Business demand control strategy determination method and device and electronic equipment

Abstract

The invention provides a business demand control strategy determination method and device and electronic equipment, and relates to the technical field of data processing and artificial intelligence. The method comprises the following steps: obtaining candidate service requirements; determining a target business demand according to the semantic analysis result of the candidate business demand, and establishing a knowledge graph of the target business demand; based on the knowledge graph, determining an execution process corresponding to the target business demand, a plurality of process child nodes in the execution process, and risk entropy values and candidate control strategies of the process child nodes; and in response to the fact that the risk entropy value of the process child node is smaller than or equal to a set threshold value, performing multi-dimensional evaluation on at least one candidate control strategy of the process child node, and determining a target control strategy of the target business demand according to an evaluation result of the candidate control strategy. Therefore, according to the scheme, multi-dimensional analysis is carried out on the service requirements and the control strategies, so that the decision-making precision of the target control strategies is improved, and the adaptation degree and feasibility of the target control strategies and service scenes are improved.

Description

Technical Field

[0001] This disclosure relates to the fields of data processing and artificial intelligence, and in particular to a method, apparatus, and electronic device for determining a business demand control strategy. Background Technology

[0002] In current, traditional requirements analysis methods, for some control-related requirements, due to the limitations of natural language description, it is difficult for requirements analysts to effectively identify which business requirements need to be controlled by business procedures and which need to be controlled by the system. There is too much reliance on the personal work experience of analysts and a lack of an effective quantitative model for quantitative analysis, which leads to blurred control boundaries of requirements and brings great risks to subsequent testing and safe production operations. Summary of the Invention

[0003] This disclosure provides a method, apparatus, and electronic device for determining business demand control strategies, in order to solve the problem of the inability to quantitatively analyze control methods for business demands.

[0004] Therefore, one objective of this disclosure is to propose a method for determining business demand control strategies.

[0005] The second objective of this disclosure is to provide a device for determining business demand control strategies.

[0006] The third objective of this disclosure is to propose an electronic device.

[0007] The fourth objective of this disclosure is to provide a non-transitory computer-readable storage medium.

[0008] The fifth objective of this disclosure is to provide a computer program product.

[0009] To achieve the above objectives, a first aspect of this disclosure proposes a method for determining a business requirement control strategy, comprising: acquiring candidate business requirements; determining a target business requirement based on the semantic analysis results of the candidate business requirements, and establishing a knowledge graph of the target business requirement; determining an execution flow corresponding to the target business requirement based on the knowledge graph, and determining multiple process sub-nodes in the execution flow, as well as a risk entropy value and a candidate control strategy for each process sub-node; wherein the candidate control strategy is used to indicate the proportion of different control methods used to control the target business requirement; in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, performing a multi-dimensional evaluation of at least one candidate control strategy for each process sub-node, and determining the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies.

[0010] According to one embodiment of this disclosure, the method further includes: in response to the existence of a first process sub-node with a risk entropy value greater than the set threshold, determining the number of the first process sub-nodes; in response to the number being greater than the number threshold, modifying the target business requirement associated with the first process sub-node until the risk entropy value of the first process sub-node is less than or equal to the set threshold.

[0011] According to one embodiment of this disclosure, determining the risk entropy value of each process sub-node includes: determining the node type of each process sub-node; determining a pre-set risk assessment index; performing a risk assessment on each process sub-node based on the node type and the risk assessment index to obtain a first assessment value; and determining the risk entropy value of each process sub-node based on a first weight value of the risk assessment index and the first assessment value.

[0012] According to one embodiment of this disclosure, the control method includes a first control method and a second control method. Determining a candidate control strategy for each process sub-node includes: determining a control constraint index corresponding to the candidate control strategy; evaluating each process sub-node based on the node type and the control constraint index to obtain a second evaluation value; determining a first control ratio value based on the second weight value of each of the control constraint indices and the second evaluation value, and determining a second control ratio value based on the first control ratio value; determining the ratio of controlling the process sub-node based on the first control method as the first control ratio value; and determining the ratio of controlling the process sub-node based on the second control method as the second control ratio value.

[0013] According to one embodiment of this disclosure, the multi-dimensional evaluation of at least one candidate control strategy for each process sub-node includes: evaluating the matching degree of the candidate control strategy based on a pre-set matching degree evaluation index to obtain a third evaluation value corresponding to each matching degree evaluation index; and determining the evaluation result of the candidate control strategy based on the third evaluation value and the third weight value of each matching degree evaluation index.

[0014] According to one embodiment of this disclosure, determining the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies includes: screening the candidate control strategies based on the evaluation results, and selecting the candidate control strategies that meet the screening criteria as the target control strategy.

[0015] According to one embodiment of this disclosure, the method further includes: establishing a multi-dimensional evaluation model based on the matching degree evaluation index; and evaluating the matching degree of the candidate control strategy through the multi-dimensional evaluation model to obtain the evaluation result.

[0016] According to one embodiment of this disclosure, determining the target service requirement based on the semantic analysis results of the candidate service requirements includes: in response to the semantic analysis results indicating the existence of a first candidate service requirement with a semantic score less than a semantic score threshold, determining abnormal information of the first candidate service requirement; receiving a second candidate service requirement sent by the client based on the abnormal information, and re-determining the semantic analysis results of the second candidate service requirement; in response to the semantic analysis results of the second candidate service requirement indicating that the semantic score of the second candidate service requirement is greater than or equal to the semantic score threshold, determining the second candidate service requirement as the target service requirement.

[0017] According to one embodiment of this disclosure, the process of determining the semantic analysis result includes: obtaining a pre-set semantic quality assessment index; performing a quality assessment on the candidate business requirements based on the semantic quality assessment index using a large language model to obtain a fourth assessment value corresponding to each semantic quality assessment index; and determining the semantic score as the semantic analysis result based on the fourth assessment value and the fourth weight value corresponding to the semantic quality assessment index.

[0018] To achieve the above objectives, a second aspect of this disclosure provides an apparatus for determining a business requirement control strategy, comprising: an acquisition module for acquiring candidate business requirements; a first filtering module for determining a target business requirement based on the semantic analysis results of the candidate business requirements and establishing a knowledge graph of the target business requirement; a determination module for determining an execution flow corresponding to the target business requirement based on the knowledge graph, and determining multiple process sub-nodes in the execution flow, as well as a risk entropy value and a candidate control strategy for each process sub-node; wherein the candidate control strategy is used to indicate the proportion of different control methods used to control the target business requirement; and a second filtering module for performing multi-dimensional evaluation of at least one candidate control strategy for each process sub-node in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, and determining a target control strategy for the target business requirement based on the evaluation results of the candidate control strategies.

[0019] According to one embodiment of this disclosure, the second screening module is further configured to: determine the number of first process sub-nodes in response to the existence of a first process sub-node with a risk entropy value greater than the set threshold; and modify the target business requirements associated with the first process sub-nodes in response to the number being greater than the number threshold, until the risk entropy value of the first process sub-node is less than or equal to the set threshold.

[0020] According to one embodiment of this disclosure, the second screening module is further configured to: determine the node type of each process sub-node; determine a pre-set risk assessment indicator; perform a risk assessment on each process sub-node based on the node type and the risk assessment indicator to obtain a first assessment value; and determine the risk entropy value of each process sub-node based on a first weight value of the risk assessment indicator and the first assessment value.

[0021] According to one embodiment of this disclosure, the control method includes a first control method and a second control method. The second screening module is further configured to: determine the control constraint index corresponding to the candidate control strategy; evaluate each process sub-node based on the node type and the control constraint index to obtain a second evaluation value; determine a first control ratio value based on the second weight value of each of the control constraint indices and the second evaluation value, and determine a second control ratio value based on the first control ratio value; determine the ratio of controlling the process sub-node based on the first control method as the first control ratio value; and determine the ratio of controlling the process sub-node based on the second control method as the second control ratio value.

[0022] According to one embodiment of this disclosure, the second screening module is further configured to: evaluate the matching degree of the candidate control strategy based on a pre-set matching degree evaluation index to obtain a third evaluation value corresponding to each matching degree evaluation index; and determine the evaluation result of the candidate control strategy based on the third evaluation value and the third weight value of each matching degree evaluation index.

[0023] According to one embodiment of this disclosure, the second screening module is further configured to: screen the candidate control strategies based on the evaluation results, and select the candidate control strategies that meet the screening conditions as the target control strategy.

[0024] According to one embodiment of this disclosure, the second screening module is further configured to: establish a multi-dimensional evaluation model based on the matching degree evaluation index; and evaluate the matching degree of the candidate control strategy through the multi-dimensional evaluation model to obtain the evaluation result.

[0025] According to one embodiment of this disclosure, the first screening module is further configured to: determine abnormal information of the first candidate service requirement in response to the semantic analysis result indicating the existence of a first candidate service requirement with a semantic score less than a semantic score threshold; receive a second candidate service requirement sent by the client based on the abnormal information, and re-determine the semantic analysis result of the second candidate service requirement; and determine the second candidate service requirement as the target service requirement in response to the semantic analysis result of the second candidate service requirement indicating that the semantic score of the second candidate service requirement is greater than or equal to the semantic score threshold.

[0026] According to one embodiment of this disclosure, the first screening module is further configured to: obtain a pre-set semantic quality assessment index; perform a quality assessment on the candidate business requirements based on the semantic quality assessment index using a large language model to obtain a fourth assessment value corresponding to each semantic quality assessment index; and determine the semantic score as the semantic analysis result based on the fourth assessment value and the fourth weight value corresponding to the semantic quality assessment index.

[0027] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to implement the method for determining a service demand control strategy as described in the first aspect of this disclosure.

[0028] To achieve the above objectives, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the method for determining a business demand control strategy as described in the first aspect of this disclosure.

[0029] To achieve the above objectives, a fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, is used to implement the method for determining a business requirement control strategy as described in the first aspect of this disclosure. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0031] Figure 1 A flowchart illustrating a method for determining a business demand control strategy provided in this embodiment of the disclosure; Figure 2 A flowchart illustrating another method for determining a business demand control strategy provided in this embodiment of the disclosure; Figure 3 A flowchart illustrating another method for determining a business demand control strategy provided in this embodiment of the disclosure; Figure 4 A flowchart illustrating the determination of a target control strategy provided in an embodiment of this disclosure; Figure 5 A structural example diagram of a device for determining a business demand control strategy provided in an embodiment of this disclosure; Figure 6 This is a structural example diagram of an electronic device provided in an embodiment of this disclosure.

[0032] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0033] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0034] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0035] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the provisions of relevant laws and regulations.

[0036] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant laws, regulations and standards.

[0037] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the relevant content of the solution.

[0038] Figure 1 This is a flowchart illustrating a method for determining a business demand control strategy, as provided in an embodiment of this disclosure. Figure 1 As shown, the method for determining this business demand control strategy includes: S101, Obtain candidate business requirements.

[0039] It should be noted that the execution subject of the method for determining the business demand control strategy provided in this disclosure is an electronic device, which may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices may be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices may be network attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This disclosure does not impose specific limitations.

[0040] In some embodiments, candidate service requests sent by clients can be received; that is, candidate service requests are service requests proposed by different users. These different users can be users from different departments, or users with different roles within the same department.

[0041] In some embodiments, candidate business requirements are requirements from different business scenarios. Optionally, candidate business requirements may be business requirements proposed by the same user for different business scenarios; alternatively, candidate business requirements may be business requirements proposed by different users for the same business scenario.

[0042] In some embodiments, candidate service requirements can be received from the client or retrieved from the client periodically.

[0043] In some embodiments, the client may be an electronic device different from the executing entity of this disclosure, receiving service requests sent by different clients and using these service requests as candidate service requests. The form of the candidate service requests is not specifically limited.

[0044] In other words, candidate business requirements can be in text form or in voice form.

[0045] S102. Based on the semantic analysis results of the candidate business requirements, determine the target business requirements and establish a knowledge graph of the target business requirements.

[0046] In some embodiments, semantic analysis results can be obtained by performing semantic analysis on candidate business requirements. Optionally, the semantic analysis result can be a semantic score of the candidate business requirements. That is, during the semantic analysis of candidate business requirements, a quality assessment can be performed on the candidate business requirements, and the assessment score can be used as the semantic score.

[0047] In some embodiments, for any candidate business requirement, multiple evaluation metrics can be obtained, and quality assessment can be performed according to these metrics. For example, the quality of candidate business requirements can be assessed based on metrics such as whether the statement is legal, whether the content is relevant to the business scenario, and whether the context is consistent.

[0048] In other words, for any given metric, a score can be determined for a candidate business requirement under that metric, and based on the score for each metric, a semantic score for the candidate business requirement can be calculated. For example, the semantic score of a candidate business requirement can be obtained by weighting the scores.

[0049] In some embodiments, candidate business requirements can be filtered based on semantic analysis results to determine target business requirements. This is achieved by defining filtering criteria for target business requirements and selecting candidate business requirements that meet these criteria as target business requirements.

[0050] In some embodiments, the filtering condition can be that the semantic score is greater than or equal to the semantic score threshold, in which case the candidate business requirements corresponding to the semantic score greater than or equal to the semantic score threshold can be used as the target business requirements.

[0051] In some embodiments, after determining the target business requirements, entities and entity relationships can be extracted from the target business requirements, and a knowledge graph can be built based on the entities and entity relationships. Optionally, the knowledge graph of the target business requirements can be built using any of the related technologies for building knowledge graphs, and there is no limitation thereto.

[0052] S103, based on the knowledge graph, determine the execution process corresponding to the target business requirement, and determine multiple process sub-nodes in the execution process, as well as the risk entropy value and candidate control strategy of each process sub-node.

[0053] In some embodiments, the target business requirement can be converted into an executable sequence of steps based on a knowledge graph, and the dependencies of the sequence of steps can be identified based on information such as entities and entity relationships in the knowledge graph, thereby obtaining the execution flow corresponding to the target business requirement.

[0054] In some embodiments, using knowledge graphs to define processes can ensure the rationality, completeness, and flexibility of those processes.

[0055] In some embodiments, for the execution process of the target business requirements, multiple process sub-nodes corresponding to the execution process can be determined by splitting the process nodes in the execution process. Here, a process sub-node is a sub-node after splitting a process node, and a sub-node cannot be split.

[0056] For example, taking information review as the target business requirement, the corresponding execution process is: A [Information Submission], B [Information Initial Review], C [Review Approved]. Here, A, B, and C are multiple process nodes in the execution process. By breaking down the process nodes, the execution process is: A1 [Identity Information Scan], A2 [Information Review and Entry], B1 [Automatic Identity Verification], B2 [Information Integrity Judgment], C [Review Approved]. Then, A1, A2, B1, and B2 are process sub-nodes.

[0057] In some embodiments, after identifying process sub-nodes, a risk entropy value for each sub-node can be determined by performing a risk assessment. By determining the proportion of different control methods applied to the process sub-nodes, candidate control strategies for each sub-node can be identified.

[0058] In other words, candidate control strategies are used to indicate the proportion of different control methods used to control the target business needs.

[0059] In this embodiment of the disclosure, the control methods include business system control and system control.

[0060] Understandably, business system control refers to the process of establishing a series of rules, regulations, process specifications, operation manuals, and other documents to clarify the execution standards, approval processes, and division of responsibilities for business operations, thereby ensuring that business operations are conducted in accordance with established rules and processes.

[0061] System control refers to the use of information technology systems to automatically control and constrain business operations through functions such as setting system parameters, managing permissions, and verifying business logic.

[0062] In some embodiments, for any control method, a control ratio value can be determined and used as the ratio value corresponding to the control process sub-nodes of that control method. For each process sub-node, the control ratio value of the control method corresponding to each process sub-node is determined, thereby determining the control strategy for the target business requirements.

[0063] In some embodiments, the evaluation value of the process sub-node under each control constraint index can be evaluated according to the control constraint index corresponding to the control strategy, and the control ratio value can be determined based on the evaluation value.

[0064] For example, the evaluation values ​​of candidate control strategies can be assessed under indicators such as regulatory intensity, technological maturity, and cost constraints.

[0065] In some embodiments, after determining the control ratio value of a process sub-node, the control ratio value can be used as a control method to control the ratio value corresponding to the process sub-node, and the difference between the control ratio value and the set value can be used as another control method to control the ratio value corresponding to the process sub-node, thereby obtaining the candidate control strategy for the process sub-node.

[0066] In some embodiments, different evaluation methods can be used in the evaluation process of each control constraint index sub-node during the evaluation of the evaluation value. Each evaluation method corresponds to an evaluation value. That is, by evaluating through multiple evaluation methods, different evaluation values ​​are obtained, and different control ratio values ​​can be determined based on the different evaluation values, so as to determine different candidate control strategies based on different control ratio values.

[0067] S104, in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, perform multi-dimensional evaluation of at least one candidate control strategy for each process sub-node, and determine the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies.

[0068] In some embodiments, after determining the risk entropy value and candidate control strategies of process sub-nodes, the candidate control strategies of low-risk process sub-nodes can be evaluated to assess the degree of matching between the candidate control strategies and the business scenarios corresponding to the target business requirements.

[0069] Furthermore, the candidate control strategy that best matches the business scenario corresponding to the target business requirement will be used as the target control strategy for the target business requirement.

[0070] Optionally, process sub-nodes whose risk entropy values ​​are all less than or equal to a set threshold are considered low-risk process sub-nodes. The risk of a process sub-node can be the risk of operational errors when executing target business requirements.

[0071] In some embodiments, by evaluating the candidate control strategies of process sub-nodes in multiple dimensions, a matching degree value can be obtained to determine the degree of matching between the candidate control strategies and the business scenarios corresponding to the target business requirements, and the matching degree value can be used as the evaluation result.

[0072] In some embodiments, since each process sub-node includes at least one candidate control strategy, for any process sub-node, the evaluation result of the candidate control strategy corresponding to the process sub-node is determined, and the candidate control strategy with the largest matching degree value is determined from the evaluation result as the first target control strategy of the process sub-node.

[0073] Furthermore, the first target control strategy for each process sub-node can be determined, and the target control strategy for the target business requirements can be determined based on the first target control strategy.

[0074] In some embodiments, the first target control strategy can be combined according to the dependencies between process sub-nodes to obtain the target control strategy for the target business requirements.

[0075] In the method for determining business requirement control strategies provided in this disclosure, candidate business requirements are identified, and then a target business requirement is determined from these candidate requirements. A knowledge graph of the target business requirement is established, and the execution flow corresponding to the target business requirement is split based on the knowledge graph to obtain multiple process sub-nodes in the execution flow. The risk entropy value and candidate control strategies for each process sub-node are then determined. When the risk entropy value of each process sub-node is less than or equal to a set threshold, at least one candidate control strategy for each process sub-node is evaluated from multiple dimensions. Based on the evaluation results of the candidate control strategies, the target control strategy for the target business requirement is determined. Therefore, this solution can analyze business requirements, analyze the execution flow of business requirements, and analyze the control strategies for each process sub-node. Through multiple analyses, the target control strategy corresponding to the target business requirement is finally determined, which can improve the decision-making accuracy of the target control strategy and enhance its adaptability to the business scenario. Simultaneously, by using the method of this disclosure, the control boundaries of the target control strategy can be clearly defined, improving the feasibility of the target control strategy.

[0076] Based on any of the above embodiments, when a process sub-node has a high risk, the target business requirements associated with the high-risk process sub-node can be updated and modified to reduce the risk of the process sub-node.

[0077] In some embodiments, when the number of high-risk process sub-nodes exceeds a certain threshold, the target business requirements associated with that process sub-node can be modified.

[0078] It should be noted that a target business requirement corresponds to multiple process sub-nodes. If, among the multiple process sub-nodes corresponding to the target business requirement, there are process sub-nodes whose risk entropy values ​​exceed a set threshold, then the target business requirement will be modified.

[0079] In other words, in response to the existence of a first process sub-node with a risk entropy value greater than a set threshold, the number of first process sub-nodes is determined. In response to the number being greater than a threshold, the target business requirements associated with the first process sub-nodes are modified until the risk entropy value of the first process sub-node is less than or equal to the set threshold.

[0080] In some embodiments, risk alarm information can be generated and sent to the client corresponding to the target business requirement associated with the first process sub-node, thereby receiving modification information of the target business requirement sent by the client and modifying the target business requirement.

[0081] Based on any of the above embodiments, this disclosure can further explain the process for determining the risk entropy value of each process sub-node. Optionally, the risk entropy value can be determined by obtaining risk assessment indicators and performing risk assessments on the process sub-nodes based on these indicators, thereby determining the risk entropy value based on the assessed risk values.

[0082] In some embodiments, since process sub-nodes include types such as execution nodes and decision nodes, different types of process sub-nodes may have different risks under the same risk assessment indicator. Therefore, the risk assessment of process sub-nodes can be carried out according to the node type of the process sub-node.

[0083] In some embodiments, by determining the node type of each process sub-node and determining pre-defined risk assessment indicators, a risk assessment can be performed on each process sub-node based on the node type and risk assessment indicators to obtain a first assessment value.

[0084] Furthermore, the risk entropy value of each process sub-node can be determined based on the first weight value and the first assessment value of the risk assessment indicators. By weighting the first assessment value based on the first weight value, the risk entropy value of each process sub-node can be determined.

[0085] For example, the risk assessment indicators include: the error probability, the scope of impact, and the difficulty of repair of the process sub-nodes, with corresponding first weight values ​​of 0.4, 0.3, and 0.3, respectively. Then, the risk entropy value = 0.4 × (error probability) + 0.3 × (scope of impact) + 0.3 × (repair difficulty).

[0086] Taking the aforementioned target business requirement as information verification as an example, its corresponding process sub-nodes include A1 [Identity Information Scanning], A2 [Information Verification and Entry], B1 [Automatic Identity Verification], and B2 [Information Integrity Judgment]. The risk entropy values ​​of the process sub-nodes are shown in Table 1 below: Table 1

[0087] It is understood that each element in Table 1 exists independently. These elements are listed in the same table as an example, but this does not mean that all elements in the table must exist simultaneously as shown in the table. The value of each element is independent of the values ​​of any other element in Table 1. Therefore, those skilled in the art will understand that the value of each element in Table 1 is an independent embodiment.

[0088] In some embodiments, the different control methods used to control the target business requirements include a first control method and a second control method. By determining the proportion of process sub-nodes controlled by the first control method and the proportion of process sub-nodes controlled by the second control method, candidate control strategies for process sub-nodes can be determined.

[0089] In some embodiments, candidate control strategies can be implemented under set constraints. Then, by determining the control constraint indicators corresponding to the candidate control strategies, and evaluating each process sub-node based on the node type and control constraint indicators, a second evaluation value is obtained. Thus, a first control ratio value can be determined based on the second weight value and the second evaluation value of each control constraint indicator, and a second control ratio value can be determined based on the first control ratio value.

[0090] In some embodiments, the first control ratio value for each process sub-node can be determined by weighting the second evaluation value based on the second weight value. For example, if the control constraint indicators are: regulatory intensity, technological maturity, and cost constraint, with corresponding weight values ​​of 0.5, 0.3, and 0.2 respectively, then the first control ratio value = 0.5 × (regulatory intensity) + 0.3 × (technological maturity) + 0.2 × (cost constraint).

[0091] In some embodiments, process sub-nodes are evaluated based on node type and control constraint indicators. Different evaluation methods can be used to obtain different second evaluation values, thereby enabling the determination of different candidate control strategies based on different second evaluation values, making the candidate control strategies selective.

[0092] For example, the evaluation method can be to use a large, pre-trained model; or it can be to have a human evaluate the process sub-nodes.

[0093] In some embodiments, determining the second control proportional value based on the first control proportional value means calculating the difference between the setpoint and the first control proportional value, and using this difference as the second control proportional value. The setpoint is 1.

[0094] In some embodiments, for the first control method, the proportion of process sub-nodes controlled based on the first control method is determined as the first control proportion value; for the second control method, the proportion of process sub-nodes controlled based on the second control method is determined as the second control proportion value.

[0095] Figure 2 A flowchart illustrating another method for determining a business demand control strategy provided in this embodiment of the disclosure. Figure 2 As shown, the method for determining this business demand control strategy includes: S201, Obtain candidate business requirements.

[0096] S202. Based on the semantic analysis results of the candidate business requirements, determine the target business requirements and establish a knowledge graph of the target business requirements.

[0097] S203, based on the knowledge graph, determine the execution process corresponding to the target business requirement, and determine multiple process sub-nodes in the execution process, as well as the risk entropy value and candidate control strategy of each process sub-node.

[0098] The relevant content of steps S201-S203 can be found in the above embodiments, and will not be repeated here.

[0099] S204, in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, the candidate control strategy is evaluated based on a pre-set matching degree evaluation index to obtain a third evaluation value corresponding to each matching degree evaluation index.

[0100] In some embodiments, when the risk entropy values ​​of all process sub-nodes are less than or equal to a set threshold, the process sub-node is determined to be a low-risk process sub-node. The risk of a process sub-node can be the risk of operational errors when executing target business requirements.

[0101] In some embodiments, evaluating the matching degree of candidate control strategies refers to assessing the degree of matching between the candidate control strategies and the business scenarios corresponding to the target business needs, which can be evaluated from aspects such as technical feasibility, economy, and timeliness.

[0102] In other words, the matching evaluation indicators can be technical feasibility, economic efficiency, and timeliness.

[0103] In some embodiments, a large model can be used to evaluate the matching degree of candidate control strategies based on matching degree evaluation metrics, thereby obtaining a third evaluation value corresponding to each matching degree evaluation metric.

[0104] S205, based on the third evaluation value and the third weight value of each matching degree evaluation index, determine the evaluation result of the candidate control strategy.

[0105] In some embodiments, after obtaining the third evaluation value, the third evaluation value can be weighted and calculated based on the third weight value of each matching degree evaluation index to obtain the matching value as the evaluation result of the candidate control strategy.

[0106] For example, the matching degree evaluation indicators are: technical feasibility, economy and timeliness, with their respective third weight values ​​of 0.4, 0.35 and 0.25. Then the evaluation result = 0.4 × (technical feasibility) + 0.35 × (economy) + 0.25 × (timeliness).

[0107] For example, suppose the candidate control strategies corresponding to process sub-node 1 include strategy A, strategy B, and strategy C. Then, the third evaluation value and evaluation results of different candidate control strategies are shown in Table 2 below:

[0108] It is understood that each element in Table 2 exists independently. These elements are listed in the same table as an example, but this does not mean that all elements in the table must exist simultaneously as shown in the table. The value of each element is independent of the values ​​of any other element in Table 2. Therefore, those skilled in the art will understand that the value of each element in Table 2 is an independent embodiment.

[0109] In some embodiments, a multi-dimensional evaluation model can be established based on the matching degree evaluation index, and the matching degree of candidate control strategies can be evaluated through the multi-dimensional evaluation model to obtain the evaluation results.

[0110] S206, Based on the evaluation results, candidate control strategies are screened, and the candidate control strategies that meet the screening conditions are taken as the target control strategies.

[0111] In some embodiments, the screening criterion may be that the evaluation result indicates the candidate control strategy with the largest matching value. That is, for any process sub-node, the evaluation results of the candidate control strategies corresponding to the process sub-node are sorted, and the candidate control strategy with the largest matching value is determined from the sorted results. Then, the candidate control strategy is the candidate control strategy that satisfies the screening criterion.

[0112] It should be noted that for the target business requirements, there are multiple process sub-nodes, and each process sub-node has a different candidate control strategy. In other words, the candidate control strategies of the process sub-nodes can be screened first, and the candidate control strategies that meet the screening conditions can be used as the first target control strategy of the process sub-node.

[0113] In some embodiments, by determining a first target control strategy for each process sub-node and combining the first target control strategies according to the dependencies between process sub-nodes, a target control strategy for the target business requirements can be obtained.

[0114] In the method for determining business requirement control strategies provided in this disclosure, a pre-set matching degree evaluation index is used to assess the degree of matching between candidate control strategies and the corresponding business scenarios of target business requirements. A third evaluation value for each matching degree evaluation index can be determined. Based on this third evaluation value, the matching value between the candidate control strategy and the business scenario can be determined as the evaluation result. Therefore, the target control strategy can be determined based on the evaluation result, and the target business requirements can be controlled based on the target control strategy. By evaluating multiple matching degree evaluation indices to determine the target control strategy, the decision-making accuracy of the target control strategy can be improved, its adaptability to the business scenario can be enhanced, and the control boundaries of the target control strategy can be clearly defined, thereby improving the feasibility of the target control strategy.

[0115] Figure 3 A flowchart illustrating another method for determining a business demand control strategy provided in this embodiment of the disclosure. Figure 3 As shown, the method for determining this business demand control strategy includes: S301, Obtain candidate business requirements.

[0116] The details of step S301 can be found in the above embodiments and will not be repeated here.

[0117] S302, determine the semantic analysis results of candidate business requirements.

[0118] In some embodiments, candidate business requirements can be input into a large language model, which then performs semantic analysis on the candidate business requirements to obtain the semantic analysis results.

[0119] In some embodiments, the semantic analysis results of candidate business requirements can also be determined by different indicators. That is, the quality of candidate business requirements can be evaluated based on different indicators, thereby determining the quality evaluation results as semantic analysis results.

[0120] In some embodiments, by obtaining pre-defined semantic quality assessment indicators and using a large language model to assess the quality of candidate business requirements based on these indicators, a fourth assessment value is obtained for each semantic quality assessment indicator.

[0121] Furthermore, the semantic score can be determined as the semantic analysis result based on the fourth evaluation value and the fourth weight value corresponding to the semantic quality evaluation index. Optionally, the semantic score can be obtained by weighting the fourth evaluation result based on the fourth weight value.

[0122] For example, semantic quality assessment indicators may include statement legality, content adaptability to business scenarios, and contextual consistency, with their respective fourth weight values ​​being α, β, and γ. Then, the semantic analysis result = α × (statement legality) + β × (content adaptability to business scenarios) + γ × (contextual consistency).

[0123] S303, in response to the semantic analysis result indicating the existence of a first candidate business requirement with a semantic score less than the semantic score threshold, determine the abnormal information of the first candidate business requirement.

[0124] S304, Receive the second candidate service requirement sent by the client based on the abnormal information, and redetermine the semantic analysis result of the second candidate service requirement.

[0125] S305, in response to the semantic analysis result indicating that the semantic score of the second candidate business requirement is greater than or equal to the semantic score threshold, the second candidate business requirement is determined as the target business requirement.

[0126] In some embodiments, if the semantic analysis results indicate that there is a first candidate service requirement with a semantic score less than the semantic score threshold, it can be determined that the semantic quality of the first candidate service requirement is poor and that there is an anomaly in the first candidate service requirement, and thus the anomaly information of the first candidate service requirement can be determined.

[0127] In some embodiments, abnormal information can be determined based on the first four evaluation values. If the semantic score is less than the semantic score threshold, the semantic quality evaluation index with the smallest evaluation value is determined from the fourth evaluation values, and the information indicated by the index is taken as abnormal information.

[0128] For example, if the fourth evaluation value corresponding to context consistency is the smallest among statement validity, content adaptability to business scenario, and context consistency, then the context inconsistency indicated by context consistency can be regarded as an exception.

[0129] In some embodiments, after receiving an anomaly message, the client can modify the first candidate service requirement based on the anomaly message, thereby receiving the modified second candidate service requirement, and re-evaluating the semantic quality of the second candidate service requirement to obtain the semantic analysis result of the second candidate service requirement.

[0130] If the semantic analysis results of the second candidate business requirement indicate that its semantic score is greater than or equal to the semantic score threshold, the second candidate business requirement can be determined as the target business requirement.

[0131] S306, Establish a knowledge graph of the target business requirements.

[0132] S307, based on the knowledge graph, determines the execution process corresponding to the target business requirement, and determines multiple process sub-nodes in the execution process, as well as the risk entropy value and candidate control strategy of each process sub-node.

[0133] S308, in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, performs a multi-dimensional evaluation of at least one candidate control strategy for each process sub-node, and determines the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies.

[0134] The relevant content of steps S306-S308 can be found in the above embodiments, and will not be repeated here.

[0135] In the method for determining business requirement control strategies provided in this disclosure, semantic analysis is performed on candidate business requirements to determine target business requirements based on the semantic analysis results. Determining target business requirements through semantic analysis improves the rationality of the target business requirements, which is beneficial for subsequent process decomposition of the target business requirements and enhances the accuracy of the process decomposition.

[0136] Figure 4 This is a flowchart illustrating the process of determining a target control strategy according to an embodiment of this disclosure. For candidate service requirements, semantic analysis can be performed to obtain the semantic analysis results. Based on these results, the target service requirement can be determined, and a knowledge graph of the target service requirement can be established.

[0137] Furthermore, based on the knowledge graph, the execution process corresponding to the target business requirement can be determined, and the execution process can be decomposed into multiple process sub-nodes. By determining the risk entropy value and candidate control strategies of the process sub-nodes, the candidate control strategies of process sub-nodes with risk entropy values ​​less than or equal to a set threshold can be evaluated from multiple dimensions, thereby determining the target control strategy for the target business requirement.

[0138] Corresponding to the methods for determining business demand control strategies provided in the above embodiments, one embodiment of this disclosure also provides a device for determining business demand control strategies. Since the device for determining business demand control strategies provided in this disclosure corresponds to the methods for determining business demand control strategies provided in the above embodiments, the implementation methods for determining business demand control strategies described above are also applicable to the device for determining business demand control strategies provided in this disclosure, and will not be described in detail in the following embodiments.

[0139] Figure 5 This is a structural example diagram of a device for determining a business demand control strategy, provided in an embodiment of this disclosure. (See diagram below.) Figure 5As shown, the device for determining the business demand control strategy includes: an acquisition module 501, a first filtering module 502, a determination module 503, and a second filtering module 504.

[0140] Module 501 is used to acquire candidate business requirements; The first screening module 502 is used to determine the target business requirement based on the semantic analysis results of the candidate business requirements, and to establish a knowledge graph of the target business requirement. The determination module 503 is used to determine the execution process corresponding to the target business requirement based on the knowledge graph, and to determine multiple process sub-nodes in the execution process, as well as the risk entropy value and candidate control strategy of each process sub-node; wherein, the candidate control strategy is used to indicate the proportion of different control methods used to control the target business requirement; The second screening module 504 is used to perform multi-dimensional evaluation of at least one candidate control strategy for each process sub-node in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, and to determine the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies.

[0141] According to one embodiment of this disclosure, the second screening module 504 is further configured to: determine the number of first process sub-nodes in response to the existence of a first process sub-node with a risk entropy value greater than the set threshold; and modify the target business requirements associated with the first process sub-nodes in response to the number being greater than the number threshold, until the risk entropy value of the first process sub-node is less than or equal to the set threshold.

[0142] According to one embodiment of this disclosure, the second screening module 504 is further configured to: determine the node type of each process sub-node; determine a pre-set risk assessment indicator; perform a risk assessment on each process sub-node based on the node type and the risk assessment indicator to obtain a first assessment value; and determine the risk entropy value of each process sub-node based on a first weight value of the risk assessment indicator and the first assessment value.

[0143] According to one embodiment of this disclosure, the control method includes a first control method and a second control method. The second screening module 504 is further configured to: determine the control constraint index corresponding to the candidate control strategy; evaluate each process sub-node based on the node type and the control constraint index to obtain a second evaluation value; determine a first control ratio value based on the second weight value of each of the control constraint indexes and the second evaluation value, and determine a second control ratio value based on the first control ratio value; determine the ratio of controlling the process sub-node based on the first control method as the first control ratio value; and determine the ratio of controlling the process sub-node based on the second control method as the second control ratio value.

[0144] According to one embodiment of this disclosure, the second screening module 504 is further configured to: evaluate the matching degree of the candidate control strategy based on a pre-set matching degree evaluation index to obtain a third evaluation value corresponding to each matching degree evaluation index; and determine the evaluation result of the candidate control strategy based on the third evaluation value and the third weight value of each matching degree evaluation index.

[0145] According to one embodiment of this disclosure, the second screening module 504 is further configured to: screen the candidate control strategies based on the evaluation results, and select the candidate control strategies that meet the screening conditions as the target control strategies.

[0146] According to one embodiment of this disclosure, the second screening module 504 is further configured to: establish a multi-dimensional evaluation model based on the matching degree evaluation index; and evaluate the matching degree of the candidate control strategy through the multi-dimensional evaluation model to obtain the evaluation result.

[0147] According to one embodiment of this disclosure, the first screening module 502 is further configured to: determine abnormal information of the first candidate service requirement in response to the semantic analysis result indicating that there is a first candidate service requirement with a semantic score less than a semantic score threshold; receive a second candidate service requirement sent by the client based on the abnormal information, and re-determine the semantic analysis result of the second candidate service requirement; and determine the second candidate service requirement as the target service requirement in response to the semantic analysis result of the second candidate service requirement indicating that the semantic score of the second candidate service requirement is greater than or equal to the semantic score threshold.

[0148] According to one embodiment of this disclosure, the first screening module 502 is further configured to: obtain a pre-set semantic quality assessment index; perform a quality assessment on the candidate business requirements based on the semantic quality assessment index using a large language model to obtain a fourth assessment value corresponding to each semantic quality assessment index; and determine the semantic score as the semantic analysis result based on the fourth assessment value and the fourth weight value corresponding to the semantic quality assessment index.

[0149] In the business requirement control strategy determination apparatus provided in this disclosure, candidate business requirements are determined, and a target business requirement is determined from these candidate requirements. A knowledge graph of the target business requirement is established, and the execution flow corresponding to the target business requirement is split based on the knowledge graph to obtain multiple process sub-nodes in the execution flow. The risk entropy value and candidate control strategy of each process sub-node are determined. When the risk entropy value of each process sub-node is less than or equal to a set threshold, at least one candidate control strategy for each process sub-node is evaluated from multiple dimensions. Based on the evaluation results of the candidate control strategies, the target control strategy for the target business requirement is determined. Therefore, this solution can analyze business requirements, analyze the execution flow of business requirements, and analyze the control strategy of each process sub-node. Through multiple analyses, the target control strategy corresponding to the target business requirement is finally determined, which can improve the decision-making accuracy of the target control strategy and enhance its adaptability to the business scenario. Simultaneously, by using the method of this disclosure, the control boundary of the target control strategy can be clearly defined, improving the feasibility of the target control strategy.

[0150] Figure 6 This is an example structural diagram of an electronic device provided in an embodiment of this disclosure. For example... Figure 6 As shown, the electronic device 600 may include: a transceiver 601, a processor 602, and a memory 603.

[0151] The processor 602 executes computer execution instructions stored in the memory, causing the processor 602 to perform the scheme in the above embodiments. The processor 602 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0152] The memory 603 is connected to the processor 602 via the system bus and completes communication between them. The memory 603 is used to store computer program instructions.

[0153] Transceiver 601 can be used to obtain the task to be run and its configuration information.

[0154] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Transceivers are used to enable communication between database access devices and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory.

[0155] The electronic device provided in this disclosure can be the terminal device described in the above embodiments.

[0156] This disclosure also provides a chip for executing instructions, which is used to implement the technical solution of the method for determining the business demand control strategy in the above embodiments.

[0157] This disclosure also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the technical solution of the method for determining the business requirement control strategy described in the above embodiments.

[0158] This disclosure also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the technical solution of the method for determining the business requirement control strategy in the above embodiments.

[0159] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0160] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for determining a business requirements control strategy, characterized in that, The method includes: Obtain candidate business requirements; Based on the semantic analysis results of the candidate business requirements, the target business requirements are determined, and a knowledge graph of the target business requirements is established. Based on the knowledge graph, the execution process corresponding to the target business requirement is determined, and multiple process sub-nodes in the execution process are determined, as well as the risk entropy value and candidate control strategy of each process sub-node; wherein, the candidate control strategy is used to indicate the proportion of different control methods used to control the target business requirement; In response to the fact that the risk entropy value of each process sub-node is less than or equal to a set threshold, at least one candidate control strategy for each process sub-node is evaluated in multiple dimensions, and the target control strategy for the target business requirement is determined based on the evaluation results of the candidate control strategies.

2. The method according to claim 1, characterized in that, The method further includes: In response to the existence of a first process sub-node with a risk entropy value greater than the set threshold, the number of the first process sub-nodes is determined; In response to the quantity exceeding a threshold, the target business requirements associated with the first process sub-node are modified until the risk entropy value of the first process sub-node is less than or equal to the set threshold.

3. The method according to claim 1, characterized in that, Determining the risk entropy value of each process sub-node includes: Determine the node type for each process sub-node; Determine pre-defined risk assessment indicators; Based on the node type and the risk assessment indicators, a risk assessment is performed on each process sub-node to obtain a first assessment value; Based on the first weight value and the first assessment value of the risk assessment indicator, the risk entropy value of each process sub-node is determined.

4. The method according to claim 3, characterized in that, The control method includes a first control method and a second control method, and the candidate control strategy for each process sub-node is determined, including: Determine the control constraint indicators corresponding to the candidate control strategies; Based on the node type and the control constraint index, each process sub-node is evaluated to obtain a second evaluation value; Based on the second weight value and the second evaluation value of each of the control constraint indicators, a first control ratio value is determined, and a second control ratio value is determined based on the first control ratio value. The proportion of the process sub-node controlled based on the first control method is determined as the first control proportion value; The proportion of the process sub-node controlled based on the second control method is determined as the second control proportion value.

5. The method according to any one of claims 1-4, characterized in that, The multi-dimensional evaluation of at least one candidate control strategy for each process sub-node includes: Based on the pre-set matching degree evaluation index, the candidate control strategy is evaluated to obtain a third evaluation value corresponding to each matching degree evaluation index. Based on the third evaluation value and the third weight value of each matching degree evaluation index, the evaluation result of the candidate control strategy is determined.

6. The method according to claim 5, characterized in that, The step of determining the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies includes: Based on the evaluation results, the candidate control strategies are screened, and the candidate control strategies that meet the screening criteria are taken as the target control strategies.

7. The method according to claim 5, characterized in that, The method further includes: A multi-dimensional evaluation model is established based on the aforementioned matching degree evaluation index; The candidate control strategies are evaluated using the multi-dimensional evaluation model to obtain the evaluation results.

8. The method according to any one of claims 1-4, characterized in that, The step of determining the target business requirement based on the semantic analysis results of the candidate business requirements includes: In response to the semantic analysis result indicating the existence of a first candidate service requirement with a semantic score less than a semantic score threshold, anomaly information of the first candidate service requirement is determined; Receive the second candidate service request sent by the client based on the abnormal information, and redetermine the semantic analysis result of the second candidate service request; In response to the semantic analysis result indicating that the semantic score of the second candidate service requirement is greater than or equal to the semantic score threshold, the second candidate service requirement is determined as the target service requirement.

9. The method according to claim 8, characterized in that, The process of determining the semantic analysis result includes: Obtain pre-defined semantic quality assessment metrics; The candidate business requirements are evaluated using a large language model based on the semantic quality evaluation indicators to obtain a fourth evaluation value for each semantic quality evaluation indicator. Based on the fourth evaluation value and the fourth weight value corresponding to the semantic quality evaluation index, the semantic score is determined as the semantic analysis result.

10. A device for determining a business demand control strategy, characterized in that, The device includes: The acquisition module is used to acquire candidate business requirements; The first screening module is used to determine the target business requirement based on the semantic analysis results of the candidate business requirements, and to establish a knowledge graph of the target business requirement. The determination module is used to determine the execution process corresponding to the target business requirement based on the knowledge graph, and to determine multiple process sub-nodes in the execution process, as well as the risk entropy value and candidate control strategy of each process sub-node; wherein, the candidate control strategy is used to indicate the proportion of different control methods used to control the target business requirement; The second screening module is used to evaluate at least one candidate control strategy for each process sub-node in a multi-dimensional manner in response to the risk entropy value of each process sub-node being less than or equal to a set threshold, and to determine the target control strategy for the target business requirement based on the evaluation results of the candidate control strategies.

11. The apparatus according to claim 10, characterized in that, The second filtering module is also used for: In response to the existence of a first process sub-node with a risk entropy value greater than the set threshold, the number of the first process sub-nodes is determined; In response to the quantity exceeding a threshold, the target business requirements associated with the first process sub-node are modified until the risk entropy value of the first process sub-node is less than or equal to the set threshold.

12. The apparatus according to claim 10, characterized in that, The second filtering module is also used for: Determine the node type for each process sub-node; Determine pre-defined risk assessment indicators; Based on the node type and the risk assessment indicators, a risk assessment is performed on each process sub-node to obtain a first assessment value; Based on the first weight value and the first assessment value of the risk assessment indicator, the risk entropy value of each process sub-node is determined.

13. The apparatus according to claim 12, characterized in that, The control method includes a first control method and a second control method, and the second filtering module is further used for: Determine the control constraint indicators corresponding to the candidate control strategies; Based on the node type and the control constraint index, each process sub-node is evaluated to obtain a second evaluation value; Based on the second weight value and the second evaluation value of each of the control constraint indicators, a first control ratio value is determined, and a second control ratio value is determined based on the first control ratio value. The proportion of the process sub-node controlled based on the first control method is determined as the first control proportion value; The proportion of the process sub-node controlled based on the second control method is determined as the second control proportion value.

14. The apparatus according to any one of claims 10-13, characterized in that, The second filtering module is also used for: Based on the pre-set matching degree evaluation index, the candidate control strategy is evaluated to obtain a third evaluation value corresponding to each matching degree evaluation index. Based on the third evaluation value and the third weight value of each matching degree evaluation index, the evaluation result of the candidate control strategy is determined.

15. The apparatus according to claim 14, characterized in that, The second filtering module is also used for: Based on the evaluation results, the candidate control strategies are screened, and the candidate control strategies that meet the screening criteria are taken as the target control strategies.

16. The apparatus according to claim 14, characterized in that, The second filtering module is also used for: A multi-dimensional evaluation model is established based on the aforementioned matching degree evaluation index; The candidate control strategies are evaluated using the multi-dimensional evaluation model to obtain the evaluation results.

17. The apparatus according to any one of claims 10-13, characterized in that, The first filtering module is further configured to: In response to the semantic analysis result indicating the existence of a first candidate service requirement with a semantic score less than a semantic score threshold, anomaly information of the first candidate service requirement is determined; Receive the second candidate service request sent by the client based on the abnormal information, and redetermine the semantic analysis result of the second candidate service request; In response to the semantic analysis result indicating that the semantic score of the second candidate service requirement is greater than or equal to the semantic score threshold, the second candidate service requirement is determined as the target service requirement.

18. The apparatus according to claim 17, characterized in that, The first filtering module is further configured to: Obtain pre-defined semantic quality assessment metrics; The candidate business requirements are evaluated using a large language model based on the semantic quality evaluation indicators to obtain a fourth evaluation value for each semantic quality evaluation indicator. Based on the fourth evaluation value and the fourth weight value corresponding to the semantic quality evaluation index, the semantic score is determined as the semantic analysis result.

19. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-9.

20. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-9.

21. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-9.

Images