Disclosure of Invention
In order to solve the technical problems in the related art, the invention provides a method and a system for sharing industrial internet data.
In a first aspect, an embodiment of the present invention provides a method for sharing industrial internet data, which is applied to a data sharing system, and the method includes:
the method comprises the steps of obtaining a plurality of groups of industrial internet data of an industrial internet data set to be shared, carrying out shared data induction processing on the plurality of groups of industrial internet data to obtain a first common data type of the plurality of groups of industrial internet data, wherein the first common data type comprises local industrial internet data corresponding to a data sharing event and cloud industrial internet data corresponding to the data sharing event;
analyzing the data sharing event based on the local industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the local industrial internet data corresponding to the data sharing event; analyzing the data sharing event based on the cloud industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the cloud industrial internet data corresponding to the data sharing event;
and determining a data sharing indication label of the industrial internet data set to be shared based on the first data induction knowledge characteristic.
Optionally, the induction processing of shared data on the multiple groups of industrial internet data to obtain a first common data category of the multiple groups of industrial internet data includes:
carrying out data sharing event identification on the industrial internet data to obtain at least one data sharing event window;
determining a global credibility score of the data sharing event window based on the credibility score of the data sharing event window, the correlation degree of the data sharing event window and a designated data area of the industrial internet data and the proportion of the coverage range of the data sharing event window in the industrial internet data;
and taking the common data type corresponding to the data sharing event window with the maximum global credibility score as the first common data type of the industrial internet data.
Optionally, each first feature member in the first data induction knowledge features corresponds to a second generic data category, and the feature value of the first feature member indicates a credibility score of the industrial internet data for the second generic data category corresponding to the first feature member.
Optionally, the determining a data sharing indication tag of the industrial internet data set to be shared based on the first data induction knowledge characteristic includes:
the industrial internet data corresponding to the first data induction knowledge characteristics are induced into at least one second common data category based on the first data induction knowledge characteristics; each second common data category corresponds to an industrial internet data queue;
determining the industrial internet data set to be shared as a credibility score of a second common data category corresponding to the industrial internet data queue based on the first data induction knowledge characteristics of each industrial internet data in the industrial internet data queue;
determining a data sharing indication label of the industrial Internet data set to be shared based on the credible score of the second generic data category.
Optionally, the inducing industrial internet data corresponding to the first data induction knowledge characteristic to be at least one second common data category based on the first data induction knowledge characteristic includes:
obtaining a data induction variable;
comparing and analyzing the characteristic value of each first characteristic member in the first data induction knowledge characteristic with the size of the data induction variable;
and if the characteristic value of the first characteristic member is higher than the data induction variable, the industrial internet data corresponding to the first data induction knowledge characteristic is induced into a second common data category corresponding to the first characteristic member.
Optionally, the method further includes: analyzing the keywords of the data sharing event based on the local industrial internet data corresponding to the data sharing event to obtain a keyword credibility score of the keywords of the data sharing event in the local industrial internet data corresponding to the data sharing event; determining an influence index of local industrial internet data corresponding to the data sharing event based on the keyword credibility score;
the determining that the to-be-shared industrial internet data set is the credibility score of the second common data category corresponding to the industrial internet data queue based on the first data induction knowledge characteristics of each industrial internet data in the industrial internet data queue comprises: fusing first data induction knowledge characteristics of local industrial internet data corresponding to the data sharing events in an industrial internet data queue based on the influence indexes of the local industrial internet data corresponding to the data sharing events to obtain first fused data induction knowledge characteristics; and determining the industrial Internet data set to be shared as a credibility score of a second common data type corresponding to the industrial Internet data queue based on the first fused data induction knowledge characteristics.
Optionally, the determining, based on the keyword confidence score, an influence index of local industrial internet data corresponding to the data sharing event includes:
obtaining an influence index judgment value;
when the keyword credibility score is not smaller than the influence index judgment value, determining an influence index of local industrial internet data corresponding to the data sharing event based on the influence index judgment value and the keyword credibility score, wherein the first influence index is a first influence index;
when the credible keyword score is smaller than the influence index judgment value, setting a set influence index as the influence index of the local industrial internet data corresponding to the data sharing event; wherein the set impact index is not higher than the first impact index.
Optionally, the method further includes: acquiring a data description field of the industrial internet data set to be shared; determining a first quantitative evaluation based on the data description field, wherein the value of the first quantitative evaluation is related to the accumulated value of the type description field with the second generic data type in the data description field;
the determining that the to-be-shared industrial internet data set is the credibility score of the second common data category corresponding to the industrial internet data queue based on the first data induction knowledge characteristics of each industrial internet data in the industrial internet data queue comprises: determining the industrial internet data set to be shared as a first credibility score of a second common data category corresponding to the industrial internet data queue based on the first data induction knowledge characteristics of each industrial internet data in the industrial internet data queue; and determining the industrial Internet data set to be shared as the credibility score of the second common data type corresponding to the industrial Internet data queue based on the first quantitative evaluation and the first credibility score of the second common data type.
Optionally, the determining a first quantitative evaluation based on the data description field includes:
matching the data description field of the industrial internet data set to be shared with the second generic data type to obtain the accumulated value of the type description field of each second generic data type in the data description field;
and determining a first quantitative evaluation of each second generic data type based on the accumulated value, wherein the first quantitative evaluation and the accumulated value have a set mapping relation.
Optionally, the determining, based on the confidence score of the second generic data category, a data sharing indication tag of the industrial internet data set to be shared includes:
obtaining a data induction judgment value;
comparing and analyzing the credibility score of the second generic data with the data induction judgment value;
and determining the second common data category with the credibility score higher than the data induction judgment value as the data sharing indication label of the industrial Internet data set to be shared.
In a second aspect, the present invention also provides a data sharing system, including a processor and a memory; the processor is connected with the memory in communication, and the processor is used for reading the computer program from the memory and executing the computer program to realize the method.
The technical scheme provided by the embodiment of the invention obtains a plurality of groups of industrial internet data of an industrial internet data set to be shared; carrying out shared data induction processing on the plurality of groups of industrial internet data to obtain a first common data type of the plurality of groups of industrial internet data, wherein the first common data type comprises local industrial internet data corresponding to a data sharing event and cloud industrial internet data corresponding to the data sharing event; analyzing the data sharing event based on the local industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the local industrial internet data corresponding to the data sharing event; analyzing the data sharing event based on the cloud industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the cloud industrial internet data corresponding to the data sharing event; and determining a data sharing indication label of the industrial internet data set to be shared based on the first data induction knowledge characteristic.
By means of the design, independent data induction knowledge characteristic mining is carried out by combining the local industrial internet data corresponding to the data sharing event and the cloud industrial internet data corresponding to the data sharing event, two first data induction knowledge characteristics focusing on the local industrial internet data and the cloud industrial internet data can be obtained, the data sharing indication label of the industrial internet data set to be shared is further determined through the first data induction knowledge characteristics, the defect that the whole checking range of data sharing knowledge label matching of the industrial internet data set is poor can be overcome, the corresponding data sharing indication label can be configured for the industrial internet data set to be shared so as to achieve processing of the industrial internet data set to be shared, and subsequent targeted and safe data sharing processing can be conveniently carried out according to the data sharing indication label.
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 invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided by the embodiments of the present invention may be executed in a data sharing system, a computer device, or a similar computing device. Taking the example of operating on a data sharing system, the data sharing system 10 may include one or more processors 102 (the processors 102 may include, but are not limited to, processing devices 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. It will be understood by those of ordinary skill in the art that the above-described structure is merely illustrative and is not intended to limit the structure of the data sharing system. For example, the data sharing system 10 may also include more or fewer components than shown above, or have a different configuration than shown above.
The memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a method for sharing industrial internet data in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, 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, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the data sharing 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 the data sharing 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. 1, where fig. 1 is a schematic flowchart of a method for sharing industrial internet data according to an embodiment of the present invention, the method is applied to a data sharing system, and further includes the following technical solutions.
STEP101, obtain several groups of industrial Internet data sets to be shared.
In the embodiment of the present invention, the industrial internet data set to be shared may be any kind of industrial internet data set. The industrial internet data set may be an operation data set of a digital factory, or a security detection data set of an intelligent production line, which is not limited herein.
In some examples, the to-be-shared industrial internet data set may be called from a setting database, or received through a setting data transmission interface, such as calling the to-be-shared industrial internet data set from a setting relational database, or receiving the to-be-shared industrial internet data set transmitted by a data sharing terminal through a GUI data transmission interface, or the like.
Further, the obtaining of the sets of industrial internet data of the industrial internet data set to be shared includes: and carrying out data sampling on the industrial internet data set to be shared based on the data sampling step length to obtain the plurality of groups of industrial internet data. For example, the industrial internet DATA set to be shared is subjected to DATA sampling based on step lengths of 2 groups of industrial internet DATA/second, and an industrial internet DATA set DATA = [ DATA1, DATA 2., DATAn ] is obtained, where n reflects the number of industrial internet DATA.
Further, in order to facilitate the resolution of the data sharing event in the industrial internet data, adaptive processing of the industrial internet data may be further included in this step. For example, at this step, the industrial internet data is normalized to a set window size (e.g., a window with a horizontal constraint of M and a vertical constraint of N).
Further, the method for sharing industrial internet data further comprises the following steps.
The STEP102, carrying out induction processing on the shared data of the plurality of groups of industrial internet data to obtain a first common data type of the plurality of groups of industrial internet data.
In an embodiment of the present invention, the first common data category includes local industrial internet data corresponding to the data sharing event and cloud industrial internet data corresponding to the data sharing event.
The first common data category is that the industrial internet data is summarized into local industrial internet data corresponding to a data sharing event comprising the local data characteristic of the data sharing event and cloud industrial internet data corresponding to a data sharing event comprising the cloud data characteristic of the data sharing event.
The local industrial internet data correspond to the operation data of the local intelligent factory, and the cloud industrial internet data correspond to the operation data of the remote/allopatric intelligent factory. Further, the data sharing event includes a fault recovery record sharing event, a safety precaution report sharing event and the like, and a series of events related to intelligent production and industrial internet, and those skilled in the art know that the data sharing event may correspond to a part of a data set.
In order to avoid an analysis error caused by a high proportion of non-data sharing events when a plurality of data sharing events exist in the industrial internet data, the STEP102 further includes the following contents.
STEP201, data sharing event identification is carried out on the industrial internet data to obtain at least one data sharing event window.
STEP202, determining a global credibility score of the data sharing event window based on the credibility score of the data sharing event window, the correlation degree of the data sharing event window and a designated data area of the industrial internet data and the proportion of the coverage range of the data sharing event window in the industrial internet data.
STEP203, using the common data type corresponding to the data sharing event window with the maximum global credibility score as the first common data type of the industrial internet data.
In the embodiment of the present invention, the STEP201 may be implemented by a deep learning network (DNN) that is successfully debugged in advance. The deep learning network (DNN) is used for identifying industrial internet data of two common data types, namely local industrial internet data and cloud industrial internet data. In practical implementation, if the identification result of certain industrial internet data is an empty set, the group does not contain a data sharing event, and therefore the group can be deleted. And if the identification result of certain industrial internet data is a non-empty set, outputting not less than one data sharing event window by a deep learning network (DNN).
In STEP202, each data output by the deep learning network shares the global credibility score of the event window, and at least one global credibility score (comprehensive confidence) is obtained.
In STEP203, the at least one global credible score is sorted based on a descending order, and the common data type corresponding to the data sharing event window with the maximum global credible score is used as the first common data type of the industrial Internet data.
In STEP201-STEP203, by adding distribution area evaluation and coverage area ratio during data sharing event identification, shared data induction processing (such as data classification or data clustering) can be performed on the industrial internet data as accurately as possible when a plurality of data sharing event windows are identified.
In some examples, the industrial internet data sharing method may further include the following.
STEP103, analyzing the data sharing event based on the local industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the local industrial internet data corresponding to the data sharing event.
The STEP104 analyzes the data sharing event based on the cloud industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the cloud industrial internet data corresponding to the data sharing event.
Further, for the STEP103, the naive bayes algorithm that inputs the industrial internet data summarized as the local industrial internet data corresponding to the data sharing event in the STEP102 into the local industrial internet data successfully debugged in advance is used for performing the shared data summarization processing on the industrial internet data through the local industrial internet data corresponding to the data sharing event.
Further, for the STEP104, the industrial internet data summarized as the cloud industrial internet data corresponding to the data sharing event in the STEP102 is input into a naive bayesian algorithm of cloud industrial internet data successfully debugged in advance, and the naive bayesian algorithm of the cloud industrial internet data is used for carrying out shared data summarization processing on the industrial internet data through the cloud industrial internet data corresponding to the data sharing event.
In some examples, to improve data processing efficiency, the industrial internet data entered into the naive bayes algorithm for the local industrial internet data or the naive bayes algorithm for the cloud industrial internet data can be a data set within a window of data sharing events obtained in the STEP 102.
Further, each first feature member (element) in the first data induction knowledge feature corresponds to a second generic data category, and the feature value of the first feature member represents the credibility score (confidence) of the industrial internet data for the second generic data category corresponding to the first feature member. For example, the first data induction knowledge feature is a normalized one-dimensional array output by a naive bayes algorithm of the local industrial internet data or a naive bayes algorithm of the cloud industrial internet data.
Through STEP103 and STEP104, the local industrial internet data corresponding to the data sharing event and the cloud industrial internet data corresponding to the data sharing event are respectively analyzed and classified to obtain a first data induction knowledge characteristic, processing of the cloud industrial internet data corresponding to the data sharing event is added on the basis of the local industrial internet data corresponding to the data sharing event, and therefore the global recall degree (such as recall rate) of classification of the industrial internet data set is improved.
In some possible examples, the method for sharing industrial internet data may further include the following.
STEP105, and determining a data sharing indication label of the industrial Internet data set to be shared based on the first data induction knowledge characteristic.
In STEP103 and STEP104, performing shared data induction processing on the industrial internet data of the industrial internet data set to be shared to identify that at least one first data induction knowledge characteristic is obtained, generally speaking, a plurality of first data induction knowledge characteristics are obtained, and in STEP105, determining a data sharing indication tag of the industrial internet data set to be shared by integrating the plurality of first data induction knowledge characteristics, for example, a second common data type of the industrial internet data set to be shared.
In some possible embodiments, the STEP105 further may include the content recorded by STEPs 301-303 as follows.
STEP301, summarizing the industrial internet data corresponding to the first data summarization knowledge characteristic into at least one second common data type based on the first data summarization knowledge characteristic; and each second generic data category corresponds to an industrial internet data queue.
STEP302, determining the industrial internet data set to be shared as a credibility score of a second common data category corresponding to the industrial internet data queue based on the first data induction knowledge characteristics of each industrial internet data in the industrial internet data queue.
STEP303, determining a data sharing indication tag of the industrial internet data set to be shared based on the credibility score of the second generic data category.
In the embodiment of the present invention, for the local industrial internet data corresponding to each data sharing event obtained through the STEP102 and the cloud industrial internet data corresponding to the data sharing event, a corresponding first data induction knowledge characteristic (data induction vector/data classification vector) can be obtained through the STEP103 or the STEP104, and through the data induction knowledge characteristic, the industrial internet data can be classified into not less than a second common data category, for example, the second common data category of the industrial internet data is determined by the feature value of the largest first feature member in the first data induction knowledge characteristic. In order to improve the accuracy of classification, a data induction variable can be set in advance, and shared data induction processing can be performed on the industrial internet data based on the data induction variable.
Further, the STEP301 may further include contents recorded by the following STEPs 401 to 403.
STEP401, data induction variables are obtained.
The data induction variable can be understood as a classification index or a clustering index.
STEP402, comparing and analyzing the feature value of each first feature member in the first data induction knowledge features with the size of the data induction variable.
STEP403, if the feature value of the first feature member is higher than the data induction variable, inducing the industrial internet data corresponding to the first data induction knowledge feature into a second generic data type corresponding to the first feature member.
By implementing STEP401-STEP403, the industrial internet data corresponding to each of the R second common data types can be obtained, that is, each second common data type corresponds to an industrial internet data queue, where the industrial internet data queue includes local industrial internet data corresponding to the data sharing event and/or cloud industrial internet data corresponding to the data sharing event.
In STEP302, a first global credibility score inductive knowledge feature of each second generic data type is determined, and further, the first global credibility score inductive knowledge feature is determined through a standardized idea after the first data inductive knowledge feature of each industrial internet data in the industrial internet data queue corresponding to the second generic data type is subjected to superposition processing (weighting).
For each second common data category, the confidence score of the second common data category may be determined, and then the second common data category corresponding to the greatest confidence score of the second common data category may be determined as the data sharing indication tag of the industrial internet data set to be shared in STEP 303.
In order to reduce the amount of computation, before the STEP302, the method may further include the following: and screening the second generic data type. Further, the screening comprises cleaning a second common data category with less data of the industrial internet. Further, a number limit value index2 is set, wherein the value range of the index2 is 0 to 1, so that the number threshold value can be obtained as follows: n index2, cleaning second common data types corresponding to the industrial internet data queues of which the number of the industrial internet data is smaller than the number threshold, and participating in the later steps of determining the first global credibility score induction knowledge characteristics and determining the credibility score of the second common data types by the remaining second common data types. The erroneous second generic data type can thus be purged to reduce the amount of certainty in determining the confidence score for the second generic data type.
For STEP303, since each second generic data category participating in the first global credibility score generalization knowledge characteristic determination obtains a corresponding class1, in this STEP, the size of all classes 1 may be comparatively analyzed, and the second generic data category with the largest value of class1 is used as the data sharing indication tag of the industrial internet data set to be shared.
Further, if the second common data category with the largest value of all class1 is used as the data sharing indication label of the industrial internet data set to be shared, all class1 values may not be large, in which case the accuracy of the data sharing indication label (data sharing classification label) is controversial.
Thus, for the purpose of indicating the accuracy of the tag for the last data sharing, STEP303 further includes the following: obtaining a data induction judgment value; comparing and analyzing the credibility score of the second generic data category with the data induction judgment value; and determining the second common data category with the credibility score higher than the data induction judgment value as the data sharing indication label of the industrial Internet data set to be shared.
In an embodiment of the present invention, the data summarization determination value is a determination value index3 configured in advance, when class1> index3, it is determined that the data sharing indication tag of the industrial internet data set to be shared is of class i, and in order to avoid summarizing the industrial internet data set to be shared into a plurality of second common data categories, the index3 may be: index3=0.9.
Through the content recorded by the STEPs 101-STEPS105, when the shared data induction processing is performed on the industrial internet data set, the cloud data characteristic of the data sharing event is added besides the local data characteristic of the data sharing event, so that the classification of the industrial internet data set comprising the cloud industrial internet data and the local industrial internet data is more accurate, the defect of poor overall search degree caused by the fact that the shared data induction processing is performed on the industrial internet data set only through the industrial internet data of the local industrial internet data can be overcome, and meanwhile, the defect of data induction accuracy can be overcome; in addition, the distribution area and the coverage range of the data sharing event window can be combined, and the error of data induction can be reduced.
Further, in some embodiments, data sharing events in some industrial internet data sets are obviously keyword, which can accurately perform shared data induction processing on the industrial internet data sets.
Further, the industrial internet data sharing method may further include the technical solutions recorded by STEP501-STEP 504.
The STEP501 analyzes the keywords of the data sharing event based on the local industrial internet data corresponding to the data sharing event to obtain the keyword credibility score of the keyword including the keyword of the data sharing event in the local industrial internet data corresponding to the data sharing event.
STEP502, determining an influence index (weight value) of local industrial internet data corresponding to the data sharing event based on the keyword credibility score.
Further, the STEP302 may further include the following.
STEP503, fusing the first data induction knowledge characteristics of the local industrial internet data corresponding to the data sharing events in the industrial internet data queue based on the influence indexes of the local industrial internet data corresponding to the data sharing events to determine first fused data induction knowledge characteristics.
STEP504, determining the industrial internet data set to be shared as a credibility score of a second common data category corresponding to the industrial internet data queue based on the first fused data induction knowledge characteristics.
For the STEP501, the local industrial internet data corresponding to the data sharing event may be input into a recognition network of data sharing event keywords (event identifiers) that are successfully debugged in advance to analyze whether the local industrial internet data corresponding to the data sharing event includes the keywords of the data sharing event, and the generation content of the recognition network of the data sharing event keywords is similar to the output of the recognition network in the STEP102, that is, one or more data sharing event windows are output. In the present invention, since shared data induction processing is performed on local industrial internet data corresponding to an independent thread data sharing event, in the STEP501, it is possible to recognize only whether or not a keyword of a data sharing event is included in the local industrial internet data corresponding to the data sharing event, without performing shared data induction processing on the keyword. Therefore, the keyword credibility scores of the data sharing event windows can be contrastingly analyzed, and the maximum keyword credibility score is obtained.
Further, in STEP502, an influence index of local industrial internet data corresponding to the data sharing event is determined based on the keyword confidence score, which may include contents recorded by STEPs 601 to STEP 603.
STEP601, obtaining an influence index judgment value.
STEP602, when the keyword credibility score is not less than the influence index determination value, determining an influence index of local industrial internet data corresponding to the data sharing event based on the influence index determination value and the keyword credibility score, wherein the first influence index is a first influence index.
STEP603, when the credible score of the keyword is smaller than the influence index judgment value, setting a set influence index as the influence index of the local industrial internet data corresponding to the data sharing event; wherein the set impact index is not higher than the first impact index.
For example, an influence index determination value index4 is configured in advance, and the keyword credibility score of the local industrial internet data corresponding to the data sharing event obtained in STEP502 is tag _ value.
For STEP503, a first data induction knowledge characteristic of local industrial internet data corresponding to the data sharing event in the industrial internet data queue is fused and determined to obtain a first fused data induction knowledge characteristic. Based on the above, the first fused data induction knowledge characteristic of the industrial internet data _ q in the industrial internet data queue m1 with the generic data type l may be a multidimensional vector matrix.
For STEP504, first, a comprehensive first fused data induction knowledge feature is obtained based on the first fused data induction knowledge features of all the industrial internet data in the queue m1, so that the credible score of the second generic data category of the final generic data category 1 is: class1. Thereafter, the process of determining the data sharing indication tag of the industrial internet data set to be shared is combined with STEP105.
Further, when the first global credibility score is determined to summarize the knowledge characteristics, the industrial internet data containing the data sharing event keywords are subjected to superposition processing, so that the weight of the industrial internet data is increased, the weight of the data set is increased when the keyword credibility score is larger, and the characteristic identification degree is increased when the comprehensive first fused data summarization knowledge characteristics are determined, so that the noise rate of the final data sharing indication label is lower, and the classification is more accurate.
In the embodiment, the classification process has a relation with the characteristics of the industrial internet data; in some cases, in order to improve the credibility of data classification, the data sharing indication label can be optimized through the data description field of the industrial internet data set to be shared.
Further, the industrial internet data sharing method may further include the following technical solutions recorded by STEP701-STEP 704.
And STEP701, acquiring a data description field of the industrial Internet data set to be shared.
STEP702, determining a first quantitative evaluation based on the data description field, wherein a value of the first quantitative evaluation is related to an accumulated value of a type description field of the second generic data type in the data description field.
At this time, the STEP302 further includes the following.
STEP703, determining the to-be-shared industrial internet data set as a first credibility score of a second common data category corresponding to the industrial internet data queue based on the first data induction knowledge characteristics of each industrial internet data in the industrial internet data queue.
STEP704, determining the industrial internet data set to be shared as the credibility score of the second common data category corresponding to the industrial internet data queue based on the first quantitative evaluation and the first credibility score of the second common data category.
In STEP702, significant vector mining is performed on the data description fields of the industrial internet data set to be shared to obtain feature vectors paired with the type description fields of the second generic data category, where the number of the feature vectors may be any number. Determining a first quantitative rating for a second category of commonality data corresponding to the industrial internet data queue based on the number of feature vectors paired with a type description field for the second category of commonality data.
Further, the STEP702 further includes the following contents: matching the data description field of the industrial internet data set to be shared with the second generic data type to obtain the accumulated value of the type description field of each second generic data type in the data description field; and determining a first quantitative evaluation of each second common data type based on the accumulated value, wherein the first quantitative evaluation and the accumulated value have a set mapping relationship.
In STEP703, a first confidence score of a second generic data is determined, and the first confidence score of the second generic data may be the confidence score of the second generic data determined in STEP302 or the confidence score of the second generic data determined in STEP 504.
In STEP704, it is determined that the to-be-shared industrial internet data set is the credible score of the second common data category corresponding to the industrial internet data queue based on the first quantitative evaluation and the first credible score of the second common data category. Further, determining the confidence score of the second generic data by the index of the first confidence score of the first quantitative rating of the second generic data.
Therefore, the data sharing indication label is interfered by the data description field, and the data sharing indication label can be optimized by the characteristics contained in the data description field, so that the anti-interference performance of the final data sharing indication label is enhanced, and the classification is more accurate.
The embodiment of the invention discloses a method for sharing industrial internet data, which comprises the following steps: obtaining a plurality of groups of industrial internet data of an industrial internet data set to be shared; carrying out shared data induction processing on the plurality of groups of industrial internet data to obtain a first common data type of the plurality of groups of industrial internet data, wherein the first common data type comprises local industrial internet data corresponding to a data sharing event and cloud industrial internet data corresponding to the data sharing event; analyzing the data sharing event based on the local industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the local industrial internet data corresponding to the data sharing event; analyzing the data sharing event based on the cloud industrial internet data corresponding to the data sharing event to obtain a first data induction knowledge characteristic of the cloud industrial internet data corresponding to the data sharing event; and determining a data sharing indication label of the industrial internet data set to be shared based on the first data induction knowledge characteristic. According to the method, the defect that the checking range of the data sharing knowledge tag matching of the industrial internet data set is poor can be overcome by combining the local industrial internet data corresponding to the data sharing event and the cloud industrial internet data corresponding to the data sharing event.
In some implementations which can be independent, after the data sharing indication tag of the industrial internet data set to be shared is determined, targeted data sharing can be performed according to the received sharing request, and the intelligent degree of data sharing is improved. Based on this, the method may further include the following: in response to a pending data sharing request, determining a desired tag corresponding to the data sharing request; determining a correlation coefficient of the expected tag and the data sharing indication tag; when the correlation coefficient is larger than or equal to a set coefficient, determining the industrial internet data set to be shared as a target data set matched with the data sharing request to be processed, and carrying out data sharing on the industrial internet data set to be shared; and when the correlation coefficient is smaller than a set coefficient, issuing a sharing request rejection prompt to a request end of the to-be-processed data sharing request.
Therefore, targeted data sharing processing can be performed according to correlation coefficient calculation among different labels, and potential safety hazards in the data sharing process are avoided.
In some implementations, in response to a pending data sharing request, determining a desired tag corresponding to the data sharing request may include: performing text analysis on the to-be-processed data sharing request to obtain a sharing requirement text data sequence, wherein the sharing requirement text data sequence comprises Y groups of sharing requirement text data with correlation, and Y is an integer greater than or equal to 1; determining an auxiliary requirement text data sequence according to the sharing requirement text data sequence, wherein the auxiliary requirement text data sequence comprises Y groups of associated auxiliary requirement text data; based on the shared demand text data sequence, acquiring a shared demand knowledge distribution sequence through a first demand detail knowledge mining model included in a shared demand analysis algorithm, wherein the shared demand knowledge distribution sequence comprises Y shared demand knowledge distributions; acquiring an auxiliary demand knowledge distribution sequence through a second demand detail knowledge mining model included in the shared demand analysis algorithm based on the auxiliary demand text data sequence, wherein the auxiliary demand knowledge distribution sequence includes Y auxiliary demand knowledge distributions; based on the sharing demand knowledge distribution sequence and the auxiliary demand knowledge distribution sequence, obtaining a sharing demand score corresponding to the sharing demand text data through a demand forecasting module included in the sharing demand analysis algorithm; and determining an expected tag of the sharing requirement text data sequence according to the sharing expected score.
In the embodiment of the invention, the auxiliary demands can be obtained by prediction based on the sharing demands, the auxiliary demands can reflect some demands with low importance except the data sharing demands, and the interference of the auxiliary demands on the sharing expectation score can be reduced by considering the auxiliary demands, so that the sharing expectation score can be ensured to be concentrated on the evaluation of the sharing demands as much as possible, and the corresponding expectation label can be accurately determined.
Based on the same or similar inventive concepts, please refer to fig. 2 in combination, which further provides an architectural diagram of an application environment 30 of the method for sharing industrial internet data, including a data sharing system 10 and a data sharing participant 20, where the data sharing system 10 and the data sharing participant 20 implement or partially implement the technical solution described in the above method embodiment when operating.
Further, a readable storage medium is provided, on which a program is stored, which when executed by a processor implements the method described above.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part thereof, which essentially contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a media service server 10, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.