set of traffic event salient content, determining a first local downsampling salient content by a local downsampling unit covered by the first scene trending model; wherein the first scene trending model matches the pre-set GCN network;
for each group of the business event salient content in the business event salient content set, determining a first global down-sampling salient content through a global down-sampling unit covered by the first scene trending model;
for each group of the business event salient contents in the business event salient content set, determining a first multi-modal salient content through a feature optimization unit covered by the first scene tendency model according to the first local downsampled salient content and the first global downsampled salient content;
for each group of the business event salient contents in the business event salient content set, determining a first description array through a first global down-sampling unit covered by the first scene tendency model according to the first multi-modal salient contents and the business event salient contents.
6. The method according to claim 4, wherein said determining at least one second description array by a second scene trending model covered by said predetermined GCN network according to said abnormal event significant content set comprises:
for each set of exceptional salient content in the set of exceptional salient content, determining a second locally downsampled salient content by a locally downsampling unit covered by the second scene trending model; wherein the second scene trending model matches the pre-set GCN network;
for each set of exceptional salient content in the set of exceptional salient content, determining a second globally downsampled salient content by a global downsampling unit covered by the second scene trending model;
for each group of the abnormal event salient contents in the abnormal event salient content set, determining a second multi-modal salient content through a feature optimization unit covered by the second scene tendency model according to the second local downsampling salient content and the second global downsampling salient content;
for each group of the abnormal event salient content in the abnormal event salient content set, determining a second description array through a second global down-sampling unit covered by the second scene trend model according to the second multi-modal salient content and the abnormal event salient content.
7. The method of claim 4, wherein the target description array is plural; the determining, according to the at least one target description array, the semantic description value matched with the service event handling record set through the semantic parsing subnet covered by the preset GCN network includes:
determining a multi-modal description array through a sequence tendency model covered by the preset GCN network according to the at least one target description array; wherein the multimodal descriptor array is determined via the at least one target descriptor array and at least one priority index, each target descriptor array corresponding to a priority index;
according to the multi-modal description array, determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN network;
wherein the determining a multi-modal description array through the sequence trend model covered by the predetermined GCN network according to the at least one objective description array comprises: determining at least one first local description array through a first local model covered by the sequential tendency model according to the at least one target description array; wherein the sequential trending model matches the pre-set GCN network; determining at least one second local description array through a second local model covered by the sequence tendency model according to the at least one first local description array; determining at least one priority index via the at least one second local description array; wherein each priority index corresponds to a target description array; determining the multimodal description array via the at least one target description array and at least one priority index.
8. The method of claim 3, wherein the first descriptor array is plural; the determining, according to the significant content set of the business event and the significant content set of the abnormal event, the semantic description value matched with the business event transaction record through the semantic parsing subnet covered by the preset GCN network includes:
determining at least one first description array through a first global down-sampling unit covered by the preset GCN network according to the service event significant content set; wherein each first description array corresponds to a service event salient content;
determining at least one second description array through a second global down-sampling unit covered by the preset GCN according to the abnormal event significant content set; wherein each second description array corresponds to a significant content of an exceptional event;
performing a connecting operation on the at least one first description array and the at least one second description array to obtain at least one target description array; each target description array covers a first description array and a second description array;
determining a multi-modal description array through a sequence tendency model covered by the preset GCN network according to the at least one target description array; wherein the multimodal descriptor array is determined via the at least one target descriptor array and at least one priority index, each target descriptor array corresponding to a priority index;
according to the multi-modal description array, determining semantic description values matched with the business event handling record set through the semantic parsing sub-network covered by the preset GCN network;
wherein determining an exception event transaction record set via the transaction event transaction record set comprises: for each group of business event handling records in the business event handling record set, determining first abnormal event distribution, second abnormal event distribution and third abnormal event distribution through a handling record optimization network; and generating abnormal event handling records matched with each group of business event handling records through the first abnormal event distribution, the second abnormal event distribution and the third abnormal event distribution matched with each group of business event handling records.
9. A business processing system is characterized by comprising a business processing cloud platform and a digital business terminal which are in communication connection in advance;
the digital service terminal is used for initiating a service processing application to the service processing cloud platform;
the digital service terminal is used for responding to a service processing application initiated by the digital service terminal and determining a service data set to be called corresponding to the service processing application; determining an associated service data set corresponding to each group of service data to be called aiming at each group of service data to be called in the service data set to be called; and calling the service data according to the associated service data set corresponding to each group of the service data to be called.
10. A business processing cloud platform is characterized by comprising a processor and a memory; the processor is connected in communication with the memory, and the processor is configured to read the computer program from the memory and execute the computer program to implement the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210218507.9A CN114281553B (en) | 2022-03-08 | 2022-03-08 | Business processing method and system and cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210218507.9A CN114281553B (en) | 2022-03-08 | 2022-03-08 | Business processing method and system and cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114281553A true CN114281553A (en) | 2022-04-05 |
| CN114281553B CN114281553B (en) | 2022-05-13 |
Family
ID=80882293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210218507.9A Active CN114281553B (en) | 2022-03-08 | 2022-03-08 | Business processing method and system and cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114281553B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110302124A1 (en) * | 2010-06-08 | 2011-12-08 | Microsoft Corporation | Mining Topic-Related Aspects From User Generated Content |
| US20140143316A1 (en) * | 2012-11-16 | 2014-05-22 | Huawei Technologies Co., Ltd. | Method, apparatus, and system for acquiring object |
| CN110428522A (en) * | 2019-07-24 | 2019-11-08 | 青岛联合创智科技有限公司 | A kind of intelligent safety and defence system of wisdom new city |
| CN111651285A (en) * | 2020-05-27 | 2020-09-11 | 平安养老保险股份有限公司 | Batch business data processing method and device, computer equipment and storage medium |
| CN112818023A (en) * | 2021-01-26 | 2021-05-18 | 龚世燕 | Big data analysis method and cloud computing server in associated cloud service scene |
| CN112884435A (en) * | 2021-02-10 | 2021-06-01 | 南京苏宁软件技术有限公司 | Service data processing method, device, system, computer equipment and storage medium |
| CN113011907A (en) * | 2020-12-18 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Data processing method, device, storage medium and equipment |
| CN113112348A (en) * | 2021-05-08 | 2021-07-13 | 中国建设银行股份有限公司 | Processing method and device of social security data, electronic equipment and storage medium |
| CN113722289A (en) * | 2021-08-09 | 2021-11-30 | 杭萧钢构股份有限公司 | Method, device, electronic equipment and medium for constructing data service |
| CN113946363A (en) * | 2021-10-20 | 2022-01-18 | 平安消费金融有限公司 | Method and device for executing and configuring service data, computer equipment and storage medium |
-
2022
- 2022-03-08 CN CN202210218507.9A patent/CN114281553B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110302124A1 (en) * | 2010-06-08 | 2011-12-08 | Microsoft Corporation | Mining Topic-Related Aspects From User Generated Content |
| US20140143316A1 (en) * | 2012-11-16 | 2014-05-22 | Huawei Technologies Co., Ltd. | Method, apparatus, and system for acquiring object |
| CN110428522A (en) * | 2019-07-24 | 2019-11-08 | 青岛联合创智科技有限公司 | A kind of intelligent safety and defence system of wisdom new city |
| CN111651285A (en) * | 2020-05-27 | 2020-09-11 | 平安养老保险股份有限公司 | Batch business data processing method and device, computer equipment and storage medium |
| CN113011907A (en) * | 2020-12-18 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Data processing method, device, storage medium and equipment |
| CN112818023A (en) * | 2021-01-26 | 2021-05-18 | 龚世燕 | Big data analysis method and cloud computing server in associated cloud service scene |
| CN112884435A (en) * | 2021-02-10 | 2021-06-01 | 南京苏宁软件技术有限公司 | Service data processing method, device, system, computer equipment and storage medium |
| CN113112348A (en) * | 2021-05-08 | 2021-07-13 | 中国建设银行股份有限公司 | Processing method and device of social security data, electronic equipment and storage medium |
| CN113722289A (en) * | 2021-08-09 | 2021-11-30 | 杭萧钢构股份有限公司 | Method, device, electronic equipment and medium for constructing data service |
| CN113946363A (en) * | 2021-10-20 | 2022-01-18 | 平安消费金融有限公司 | Method and device for executing and configuring service data, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114281553B (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230179548A1 (en) | Natural language processing for information extraction | |
| CN109739873A (en) | A kind of business datum querying method, device, equipment and readable storage medium storing program for executing | |
| CN110782318A (en) | Marketing method and device based on audio interaction and storage medium | |
| CN109766422A (en) | Information processing method, apparatus and system, storage medium, terminal | |
| CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
| CN111126071B (en) | Method and device for determining questioning text data and method for processing customer service group data | |
| CN115455151A (en) | AI emotion visual identification method and system and cloud platform | |
| CN114281553B (en) | Business processing method and system and cloud platform | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| CN112801721A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN112331201A (en) | Voice interaction method and device, storage medium and electronic device | |
| CN114372383B (en) | Scene fast switching method and system based on VR simulation scene | |
| CN116303931A (en) | Task completion method and device for intelligent customer service | |
| CN116071590A (en) | Model training method, system, computer device and storage medium | |
| US20220262353A1 (en) | Method and device for Processing Voice Information, Storage Medium and Electronic Apparatus | |
| CN110929519A (en) | Entity attribute extraction method and device | |
| CN111324778B (en) | Data and service processing method and device and electronic equipment | |
| CN114443853A (en) | Topic view portrait map processing method and system based on big data | |
| CN114222028A (en) | Speech recognition method, speech recognition device, computer equipment and storage medium | |
| CN110751204A (en) | Data fusion method and device, storage medium and electronic device | |
| CN115174633B (en) | Industrial Internet service data processing method and system and cloud platform | |
| CN113676603B (en) | Call control method, device, equipment and storage medium | |
| US20240193190A1 (en) | Automated key-value extraction using natural language intents | |
| CN114325778B (en) | Beidou signal processing method and system | |
| CN109840274B (en) | Data processing method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |