CN114638117B - Data processing method and system based on artificial intelligence and cloud platform - Google Patents
Data processing method and system based on artificial intelligence and cloud platform Download PDFInfo
- Publication number
- CN114638117B CN114638117B CN202210317932.3A CN202210317932A CN114638117B CN 114638117 B CN114638117 B CN 114638117B CN 202210317932 A CN202210317932 A CN 202210317932A CN 114638117 B CN114638117 B CN 114638117B
- Authority
- CN
- China
- Prior art keywords
- task description
- key task
- communication data
- industrial production
- example industrial
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Abstract
According to the data processing method, the data processing system and the cloud platform based on the artificial intelligence, the production demand analysis model is obtained based on the joint debugging of the topological structure processing model, the production demand analysis model can achieve the conclusion of key task description, so that the first key task description obtained by performing key task description analysis on target industrial production communication data through the production demand analysis model and a plurality of second key task descriptions obtained by performing key task description analysis on a plurality of historical industrial production communication data through the production demand analysis model existing in a key task description set can be paired accurately and completely, similar key task descriptions can be paired as far as possible, the production demand information with higher precision and reliability can be determined, and the analysis quality of the production demand analysis is improved to a certain extent.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a data processing method and system based on artificial intelligence and a cloud platform.
Background
Artificial intelligence development enters a new stage. Through development and evolution for more than 60 years, particularly under the common drive of new theoretical and new technologies such as mobile internet, big data, super computing, sensor network, brain science and the like and strong requirements of economic and social development, artificial intelligence is developed in an accelerated way, and new characteristics such as deep learning, cross-border fusion, man-machine cooperation, crowd intelligence development, autonomous control and the like are presented. The development of related disciplines of new generation artificial intelligence, theoretical modeling, technical innovation, software and hardware upgrading and the like are integrally promoted, chain breakthrough is initiated, and the jump from digitization and networking to intelligent acceleration in various fields of the economy and society is promoted. Nowadays, industrial production technology is mostly realized by combining industrial production equipment and communication technology to realize product production. However, the inventor has found that, for the product production process of the industrial production equipment, how to realize high-quality production demand analysis based on artificial intelligence is the current pain point.
Disclosure of Invention
In order to solve the technical problems in the related art, the application provides a data processing method and system based on artificial intelligence and a cloud platform.
In a first aspect, an embodiment of the present application provides an artificial intelligence based data processing method, which is applied to a communication data processing system, and the method includes: performing key task description analysis on target industrial production communication data through a production demand analysis model to obtain a first key task description corresponding to the target industrial production communication data, wherein the production demand analysis model is obtained by performing joint debugging by combining a topological structure processing model; and performing key task description pairing on the first key task description and a plurality of second key task descriptions existing in a key task description set to obtain production demand information corresponding to the target industrial production communication data, wherein the plurality of second key task descriptions are obtained by performing key task description analysis on a plurality of historical industrial production communication data by using the production demand analysis model.
In one possible embodiment, the debugging instance of the production demand analysis model comprises a first set number of instance industrial production communication data; the debugging step of the production demand analysis model comprises the following steps:
carrying out artificial intelligence-based data processing on the first set number of example industrial production communication data through the production demand analysis model to obtain a third key task description corresponding to each example industrial production communication data;
performing artificial intelligence-based data processing on the first set number of example industrial production communication data through the topological structure processing model to obtain a fourth key task description corresponding to each example industrial production communication data, wherein the artificial intelligence-based data processing on the first set number of example industrial production communication data through the topological structure processing model to obtain the fourth key task description corresponding to each example industrial production communication data includes: performing staged key task description analysis on the first set number of example industrial production communication data through the topological structure processing model to obtain a first staged key task description and a second staged key task description corresponding to each example industrial production communication data; merging the first phased key task description and the second phased key task description corresponding to each example industrial production communication data to obtain a fourth key task description corresponding to each example industrial production communication data;
determining a first model expected difference according to the third key task description and the fourth key task description corresponding to each example industrial production communication data;
updating the production demand analysis model according to the expected difference of the first model;
wherein, annotations exist corresponding to each historical industrial production communication data; the key task description pairing the first key task description and a plurality of second key task descriptions existing in a key task description set to obtain production demand information corresponding to the target industrial production communication data includes:
determining a mission critical description commonality index between the first mission critical description and each of the second mission critical descriptions;
determining the second key task description with the key task description commonality index being greater than a specified judgment value as a target second key task description successfully paired with the first key task description;
and determining the annotation of the historical industrial production communication data corresponding to the target second key task description as the production demand information.
In one possible embodiment, the first model expected difference comprises a first expected difference; the determining a first model expected difference according to the third key task description and the fourth key task description corresponding to each example industrial production communication data comprises:
according to the third key task description corresponding to each example industrial production communication data, performing full connection processing on the first set quantity of example industrial production communication data, and determining a first full connection processing estimation result corresponding to each example industrial production communication data;
according to the fourth key task description corresponding to each example industrial production communication data, performing full connection processing on the first set number of example industrial production communication data, and determining a second full connection processing estimation result corresponding to each example industrial production communication data;
determining the first expected difference according to the first full-connection processing estimation result and the second full-connection processing estimation result corresponding to each example industrial production communication data;
wherein, the performing full-connection processing on the first set number of example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data, and determining a second full-connection processing estimation result corresponding to each example industrial production communication data includes: determining the distribution of the basic key task description corresponding to each example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data; performing key task description induction on the basic key task description distribution corresponding to each example industrial production communication data by using the topological structure processing model to obtain induced key task description corresponding to each example industrial production communication data; and performing full-connection processing on the first set number of example industrial production communication data according to the generalized key task description corresponding to each example industrial production communication data, and determining the second full-connection processing estimation result corresponding to each example industrial production communication data.
In one possible embodiment, the first model expected difference comprises a second expected difference; the determining a first model expected difference according to the third key task description and the fourth key task description corresponding to each example industrial production communication data comprises:
determining a first target key task description distribution corresponding to each example industrial production communication data according to the third key task description corresponding to each example industrial production communication data;
determining second target key task description distribution corresponding to each example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data;
determining the second expected difference according to the first target mission critical description distribution and the second target mission critical description distribution corresponding to each example industrial production communication data.
In one possible embodiment, the updating the production demand analysis model based on the first model expected difference comprises: updating the production demand analysis model by the first expected difference and/or the second expected difference;
wherein the determining a second target mission critical description distribution corresponding to each example industrial production communication data according to the fourth mission critical description corresponding to each example industrial production communication data includes:
determining the fourth key task description corresponding to each example industrial production communication data as a key task description unit corresponding to each example industrial production communication data to obtain a first set number of key task description units;
determining a second set number of tight key task description units with the smallest quantization difference with a target key task description unit as a first type of tight key task description units corresponding to the target key task description unit, wherein the target key task description unit is a key task description unit corresponding to target example industrial production communication data, and the target example industrial production communication data is one of the example industrial production communication data;
determining a third set number of tight key task description units with the smallest quantization difference with each first type of tight key task description unit as a second type of tight key task description unit corresponding to the target key task description unit;
determining basic key task description distribution corresponding to the target example industrial production communication data according to the first type of close key task description unit and the second type of close key task description unit;
and determining second target key task description distribution corresponding to the target example industrial production communication data according to the basic key task description distribution corresponding to the target example industrial production communication data.
In a possible embodiment, a basic mission critical description distribution corresponding to the target example industrial production communication data comprises a first mission critical description unit sequence and a first association description list;
the determining of the basic key task description distribution corresponding to the target example industrial production communication data according to the first type of tight key task description unit and the second type of tight key task description unit includes:
according to the target key task description units, dimensionless processing is carried out on the key task description units with the first set number, and the key task description units with the first set number after dimensionless processing are obtained;
generating a first key task description unit sequence according to the first set number of key task description units subjected to dimension removal processing, including a first type of tight key task description unit subjected to dimension removal processing and a second type of tight key task description unit subjected to dimension removal processing;
for an a-th key task description unit in the first key task description unit sequence, determining b close key task description units with minimum quantization difference with the a-th key task description unit in the first set number of key task description units after the de-dimension processing;
determining a mission-critical description association tag between the a-th mission-critical description unit and a c-th close mission-critical description unit, wherein the c-th close mission-critical description unit is a mission-critical description unit present in the first sequence of mission-critical description units;
and determining the first association description list according to the upstream and downstream association corresponding to each key task description unit in the first key task description unit sequence.
In a possible embodiment, the second target mission-critical description distribution includes a second mission-critical description unit sequence and a second association description list; the determining the second target mission critical description distribution corresponding to the target example industrial production communication data according to the base mission critical description distribution corresponding to the target example industrial production communication data includes:
loading the key task description units which are not in the first key task description unit sequence in the first set number of key task description units after the dimension removal processing to the first key task description unit sequence to generate a second key task description unit sequence;
for a non-critical task description unit in the second critical task description unit sequence, determining a compact critical task description unit corresponding to the non-critical task description unit in the first set number of critical task description units after the dimensionless processing, wherein the non-critical task description unit is one of the critical task description units which are not in the first critical task description unit sequence and are in the first set number of critical task description units after the dimensionless processing;
determining a non-critical task description association tag between the non-critical task description unit and a close critical task description unit corresponding to the non-critical task description unit;
and determining the second association description list according to the upstream and downstream association corresponding to each key task description unit in the second key task description unit sequence.
In a possible embodiment, the debugging example further includes an actual annotation corresponding to each of the example industrial production communication data, and the second full-connection processing estimation result corresponding to each of the example industrial production communication data includes an estimation annotation corresponding to each of the example industrial production communication data;
the debugging method of the production demand analysis model further comprises the following steps: determining a second model expected difference according to the actual annotation and the estimated annotation corresponding to each example industrial production communication data; updating the topology processing model in accordance with the second model expected difference.
In a second aspect, the present application further provides a communication data processing system comprising a processor and a memory; the processor is connected with the memory in communication, and the processor is used for reading the computer program from the memory and executing the computer program to realize the method.
In a third aspect, the present application further provides a cloud platform including a readable storage medium storing a program to perform the method.
In the embodiment of the application, a production demand analysis model is obtained based on joint debugging of a topological structure processing model, so that the production demand analysis model can realize conclusion of key task description, a first key task description obtained by performing key task description analysis on target industrial production communication data through the production demand analysis model can be matched with a plurality of second key task descriptions obtained by performing key task description analysis on a plurality of historical industrial production communication data through the production demand analysis model existing in a key task description set, accurate and complete key task description matching can be performed, similar key task descriptions can be matched as far as possible, production demand information with higher precision and reliability can be determined, and the analysis quality of production demand analysis is improved to a certain extent.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic hardware configuration diagram of a communication data processing system according to an embodiment of the present application.
Fig. 2 is a schematic flowchart of a data processing method based on artificial intelligence according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided by the embodiments of the present application may be executed in a communication data processing system, a computer device, or a similar computing device. Taking an example of the application running on a communication data processing system, fig. 1 is a hardware structure block diagram of a communication data processing system implementing an artificial intelligence based data processing method according to an embodiment of the application. As shown in fig. 1, communication data processing system 10 may include one or more (only one shown in fig. 1) processors 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data, and optionally may also include a transmission device 106 for communication functions. Those skilled in the art will appreciate that the configuration shown in FIG. 1 is illustrative only and is not intended to limit the configuration of a communications data processing system described above. For example, communication data processing system 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the artificial intelligence based data processing method in the embodiment of the present application, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, i.e. implementing the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which may be connected to communication 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 device 106 is used for receiving or transmitting data via a network. Specific examples of such networks may include wireless networks provided by communication providers of communication data processing system 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
Based on this, please refer to fig. 2, fig. 2 is a schematic flowchart of a data processing method based on artificial intelligence according to an embodiment of the present invention, the method is applied to a communication data processing system, and further includes the following steps 10 and 20.
In the embodiment of the application, the target industrial production communication data can be understood as data generated by mutual interaction between the communication data processing system and the industrial production equipment in the communication process. Such as: production feedback data, production instruction data, production flow data, and the like. The key task description analysis of the target industrial production communication data can be understood as the production characteristic information extraction of the target industrial production communication data. Further, the first key task description can be understood as a feature vector obtained by extracting production feature information of the target industrial production communication data, and the feature vector is used for representing more key production features. The production demand analysis model is obtained by performing combined debugging in combination with a topological structure processing model, wherein the combined topological structure processing model can be a Convolutional Neural Network (CNN) or a graph convolutional neural network (GCN).
In one possible embodiment, the debugging instance of the production demand analysis model includes a first set number of instance industrial production communication data. Further, the debugging step of the production demand analysis model may specifically include the contents recorded in steps 11 to 14.
And 11, carrying out artificial intelligence-based data processing on the first set number of example industrial production communication data through the production demand analysis model to obtain a third key task description corresponding to each example industrial production communication data.
And 12, carrying out artificial intelligence-based data processing on the first set number of example industrial production communication data through the topological structure processing model to obtain a fourth key task description corresponding to each example industrial production communication data.
In a possible embodiment, the data processing based on artificial intelligence is performed on the first set number of example industrial production communication data through the topological structure processing model recorded in step 12, so as to obtain a fourth mission critical description corresponding to each example industrial production communication data, which may exemplarily include the content recorded in step 121 and step 122.
And 121, performing staged key task description analysis on the first set number of example industrial production communication data through the topological structure processing model to obtain a first staged key task description and a second staged key task description corresponding to each example industrial production communication data.
For example, a staged mission critical description may be understood as a local mission critical description.
And step 122, merging the first phased key task description and the second phased key task description corresponding to each example industrial production communication data to obtain a fourth key task description corresponding to each example industrial production communication data.
In the embodiment of the application, the step-wise mission-critical description parsing of the example industrial production communication data can be understood as carrying out hierarchical feature extraction on the example industrial production communication data. The staged key task description can be obtained by carrying out hierarchical characteristic extraction on example industrial production communication data, wherein the first staged key task description and the second staged key task description are mainly used for distinguishing the staged key task description, and further, the staged key task description can also be understood as a local characteristic.
And step 13, determining expected differences of the first model according to the third key task description and the fourth key task description corresponding to each example industrial production communication data.
For example, the model expected difference can be understood as a model loss function.
In one possible embodiment, the first model expected difference comprises a first expected difference. Determining the expected difference of the first model according to the third key task description and the fourth key task description corresponding to each example industrial production communication data recorded in step 13 may specifically include the contents recorded in steps 131 to 133.
Step 131, performing full-connection processing (which may be understood as classification processing) on the first set number of example industrial production communication data according to the third key task description corresponding to each example industrial production communication data, and determining a first full-connection processing estimation result corresponding to each example industrial production communication data.
Step 132, performing full-connection processing on the first set number of example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data, and determining a second full-connection processing estimation result corresponding to each example industrial production communication data.
In a possible embodiment, the step 132 of performing full-connection processing on the first set number of example industrial production communication data according to the fourth mission-critical description corresponding to each example industrial production communication data, and determining a second full-connection processing estimation result corresponding to each example industrial production communication data may specifically include the following steps: determining the distribution of the basic key task description corresponding to each example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data;
performing key task description induction (which can be understood as feature aggregation) on the basic key task description distribution corresponding to each example industrial production communication data by using the topological structure processing model to obtain induced key task description corresponding to each example industrial production communication data;
and performing full-connection processing on the first set number of example industrial production communication data according to the generalized key task description corresponding to each example industrial production communication data, and determining the second full-connection processing estimation result corresponding to each example industrial production communication data.
In the embodiment of the present application, the basic mission critical description distribution may be understood as an initial feature connectivity graph. In this way, the accuracy of the second full-connection process estimation result can be ensured.
Step 133, determining the first expected difference (loss) according to the first full connection processing estimation result and the second full connection processing estimation result corresponding to each example industrial production communication data.
When the steps 131 to 133 are performed, the full connection processing is performed on the example industrial production communication data, and the first expected difference is determined based on the estimation result of the full connection processing, so that the accuracy of the first expected difference can be ensured.
In one possible embodiment, the first model expected difference comprises a second expected difference. Determining the expected difference of the first model according to the third key task description and the fourth key task description corresponding to each example industrial production communication data recorded in step 13, which may specifically include the following: determining a first target key task description distribution corresponding to each example industrial production communication data according to the third key task description corresponding to each example industrial production communication data; determining second target key task description distribution corresponding to each example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data; determining the second expected difference according to the first target mission critical description distribution and the second target mission critical description distribution corresponding to each example industrial production communication data. In this way, the accuracy of the second desired difference can be ensured.
In a possible embodiment, the updating the production demand analysis model according to the expected difference of the first model specifically may include: updating the production demand analysis model with the first expected difference and/or the second expected difference.
In a possible embodiment, the determining, according to the fourth mission critical description corresponding to each example industrial production communication data, the second target mission critical description distribution corresponding to each example industrial production communication data, which is recorded as above, may exemplarily include: determining the fourth key task description corresponding to each example industrial production communication data as a key task description unit corresponding to each example industrial production communication data to obtain a first set number of key task description units; determining a second set number of tight key task description units with the smallest quantization difference with a target key task description unit as a first type of tight key task description units corresponding to the target key task description unit, wherein the target key task description unit is a key task description unit corresponding to target example industrial production communication data, and the target example industrial production communication data is one of the example industrial production communication data; determining a third set number of tight key task description units with the smallest quantization difference with each first type of tight key task description unit as a second type of tight key task description unit corresponding to the target key task description unit; determining basic key task description distribution corresponding to the target example industrial production communication data according to the first type of tight key task description unit and the second type of tight key task description unit; and determining second target key task description distribution corresponding to the target example industrial production communication data according to the basic key task description distribution corresponding to the target example industrial production communication data.
In the embodiment of the present application, the close mission critical description unit may be understood as a mission critical description unit having the smallest quantization difference with the target mission critical description unit. In this way, the second target mission critical description distribution is determined by determining the tight mission critical description unit, so that the comprehensiveness of the second target mission critical description distribution can be improved.
In one possible embodiment, the base mission critical description distribution corresponding to the target example industrial production communication data includes a first mission critical description unit sequence and a first association description list. Based on this, the determining, according to the first type of close key task description unit and the second type of close key task description unit, the basic key task description distribution corresponding to the target example industrial production communication data may specifically include: according to the target key task description units, performing dimensionless processing (which can also be understood as normalization processing) on the first set number of key task description units to obtain a first set number of key task description units subjected to dimensionless processing; generating a first key task description unit sequence according to the first set number of key task description units subjected to dimension removal processing, including a first type of tight key task description unit subjected to dimension removal processing and a second type of tight key task description unit subjected to dimension removal processing; for an a-th key task description unit in the first key task description unit sequence, determining b close key task description units with minimum quantization difference with the a-th key task description unit in the first set number of key task description units after the de-dimension processing; determining a mission-critical description association tag between the a-th mission-critical description unit and a c-th close mission-critical description unit, wherein the c-th close mission-critical description unit is a mission-critical description unit present in the first sequence of mission-critical description units; and determining the first association description list (which can also be understood as an adjacent feature matrix) according to the upstream and downstream association corresponding to each key task description unit in the first key task description unit sequence.
In the embodiment of the application, a set number of key task description units are subjected to de-dimension processing one by one to obtain a first key task description unit sequence, and then a first association description list can be determined quickly and accurately according to the association relation corresponding to each key task description unit in the first key task description unit sequence.
In a possible embodiment, the second target mission critical description distribution comprises a second sequence of mission critical description units and a second list of association descriptions. Based on this, the above-described determining the second target key task description distribution corresponding to the target example industrial production communication data according to the base key task description distribution corresponding to the target example industrial production communication data may exemplarily include: loading the key task description units which do not exist in the first key task description unit sequence in the first set number of key task description units after the dimension removal processing into the first key task description unit sequence, and generating a second key task description unit sequence; for a non-critical task description unit in the second sequence of critical task description units, determining a close critical task description unit corresponding to the non-critical task description unit from the first set number of critical task description units after the dimensionless processing, where the non-critical task description unit (which may also be understood as a task description unit with lower importance) is one of the critical task description units that is not present in the first sequence of critical task description units in the first set number of critical task description units after the dimensionless processing; determining a non-critical task description association tag between the non-critical task description unit and a close critical task description unit corresponding to the non-critical task description unit; and determining the second association description list according to the upstream and downstream association corresponding to each key task description unit in the second key task description unit sequence.
In this way, a second key task description unit sequence is produced through key task description units which are not in the first key task description unit sequence in the key task description units after the dimensionless processing, false task description units in the key task description unit sequence are determined, and then a second association description list is determined in a targeted mode according to the false task description units.
Step 14, updating (optimizing or improving) the production demand analysis model according to the expected difference of the first model.
In the embodiments of the present application, the example industrial production communication data may be understood as sample industrial production communication data. The model expectation variance can be understood as a network loss. In this way, when the steps 11 to 14 are performed, the stability of the production demand analysis model can be ensured by continuously updating the production demand analysis model, and the accuracy of performing the key task description analysis on the target industrial production communication data can be further improved.
In a possible embodiment, the debugging example further includes an actual annotation corresponding to each of the example industrial production communication data, and the second fully-connected processing estimation result corresponding to each of the example industrial production communication data includes an estimation annotation corresponding to each of the example industrial production communication data. Based on this, the method for debugging the production demand analysis model may further include the following steps: determining a second model expected difference from the actual annotation (true tag) and the estimated annotation (predicted tag) corresponding to each of the example industrial production communication data; and updating the topological structure processing model according to the expected difference of the second model. Thus, the expected difference of the second model is determined according to the actual annotation and the estimated annotation, and the topological structure processing model is updated according to the expected difference of the second model. Therefore, the method can improve the state of keeping the latest model configuration in the production demand analysis model implementation, and can also improve the robustness of the production demand analysis model.
And 20, performing key task description pairing on the first key task description and a plurality of second key task descriptions existing in a key task description set to obtain production demand information corresponding to the target industrial production communication data.
In the embodiment of the present application, the set of mission critical descriptions may be understood as a library of mission critical descriptions set in advance. Mission critical description pairing may be understood as mission critical description matching. The second key task descriptions are obtained by performing key task description analysis on the historical industrial production communication data by using the production demand analysis model. The production demand information can be understood as content obtained by performing key task description analysis on target industrial production communication data through a production demand analysis model, such as: user preferences or user requirements such as parameter indexes set by the user for the production pattern.
In one possible embodiment, there is an annotation corresponding to each historical industrial production communication data; the key task description pairing is performed on the first key task description and a plurality of second key task descriptions existing in a key task description set to obtain production demand information corresponding to the target industrial production communication data, and the example may include: determining a mission critical description commonality index between the first mission critical description and each of the second mission critical descriptions; determining the second key task description with the key task description commonality index being greater than a specified judgment value (a set threshold) as a target second key task description successfully paired with the first key task description; and determining the annotation of the historical industrial production communication data corresponding to the target second key task description as the production demand information.
In the embodiment of the present application, the mission critical description commonality index may be understood as a feature similarity between the first mission critical description and each of the second mission critical descriptions. Therefore, the production demand information with higher precision and reliability can be determined, and the analysis quality of the production demand analysis is obviously improved to a certain extent.
In summary, the production demand analysis model is obtained based on joint debugging of the topological structure processing model, so that the production demand analysis model can achieve summarization of key task descriptions, a first key task description obtained by performing key task description analysis on target industrial production communication data through the production demand analysis model and a plurality of second key task descriptions obtained by performing key task description analysis on a plurality of historical industrial production communication data through the production demand analysis model existing in a key task description set can be paired accurately and completely, similar key task descriptions can be paired as far as possible, production demand information with higher precision and reliability can be determined, and the analysis quality of production demand analysis is improved to a certain extent.
An embodiment of the present application further provides a cloud platform, where the cloud platform includes a readable storage medium storing a program to execute the method.
Further, a readable storage medium is provided, on which a program is stored, which when executed by a processor implements the method described above.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. 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 application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a media service server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and 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 a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (9)
1. An artificial intelligence based data processing method, applied to a communication data processing system, the method comprising:
performing key task description analysis on target industrial production communication data through a production demand analysis model to obtain a first key task description corresponding to the target industrial production communication data, wherein the production demand analysis model is obtained by performing joint debugging in combination with a topological structure processing model;
performing key task description pairing on the first key task description and a plurality of second key task descriptions existing in a key task description set to obtain production demand information corresponding to the target industrial production communication data, wherein the plurality of second key task descriptions are obtained by performing key task description analysis on a plurality of historical industrial production communication data by using the production demand analysis model; the debugging examples of the production demand analysis model comprise a first set number of example industrial production communication data; the debugging step of the production demand analysis model comprises the following steps:
carrying out artificial intelligence-based data processing on the first set number of example industrial production communication data through the production demand analysis model to obtain a third key task description corresponding to each example industrial production communication data;
carrying out data processing based on artificial intelligence on the first set number of example industrial production communication data through a topological structure processing model to obtain a fourth key task description corresponding to each example industrial production communication data, wherein the step of carrying out data processing based on artificial intelligence on the first set number of example industrial production communication data through the topological structure processing model to obtain the fourth key task description corresponding to each example industrial production communication data comprises the following steps: performing staged key task description analysis on the first set number of example industrial production communication data through the topological structure processing model to obtain a first staged key task description and a second staged key task description corresponding to each example industrial production communication data; merging the first phased key task description and the second phased key task description corresponding to each example industrial production communication data to obtain a fourth key task description corresponding to each example industrial production communication data;
determining a first model expected difference according to the third key task description and the fourth key task description corresponding to each example industrial production communication data;
updating the production demand analysis model according to the expected difference of the first model;
wherein, annotations exist corresponding to each historical industrial production communication data; the key task description pairing the first key task description and a plurality of second key task descriptions existing in a key task description set to obtain production demand information corresponding to the target industrial production communication data includes:
determining a mission critical description commonality index between the first mission critical description and each of the second mission critical descriptions;
determining the second key task description with the key task description commonality index being greater than a specified judgment value as a target second key task description successfully paired with the first key task description;
and determining the annotation of the historical industrial production communication data corresponding to the target second key task description as the production demand information.
2. The method of claim 1, in which the first model expected difference comprises a first expected difference; the determining a first model expected difference according to the third key task description and the fourth key task description corresponding to each example industrial production communication data comprises:
according to the third key task description corresponding to each example industrial production communication data, performing full connection processing on the first set quantity of example industrial production communication data, and determining a first full connection processing estimation result corresponding to each example industrial production communication data;
according to the fourth key task description corresponding to each example industrial production communication data, performing full connection processing on the first set number of example industrial production communication data, and determining a second full connection processing estimation result corresponding to each example industrial production communication data;
determining the first expected difference according to the first full connection processing estimation result and the second full connection processing estimation result corresponding to each example industrial production communication data;
wherein, the performing full-connection processing on the first set number of example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data, and determining a second full-connection processing estimation result corresponding to each example industrial production communication data includes: determining the distribution of the basic key task description corresponding to each example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data; performing key task description induction on the basic key task description distribution corresponding to each example industrial production communication data by using the topological structure processing model to obtain induced key task description corresponding to each example industrial production communication data; and performing full-connection processing on the first set number of example industrial production communication data according to the generalized key task description corresponding to each example industrial production communication data, and determining the second full-connection processing estimation result corresponding to each example industrial production communication data.
3. The method of claim 2, in which the first model expected difference comprises a second expected difference; the determining a first model expected difference according to the third key task description and the fourth key task description corresponding to each example industrial production communication data comprises:
determining a first target key task description distribution corresponding to each example industrial production communication data according to the third key task description corresponding to each example industrial production communication data;
determining second target key task description distribution corresponding to each example industrial production communication data according to the fourth key task description corresponding to each example industrial production communication data;
determining the second expected difference according to the first target mission critical description distribution and the second target mission critical description distribution corresponding to each example industrial production communication data.
4. The method of claim 3, wherein said updating said production demand analysis model as a function of said first model expected differences comprises: updating the production demand analysis model by the first expected difference and/or the second expected difference;
wherein the determining a second target mission critical description distribution corresponding to each example industrial production communication data according to the fourth mission critical description corresponding to each example industrial production communication data includes:
determining the fourth key task description corresponding to each example industrial production communication data as a key task description unit corresponding to each example industrial production communication data to obtain a first set number of key task description units;
determining a second set number of close key task description units with the smallest quantization difference with a target key task description unit as first type of close key task description units corresponding to the target key task description unit, wherein the target key task description unit is a key task description unit corresponding to target example industrial production communication data, and the target example industrial production communication data is one of a plurality of example industrial production communication data;
determining a third set number of tight key task description units with the smallest quantization difference with each first type of tight key task description unit as a second type of tight key task description unit corresponding to the target key task description unit;
determining basic key task description distribution corresponding to the target example industrial production communication data according to the first type of close key task description unit and the second type of close key task description unit;
and determining second target key task description distribution corresponding to the target example industrial production communication data according to the basic key task description distribution corresponding to the target example industrial production communication data.
5. The method of claim 4, wherein a base mission critical description distribution corresponding to the target example industrial production communication data includes a first sequence of mission critical description units and a first list of association descriptions;
the determining of the basic key task description distribution corresponding to the target example industrial production communication data according to the first type of tight key task description unit and the second type of tight key task description unit includes:
according to the target key task description units, performing dimensionless processing on the key task description units with the first set number to obtain key task description units with the first set number after the dimensionless processing;
generating a first key task description unit sequence according to the first set number of key task description units subjected to dimension removal processing, including a first type of tight key task description unit subjected to dimension removal processing and a second type of tight key task description unit subjected to dimension removal processing;
for an a-th key task description unit in the first key task description unit sequence, determining b close key task description units with minimum quantization difference with the a-th key task description unit in the first set number of key task description units after the de-dimension processing;
determining a mission-critical description association tag between the a-th mission-critical description unit and a c-th close mission-critical description unit, wherein the c-th close mission-critical description unit is a mission-critical description unit present in the first sequence of mission-critical description units;
and determining the first association description list according to the upstream and downstream association corresponding to each key task description unit in the first key task description unit sequence.
6. The method of claim 5, wherein the second target mission critical description distribution includes a second sequence of mission critical description units and a second list of association descriptions; the determining the second target mission critical description distribution corresponding to the target example industrial production communication data according to the base mission critical description distribution corresponding to the target example industrial production communication data includes:
loading the key task description units which do not exist in the first key task description unit sequence in the first set number of key task description units after the dimension removal processing into the first key task description unit sequence, and generating a second key task description unit sequence;
for a non-critical task description unit in the second critical task description unit sequence, determining a compact critical task description unit corresponding to the non-critical task description unit in the first set number of critical task description units after the dimensionless processing, wherein the non-critical task description unit is one of the critical task description units which are not in the first critical task description unit sequence and are in the first set number of critical task description units after the dimensionless processing;
determining a non-critical task description association tag between the non-critical task description unit and a close critical task description unit corresponding to the non-critical task description unit;
and determining the second association description list according to the upstream and downstream association corresponding to each key task description unit in the second key task description unit sequence.
7. The method of claim 3, wherein the debugging instance further comprises actual annotations corresponding to each of the instance industrial production communication data, and wherein the second fully-connected process estimation results corresponding to each of the instance industrial production communication data comprise estimation annotations corresponding to each of the instance industrial production communication data;
the debugging method of the production demand analysis model further comprises the following steps: determining a second model expected difference according to the actual annotation and the estimated annotation corresponding to each example industrial production communication data; updating the topology processing model in accordance with the second model expected difference.
8. A communications data processing system comprising a processor and a memory; the processor is connected in communication with the memory, and the processor is configured to read the computer program from the memory and execute the computer program to implement the method of any one of claims 1 to 7.
9. A cloud platform comprising a readable storage medium storing a program to perform the method recited in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210317932.3A CN114638117B (en) | 2022-03-29 | 2022-03-29 | Data processing method and system based on artificial intelligence and cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210317932.3A CN114638117B (en) | 2022-03-29 | 2022-03-29 | Data processing method and system based on artificial intelligence and cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114638117A CN114638117A (en) | 2022-06-17 |
| CN114638117B true CN114638117B (en) | 2022-11-08 |
Family
ID=81952483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210317932.3A Active CN114638117B (en) | 2022-03-29 | 2022-03-29 | Data processing method and system based on artificial intelligence and cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638117B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932571A (en) * | 2017-05-24 | 2018-12-04 | 龙岩烟草工业有限责任公司 | The setting method and device of cigarette primary processing initial technological parameter |
| CN108985617A (en) * | 2018-07-11 | 2018-12-11 | 广东人励智能工程有限公司 | A kind of product manufacturing process dispatching method and system based on intelligence manufacture |
| CN110435105A (en) * | 2019-08-12 | 2019-11-12 | 上海智引信息科技有限公司 | The system and method for plastic shaping optimal procedure parameters intelligent recommendation control are realized based on quality information |
| CN110675055A (en) * | 2019-09-23 | 2020-01-10 | 广东工业大学 | Automatic production line modeling and layout planning method and system |
| CN113792147A (en) * | 2021-09-18 | 2021-12-14 | 北京理工大学 | Method, device and equipment for predicting product design parameters based on user requirements |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19718262A1 (en) * | 1997-04-30 | 1998-11-05 | Schenck Panel Production Syste | Method and system for generating a process model of a technical problem |
| EP1647927A1 (en) * | 2004-10-15 | 2006-04-19 | Sap Ag | New product demand forecasting |
| US10789561B2 (en) * | 2011-11-21 | 2020-09-29 | Hewlett-Packard Development Company, L.P. | Recommending production plans |
| CN112001527B (en) * | 2020-07-29 | 2024-01-30 | 中国计量大学 | Industrial production process target data prediction method of multi-feature fusion depth neural network |
-
2022
- 2022-03-29 CN CN202210317932.3A patent/CN114638117B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932571A (en) * | 2017-05-24 | 2018-12-04 | 龙岩烟草工业有限责任公司 | The setting method and device of cigarette primary processing initial technological parameter |
| CN108985617A (en) * | 2018-07-11 | 2018-12-11 | 广东人励智能工程有限公司 | A kind of product manufacturing process dispatching method and system based on intelligence manufacture |
| CN110435105A (en) * | 2019-08-12 | 2019-11-12 | 上海智引信息科技有限公司 | The system and method for plastic shaping optimal procedure parameters intelligent recommendation control are realized based on quality information |
| CN110675055A (en) * | 2019-09-23 | 2020-01-10 | 广东工业大学 | Automatic production line modeling and layout planning method and system |
| CN113792147A (en) * | 2021-09-18 | 2021-12-14 | 北京理工大学 | Method, device and equipment for predicting product design parameters based on user requirements |
Non-Patent Citations (2)
| Title |
|---|
| A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks;M. Nuruzzaman et al;《2018 IEEE 15th International Conference on e-Business Engineering (ICEBE)》;20181231;第54-61页 * |
| 基于构件的制造执行系统产品线关键技术研究;任守纲;《中国博士学位论文全文数据库 (工程科技Ⅱ辑)》;20050515;第C029-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114638117A (en) | 2022-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Verwer et al. | Learning decision trees with flexible constraints and objectives using integer optimization | |
| US20180336207A1 (en) | Data clustering | |
| CN113608882B (en) | Information processing method and system based on artificial intelligence and big data and cloud platform | |
| CN109933778B (en) | Word segmentation method, word segmentation device and computer readable storage medium | |
| CN110866029B (en) | sql statement construction method, device, server and readable storage medium | |
| CN111538766A (en) | Text classification method, device, processing equipment and bill classification system | |
| Alalfi et al. | Semi-automatic identification and representation of subsystem variability in simulink models | |
| CN111400681A (en) | Data permission processing method, device and equipment | |
| CN114821045A (en) | Semantic segmentation method and device, electronic equipment and storage medium | |
| Hoekstra | The knowledge reengineering bottleneck | |
| CN114638117B (en) | Data processing method and system based on artificial intelligence and cloud platform | |
| Kozmina et al. | Information requirements for big data projects: A review of state-of-the-art approaches | |
| CN111125332B (en) | Method, device, equipment and storage medium for calculating TF-IDF value of word | |
| CN110765276A (en) | Entity alignment method and device in knowledge graph | |
| CN108595395B (en) | Nickname generation method, device and equipment | |
| CN115718879A (en) | Data governance method, device and storage medium | |
| Alalfi et al. | Variability identification and representation for automotive Simulink models | |
| CN115271407A (en) | Industrial Internet data processing method and system based on artificial intelligence | |
| CN114691875A (en) | Data classification and classification processing method and device | |
| CN113468604A (en) | Big data privacy information analysis method and system based on artificial intelligence | |
| CN114816512B (en) | Resource pool construction method and system and cloud platform | |
| Grigori et al. | Service retrieval based on behavioral specification | |
| CN112085522A (en) | Construction cost data processing method, system, device and medium for engineering project | |
| CN113010642B (en) | Semantic relation recognition method and device, electronic equipment and readable storage medium | |
| Rodriguez et al. | A novel unsupervised learning approach for assessing web services refactoring |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221018 Address after: Room 2007, No. 93, Hubin East Road, Siming District, Xiamen City, Fujian Province, 361000 (address for service of legal documents) Applicant after: Xiamen Lianjian Technology Co.,Ltd. Address before: No. 44, Beijing Road, Panlong District, Kunming, Yunnan 650000 Applicant before: Shi Kunhong |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |