Total factor intelligent service modeling method, device and equipment

Abstract

The application discloses a kind of full-factor intelligent business modeling methods, device and equipment, it is related to computer technical field, the method includes: obtaining the multi-source heterogeneous data in business scene and business optimization target, data is filled in to multi-source heterogeneous data Processing, obtain structured data set;Structural data set is mined to element and is handled, and obtain structured element set;Structured element set includes: entity element, environmental element and tool element;Based on structural element set carries out process digitization processing, constructs business process model;Business process model is used to characterize the process relationship between each element in structured element set;To business process model carries out decision prediction processing, obtain predictive information;Based on predictive information and business optimization target carries out business target optimization processing, determines business decision result.The application makes that the modeling element obtained is more comprehensive, improves the accuracy of modeling processing.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and equipment for full-element intelligent business modeling. Background Technology

[0002] As industrial digitalization deepens, business modeling and intelligent decision-making technologies have gradually become core drivers for overcoming efficiency bottlenecks across various industries. Whether it's precise production control in manufacturing, comprehensive collaborative management of the supply chain, risk control in finance, accurate diagnosis in healthcare, or efficient scheduling in energy systems, all these applications place unprecedented demands on the accuracy, responsiveness, and adaptability of modeling and decision-making. Therefore, researching intelligent modeling of business activities is crucial for improving business efficiency, optimizing decision quality, and strengthening risk control.

[0003] Currently, related technologies employ traditional modeling methods for business modeling, including statistical modeling, machine learning, and business process modeling. However, when faced with complex and ever-changing real-world business scenarios, this approach relies on static, manual intervention and cannot automatically handle issues such as missing data or element biases, resulting in low modeling accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, and equipment for full-element intelligent business modeling.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] Firstly, this application provides a comprehensive intelligent business modeling method, including:

[0007] Obtain multi-source heterogeneous data and business optimization goals from the business scenario, perform data completion processing on the multi-source heterogeneous data, and obtain a structured data set;

[0008] The structured dataset is subjected to element mining processing to obtain a structured element set; the structured element set includes: entity elements, environmental elements, and tool elements;

[0009] Based on the structured element set, process digitization is performed to construct a business process model; the business process model is used to characterize the process relationships between the various elements in the structured element set.

[0010] The business process model is subjected to decision prediction processing to obtain predictive information;

[0011] Based on the predictive information and the business optimization objectives, business objectives are optimized to determine the business decision results.

[0012] Secondly, this application provides a full-element intelligent business modeling device, which includes:

[0013] The data completion module is used to acquire multi-source heterogeneous data and business optimization goals in the business scenario, and to perform data completion processing on the multi-source heterogeneous data to obtain a structured data set.

[0014] The feature mining module is used to perform feature mining processing on the structured data set to obtain a structured feature set; the structured feature set includes: entity features, environmental features, and tool features;

[0015] The process digitization module is used to perform process digitization processing based on the structured element set and construct a business process model; the business process model is used to represent the process relationships between the various elements in the structured element set.

[0016] The decision prediction module is used to perform decision prediction processing on the business process model to obtain predictive information;

[0017] The target optimization module is used to perform business target optimization processing based on the predictive information and the business optimization target, and determine the business decision result.

[0018] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the full-element intelligent business modeling method described in any one of the above.

[0019] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0020] This application provides a method, apparatus, and equipment for full-element intelligent business modeling. The method includes: acquiring multi-source heterogeneous data and business optimization objectives in a business scenario; performing data completion processing on the multi-source heterogeneous data to obtain a structured data set; performing element mining processing on the structured data set to obtain a structured element set; the structured element set includes: entity elements, environmental elements, and tool elements; performing process digitization processing based on the structured element set to construct a business process model; the business process model is used to represent the process relationships between various elements in the structured element set; performing decision prediction processing on the business process model to obtain predictive information; and performing business objective optimization processing based on the predictive information and business optimization objectives to determine the business decision result. Compared with existing technologies, this solution addresses the weak modeling foundation caused by data gaps in traditional modeling by acquiring multi-source heterogeneous data and performing data completion processing, providing complete and reliable structured data support for subsequent modeling. It also performs element mining on the structured data set to extract entity, environment, and tool elements, overcoming the shortcomings of traditional modeling elements being singular and biased, ensuring that the acquired modeling elements are more comprehensive and targeted. Furthermore, it constructs a business process model based on the structured element set, breaking the limitations of traditional business process modeling relying on static manual driving, and achieving dynamic and accurate representation of relationships between elements through process digitization. The solution performs decision prediction processing on the business process model, changing the situation where traditional modeling struggles to cope with dynamic changes in complex scenarios, and generating predictive information that fits reality. Finally, it combines predictive information and business optimization goals to determine business decision results, avoiding the problem of traditional modeling decisions being disconnected from goals, ultimately significantly improving the accuracy of modeling processing and the scientific nature and effectiveness of business decisions. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the application environment of a full-element intelligent business modeling method according to an embodiment of this application;

[0023] Figure 2 A flowchart illustrating a full-element intelligent business modeling method provided in an embodiment of this application;

[0024] Figure 3 This is a schematic diagram of a structured set of elements provided in an embodiment of this application;

[0025] Figure 4A flowchart illustrating a full-element intelligent business modeling method provided in another embodiment of this application;

[0026] Figure 5 A schematic diagram of the functional modules of a full-element intelligent business modeling device provided in an embodiment of this application;

[0027] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] Traditional modeling methods, including statistical modeling, machine learning, and business process modeling, are used in related technologies for business modeling. However, when faced with complex and ever-changing real-world business scenarios, these methods rely on static, manual intervention and cannot automatically handle issues such as data inaccuracies and element deviations, resulting in low modeling accuracy.

[0031] To address the aforementioned shortcomings, this application provides a comprehensive intelligent business modeling method. Compared to existing technologies, this solution solves the problem of weak modeling foundation caused by data gaps in traditional modeling by acquiring multi-source heterogeneous data and performing data completion processing, providing complete and reliable structured data support for subsequent modeling. It also performs element mining on the structured data set to extract entity, environment, and tool elements, overcoming the shortcomings of single and biased data elements in traditional modeling, ensuring that the acquired modeling elements are more comprehensive and targeted. Furthermore, it constructs a business process model based on the structured element set, breaking the limitations of traditional business process modeling relying on static manual driving, and achieving dynamic and accurate representation of relationships between elements through process digitization. The business process model undergoes decision prediction processing, changing the situation where traditional modeling struggles to cope with dynamic changes in complex scenarios, and generating predictive information that fits reality. Finally, it combines predictive information and business optimization goals to determine business decision results, avoiding the problem of traditional modeling decisions being disconnected from goals, ultimately significantly improving the accuracy of modeling processing and the scientific nature and effectiveness of business decisions.

[0032] This application provides a full-element intelligent business modeling method that can be applied to, for example... Figure 1 The application environment of the full-element intelligent business modeling method is shown. This application environment includes: terminal 102, server 104, and data storage system. Terminal 102 communicates with server 104 via a network. The data storage system can store multi-source heterogeneous data from the business scenario acquired by server 104. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send the acquired test vehicle information from a closed site to server 104. After acquiring the multi-source heterogeneous data, server 104 determines the business decision result through data completion, element mining, process digitization, decision prediction, and business objective optimization. Furthermore, in some embodiments, the intelligent business modeling method can also be implemented independently by server 104 or terminal 102. For example, terminal 102 can directly acquire multi-source heterogeneous data from the business scenario to construct an initial population, and then perform data completion, element mining, process digitization, decision prediction, and business objective optimization to determine the business decision result.

[0033] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0034] In one exemplary embodiment, such as Figure 2 As shown, a comprehensive intelligent business modeling method is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S201 to S205. Wherein:

[0035] Step S201: Obtain multi-source heterogeneous data and business optimization goals in the business scenario, perform data completion processing on the multi-source heterogeneous data, and obtain a structured data set.

[0036] It should be noted that the aforementioned business scenarios can include a variety of applications, such as precision production control in manufacturing, global collaborative management of the supply chain, risk control in the financial sector, accurate diagnosis in the medical industry, and efficient scheduling in energy systems. Here, "multi-source" refers to the diversity of data sources, and "heterogeneous" refers to the differences in data formats. Multi-source heterogeneous data in business scenarios refers to data with different structures from different data sources. Different business scenarios correspond to different multi-source heterogeneous data. Multi-source heterogeneous data can be obtained through a multi-tiered storage architecture.

[0037] Optionally, the multi-source heterogeneous data in the above business scenarios can be obtained from external devices, imported from blockchain or databases, or obtained in real time by analyzing the entire business process in the business scenario. This embodiment does not limit the acquisition method of multi-source heterogeneous data in the business scenario.

[0038] For example, taking an e-commerce marketing scenario as an example, this multi-source heterogeneous data can come from user behavior logs, transaction systems, customer service records, external third parties, etc., and the data format can be structured data, semi-structured data, or unstructured data. Among them, structured data can be transaction data in an Excel spreadsheet, semi-structured data can be user behavior logs in JSON format, and unstructured data can be customer service voice-transcribed text, product review images, etc.

[0039] The aforementioned business optimization goals refer to data processing objectives. For example, for retail business, the business optimization goal could be to increase repurchase rate, while for supply chain business, the business optimization goal could be to reduce inventory turnover days.

[0040] Understandably, due to the potential for missing data in multi-source heterogeneous data, data completion processing is necessary to fill in the missing values ​​in order to obtain more comprehensive data. This can be achieved through rule-based completion, algorithm-based completion, or cross-source complementary completion, thereby obtaining a structured dataset. This structured dataset refers to the comprehensive structured data after data completion processing.

[0041] This step involves acquiring multi-source heterogeneous data from business scenarios, which enables the acquired data to better cover all dimensions of business characteristics. This solves the problem of weak modeling foundation caused by single data sources and serious data gaps generated by traditional modeling, while also ensuring the relevance of data to business objectives, providing higher quality data information for subsequent element mining and process modeling.

[0042] In one embodiment, this application also provides a specific implementation method for performing data completion processing on multi-source heterogeneous data to obtain a structured data set, the method comprising:

[0043] Repeatedly execute the first specified operation until the overall quality score of the current dataset is not less than the quality score threshold, thus obtaining a structured data set;

[0044] The first specified operation includes:

[0045] The current dataset is comprehensively evaluated to obtain a data completeness score and a data consistency score. When the first specified operation is executed for the first time, the current dataset is multi-source heterogeneous data. When the first specified operation is not executed for the first time, the current dataset is the updated dataset obtained when the first specified operation was executed previously.

[0046] Based on the data completeness score and data consistency score, a comprehensive quality score is obtained, and it is determined whether the comprehensive quality score is less than the quality score threshold.

[0047] If the overall quality score is less than the quality score threshold, retrieve the data completion source, determine the updated dataset based on the data completion source and the multi-source heterogeneous data, and then proceed to the next specified operation.

[0048] When the overall quality score is not less than the quality score threshold, the control will not proceed to the next first specified operation.

[0049] Understandably, any effective modeling requires high-quality, complete data. The acquired raw, multi-source, heterogeneous data D raw This requirement cannot be directly met. Therefore, a heterogeneous functional module is needed to handle multi-source heterogeneous data from a multi-tiered storage architecture. raw Automatic processing into high-quality structured data sets D quality In this application, a self-emergent stage is set up to achieve high-quality data completion processing, and this self-emergent stage adopts a self-emergent data completion algorithm.

[0050] Specifically, in acquiring multi-source heterogeneous data D raw Then, it can be achieved through an emergent approach, by combining a pre-defined knowledge set K. expert Data completion processing is performed on multi-source heterogeneous data to obtain a structured dataset D. quality It can be done through function D qua lity=f emerge (D raw ,K expert The function uses a built-in emergent data completion algorithm to iteratively improve data quality until a preset data completeness assessment threshold is met. This preset knowledge data set can be obtained through expert knowledge and business objectives.

[0051] In this embodiment, the process of obtaining the structured data set is modeled as an iterative optimization problem, and its algorithm iteration process can be represented by the following formula:

[0052]

[0053] Among them, D (k) For the current dataset, D (k+1) For the updated dataset, This is the optimal data point.

[0054] First, obtain the current dataset D. (k) Let represent the dataset at the k-th iteration. A comprehensive evaluation of the current dataset can include checking its completeness and obtaining a completeness score S. c (D (k) The completeness status includes: statistically analyzing the proportion of missing fields, record completeness, etc., and detecting data conflict rate, format consistency, etc., to obtain a consistency score S. a (D (k) Then, according to the preset weights, the overall quality score Q(D) is obtained. (k) This can be expressed by the following formula:

[0055] Q(D) = w c ·S c (D)+w a ·S a (D);

[0056] Among them, S c (D) represents the completeness score, S a (D) represents the data consistency score, w c The weights corresponding to the completeness score, w a The weights corresponding to the consistency scores. Weight w c w a It can be determined through expert knowledge settings, historical modeling effect feedback, or importance analysis based on specific business scenarios, and supports dynamic adjustment to adapt to different application needs. It can also be customized based on the importance of completeness score and consistency score.

[0057] The overall quality score is compared with the quality score threshold Q. threshold When comparing, when Q(D) (k) ) threshold When this happens, the data completion process is triggered, forming a quality-driven iterative mechanism; when Q(D) (k) )≥Q threshold ​In the first iteration, no iterative processing is performed; the current dataset is treated as a structured data set. Specifically, the current dataset in the first iteration is the initial multi-source heterogeneous data; in subsequent iterations, the current dataset is the multi-source heterogeneous data obtained after the previous processing. During the first execution of the iteration process, the originally acquired multi-source heterogeneous data is used as the initial current dataset, and a comprehensive evaluation is performed to obtain a comprehensive quality score to determine if it is below a quality score threshold. In subsequent iterations, the updated dataset obtained from the previous iteration is used as the next current dataset, and the iteration process is executed after comprehensive evaluation.

[0058] Based on the data source and the multi-source heterogeneous data, the updated dataset is determined, including: obtaining a candidate data subset from the data completion source; obtaining a preset knowledge data set and determining the posterior probability of each data point in the candidate data subset under the conditions of multi-source heterogeneous data and the knowledge data set; selecting the data point with the highest posterior probability from the candidate data subset as the optimal data point; and supplementing the optimal data point into the multi-source heterogeneous data to obtain the updated dataset.

[0059] During the data completion process, the system can automatically locate potential data completion sources, which may include historical databases and knowledge bases, and obtain candidate data subsets from these sources. Then, core completion and expert knowledge enhancement operations are performed, the core of which is to select the optimal data point from the candidate data subset. Given a set of multi-source heterogeneous data and knowledge data, we can obtain the posterior probability of each data point in the candidate data subset. Then, we select the data point with the highest posterior probability from the candidate data subset as the optimal data point. The optimal data point is represented by the following formula:

[0060]

[0061] in, Let d be a single data point in the candidate data subset, representing the optimal selected data point. Let P(d|D) be the subset of candidate data selected from potential sources such as the history database and knowledge base in the k-th iteration. (k) ,K expert ) is for the current dataset D (k) and knowledge data set K expert Given the condition, the posterior probability of data point d.

[0062] After determining the optimal data points Then, the optimal data point is added to the current dataset D. (k) In the process, the updated dataset D is obtained. (k+1)Then, the updated dataset is used as the current dataset for the next iteration, and a comprehensive evaluation is performed on it to obtain the overall quality score Q(D) of the updated dataset. (k+1) ), and compare it with the quality score threshold Q. threshold Perform a comparison, when Q(D) (k+1) )<Q threshold When Q(D) is reached, the next iteration is executed; when Q(D) is reached... (k+1) )≥Q threshold When the loop terminates, the final high-quality structured data set D is output. quality .

[0063] In this embodiment, by executing the first specified operation, the current dataset (initially multi-source heterogeneous data, and subsequently the results of the previous update) is comprehensively evaluated to obtain data completeness and consistency scores. Then, the comprehensive quality score is calculated and compared with the threshold. If it does not meet the standard, the updated dataset is determined based on the data completion source and multi-source heterogeneous data, and the loop continues until the comprehensive quality score meets the standard and a structured data set is obtained. This realizes dynamic iterative optimization of data completion. With continuous evaluation and targeted completion, it effectively solves the problem of weak foundation caused by data missing and inconsistency in traditional modeling, and provides more complete, accurate and high-quality structured data support for subsequent business modeling, improving the accuracy of modeling processing from the data source.

[0064] Step S202: Perform feature mining processing on the structured data set to obtain a structured feature set; the structured feature set includes: entity features, environmental features, and tool features.

[0065] After obtaining the structured dataset, a set of structured elements A for business activities can be obtained through a self-reinforcing approach. This process involves complex element definition and mining; therefore, a functional module is needed to automatically mine and structurally define structured elements from the data. These structured elements include entity elements, environmental elements, and tool elements, with tool elements being the most complex. This application implements element mining processing by setting a self-reinforcing stage, which employs a self-reinforcing element mining algorithm.

[0066] In one embodiment, a specific implementation method for performing feature mining on a structured dataset to obtain a structured feature set is also provided, the method including:

[0067] The second specified operation is executed repeatedly until the current structured dataset meets the iteration termination condition, resulting in a set of structured features. The iteration termination condition includes reaching the required number of iterations or the integrity score being no less than the integrity score threshold. The second specified operation includes:

[0068] The integrity of each element in the current structured dataset is evaluated to obtain an integrity metric. When the second specified operation is executed for the first time, the current structured dataset is a set of structured data. When the second specified operation is not executed for the first time, the current structured dataset is the updated set of structured data obtained in the previous execution of the second specified operation.

[0069] Based on the integrity metric and integrity weight, an integrity score is obtained, and it is determined whether the current structured dataset meets the iteration termination condition.

[0070] If the current structured dataset does not meet the iteration termination condition, candidate generation and mining are performed based on the structured dataset to obtain an updated structured dataset, and then the process is controlled to enter the next second specified operation.

[0071] If the current structured dataset meets the iteration termination condition, control will not proceed to the next specified second operation.

[0072] Specifically, after obtaining the structured data set D quality Then, the structured element definition can be mined and completed through a self-reinforcing method until it meets the preset element completeness evaluation criteria, thereby obtaining a set of structured elements A, which can be obtained through the function A = f enhance (D quality The function is defined as follows: This function contains a self-reinforcing feature mining algorithm that iteratively mines and completes the full feature definition until it meets the preset feature completeness evaluation criteria.

[0073] In this embodiment, the feature mining process is modeled as a structured knowledge discovery and enhancement process. Its goal is to maximize the integrity score C(A) of the structured feature set A. This integrity score is used to comprehensively evaluate the internal structural integrity of all features in the structured data set, and can be expressed by the following formula:

[0074]

[0075] Among them, a i For a single feature in a structured dataset, V(a) i ) represents the integrity metric, w iThe importance weight is used to characterize the completeness of an evaluation element across multiple dimensions, including attribute completeness (whether required attributes are complete), relational completeness (whether the association with other elements is complete), and structural consistency (whether the internal structure meets standards). The importance weight ranges from 0 to 1, and a weighted summation method is used to obtain the completeness score. This importance weight can be determined comprehensively based on factors such as the element's business impact, frequency of use, criticality, and complexity of dependencies. It can be obtained and dynamically adjusted through expert evaluation, historical data analysis, and calculation of business value contribution.

[0076] The updated structured data set, obtained through candidate generation and mining based on the structured data set, includes:

[0077] Obtain a preset standard knowledge base and generate candidate incremental update options based on the standard knowledge base; the candidate incremental update options include at least one of the following: data to complete missing attributes, information to repair key connections, enhanced components of functional modules, and version upgrade configuration information of tool elements; calculate the confidence level of each update item in the candidate incremental update options; select update items with a confidence level greater than a preset confidence threshold from the candidate incremental update options as the update set; apply the update set to the structured dataset to obtain the updated structured dataset.

[0078] The self-reinforcing algorithm in this embodiment continuously updates the feature set incrementally through a spiral iterative reinforcement method. Its iterative process can be represented by the following formula:

[0079] A (k+1) =A (k) ⊕ΔA * ;

[0080] Among them, A (k+1) For the updated structured data set, A (k) For a structured dataset, ΔA * For the updated set.

[0081] Specifically, during the iteration process, missing data detection and candidate generation are performed first. The completeness of each element in the current structured dataset is assessed through structured analysis of the necessary attributes, relational links, and functional completeness of each element. By comparing with standard element templates or domain knowledge bases, specific missing elements such as missing attributes, broken relational links, and incomplete functions are identified, and their impact is quantified to obtain the completeness metric value for each element. This metric is then weighted and summed with corresponding weights to obtain a completeness score. Subsequently, candidate incremental update options are generated based on knowledge graph reasoning, similar element matching, and expert knowledge base queries. The candidate incremental update option can be understood as a candidate incremental update scheme, including: data completion for missing attributes, repair information for key connections, enhanced components for functional modules, and version upgrade configuration information for tool elements, etc., which are structured update contents.

[0082] After missing detection and candidate generation, deep mining and inference completion are performed. The core decision of this algorithm lies in selecting an optimal, high-confidence update set ΔA from the candidate solutions. * This screening process is based on confidence assessment, meaning that only those samples from the pre-defined standard knowledge base MathCalcA are considered. (k) Under the given conditions, only updates with a confidence level higher than a preset threshold will be adopted. The update set, consisting of updates with a confidence level greater than the preset threshold, can be represented by the following formula:

[0083]

[0084] Where, ΔA * Let δ be the update set, and δ be the update term. A is a candidate incremental update option. (k) For structured data collections, Conf threshold This is the confidence threshold.

[0085] After obtaining the updated set, the selected high-confidence updated sets are applied to the current structured dataset to obtain the updated structured dataset A. (k+1) Then, a comprehensive evaluation is performed on the updated structured dataset to obtain an integrity score. To determine whether the integrity score has converged, the iteration termination condition is met when the integrity score satisfies the integrity score convergence (i.e., |C(A)|). (k+1) )-C(A (k) When the integrity score threshold is reached or the maximum number of iterations is reached, the loop terminates, and the current structured dataset is used as the final structured feature set A. If the integrity score does not meet the iteration conditions, the next iteration is executed.

[0086] This embodiment systematically proposes for the first time a unified modeling framework for the three elements of entity, environment, and tool, especially the versioned structure design of the tool element, which provides new data guidance for the reusable and evolving modeling of business processes.

[0087] For example, please see Figure 3 As shown, Figure 3 This is a schematic diagram of the structured element set provided in the embodiments of this application. Taking manufacturing production scheduling as a scenario, multi-source heterogeneous data in this business scenario is obtained, and data completion processing and element mining processing are performed on it to obtain a structured element set A = {E}. ent ity,Eenv ,T set The framework includes: entity elements, environmental elements, and tool elements. Entity elements include physical objects such as production equipment, workers, raw materials, and product orders. Each entity element has a set of attributes describing its characteristics. This set of characteristic attributes can be accessed via E... entity E indicates entity ={a1, a2, ..., a n}, where a n This represents the nth characteristic attribute of the entity. Environmental Element: Used to characterize external conditions and background information affecting business activities, including production time, market demand, policies and regulations, etc. Each environmental element has a set of attributes describing its characteristics. The set of status attributes corresponding to this environmental element can be obtained through E... env E indicates env ={e1, e2, ..., e m}, where e m This represents the m-th status attribute of the environment. Tool elements are used to represent the smallest granularity of abstract information about operational nodes in a business process, and can be represented by T... set This means that production scheduling algorithms, quality inspection processes, and equipment maintenance strategies can all be abstracted into tool elements with versioned structures.

[0088] For entity elements, personnel include skill attributes, role definitions, and performance records; equipment includes technical parameters, operating status, and maintenance history; materials include physical characteristics, quality standards, and supply information; and products include specifications, quality indicators, and market positioning. For environmental elements, time includes seasonal cycles, business cycles, and unexpected events; location includes geographical location, infrastructure, and resource distribution; market includes demand changes, competitive landscape, and price fluctuations; and policy includes regulatory requirements, industry standards, and compliance constraints. Tool elements are represented using a versioned structure, including business data (historical execution, training samples, and performance records); model parameters (algorithm logic, model application, and parameter configuration); and metadata (input / output contracts, execution constraints, and performance indicators). A full-element model is established, comprising an ordered combination of multiple tool elements, represented as a Directed Acyclic Graph (DAG) business process diagram, possessing interpretable, traceable, and executable characteristics.

[0089] The above-mentioned tool elements can be represented by the following versioned structure:

[0090]

[0091]

[0092] Optionally, in addition to the meta-model-data three-element structure, the versioned structure of the above tool elements can also adopt other structured definition methods, such as the configuration-algorithm-history organization form, but the core idea is still the versioned executable unit abstraction.

[0093] This embodiment employs a self-reinforcing feature mining algorithm, which continuously refines the internal structure definition of tool elements through spiral iteration while dynamically updating the feature knowledge graph. Specifically, by repeatedly executing the second specified operation, starting with a structured dataset, the algorithm performs a completeness assessment on the first execution. Subsequent evaluations are based on the results of previous updates, combining completeness metrics and weights to obtain a completeness score. The iteration is terminated based on the score and the number of iterations. If the conditions are not met, candidate generation and mining processes are used to update the dataset, and the loop continues until the conditions are met to obtain a structured feature set. This process dynamically and continuously optimizes the completeness of elements in the structured dataset, solving the problems of omissions and biases that are prone to occur in traditional modeling feature mining. This results in a more comprehensive and accurate set of structured elements, building a solid element foundation for subsequent business process models and improving the adaptability and accuracy of business modeling to complex scenarios.

[0094] Step S203: Based on the structured element set, perform process digitization processing to construct a business process model; the business process model is used to represent the process relationships between various elements in the structured element set.

[0095] Understandably, after obtaining a structured set of elements A, an executable business process model G is assembled from the mathematical model relationships between the elements through a self-arranging method. DAG Therefore, functional modules are needed to automatically orchestrate them into complete business processes based on the interface contracts and dependencies of each tool element.

[0096] In one embodiment, a business process model is constructed by performing process digitization processing based on a structured set of elements, including: instantiating the structured set of elements into tools to obtain an instantiated tool set; constructing an initial business process based on the instantiated tool set and the dependencies between elements using topological sorting rules; obtaining interface rules and, based on the interface rules and the updated dataset, initializing the initial business process to obtain an interface-compatible intermediate business process; performing logical identification and completion processing on the intermediate business process to obtain a logically complete complete business process; and performing global verification processing on the complete business process to obtain an executable business process model.

[0097] After obtaining the structured feature set A, the function G is used... DAG =f orchestrate(A) Processing yields the business process model G DAG This function assembles disparate tool elements into a topologically ordered, interface-compatible, and globally complete executable business process through a built-in intelligent DAG orchestration and global integrity verification algorithm. The structure of the business process model can be a directed acyclic graph (DAG).

[0098] Specifically, after obtaining the structured feature set, a tool instantiation operation is performed. By inputting the structured feature set A, selecting the optimal version and configuration, and outputting the instantiated tool set T, the process is complete. instances And perform intelligent orchestration operations by inputting the instantiated toolkit T instances Based on dependencies, the initial business process G is constructed using topological sorting. initial And perform interface matching, inputting the initial business process G. initial In accordance with interface specifications, output interface-compatible intermediate business processes G compatible Then execute breakpoint supplementation and input the intermediate business process G. compatible Identify and complete logical gaps, and output a complete business process G with full logical structure. complete And perform global validation by inputting the complete business process G. complete A global verification process is performed to obtain the final executable business process model G. DAG .

[0099] Optionally, in addition to knowledge graphs, the modeling method for element relationships in this embodiment can also be based on relational databases, vector databases, etc. However, the core idea is still the structured expression and reasoning application of relationships between elements. This embodiment does not impose any limitations on the modeling method for element relationships.

[0100] This embodiment employs a self-arrangement mechanism to achieve intelligent transformation from scattered tool elements to complete business processes. It possesses complete capabilities for automatic arrangement, intelligent optimization, and global verification, breaking the limitations of traditional business process modeling that relies on static manual driving. Through process digitization, it achieves dynamic and accurate representation of the relationships between elements.

[0101] The mathematical model among the above elements includes the objective relationship matrix R. obj ∈R N×N Process Dependencies R flow The input-output mapping relationship f; the objective relationship matrix is ​​used to represent the inherent relationship between the entity elements and environmental elements, and the process dependency relationship is used to represent the relationship between various tool elements. It can be represented by a DAG structure, such as a directed acyclic graph G = (V, E), where V is the set of tool elements and E is the set of dependency edges. The input-output mapping relationship f: Input→Output is used to represent the processing transformation relationship between tool elements and entity elements.

[0102] The digital representation and storage architecture for elements adopts a multi-layered storage architecture, including a vectorized representation layer, a relationship graph layer, and a model storage layer. The vectorized representation layer refers to the vectorized representation of element attributes. i ∈R d The relationship graph layer refers to the element knowledge graph KG = (Entities, Relations, Attributes), and the model storage layer refers to the versioned model storage and management of tool elements.

[0103] Step S204: Perform decision prediction processing on the business process model to obtain predictive information.

[0104] It is understandable that any static business process model will become ineffective due to changes in the external environment. Therefore, the system must have a functional module to run the model in a simulation environment and continuously and automatically optimize the model based on the differences between the simulation results and real-world feedback, making it adaptable to environmental changes. This application obtains the business process model G. DAG Subsequently, a self-evolutionary approach can be adopted. In the self-evolutionary stage, a self-evolutionary prediction optimization algorithm is used to obtain predictive information I. predict It can be done through function I predict =f evolve (G DAG This indicates that the function uses a built-in self-evolving predictive optimization algorithm to simulate and learn the business process model in a digital twin environment, continuously optimizing the model's predictive accuracy in an iterative manner. The predictive information can be understood as predictive insights and decision support information.

[0105] In one embodiment of this application, decision prediction processing is performed on a business process model to obtain predictive information, including:

[0106] The business process model is used as an agent in the reinforcement learning framework to perform business simulation actions in a digital environment, and an objective function is constructed. The objective function aims to maximize business value. The business process model is executed to obtain interaction trajectories and identify key deviations between the simulated prediction results and the actual results. The interaction trajectories are analyzed to evaluate the contribution of each element in the business process model to the key deviations. Based on the contribution, the internal model parameters are optimized using the policy gradient method until the predictive performance index of the business process model converges or the maximum number of training rounds is reached, thus obtaining predictive information.

[0107] Specifically, after obtaining the business process model, the prediction and optimization process in the twin universe is modeled as a reinforcement learning problem. Within this framework, the entire business process model G... DAGViewed as an intelligent agent, it learns how to adjust its own strategies (i.e., the model parameters of its internal tool elements) to maximize long-term business value through trial and error in the dynamic environment of digital twins.

[0108] The core objective of the above algorithm is to find the optimal business process model. Construct an objective function that performs a series of actions in the digital twin environment, i.e., conducts business simulations, to maximize the long-term expected reward. This objective function can be expressed by the following formula:

[0109]

[0110] Among them, s t It is the environmental state at time t, a t It is G DAG The action to be performed, R(s) t ,a t The objective function is the immediate reward calculated by comparing the predicted result of the action with the actual business value, where γ is the discount factor for future rewards. Known parameters in this objective function include the upper limit of the time range, the discount factor, T (the upper limit of the time range), γ (the discount factor), and R(s). t ,a t Let G be the reward function for the environment state and the agent's actions, and let G be the parameter to be optimized, representing the business process model. DAG The model parameters θ of its internal tool elements i The dynamic parameters are the environmental state and the action sequence s. t ,a t And the expected value E[·].

[0111] In this embodiment, to maximize the aforementioned expected value, self-evolutionary reinforcement is achieved through the following core mechanism: execution environment interaction and deviation detection: executing business process model G in the digital twin universe. DAG The algorithm obtains a series of interaction trajectories (s0, a0, r1, s1, ...) and identifies key deviation points between simulated predictions and actual results. It then performs credit allocation and impact localization operations: by analyzing the interaction trajectories, the algorithm evaluates each tool element T in the process. i The algorithm identifies the key factors affecting prediction accuracy by assessing the contribution of each tool to the final overall reward (or bias). Policy optimization and precise update operations: Based on the contribution of each tool, the algorithm uses methods such as policy gradient to update its internal model parameters θ. i (i.e., the agent's policy π) θ A portion of it is precisely optimized. Its strategy update rules can be expressed as:

[0112]

[0113] in, This is the policy performance metric for the tool, where α is the learning rate. For the internal model parameters of the k-th iteration, These are the updated internal model parameters. This process iterates until the overall business process model's predictive performance metrics (such as average reward) converge or the maximum number of training epochs is reached, thus obtaining predictive information I. predict .

[0114] In this embodiment, a self-evolving prediction optimization algorithm is used to continuously optimize the performance of tool elements through reinforcement learning, thereby improving the prediction accuracy and reliability of the twin universe.

[0115] Step S205: Based on predictive information and business optimization objectives, perform business objective optimization processing to determine the business decision results.

[0116] Understandably, upon obtaining predictive information I... predict Next, it needs to be translated into actionable business decisions to create value. This requires a functional module that combines predictive insights with business objectives to generate optimal decisions and provides closed-loop feedback based on execution results, thereby continuously improving business value. In this application, a self-optimizing approach is used, through the function S... optimal =f optimize (I predict ,K expert This function, through its built-in closed-loop iterative mechanism based on business value feedback, combines predictive insights with business optimization goals to generate quantifiable and sustainably optimized business decision-making solutions. The final business decision outcome, S, is then determined. optimal .

[0117] This includes optimizing business objectives based on predictive information and business optimization goals to determine business decision results, including:

[0118] The process involves: acquiring initial business decision options and obtaining actual execution results through business monitoring; calculating the deviation based on the actual execution results and predictive information; adjusting the business decision logic and process parameters based on the deviation and a pre-defined knowledge base to obtain adjusted business decision options; optimizing key elements in the adjusted business decision options to obtain an optimized set of elements; and determining the business decision result based on the optimized set of elements when it meets the evaluation criteria.

[0119] Specifically, obtain the initial business decision options S optimal The system collects actual execution performance information through business monitoring and outputs this information via dataset D. actual Indicate and perform deviation analysis: Input Dactual and expected target I predict Calculate the deviation between the actual performance information and the predicted information, identify the causes, and output a deviation analysis report Δ. analysis Then execute the strategy adjustment: input the deviation analysis report Δ analysis and the pre-set knowledge dataset K expert Adjust the decision-making logic and process parameters, and output the adjusted business decision options S. adjusted And perform element optimization: Input S adjusted Identify the key elements and perform targeted optimization based on them, outputting an optimized set of elements. Then, a closed-loop iterative process is performed to determine whether the optimized set of elements meets the evaluation criteria, such as the degree of business value improvement. When the evaluation criteria are met, the final optimized business decision result is output. When the optimized set of elements does not meet the evaluation criteria, a new round of iteration is triggered until the business decision is obtained.

[0120] Optionally, the above algorithms can be customized according to actual needs. For example, in addition to emergent, self-reinforcing, and self-evolutionary algorithms, different mathematical optimization algorithms, such as genetic algorithms, particle swarm optimization, and reinforcement learning, can be used. However, the core mechanism remains iterative improvement based on quality assessment. In the above implementation methods of the digital twin environment, other simulation and visualization technologies can also be used to construct the twin environment, but the core concept remains virtual-real mapping and predictive extrapolation based on a full-element model.

[0121] The intelligent business modeling method provided in this application, through a "five-self" collaborative mechanism (self-emergence, self-reinforcement, self-arrangement, self-evolution, and self-optimization), supported by innovative core algorithms such as self-emergent data completion, self-reinforcement element mining, and self-evolutionary predictive optimization algorithms, constructs a system-level modeling architecture from raw data to an executable business model. It achieves a predictive optimization closed loop with the help of digital twins, allowing the modeling results to be directly transformed into business value. At the same time, relying on the built-in feedback and closed-loop optimization mechanism, the system has the ability to continuously self-optimize, forming an end-to-end intelligent modeling closed loop. This not only significantly improves the automation and intelligence level of the modeling process, but also ensures the continuous evolution of modeling quality, efficiently adapts to complex and ever-changing business scenarios, and promotes the leap of business modeling from static manual driving to dynamic intelligent iteration.

[0122] Please see Figure 4As shown, the process begins by inputting multi-source heterogeneous data, professional knowledge, and business objectives into the input layer. These are then processed through the ATOMS core system. The data is processed using an emergent data completion algorithm to obtain a high-quality structured data set (high-quality data elements). This is further processed using a self-reinforcing element mining algorithm to obtain a structured element set (structured full element set). Then, an executable business process model is obtained through an intelligent DAG orchestration algorithm. Finally, predictive information (i.e., predictive insight information) is obtained through a self-evolving predictive optimization algorithm. Finally, through closed-loop iterative optimization, the final business decision solution (business decision result) is obtained.

[0123] This application provides a full-element intelligent business modeling method, which includes: acquiring multi-source heterogeneous data and business optimization objectives in a business scenario; performing data completion processing on the multi-source heterogeneous data to obtain a structured data set; performing element mining processing on the structured data set to obtain a structured element set; the structured element set includes: entity elements, environmental elements, and tool elements; performing process digitization processing based on the structured element set to construct a business process model; the business process model is used to represent the process relationships between various elements in the structured element set; performing decision prediction processing on the business process model to obtain predictive information; and performing business objective optimization processing based on the predictive information and business optimization objectives to determine the business decision results. Compared with existing technologies, this solution addresses the weak modeling foundation caused by data gaps in traditional modeling by acquiring multi-source heterogeneous data and performing data completion processing, providing complete and reliable structured data support for subsequent modeling. It also performs element mining on the structured data set to extract entity, environment, and tool elements, overcoming the shortcomings of traditional modeling elements being singular and biased, ensuring that the acquired modeling elements are more comprehensive and targeted. Furthermore, it constructs a business process model based on the structured element set, breaking the limitations of traditional business process modeling relying on static manual driving, and achieving dynamic and accurate representation of relationships between elements through process digitization. The solution performs decision prediction processing on the business process model, changing the situation where traditional modeling struggles to cope with dynamic changes in complex scenarios, and generating predictive information that fits reality. Finally, it combines predictive information and business optimization goals to determine business decision results, avoiding the problem of traditional modeling decisions being disconnected from goals, ultimately significantly improving the accuracy of modeling processing and the scientific nature and effectiveness of business decisions.

[0124] Based on the same inventive concept, this application also provides an intelligent business modeling apparatus for implementing the aforementioned method. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the full-element intelligent business modeling apparatus provided below can be found in the limitations of the full-element intelligent business modeling method described above, and will not be repeated here.

[0125] In one exemplary embodiment, such as Figure 5 As shown, a full-element intelligent business modeling device is provided, the device comprising:

[0126] The data completion module 510 is used to acquire multi-source heterogeneous data and business optimization goals in the business scenario, perform data completion processing on the multi-source heterogeneous data, and obtain a structured data set.

[0127] The feature mining module 520 is used to perform feature mining processing on structured datasets to obtain structured feature sets; the structured feature sets include: entity features, environmental features, and tool features;

[0128] The process digitization module 530 is used to digitize processes based on a set of structured elements and build a business process model; the business process model is used to represent the process relationships between the various elements in the set of structured elements.

[0129] The decision prediction module 540 is used to perform decision prediction processing on the business process model to obtain predictive information;

[0130] The target optimization module 550 is used to optimize business targets based on predictive information and business optimization targets, and to determine the business decision results.

[0131] As an optional implementation, the data completion module 510 is specifically used for:

[0132] Repeatedly execute the first specified operation until the overall quality score of the current dataset is not less than the quality score threshold, thus obtaining a structured data set;

[0133] The first specified operation includes:

[0134] The current dataset is comprehensively evaluated to obtain data completeness score and data consistency score. When the first specified operation is executed for the first time, the current dataset is multi-source heterogeneous data. When the first specified operation is not executed for the first time, the current dataset is the updated dataset obtained when the first specified operation was executed before.

[0135] Based on the data completeness score and data consistency score, a comprehensive quality score is obtained, and it is determined whether the comprehensive quality score is less than the quality score threshold.

[0136] When the overall quality score is less than the quality score threshold, the data completion source is obtained. Based on the data completion source and the multi-source heterogeneous data, the updated dataset is determined, and the process is controlled to proceed to the next first specified operation.

[0137] When the overall quality score is not less than the quality score threshold, the control will not proceed to the next first specified operation.

[0138] As an optional implementation, the data completion module 510 is also used for:

[0139] Obtain a subset of candidate data from the data completion source;

[0140] Obtain a preset knowledge data set and determine the posterior probability of each data point in the candidate data subset under the conditions of multi-source heterogeneous data and knowledge data set;

[0141] Select the data point with the highest posterior probability from the candidate data subset as the optimal data point;

[0142] The optimal data points are added to the multi-source heterogeneous data to obtain the updated dataset.

[0143] As an optional implementation, the feature mining module 520 is specifically used for:

[0144] The second specified operation is executed repeatedly until the current structured dataset meets the iteration termination condition, resulting in a set of structured features. The iteration termination condition includes reaching the number of iterations or the integrity score being not less than the integrity score threshold.

[0145] The second specified operation includes:

[0146] The integrity of each element in the current structured dataset is evaluated to obtain an integrity metric. When the second specified operation is executed for the first time, the current structured dataset is a structured data set. When the second specified operation is not executed for the first time, the current structured dataset is the updated structured data set obtained when the second specified operation was executed previously.

[0147] Based on the integrity metric and integrity weight, an integrity score is obtained, and it is determined whether the current structured dataset meets the iteration termination condition.

[0148] If the current structured dataset does not meet the iteration termination condition, candidate generation and mining are performed based on the structured dataset to obtain an updated structured dataset, and then the process is controlled to enter the next second specified operation.

[0149] If the current structured dataset meets the iteration termination condition, control will not proceed to the next specified second operation.

[0150] As an optional implementation, the feature mining module 520 is also used for:

[0151] Obtain a preset standard knowledge base and generate candidate incremental update options based on the standard knowledge base; the candidate incremental update options include at least one of the following: data to complete missing attributes, information to repair key connections, enhanced components of functional modules, and version upgrade configuration information of tool elements;

[0152] Calculate the confidence level of each update item in the candidate incremental update options;

[0153] Select update items with a confidence level greater than a preset confidence threshold from the candidate incremental update options as the update set;

[0154] The updated set is applied to the structured data set to obtain the updated structured data set.

[0155] As an optional implementation, the process digitization module 530 is specifically used for:

[0156] The structured feature set is instantiated to obtain an instantiated tool set;

[0157] Based on the instantiated toolset and the dependencies between elements, the initial business process is constructed using topological sorting rules.

[0158] Obtain the interface rules, and based on the interface rules and the initial business process, obtain the interface-compatible intermediate business process;

[0159] The intermediate business processes are logically identified and completed to obtain a logically complete business process.

[0160] Perform global validation on the complete business process to obtain an executable business process model.

[0161] As an optional implementation, the decision prediction module 540 is specifically used for:

[0162] The business process model is used as an agent in the reinforcement learning framework to perform business simulation actions in a digital environment, and an objective function is constructed; the objective function aims to maximize the expected value.

[0163] Execute the business process model, acquire the interaction trajectory, and identify the key deviations between the simulated prediction results and the actual results;

[0164] Analyze interaction trajectories and evaluate the contribution of each element in the business process model to key deviation points;

[0165] Based on the contribution, the internal model parameters are optimized using the policy gradient method until the predictive performance index of the business process model converges or reaches the maximum number of training rounds, thus obtaining predictive information.

[0166] As an optional implementation, the target optimization module 550 is specifically used for:

[0167] Obtain initial business decision options and obtain actual execution effect information through business monitoring;

[0168] Calculate the deviation based on actual performance information and predictive information;

[0169] Based on the deviation and a pre-set knowledge base, the business decision-making logic and process parameters are adjusted to obtain the adjusted business decision options.

[0170] The key elements in the adjusted business decision options are optimized to obtain an optimized set of elements.

[0171] When the optimized set of elements meets the evaluation criteria, the business decision result is determined based on the optimized set of elements.

[0172] The all-element intelligent business modeling device provided in this application addresses the weak modeling foundation caused by data gaps in traditional modeling by acquiring multi-source heterogeneous data and performing data completion processing, providing complete and reliable structured data support for subsequent modeling. It mines and extracts entity, environment, and tool elements from the structured data set, overcoming the shortcomings of traditional modeling elements being singular and biased, ensuring more comprehensive and targeted modeling elements. Furthermore, it constructs a business process model based on the structured element set, breaking the limitations of traditional business process modeling relying on static manual driving, and achieving dynamic and accurate representation of relationships between elements through process digitization. It performs decision prediction processing on the business process model, changing the situation where traditional modeling struggles to cope with dynamic changes in complex scenarios, and generating predictive information that fits reality. Combining predictive information and business optimization goals to determine business decision results avoids the problem of traditional modeling decisions being disconnected from goals, ultimately significantly improving the accuracy of modeling processing and the scientific nature and effectiveness of business decisions.

[0173] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores video tag processing data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a comprehensive intelligent business modeling method.

[0174] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0175] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0176] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0177] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0178] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0179] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0180] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0181] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0182] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for modeling all-element intelligent business processes, characterized in that, The comprehensive intelligent business modeling method includes: Obtain multi-source heterogeneous data and business optimization goals from the business scenario, perform data completion processing on the multi-source heterogeneous data, and obtain a structured data set; The structured dataset is subjected to element mining processing to obtain a structured element set; the structured element set includes: entity elements, environmental elements, and tool elements; Based on the structured element set, process digitization is performed to construct a business process model; the business process model is used to characterize the process relationships between the various elements in the structured element set. The business process model is subjected to decision prediction processing to obtain predictive information; Based on the predictive information and the business optimization objectives, business objectives are optimized to determine the business decision results; Specifically, the structured data set undergoes feature mining processing to obtain a structured feature set, including: The second specified operation is executed repeatedly until the current structured dataset meets the iteration termination condition, and the structured feature set is obtained. The iteration termination condition includes reaching the number of iterations or the integrity score is not less than the integrity score threshold. The second specified operation includes: Integrity assessment is performed on each element in the current structured dataset to obtain an integrity metric value; when the second specified operation is executed for the first time, the current structured dataset is the structured data set; when the second specified operation is not executed for the first time, the current structured dataset is the updated structured data set obtained in the previous execution of the second specified operation. Based on the integrity metric and integrity weight, an integrity score is obtained, and it is determined whether the current structured dataset meets the iteration termination condition. If the current structured dataset does not meet the iteration termination condition, candidate generation and mining are performed based on the structured dataset to obtain an updated structured dataset, and then the process is controlled to enter the next second specified operation. If the current structured dataset meets the iteration termination condition, control will not proceed to the next specified second operation.

2. The full-element intelligent business modeling method according to claim 1, characterized in that, The multi-source heterogeneous data is augmented to obtain a structured data set, including: The first specified operation is executed repeatedly until the overall quality score of the current dataset is not less than the quality score threshold, thus obtaining the structured data set; The first specified operation includes: The current dataset is comprehensively evaluated to obtain a data completeness score and a data consistency score; when the first specified operation is executed for the first time, the current dataset is the multi-source heterogeneous data; when the first specified operation is not executed for the first time, the current dataset is the updated dataset obtained when the first specified operation was executed previously. Based on the data completeness score and the data consistency score, a comprehensive quality score is obtained, and it is determined whether the comprehensive quality score is less than the quality score threshold. When the overall quality score is less than the quality score threshold, the data completion source is obtained, and the updated dataset is determined based on the data completion source and the multi-source heterogeneous data, and the system is controlled to enter the next first specified operation. When the overall quality score is not less than the quality score threshold, the control will not proceed to the next specified operation.

3. The full-element intelligent business modeling method according to claim 2, characterized in that, Based on the data source and the multi-source heterogeneous data, the updated dataset is determined, including: Obtain a subset of candidate data from the data completion source; Obtain a preset knowledge data set, and determine the posterior probability of each data point in the candidate data subset under the conditions of the multi-source heterogeneous data and the knowledge data set; Select the data point with the highest posterior probability from the candidate data subset as the optimal data point; The optimal data points are added to the multi-source heterogeneous data to obtain the updated dataset.

4. The full-element intelligent business modeling method according to claim 1, characterized in that, Based on the structured dataset, candidate generation and mining processes are performed to obtain an updated structured dataset, including: Obtain a preset standard knowledge base, and generate candidate incremental update options based on the standard knowledge base; the candidate incremental update options include at least one of the following: data to complete missing attributes, information to repair key connections, enhanced components of functional modules, and version upgrade configuration information of tool elements; Calculate the confidence level of each update item in the candidate incremental update options; From the candidate incremental update options, select update items with a confidence level greater than a preset confidence threshold as the update set; The updated set is applied to the structured data set to obtain the updated structured data set.

5. The full-element intelligent business modeling method according to claim 1, characterized in that, Based on the aforementioned set of structured elements, a business process model is constructed through digital processing, including: The structured element set is instantiated to obtain an instantiated tool set; Based on the instantiated toolset and the dependencies between elements, an initial business process is constructed using topological sorting rules. Obtain the interface rules, and based on the interface rules and the initial business process, obtain the interface-compatible intermediate business process; The intermediate business processes are logically identified and completed to obtain a logically complete business process. The complete business process is then subjected to global verification to obtain an executable business process model.

6. The full-element intelligent business modeling method according to claim 1, characterized in that, The business process model is subjected to decision prediction processing to obtain predictive information, including: The business process model is used as an agent in a reinforcement learning framework to perform business simulation actions in a digital environment, and an objective function is constructed; the objective function aims to maximize the expected value. Execute the business process model, obtain the interaction trajectory, and identify the key deviation points between the simulated prediction results and the actual results; Analyze the interaction trajectory and evaluate the contribution of each element in the business process model to the key deviation point; Based on the contribution, the internal model parameters are optimized using the policy gradient method until the predictive performance index of the business process model converges or reaches the maximum number of training rounds, thereby obtaining the predictive information.

7. The full-element intelligent business modeling method according to claim 1, characterized in that, Based on the predictive information and the business optimization objectives, business objective optimization processing is performed to determine the business decision results, including: Obtain initial business decision options and obtain actual execution effect information through business monitoring; The deviation is calculated based on the actual performance information and the predictive information; Based on the deviation and the preset knowledge base, the business decision-making logic and process parameters are adjusted to obtain the adjusted business decision options. The key elements in the adjusted business decision options are optimized to obtain an optimized set of elements. When the optimized set of elements meets the evaluation criteria, the business decision result is determined based on the optimized set of elements.

8. A full-element intelligent business modeling device, characterized in that, The all-element intelligent business modeling device includes: The data completion module is used to acquire multi-source heterogeneous data and business optimization goals in the business scenario, and to perform data completion processing on the multi-source heterogeneous data to obtain a structured data set. The feature mining module is used to perform feature mining processing on the structured data set to obtain a structured feature set; the structured feature set includes: entity features, environmental features, and tool features; The process digitization module is used to perform process digitization processing based on the structured element set and construct a business process model; the business process model is used to represent the process relationships between the various elements in the structured element set. The decision prediction module is used to perform decision prediction processing on the business process model to obtain predictive information; The target optimization module is used to perform business target optimization processing based on the predictive information and the business optimization target, and determine the business decision result; The feature mining module is specifically used for: The second specified operation is executed repeatedly until the current structured dataset meets the iteration termination condition, and the structured feature set is obtained. The iteration termination condition includes reaching the number of iterations or the integrity score is not less than the integrity score threshold. The second specified operation includes: Integrity assessment is performed on each element in the current structured dataset to obtain an integrity metric value; when the second specified operation is executed for the first time, the current structured dataset is the structured data set; when the second specified operation is not executed for the first time, the current structured dataset is the updated structured data set obtained in the previous execution of the second specified operation. Based on the integrity metric and integrity weight, an integrity score is obtained, and it is determined whether the current structured dataset meets the iteration termination condition. If the current structured dataset does not meet the iteration termination condition, candidate generation and mining are performed based on the structured dataset to obtain an updated structured dataset, and then the process is controlled to enter the next second specified operation. If the current structured dataset meets the iteration termination condition, control will not proceed to the next specified second operation.

9. A computer device, comprising: The memory and processor contain a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the full-element intelligent business modeling method according to any one of claims 1-7.

Images