CN115766725B

CN115766725B - Data processing method and system based on industrial Internet

Info

Publication number: CN115766725B
Application number: CN202211553201.5A
Authority: CN
Inventors: 付勇; 陈志权
Original assignee: Beijing Guolian Video Information Technology Co ltd
Current assignee: Beijing Guolian Video Information Technology Co ltd
Priority date: 2022-12-06
Filing date: 2022-12-06
Publication date: 2023-11-07
Anticipated expiration: 2042-12-06
Also published as: CN115766725A

Abstract

According to the data processing method and system based on the industrial Internet, the linkage interaction information binary set can be determined through the interaction environment knowledge vectors respectively corresponding to the cloud service interaction records; because the interaction environment knowledge vectors corresponding to the two groups of cloud service interaction information in the linkage interaction information binary group respectively can reflect that the environment element difference degree corresponding to the two groups of cloud service interaction information binary groups meets the set difference requirement, when the feature knowledge network combination is carried out on the target digital service process based on the linkage interaction information binary group, the environment element difference degree between the different cloud service interaction information can be realized, the combination of the feature knowledge network is guided, the interference of the redundant digital service process due to different distribution links on the combination quality of the feature knowledge network can be reduced in the target digital service process with partial redundant digital service process, the error in the feature knowledge network combination is avoided, and the precision and the reliability of the feature knowledge network combination are improved.

Description

Data processing method and system based on industrial Internet

Technical Field

The invention relates to the technical field of data processing, in particular to a data processing method and system based on industrial Internet.

Background

The industrial Internet has more abundant connotation and extension. The system takes a network as a basis, a platform as a center, data as an element and safety as a guarantee, is not only an infrastructure for industrial digitization, networking and intelligent transformation, but also an application mode for the deep integration of Internet, big data, artificial intelligence and entity economy, and is also a new business state and new industry, and the morphology, supply chain and industry chain of an enterprise are remodeled. With the continuous development of the industrial internet, feature mining analysis for various digital services has become an important point of attention.

Disclosure of Invention

In order to improve the technical problems in the related art, the invention provides a data processing method and system based on the industrial Internet.

In a first aspect, an embodiment of the present invention provides a data processing method based on industrial internet, applied to a data processing system, where the method includes: acquiring a plurality of cloud service interaction records collected about a target digital service process and interaction environment knowledge vectors respectively corresponding to the cloud service interaction records; the interaction environment knowledge vector is obtained by determining environment elements of a target service environment detection module deployed in the target digital service process when the cloud service interaction records are collected; each cloud service interaction record comprises a plurality of groups of cloud service interaction information; combining the interaction environment knowledge vector, and determining a plurality of linkage interaction information tuples from the cloud service interaction records; and combining the linkage interaction information binary groups to perform characteristic knowledge network combination on the target digital service process to obtain a characteristic knowledge network of the target digital service process.

It can be seen that a plurality of linkage interaction information tuples can be determined through interaction environment knowledge vectors respectively corresponding to a plurality of cloud service interaction records; because the interaction environment knowledge vectors corresponding to the two groups of cloud service interaction information in the linkage interaction information binary group respectively can reflect that the environment element difference degree corresponding to the two groups of cloud service interaction information binary groups meets the set difference requirement, when the feature knowledge network combination is carried out on the target digital service process based on the linkage interaction information binary group, the environment element difference degree between the different cloud service interaction information can be realized, and the combination of the feature knowledge network is guided, so that in the target digital service process with partial redundant digital service process, the interference of the redundant digital service process with the feature knowledge network combination quality due to different distribution links can be reduced, the error during the feature knowledge network combination can be avoided as much as possible, and the precision and the reliability of the feature knowledge network combination can be improved.

In some possible embodiments, the determining, in combination with the interaction environment knowledge vector, a plurality of linkage interaction information tuples from the plurality of cloud service interaction records includes: excavating interaction behavior description fields of each group of cloud service interaction information in a plurality of cloud service interaction records; determining a plurality of cloud service interaction information tuples to be processed through the commonality coefficients among interaction behavior description fields of different cloud service interaction information; each cloud service interaction information binary group to be processed comprises first cloud service interaction information and second cloud service interaction information; based on interaction environment knowledge vectors respectively corresponding to first cloud service interaction information and second cloud service interaction information in a plurality of cloud service interaction information tuples to be processed, extracting linkage interaction information tuples from the cloud service interaction information tuples to be processed.

Therefore, the timeliness of extracting linkage interaction information tuples from the cloud service interaction information tuples to be processed based on the interaction environment knowledge vector can be improved by carrying out first screening on the cloud service interaction information tuples to be processed based on the interaction behavior description field of the cloud service interaction information, and then extracting linkage interaction information tuples from the cloud service interaction information tuples to be processed by respectively corresponding interaction environment knowledge vectors of the first cloud service interaction information and the second cloud service interaction information in each cloud service interaction information tuple to be processed, so that the cloud service interaction information tuples to be processed, of which the interaction behavior description field is similar but not the same digital service process, are filtered as accurately as possible.

In some possible embodiments, the extracting the linkage interaction information binary group from the cloud service interaction information binary group to be processed based on interaction environment knowledge vectors respectively corresponding to the first cloud service interaction information and the second cloud service interaction information in the cloud service interaction information binary group to be processed includes: for each cloud service interaction information binary group to be processed in a plurality of cloud service interaction information binary groups to be processed, determining the difference degree of environmental elements between the first cloud service interaction information and the second cloud service interaction information by combining an interaction environment knowledge vector of a first cloud service interaction information binary group in each cloud service interaction information binary group to be processed and an interaction environment knowledge vector of a second cloud service interaction information binary group in each cloud service interaction information binary group to be processed; and if the difference degree of the environmental elements between the first cloud service interaction information and the second cloud service interaction information is lower than a set difference limit value, taking the cloud service interaction information binary group to be processed as the linkage interaction information binary group.

Therefore, by introducing continuous period of environmental element detection into the cloud service interaction information of the feature knowledge network combination, in the process of feature knowledge network combination through linkage interaction information binary groups, whether the cloud service interaction information is the same digital service process or similar digital service process is judged by comparing the environmental element difference degree between the cloud service interaction information binary group interaction environmental knowledge vectors, and the interference of the similar digital service process on the feature knowledge network combination is reduced.

In some possible embodiments, the interaction environment knowledge vector comprises: detection module tag data respectively corresponding to each group of cloud service interaction information in the target cloud service interaction record; combining the interaction environment knowledge vector of the first cloud service interaction information binary group in each cloud service interaction information binary group to be processed and the interaction environment knowledge vector of the second cloud service interaction information binary group in each cloud service interaction information binary group to be processed, determining the environment factor difference degree between the first cloud service interaction information and the second cloud service interaction information comprises the following steps: determining the number of associated service environment detection modules corresponding to the first cloud service interaction information and the second cloud service interaction information by combining the detection module label data corresponding to the first cloud service interaction information doublet and the detection module label data corresponding to the second cloud service interaction information doublet; determining the environmental element difference degree corresponding to the first cloud service interaction information and the second cloud service interaction information by combining the number; wherein the environmental element difference degree and the number of the associated service environment detection modules have a set quantization relationship.

Therefore, the environment element difference degree between the two cloud service interaction information is reflected through the associated service environment detection module information of the interaction environment knowledge vectors of the two cloud service interaction information tuples, and the environment element difference degree of the two interaction environment knowledge vectors is judged, so that efficient extraction is performed on linkage interaction information tuple extraction, and timeliness of feature knowledge network combination is improved.

In some possible embodiments, the interaction environment knowledge vector comprises: environmental element thermal data and detection module label data respectively corresponding to each group of cloud service interaction information in the target cloud service interaction record; combining the interaction environment knowledge vector of the first cloud service interaction information binary group in each cloud service interaction information binary group to be processed and the interaction environment knowledge vector of the second cloud service interaction information binary group in each cloud service interaction information binary group to be processed, determining the environment factor difference degree between the first cloud service interaction information and the second cloud service interaction information comprises the following steps: combining the detection module label corresponding to the first cloud service interaction information binary group and the detection module label corresponding to the second cloud service interaction information binary group to determine an associated service environment detection module and a non-associated service environment detection module corresponding to the first cloud service interaction information binary group and the second cloud service interaction information binary group; determining a thermal comparison result of the associated service environment detection module by combining the environmental element thermal data respectively corresponding to the first cloud service interaction information and the second cloud service interaction information; and determining the difference degree of the environmental elements between the first cloud service interaction information and the second cloud service interaction information by combining the thermal comparison result and the difference degree of the preset environmental elements corresponding to the non-associated service environment detection module.

Therefore, the environment element difference degree between two groups of cloud service interaction information can be accurately and reliably determined, the knowledge vector accuracy in the characteristic knowledge network combination process is improved, and the negative influence of similar digital service processes on the characteristic knowledge network combination is reduced.

In some possible embodiments, the combining the linkage interaction information binary group to perform feature knowledge network combination on the target digital service process to obtain a feature knowledge network of the target digital service process includes: combining characteristic knowledge network combination is carried out on each cloud service interaction record in a plurality of cloud service interaction records by combining a plurality of groups of cloud service interaction information in each cloud service interaction record, so as to obtain a local characteristic knowledge network corresponding to each cloud service interaction record; and combining the linkage interaction information binary groups, and carrying out fusion operation on the local feature knowledge networks corresponding to the cloud service interaction records respectively to obtain the feature knowledge network of the target digital service process.

Therefore, the interaction relation among the cloud service interaction records can be judged through the linkage interaction information binary groups so as to fuse the characteristic knowledge networks, and the accuracy of characteristic knowledge network combination is improved based on the characteristic knowledge network fusion of the linkage interaction information binary groups.

In some possible embodiments, the combining the linkage interaction information binary group performs a fusion operation on local feature knowledge networks corresponding to the cloud service interaction records respectively to obtain a feature knowledge network of the target digital service process, where the fusion operation includes: for every two cloud service interaction records, determining whether a target linkage interaction information binary group exists between the two cloud service interaction records; the first linkage cloud service interaction information and the second linkage cloud service interaction information in the target linkage interaction information binary group respectively correspond to the two cloud service interaction records; if the target linkage interaction information binary group exists between the two cloud service interaction records, determining a feature mapping indication between local feature knowledge networks corresponding to the two cloud service interaction records respectively based on the target linkage interaction information binary group between the two cloud service interaction records, and combining the feature mapping indication to perform fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively; and obtaining the characteristic knowledge network of the target digital service process based on the fusion results respectively corresponding to the cloud service interaction records.

Therefore, based on the two cloud service interaction information belonging to different cloud service interaction records in the same linkage interaction information binary group, the feature mapping indication of the two local feature knowledge networks can be determined, so that the fusion quality of the local feature knowledge networks is as good as possible.

In some possible embodiments, the determining, based on the target linkage interaction information binary set between the two cloud service interaction records, a feature mapping indication between the local feature knowledge networks respectively corresponding to the two cloud service interaction records, and combining the feature mapping indication, and performing a fusion operation on the local feature knowledge networks respectively corresponding to the two cloud service interaction records includes: the following cycle phases are implemented: determining a first target linkage interaction information binary group corresponding to the current circulation stage from the target linkage interaction information binary groups; combining the first target linkage interaction information binary group to determine the current feature mapping indication between the local feature knowledge networks respectively corresponding to the two cloud service interaction records; combining the current feature mapping indication, and carrying out fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively to obtain a fused knowledge network corresponding to the current circulation stage; combining distributed variables reflected by the residual target linkage interaction information tuples except the first target linkage interaction information tuple in the target linkage interaction information tuples, and carrying out knowledge network fusion checking on the fused knowledge network; if the knowledge network fusion and correction pass, taking the fused knowledge network corresponding to the current circulation stage as a final result of fusion operation on the local feature knowledge networks respectively corresponding to the two cloud service interaction records, and terminating circulation processing; if the knowledge network fusion check does not pass, entering the next circulation stage; if all the target linkage interaction information tuples are sequentially used as the first target linkage interaction information tuple and are not subjected to knowledge network fusion checking, the fact that the knowledge network fusion requirements are not met between the local feature knowledge networks respectively corresponding to the two cloud service interaction records is indicated.

Therefore, the fusion correction is carried out on all linkage interaction information binary groups in the two cloud service interaction records by using the thought of cyclic processing, so that the fusion error of the characteristic knowledge network can be avoided as much as possible, and the quality of the characteristic knowledge network combination is improved.

In some possible embodiments, the combining the linkage interaction information binary group to perform feature knowledge network combination on the target digital service process to obtain a feature knowledge network of the target digital service process includes: sequentially accessing each linkage interaction information binary group in the linkage interaction information binary groups, and combining the characteristic knowledge networks based on the sequentially accessed linkage interaction information binary groups to obtain a characteristic knowledge network corresponding to the sequentially accessed linkage interaction information binary groups; and carrying out network integration on the characteristic knowledge networks respectively corresponding to the plurality of linkage interaction information tuples to obtain the characteristic knowledge network of the target digital service process.

Therefore, through the interactive connection among the linkage cloud service interaction information, the local feature knowledge networks corresponding to the cloud service interaction records are fused to obtain the feature knowledge network corresponding to the target digital service process, so that the interference of the redundant digital service process on the feature knowledge network combination of the target digital service process can be reduced.

In some possible embodiments, the combining the feature knowledge network based on the sequentially accessed linkage interaction information tuples to obtain a feature knowledge network corresponding to the sequentially accessed linkage interaction information tuples includes: based on the states of the data acquisition modules respectively corresponding to the first cloud service interaction information and the second cloud service interaction information in the linkage interaction information binary groups accessed in sequence, and the first cloud service interaction information and the second cloud service interaction information are combined through a feature knowledge network to obtain a first feature knowledge network; determining mapping deviation of the first feature knowledge network by combining the first cloud service interaction information, the second cloud service interaction information, the state of a data acquisition module corresponding to the first cloud service interaction information and the second cloud service interaction information respectively, and the first feature knowledge network; and determining the difference loss of the environmental elements between the first cloud service interaction information and the second cloud service interaction information by combining the interaction environment knowledge vector corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and the detection module distribution of the target service environment detection module corresponding to the interaction environment knowledge vector; optimizing the states of the data acquisition modules corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and the distribution of the detection modules of the target service environment detection module by combining the mapping deviation and the environmental element difference loss to obtain target interaction states corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and target distribution variables of the target service environment detection module; and combining the first cloud service interaction information, the second cloud service interaction information and the target interaction state to perform characteristic knowledge network combination to obtain the characteristic knowledge network corresponding to the linkage interaction information binary group which is accessed in sequence.

Therefore, the distribution variable of the service environment detection module and the distribution variable of the data acquisition module can be improved in parallel through the feature mapping loss algorithm and the environment element difference loss algorithm, so that combination deviation can be avoided, and the combination of the feature knowledge network and the distribution variable state and the feature knowledge member information of the data acquisition module can be obtained.

In some possible embodiments, further comprising: and generating a detection module distribution track chain based on target distribution variables of the target service environment detection modules respectively corresponding to the plurality of linkage cloud service interaction information.

It can integrate the interaction environment knowledge vector and the visual characteristic knowledge net combination, and simultaneously generate the detection module distribution track chain and the characteristic knowledge net combination.

In a second aspect, the present invention also provides a data processing system comprising a processor and a memory; the processor is in communication with the memory, and the processor is configured to read and execute a computer program from the memory to implement the method described above.

In a third aspect, the present invention also provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the method described above.

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 flow chart of a data processing method based on industrial internet according to an embodiment of the present invention.

Fig. 2 is a schematic diagram of a communication architecture of an application environment of a data processing method based on an industrial internet according to an embodiment of the present invention.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.

The method embodiments provided by the embodiments of the present invention may be performed in a data processing system, a computer device, or a similar computing device. Taking the example of running on a data processing system, data processing system 10 may include one or more processors 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or programmable logic device FPGA) and memory 104 for storing data, and optionally, a transmission device 106 for communication functions. It will be appreciated by those of ordinary skill in the art that the above-described architecture is merely illustrative and is not intended to limit the architecture of the data processing system described above. For example, data processing system 10 also may include more or fewer components than those shown above, or have different configurations than those shown above.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to an industrial internet-based data processing method in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. 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 data processing system 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 means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communications provider of data processing system 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.

Based on this, referring to fig. 1, fig. 1 is a schematic flow chart of a data processing method based on industrial internet according to an embodiment of the present invention, where the method is applied to a data processing system, and further may include the technical schemes described in S1-S3.

S1, acquiring a plurality of cloud service interaction records collected by a target digital service process and interaction environment knowledge vectors respectively corresponding to the cloud service interaction records.

In the embodiment of the invention, the interaction environment knowledge vector is obtained by determining environment elements of a target service environment detection module deployed in the target digital service process when the cloud service interaction records are collected, and each cloud service interaction record comprises a plurality of groups of cloud service interaction information.

For example, a target digital service process may be understood as a digital service scenario or digital service environment, including but not limited to a virtual mall service, a digital community service, an online government enterprise service, etc., scenario/environment. And the cloud service interaction records can record the service interaction condition or interaction condition between the user and the service platform system. Further, the target service environment detection module deployed in the target digital service process is used for performing omnibearing coverage on the target digital service process, so that the full-flow detection on the target digital service process is realized. For example, the target service environment detection module can cover different service links or service nodes of the virtual mall service, so that scene detection processing of the whole virtual mall service is realized, and macroscopic monitoring of the virtual mall service is ensured. The environment elements of the target service environment detection module comprise network environment characteristics, interaction environment characteristics, service environment characteristics and the like, and the network environment characteristics, the interaction environment characteristics and the service environment characteristics can reflect the process running condition of the target digital service process from different layers. In addition, cloud service interaction information can be recorded in a text or image-text mode.

S2, combining the interaction environment knowledge vector, and determining a plurality of linkage interaction information tuples from the cloud service interaction records.

For example, the linkage interaction information binary group can be understood that there is an associated cloud service interaction information pair, for example, the linkage interaction information binary group 1 includes cloud service interaction information m11 and cloud service interaction information m12 which are associated, and the linkage interaction information binary group 2 includes cloud service interaction information m21 and cloud service interaction information m22 which are associated.

And S3, combining the linkage interaction information binary groups, and combining the characteristic knowledge network of the target digital service process to obtain the characteristic knowledge network of the target digital service process.

For example, the feature knowledge network combination can be understood as performing feature map or feature relation chain construction based on the interaction behavior features corresponding to the linkage interaction information binary group, so as to obtain a feature knowledge base reflecting the overall interaction features or the global interaction features of the target digital service process. Furthermore, the characteristic knowledge network can be constructed by combining related knowledge graph technology, so that an analysis basis as rich and accurate as possible can be provided for subsequent requirement mining analysis.

The method is applied to S1-S3, and a plurality of linkage interaction information tuples can be determined through a plurality of cloud service interaction records respectively corresponding interaction environment knowledge vectors; because the interaction environment knowledge vectors corresponding to the two groups of cloud service interaction information in the linkage interaction information binary group respectively can reflect that the environment element difference degree corresponding to the two groups of cloud service interaction information binary groups meets the set difference requirement, when the feature knowledge network combination is carried out on the target digital service process based on the linkage interaction information binary group, the environment element difference degree between the different cloud service interaction information can be realized, and the combination of the feature knowledge network is guided, so that in the target digital service process with partial redundant digital service process, the interference of the redundant digital service process with the feature knowledge network combination quality due to different distribution links can be reduced, the error during the feature knowledge network combination can be avoided as much as possible, and the precision and the reliability of the feature knowledge network combination can be improved.

In some possible embodiments, the determining, by using the interaction environment knowledge vector described in S2, a plurality of linkage interaction information tuples from the plurality of cloud service interaction records may include the technical solutions described in S21-S23.

S21, excavating interaction behavior description fields of each group of cloud service interaction information in a plurality of cloud service interaction records.

For example, the interaction behavior description field may be understood as an interaction behavior feature or an interaction behavior vector of the user corresponding to the cloud service interaction information.

S22, determining a plurality of cloud service interaction information tuples to be processed through the commonality coefficients among interaction behavior description fields of different cloud service interaction information; each cloud service interaction information binary group to be processed comprises first cloud service interaction information and second cloud service interaction information.

For example, the commonality coefficient may be understood as the similarity between the interactive behavior description fields, and may be generally obtained based on the calculation idea of cosine similarity.

S23, extracting linkage interaction information tuples from the cloud service interaction information tuples to be processed based on interaction environment knowledge vectors respectively corresponding to first cloud service interaction information and second cloud service interaction information in the cloud service interaction information tuples to be processed.

After determining a plurality of cloud service interaction information tuples to be processed, screening processing of linkage interaction information tuples can be achieved based on interaction environment knowledge vectors. The method is applied to S21-S23, the first screening of the cloud service interaction information binary groups to be processed is carried out based on the interaction behavior description field of the cloud service interaction information, the timeliness of extracting linkage interaction information binary groups from the cloud service interaction information binary groups to be processed based on the interaction environment knowledge vector can be improved, then the linkage interaction information binary groups are extracted from the cloud service interaction information binary groups to be processed through the interaction environment knowledge vector respectively corresponding to the first cloud service interaction information and the second cloud service interaction information in each cloud service interaction information binary group to be processed, and the cloud service interaction information binary groups to be processed with similar interaction behavior description fields but not identical digital service processes are filtered as accurately as possible.

In some possible embodiments, the interaction environment knowledge vectors described in S23 and corresponding to the first cloud service interaction information and the second cloud service interaction information in the plurality of cloud service interaction information tuples to be processed respectively extract the linkage interaction information tuple from the cloud service interaction information tuples to be processed, which may include the technical solutions described in S231 and S232.

S231, for each of a plurality of cloud service interaction information tuples to be processed, determining the degree of difference of environmental elements between the first cloud service interaction information and the second cloud service interaction information by combining the interaction environment knowledge vector of the first cloud service interaction information tuple in each cloud service interaction information tuple to be processed and the interaction environment knowledge vector of the second cloud service interaction information tuple in each cloud service interaction information tuple to be processed.

For example, the environmental element difference reflects a time sequence difference or a service scene difference between the first cloud service interaction information and the second cloud service interaction information in an interaction stage or an interaction link, and the environmental element difference can be used as a quantitative decision basis for associating different cloud service interaction information.

S232, if the difference degree of the environmental elements between the first cloud service interaction information and the second cloud service interaction information is lower than a set difference limit value, taking the cloud service interaction information binary group to be processed as the linkage interaction information binary group.

It can be understood that, in the application to S231 and S232, by introducing continuous period of environmental element detection into the cloud service interaction information of the feature knowledge network combination, in the process of feature knowledge network combination through linkage interaction information tuples, by comparing the environmental element difference between the cloud service interaction information tuple interaction environmental knowledge vectors, it is determined whether the cloud service interaction information pair reflects the same digital service process or similar digital service processes, so that the interference of the similar digital service process on the feature knowledge network combination is reduced.

In some possible embodiments, the interaction environment knowledge vector comprises: and the detection module label data respectively corresponds to each group of cloud service interaction information in the target cloud service interaction record, and the detection module label data can be understood as the identification of the target service environment detection module. Based on this, the determining, in S231, the degree of difference of environmental elements between the first cloud service interaction information and the second cloud service interaction information according to the interaction environment knowledge vector of the first cloud service interaction information binary in each of the cloud service interaction information binary groups to be processed and the interaction environment knowledge vector of the second cloud service interaction information binary in each of the cloud service interaction information binary groups to be processed, may include the technical schemes described in S2311 and S2312.

S2311, determining the number of associated service environment detection modules corresponding to the first cloud service interaction information and the second cloud service interaction information by combining the detection module label data corresponding to the first cloud service interaction information binary group and the detection module label data corresponding to the second cloud service interaction information binary group.

S2312, combining the numbers, and determining the environmental element difference degree corresponding to the first cloud service interaction information and the second cloud service interaction information binary group; wherein the environmental element difference degree and the number of the associated service environment detection modules have a set quantization relationship.

The set quantization relationship may be understood as a negative correlation relationship, that is, the greater the number of the associated service environment detection modules, the greater the degree of difference between the environmental elements; the fewer the number of the associated service environment detection modules, the greater the degree of difference of the environment elements. In this way, the environment element difference degree between the two cloud service interaction information is reflected by the associated service environment detection module information of the interaction environment knowledge vectors of the two cloud service interaction information tuples, and the environment element difference degree of the two interaction environment knowledge vectors is judged, so that efficient extraction is performed on linkage interaction information tuple extraction, and timeliness of feature knowledge network combination is improved.

In some possible embodiments, the interaction environment knowledge vector comprises: environmental element thermal data and detection module label data respectively corresponding to each group of cloud service interaction information in the target cloud service interaction record. Further, the environmental element thermal data may be understood as the degree of attention, liveness or heat of a service link or service phase. Based on this, the determining, in S231, the degree of difference of environmental elements between the first cloud service interaction information and the second cloud service interaction information according to the interaction environment knowledge vector of the first cloud service interaction information binary in each of the cloud service interaction information binary groups to be processed and the interaction environment knowledge vector of the second cloud service interaction information binary in each of the cloud service interaction information binary groups to be processed, may include the technical scheme described in S231a-S231 c.

S231a, combining the detection module label corresponding to the first cloud service interaction information binary group and the detection module label corresponding to the second cloud service interaction information binary group, and determining the associated service environment detection module and the non-associated service environment detection module corresponding to the first cloud service interaction information binary group and the second cloud service interaction information binary group.

For example, the associated service environment detection module and the non-associated service environment detection module may be determined by the class of detection module tags.

S231b, determining a thermal comparison result of the associated service environment detection module by combining the environmental element thermal data respectively corresponding to the first cloud service interaction information and the second cloud service interaction information.

For example, the thermal difference value of the associated service environment detection module may be calculated based on the environmental element thermal data.

And S231c, combining the thermal comparison result and the preset environmental element difference degree corresponding to the non-associated service environment detection module, and determining the environmental element difference degree between the first cloud service interaction information and the second cloud service interaction information.

The method is applied to S231a-S231c, the degree of difference of the environmental elements between two groups of cloud service interaction information can be accurately and reliably determined, the accuracy of knowledge vectors in the characteristic knowledge network combination process is improved, and the negative influence of similar digital service processes on the characteristic knowledge network combination is reduced.

In some possible embodiments, the combining the linkage interaction information binary group described in S3 performs feature knowledge network combination on the target digital service process to obtain a feature knowledge network of the target digital service process, which may include the contents described in S31 and S32.

And S31, combining the characteristic knowledge network with the plurality of groups of cloud service interaction information in each cloud service interaction record to obtain a local characteristic knowledge network corresponding to each cloud service interaction record.

For example, the local feature knowledge network is used for reflecting the user behavior feature or activity preference feature of each cloud service interaction record from the local level or the stage level, and can be used as a sub-network for feature knowledge network integration and fusion.

S32, combining the linkage interaction information binary groups, and carrying out fusion operation on the local feature knowledge networks corresponding to the cloud service interaction records respectively to obtain the feature knowledge network of the target digital service process.

The method is applied to S31 and S32, the interaction relation among the cloud service interaction records can be judged through the linkage interaction information binary group so as to fuse the characteristic knowledge network, and the accuracy of characteristic knowledge network combination is improved based on the characteristic knowledge network fusion of the linkage interaction information binary group.

In some possible embodiments, the combining the linkage interaction information binary group described in S32 performs a fusion operation on local feature knowledge networks corresponding to the cloud service interaction records respectively to obtain a feature knowledge network of the target digitalized service process, which may include the technical schemes described in S321-S323.

S321, for every two cloud service interaction records, determining whether a target linkage interaction information binary group exists between the two cloud service interaction records; and the first linkage cloud service interaction information and the second linkage cloud service interaction information in the target linkage interaction information binary group respectively correspond to the two cloud service interaction records.

S322, if the target linkage interaction information binary group exists between the two cloud service interaction records, determining feature mapping indication between local feature knowledge networks corresponding to the two cloud service interaction records respectively based on the target linkage interaction information binary group between the two cloud service interaction records, and combining the feature mapping indication to perform fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively.

For example, the feature mapping indication may be understood as a conversion relationship of the feature knowledge network in the fusion process, including, but not limited to, a conversion correspondence relationship and a mapping relationship of attributes such as a connection of feature knowledge members, keywords, feature values, and the like.

S323, obtaining the characteristic knowledge network of the target digital service process based on the fusion results respectively corresponding to the cloud service interaction records.

The method is applied to S321-S323, and based on the two cloud service interaction information belonging to different cloud service interaction records in the same linkage interaction information binary group, the feature mapping indication of the two local feature knowledge networks can be determined, so that the fusion quality of the local feature knowledge networks is as good as possible.

In some possible embodiments, the determining, based on the target linkage interaction information binary set between the two cloud service interaction records described in S322, a feature mapping indication between the local feature knowledge networks corresponding to the two cloud service interaction records respectively, and combining the feature mapping indication to perform a fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively may include the following: the following cycle phases are implemented: determining a first target linkage interaction information binary group corresponding to the current circulation stage from the target linkage interaction information binary groups; combining the first target linkage interaction information binary group to determine the current feature mapping indication between the local feature knowledge networks respectively corresponding to the two cloud service interaction records; combining the current feature mapping indication, and carrying out fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively to obtain a fused knowledge network corresponding to the current circulation stage; combining distributed variables reflected by the residual target linkage interaction information tuples except the first target linkage interaction information tuple in the target linkage interaction information tuples, and carrying out knowledge network fusion checking on the fused knowledge network; if the knowledge network fusion and correction pass, taking the fused knowledge network corresponding to the current circulation stage as a final result of fusion operation on the local feature knowledge networks respectively corresponding to the two cloud service interaction records, and terminating circulation processing; if the knowledge network fusion check does not pass, entering the next circulation stage; if all the target linkage interaction information tuples are sequentially used as the first target linkage interaction information tuple and are not subjected to knowledge network fusion checking, the fact that the knowledge network fusion requirements are not met between the local feature knowledge networks respectively corresponding to the two cloud service interaction records is indicated. By means of the design, fusion correction is conducted on all linkage interaction information binary groups in two cloud service interaction records through the thought of cyclic processing, errors of feature knowledge network fusion can be avoided as much as possible, and quality of feature knowledge network combination is improved.

In some possible embodiments, the combining the linkage interaction information binary group described in S3 performs feature knowledge network combination on the target digital service process to obtain a feature knowledge network of the target digital service process, which may include the technical solutions described in S3a and S3 b.

S3a, sequentially accessing each linkage interaction information binary group in the linkage interaction information binary groups, and combining the characteristic knowledge networks based on the sequentially accessed linkage interaction information binary groups to obtain the characteristic knowledge network corresponding to the sequentially accessed linkage interaction information binary groups.

And S3b, carrying out network integration on the characteristic knowledge networks respectively corresponding to the plurality of linkage interaction information tuples to obtain the characteristic knowledge network of the target digital service process.

The sequential access can be understood as traversal processing, and by utilizing the interaction between the interaction information of the linkage cloud service and the interaction information of the linkage cloud service, the local feature knowledge networks corresponding to the interaction records of the plurality of cloud services are fused to obtain the feature knowledge network corresponding to the target digital service process, so that the interference of the redundant digital service process on the feature knowledge network combination of the target digital service process can be reduced.

In some possible embodiments, the combining of the feature knowledge network based on the sequentially accessed linkage interaction information tuples described in S3a to obtain a feature knowledge network corresponding to the sequentially accessed linkage interaction information tuples may include S3a1-S3a5.

S3a1, combining feature knowledge networks based on states of data acquisition modules respectively corresponding to the first cloud service interaction information and the second cloud service interaction information and the first cloud service interaction information and the second cloud service interaction information in the linkage interaction information binary groups accessed in sequence to obtain a first feature knowledge network.

For example, the state of the data acquisition module may reflect the operational state of the data acquisition module, including a series of states of acquisition rules, acquisition modes, acquisition periods, acquisition trigger conditions, and the like.

S3a2, combining the first cloud service interaction information, the second cloud service interaction information, the state of the data acquisition module respectively corresponding to the first cloud service interaction information and the second cloud service interaction information, and the first characteristic knowledge network, and determining the mapping deviation of the first characteristic knowledge network.

For example, a mapping bias may be understood as an error or loss of feature mapping.

S3a3, combining the interaction environment knowledge vector corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and the detection module distribution of the target service environment detection module corresponding to the interaction environment knowledge vector, and determining the environmental element difference loss between the first cloud service interaction information and the second cloud service interaction information.

For example, the environmental element difference loss may be understood as error information of the environmental element difference.

S3a4, combining the mapping deviation and the environmental element difference loss, optimizing the states of the data acquisition modules corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and the distribution of the detection modules of the target service environment detection module to obtain target interaction states corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and target distribution variables of the target service environment detection module.

For example, the target interaction state includes states of interaction timeliness, interaction heat, interaction mode and the like of the user, and the distribution of the detection modules can reflect the deployment position or the deployment link of the target service environment detection module in the whole service process. The target distribution variable of the target service environment detection module can be understood as the target distribution variable for completing optimization adjustment.

And S3a5, combining the first cloud service interaction information, the second cloud service interaction information and the target interaction state to perform characteristic knowledge network combination, so as to obtain the characteristic knowledge network corresponding to the linkage interaction information binary group which is accessed in sequence.

The method is applied to S3a1-S3a5, and the distribution variable of the service environment detection module and the distribution variable of the characteristic knowledge member and the distribution variable of the data acquisition module can be improved in parallel through a characteristic mapping loss algorithm and an environment element difference loss algorithm, so that combination deviation can be avoided, and the characteristic knowledge network combination comprises the distribution variable state and the characteristic knowledge member information of the data acquisition module.

In some possible embodiments, the method may further comprise: and generating a detection module distribution track chain based on target distribution variables of the target service environment detection modules respectively corresponding to the plurality of linkage cloud service interaction information.

The detection module distribution track chain can be information which records the deployment position of the detection module in a map form, so that the interaction environment knowledge vector and the visual characteristic knowledge network combination can be integrated, and meanwhile the detection module distribution track chain and the characteristic knowledge network combination are generated.

Based on the same or similar inventive concept as described above, referring to fig. 2 in combination, there is further provided a schematic architecture of an application environment 30 of an industrial internet-based data processing method, including a data processing system 10 and a service platform system 20 that communicate with each other, where the data processing system 10 and the service platform system 20 implement or partially implement the technical solutions described in the above method embodiments at runtime.

Further, there is also provided a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the above-described method.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus and method embodiments described above are merely illustrative, for example, flow diagrams 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, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single 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 this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a network device, or the like) 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, random Access Memory), a magnetic disk, or an optical disk, or 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. 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 the industrial internet, which is applied to a data processing system, the method comprising:

acquiring a plurality of cloud service interaction records collected about a target digital service process and interaction environment knowledge vectors respectively corresponding to the cloud service interaction records; the interaction environment knowledge vector is obtained by determining environment elements of a target service environment detection module deployed in the target digital service process when the cloud service interaction records are collected; each cloud service interaction record comprises a plurality of groups of cloud service interaction information;

combining the interaction environment knowledge vector, and determining a plurality of linkage interaction information tuples from the cloud service interaction records; combining the linkage interaction information binary group, and carrying out characteristic knowledge network combination on the target digital service process to obtain a characteristic knowledge network of the target digital service process;

Wherein, the determining a plurality of linkage interaction information tuples from the plurality of cloud service interaction records by combining the interaction environment knowledge vector comprises:

excavating interaction behavior description fields of each group of cloud service interaction information in a plurality of cloud service interaction records;

determining a plurality of cloud service interaction information tuples to be processed through the commonality coefficients among interaction behavior description fields of different cloud service interaction information; each cloud service interaction information binary group to be processed comprises first cloud service interaction information and second cloud service interaction information;

based on interaction environment knowledge vectors respectively corresponding to first cloud service interaction information and second cloud service interaction information in a plurality of cloud service interaction information tuples to be processed, extracting linkage interaction information tuples from the cloud service interaction information tuples to be processed;

the extracting, based on interaction environment knowledge vectors respectively corresponding to first cloud service interaction information and second cloud service interaction information in a plurality of cloud service interaction information tuples to be processed, the linkage interaction information tuple from the cloud service interaction information tuples to be processed includes:

For each cloud service interaction information binary group to be processed in a plurality of cloud service interaction information binary groups to be processed, determining the difference degree of environmental elements between the first cloud service interaction information and the second cloud service interaction information by combining an interaction environment knowledge vector of a first cloud service interaction information binary group in each cloud service interaction information binary group to be processed and an interaction environment knowledge vector of a second cloud service interaction information binary group in each cloud service interaction information binary group to be processed;

if the difference degree of the environmental elements between the first cloud service interaction information and the second cloud service interaction information is lower than a set difference limit value, taking the cloud service interaction information binary group to be processed as the linkage interaction information binary group;

and determining feature mapping indication of the two local feature knowledge networks based on the two cloud service interaction information belonging to different cloud service interaction records in the same linkage interaction information binary group.

2. The method of claim 1, wherein the interaction context knowledge vector comprises: detection module tag data respectively corresponding to each group of cloud service interaction information in the target cloud service interaction record; combining the interaction environment knowledge vector of the first cloud service interaction information binary group in each cloud service interaction information binary group to be processed and the interaction environment knowledge vector of the second cloud service interaction information binary group in each cloud service interaction information binary group to be processed, determining the environment factor difference degree between the first cloud service interaction information and the second cloud service interaction information comprises the following steps:

Determining the number of associated service environment detection modules corresponding to the first cloud service interaction information and the second cloud service interaction information by combining the detection module label data corresponding to the first cloud service interaction information doublet and the detection module label data corresponding to the second cloud service interaction information doublet;

determining the environmental element difference degree corresponding to the first cloud service interaction information and the second cloud service interaction information by combining the number; wherein the environmental element difference degree and the number of the associated service environment detection modules have a set quantization relationship.

3. The method of claim 1, wherein the interaction context knowledge vector comprises: environmental element thermal data and detection module label data respectively corresponding to each group of cloud service interaction information in the target cloud service interaction record; combining the interaction environment knowledge vector of the first cloud service interaction information binary group in each cloud service interaction information binary group to be processed and the interaction environment knowledge vector of the second cloud service interaction information binary group in each cloud service interaction information binary group to be processed, determining the environment factor difference degree between the first cloud service interaction information and the second cloud service interaction information comprises the following steps: combining the detection module label corresponding to the first cloud service interaction information binary group and the detection module label corresponding to the second cloud service interaction information binary group to determine an associated service environment detection module and a non-associated service environment detection module corresponding to the first cloud service interaction information binary group and the second cloud service interaction information binary group; determining a thermal comparison result of the associated service environment detection module by combining the environmental element thermal data respectively corresponding to the first cloud service interaction information and the second cloud service interaction information; determining the difference degree of the environmental elements between the first cloud service interaction information and the second cloud service interaction information by combining the thermal comparison result and the difference degree of the preset environmental elements corresponding to the non-associated service environment detection module;

The combining the linkage interaction information binary group, performing feature knowledge network combination on the target digital service process to obtain a feature knowledge network of the target digital service process, including: combining characteristic knowledge network combination is carried out on each cloud service interaction record in a plurality of cloud service interaction records by combining a plurality of groups of cloud service interaction information in each cloud service interaction record, so as to obtain a local characteristic knowledge network corresponding to each cloud service interaction record; and combining the linkage interaction information binary groups, and carrying out fusion operation on the local feature knowledge networks corresponding to the cloud service interaction records respectively to obtain the feature knowledge network of the target digital service process.

4. The method of claim 3, wherein the combining the linkage interaction information binary group performs a fusion operation on local feature knowledge networks corresponding to the cloud service interaction records respectively to obtain the feature knowledge network of the target digital service process, and the method comprises:

for every two cloud service interaction records, determining whether a target linkage interaction information binary group exists between the two cloud service interaction records; the first linkage cloud service interaction information and the second linkage cloud service interaction information in the target linkage interaction information binary group respectively correspond to the two cloud service interaction records;

If the target linkage interaction information binary group exists between the two cloud service interaction records, determining a feature mapping indication between local feature knowledge networks corresponding to the two cloud service interaction records respectively based on the target linkage interaction information binary group between the two cloud service interaction records, and combining the feature mapping indication to perform fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively;

and obtaining the characteristic knowledge network of the target digital service process based on the fusion results respectively corresponding to the cloud service interaction records.

5. The method according to claim 4, wherein determining a feature mapping indication between the local feature knowledge networks respectively corresponding to the two cloud service interaction records based on the target linkage interaction information binary group between the two cloud service interaction records, and combining the feature mapping indication to perform a fusion operation on the local feature knowledge networks respectively corresponding to the two cloud service interaction records, includes: the following cycle phases are implemented:

determining a first target linkage interaction information binary group corresponding to the current circulation stage from the target linkage interaction information binary groups;

Combining the first target linkage interaction information binary group to determine the current feature mapping indication between the local feature knowledge networks respectively corresponding to the two cloud service interaction records;

combining the current feature mapping indication, and carrying out fusion operation on the local feature knowledge networks corresponding to the two cloud service interaction records respectively to obtain a fused knowledge network corresponding to the current circulation stage;

combining distributed variables reflected by the residual target linkage interaction information tuples except the first target linkage interaction information tuple in the target linkage interaction information tuples, and carrying out knowledge network fusion checking on the fused knowledge network;

if the knowledge network fusion and correction pass, taking the fused knowledge network corresponding to the current circulation stage as a final result of fusion operation on the local feature knowledge networks respectively corresponding to the two cloud service interaction records, and terminating circulation processing;

if the knowledge network fusion check does not pass, entering the next circulation stage;

if all the target linkage interaction information tuples are sequentially used as the first target linkage interaction information tuple and are not subjected to knowledge network fusion checking, the fact that the knowledge network fusion requirements are not met between the local feature knowledge networks respectively corresponding to the two cloud service interaction records is indicated.

6. The method of claim 5, wherein combining the linkage interaction information tuples to perform feature knowledge network combination on the target digital service process to obtain a feature knowledge network of the target digital service process, comprises:

sequentially accessing each linkage interaction information binary group in the linkage interaction information binary groups, and combining the characteristic knowledge networks based on the sequentially accessed linkage interaction information binary groups to obtain a characteristic knowledge network corresponding to the sequentially accessed linkage interaction information binary groups;

and carrying out network integration on the characteristic knowledge networks respectively corresponding to the plurality of linkage interaction information tuples to obtain the characteristic knowledge network of the target digital service process.

7. The method according to claim 6, wherein the feature knowledge network combining based on the sequentially accessed linkage interaction information tuples to obtain a feature knowledge network corresponding to the sequentially accessed linkage interaction information tuples comprises:

based on the states of the data acquisition modules respectively corresponding to the first cloud service interaction information and the second cloud service interaction information in the linkage interaction information binary groups accessed in sequence, and the first cloud service interaction information and the second cloud service interaction information are combined through a feature knowledge network to obtain a first feature knowledge network;

Determining mapping deviation of the first feature knowledge network by combining the first cloud service interaction information, the second cloud service interaction information, the state of a data acquisition module corresponding to the first cloud service interaction information and the second cloud service interaction information respectively, and the first feature knowledge network;

combining the interaction environment knowledge vectors respectively corresponding to the first cloud service interaction information and the second cloud service interaction information and the detection module distribution of the target service environment detection modules corresponding to the interaction environment knowledge vectors, and determining the environmental element difference degree loss between the first cloud service interaction information and the second cloud service interaction information;

optimizing the states of the data acquisition modules corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and the distribution of the detection modules of the target service environment detection module by combining the mapping deviation and the environmental element difference loss to obtain target interaction states corresponding to the first cloud service interaction information and the second cloud service interaction information respectively and target distribution variables of the target service environment detection module;

Combining the first cloud service interaction information, the second cloud service interaction information and the target interaction state to perform characteristic knowledge network combination to obtain a characteristic knowledge network corresponding to the sequentially accessed linkage interaction information binary group;

wherein, still include: and generating a detection module distribution track chain based on target distribution variables of the target service environment detection modules respectively corresponding to the plurality of linkage cloud service interaction information.

8. A data processing system comprising a processor and a memory; the processor is communicatively connected to the memory, the processor being configured to read a computer program from the memory and execute the computer program to implement the method of any of claims 1-7.