CN112818130A - Knowledge graph-based online inspection method - Google Patents
Knowledge graph-based online inspection method Download PDFInfo
- Publication number
- CN112818130A CN112818130A CN202110125609.1A CN202110125609A CN112818130A CN 112818130 A CN112818130 A CN 112818130A CN 202110125609 A CN202110125609 A CN 202110125609A CN 112818130 A CN112818130 A CN 112818130A
- Authority
- CN
- China
- Prior art keywords
- inspection
- marketing
- preliminary
- service information
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses an online inspection method based on a knowledge graph, relates to power grid information management, and solves the technical problem that the problem is difficult to find due to the limitation of a data source and a marketing system in the conventional inspection mode. Constructing a preliminary inspection knowledge graph according to inspection rules; performing full data cruise on all marketing service information of the marketing domain data center, and supplementing a preliminary inspection knowledge map; optimizing and summarizing the preliminary knowledge graph according to the commonalities of the preliminary knowledge graph and the inspection results of the past years to form an inspection expert intelligence base; inspecting the inspection sample according to the intelligent database of the inspection expert to determine the inspection problems of the inspection sample; and cleaning and positioning the inspection problems step by step, and displaying the inspection result in a visual mode. The invention realizes the intelligent and accurate inspection of marketing full business, full data, full specialty and full risk, and promotes the intelligent and lean management of inspection work.
Description
Technical Field
The invention relates to power grid information management, in particular to an online inspection method based on a knowledge graph.
Background
In the current inspection rule, the data source is only limited to the data of the marketing system, but not the data of the data center of the whole marketing business domain. Moreover, the operator environment requires that enterprise services are more flexible and standard, the power connection time is shortened, the power supply quality is more reliable, the power supply does not run once, and the inspection of the service quality changes along with the change of the market environment. Due to the limitation of the data source of the inspection rule, the existing inspection mode cannot catch up with the change of the market environment, the problems are difficult to be inspected in the inspection process, and the problems cannot be prevented and corrected in time during the audit inspection.
Disclosure of Invention
The invention provides an online inspection method based on a knowledge graph aiming at the defects of the prior art, and solves the problem that the problems are difficult to find due to the limitation of data sources and a marketing system in the conventional inspection mode.
The technical scheme of the invention is as follows: an online inspection method based on knowledge graph comprises the following steps:
s1, constructing a preliminary inspection knowledge map according to the inspection rule;
s2, applying the preliminary inspection knowledge graph to perform full data cruise on all marketing service information of the marketing domain data center to find marketing service information with suspected inspection problems; supplementing the preliminary inspection knowledge graph according to the marketing service information with suspected inspection problems;
s3, optimizing and summarizing the preliminary knowledge graph according to the commonalities of the preliminary knowledge graph and the inspection results of the past years to form an inspection expert intelligence base;
s4, inspecting the inspection sample according to the intelligent database of the inspection expert to determine the inspection problems of the inspection sample;
and S5, gradually cleaning and positioning the inspection problems, and simultaneously visually displaying the inspection results.
In a further improvement, S1 specifically includes:
s11, combing and analyzing the inspection rules to construct a first inspection clue;
s12, adopting BP neural network and semi-monitoring mode to construct self-adapting management of the checking rule;
s13, on the basis of the self-adaptive management of the inspection rules, adopting an SAE algorithm model to refine the inspection characteristics according to the marketing monitoring, the abnormal rules and the audit risks, simultaneously constructing new inspection clues, and automatically updating the inspection characteristics into the new inspection clues to form a preliminary inspection knowledge map.
Further, the self-adaptive management of the inspection rules comprises self-adaptive updating of the inspection rules and self-defined combination of the inspection rules; the self-adaptive updating of the inspection rule specifically comprises the following steps: and matching corresponding inspection rules by using an NLP technology and captured keywords, and periodically synchronizing the inspection rules of the marketing domain data center.
Further, S2 specifically includes:
s21, periodically synchronizing the marketing business information of the marketing domain data center;
s22, automatically extracting the synchronized marketing service information through the etl timing task, and checking the data integrity of the extracted marketing service information; storing incomplete marketing service information into an auxiliary database, and storing complete marketing service information into a task database;
s23, cruising the marketing service information in the task database by applying the preliminary inspection knowledge map to find out the marketing service information with suspected inspection problems; and supplementing the preliminary inspection knowledge graph according to the marketing service information with suspected inspection problems.
Further, in S23, after the marketing service information with suspected inspection problems is found, the suspected inspection problems in the marketing service information with suspected inspection problems are identified, and the risk level is identified.
Further, the step S3 specifically includes searching for commonalities of the preliminary inspection knowledge-graph through PDCA closed-loop mode, and refining and summarizing the preliminary inspection knowledge-graph to obtain a professional knowledge-graph; and summarizing the professional knowledge graph and the inspection results of the past years to form an inspection knowledge graph typical case library, and filing the inspection knowledge graph typical case library into an inspection expert intelligent library.
Advantageous effects
The invention has the advantages that: according to the inspection rule, the information of the marketing business of the marketing full business domain is utilized to construct an inspection knowledge map library, the inspection sample is inspected and displayed simultaneously in a map mode, so that a knowledge map of the inspection specialty is established and is filed in an inspection expert intelligent library for service inspection work, and intelligent and accurate inspection of the marketing full business, the full data, the full specialty and the full risk is realized.
Drawings
FIG. 1 is a block diagram illustrating a flow of an inspection method according to the present invention;
fig. 2 is an expansion view of visual display of inspection results according to the present invention.
Detailed Description
The invention is further described below with reference to examples, but not to be construed as being limited thereto, and any number of modifications which can be made by anyone within the scope of the claims are also within the scope of the claims.
Referring to fig. 1-2, the invention relates to an online inspection method based on knowledge graph, which comprises the following steps:
s1, constructing a preliminary inspection knowledge map according to the inspection rule.
S1 specifically includes:
s11, the inspection rule is sorted and analyzed to construct the first inspection clue. For example, a company in a province has 143 marketing inspection rules, and first the local application of the 143 inspection rules is sorted and analyzed to construct a first inspection clue from the application of the inspection rules.
S12, adopting BP neural network and semi-monitoring mode to build self-adapting management of checking rule, thereby achieving effective management of checking rule.
The self-adaptive management of the inspection rules comprises self-adaptive updating of the inspection rules and self-defined combination of the inspection rules. The self-adaptive updating of the inspection rule specifically comprises the following steps: and matching the corresponding inspection rule by the captured keywords through an NLP technology, and periodically synchronizing the inspection rule of the data center of the marketing domain.
The inspection rule is updated regularly, and the version of the marketing inspection rule is upgraded through the function, so that the management of the rule is facilitated. Meanwhile, the historical inspection rule version and the corresponding basic rule detail can be inquired, and a plurality of pieces of information can be combined for inquiry and a list can be exported. And the accuracy of the adjustment of the inspection rule can be monitored and evaluated, so that data support is provided for the perfection of the inspection rule. The inspection rule management function of the inspection system is connected with the data center of the marketing domain to realize the acquisition of the inspection rules, so that the data is synchronized periodically. In addition, the inspection system also supports the introduction of the latest inspection rule in a manual mode, and meanwhile, the operation of adding, deleting and modifying the inspection rule of a certain service class can be realized.
The self-defined combination function of the inspection rules realizes the combination of the inspection rules of different marketing services of the same service type. The combination of different marketing service inspection rules is a problem list meeting the screening and re-checking conditions under various rule conditions after the combination is carried out by a marketing inspection auxiliary system.
S13, on the basis of self-adaptive updating, according to marketing monitoring, abnormal rules and audit risks, adopting an SAE algorithm model to refine audit characteristics, and simultaneously constructing new audit clues to form an automatic updating mechanism of the audit clues so as to ensure the correctness of audit points. Automatically updating the inspection characteristics to the new inspection clues to form a preliminary inspection knowledge map.
S2, applying the preliminary inspection knowledge graph to perform full data cruise on all marketing service information of the marketing domain data center to find marketing service information with suspected inspection problems. And supplementing the preliminary inspection knowledge graph according to the marketing service information with suspected inspection problems.
S2 specifically includes:
and S21, periodically synchronizing the marketing business information of the marketing domain data center. Specifically, marketing business information is synchronized from a marketing domain data center monthly as needed for full audit business. The marketing service information specifically comprises a task number, a task name, a service type, a synchronization date, an operator and a state, and the monitoring and management of the service data synchronization task are facilitated. According to the development need of the inspection service, service data are synchronized from the marketing domain data center to the intelligent accurate inspection system database periodically, and a data source is provided for inspection.
And S22, automatically extracting the synchronized marketing service information through the etl timing task, and checking the data integrity of the extracted marketing service information. Namely, data of the synchronous marketing service information is summarized, and synchronous abnormal data, database table loss and the like are displayed so as to ensure the correctness of source data. And storing the incomplete marketing business information into the auxiliary database, and storing the complete marketing business information into the task database.
The marketing service information is automatically acquired and supplemented, the information is automatically extracted through the etl timing task, and when the marketing service information is abnormal and the data acquisition cannot be completed, the marketing service information can be synchronized into the database of the inspection auxiliary system through the functional operation.
S23, cruising the marketing business information in the task database by applying the preliminary inspection knowledge map to find out the marketing business information with suspected inspection problems. And supplementing the preliminary inspection knowledge graph according to the marketing service information with suspected inspection problems, thereby achieving the purpose of continuously improving and enriching the knowledge graph.
Preferably, after the marketing service information with the suspected inspection problem is found, the suspected inspection problem in the marketing service information with the suspected inspection problem is identified, and the risk level is identified.
And S3, optimizing and summarizing the preliminary knowledge map according to the commonalities of the preliminary knowledge map and the inspection results of the past years to form an inspection expert intelligence base.
S3 includes, through PDCA closed loop mode, searching the commonality of preliminary inspection knowledge map, and abstracting and summarizing it to obtain professional knowledge map, thereby further perfecting knowledge map and promoting intelligent lean management of inspection. For example, the suspected problems are traced to the source by adopting a knowledge graph technology, the accounts and the reading and checking processes are subjected to flow inspection by adopting a balance principle, different rules are arranged and grouped by adopting a gene recombination mode, and the like, so that all-around inspection is realized, and the holographic information of the sample portrait is formed. Namely, one sample has a plurality of suspected problems, and the same multi-surface correlation display and the like are realized, so that the aims of intelligent inspection and accurate inspection are realized.
And summarizing the professional knowledge map and the inspection results of the past years to form an inspection knowledge map typical case library, and filing the inspection knowledge map typical case library into an inspection expert intelligent library to serve inspection work. By summarizing the professional knowledge map and the inspection results of the past years, the intelligent inspection rules are systematically combed to form an intelligent inspection rule system, namely an inspection knowledge map typical case base. And finally, filing the information into an intelligent database of the inspection expert. With the accumulation of rules in the intelligent database of the inspection experts, the intelligent inspection has stronger and stronger capability of solving business problems.
And S4, inspecting the inspected sample according to the intelligent database of the inspection expert to determine the inspection problems of the inspected sample. The example is not limited to only checking one type of related checking rule at the same time during checking. The inspection rules can be classified and combined to form a combined knowledge graph. If the check rule related to business expansion overtime and the check rule related to power charge error are combined, a customer satisfaction degree knowledge graph is formed; and combining and refining the inspection rules related to business expansion and installation and the inspection rules related to the customer files to form a customer file knowledge graph.
And S5, gradually cleaning and positioning the inspection problems, visually displaying the inspection results, displaying the inspection results and displaying all suspected sample lists under the inspection rules. For example, a clear location presentation of work orders for which there is an inspection issue. And (4) selecting abnormal work orders based on knowledge graph tracing, performing display line expansion analysis on all related entities of the work orders, and analyzing and obtaining the number of rules and samples related to each work order. And a sample is distributed through the ring, and the chain structure is subjected to problem positioning display, the sample in a list is comprehensive, and the comprehensive visual analysis and the accurate positioning of the sample problem are realized. If all links of the work order are overtime or not, whether internal circulation exists or not, if a certain link of the work order is overtime, who is the processing person of the link of the work order, and whether all work orders related to the person have problems or not, so that whether the working quality of the person has problems or not is determined. The power supply station with problems due to personal work quality can also be unfolded to determine whether other people have problems, and further determine whether to manage the problems.
Specifically, the visual display of the inspection result comprises visual display of the overall condition of the marketing service, visual display of the total inspection result, visual display of the cleaning and positioning result of the inspection problem, statistical analysis of the adjustment and modification result of the inspection problem, mining and analysis of the reexamination customer problem, visual display based on a knowledge graph and one-key derivation of the inspection report.
And the visual display of the marketing service overall situation is realized, and the query result is visually displayed for the marketing overall service of the data center according to multiple dimensions and multiple graphic display modes. And the visual display of the total inspection result is realized, and the visual display of the query result in multiple dimensions and multiple graphic display modes is realized on the total service inspection result data according to the specialty, rule, unit and problem classification. And the visual display of the inspection problem cleaning positioning result is realized, and the visual display of the query result of the inspection problem cleaning positioning result data according to various dimensions and various graphic display modes is realized. And the statistical analysis of the inspection problem rectification result is realized, and the visual display of the query result of the inspection problem data rectification result data according to various dimensions and various graphic display modes is realized. And the problem mining and analysis of the rechecked customers are realized, and the visual display of the query result of the result data of the rechecked customer inspection problems according to various dimensions and various graphic display modes is realized. The inspection customer problem mining analysis is to cluster and divide characteristic samples by taking abnormal samples as research objects based on a clustering algorithm, such as k-Means. And (4) classifying the sample abnormality, and taking the average abnormal constant, abnormal frequency, abnormal standard deviation and abnormal slope as characterization variables of the sample. And performing abnormal problem association on abnormal problems according to association rules, mining and analyzing the inspection problem results, and realizing mining and analysis of problem ranking, problem frequency, problem commonality, problem density and problem association according to problem classification. The method comprises the steps of visual display based on a knowledge graph, marketing service problem entity associated display, risk associated display and rule associated display analysis based on graph data, one-key export of inspection reports, one-key export of statistical analysis reports of inspection, and provision of working condition statistical reports specific to individuals based on the knowledge graph.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various changes and modifications without departing from the structure of the invention, which will not affect the effect of the invention and the practicability of the patent.
Claims (6)
1. An online inspection method based on knowledge graph is characterized by comprising the following steps:
s1, constructing a preliminary inspection knowledge map according to the inspection rule;
s2, applying the preliminary inspection knowledge graph to perform full data cruise on all marketing service information of the marketing domain data center to find marketing service information with suspected inspection problems; supplementing the preliminary inspection knowledge graph according to the marketing service information with suspected inspection problems;
s3, optimizing and summarizing the preliminary knowledge graph according to the commonalities of the preliminary knowledge graph and the inspection results of the past years to form an inspection expert intelligence base;
s4, inspecting the inspection sample according to the intelligent database of the inspection expert to determine the inspection problems of the inspection sample;
and S5, gradually cleaning and positioning the inspection problems, and simultaneously visually displaying the inspection results.
2. The knowledge-graph-based online inspection method of claim 1, wherein the step S1 specifically comprises:
s11, combing and analyzing the inspection rules to construct a first inspection clue;
s12, adopting BP neural network and semi-monitoring mode to construct self-adapting management of the checking rule;
s13, on the basis of the self-adaptive management of the inspection rules, adopting an SAE algorithm model to refine the inspection characteristics according to the marketing monitoring, the abnormal rules and the audit risks, simultaneously constructing new inspection clues, and automatically updating the inspection characteristics into the new inspection clues to form a preliminary inspection knowledge map.
3. The method of claim 2, wherein the adaptive management of the audit rules comprises adaptive updating of audit rules, custom combination of audit rules; the self-adaptive updating of the inspection rule specifically comprises the following steps: and matching corresponding inspection rules by using an NLP technology and captured keywords, and periodically synchronizing the inspection rules of the marketing domain data center.
4. The knowledge-graph-based online inspection method of claim 1, wherein the step S2 specifically comprises:
s21, periodically synchronizing the marketing business information of the marketing domain data center;
s22, automatically extracting the synchronized marketing service information through the etl timing task, and checking the data integrity of the extracted marketing service information; storing incomplete marketing service information into an auxiliary database, and storing complete marketing service information into a task database;
s23, cruising the marketing service information in the task database by applying the preliminary inspection knowledge map to find out the marketing service information with suspected inspection problems; and supplementing the preliminary inspection knowledge graph according to the marketing service information with suspected inspection problems.
5. The method of claim 4, wherein in S23, after the marketing service information with suspected inspection problems is found, the suspected inspection problems in the marketing service information with suspected inspection problems are identified and the risk level is identified.
6. The method of claim 1, wherein the S3 specifically comprises finding commonalities of the preliminary inspection knowledge-graph through PDCA closed-loop mode, and refining and summarizing the preliminary inspection knowledge-graph to obtain a professional knowledge-graph; and summarizing the professional knowledge graph and the inspection results of the past years to form an inspection knowledge graph typical case library, and filing the inspection knowledge graph typical case library into an inspection expert intelligent library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110125609.1A CN112818130A (en) | 2021-01-29 | 2021-01-29 | Knowledge graph-based online inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110125609.1A CN112818130A (en) | 2021-01-29 | 2021-01-29 | Knowledge graph-based online inspection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112818130A true CN112818130A (en) | 2021-05-18 |
Family
ID=75860187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110125609.1A Pending CN112818130A (en) | 2021-01-29 | 2021-01-29 | Knowledge graph-based online inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112818130A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214719A (en) * | 2018-11-02 | 2019-01-15 | 广东电网有限责任公司 | A kind of system and method for the marketing inspection analysis based on artificial intelligence |
| US20190340303A1 (en) * | 2018-05-07 | 2019-11-07 | Apple Inc. | Smart Updates From Historical Database Changes |
| CN110929036A (en) * | 2019-11-29 | 2020-03-27 | 南方电网数字电网研究院有限公司 | Electric power marketing inspection management method and device, computer equipment and storage medium |
-
2021
- 2021-01-29 CN CN202110125609.1A patent/CN112818130A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190340303A1 (en) * | 2018-05-07 | 2019-11-07 | Apple Inc. | Smart Updates From Historical Database Changes |
| CN109214719A (en) * | 2018-11-02 | 2019-01-15 | 广东电网有限责任公司 | A kind of system and method for the marketing inspection analysis based on artificial intelligence |
| CN110929036A (en) * | 2019-11-29 | 2020-03-27 | 南方电网数字电网研究院有限公司 | Electric power marketing inspection management method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 何伟刚;: "电力稽查模式未来发展趋势分析", 机电信息, no. 612, pages 103 - 104 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021184630A1 (en) | Method for locating pollutant discharge object on basis of knowledge graph, and related device | |
| CN108764663B (en) | Method and system for generating and managing power customer portrait | |
| CN108170769A (en) | A kind of assembling manufacturing qualitative data processing method based on decision Tree algorithms | |
| CN112766550A (en) | Power failure sensitive user prediction method and system based on random forest, storage medium and computer equipment | |
| CN109934483A (en) | A kind of manufacturing quality information managing and control system and method towards quality in kind promotion | |
| CN112860769A (en) | Energy planning data management system | |
| CN113283772A (en) | Electric power marketing inspection business rule analysis and application method | |
| Izquierdo-Cortazar et al. | Towards automated quality models for software development communities: The QualOSS and FLOSSMetrics case | |
| CN112883062A (en) | Self-defined rule checking method not based on rule | |
| CN112818130A (en) | Knowledge graph-based online inspection method | |
| Tanphet et al. | Applying business intelligence technology for equipment maintenance and repair plan of telecommunications services provider | |
| CN116308843A (en) | Financial funds management method | |
| CN113269446A (en) | Cultural and tourism economic operation data monitoring system architecture | |
| CN113221001A (en) | Scientific and technological service intelligent matching and recommending method based on big data | |
| CN113537758A (en) | Manufacturing industry high-quality development comprehensive evaluation method and system based on big data technology | |
| CN112966897A (en) | Multi-dimensional data analysis method based on maintenance platform | |
| CN113706015A (en) | Data collection system for enterprise asset arrangement based on block chain | |
| US20040210462A1 (en) | Computer-implemented system and method for replicating standard practices | |
| CN112215560A (en) | Intelligent shift arrangement system and implementation method thereof | |
| Lin | IoT-based enhanced decision-making and data mining for digital transformation of tobacco companies | |
| CN113537760A (en) | Intelligent recommendation method and system for fault handling plan | |
| CN117993737A (en) | Enterprise big data analysis system based on artificial intelligence | |
| Travé-Massuyès et al. | Assessing product quality from the production process health status | |
| CN117785605A (en) | Mobile terminal data monitoring and analyzing system based on big data | |
| CN117391440A (en) | Enterprise information reconnaissance platform and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |