WO2022010380A1 - Procédé et système automatisé de résolution de tâches - Google Patents

Procédé et système automatisé de résolution de tâches Download PDF

Info

Publication number
WO2022010380A1
WO2022010380A1 PCT/RU2021/050099 RU2021050099W WO2022010380A1 WO 2022010380 A1 WO2022010380 A1 WO 2022010380A1 RU 2021050099 W RU2021050099 W RU 2021050099W WO 2022010380 A1 WO2022010380 A1 WO 2022010380A1
Authority
WO
WIPO (PCT)
Prior art keywords
module
solving
actions
objects
subgoals
Prior art date
Application number
PCT/RU2021/050099
Other languages
English (en)
Russian (ru)
Inventor
Илья Владимирович ВОЛОЧКОВ
Original Assignee
Илья Владимирович ВОЛОЧКОВ
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Илья Владимирович ВОЛОЧКОВ filed Critical Илья Владимирович ВОЛОЧКОВ
Publication of WO2022010380A1 publication Critical patent/WO2022010380A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions

Definitions

  • This technical solution relates to the field of computer technology, in particular to a method and system for solving problems.
  • the knowledge management system for resolving situations contains: a knowledge creation unit; a knowledge organization unit, the input of which is connected to the output of the knowledge creation unit; a knowledge localization unit, with the input of which the output of the knowledge organization unit is connected; a knowledge positioning unit, with the input of which the output of the knowledge localization unit is connected, and a knowledge reuse unit, with the inputs of which the outputs of the knowledge localization and positioning units are connected; a system integration block, the inputs and outputs of which are connected, respectively, with the inputs and outputs of the blocks of knowledge creation, knowledge organization, knowledge localization, knowledge positioning, knowledge reuse; and a system visualization unit, the input of which is connected to the output of the system integration unit.
  • the well-known solution is a hybrid expert system (ES) using knowledge models combined into a knowledge base with an inference machine. It is possible to search for suitable documents by query based on semantic analysis both in local databases (DB) and on the Internet.
  • the "inventing machine” has knowledge (and produces answers) that in its part exceeds the knowledge of the most qualified specialists. It contains powerful information bases of technical special effects from different fields of knowledge, catalog of methods for solving problems, some calculation models are used, in particular, functional cost analysis.
  • Some of these databases are built using knowledge models, in particular semantic networks, production models, and subject-action-object models (SAO models). Visual and graphic images are also used: graphs, images, drawings to improve work efficiency, connected to some knowledge models.
  • the system was implemented on standard machine-readable media protected from copying by access codes, without special devices for reading machine-readable media and their protection.
  • the system is connected to computers through reading devices, and during operation, the PS core is read into the computer and work is performed in the computer's RAM with swapping information volumes from a machine-readable medium.
  • the claimed results are achieved through the implementation of a computer-implemented method of solving problems, performed using at least one processor and containing the steps at which: a) receive data containing parameters characterizing the problem being solved; while the parameters contain at least a description of the objects of the task and data describing the conditions and restrictions; b) modeling at least one state of the objects of the problem being solved at the time of obtaining the final result using a database containing information on similar categories of tasks, taking into account the conditions, restrictions and objects of the task entered at step a); c) create a list of successive stages of action to achieve a positive final result of solving the problem; d) form subgoals within the steps identified in step c); at the same time, subgoals contain actions and/or properties of stage objects that are necessary to solve the task of this stage; e) identify the operating systems necessary for the implementation of the final result and for the implementation of sub-goals within the stages; while the systems contain a set of actions and/or objects; f) model the properties of existing systems, in which
  • each subgoal within the stage of actions on the way to the final result of solving the problem is taken as an independent final result of solving the problem and analyzed with the execution of stages a) - k) for it.
  • a database is used that contains information on similar categories of tasks, taking into account the conditions, restrictions and objects entered at step a) tasks.
  • the method is implemented using a machine learning model.
  • the results of the machine learning model are evaluated and corrected via the Internet.
  • • data receiving module that receives data containing parameters characterizing the problem being solved; while the parameters contain at least a description of the objects of the task and data describing the conditions and restrictions;
  • a module for creating a list of action steps that creates a list of successive action steps to achieve a positive final result of solving the problem • a sub-goal formation module that generates sub-goals within the stages; at the same time, subgoals contain actions and/or properties of stage objects that are necessary to solve the task of this stage;
  • action option selection module which selects action options for modeling the properties of existing systems, in which subgoals are implemented with the least resource costs, and options for eliminating the causes of interference based on the parameters that characterize the task;
  • the system is implemented as a cloud platform.
  • system further comprises a machine learning module containing at least one machine learning model capable of making decisions and automated learning based on the tasks being solved.
  • the results of the machine learning module are further evaluated and trained via the Internet. DESCRIPTION OF THE DRAWINGS
  • FIG. 1 illustrates a computer-implemented method for solving problems.
  • FIG. 2 illustrates an automated problem solving system.
  • FIG. 3 illustrates an example of a general view of a computing system that provides the implementation of the claimed solution.
  • the present invention is aimed at providing a computer-implemented method and system for solving problems (author's name in Russian - "Troublehacking", in English - “Troublehacking”).
  • troublehacking is a methodology for improving systems, a set of methods and tools aimed at inventing non-standard ways to solve problems and applying them in practice.
  • Most of the troublehacking methods are based in their essence on the well-known theory of inventive problem solving (TRIZ), which has been refined and improved taking into account current developments and advances in the technical level.
  • TRIZ inventive problem solving
  • the main difference between troublehacking and TRIZ is the scope of the methods. If TRIZ serves for the most part to solve technical problems, then troublehacking serves to solve a wide range of problems, including not only technical, but also non-technical problems, which can also be solved using existing technical means and computational algorithms (approaches).
  • the claimed computer-implemented method for solving problems (100) can be executed using standardized computing devices.
  • step (101) receive data containing parameters characterizing the problem being solved; wherein the parameters contain at least a description of the task objects and data describing the conditions and constraints.
  • various input information can be used to model the implementation of the input task. For example, forecasting an increase in attendance at a business facility, an increase in sales, an increase in the company's capitalization, the geographical location of an object, average throughput, the number of employees, costs, consumables, etc.
  • the data generates common basic entities for the formation of the input state of the model, its further formation and analysis of the stages for solving the problem.
  • step (102) using a database containing information on similar categories of tasks, taking into account the conditions, constraints, and task objects entered at step (101), at least one state of the objects of the problem being solved is modeled at the time of obtaining the final result.
  • the database is updated and contains information about similar implementations of tasks, which allows you to obtain modeling parameters for solving a problem based on successful examples of implementing similar or similar tasks.
  • the state of an object is understood as its property, in which it meets the criteria of the entered parameters. In this case, a situation is possible when the object, based on the specified criteria, cannot be implemented, which is reported using the computing environment.
  • the state of the object must correspond to the objective properties of the model, which does not contradict the input data and the imposed restrictions. For example, an increase in sales for a coffeeshop with a cost budget of 500,000 rubles in a period of 1 month.
  • the input parameters determine the existing variations of already performed successful calculations, which will be selected as possible relevant solutions to the current problem.
  • step (103) a list of sequential action steps is created to achieve a positive final result of solving the problem.
  • similar results of modeling similar solutions to problems are selected from the database or the machine learning module is involved, which is trained on user requests and the choice of criteria for the formation of related solution results, depending on the possibility of classifying the input task.
  • the generated stages contain information on the hierarchical order of the implementation of the task, starting from the parent step (the final result), in the direction of the key actions necessary to achieve the final state of the model.
  • subgoals are formed within the steps identified at step (SW); at the same time, subgoals contain actions and/or properties of stage objects that are necessary to solve the task of this stage.
  • Each stage contains a set of parameters and actions of one or more objects associated with the result of solving the input problem.
  • the parameters that have a critical impact on the successful implementation of each stage can be: stage implementation period, stage costs, geographical location, change in the mode of operation of the object, etc.
  • the ranking of subgoals is performed to determine the subgoal with the highest weight for solving the problem; at the same time, such a subgoal is taken as an independent final result of solving the problem and can be analyzed as an independent task within the framework of modeling each of the subgoals.
  • the parameters mentioned above are analyzed for each sub-objective within the stage depending on the associated data and properties. For example, an increase in sales is associated with equipment and / or advertising for a particular business area.
  • the model generates an associated state matrix depending on the input parameters at step (101), choosing the most optimal solutions, based, for example, on the established costs for the implementation of the corresponding step.
  • each subgoal can be represented as a state matrix, which can be processed using a machine learning model, such as an artificial neural network (ANN), to find possible variations in the execution of a step and then rank them to select the optimal one.
  • ANN artificial neural network
  • step (106) the properties of the operating systems are modeled, in which the subgoals are implemented with the least resource costs. This is done by ranking the modeled variations in step (105) and selecting on a set of parameters including systems to identify the most resource efficient outcomes.
  • a database or knowledge base can be used that contains information on similar categories of tasks, taking into account the input conditions, constraints and objects of the task introduced at step (101).
  • Interferences that affect the implementation of subgoals and entail resource costs are identified.
  • Interferences are objects, their properties, as well as external influences that have a negative impact on the successful implementation of subgoals.
  • disruptions may include, but are not limited to, fluctuations in exchange rates, the interruption of the supply of required products from specified suppliers, changes in location conditions of a territorial nature (for example, the demolition of a building), a decline in demand for facilities, etc.
  • the causes of interference are identified in the form of determining the properties of operating systems that most lead to the occurrence of interference identified at step (107).
  • Interference includes parameters that are critical for the simulated subgoals and on which it becomes possible to model future states.
  • the noise parameters are analyzed in the time range associated with the input data and take into account combinations of analytical approaches and synthetic modeling based on the generated knowledge base on the subject of the problem being solved. The ranking of systems and their influence allows for a more accurate filtering of the outcomes of solving the problem.
  • step (109) the selection of options for modeling the properties of existing systems, in which subgoals are implemented with the least resource costs, and options for eliminating the causes of interference based on the parameters characterizing the task, are selected.
  • This stage is carried out with the help of a decisive block and a knowledge base, based on the ranking of subgoals for their final accounting.
  • the selected options are filtered and sorted, taking into account the input conditions and restrictions, after which at the stage (111) generate a chain of actions for solving problems based on the options identified at the stage (PO).
  • the chain of actions includes a set of options for actions leading to the final result of solving the problem.
  • the chain of actions is formed based on the maximum saving of resources with the maximum expected result of solving the problem.
  • the chain of actions may take into account: the likely speed of the implementation of the action, the amount of resources needed for the action, the amount of potential financial and other types of costs, potential negative impacts, the skills and knowledge necessary for the implementation of the action, organizations interested in solving the problem, the necessary conditions for the implementation of the action, required systems in the form of objects and actions.
  • the chain is formed in a hierarchical order, where for each action there can be several stages, which can form variations of the chains of stages and goals to achieve the desired effect.
  • FIG. 2 shows a general view of the automated problem solving system (200).
  • the claimed system consists of the following components:
  • the above modules (201) - (211) are interconnected and can be a single computing device, such as a computer, or a set of devices that provide the implementation of a given functionality.
  • the system (200) makes it possible to implement the above method (100) with the help of firmware, with the execution of the corresponding steps of the method (100) using firmware modules, the functionality of which will be described below.
  • the data receiving module (201) is configured to receive data containing parameters characterizing the task being solved, which include a description of the task objects and data describing conditions and restrictions.
  • various input information can be used as input to model the implementation of the input task. For example, predicting an increase in the attendance of a business facility, an increase in sales, an increase in the company's capitalization, the geographic location of an object, the average throughput, the number of employees, costs, consumables, etc.
  • the data forms common basic entities to form the input state of the model for its further formation and analysis of stages to solve the problem.
  • the database (202) contains information on similar categories of tasks, taking into account the received data containing the conditions, restrictions and objects of the task.
  • the database is updated and contains information about similar implementations of tasks, which allows you to obtain modeling parameters for solving a problem based on successful examples of implementing similar or similar tasks.
  • the simulation module (203) is configured to simulate at least one state of the objects of the problem being solved at the time of obtaining the final result using the database.
  • the module for creating a list of steps of actions (204) is configured to create a list of sequential steps of actions to achieve a positive final result of solving the problem.
  • the sub-goal generation module (205) is configured to generate sub-goals within the steps; at the same time, subgoals contain actions and/or properties of stage objects that are necessary to solve the task of this stage.
  • the module for detecting operating systems (206) is configured to identify operating systems necessary for the implementation of the final result and for the implementation of subgoals within the stages; while the systems contain a set of actions and/or objects.
  • the module for modeling the properties of operating systems (207) performs modeling of the properties of operating systems, in which subgoals are implemented with the least cost of resources.
  • the interference detection module (208) is configured to:
  • the module for selecting options for actions (209) selects options for modeling the properties of existing systems in which subgoals are implemented with the least resource costs, and options for eliminating the causes of interference based on the parameters that characterize the task.
  • the filtering and sorting module (210) is configured to filter and sort the selected actions based on input conditions and constraints.
  • the generation module (211) is configured to generate a chain of actions for solving problems based on the options determined by the filtering and sorting module.
  • the claimed decision is carried out using a machine learning model, and the results of the machine learning model can be evaluated and corrected via the Internet. Correction is necessary for a more accurate selection of options for actions, systems and objects to solve the problem at each stage. For the most effective solution of problems, it is necessary to rely on reliable information in the current and predicted time slices. Additional training of machine learning models allows leveling possible inaccuracies in the classification of events and related parameters.
  • the system (200) can be implemented as a cloud platform and be a client-server architecture for end users to access it. Also, the system (200) can be executed as an expert system and integrated into the company's internal infrastructure, for example, to generate business plans, analytical slices, etc.
  • FIG. 3 shows an example of a general view of a computing system (300), which provides the implementation of the claimed method (100) or is a part of a computer system (for example: a server, a personal computer, a part of a computing cluster) that processes the necessary data to implement the claimed technical solution.
  • a computing system 300
  • FIG. 3 shows an example of a general view of a computing system (300), which provides the implementation of the claimed method (100) or is a part of a computer system (for example: a server, a personal computer, a part of a computing cluster) that processes the necessary data to implement the claimed technical solution.
  • the system (300) comprises one or more processors (301), memory means such as RAM (302) and ROM (303), input/output interfaces (304), one or more means of input/output (305) and a device for networking (306).
  • the processor (301) (or multiple processors, multi-core processor, etc.) can be selected from a variety of devices currently widely used, for example, manufacturers such as IntelTM, AMDTM, AppleTM, Samsung ExynosTM , MediaTEKTM, Qualcomm SnapdragonTM, etc.
  • the processor or one of the processors used in the system (300) should also be understood as a graphics processor, such as NVIDIA GPU or Graphcore, the type of which is also suitable for full or partial execution of the method (100), and can also be used to train and apply machine learning models in various information systems.
  • a graphics processor such as NVIDIA GPU or Graphcore, the type of which is also suitable for full or partial execution of the method (100), and can also be used to train and apply machine learning models in various information systems.
  • RAM (302) is a random access memory and is designed to store machine-readable instructions executable by the processor (301) to perform the necessary data logical processing operations.
  • the RAM (302) typically contains the executable instructions of the operating system and associated software components (applications, program modules, etc.). In this case, the RAM (302) may be the available memory of the graphics card or graphics processor.
  • a ROM (303) is one or more persistent storage devices such as a hard disk drive (HDD), a solid state drive (SSD), flash memory (EEPROM, NAND, etc.), optical storage media ( CD-R/RW, DVD-R/RW, BlueRay Disc, MD), etc.
  • I/O interfaces (304) are used to organize the operation of system components (300) and organize the operation of external connected devices.
  • the choice of appropriate interfaces depends on the specific version of the computing device, and therefore the I / O interfaces (304) can be: PCI, AGP, PS / 2, IrDa, FireWire, LPT, COM, SATA, WEE, Lightning, USB (2.0 , 3.0, 3.1, micro, mini, type C), TRS/Audio jack (2.5, 3.5, 6.35), HDMI, DVI, VGA, Display Port, RJ45, RS232 and T. n.
  • various means (305) of I/O information are used, for example: keyboard, display (monitor), touch display, touchpad, joystick, mouse, light pen, stylus, touch panel , trackball, speakers, microphone, augmented reality, optical sensors, tablet, indicator lights, projector, camera, biometric identification tools (retinal scanner, fingerprint scanner, voice recognition module), etc.
  • the networking tool (306) provides data transmission via an internal or external computer network, for example: intranet, Internet, LAN, etc.
  • One or more means (306) can be used (but not limited to): Ethemet card, GSM modem, GPRS modem, LTE modem, 5C modem, satellite communication module, NFC module, Bluetooth and/or BLE module, Wi-Fi module, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention concerne un procédé et un système de résolution de tâches. Le procédé de résolution de tâches comprend les étapes suivantes: obtenir des données comprenant des paramètres caractérisant la tâche à résoudre; modéliser l'état d'objets de la tâche à résoudre au moment de l'obtention d'un résultat initial; générer une liste des étapes successives d'actions afin d'obtenir un résultat initial positif de la résolution de tâche; générer des objectifs secondaires dans les étapes; révéler les systèmes actifs nécessaires pour atteindre le résultat initialé et pour atteindre les objectifs secondaires dans les étapes; modéliser les propriétés des systèmes actifs selon lesquels les objectifs secondaires sont réalisés en consommant un minimum de ressources; révéler les interférences ayant une action sur la réalisation des objectifs secondaires et des consommations de ressources s'y greffant; découvrir les raisons des interférences; effectuer une sélection des variantes d'action afin de modéliser les propriétés des systèmes actifs selon lesquels les objectifs secondaires sont réalisés en consommant un minimum de ressources, et des variantes d'élimination des causes des interférences sur la base des paramètres caractérisant la tâche; effectuer une filtration et un tri des variantes d'actions choisies; et générer une chaîne d'actions afin de résoudre les tâches sur la base des variantes.
PCT/RU2021/050099 2020-07-09 2021-04-14 Procédé et système automatisé de résolution de tâches WO2022010380A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
RU2020122823 2020-07-09
RU2020122823A RU2744767C1 (ru) 2020-07-09 2020-07-09 Способ и автоматизированная система решения задач

Publications (1)

Publication Number Publication Date
WO2022010380A1 true WO2022010380A1 (fr) 2022-01-13

Family

ID=74874364

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2021/050099 WO2022010380A1 (fr) 2020-07-09 2021-04-14 Procédé et système automatisé de résolution de tâches

Country Status (2)

Country Link
RU (1) RU2744767C1 (fr)
WO (1) WO2022010380A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117235829A (zh) * 2023-09-20 2023-12-15 四川大学 一种创新设计机会识别与表征方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5596502A (en) * 1994-11-14 1997-01-21 Sunoptech, Ltd. Computer system including means for decision support scheduling
US7512583B2 (en) * 2005-05-03 2009-03-31 Palomar Technology, Llc Trusted decision support system and method
RU2607977C1 (ru) * 2015-06-30 2017-01-11 Александр Игоревич Колотыгин Способ создания модели объекта

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5596502A (en) * 1994-11-14 1997-01-21 Sunoptech, Ltd. Computer system including means for decision support scheduling
US7512583B2 (en) * 2005-05-03 2009-03-31 Palomar Technology, Llc Trusted decision support system and method
RU2607977C1 (ru) * 2015-06-30 2017-01-11 Александр Игоревич Колотыгин Способ создания модели объекта

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
PETROVSKY A.B.: "Teoriya prinyatiya resheny", UNIVERSITETSKY UCHEBNIK. PRIKLADNAYA MATEMATIKA I INFORMATIKA. MOSKVA, IZDATELSKY TSENTR ''AKADEMIYA, 2009, ISBN: 978-5-7695-5093-5 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117235829A (zh) * 2023-09-20 2023-12-15 四川大学 一种创新设计机会识别与表征方法及系统
CN117235829B (zh) * 2023-09-20 2024-04-30 四川大学 一种创新设计机会识别与表征方法及系统

Also Published As

Publication number Publication date
RU2744767C1 (ru) 2021-03-15

Similar Documents

Publication Publication Date Title
Masum et al. Intelligent human resource information system (i-HRIS): A holistic decision support framework for HR excellence.
Angilella et al. The financing of innovative SMEs: A multicriteria credit rating model
Holdaway Harness oil and gas big data with analytics: Optimize exploration and production with data-driven models
Owolabi et al. Predicting completion risk in PPP projects using big data analytics
Assefa Tsehayae et al. Developing and optimizing context-specific fuzzy inference system-based construction labor productivity models
US20120158624A1 (en) Predictive modeling
Alalawneh et al. The barriers to big data adoption in developing economies
Dittert et al. A data analytics framework for business in small and medium-sized organizations
WO2022010380A1 (fr) Procédé et système automatisé de résolution de tâches
CN117519656A (zh) 一种基于智能制造的软件开发系统
Elwakil et al. Construction knowledge discovery system using fuzzy approach
Saleem et al. Systematic literature review of identifying issues in software cost estimation techniques
Ensafi et al. Machine learning and artificial intelligence applications in building construction: present status and future trends
US20220414504A1 (en) Identifying traits of partitioned group from imbalanced dataset
Dagnaw et al. Data management practice in 21st century: systematic review
Filipkovska et al. Managerial decision support making in economic systems based on cognitive modeling
Puica Predictive analytics functionalities in supply chain management
Nguyen et al. Digital Strategies for Aiding Ease of Decision-Making in the Services Sector
Alshammari Design of System‐of‐System Acquisition Analysis Using Machine Learning
CN109359133B (zh) 基于大数据和深度学习的个性化认定方法和机器人系统
Nikolaevich Problem of Criteria Space Dynamism at Management and Conceptual Approaches for Its Solutions
Chaitongrat et al. Comparing data mining methods for predicting cost construction projects: A case study of cost management datasets from Thailand
Leopold et al. Artificial Intelligence Landscape
Shrivastava et al. Machine Learning: Future Prospectus and Research Direction
Hammoumi et al. Machine Learning (ai) for Identifying Smart Cities

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21837545

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21837545

Country of ref document: EP

Kind code of ref document: A1