Intelligent decision-making method and device based on service configuration, equipment and medium

Abstract

The invention discloses an intelligent decision-making method and device based on service configuration, equipment and a medium, and the method comprises the steps: collecting real-time service data in a service system, employing a machine learning algorithm to carry out the learning recognition of noise data features, dynamically updating a data cleaning rule, and carrying out the recognition of the real-time service data. Cleaning the real-time business data according to the updated data cleaning rule to obtain standardized business data, obtaining a current business configuration model according to the business type, importing the standardized business data into the current business configuration model, and analyzing and processing the standardized business data through the current business configuration model to obtain the real-time business data. According to the method, the decision can be accurately adjusted according to the new situation, and the decision method is dynamically and flexibly configured based on the service data, so that new requirements brought by service changes are adaptively met.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent decision-making method, device, equipment and medium based on business configuration. Background Art

[0002] At present, facing massive data and a rapidly changing business environment, the business scenarios required by various industries are becoming increasingly complex and diverse. Traditional business decision-making models mostly rely on manual experience. Decision makers need to spend a lot of time collecting, organizing and analyzing various types of business data, trying to find patterns from complex information to make appropriate decisions. For example, in the field of supply chain management, manual labor must comprehensively consider many factors such as raw material price fluctuations, supplier delivery cycles, inventory levels, market demand forecasts, etc., which is not only inefficient, but also prone to decision-making errors due to human negligence or cognitive limitations. Even if some business scenarios introduce information automation systems to assist decision-making, these systems are often inflexible and mostly run based on fixed algorithms for preset scenarios. When business rules, processes or external environments change, the original automated decision-making module cannot quickly and accurately adjust decisions based on the new situation, making it difficult to adaptably meet new demands brought about by business changes. Summary of the invention

[0003] The embodiments of the present invention provide an intelligent decision-making method, device, equipment and medium based on business configuration to solve the problem that the original automated decision-making module cannot quickly and accurately adjust the decision according to the new situation, and thus it is difficult to adaptively meet the new demands brought about by business changes.

[0004] An intelligent decision-making method based on business configuration, comprising: Collect real-time business data in the business system, including business type, business process information, business resource status information and user interaction information; Use machine learning algorithms to learn and identify the characteristics of noise data, dynamically update data cleaning rules, clean real-time business data according to the updated data cleaning rules, remove noise data and redundant data, and obtain standardized business data; According to the business type, determine the matching historical business configuration model, fine-tune the business configuration model in real time based on real-time data, and obtain the current business configuration model; Import standardized business data into the current business configuration model; Standardized business data is analyzed and processed through the current business configuration model, and intelligent decision results corresponding to the business type are generated through the decision logic module.

[0005] An intelligent decision-making device based on business configuration, comprising: The business data collection module is used to collect real-time business data in the business system. The real-time business data includes business type, business process information, business resource status information and user interaction information; The business data acquisition module is used to use machine learning algorithms to learn and identify the characteristics of noise data, dynamically update data cleaning rules, clean real-time business data according to the updated data cleaning rules, remove noise data and redundant data, and obtain standardized business data; The business model acquisition module is used to determine the matching historical business configuration model according to the business type, fine-tune the business configuration model in real time based on real-time data, and obtain the current business configuration model; Business data import module, used to import standardized business data into the current business configuration model; The decision result generation module is used to analyze and process the standardized business data through the current business configuration model, and generate intelligent decision results corresponding to the business type through the decision logic module.

[0006] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned intelligent decision-making method based on business configuration when executing the computer program.

[0007] A computer-readable medium stores a computer program, and when the computer program is executed by a processor, the intelligent decision-making method based on business configuration is implemented.

[0008] The above-mentioned intelligent decision-making method, device, equipment and medium based on business configuration collect real-time business data in the business system, use machine learning algorithms to learn and identify noise data characteristics, dynamically update data cleaning rules, clean the real-time business data according to the updated data cleaning rules, obtain standardized business data, obtain the current business configuration model according to the business type, import the standardized business data into the current business configuration model, analyze and process the standardized business data through the current business configuration model, and generate intelligent decision results corresponding to the business type through the decision logic module. When the business rules, processes or external environment change, this method can accurately adjust the decision according to the new situation, and dynamically and flexibly configure the decision-making method based on the business data, so as to adaptively meet the new needs brought about by business changes and improve the accuracy of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0010] Figure 1 A schematic diagram of an application environment of an intelligent decision-making method based on business configuration in one embodiment of the present invention is depicted; Figure 2 A first flow chart of an intelligent decision-making method based on business configuration in a first embodiment of the present invention is shown; Figure 3 A second flow chart of the intelligent decision-making method based on business configuration in the second embodiment of the present invention is shown; Figure 4 A third flow chart of the intelligent decision-making method based on business configuration in the third embodiment of the present invention is shown; Figure 5 A fourth flow chart of an intelligent decision-making method based on business configuration in a fourth embodiment of the present invention is shown; Figure 6 A schematic diagram of an intelligent decision-making device based on business configuration in one embodiment of the present invention is depicted; Figure 7 A schematic diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] The intelligent decision-making method based on business configuration provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the intelligent decision method based on business configuration is applied in an intelligent decision system based on business configuration, and the intelligent decision system based on business configuration includes a client and a server, wherein the client communicates with the server through a network. The client, also known as the user end, refers to a program corresponding to the server and providing local services for the client.

[0013] Furthermore, the client is a computer program, an APP program of a smart device, or a third-party applet embedded in other APPs. The client can be installed on, but not limited to, various electronic devices such as personal computers, laptops, smart phones, tablet computers, and portable wearable devices.

[0014] The server can be implemented as an independent server or a server cluster consisting of multiple servers to build the infrastructure of the entire intelligent decision-making system and build an initial business configuration model framework including a business rule library, a business parameter library, and a decision logic module. The business rule library organizes and stores detailed operating rules for various businesses based on past business experience, industry specifications, and internal corporate standards; the business parameter library refers to key parameters in the business process, such as the upper limit of order processing time, resource utilization threshold, etc., and clarifies the conventional threshold range; the decision logic module is based on pre-set business rules and parameter threshold ranges, and has the initial ability to generate decision recommendations, providing an infrastructure for subsequent accurate decision-making based on real-time data.

[0015] In one embodiment, if Figure 2 As shown, an intelligent decision-making method based on business configuration is provided, and the method is applied in Figure 1 The server in the example is used as an example, and the specific steps include the following: S110. Collect real-time business data in the business system, where the real-time business data includes business type, business process information, business resource status information, and user interaction information.

[0016] Specifically, in order to ensure that the real-time information of dynamic changes in the operation of the business system can be captured accurately and comprehensively, this embodiment proposes a distributed data collection architecture that is both innovative and efficient. This architecture integrates IoT sensor technology, intelligent network routing strategies, and adaptive data transmission protocols. Whether it is the source endpoint for business initiation, such as the entry interface for customers to submit business applications; or the core hub of business flow, such as the department system responsible for key approval and data processing in the internal process; or the boundary port for interaction with external related parties, such as the data interface for connecting suppliers and partners, all belong to the scope of information collection.

[0017] Real-time monitoring of business resource status information. Taking a large cloud computing data center as an example, the probe continuously monitors the real-time status of various resources. At the hardware level, it not only closely monitors the physical cabinet space occupancy rate of the server room and the real-time operating parameters of the server cooling system to ensure a stable and appropriate server operating environment, but also monitors key indicators such as port utilization, bandwidth throughput, and other network devices such as network switches and routers in real time to ensure high-speed and smooth data transmission; at the software level, it continuously monitors the number of various virtual instances running in the cloud computing management system (CMS), the length of the massive data task queue being processed, the data interaction delay with external customers, and the allocation and utilization of storage resources.

[0018] The acquisition of user interaction information is explained through a game platform scenario. Every time a user logs in to a game, creates a character, selects a level, purchases and uses items, communicates and speaks in the game community, and the length and location of a user's hesitation on the main interface of the game are accurately captured by the probe. With the help of deep learning algorithms, sentiment analysis engines, and user behavior clustering models, the user's game preferences are deeply analyzed, such as the type of game they are interested in, whether it is competitive battle, role-playing, or casual puzzle; the user's game emotions are captured in real time, such as the frustration after losing several games in a row, or the excitement after conquering a difficult level.

[0019] In summary, through the comprehensive, real-time and in-depth collection of business types, business process information, business resource status information and user interaction information, effective data is provided for the intelligent decision-making system of the embodiment of the present application to drive the efficient operation of subsequent key processes such as data cleaning, dynamic optimization of models and accurate decision-making.

[0020] S120. Use machine learning algorithms to learn and identify the characteristics of noise data, dynamically update data cleaning rules, clean real-time business data according to the updated data cleaning rules, remove noise data and redundant data, and obtain standardized business data.

[0021] Specifically, machine learning algorithms, not limited to support vector machines, random forests, gradient boosting trees, etc., are used to perform deep learning and identification of noise data features to adapt to the dynamic changes of business data. With the continuous advancement of business and the continuous accumulation of data, the algorithm continues to evolve and dynamically update the data cleaning rules. According to the updated rules, the business data collected in real time is finely cleaned, the noise data is accurately removed, the relevant data is extracted from the data source, and cleaned, converted and standardized to form decision input data, such as erroneous data caused by network fluctuations, abnormal readings caused by sensor failures, and redundant data, such as duplicated business process information, etc., so as to obtain high-quality standardized business data and provide effective basic data for subsequent analysis and processing.

[0022] S130. Determine a matching historical business configuration model according to the business type, perform real-time fine-tuning on the business configuration model based on real-time data, and obtain a current business configuration model.

[0023] Specifically, based on the business type in the collected real-time business data, quickly determine the matching historical business configuration model in the existing model library. At the same time, based on the real-time, complexity and data volume characteristics of real-time data, fine-tune the model in real time. Analyze the complexity of real-time business data. If it involves complex businesses with multi-process intersections and multi-department collaboration, appropriately increase the complexity of the model; consider real-time requirements, and optimize the model structure to improve computing efficiency for businesses with extremely high response speed requirements; combined with the size of the data, reasonably expand the processing capabilities of the model in large data volume scenarios. Introduce a model library containing pre-trained model templates, and quickly generate a current business configuration model that accurately adapts to current business needs based on the model type and complexity determined by the above analysis.

[0024] S140. Import the standardized business data into the current business configuration model.

[0025] S150. The current business configuration model analyzes and processes the standardized business data, and generates intelligent decision results corresponding to the business type through the decision logic module.

[0026] Specifically, the standardized business data includes business rules, user-defined policies and system default policies, the business rules, user-defined policies and system default policies are merged to generate comprehensive business rules, the comprehensive business rules are parsed to generate logical expressions, and the logical expressions are converted into executable decision trees or rule engines.

[0027] The current business configuration model predicts, classifies or optimizes the standardized business data, generates intelligent decision results corresponding to the business type through the decision logic module, and outputs the final decision results in a user-understandable form, including but not limited to reports, charts or direct operation instructions. Accurately import the cleaned standardized business data into the current business configuration model, and the various components within the model work together. The business rule library provides basic rule guidance, the business parameter library sets key parameter constraints, and the decision logic module conducts in-depth analysis and processing of standardized business data based on core elements, generates intelligent decision results for the current business type, and provides adaptive action plans for business operations.

[0028] The intelligent decision-making method based on business configuration provided in this embodiment collects real-time business data in the business system, adopts a machine learning algorithm to learn and identify the characteristics of noise data, dynamically updates data cleaning rules, cleans the real-time business data according to the updated data cleaning rules, obtains standardized business data, obtains the current business configuration model according to the business type, imports the standardized business data into the current business configuration model, analyzes and processes the standardized business data through the current business configuration model, and generates intelligent decision results corresponding to the business type through the decision logic module. When the business rules, processes or external environment change, the method can accurately adjust the decision according to the new situation, and dynamically and flexibly configure the decision-making method based on the business data, so as to adaptively meet the new needs brought about by business changes and improve the accuracy of decision-making.

[0029] In a specific embodiment, in step S110, i.e. collecting real-time business data in the business system, the following steps are specifically included: S210. Adopt a distributed data collection architecture, set up data collection probes at multiple key nodes of the business system, and aggregate the collected data into a data buffer pool through asynchronous transmission.

[0030] Specifically, a distributed data collection architecture is adopted to deploy data collection probes at various key nodes of the business system. These nodes cover the starting end of the business process, key processing links, and parts that frequently interact with users, etc., which can fully capture various types of information on business operations. Through asynchronous transmission, the collected data is efficiently and stably aggregated into the data buffer pool, providing sufficient original materials for subsequent data processing.

[0031] During the daily operation of the business system, data collection probes are continuously active, accurately collecting real-time business data. These real-time business data not only cover the business type, clearly identifying the specific category of the current business, such as e-commerce order processing, financial loan approval, etc.; they also include detailed business process information, recording the flow status and processing time of the business in each link; business resource status information is also crucial, reflecting the server load, inventory quantity, human resource allocation, etc. in real time; as well as user interaction information, such as user operation records, feedback, preference choices, etc. Through all-round collection, rich and three-dimensional data support is provided for intelligent decision-making to ensure the timeliness and comprehensiveness of data collection and reduce interference with the normal operation of the business system.

[0032] In a specific embodiment, if Figure 3 As shown, the intelligent decision-making method based on business configuration provided in this embodiment further specifically includes the following steps: S310. Regularly update and maintain the business configuration model, including: S311. Every preset time period, collect new historical business data, update and improve the business rules in the business rule library, add new business rules or correct old rules.

[0033] S312. Recalibrate key parameters and their threshold ranges in the business parameter library based on business development needs and industry dynamics.

[0034] S313. Use reinforcement learning algorithm to optimize and train the decision logic module.

[0035] Specifically, a comprehensive model update and maintenance process is initiated at preset time intervals. New historical business data is fully collected, new business rules are mined, and the business rule library is added in a timely manner. At the same time, old rules are revised, such as data that does not conform to actual business conditions to ensure the real-time nature of the rules; at the same time, the key parameters and their threshold ranges in the business parameter library are recalibrated in close combination with business development needs and industry dynamic adjustments to match the current business environment. The decision logic module is trained with high intensity optimization using reinforcement learning algorithms to continuously improve the scientificity and accuracy of its decisions, and can generate more accurate and efficient decision recommendations based on updated business rules and parameter threshold ranges.

[0036] In a specific embodiment, before step S130, that is, before determining the matching historical service configuration model, the following steps are further specifically included: S410. Construct an initial business configuration model based on historical business data and industry standard business processes, which is used to generate a historical business configuration model based on real-time data and the initial business configuration model, wherein the initial business configuration model includes: a business rule library, a business parameter library and a decision logic module, wherein the business rule library stores the operating rules of various types of businesses, the business parameter library stores the key parameters in the business process and their threshold ranges, and the decision logic module generates decision recommendations based on the business rules and parameter threshold ranges.

[0037] Specifically, the business rule library includes business rules, user-defined policies, and system default policies. This embodiment first collects massive and representative historical business data, which are derived from business records accumulated over a long period of time in the past, covering practical data at different stages and in different business scenarios. Taking financial credit business as an example, historical business data includes loan application records over the years, involving detailed information such as credit qualifications, loan amounts, repayment periods, default situations, etc. of different customer groups; industry standard business processes include standard operating sequences and specification requirements for each link from customer loan application submission, to credit assessment, risk review, loan approval, and post-loan management.

[0038] Based on the above solid data and process foundation, we started to build the initial business configuration model. For financial credit business, the rule base stores rules such as customer qualification review rules, which clearly stipulate the minimum credit score requirements corresponding to different loan amount ranges; loan issuance rules, which record the risk assessment level under which loans can be approved and the upper limit of the loan amount; post-loan monitoring rules, such as the time node and frequency of overdue repayment reminders, and the trigger conditions for taking collection measures and other operational details.

[0039] The business parameter library stores key parameters and their threshold ranges in the business process. Taking the credit business as an example, key parameters include the annual interest rate of the loan. A reasonable threshold range is set based on factors such as market interest rate fluctuation trends, corporate funding costs, and risk premiums. For example, in a stable market, the annual interest rate threshold for conventional consumer loans is set at 4% to 12%; the upper limit of the loan amount is set based on the company's capital reserves and risk tolerance, and differentiated upper limits are set for customers with different credit ratings. For example, customers with good credit can borrow up to 500,000 yuan, and ordinary customers can borrow up to 200,000 yuan; the weight of risk assessment indicators, such as credit score accounting for 40%, assets and liabilities accounting for 30%, and income stability accounting for 30%, etc., accurately quantify the impact of various factors on risk judgment.

[0040] The decision logic module is a decision suggestion module generated based on business rules and parameter threshold ranges. When real-time business data flows in, such as a customer submitting a loan application, the module quickly retrieves the business rule library to verify whether the customer meets the basic application conditions, and then refers to the business parameter library to assess its risk status. If the customer's credit score is 70 points and applies for a 3-year loan of 300,000 yuan, the module will determine that the customer's risk is controllable based on the set rules and parameters, combined with the current market interest rate of 6%, and recommend approval of the loan. At the same time, it will give detailed decision content such as the recommended loan interest rate of 6% and a repayment period of 3 years.

[0041] The initial business configuration model constructed above can quickly integrate and interact with the data after receiving real-time data. Through continuous iterative optimization, it can generate a historical business configuration model that is highly adapted to the current business scenario and continuously provide intelligent decision-making.

[0042] For other industry fields, such as manufacturing and e-commerce, targeted optimization can be carried out in terms of historical business data selection, compliance with industry standard processes, business rule customization, parameter threshold setting, and decision logic design based on the characteristics of each industry, to ensure the unity of universality and professionalism of the initial business configuration model.

[0043] In a specific embodiment, the real-time business data also includes target optimization indicators. Figure 4 As shown, after step S150, that is, after the intelligent decision result corresponding to the business type is generated by the decision logic module, the following steps are specifically included: S510. Evaluate the intelligent decision-making results according to the target optimization index. If the preset standard is not met, extract the parameter deviation item.

[0044] Specifically, this embodiment can set a target optimization indicator system for different business types. Taking the e-commerce order processing business as an example, the target optimization indicator covers the order processing time, which can control the average processing time within a specific threshold, such as within 2 hours; inventory turnover rate, which is expected to be maintained in a trust interval through reasonable decision-making to ensure capital liquidity, such as 3-5 turnovers per month; customer return rate, which is reduced to a certain proportion not exceeding 5%, reflecting that the quality of products and services meets market demand.

[0045] When the intelligent decision-making system outputs the processing decision for a batch of e-commerce orders based on the current business configuration model, the evaluation process is immediately started. By real-time monitoring of the actual time spent in each link from order receipt to delivery, comparing the real-time inventory change data fed back by the inventory system and the customer return information counted by the after-sales department, and checking them one by one with the preset target optimization indicators. When the average processing time of the order reaches 3 hours, exceeding the preset 2-hour standard, the system quickly enters the deep analysis mode to extract the parameter deviation items that caused this delay. After investigation, it was found that the unreasonable scheduling of delivery vehicles in a certain area in the logistics distribution link caused some orders to wait too long for delivery. The "logistics distribution vehicle allocation ratio" was accurately locked as the key parameter deviation item.

[0046] S520. Obtain all relevant deviation factors related to the parameter deviation item, and based on all relevant deviation factors, adjust the current business configuration model or adopt other optimization strategies until the target optimization index is met.

[0047] Specifically, continuing with the previous example, after locking in the parameter deviation item "logistics distribution vehicle allocation ratio", the system can conduct a comprehensive search to mine all relevant deviation factors closely related to it. The relevant deviation factors that affect the vehicle allocation ratio include: real-time fluctuations in order volume in different regions, where the order volume in some popular regions surges during promotional activities, but the original vehicle allocation is not followed up in time; road condition information, where some distribution routes become congested due to construction, traffic control and other emergencies, but this is not fully considered during vehicle dispatch; vehicle loading efficiency, where the actual cargo capacity of some models is far lower than the designed capacity due to unreasonable cargo loading layout, reducing the overall distribution efficiency.

[0048] Based on these relevant deviation factors, the system quickly formulates optimization strategies. On the one hand, the current business configuration model is precisely adjusted, and a real-time order volume monitoring module is introduced in the logistics distribution sub-model, so that it can automatically optimize the vehicle allocation ratio according to the dynamic changes in the order volume in different regions; at the same time, the real-time road condition update function is embedded, combined with map navigation data, to plan the optimal route for delivery vehicles to avoid congested sections; and optimize the cargo loading algorithm, according to the type and volume of the order goods, reasonably arrange the vehicle loading plan to improve loading efficiency. On the other hand, if the model adjustment is difficult to take effect quickly in the short term, other auxiliary optimization strategies will be immediately activated, such as temporarily increasing outsourced delivery vehicles to alleviate the shortage of transportation capacity during the peak order period; establish information communication channels with the transportation department, obtain road condition warnings in advance, and plan backup routes in advance.

[0049] Continuously execute these two steps in a loop, constantly evaluate decision results based on target optimization indicators, accurately extract and overcome parameter deviation items and their related deviation factors, flexibly adjust models and application strategies, until the e-commerce order processing business fully meets all preset target optimization indicators and improves business operation efficiency.

[0050] Similarly, in other industry business scenarios such as financial credit approval and manufacturing production scheduling, this evaluation and optimization process can also be followed. Only based on the unique target optimization indicators, parameter characteristics and deviation factor association logic of each industry, can the adaptive evaluation methods and adjustment strategies be customized to ensure that the intelligent decision-making system can be accurately adapted in various fields.

[0051] In a specific embodiment, if Figure 5 As shown, in step S130, the business configuration model is fine-tuned in real time based on real-time data to obtain the current business configuration model, which specifically includes the following steps: S610. Analyze the complexity, real-time requirements and data volume of real-time business data, and determine the model type and model complexity.

[0052] Specifically, in the face of real-time business data that increases in real time in different business scenarios, the system first starts a deep analysis process. Take the remote medical diagnosis business in the field of smart medical care as an example. The complexity of real-time business data is reflected in the information intersection of multi-dimensional information. On the one hand, it contains various physiological monitoring data uploaded by patients, such as heart rate, blood pressure, blood sugar and other continuously fluctuating data sequences. The interpretation of these data requires professional medical knowledge, and there are potential correlations and mutual influences between different indicators; on the other hand, there are also unstructured or semi-structured data such as patients' medical history information and imaging diagnosis reports. These heterogeneous data need to be integrated and the key information contained therein needs to be mined.

[0053] Medical data has high real-time requirements. For the diagnosis of some critical diseases, every second of delay may affect the patient's life safety. The system is required to give preliminary diagnostic suggestions within a very short time after receiving the data, such as within a few minutes or even tens of seconds, so that medical staff can take timely treatment measures.

[0054] With the popularity of wearable medical devices and the increase in the frequency of patients seeking medical treatment, data is increasing at a massive rate. For example, a large telemedicine platform may receive various monitoring data from tens of thousands of patients every day, which can accumulate to several GB or more.

[0055] Based on the precise analysis of these characteristics, the system determines the type and complexity of the model that is suitable for it. For this telemedicine diagnosis business, considering the complexity of the data, an intelligent diagnosis model that integrates deep learning algorithms is selected, which can automatically learn the complex mapping relationship between physiological data and diseases, and use natural language processing technology to analyze medical history data; in view of the high real-time requirements, the model structure needs to be optimized and streamlined, reducing unnecessary computing levels to ensure fast computing; in the face of large amounts of data, a distributed computing architecture is used to support model operation and improve data processing capabilities to meet the needs of efficient analysis of massive information, and determine a model architecture that can meet business needs and have efficient execution capabilities.

[0056] S620. Introduce a model library including pre-trained model templates, and generate a current business configuration model based on the model type and model complexity.

[0057] Specifically, after completing the above analysis, the system introduces a model library, which includes a large number of pre-trained model templates. These templates are built based on data and practical experience accumulated in different industries and multiple business scenarios, and have wide applicability and versatility.

[0058] Taking the remote medical diagnosis business as an example, the medical diagnosis model template that best matches the previously determined model type and complexity is selected from the model library. This template has been pre-trained using massive medical data in the early stage, and has a preliminary understanding of the characteristic patterns of common diseases, the relationship between abnormal physiological indicators and diseases, etc.

[0059] Based on this template, we conduct targeted fine-tuning in combination with the real-time data characteristics of current telemedicine services. In terms of data complexity, we optimize the model's feature extraction layer based on the distribution of special diseases in the local patient population and the characteristics of regional high-incidence diseases, so that it can focus more on the disease-related indicators that are of local concern; based on real-time requirements, we further adjust the model's hyperparameters, such as shortening the iterative calculation cycle and optimizing the memory usage strategy to ensure that the model outputs the diagnosis results within the specified time; considering the data volume factor, we rationally configure distributed computing resources to make the model more robust and efficient when processing large-scale data.

[0060] Through such precise adaptation and adjustment process, a current business configuration model that fully meets the current needs of remote medical diagnosis business is finally generated, providing support for subsequent accurate and efficient intelligent decision-making.

[0061] Similarly, in other fields such as intelligent traffic control and industrial automation production, facing the respective real-time business data characteristics, such as real-time road condition data and vehicle driving trajectory data in intelligent traffic, equipment operation parameters and product quality monitoring data in industrial production, this process is strictly followed to ensure that the generated business configuration model is closely related to the actual business, so as to achieve efficient and intelligent operation management.

[0062] and / or After the intelligent decision result corresponding to the business type is generated by the decision logic module, the following steps are specifically included: S630. Use at least one of cross-validation, A / B testing or simulation to verify the intelligent decision-making results and obtain the verification results.

[0063] S640. Continue to adjust the current business configuration model or introduce an adjustment data source according to the verification result.

[0064] Specifically, at least one of the following methods, cross-validation, A / B testing or simulation, is used to rigorously verify the results of intelligent decision-making. Cross-validation uses multiple group tests to comprehensively evaluate the stability and reliability of the model; A / B testing compares the performance differences of different decision-making solutions in actual business scenarios and selects the best solution; simulation uses a virtual environment to simulate business operations and predict the effect of the decision in advance. After obtaining the verification results, if it is found that the decision results are insufficient, continue to fine-tune the current business configuration model based on the feedback of the results, or introduce adjustment data sources and re-optimize the decision process until the decision results reach an effective state.

[0065] In a specific embodiment, the intelligent decision-making method based on business configuration further specifically includes a user interaction interface for displaying business configuration options, decision-making process and optimization suggestions, allowing users to adjust the configuration or confirm the results.

[0066] Specifically, the system is equipped with an intuitive and friendly user interface, which clearly displays business configuration options, allowing users to easily adjust model parameters according to actual business needs; presents the decision-making process in real time, allowing users to gain an in-depth understanding of the decision basis and logical deduction; and provides optimization suggestions to assist users in making more informed decisions. At the same time, it allows users to confirm the final decision results to ensure the smoothness and acceptance of the decision implementation.

[0067] In a specific embodiment, the intelligent decision-making method based on business configuration further specifically includes: establishing a risk warning mechanism to perform real-time monitoring and warning of potential risk points.

[0068] Specifically, a comprehensive risk warning mechanism is established to conduct uninterrupted real-time monitoring of potential risk points in the business operation process. Through comprehensive analysis of multi-dimensional information such as real-time business data, model operation status, external environmental factors, etc., risks can be predicted in advance, such as business process blockage risk, resource depletion risk, user loss risk, etc., and accurate warnings can be issued in a timely manner to buy valuable time for enterprises to take timely response measures and ensure the steady and sustainable development of the business.

[0069] The intelligent decision-making method based on business configuration provided in this embodiment collects real-time business data in the business system, adopts a machine learning algorithm to learn and identify the characteristics of noise data, dynamically updates data cleaning rules, cleans the real-time business data according to the updated data cleaning rules, obtains standardized business data, obtains the current business configuration model according to the business type, imports the standardized business data into the current business configuration model, analyzes and processes the standardized business data through the current business configuration model, and generates intelligent decision results corresponding to the business type through the decision logic module. When the business rules, processes or external environment change, the method can accurately adjust the decision according to the new situation, dynamically and flexibly configure the decision-making method based on the business data, ensure the safety and controllability of the decision-making process, thereby adaptively meeting the new needs brought about by business changes and improving the accuracy of decisions.

[0070] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0071] In one embodiment, a smart decision-making device based on business configuration is provided, and the smart decision-making device based on business configuration corresponds to the smart decision-making method based on business configuration in the above embodiment. Figure 6 As shown, the intelligent decision-making device based on business configuration includes a business data collection module 110, a business data acquisition module 120, a business model acquisition module 130, a business data import module 140 and a decision result generation module 150. The functional modules are described in detail as follows: The business data collection module 110 is used to collect real-time business data in the business system. The real-time business data includes business type, business process information, business resource status information and user interaction information.

[0072] The business data acquisition module 120 is used to use a machine learning algorithm to learn and identify noise data features, dynamically update data cleaning rules, clean real-time business data according to the updated data cleaning rules, remove noise data and redundant data, and obtain standardized business data.

[0073] The business model acquisition module 130 is used to determine a matching historical business configuration model according to the business type, perform real-time fine-tuning on the business configuration model based on real-time data, and acquire a current business configuration model.

[0074] The business data import module 140 is used to import standardized business data into the current business configuration model.

[0075] The decision result generation module 150 is used to analyze and process the standardized business data through the current business configuration model, and generate an intelligent decision result corresponding to the business type through the decision logic module.

[0076] For the specific limitations of the intelligent decision-making device based on business configuration, please refer to the limitations of the intelligent decision-making method based on business configuration above, which will not be repeated here. Each module in the above-mentioned intelligent decision-making device based on business configuration can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0077] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile medium and an internal memory. The non-volatile medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile medium. The database of the electronic device is used for data related to the intelligent decision-making method based on business configuration. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent decision-making method based on business configuration is implemented.

[0078] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the intelligent decision-making method based on business configuration in the above embodiment is implemented, for example Figure 2Alternatively, when the processor executes the computer program, the functions of each module / unit of the intelligent decision-making device based on business configuration in the above embodiment are realized, for example Figure 6 The functions of the modules 110 to 150 are shown in detail and will not be described again to avoid repetition.

[0079] In one embodiment, a computer readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the intelligent decision-making method based on business configuration in the above embodiment is implemented, for example Figure 2 Alternatively, when the computer program is executed by the processor, the functions of each module / unit in the intelligent decision-making device based on business configuration in the above device embodiment are realized, for example Figure 6 The functions of the modules 110 to 150 are shown in detail and will not be described again to avoid repetition.

[0080] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments of the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (RM), programmable RM (PRM), electrically programmable RM (EPRM), electrically erasable programmable RM (EEPRM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0081] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0082] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent decision-making method based on business configuration, characterized in that: include: Collecting real-time business data in the business system, the real-time business data includes business type, business process information, business resource status information and user interaction information; Using a machine learning algorithm to learn and identify the characteristics of noise data, dynamically updating data cleaning rules, cleaning the real-time business data according to the updated data cleaning rules, removing noise data and redundant data, and obtaining standardized business data; According to the business type, a matching historical business configuration model is determined, and the business configuration model is fine-tuned in real time based on real-time data to obtain a current business configuration model; Importing the standardized business data into the current business configuration model; The standardized business data is analyzed and processed through the current business configuration model, and an intelligent decision result corresponding to the business type is generated through a decision logic module.

2. The intelligent decision-making method based on business configuration according to claim 1, characterized in that: The real-time business data collected in the business system includes: Adopting a distributed data collection architecture, setting up data collection probes at multiple key nodes of the business system, and aggregating the collected data into a data buffer pool through asynchronous transmission; The method according to claim 1, the intelligent decision-making method based on business configuration according to claim 1, characterized in that it also includes: Regularly update and maintain the business configuration model, including: At preset time intervals, new historical business data is collected to update and improve the business rules in the business rule library, supplement new business rules or amend old rules; Recalibrate the key parameters and their threshold ranges in the business parameter library according to business development needs and industry dynamic adjustments; The decision logic module is optimized and trained using a reinforcement learning algorithm.

3. The intelligent decision-making method based on business configuration according to claim 1, characterized in that: Before determining the matching historical business configuration model, the method further includes: An initial business configuration model is constructed based on historical business data and industry standard business processes, and is used to generate a historical business configuration model based on real-time data and the initial business configuration model, wherein the initial business configuration model includes: a business rule library, a business parameter library, and a decision logic module, wherein the business rule library stores the operation rules of various types of businesses, the business parameter library stores the key parameters in the business process and their threshold ranges, and the decision logic module generates decision recommendations based on the business rules and parameter threshold ranges.

4. The intelligent decision-making method based on business configuration according to claim 1, characterized in that: The real-time business data also includes target optimization indicators; After the intelligent decision result corresponding to the business type is generated by the decision logic module, the method further includes: Evaluate the intelligent decision-making result according to the target optimization index, and if it does not meet the preset standard, extract the parameter deviation item; All relevant deviation factors related to the parameter deviation item are obtained, and based on all the relevant deviation factors, the current business configuration model is adjusted or other optimization strategies are adopted until the target optimization index is met.

5. The intelligent decision-making method based on business configuration according to claim 1, characterized in that: The fine-tuning of the service configuration model in real time based on the real-time data to obtain the current service configuration model includes: Analyze the complexity, real-time requirements and data volume of the real-time business data to determine the model type and model complexity; Introducing a model library including pre-trained model templates, and generating the current business configuration model according to the model type and the model complexity; and / or After the intelligent decision result corresponding to the business type is generated by the decision logic module, the method further includes: Verify the intelligent decision-making result by using at least one method of cross-validation, A / B testing or simulation, and obtain the verification result; The current business configuration model continues to be adjusted or an adjustment data source is introduced according to the verification result.

6. The intelligent decision-making method based on business configuration according to claim 1, characterized in that: It also includes a user interaction interface for displaying business configuration options, decision-making processes and optimization suggestions, allowing users to make configuration adjustments or confirm results.

7. The intelligent decision-making method based on business configuration according to claim 1, characterized in that: It also includes establishing a risk warning mechanism to conduct real-time monitoring and warning of potential risk points.

8. An intelligent decision-making device based on business configuration, characterized in that: include: A business data collection module is used to collect real-time business data in the business system, wherein the real-time business data includes business type, business process information, business resource status information and user interaction information; A business data acquisition module is used to learn and identify noise data features using a machine learning algorithm, dynamically update data cleaning rules, clean the real-time business data according to the updated data cleaning rules, remove noise data and redundant data, and obtain standardized business data; A business model acquisition module is used to determine a matching historical business configuration model according to the business type, and to fine-tune the business configuration model in real time based on real-time data to obtain a current business configuration model; A business data import module, used to import the standardized business data into the current business configuration model; The decision result generating module is used to analyze and process the standardized business data through the current business configuration model, and to generate an intelligent decision result corresponding to the business type through a decision logic module.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the intelligent decision-making method based on business configuration as described in any one of claims 1 to 7 is implemented.

10. A computer-readable medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent decision-making method based on business configuration as claimed in any one of claims 1 to 7 is implemented.

Images