CN116126930A

CN116126930A - Production process monitoring method and system based on big data analysis

Info

Publication number: CN116126930A
Application number: CN202211472923.8A
Authority: CN
Inventors: 李继庚; 洪蒙纳; 梁广智; 陈怡�
Original assignee: Guangzhou Poi Intelligent Information Technology Co ltd
Current assignee: Guangzhou Poi Intelligent Information Technology Co ltd
Priority date: 2022-11-23
Filing date: 2022-11-23
Publication date: 2023-05-16

Abstract

According to the production process monitoring method and the production process monitoring system based on big data analysis, based on the production process monitoring method based on big data analysis, the multi-dimensional behavior description content is obtained through the relative distribution adjustment operation and the key user behavior description mining operation, production process monitoring on online user activity information is facilitated, the multi-dimensional behavior description content is obtained through the multi-dimensional mining operation, and therefore the multi-dimensional behavior description content can be obtained more accurately, the accuracy of the mining operation is improved, and therefore the accuracy and the credibility of the description content are effectively improved through the multi-dimensional mining operation.

Description

Production process monitoring method and system based on big data analysis

Technical Field

The application relates to the technical field of data monitoring analysis, in particular to a production process monitoring method and system based on big data analysis.

Background

Big data analysis refers to analysis of data of huge scale. Big data can be summarized as 4V: large data Volume (Volume), fast speed (Velocity), multiple types (Variety), and Value (Value). The use of big data as the word of the IT industry that is the hottest in time, with the consequent data warehouse, data security, data analysis, data mining, etc. around the business value of big data is becoming the focus of profit struggled by industry personnel.

Currently, the scope of big data analysis technology is expanding, such as data analysis processing in combination with smart medical (Wise Information Technology of med) and smart home (smart home home automation). In addition, with the intelligent upgrading of the production process, the combination of big data and the generation process is more and more mature, even if the related data can be greatly disturbed when being accurately analyzed by various conditions of the process monitoring data, if each condition is not considered, the accuracy and the credibility of the production process monitoring data are difficult to ensure.

Disclosure of Invention

In view of this, the present application provides a method and system for monitoring a process of a production process based on big data analysis.

In a first aspect, a method for monitoring a production process based on big data analysis is provided, including:

determining a plurality of target online user activity information in a plurality of online user activity information of business user big data to be analyzed; performing key user behavior description mining operation of a plurality of production process states on the plurality of target online user activity information respectively, and acquiring first key user behavior description distribution of the plurality of production process states of the target online user activity information;

Performing multi-dimensional mining operation on a first key user behavior description distribution of the target online user activity information to obtain multi-dimensional behavior description content of the target online user activity information, wherein the multi-dimensional mining operation comprises a relative distribution adjustment operation and a key user behavior description mining operation, and the relative distribution adjustment operation comprises relative distribution adjustment on an original key user behavior description distribution of one or a plurality of key user behavior description mining operations and a processed key user behavior description distribution; and carrying out production process monitoring on the business user big data to be analyzed based on the multidimensional behavior description content to obtain a production process monitoring condition.

In an independent embodiment, performing a multidimensional mining operation on a first key user behavior description distribution of the target online user activity information to obtain multidimensional behavior description content of the target online user activity information, including:

performing first relative distribution adjustment operation on first key user behavior description distribution of the target online user activity information to obtain a plurality of first key user behavior description distribution sets, wherein the precedence relationship of the first key user behavior description distribution in the first key user behavior description distribution sets is consistent with the precedence relationship of the corresponding target online user activity information;

Performing key user behavior description mining operation on a first key user behavior description distribution in the first key user behavior description distribution set to obtain a second key user behavior description distribution set, wherein the second key user behavior description distribution set covers a second key user behavior description distribution corresponding to the first key user behavior description distribution;

and performing a second relative distribution adjustment operation on the second key user behavior description distribution set to acquire the multidimensional behavior description content.

In an independent embodiment, performing a first relative distribution adjustment operation on a first key user behavior description distribution of the target online user activity information to obtain a plurality of first key user behavior description distribution sets, including:

clustering a plurality of first key user behavior description distributions of the target online user activity information for each target online user activity information to obtain a plurality of first key user behavior description clusters of the target online user activity information, wherein each first key user behavior description cluster carries a semantic tag, and the first key user behavior description clusters of the target online user activity information carrying the same semantic tag correspond to the same group of production process states in a plurality of production process states;

And in the first key user behavior description clusters of the target online user activity information, the first key user behavior description cluster clusters with consistent semantic labels are spliced according to the precedence relation of the target online user activity information, and a first key user behavior description distribution set corresponding to the semantic labels is obtained.

In an independently implemented embodiment, performing a second relative distribution adjustment operation on the second set of key user behavior description distributions to obtain the multi-dimensional behavior description content, including:

clustering the second key user behavior description distribution in the second key user behavior description distribution set based on the corresponding target online user activity information to obtain a second key user behavior description cluster, wherein the second key user behavior description distribution in the same second key user behavior description cluster corresponds to the same target online user activity information;

and respectively splicing the second key user behavior description clusters to obtain multidimensional behavior description contents corresponding to the target online user activity information.

Performing first key user behavior description mining operation on first key user behavior description distribution of the target online user activity information, and acquiring third key user behavior description distribution corresponding to the first key user behavior description distribution;

performing third relative distribution adjustment operation on the third key user behavior description distribution to obtain a plurality of third key user behavior description distribution sets, wherein the precedence relationship of the third key user behavior description distribution in the third key user behavior description distribution sets is consistent with the precedence relationship of the corresponding target online user activity information;

performing a second key user behavior description mining operation on a third key user behavior description distribution in the third key user behavior description distribution set to obtain a fourth key user behavior description distribution set, wherein the fourth key user behavior description distribution set covers a fourth key user behavior description distribution corresponding to the third key user behavior description distribution;

performing fourth relative distribution adjustment operation on the fourth key user behavior description distribution set to obtain a third key user behavior description cluster corresponding to the target online user activity information;

And performing third key user behavior description mining operation on fourth key user behavior description distribution in the third key user behavior description cluster, and acquiring multidimensional behavior description content corresponding to the target online user activity information.

In an independent embodiment, determining a plurality of target online user activity information in a plurality of online user activity information of business user big data to be analyzed, including:

screening operation is carried out on a plurality of online user activity information of the business user big data to be analyzed, and a plurality of business user big data fragments to be analyzed are obtained;

and carrying out information analysis operation on the business user big data fragments to be analyzed to obtain the plurality of target online user activity information.

In an independently implemented embodiment, the big data analysis based production process monitoring method is implemented by a machine learning model, the method further comprising:

determining the example online user activity information from a plurality of online user activity information of the example service user big data;

loading the on-line user activity information of the example into the machine learning model to obtain the monitoring condition of the test production process of the big data of the example service user;

Determining a model quality evaluation of the machine learning model based on the test production process monitoring condition and prior annotations of the example business user big data;

optimizing the machine learning model based on the model quality assessment.

In a second aspect, a production process monitoring system based on big data analysis is provided, comprising a processor and a memory in communication with each other, the processor being adapted to retrieve a computer program from the memory and to implement the above-mentioned method by running the computer program.

According to the production process monitoring method and the production process monitoring system based on big data analysis, the multi-dimensional behavior description content is obtained through the relative distribution adjustment operation and the key user behavior description mining operation, production process monitoring of on-line user activity information is facilitated, the multi-dimensional behavior description content is obtained through the multi-dimensional mining operation, and therefore the multi-dimensional behavior description content can be obtained more accurately, the accuracy of the mining operation is improved, and therefore the accuracy and the credibility of the description content are effectively improved through the multi-dimensional mining operation.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a production process monitoring method based on big data analysis according to an embodiment of the present application.

Fig. 2 is a block diagram of a production process monitoring device based on big data analysis according to an embodiment of the present application.

FIG. 3 is a block diagram of a process monitoring system based on big data analysis according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.

Referring to FIG. 1, a method for monitoring a manufacturing process based on big data analysis is shown, which may include the following steps 11-14.

step11, determining a plurality of target online user activity information in a plurality of online user activity information of business user big data to be analyzed.

By way of example, the targeted online user activity information may characterize information related to real-time monitoring during production (such as production flow data monitored by a monitoring device).

step12, performing key user behavior description mining operation of a plurality of production process states on the plurality of target online user activity information respectively, and obtaining first key user behavior description distribution of the plurality of production process states of the target online user activity information.

Illustratively, the production process state is used to characterize the state of the associated production facility at the time of production.

step13, performing multidimensional mining operation on the first key user behavior description distribution of the target online user activity information, and obtaining multidimensional behavior description content of the target online user activity information.

Illustratively, the multi-dimensional mining operations include a relative distribution adjustment operation and a key user behavior description mining operation, wherein the relative distribution adjustment operation includes a relative distribution adjustment of an original key user behavior description distribution and a processed key user behavior description distribution of one or several key user behavior description mining operations.

step14, based on the multidimensional behavior description content, carrying out production process monitoring on the business user big data to be analyzed to obtain a production process monitoring condition.

By way of example, production process monitoring may be understood as the result of monitoring and analyzing the production process with respect to monitoring.

It can be understood that, according to the production process monitoring method based on big data analysis in the embodiment of the application, the multidimensional behavior description content is obtained through the relative distribution adjustment operation and the key user behavior description mining operation, so that the production process monitoring of the online user activity information is facilitated, and the multidimensional behavior description content is obtained through the multidimensional mining operation, so that the multidimensional behavior description content can be obtained more accurately, the accuracy of the mining operation is improved, and the accuracy and the credibility of the description content are effectively improved through the multidimensional mining operation.

In an alternative embodiment, the business user big data to be analyzed may be any online user activity information, for example, the online user activity information recorded by the process monitoring system, and the business user big data to be analyzed may cover one of the contents. The business user big data to be analyzed can comprise a plurality of online user activity information, and in the monitoring step of monitoring the content of the business user big data to be analyzed in the production process, the global online user activity information of the business user big data to be analyzed can be identified, and the local online user activity information can be screened for identification, for example, the online user activity information with local significance can be screened for identification.

In an alternative embodiment, the step of identifying the local online user activity information may be filtered, and may specifically include what is described in step 11.

Screening operation is carried out on a plurality of online user activity information of the business user big data to be analyzed, and a plurality of business user big data fragments to be analyzed are obtained; and carrying out information analysis operation on the business user big data fragments to be analyzed to obtain the plurality of target online user activity information.

It can be appreciated that in the case of a plurality of online user activity information of business user big data to be analyzed, the problem of inaccurate screening operation is improved, so that a plurality of target online user activity information can be accurately determined.

In an alternative embodiment, the screening operation may be performed on a plurality of online user activity information of the service user big data to be analyzed, for example, the screening may be performed on a plurality of online user activity information of the service user big data to be analyzed by performing data screening on a search interface, performing data screening on a data sign, and the like, so as to obtain M (M is a positive integer) service user big data segments to be analyzed. The screening methods are not limited one by one.

In an alternative embodiment, the information analysis operation may be performed on a plurality of large data segments of the service user to be analyzed.

In an alternative embodiment, in step12, the machine learning model may perform the key user behavior description mining operation of the plurality of production process states on the target online user activity information, so as to obtain the first key user behavior description distribution of the plurality of production process states of each target online user activity information. The machine learning model may be an AI machine learning model, for example.

In an alternative embodiment, step13, because there is spatial sequence information between the online user activity information of the business user big data to be analyzed, the multidimensional behavior description content of the target online user activity information can be obtained to represent the spatial sequence information between the online user activity information of the business user big data to be analyzed, thereby providing more complete information for monitoring the variety of the online user activity information in the production process.

In an alternative embodiment, the multi-dimensional behavior description content of the target online user activity information can be obtained by performing a relative distribution adjustment operation and a key user behavior description mining operation on the key user behavior description distribution of each production process state. The multidimensional behavior description content is used for representing key information of matching conditions between online user activity information, such as key user behavior description distribution distributed according to precedence relation of the online user activity information. The multi-dimensional behavior descriptive content may represent the location of the online user activity information, i.e., the description of the online user activity information may be represented according to the chronological order of the online user activity information, for example, one of the online user activity information may appear in the region Q in the first online user activity information, and the multi-dimensional behavior descriptive content appearing in the region P … in the second online user activity information may represent the description of each of the online user activity information according to the chronological order of the online user activity information. The relative distribution adjustment operation encompasses a relative distribution adjustment of an original key user behavior description distribution and a processed key user behavior description distribution of one or several key user behavior description mining operations.

Based on the steps of the multidimensional mining operation according to the embodiments of the present application, step 13 may specifically include the following.

Performing first relative distribution adjustment operation on first key user behavior description distribution of the target online user activity information to obtain a plurality of first key user behavior description distribution sets, wherein the precedence relationship of the first key user behavior description distribution in the first key user behavior description distribution sets is consistent with the precedence relationship of the corresponding target online user activity information; performing key user behavior description mining operation on a first key user behavior description distribution in the first key user behavior description distribution set to obtain a second key user behavior description distribution set, wherein the second key user behavior description distribution set covers a second key user behavior description distribution corresponding to the first key user behavior description distribution (namely, the second key user behavior description distribution obtained by performing key user behavior description mining operation through the first key user behavior description distribution); and performing a second relative distribution adjustment operation on the second key user behavior description distribution set to acquire the multidimensional behavior description content.

It can be appreciated that, when the steps are performed, the accuracy of the first key user behavior description distribution set can be effectively improved by performing the first relative distribution adjustment operation, so that the integrity and accuracy of the second key user behavior description distribution set are improved.

In an alternative embodiment, the machine learning model may include a plurality of units, the key user behavior description mining operation may be performed on the target online user activity information through at least one unit of the machine learning model, to obtain a first key user behavior description distribution of the plurality of production process states, and further, the first key user behavior description distribution of the plurality of production process states may be continuously processed through the remaining units of the machine learning model.

In an alternative embodiment, a first relative distribution adjustment operation is performed on a first key user behavior description distribution of the target online user activity information, so as to obtain a plurality of first key user behavior description distribution sets, which specifically include the following.

Clustering a plurality of first key user behavior description distributions of the target online user activity information for each target online user activity information to obtain a plurality of first key user behavior description clusters of the target online user activity information, wherein the first key user behavior description clusters carry semantic tags, and the first key user behavior description clusters of the target online user activity information carrying the same semantic tags correspond to the same group of production process states in a plurality of production process states; and in the first key user behavior description clusters of the target online user activity information, the first key user behavior description cluster clusters with consistent semantic labels are spliced according to the precedence relation of the target online user activity information, and a first key user behavior description distribution set corresponding to the semantic labels is obtained.

It can be appreciated that when the first relative distribution adjustment operation is performed on the first key user behavior description distribution of the target online user activity information, the problem of inaccurate clustering is improved, so that a plurality of first key user behavior description distribution sets can be accurately acquired

For example, the first key user behavior description distributions of each set of target online user activity information may be shown by { I, O, P }, where I (I is a positive integer) represents a production process state description result, O (O is a positive integer) represents a case of the first key user behavior description distribution, and P (P is a positive integer) represents a layout of the first key user behavior description distribution. That is, each set of targeted online user activity information corresponds to a first key user behavior description distribution of I production process states.

For example, a first key user behavior description distribution of the I production process states may be clustered, or the production process states may be clustered. The number of first key user behavior description distributions covered by each group or the number of production process states covered by each group may be determined by the number M of target online user activity information and the production process state description result I, e.g., each group may cover I/M first key user behavior description distributions or production process states. For example, if the production process state description result I is 128 and the number of target online user activity information M is 16, each group may cover 16 first key user behavior description distributions, or each group may cover 16 production process states. Each first key user behavior description cluster may carry a semantic tag.

In an alternative embodiment, in the first key user behavior description clusters of the target online user activity information, first key user behavior description distribution with consistent semantic labels is spliced according to the precedence relationship of the target online user activity information, and a first key user behavior description distribution set corresponding to the semantic labels is obtained.

For example, the first key user behavior description distributions of several production process states for each target online user activity information may be clustered in the above manner. For example, the first key user behavior description distribution of each target online user activity information may be divided into 16 groups. Further, the precedence relation of the first key user behavior description clustering credential target online user activity information of the M target online user activity information can be spliced.

The target online user activity information is an online user activity information set carrying a time sequence stamp or a frame number, that is, each target online user activity information carries a precedence relationship. And the precedence relation of the target online user activity information can be spliced by the first key user behavior description clustering credentials with consistent semantic labels.

For example, the 1 st group of first key user behavior description clusters of the 1 st target online user activity information, the 1 st group of first key user behavior description clusters of the 2 nd target online user activity information, the 1 st group of first key user behavior description clusters … … of the 3 rd target online user activity information, and the 1 st group of first key user behavior description clusters of the 16 th target online user activity information are spliced to obtain a first key user behavior description distribution set corresponding to the semantic tag 1.

For example, the first key user behavior description clusters of the 2 nd group of the 1 st target online user activity information, the first key user behavior description clusters of the 2 nd group of the 2 nd target online user activity information, the first key user behavior description clusters of the 2 nd group of the 3 rd target online user activity information, and the first key user behavior description clusters of the 2 nd group of the 16 th target online user activity information are spliced to obtain the first key user behavior description distribution set … … corresponding to the semantic tags 2, and in this way, the first key user behavior description distribution set corresponding to each semantic tag can be obtained. Namely, replacing the precedence relation of the first key user behavior description distribution taking the target online user activity information as the clustering evidence to obtain a first key user behavior description distribution set taking the semantic tag as the clustering evidence. In each first key user behavior description distribution set, each group of first key user behavior description clusters are distributed according to the precedence relation of the target online user activity information, namely, the precedence relation of the first key user behavior description clusters according to the 1 st target online user activity information and the first key user behavior description clusters … … of the 2 nd target online user activity information and the first key user behavior description clusters of the 16 th target online user activity information is distributed so as to acquire the spatial sequence information of the target online user activity information in subsequent processing.

In an alternative embodiment, the key user behavior description mining operation may be performed on a first key user behavior description distribution in the first set of key user behavior description distributions. For example, descriptions of each first key user behavior description distribution in the first key user behavior description distribution set may be extracted according to a precedence relationship of the target online user activity information, and the obtained descriptions may cover spatial order information between the target online user activity information.

For example, the key user behavior description mining operation may be performed on each first key user behavior description distribution in the first key user behavior description distribution set by using three units of 2 x 2, 6*6 and 2 x 2, so as to obtain second key user behavior description distributions bound to each first key user behavior description distribution, where each second key user behavior description distribution may form a second key user behavior description distribution set. Namely, according to the mode, the second key user behavior description distribution set corresponding to each semantic label can be obtained.

In an alternative embodiment, after the second set of key user behavior description distributions is obtained, the second set of key user behavior description distributions may be subjected to a second relative distribution adjustment operation, that is, the second relative distribution adjustment operation is performed according to the second set of key user behavior description distributions using the semantic tag as a clustering credential, and each second key user behavior description distribution in each second set of key user behavior description distributions is optimized into a clustering manner in which the target online user activity information is the clustering credential, so as to obtain the multidimensional behavior description content.

In an alternative embodiment, performing a second relative distribution adjustment operation on the second set of key user behavior description distributions to obtain the multi-dimensional behavior description content includes:

clustering the second key user behavior description distribution in the second key user behavior description distribution set based on the corresponding target online user activity information to obtain a second key user behavior description cluster, wherein the second key user behavior description distribution in the same second key user behavior description cluster corresponds to the same target online user activity information; and respectively splicing the second key user behavior description clusters to obtain multidimensional behavior description contents corresponding to the target online user activity information.

It can be appreciated that when the second relative distribution adjustment operation is performed on the second key user behavior description distribution set, the problem that the clustering of the target online user activity information is unreliable is improved, so that the multidimensional behavior description content can be reliably acquired

The second key user behavior description distribution in the second key user behavior description distribution set is obtained by mining the key user behavior description of the first key user behavior description distribution, so that the second key user behavior description distributions also respectively correspond to the target online user activity information. And clustering according to target online user activity information corresponding to the second key user behavior description distribution to obtain second key user behavior description clusters. For example, for a certain set of second key user behavior description distributions, the second key user behavior description distributions in the set may be clustered into a second key user behavior description cluster of the 1 st target online user activity information, a second key user behavior description cluster of the 2 nd target online user activity information, and a second key user behavior description cluster of the 16 th target online user activity information of … …. In this way, the second key user behavior description distributions in each second key user behavior description distribution set may be clustered, and the second key user behavior description clusters in each second key user behavior description distribution set are obtained.

For example, second key user behavior description clusters corresponding to the target online user activity information in the second key user behavior description distribution sets can be spliced. For example, the second key user behavior description cluster corresponding to the 1 st target online user activity information in the 1 st second key user behavior description distribution set, the second key user behavior description cluster … … corresponding to the 1 st target online user activity information in the 2 nd second key user behavior description distribution set, and the second key user behavior description cluster corresponding to the 1 st target online user activity information in the 16 th second key user behavior description distribution set may be spliced to obtain the multidimensional behavior description content corresponding to the 1 st target online user activity information. The second key user behavior description cluster corresponding to the 2 nd target online user activity information in the 1 st second key user behavior description distribution set, the second key user behavior description cluster … … corresponding to the 2 nd target online user activity information in the 2 nd second key user behavior description distribution set, and the second key user behavior description cluster corresponding to the 16 th target online user activity information in the 16 th second key user behavior description distribution set may be spliced to obtain multidimensional behavior description content … … corresponding to the 2 nd target online user activity information, and the second key user behavior description cluster corresponding to the 16 th target online user activity information in the 1 st second key user behavior description distribution set, and the second key user behavior description cluster … … of the 16 th second key user behavior description distribution set corresponding to the 16 th target online user activity information may be spliced to obtain multidimensional behavior description content corresponding to the 16 th target online activity information. By the method, the second key user behavior description distribution in the second key user behavior description distribution set can be spliced again, namely, second relative distribution adjustment operation is performed, and multidimensional behavior description content corresponding to each target online user activity information is obtained. In the multi-dimensional behavior description content, the spatial sequence information among the on-line user activity information of each target is covered, and the method is beneficial to monitoring the production process of the business user big data to be analyzed. For example, the production process may monitor the nature of the online user activity information, such as an indication of a goal in the online user activity information.

Through the mode, the machine learning model can acquire the multidimensional behavior description content consistent with the time sequence relation through the first relative distribution adjustment operation, the content of the online user activity information is favorably expressed according to the time sequence relation, the relative distribution of the key user behavior description distribution is adjusted to the relation with the corresponding target online user activity information as a clustering certificate through the second relative distribution adjustment operation, namely, the multidimensional behavior description content corresponding to the target online user activity information is expressed, so that the acquired multidimensional behavior description content covers the positioning information of the target online user activity information, and the production process monitoring of the business user large data to be analyzed is favorably realized.

Based on the steps of the multi-dimensional mining operation in the embodiment of the present application, step 13 may specifically include.

Performing first key user behavior description mining operation on first key user behavior description distribution of the target online user activity information, and acquiring third key user behavior description distribution corresponding to the first key user behavior description distribution; performing third relative distribution adjustment operation on the third key user behavior description distribution to obtain a plurality of third key user behavior description distribution sets, wherein the precedence relationship of the third key user behavior description distribution in the third key user behavior description distribution sets is consistent with the precedence relationship of the corresponding target online user activity information; performing a second key user behavior description mining operation on a third key user behavior description distribution in the third key user behavior description distribution set to obtain a fourth key user behavior description distribution set, wherein the fourth key user behavior description distribution set covers a fourth key user behavior description distribution corresponding to the third key user behavior description distribution; performing fourth relative distribution adjustment operation on the fourth key user behavior description distribution set to obtain a third key user behavior description cluster corresponding to the target online user activity information;

It can be understood that when the multidimensional mining operation is performed on the first key user behavior description distribution of the target online user activity information, the problem of inaccurate relative distribution adjustment operation is solved, so that the multidimensional behavior description content of the target online user activity information can be accurately obtained.

In an alternative embodiment, a first key user behavior description mining operation may be performed on the first key user behavior description distributions to obtain third key user behavior description distributions corresponding to each first key user behavior description distribution, and illustratively, the first key user behavior description distributions may be processed by 2 x 2, irrelevant information may be deleted, and third key user behavior description distributions bound to each first key user behavior description distribution may be obtained.

In an alternative embodiment, a third relative distribution adjustment operation may be performed on the third key user behavior description distribution, and a plurality of third key user behavior description distribution sets may be obtained. The third relative distribution adjustment operation is similar to the first relative distribution adjustment operation, and the third key user behavior description distribution corresponding to each target online user activity information can be clustered, for example, can be divided into 16 groups. And splicing the precedence relation of the target online user activity information by the third key user behavior description clustering evidence with consistent semantic labels. For example, the third key user behavior description cluster of the 1 st group of the 1 st target online user activity information, the third key user behavior description cluster of the 1 st group of the 2 nd target online user activity information, the third key user behavior description cluster of the 1 st group of the 3 rd target online user activity information, and the third key user behavior description cluster of the 1 st group of the 16 th target online user activity information are spliced to obtain a third key user behavior description distribution set corresponding to the semantic tag 1, and in the third key user behavior description distribution set, the third key user behavior description distribution of the 2 nd target online user activity information can be distributed and spliced according to the precedence relation of the third key user behavior description distribution … of the 3 rd target online user activity information. Further, a third key user behavior description distribution set corresponding to each semantic tag can be obtained according to the above method.

In an alternative embodiment, a second key user behavior description mining operation may be performed on a third key user behavior description distribution in the third key user behavior description distribution set to obtain a fourth key user behavior description distribution set, and exemplary, each third key user behavior description distribution may be processed in 6*6 to obtain a fourth key user behavior description distribution, and each fourth key user behavior description distribution may constitute a fourth key user behavior description distribution set. That is, according to the above manner, a fourth distribution set of key user behavior descriptions corresponding to each semantic tag may be obtained, where the fourth distribution set of key user behavior descriptions may cover spatial sequence information between the target online user activity information.

In an alternative embodiment, a fourth relative distribution adjustment operation may be performed on a fourth set of key user behavior description distributions. The fourth relative distribution adjustment operation is similar to the second relative distribution adjustment operation, and the fourth key user behavior description distribution in the fourth key user behavior description distribution set can be clustered according to the corresponding target online user activity information, and the fourth key user behavior description distributions with the same corresponding target online user activity information in each fourth key user behavior description distribution set are spliced. For example, the fourth key user behavior description distribution corresponding to the 1 st target online user activity information in the 1 st fourth key user behavior description distribution set, the fourth key user behavior description distribution … … corresponding to the 1 st target online user activity information in the 2 nd fourth key user behavior description distribution set, and the fourth key user behavior description distribution corresponding to the 1 st target online user activity information in the 16 th fourth key user behavior description distribution set may be spliced to obtain the third key user behavior description cluster corresponding to the 1 st target online user activity information. Further, in this manner, a third key user behavior description cluster corresponding to each target online user activity information may be obtained.

In an alternative embodiment, a third key user behavior description mining operation may be performed on a fourth key user behavior description distribution in the third key user behavior description cluster, to obtain multidimensional behavior description contents corresponding to the target online user activity information. For example, the fourth key user behavior description distribution in the third key user behavior description cluster may be processed by 2×2, and multidimensional behavior description content corresponding to each target online user activity information may be obtained. In the multidimensional behavior description content, the spatial sequence information among the on-line user activity information of each target is covered, so that the production process monitoring of the business user big data to be analyzed is facilitated. Illustratively, the producible process monitors the variety of online user activity information.

In an alternative embodiment, other multi-dimensional mining operations may be performed in addition to the multi-dimensional mining operation method. For example, the first relative distribution adjustment operation may have a precedence relationship between the first 2 x 2 and 6*6 or the second relative distribution adjustment operation may have a precedence relationship between 6*6 and the second 2 x 2. For another example, the third relative precedence relationship of the adjustment operation is located before the first 2×2, or the fourth relative precedence relationship of the adjustment operation is located after the second 2×2. The processing sequence relation of the multi-dimensional mining operation is not limited one by one.

In an alternative embodiment, step14 may determine a process monitoring situation of the business user big data to be analyzed based on the first key user behavior description distribution and the multidimensional behavior description content. For example, on the premise that the machine learning model is an evaluation thread, the subsequent thread unit of the machine learning model can be used for continuously processing the first key user behavior description distribution and the multidimensional behavior description content and outputting the production process monitoring condition of the business user big data to be analyzed, for example, the production process monitoring condition can be the type of the business user big data to be analyzed, the type can be expressed in a mode of percentage and the like, and the type of the business user big data to be analyzed is not limited one by one.

For example, the machine learning model may be not an evaluation thread, and may process the multi-dimensional behavior description content continuously through a subsequent thread unit of the machine learning model, and output a production process monitoring condition of business user big data to be analyzed.

In an alternative embodiment, the relative distribution adjustment operation is performed before or after no less than one unit of the machine learning model, so that the machine learning model has the performance of extracting the multi-dimensional behavior description content, and the machine learning model production process can be assisted to monitor the business user big data to be analyzed, for example, the production process monitors the variety of the business user big data to be analyzed. According to the production process monitoring method based on big data analysis, the relative distribution adjustment operation can be carried out before or after at least one unit based on actual processing requirements, so that the unit added with the relative distribution adjustment operation has the performance of acquiring the multi-dimensional behavior description content, and the machine learning model can be optimized to be a machine learning model carrying the performance of acquiring the multi-dimensional behavior description content, so that the production process monitoring performance of the big data of the business user to be analyzed by the machine learning model is enhanced.

In an alternative embodiment, the machine learning model may be optimized prior to the production process monitoring process using the machine learning model, such as the machine learning model (which may be a relative distribution adjustment operation before or after no less than one unit of the machine learning model). The method may further include the following.

Determining the example online user activity information from a plurality of online user activity information of the example service user big data; loading the on-line user activity information of the example into the machine learning model to obtain the monitoring condition of the test production process of the big data of the example service user; determining a model quality evaluation of the machine learning model based on the test production process monitoring condition and prior annotations of the example business user big data; optimizing the machine learning model based on the model quality assessment.

It will be appreciated that by accurately determining example online user activity information, the reliability of optimizing the machine learning model is improved.

For example, the machine learning model may be optimized using the example business user big data, the example business user big data may be filtered, and the information analysis operation may be performed on the selected online user activity information, so as to obtain the example online user activity information. The machine learning model can carry out key user behavior description mining, relative distribution adjustment and other processes on the sample online user activity information, and acquire the monitoring condition of the test production process of the sample service user big data, such as the type of the sample service user big data. Further, a model quality assessment of the machine learning model may be obtained based on the production process monitoring conditions (e.g., percentage of example business user big data categories, possibly anomalies) obtained by the machine learning model and prior annotations of the example business user big data (e.g., exact percentage of categories of example business user big data), and the machine learning model may be optimized by the model quality assessment.

For example, when the model quality evaluation is not greater than the decision value, or the number of optimizations satisfies the number target value, the optimization may be suspended, and the optimized machine learning model may be obtained. The optimized machine learning model can be used for monitoring the business user big data to be analyzed in the production process, for example, the variety of the business user big data to be analyzed in the production process.

Based on the steps of the production process monitoring method based on big data analysis, the method can perform screening and information analysis operations on the online user activity information of the big data of the business user to be analyzed, obtain the target online user activity information, and perform key user behavior description mining operations on the target online user activity information to obtain the first key user behavior description distribution of each target online user activity information.

In an alternative embodiment, a first relative distribution adjustment operation is performed on first key user behavior description distributions of each target online user activity information, and a plurality of first key user behavior description distribution sets are obtained. For example, each set of targeted online user activity information corresponds to a first key user behavior description distribution of I production process states.

In an alternative embodiment, the first key user behavior description distributions for each production process state of I may be clustered, e.g., each group may include I/M first key user behavior description distributions or production process states. For example, if the production process state description result I is 128 and the number of target online user activity information M is 16, each group may cover 16 first key user behavior description distributions, or each group may cover 16 production process states.

In an alternative embodiment, the 1 st group of first key user behavior description clusters of the 1 st target online user activity information, the 1 st group of first key user behavior description clusters of the 2 nd target online user activity information, the 1 st group of first key user behavior description clusters … … of the 3 rd target online user activity information and the 1 st group of first key user behavior description clusters of the 16 th target online user activity information are spliced to obtain a first key user behavior description distribution set corresponding to the semantic tag 1. The first key user behavior description clusters of the 2 nd group of the 1 st target online user activity information, the first key user behavior description clusters of the 2 nd group of the 2 nd target online user activity information, the first key user behavior description clusters of the 2 nd group of the 3 rd target online user activity information, and the first key user behavior description clusters of the 2 nd group of the 16 th target online user activity information of the … … are spliced to obtain a first key user behavior description distribution set … … corresponding to the semantic tag 2, and the first key user behavior description distribution set taking the semantic tag as a clustering credential can be obtained.

In an alternative embodiment, the key user behavior description mining operation may be performed on each first key user behavior description distribution in the set of first key user behavior description distributions. For example, key user behavior description mining operations may be performed on each first key user behavior description distribution in the first key user behavior description distribution set by using three units 2×2, 6*6, and 2×2, so as to respectively obtain second key user behavior description distributions corresponding to each first key user behavior description distribution, where each second key user behavior description distribution may form a second key user behavior description distribution set. According to the above manner, the second key user behavior description distribution sets corresponding to the first key user behavior description distribution sets can be obtained respectively.

In an alternative embodiment, the second relative distribution adjustment operation is performed on the second key user behavior description distribution set, that is, the second relative distribution adjustment operation is performed according to the second key user behavior description distribution set taking the semantic tag as the clustering credential, and the clustering mode that the online user activity information of each second key user behavior description distribution optimization target in each second key user behavior description distribution set is the clustering credential is used to obtain the multidimensional behavior description content.

In an alternative embodiment, the first key user behavior description distribution and the multidimensional behavior description content may be continuously processed by a subsequent thread unit of the machine learning model, and the kind of business user big data to be analyzed is output.

On the basis of the above, please refer to fig. 2 in combination, there is provided a production process monitoring device 200 based on big data analysis, which is applied to a production process monitoring system based on big data analysis, the device includes:

the description obtaining module 210 is configured to determine a plurality of target online user activity information from a plurality of online user activity information of the business user big data to be analyzed; performing key user behavior description mining operation of a plurality of production process states on the plurality of target online user activity information respectively, and acquiring first key user behavior description distribution of the plurality of production process states of the target online user activity information;

the process monitoring module 220 is configured to perform a multidimensional mining operation on a first key user behavior description distribution of the target online user activity information, and obtain a multidimensional behavior description content of the target online user activity information, where the multidimensional mining operation includes a relative distribution adjustment operation and a key user behavior description mining operation, and the relative distribution adjustment operation includes performing a relative distribution adjustment on an original key user behavior description distribution of one or several key user behavior description mining operations and a processed key user behavior description distribution; and carrying out production process monitoring on the business user big data to be analyzed based on the multidimensional behavior description content to obtain a production process monitoring condition.

On the basis of the above, referring to fig. 3 in combination, there is shown a production process monitoring system 300 based on big data analysis, comprising a processor 310 and a memory 320 in communication with each other, the processor 310 being configured to read and execute a computer program from the memory 320 to implement the method described above.

On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.

In summary, based on the above scheme, according to the production process monitoring method based on big data analysis according to the embodiment of the application, the multi-dimensional behavior description content is obtained through the relative distribution adjustment operation and the key user behavior description mining operation, which is beneficial to monitoring the production process of the online user activity information, and the multi-dimensional behavior description content is obtained through the multi-dimensional mining operation, so that the multi-dimensional behavior description content can be obtained more accurately, the accuracy of the mining operation is improved, and the accuracy and the credibility of the description content are effectively improved through the multi-dimensional mining operation.

It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).

It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer storage medium may be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.

The computer program code necessary for operation of portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., a conventional programming language such as C language, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, ruby and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.

Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application and are not intended to limit the order in which the processes and methods of the application are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the numbers allow for adaptive variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the present application, documents that are currently or later attached to this application for which the broadest scope of the claims to the present application is limited. It is noted that the descriptions, definitions, and/or terms used in the subject matter of this application are subject to such descriptions, definitions, and/or terms if they are inconsistent or conflicting with such descriptions, definitions, and/or terms.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of this application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present application may be considered in keeping with the teachings of the present application. Accordingly, embodiments of the present application are not limited to only the embodiments explicitly described and depicted herein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. The production process monitoring method based on big data analysis is characterized by comprising the following steps of:

2. The method of claim 1, wherein performing a multi-dimensional mining operation on a first key user behavior description distribution of the target online user activity information to obtain multi-dimensional behavior description content of the target online user activity information comprises:

3. The method of claim 2, wherein performing a first relative distribution adjustment operation on a first key user behavior description distribution of the target online user activity information to obtain a plurality of first key user behavior description distribution sets, comprises:

4. The method of claim 2, wherein performing a second relative distribution adjustment operation on the second set of key user behavior description distributions to obtain the multi-dimensional behavior description content comprises:

5. The method of claim 1, wherein performing a multi-dimensional mining operation on a first key user behavior description distribution of the target online user activity information to obtain multi-dimensional behavior description content of the target online user activity information comprises:

6. The method of claim 1, wherein determining a number of target online user activity information among a number of online user activity information of business user big data to be analyzed, comprises:

7. The method of claim 1, wherein the big data analysis based production process monitoring method is implemented by a machine learning model, the method further comprising:

optimizing the machine learning model based on the model quality assessment.

8. A production process monitoring system based on big data analysis, characterized in that it comprises a processor and a memory in communication with each other, said processor being adapted to retrieve a computer program from said memory and to implement the method according to any of claims 1-7 by running said computer program.