CN114358420B - Business workflow intelligent optimization method and system based on industrial ecology - Google Patents
Business workflow intelligent optimization method and system based on industrial ecology Download PDFInfo
- Publication number
- CN114358420B CN114358420B CN202210001767.0A CN202210001767A CN114358420B CN 114358420 B CN114358420 B CN 114358420B CN 202210001767 A CN202210001767 A CN 202210001767A CN 114358420 B CN114358420 B CN 114358420B
- Authority
- CN
- China
- Prior art keywords
- interactive
- content
- interaction
- data items
- level
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the business workflow intelligent optimization method and system based on the industrial ecology, the content elements of the automatic interactive content marks are used for dividing the threads, and time and labor consumption of manual division are avoided. Because at least two kinds of interactive content marks needing to be divided are grouped according to the content element dividing thread, and are divided through the content element dividing thread based on the classification training network, the content element dividing thread based on the database and the content element dividing thread based on the rule corresponding to different groups, the interactive content marks can be advantageously divided by utilizing the characteristics of different kinds of interactive content distinguishing attributes, so that the limitation of adopting a single content element dividing thread is avoided, for example, the content element dividing thread based on the rule is invalid for some kinds of interactive content distinguishing attributes and cannot be divided in a significant manner, the content element dividing thread based on the classification training network can be divided in a significant manner, and the problems of errors and abnormity are solved to a certain extent.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a business workflow intelligent optimization method and system based on industrial ecology.
Background
When the artificial intelligence slowly enters the life of people, great convenience is brought to people, the workload is reduced for people, and the like, so that the pressure of people is relieved, manual labor is not needed, the efficiency can be effectively improved, and the labor cost is reduced. The improvement of the business working process can more efficiently promote the industrial ecological research process.
When artificial intelligence is applied to the establishment of the industrial ecological workflow, the workflow can be planned timely and accurately, and therefore the working efficiency is improved. However, in the process of establishing the workflow, the related data is disturbed, so that a technical problem which needs to be solved is solved.
Disclosure of Invention
In view of this, the present application provides an intelligent business workflow optimization method and system based on industrial ecology.
In a first aspect, a business workflow intelligent optimization method based on industrial ecology is provided, the method including:
acquiring business interaction data items;
and aiming at least two interactive content distinguishing attributes, utilizing a content element dividing thread configured in advance to divide the service interactive data items so as to obtain a dividing interactive fact of the at least two interactive content distinguishing attributes, wherein the at least two interactive content distinguishing attributes are divided into at least two types in advance, each content element dividing thread which is different from each other is configured in advance aiming at the at least two types, and the different content element dividing threads cover the content element dividing threads based on the classification training network.
Preferably, before dividing the service interaction data transaction, the method further comprises:
classifying attributes of the service interaction data items into primary interaction key contents or secondary interaction key contents by utilizing a pre-configured interaction content classification training network;
and sift out secondary interaction critical content in the primary business interaction data transaction.
Preferably, the pre-configured interactive content classification training network comprises an acquisition plane, a training plane, a connection plane and a recognition plane, and wherein the classification training network further comprises:
acquiring an interaction file of the service interaction data items and transmitting the interaction file to the acquisition layer to decompress the interaction file into a matrix representation;
transmitting the matrix representation to a training layer to extract an interaction description vector of an interaction file of the service interaction data items;
transmitting the interactive description vectors to the connection layer to extract a target value corresponding to each interactive description vector, and integrating the target values corresponding to each extracted interactive description vector to serve as the output of the connection layer;
transmitting the output of the connection layer to the identification layer, and obtaining the identified interactive fact based on the output of the identification layer;
further, after the classifying training network and the screening, further comprising:
judging whether the business interaction data items classified as the interaction key content are significant interaction key content or not by utilizing a pre-configured interaction content classification judgment network;
and screening out non-significant interactive key content in the business interactive data items;
wherein the interactive content classification judgment network comprises an acquisition level and a random matching level, and wherein the judgment comprises:
transmitting the interaction files of the service interaction data items classified as the interaction key contents to the acquisition layer to decompress the interaction files into matrix representation;
and transmitting the matrix representation to a random matching layer so as to judge whether the service interaction data items classified as the interaction key content are significant interaction key content according to the output of the random matching layer.
Preferably, the non-identical content element division thread further comprises:
dividing threads based on content elements of a database, wherein semantic description contents in the business interaction data items are associated with semantic description contents in a database constructed in advance,
taking the semantic description contents which can be associated as the division interactive facts;
and a content element division thread based on a logic scheme, wherein an interaction file of the service interaction data items is analyzed by utilizing a preset logic scheme, and the content meeting the logic scheme is used as a division interaction fact;
further, the method further comprises the following steps:
displaying the divided interactive facts through key request content;
on the premise of receiving the update label of the division interactive fact, updating the division interactive fact;
further, a first one of the at least two categories includes interactive contents distinguishing attributes of the following categories: an interference region and a platform, and wherein the partitioning comprises:
and aiming at any kind of interactive content distinguishing attributes in the first kind, the business interactive data items are divided by utilizing a database-based content element dividing thread, wherein the database-based content element dividing thread is used for matching semantic description contents in the business interactive data items with semantic description contents in a database constructed in advance, and the matched semantic description contents are used as dividing interactive facts.
Preferably, a second one of the at least two categories includes interactive content distinguishing attributes of the following categories: standard data documentation, logging, evaluation and construction matters for the operational steps, and wherein said dividing comprises:
and aiming at any kind of interactive content distinguishing attributes in the second type, dividing the business interactive data items by utilizing a content element dividing thread based on a logic scheme, wherein the content element dividing thread based on the logic scheme is used for analyzing the business interactive data items by utilizing a preset logic scheme, and taking the content meeting the logic scheme as a dividing interactive fact.
Preferably, a third one of the at least two categories includes interactive contents distinguishing attributes of the following categories, the dividing includes:
and aiming at any kind of interactive content distinguishing attribute in the third kind, dividing the business interactive data items by utilizing a content element dividing thread based on a classification training network.
Preferably, further comprising:
statistically analyzing the divided interactive facts to obtain the similarity among the categories of the interactive content distinguishing attributes;
and/or outputting interactive content prompts based on the divided interactive facts.
Preferably, further comprising:
on the premise that the division interactive facts are divided by using content element division threads based on a classification training network, further training the classification training network by using the updated division interactive facts;
and/or iterating the database by using the updated division interactive facts on the premise that the division interactive facts are divided by using a database-based content element division thread, wherein the database-based content element division thread is used for matching semantic description contents in the business interactive data items with semantic description contents in a database constructed in advance, and the matched semantic description contents are used as the division interactive facts.
In a second aspect, an industrial ecology-based business workflow intelligent optimization system is provided, which includes a processor and a memory, which are communicated with each other, and the processor is used for reading a computer program from the memory and executing the computer program to implement the method.
In a third aspect, a server comprises:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the above-described method.
According to the business workflow intelligent optimization method and system based on the industrial ecology, the content elements of the automatic interactive content marks are used for dividing the threads, and time and labor consumption of manual division are avoided. Because at least two kinds of interactive content marks needing to be divided are grouped according to the content element dividing thread, and are divided through the content element dividing thread based on the classification training network, the content element dividing thread based on the database and the content element dividing thread based on the rule corresponding to different groups, the interactive content marks can be advantageously divided by utilizing the characteristics of different kinds of interactive content distinguishing attributes, so that the limitation of adopting a single content element dividing thread is avoided, for example, the content element dividing thread based on the rule is invalid for some kinds of interactive content distinguishing attributes and cannot be divided in a significant mode, but instead, the content element dividing thread based on the classification training network can be divided in a significant mode, and the problems of errors and exceptions are solved to a certain extent. Through interaction with key request contents, the classification training network can continuously receive interaction facts fed back by the front end, so that the classification training network is continuously trained and screened, the classification accuracy of the classification training network is continuously improved, a database can be continuously updated, and the problems of missed report and false report are solved to a certain extent. In addition, the adopted classification training network can divide the interaction description vector of the context, so that the non-malicious interaction content distinguishing attributes appearing in the report can be distinguished, and the problems of report missing and false report are solved to a certain extent. In the embodiment, a pre-configured interactive content classification training network is utilized to classify the service interactive data items into interactive key content and non-interactive key content, and the non-interactive key content is removed, so that the manpower can be further liberated, manual screening is not needed, and the method can be flexibly applied to each process resource source. In a further embodiment, a pre-configured interactive content classification judgment network is used to judge whether the service interactive data items classified as the interactive key contents are significant interactive key contents, and further remove non-significant interactive key contents in the service interactive data items, which can further help to improve the workflow establishment efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of an industrial ecology-based business workflow intelligent optimization method according to an embodiment of the present disclosure.
Fig. 2 is a block diagram of an industrial ecology-based intelligent business workflow optimization apparatus according to an embodiment of the present disclosure.
Fig. 3 is an architecture diagram of an industrial ecology-based business workflow intelligent optimization system according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
Referring to fig. 1, a business workflow intelligent optimization method based on industrial ecology is shown, which may include the technical solutions described in the following steps 100 and 200.
Step 100, obtaining service interaction data items.
It can be understood that, when the technical solutions described in the above steps 100 and 200 are executed, the thread is divided by using the content elements of the automated interactive content mark, so that the time and labor for manual division are avoided. Because at least two kinds of interactive content marks needing to be divided are grouped according to the content element dividing thread, and are divided through the content element dividing thread based on the classification training network, the content element dividing thread based on the database and the content element dividing thread based on the rule corresponding to different groups, the interactive content marks can be divided advantageously by utilizing the characteristics of different kinds of interactive content distinguishing attributes, and the limitation of adopting a single content element dividing thread is avoided. Through interaction with key request contents, the classification training network can continuously receive interaction facts fed back by the front end, so that the classification training network is continuously trained and screened, the classification accuracy of the classification training network is continuously improved, a database can be continuously updated, and the problems of missed report and false report are solved to a certain extent. In addition, the adopted classification training network can divide the interaction description vector of the context, so that the non-malicious interaction content distinguishing attributes appearing in the report can be distinguished, and the problems of report missing and false report are solved to a certain extent. In the embodiment, a pre-configured interactive content classification training network is utilized to classify the service interactive data items into interactive key content and non-interactive key content, and the non-interactive key content is removed, so that the manpower can be further liberated, manual screening is not needed, and the method can be flexibly applied to each process resource source. In a further embodiment, a pre-configured interactive content classification judgment network is used to judge whether the service interactive data items classified as the interactive key content are significant interactive key content, and further remove non-significant interactive key content in the service interactive data items, which can further help to improve the workflow establishment efficiency.
Based on the above basis, before the service interaction data item is divided, the following technical solutions described in step q1 and step q2 may also be included.
And step q1, classifying the attributes of the business interaction data items into main interaction key contents or secondary interaction key contents by utilizing a pre-configured interaction content classification training network.
Step q2, and screening out the secondary interactive key content in the primary service interactive data transaction.
It can be understood that when the technical solutions described in the above step q1 and step q2 are executed, the screening accuracy can be improved by the attribute of the service interaction data item.
In an alternative embodiment, the inventor finds that the pre-configured interactive content classification training network includes an acquisition level, a training level, a connection level and a recognition level, and wherein the classification training network has a problem of inaccurate decompression, so that it is difficult to accurately obtain the classification training network, and in order to improve the above technical problem, the pre-configured interactive content classification training network described in step q1 includes an acquisition level, a training level, a connection level and a recognition level, and wherein the step of classifying the training network may specifically include the technical solutions described in the following steps q11 to q 14.
And q11, acquiring the interaction file of the service interaction data items and transmitting the interaction file to the acquisition layer to decompress the interaction file into a matrix representation.
And q12, transmitting the matrix representation to a training layer to extract the interaction description vector of the interaction archive of the service interaction data items.
And q13, transmitting the interactive description vectors to the connection layer to extract a target value corresponding to each interactive description vector, and integrating the target values corresponding to each extracted interactive description vector to serve as the output of the connection layer.
And q14, transmitting the output of the connection layer to the identification layer, and obtaining the identified interactive fact based on the output of the identification layer.
It can be understood that, when the technical solution described in the above step q 11-step q14 is executed, the interactive content classification training network configured in advance includes an acquisition layer, a training layer, a connection layer and a recognition layer, and the classification training network avoids the problem of inaccurate decompression as much as possible, so that the classification training network can be obtained accurately.
Based on the above basis, after the classification training network and the screening, the technical solution described in the following steps w1 and w2 may be further included.
And w1, judging whether the business interaction data items classified into the interaction key contents are significant interaction key contents or not by utilizing a preset interaction content classification judgment network.
Step w2, and screening out the interaction key content which is not significant in the business interaction data item and in the business interaction data item.
It can be understood that, when the technical solutions described in the above steps w1 and w2 are executed, the accuracy of the non-significant interactive key content is improved by determining whether the service interactive data items classified as the interactive key content are significant interactive key content.
In an alternative embodiment, the inventor finds that, when the interactive content classification judgment network includes an acquisition plane and a random matching plane, there is a problem that the acquisition plane and the random matching plane are not reliable, so that it is difficult to perform reliable judgment, and in order to improve the above technical problem, the interactive content classification judgment network described in step w1 includes steps of the acquisition plane and the random matching plane, and may specifically include the technical solutions described in the following steps w1 and w 2.
And w1, transmitting the interaction file of the service interaction data items classified as the interaction key content to the acquisition layer, and decompressing the interaction file into matrix representation.
And w2, transmitting the matrix representation to a random matching layer, and judging whether the business interaction data items classified as the interaction key contents are significant interaction key contents or not according to the output of the random matching layer.
It can be understood that when the technical solutions described in the above steps w1 and w2 are executed, and the interactive content classification judgment network includes the acquisition layer and the random matching layer, the problem that the acquisition layer and the random matching layer are not reliable is solved, so that reliable judgment can be performed.
Based on the above basis, the different content elements are divided into threads, and the technical scheme described in the following steps e1 to e3 can also be included.
Step e1, dividing threads based on the content elements of the database, wherein the semantic description content in the business interaction data items is associated with the semantic description content in the database which is constructed in advance.
And e2, taking the semantic description contents which can be associated as the division interactive facts.
Step e3, and a content element dividing thread based on a logic scheme, wherein the interaction file of the business interaction data items is analyzed by using the preset logic scheme, and the content meeting the logic scheme is used as a dividing interaction fact.
It can be understood that when the technical solutions described in the above steps e1 to e3 are executed, threads are divided by content elements, so as to improve the accuracy of the content satisfying the logic solution as a division interactive fact.
Based on the above basis, the technical problems described in the following steps r1 and r2 may also be included.
And step r1, displaying the division interactive facts through key request content.
And r2, on the premise of receiving the update label of the partitioning interaction fact, updating the partitioning interaction fact.
It can be understood that when the technical problems described in the above steps r1 and r2 are performed, the update accuracy is improved by displaying the division interaction fact.
In an alternative embodiment, the inventors have found that a first of the at least two types comprises the following types of interactive content distinguishing attributes: when the region and the platform are interfered, there is a problem that any kind of interactive content distinguishing attribute is inaccurate, so that it is difficult to accurately describe the semantic description content capable of being matched as a division interactive fact, and in order to improve the above technical problem, a first one of at least two kinds described in step 200 includes the following kinds of interactive content distinguishing attributes: the step of interfering with the region and the platform may specifically include the technical scheme described in the following step t 1.
And t1, aiming at any kind of interactive content distinguishing attributes in the first type, dividing the business interactive data items by utilizing a content element dividing thread based on a database, wherein the semantic description content in the business interactive data items is matched with the semantic description content in the database constructed in advance by the content element dividing thread based on the database, and the matched semantic description content is used as a dividing interactive fact.
It can be understood that, when the technical solution described in the above step t1 is executed, a first one of the at least two kinds includes the following kinds of interactive content distinguishing attributes: when the region and the platform are interfered, the problem that the distinguishing attribute of any kind of interactive content is inaccurate is solved, and therefore matched semantic description content can be accurately used as a dividing interactive fact.
In an alternative embodiment, a second one of the at least two categories comprises the following categories of interactive content distinguishing attributes: the standard data file, the recording record, the evaluation and the construction items of the operation steps can specifically comprise the technical scheme described in the following step y 1.
Step y1, aiming at any kind of interactive content distinguishing attributes in the second type, the business interactive data items are divided by a content element dividing thread based on a logic scheme, wherein the content element dividing thread based on the logic scheme is used for analyzing the business interactive data items by a preset logic scheme, and the content meeting the logic scheme is used as a dividing interactive fact.
It can be understood that, when the technical solution described in the above step y1 is executed, the service interaction data transaction is divided by using the content element division thread based on the logic solution, so that the accuracy of the content satisfying the logic solution as the division interaction fact can be improved.
In an alternative embodiment, a third one of the at least two types includes the following types of interactive content distinguishing attributes, which may specifically include the technical solution described in the following step u 1.
And u1, aiming at any kind of interactive content distinguishing attributes in the third category, dividing the business interactive data items by utilizing a content element dividing thread based on a classification training network.
It can be understood that, when the technical solution described in the above step u1 is executed, the attributes are distinguished through any kind of interactive content, so as to improve the confidence of dividing the business interactive data items.
Based on the above basis, the technical scheme described in the following steps i1 and i2 can also be included.
And i1, statistically analyzing the divided interactive facts to obtain the similarity between the categories of the interactive content distinguishing attributes.
And step i2, and/or outputting an interactive content prompt based on the divided interactive facts.
It can be understood that, when the technical solutions described in the above step i1 and step i2 are executed, the accuracy of the interactive content prompt is improved by analyzing the divided interactive facts.
Based on the above basis, the technical scheme described in the following step o1 and step o2 can also be included.
And step o1, on the premise that the classification interactive facts are classified by using the content element classification threads based on the classification training network, further training the classification training network by using the updated classification interactive facts.
And step o2, and/or iterating the database by using the updated division interactive facts on the premise that the division interactive facts are divided by using a database-based content element division thread, wherein the database-based content element division thread is used for matching semantic description contents in the service interactive data items with semantic description contents in a database constructed in advance, and the matched semantic description contents are used as the division interactive facts.
It can be understood that, when the technical solutions described in the above step o1 and step o2 are executed, the integrity of the partitioning interaction fact is improved by the updated partitioning interaction fact.
In a possible embodiment, the classification training network comprises a first acquisition level, a second acquisition level, a sample level during the history of the first level, a sample level during the history of the second level, a feedback neural model level and a screening level; and wherein, the classifying training network is used to divide the service interaction data items, which may specifically include the technical solutions described in the following steps a1 to a 6.
Step a1, transmitting a next round of interactive elements of semantic description contents of the service interactive data items to the first acquisition layer, and decompressing the interactive elements into matrix type representation of the next round of interactive elements.
And a2, transmitting the matrix representation of the next round of interactive elements to the sample level in the first layer history record to obtain the output of the sample level in the first layer history record.
Step a3, transmitting the semantic description content of the service interaction data transaction to the second acquisition layer, so as to decompress the semantic description content into a matrix type representation of the semantic description content.
And a4, integrating the output of the sample level in the first-level historical record and the matrix representation of the semantic description content, and transmitting the integrated output to the sample level in the second-level historical record to obtain the output of the sample level in the second-level historical record.
And a5, transmitting the output of the sample level when the second level is recorded to a feedback neural model level with a floating level to obtain the importance degree of each interactive content distinguishing attribute in the semantic description content.
Step a6, transmitting the importance degree to the screening layer, and the obtained output is the interactive content distinguishing attribute in the service interactive data item.
It can be understood that when the technical solutions described in the above steps a1 to a6 are performed, the accuracy of the interactive content distinguishing attributes is improved by accurately decompressing.
On the basis, please refer to fig. 2 in combination, an intelligent optimization apparatus 200 for business workflow based on industrial ecology is provided, which is applied to a data processing terminal, and includes:
the transaction acquiring module 210 is configured to acquire a transaction interaction data transaction;
the transaction dividing module 220 is configured to, for at least two interactive content distinguishing attributes, divide the service interactive data transaction by using a pre-configured content element dividing thread to obtain a dividing interactive fact of the at least two interactive content distinguishing attributes, where the at least two interactive content distinguishing attributes are pre-divided into at least two categories, each of the at least two categories is pre-configured with a content element dividing thread that is different from the other category, and the different content element dividing threads cover content element dividing threads based on a classification training network.
On the basis of the above, please refer to fig. 3, which shows an industrial ecology-based business workflow intelligent optimization system 300, which includes a processor 310 and a memory 320, which are communicated with each other, wherein the processor 310 is configured to read a computer program from the memory 320 and execute the computer program to implement the above method.
On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.
In conclusion, based on the scheme, the content elements of the automatic interactive content marks are adopted to divide the threads, so that the time and labor consumption of manual division are avoided. Because at least two kinds of interactive content marks needing to be divided are grouped according to the content element dividing thread, and are divided through the content element dividing thread based on the classification training network, the content element dividing thread based on the database and the content element dividing thread based on the rule corresponding to different groups, the interactive content marks can be divided advantageously by utilizing the characteristics of different kinds of interactive content distinguishing attributes, and the limitation of adopting a single content element dividing thread is avoided. Through interaction with key request contents, the classification training network can continuously receive interaction facts fed back by the front end, so that the classification training network is continuously trained and screened, the classification accuracy of the classification training network is continuously improved, a database can be continuously updated, and the problems of missed report and false report are solved to a certain extent. In addition, the adopted classification training network can divide the interaction description vector of the context, so that the non-malicious interaction content distinguishing attributes appearing in the report can be distinguished, and the problems of report missing and false report are solved to a certain extent. In the embodiment, a pre-configured interactive content classification training network is utilized to classify the service interactive data items into interactive key content and non-interactive key content, and the non-interactive key content is removed, so that the manpower can be further liberated, manual screening is not needed, and the method can be flexibly applied to each process resource source. In a further embodiment, a pre-configured interactive content classification judgment network is used to judge whether the service interactive data items classified as the interactive key content are significant interactive key content, and further remove non-significant interactive key content in the service interactive data items, which can further help to improve the workflow establishment efficiency.
It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, for example such code provided on a carrier medium such as a diskette, CD-or DVD-ROM, programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It is to be noted that different embodiments may produce different advantages, and in different embodiments, the advantages that may be produced may be any one or combination of the above, or any other advantages that may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered as illustrative only and not limiting of the application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, a conventional programming language such as C, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service using, for example, software as a service (SaaS).
Additionally, unless explicitly recited in the claims, the order of processing elements and sequences, use of numbers and letters, or use of other designations in this application is not intended to limit the order of the processes and methods in this application. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application history document is inconsistent or conflicting with the present application as to the extent of the present claims, which are now or later appended to this application. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application may be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (3)
1. An intelligent business workflow optimization method based on industrial ecology is characterized by comprising the following steps:
acquiring business interaction data items;
and for at least two interactive content distinguishing attributes, utilizing a content element dividing thread configured in advance to divide the service interactive data items to obtain a dividing interactive fact of the at least two interactive content distinguishing attributes, wherein the at least two interactive content distinguishing attributes are divided into at least two types in advance, each different content element dividing thread is configured for the at least two types in advance, and the different content element dividing threads cover content element dividing threads based on a classification training network;
wherein, before dividing the service interaction data transaction, the method comprises:
classifying the attributes of the service interaction data items into main interaction key contents or secondary interaction key contents by utilizing a pre-configured interaction content classification training network;
and screening out secondary interactive key content in the primary service interactive data items;
after training the network and screening for interactive content classification, comprising:
judging whether the business interaction data items classified as the interaction key content are significant interaction key content or not by utilizing a pre-configured interaction content classification judgment network;
and screening out non-significant interactive key content in the business interactive data items;
wherein the interactive content classification training network configured in advance comprises an acquisition level, a training level, a connection level and an identification level, and wherein the classification comprises:
acquiring an interaction file of the service interaction data items and transmitting the interaction file to the acquisition layer to decompress the interaction file into a matrix representation;
transmitting the matrix representation to a training layer to extract an interaction description vector of an interaction file of the service interaction data item;
transmitting the interactive description vectors to the connection layer to extract a target value corresponding to each interactive description vector, and integrating the target values corresponding to each extracted interactive description vector to serve as the output of the connection layer;
transmitting the output of the connection layer to the identification layer, and obtaining the identified interactive fact based on the output of the identification layer;
wherein, the interactive content classification judgment network comprises an acquisition level and a random matching level, and the judgment comprises:
transmitting the interaction files of the service interaction data items classified as the interaction key contents to the acquisition layer to decompress the interaction files into matrix representation;
transmitting the matrix representation to a random matching layer so as to judge whether the service interaction data items classified as the interaction key contents are significant interaction key contents or not according to the output of the random matching layer;
wherein the disparate content element partitioning thread further comprises:
dividing threads based on content elements of a database, wherein semantic description contents in the business interaction data items are associated with semantic description contents in a database constructed in advance,
taking the semantic description contents which can be associated as the division interactive facts;
and a content element division thread based on a logic scheme, wherein an interaction file of the business interaction data items is analyzed by utilizing the preset logic scheme, and the content meeting the logic scheme is used as a division interaction fact;
displaying the division interaction facts through key request content;
on the premise of receiving the update tag of the partitioning interaction fact, updating the partitioning interaction fact;
a first one of the at least two categories includes interactive content distinguishing attributes of the following categories: an interference region and a platform, and wherein the partitioning comprises:
aiming at any kind of interactive content distinguishing attributes in the first type, the business interactive data items are divided by utilizing a content element dividing thread based on a database, wherein the semantic description content in the business interactive data items is matched with the semantic description content in the database constructed in advance by the content element dividing thread based on the database, and the matched semantic description content is used as a dividing interactive fact;
wherein a second one of the at least two categories includes interactive contents distinguishing attributes of the following categories: standard data documentation, logging, evaluation and construction matters for the operational steps, and wherein said dividing comprises:
for any kind of interactive content distinguishing attributes in the second type, dividing the business interactive data items by utilizing a content element dividing thread based on a logic scheme, wherein the content element dividing thread based on the logic scheme analyzes the business interactive data items by utilizing a preset logic scheme, and takes the content meeting the logic scheme as a dividing interactive fact;
statistically analyzing the divided interactive facts to obtain the similarity among the categories of the interactive content distinguishing attributes;
and/or outputting interactive content prompts based on the divided interactive facts;
on the premise that the dividing interactive facts are divided by using content element dividing threads based on a classification training network, further training the classification training network by using the updated dividing interactive facts;
and/or iterating the database by using the updated division interactive facts on the premise that the division interactive facts are divided by using a database-based content element division thread, wherein the database-based content element division thread is used for matching semantic description contents in the service interactive data items with semantic description contents in a database constructed in advance, and taking the matched semantic description contents as the division interactive facts;
the classification training network comprises a first acquisition layer, a second acquisition layer, a sample layer during the historical record of the first layer, a sample layer during the historical record of the second layer, a feedback neural model layer and a screening layer; and wherein, using the classification training network to classify the service interaction data items comprises:
transmitting a next round of interactive elements of semantic description contents of the service interactive data items to the first acquisition layer to be decompressed into matrix type representation of the next round of interactive elements;
transmitting the matrix representation of the next round of interactive elements to the sample level in the first level historical record to obtain the output of the sample level in the first level historical record;
transmitting semantic description contents of the service interaction data items to the second acquisition layer to be decompressed into matrix type representation of the semantic description contents;
integrating the output of the sample level in the first level historical record with the matrix representation of the semantic description content, and transmitting the integrated output to the sample level in the second level historical record to obtain the output of the sample level in the second level historical record;
transmitting the output of the sample level in the second level historical record to a feedback neural model level with a floating level to obtain the importance degree of each interactive content distinguishing attribute in the semantic description content;
and transmitting the importance degree to the screening layer, and the obtained output is the interactive content distinguishing attribute in the service interactive data items.
2. An industrial ecology-based business workflow intelligent optimization system comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method of claim 1.
3. A server, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210001767.0A CN114358420B (en) | 2022-01-04 | 2022-01-04 | Business workflow intelligent optimization method and system based on industrial ecology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210001767.0A CN114358420B (en) | 2022-01-04 | 2022-01-04 | Business workflow intelligent optimization method and system based on industrial ecology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114358420A CN114358420A (en) | 2022-04-15 |
| CN114358420B true CN114358420B (en) | 2023-04-07 |
Family
ID=81104524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210001767.0A Active CN114358420B (en) | 2022-01-04 | 2022-01-04 | Business workflow intelligent optimization method and system based on industrial ecology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358420B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11893500B2 (en) * | 2017-11-28 | 2024-02-06 | International Business Machines Corporation | Data classification for data lake catalog |
| CN109684627A (en) * | 2018-11-16 | 2019-04-26 | 北京奇虎科技有限公司 | A kind of file classification method and device |
| CN110209819A (en) * | 2019-06-05 | 2019-09-06 | 江苏满运软件科技有限公司 | File classification method, device, equipment and medium |
| CN112232731B (en) * | 2020-09-15 | 2022-11-22 | 浪潮通用软件有限公司 | Method and equipment for classifying inventory ABC |
| CN112835682B (en) * | 2021-02-25 | 2024-04-05 | 平安消费金融有限公司 | Data processing method, device, computer equipment and readable storage medium |
| CN114840853B (en) * | 2021-06-16 | 2023-04-28 | 三人行传媒集团股份有限公司 | Digital business analysis method based on big data and cloud server |
| CN113869067A (en) * | 2021-09-23 | 2021-12-31 | 国家电网有限公司 | Response method and system based on intelligent customer service |
-
2022
- 2022-01-04 CN CN202210001767.0A patent/CN114358420B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 基于UML图组的软件性能测试;王雯雯;《电脑编程技巧与维护》(第20期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114358420A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113378554A (en) | Medical information intelligent interaction method and system | |
| CN115732050A (en) | Intelligent medical big data information acquisition method and system | |
| CN115641176B (en) | Data analysis method and AI system | |
| CN114358420B (en) | Business workflow intelligent optimization method and system based on industrial ecology | |
| US11461414B2 (en) | Automatically building a searchable database of software features for software projects | |
| CN114329116B (en) | Artificial intelligence-based intelligent park resource matching degree analysis method and system | |
| CN117037982A (en) | Medical big data information intelligent acquisition method and system | |
| CN113626538A (en) | Medical information intelligent classification method and system based on big data | |
| CN115512344A (en) | Three-dimensional live-action image recognition processing method and system and cloud platform | |
| CN115514570A (en) | Network diagnosis processing method and system and cloud platform | |
| CN115640602A (en) | Private data processing method and system based on big data protection | |
| CN113947709A (en) | Image processing method and system based on artificial intelligence | |
| CN113393523A (en) | Method and device for automatically monitoring computer room image and electronic equipment | |
| CN114611478B (en) | Information processing method and system based on artificial intelligence and cloud platform | |
| CN114168670B (en) | Industrial ecological big data integration method and system and cloud platform | |
| CN115455070A (en) | Data management and control method and system for current signals | |
| CN113610117B (en) | Underwater sensing data processing method and system based on depth data | |
| CN115756576B (en) | Translation method of software development kit and software development system | |
| CN114356961A (en) | Resource retrieval method and system based on big data | |
| CN113609931A (en) | Face recognition method and system based on neural network | |
| CN114970507A (en) | Feature identification method and system based on metauniverse | |
| CN114676975A (en) | Production data template production method and device | |
| CN114663071A (en) | Method and system for processing science and technology project data on line | |
| CN115455406A (en) | Risk detection method and system for network information | |
| CN115907508A (en) | Remote data control method and system based on big data |
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 |