91 results about "Process mining" patented technology

Systems and methods are provided for improving processes in a healthcare organization by mining historical data for information that can be used to more effectively allocate resources and process components. Factors used for the analysis include time, information, motivation, skills, and authority for particular resources. Arbitrage processing is used to minimize opportunity costs and increase efficiency.

The invention provides a log mining method based on a Petri network behavior profile, and belongs to the field of process mining. The method aims to improve a business progress model by means of implementation of a mining technology, so that procedure operation efficiency and service quality are improved. The method includes the steps that firstly, log sequences are extracted from a track generated in program running and pre-processing is carried out; the behavior relation between two adjacent actions is analyzed, the behavior profile is built, and an initial model is built according to direct dependency; then the log sequence with the largest occurrence frequency is replayed, and two procedure models superior to the initial model are found according to indexes; the consistency degrees of the two models and the initial model are respectively compared by means of behavior profile consistency so as to choose the more superior model; the last two steps are repeated until log replay is finished so as to obtain the optimal business procedure model. The log mining method can guarantee that the business procedure meets the requirement of functionality, enables procedure behaviors to be concise, and shortens program running time.

Process mining and tipping point analysis is used to determine tasks at risk. Tasks At Risk Intervention lead time analysis determines whether those tasks at risk can be performed in an opportunity window cost-effectively and at a high rate of success by the current task force. Load balancing can be used to offload fungible tasks at risk to flexible resources that can perform those tasks at risk for the highest value opportunities to micro-target tasks at risk with specific countermeasures, perhaps partitioned among several task force members to ensure can be done within the window of opportunity, to ensure their success. The flexible cognitive resources performing fungible tasks can be housed in a hub resource facility to centralize load balancing and obtain scale economies benefits from the shared capacity.

The invention provides a process mining method based on a single-disease treatment process. According to the method, a series of logic optimization algorithms such as association rules, a genetic algorithm, an EM (expectation maximum) algorithm and the like are used for determining a core even item of a treatment process, then case samples are used for connecting scattered points occurring on a treatment path for drawing, a treatment path diagram is obtained through a connected graph after historical case sample drawing, then each event node on the treatment path diagram is expanded, a complete treatment event item set is formed, and the cost interval for each treatment event item set is estimated and a treatment event sequence of the whole treatment process is given; the mined treatment event sequence is subjected to rationality verification and evaluation, and the path is disassembled effectively.

A computer-implemented method is provided for providing at least one analytics package to a process mining system, wherein the processor is provided with an event log comprising process data of business processes, the process data comprising at least one process element and the process element comprising at least one process step. The event log is stored according to a predetermined data structure comprising at least a first attribute for storing a unique identifier of the process element, a second attribute for storing an identifier of the process step, and a third attribute for storing an order of the process steps. The processor is further provided with auxiliary data and a data model, and the method comprises creating, based on the data model, at least one analytics package.

The invention discloses a process model graph automatic identification and understanding method, and belongs to the field of process mining. The method comprises the steps of firstly constructing a basic graphic element template, matching a process model graph with the graphic element template, identifying model elements such as tasks, activities, events, gateways, arrowheads and the like in the process model graph, and removing repeated matching nodes and wrong matching regions by using a screening technology; secondly by using a process model graph cutting technology, obtaining pictures of regions where nodes comprising texts are located, and by using an OCR technology, recognizing the texts in the pictures; thirdly performing gray processing on the process model graph, and obtaining andstoring a gray value matrix of the process model graph; and finally according to the arrowheads in the model graph and the positions of nearest neighbor nodes, performing traversal in the gray valuematrix, and identifying a starting node and a terminating node of a directed edge. According to the method, the types and positions of the model nodes and the texts in the model nodes can be correctlyidentified, and also the directed edge in the process model graph can be correctly identified.

The invention relates to a software development activity clustering analysis method based on event logs, and belongs to the technical field of software engineering and process mining. The method comprises the following steps of Firstly, adopting a natural language processing technology for carrying out text analysis and feature word extraction on event log data of a software development process version control system, achieving software development activity event daily vectorization on the basis of word2vec, and then based on a K-means clustering algorithm, clustering vectorized software development activity events . And clustering the vectorized software development activity events by using a means clustering algorithm, obtaining an optimal clustering cluster number by using a contour coefficient method, and finally obtaining software development activities and an incidence relation between the events and the activities. According to the method, the comprehensiveness of the software development event log can be enhanced, information contained in the event log data is revealed, software development activities can be found conveniently, software development behaviors can be guided and standardized, and technical support is provided for software development.

The invention discloses a multi-language text and speech generation method for a procedural model map, and belongs to the field of procedure mining. The method comprises the following steps that: firstly, identifying a model element, a model node text and a model directed edge in the procedural model map, and storing the identified procedural model as a standard procedural model file; then, usingmultilingual semantic dependence to analyze a model element text, using an RPST (Real Time Streaming Protocol) algorithm to analyze a model structure, and using a procedural structure tree with an annotation to store the model element text and the procedural model structure information; then, according to the text information amount and structure complexity, dividing the procedural structure treewith the annotation; using a deep syntax tree to generate the multilingual text of the procedural model from the procedural structure tree with the annotation; and finally, generating the multilingualspeech of the procedural model from the multilingual text. By use of the method, the procedural model in the procedural model map can be correctly identified, the text and the structure of the procedural model can be correctly analyzed, and the text with the correct grammar and the speech with correct pronunciation can be generated.

The detection and interpretation of data pertaining to the usage of software and documents by end users, and more specifically, the automation of the mining of event logs of events generated by business processes for logging of business processes and automatic discovery of business process models.

The invention discloses a process mining system based on semantic requirement matching. The process mining system comprises a platform foundation unit, an algorithm plugin unit with an algorithm plugin, and a model visualization unit, wherein the platform foundation unit receives a requirement text and user log data, and calls the algorithm plugin in the algorithm plugin unit to carry out process mining; and after the platform foundation unit receives the mining result of the algorithm plugin unit, the platform foundation unit transmits the mining result of the algorithm plugin unit to the model visualization unit to display the mining result. The requirement text of the user and the algorithm plugin are matched to realize the automation of a plugin selection process, the dynamic integration of the algorithm plugin set improves system flexibility on an aspect of design, and the effective utilization of computation resources and the ordered execution of mining tasks can be guaranteed.

The invention discloses a method for automatically generating a natural language text by a structured process model, and belongs to the field of process mining. The method comprises the steps of firstly obtaining and analyzing tag text information in a BPMN process model by utilizing an analysis technology of a tag text; secondly, converting the structure of the BPMN process model into a process structure tree by using a process model structure conversion technology; and finally, generating the natural language text by using a natural language generation technology. According to the method, the natural language text with correct grammar and complete semantics can be generated, so that non-professionals can understand the BPMN process model by reading the natural language text.

The invention provides a comprehensive diagnosis method and apparatus of receiving faults of a remote sensing satellite ground receiving system. The method comprises: a receiving log collection step:collecting event logs of the ground receiving system in a task receiving process and performing normalization processing on the event logs; a receiving flow mining step: performing receiving flow mining according to the event logs subjected to the normalization processing; a flow diagnosis and analysis step: diagnosing whether a receiving flow obtained in the receiving flow mining step satisfies acorrect receiving flow; a receiving device information collection step: collecting the state information of devices participating in task receiving during task receiving; and a receiving device diagnosis and analysis step: diagnosing whether the devices participating in task receiving run according to correct parameters during the task execution according to a defined fault diagnosis system. By adoption of the comprehensive diagnosis method and apparatus, the receiving tasks of the remote sensing satellite ground receiving system can be automatically diagnosed to find the faults in the receiving process in time, thereby improving the success rate and reducing the manpower and material consumption.

The invention discloses a double-granularity noise log filtering method based on an incidence relation. According to the method, the mixed dependency is obtained through calculation based on the localdependency and the global dependency, and the fine-grained filtering of the noise events in logs and the coarse-grained filtering of the noise tracks can be achieved at the same time through the method. Compared with a traditional log filtering method, the log filtering method has the advantages that a double-granularity filtering mechanism is adopted, different filtering mechanisms are used fordifferent noise situations, and therefore an excellent filtering effect is achieved under the condition that the original log data is reserved as much as possible; 2, the filtered log file is used forprocess mining, so that the precision of a process discovery model can be greatly improved, and the understandability of the model is enhanced.

The invention discloses a probability-integral-method based surface movement deformation predication method for any mining working faces. According to method, a vector product method is adopted for processing mining areas in any shapes, each processed mining area is divided into a plurality of mining areas similar to rectangles along the strike to perform calculation, surface movement deformation values for the whole mining areas are calculated through accumulation, and predication of the surface movement deformation values of the mining areas in any shapes, drawing of two-dimensional, three-dimensional and cloud pictures and output of calculation data files are realized through python language programming. The innovative surface movement deformation predication method for the any mining working faces is implemented with the assistance of computer technology. The surface movement deformation predication method has the advantages that calculation of the surface movement deformation values of the mining areas with different shapes is realized; surface movement deformation predication accuracy is improved; a reliable basis is provided for prevention and treatment of damage to surface buildings and surfaces, and economic loss and environment damage are reduced; the method is convenient to use, rapid in calculation speed and the like.

The invention relates to a rhombic hydraulic support for a pseudo-inclined down mining working surface of steep coal seam. The rhombic hydraulic support is adaptable to the characteristic of a coal mining process technique in a pseudo-inclined down arrangement manner, and is in close combination with the matching characteristic of a coal mining method and equipment through researching the movement discipline of wall rocks in a comprehensive mining process mining field and the stress condition of a comprehensive mining support under the control discipline. The rhombic hydraulic support is characterized in that: a traditional four-connecting-rod stable mechanism is divided into two parts, and at the same time, the top beam and base are designed into a rhombic-like structure, thus stable beam end distance and person walking space are formed. The rhombic hydraulic support has the characteristics that: through the development of the rhombic hydraulic support for the steep coal seam, the current mining situation of the steep coal seam is changed, the coal resources are effectively and reasonable utilized, the blank in the important supporting field of comprehensive mechanical mining of the steep coal seam is filled, a premise condition is created for achieving automatic machine tracking and other unmanned automatic working surfaces of the steep coal seam, therefore, the rhombic hydraulic support has broad application prospects.

The invention discloses a method of automatically converting a Chinese process model into English natural-language text, and belongs to the field of process mining. According to the method, firstly, a label text information parsing technology is used to acquire and parsing text information on nodes and edges in the process model; then a process model structure conversion technology is used to convert a process model structure into a process structure tree; then a domain word library construction technology is used to construct a domain word library of the process model; then a label text information translation technology is used to translate Chinese label text into English; then a translation text screening technology is used to screen correct text translation according to the domain word library; then a cross-language grammar structure conversion technology is used to convert a Chinese grammar structure into an English grammar structure, and a grammar tree is used to generate short natural-language text describing node behaviors; and finally, a natural-language text generation technology is used to generate the English natural-language text.

The invention belongs to the technical field of error detection, error correction, monitoring, and discloses a data-driven two-layer software process mining method and system. Activity information isfound from the process log by clustering; the activity is converted into a single trigger sequence in the order in which the activity occurs; the single trigger sequence is divided into several loop instances by loop; the activity layer mining module is used for discovering the activity information from the process log, the input is the process log, and the output is a single trigger sequence formed by the activities associated with each event in the log, and the sequence is used as the input of the process layer; the process layer mining module is used for discovering loops in a single trigger sequence and mining each loop instance as case information. The invention divides the single trigger sequence into cyclic instances so as to reach the case information of the discovery cycle part, which is used for process mining, and perfects the current process mining method, and has obvious advantages in processing the single trigger sequence compared with other algorithms.

The invention discloses a process mining method and system based on implicit characteristics. The method comprises the steps that an original log is input, log filtering is performed to obtain a new log, the implicit characteristics in the new log are looked for, 2-degree cycles in the implicit characteristics are distinguished from a concurrent structure, the 2-degree cycles of the same type are divided through the adjoining degree between tasks, and mining is performed according to a process mining algorithm to obtain a Petri net model with a 2-degree cycle. According to the process mining analysis method based on the Petri net, the Petri net model with a short cycle is output with the log having local completeness being input.

Disclosed are systems and methods providing for automation of enterprise and other processes. The systems and methods involve receiving historical process data, applying process mining techniques and generating process models. The process models can be used to identify automation candidates. One or more automation tools designed and configured for the identified automation candidates can be deployed to automate or to increase the efficiency of the process. In one embodiment, automation tools include artificial intelligence networks, which can label a set of input data according to determined or preconfigured domain-specific labels. An aggregator module can combine the similarly labeled data as part of automating a process or to increase the efficiency of a process.

The invention discloses a method for automatically converting a process model into a multilingual text, pertaining to the field of process mining. The method comprises the following steps: firstly, creating a multilingual text template, creating a multilingual-field work stock and recognizing a language type of a model element text; then, using text information of elements in a semantic dependencyanalysis model and a multilingual translation method to translate analyzed texts of model elements into multiple languages; and using a translation result screening and cross-linguistic syntactic structure adjusting method to optimize translation results in order to make the translation results more accurate; dividing the structure of the process model into sub-processes with an RPST algorithm, combining multilingual text information of the model elements with a process structure tree and generating the process structure tree with annotations; then, generating multilingual texts with a depthsyntax tree from the process structure tree with annotations; and ultimately, using subject clustering, verb clustering and object clustering to process the multilingual texts in order to generate a multilingual text description of process.

A new method of mining low-frequency behavior of business processes based on Petri nets is proposed, which involves the discovery and optimization of low-frequency behavior based on process tree cutting and the optimization of Petri net model based on communication behavior contour. Firstly, the initial flow model is established according to the communication behavior contour, and the behavior relationship of the log is represented by the direct flow graph cut from the flow tree, which is matched with the initial model, and all the low frequency sequences are found. Then, the behavior distancevector between the log and the model is calculated, the effective low frequency log and the noise log are distinguished based on the behavior compactness, and the noise log is filtered. Secondly, according to the filtered optimization log, the module net and the feature net are established, and the module net and the feature net are fused to obtain the optimized business process Petri net model.The invention provides the new method for mining low-frequency behavior, which effectively solves the problem of distinguishing low-frequency behavior and noise behavior in the business process by using behavior attributes among different modules, and avoids the structure of influencing the business process due to ignoring the low-frequency behavior in the process mining.

The invention discloses a financial process mining method based on reinforcement learning and a related device, and provides a better environmental basis for the whole formation process of a decision by adopting a mode of establishing an environmental model by sampling. And through algorithm iteration of the reinforcement learning planning method, errors of the decision scheme are reduced, and the decision scheme is more accurate. And prediction is carried out through decision specification constraints and fact constraints, so that the decision scheme can be actually applied to scenes, and the reliability and practicability are improved. Finally, efficiency evaluation is performed on the whole decision generation process, the accuracy of the decision generation process is verified, and the accuracy and safety of the final decision are improved. The limitation that the conventional process automatic mining solidification technology and calculation depend on a template is broken through, so that the process mining is easier to maintain, and the generated final decision content is more professional and safer; dependence of a current process automatic mining method on process visualization data resources is avoided, and a final decision can still be obtained under the condition of the process visualization data resources.