Examination and approval timeout processing method and device and medium

Abstract

The invention discloses an approval timeout processing method and device and a medium, and the method comprises the steps: quantifying the behavior data of an approver through a dynamic weight algorithm, determining the cognitive load index of the approver, inputting the cognitive load index into a preset mixed causal reasoning model, generating a root cause map of approval timeout, and carrying out the approval timeout processing according to the root cause displayed by the root cause map. And determining an examination and approval decision corresponding to the overtime document, synchronizing the examination and approval decision to an original examination and approval system through a communication enhancement architecture, and generating an anti-fact auditing report containing biological feature verification. Through multi-modal causal reasoning, accurate attribution of examination and approval delay reasons is realized, meanwhile, an automatic examination and approval triggering mechanism of artificial intelligence deep processing can automatically give a processing scheme according to a root cause result, the waiting time of manual examination and approval is greatly shortened, the adaptability of an examination and approval process is improved, and the examination and approval efficiency is improved. And remarkable convenience and benefits are brought to operation and management of enterprises.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, device and medium for handling approval timeouts. Background Technology

[0002] Currently, intelligent approval technology is developing towards automation, standardization, and intelligence, with continuous advancements in technologies such as full-process automation, intelligent pre-review and instant approval, and data integration and sharing.

[0003] However, existing intelligent approval technologies rely on log recording for data collection, lack fine-grained monitoring of approver behavior, and rely on a single threshold for timeout warnings without establishing a multi-dimensional timeliness baseline model. Ultimately, this results in weak attribution capabilities of existing intelligent approval technologies, failing to deeply identify the reasons for approval timeouts and failing to fundamentally solve the problem of approval delays. At the intervention level, automated processing lacks dynamic adaptability, resulting in the need for human intervention in emergency situations. Summary of the Invention

[0004] This application provides a method, device, and medium for handling approval timeouts, which addresses the problems of weak attribution ability and poor adaptability in existing approval timeout handling methods.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] On the one hand, embodiments of this application provide a method for handling approval timeouts, the method comprising:

[0007] The behavioral data of approvers is quantified by a dynamic weighting algorithm to determine their cognitive load index. The cognitive load index is then input into a preset hybrid causal reasoning model to generate a root cause map of approval timeouts. Based on the root causes shown in the root cause map, the approval decision corresponding to the timeout document is determined. The approval decision is then synchronized to the original approval system through a communication enhancement architecture, and a counterfactual audit report including biometric verification is generated.

[0008] In one example, based on the root causes shown in the root cause graph, the approval decision corresponding to the timed-out document is determined. Specifically, this includes: when the root cause graph shows that the root cause is a process design flaw, a sandbox pre-approval mechanism of "confirmation-approval" is executed; when the root cause graph shows that the root cause is due to the approver's poor time management, a pre-authorization decision mechanism of "automatic-approval-blockchain evidence storage" is executed; and when the root cause graph shows that the root cause is due to cross-departmental collaboration blockage, a conversational document confirmation and approval mechanism is executed.

[0009] In one example, when the root cause graph shows that the root cause is a process design flaw, a confirmation-approval sandbox pre-approval mechanism is executed. This mechanism includes: comparing the content of the timed-out document with preset approval standards through a virtual execution engine; if the content of the timed-out document meets the preset approval standards, performing a security check on the content of the timed-out document; if the security check passes, approving the timed-out document according to the preset approval specifications and updating the process knowledge base synchronously; if the security check fails, sending a timed-out document anomaly alarm to the client.

[0010] In one example, when the root cause graph shows that the root cause is the approver's poor time management, an automatic-approval-blockchain notarization pre-authorization decision mechanism is executed. Specifically, this includes: when it is determined that the root cause is the approver's poor time management, approving overdue documents according to preset approval specifications and recording the approval record; verifying the approval record through a preset smart contract; if the verification passes, storing the approval record on a blockchain node and sending an approval summary report to the client; if the verification fails, readjusting the parameters of the preset hybrid causal reasoning model.

[0011] In one example, when the root cause graph shows that the root cause is blocked by cross-departmental collaboration, a conversational document confirmation and approval mechanism is executed. Specifically, this includes: sending a multimodal document confirmation instruction to the approver through the communication adaptation layer; upon receiving the approver's confirmation request, approving the timed-out document according to the preset approval specifications and recording the approval record; and triggering the timed-out approval process reconstruction according to the preset reconstruction rules.

[0012] In one example, the cognitive load index is input into a preset hybrid causal inference model to generate a root cause map of approval timeouts. Specifically, this includes: analyzing the cross-departmental collaboration delay matrix of the cognitive load index using a dynamic Bayesian network to determine the matrix analysis results; analyzing the temporal pattern of the cognitive load index using an LSTM-Transformer model to determine the temporal analysis results; fusing the matrix analysis results with the temporal analysis results to determine the root cause probability distribution and generate a root cause map; and displaying the root cause with the highest probability value in the root cause probability distribution in the map.

[0013] In one example, a dynamic weighting algorithm is used to quantify the approver's behavioral data to determine the approver's cognitive load index. Specifically, this includes: quantifying operating system behavioral data, calendar status, and historical approval records based on the matching degree between the approver's real-time behavioral flow and historical approval efficiency, and obtaining the weight ratios of the operating system behavioral data, calendar status, and historical approval records; the higher the matching degree between the real-time behavioral flow and historical approval efficiency, the higher the corresponding weight ratio; and determining the approver's cognitive load index based on the weight ratio using a preset cognitive load index formula.

[0014] In one example, based on the matching degree between the approver's real-time behavior flow and historical approval efficiency, the operating system behavior data, calendar status, and historical approval records are quantified. Specifically, this includes: quantifying calendar status data through calendar event correlation and GPS location analysis; quantifying historical approval record data through approval system operation logs and HR-related data; and quantifying operating system behavior data by preset event urgency and preset event sensitivity.

[0015] On the other hand, embodiments of this application provide an approval timeout processing device, including: 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 enable the at least one processor to perform an approval timeout processing method as described above.

[0016] On the other hand, embodiments of this application provide an approval timeout processing non-volatile computer storage medium storing computer-executable instructions that can execute any of the above-mentioned approval timeout processing methods.

[0017] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0018] This application utilizes multimodal causal reasoning to automatically identify the causes of approval delays, achieving accurate attribution of these delays. Simultaneously, the AI-powered automated approval triggering mechanism automatically provides solutions based on root cause results, thereby optimizing the approval process, improving work efficiency, significantly reducing waiting time for manual approvals, and enhancing the automation and adaptability of the approval process. This brings significant convenience and benefits to enterprise operations and management. Attached Figure Description

[0019] To more clearly illustrate the technical solution of this application, some embodiments of this application will be described in detail below with reference to the accompanying drawings, in which:

[0020] Figure 1 A flowchart illustrating an approval timeout handling method provided in this application embodiment;

[0021] Figure 2 A cognitive load index generation diagram for an approval timeout handling method provided in this application embodiment;

[0022] Figure 3 A root cause graph generation diagram for an approval timeout handling method provided in this application embodiment;

[0023] Figure 4 A flowchart illustrating the intelligent processing mechanism of an approval timeout handling method provided in this application embodiment;

[0024] Figure 5 A counterfactual audit report generation diagram for an approval timeout handling method provided in this application embodiment;

[0025] Figure 6 This is a schematic diagram of an approval timeout processing device provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] Some embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0028] Figure 1 This is a flowchart illustrating an approval timeout handling method provided in this application embodiment. This method can be applied to different business domains. Certain input parameters or intermediate results in this process allow for manual intervention and adjustment to help improve accuracy.

[0029] The analysis method involved in the embodiments of this application can be implemented by a terminal device or a server, and this application does not impose any special limitations on it. For ease of understanding and description, the following embodiments are all described in detail using a controller as an example.

[0030] Based on this Figure 1 The process may include the following steps:

[0031] S101: Quantify the approver's behavioral data through a dynamic weighting algorithm to determine the approver's cognitive load index.

[0032] In some embodiments of this application, before quantifying the approver's behavioral data using a dynamic weighting algorithm to determine the approver's cognitive load index, it is necessary to first obtain the approver's behavioral data. The obtained behavioral data includes the approver's operating system behavioral data, calendar status, and historical approval records. Specifically:

[0033] Regarding the acquisition of operating system behavior data, a lightweight monitoring SDK is integrated into the terminal devices (such as computers and mobile phones) used by approvers to capture low-level operating system logs in real time. Hook functions are used to monitor actions such as mouse clicks, keyboard input, and window switching, recording fine-grained data such as page dwell time, operation trajectory, and task switching frequency.

[0034] Regarding the acquisition of calendar status data, we connect to the calendar system used by approvers (such as Outlook or WeChat Work calendar) through an enterprise-level API interface to synchronously obtain schedule data, parse the meeting arrangements, to-do items, vacation information and other content in the calendar, and extract key time nodes and event types through natural language processing technology.

[0035] Regarding the acquisition of historical approval record data, historical approval data is extracted from the enterprise's existing approval system database, including approval document content, approval timestamps, approval node flow records, etc. The approval records scattered in different business systems are integrated through ETL (Extract-Transform-Load) tools to form a standardized historical approval trajectory dataset.

[0036] Furthermore, after acquiring the completed behavioral data, the approver's behavioral data is quantified using a dynamic weighting algorithm to determine the approver's cognitive load index, specifically including:

[0037] Based on the matching degree between the approver's real-time behavior flow and historical approval efficiency (for example, if the approver is between 22:00 and 8:00, since it is not working hours, the matching degree with the time in the calendar status is relatively low), the operating system behavior data, calendar status, and historical approval records are quantified to obtain the weight ratio of the operating system behavior data, calendar status, and historical approval records; the higher the matching degree between the real-time behavior flow and historical approval efficiency, the higher the corresponding weight ratio; then, based on the weight ratio, the approver's cognitive load index is determined through a preset cognitive load index formula.

[0038] Regarding the operation of quantifying behavioral data, each type of behavioral data has a different quantification method. Specifically, calendar status data is quantified by associating calendar events and analyzing GPS location; historical approval record data is quantified by approving system operation logs and HR-related data; and operating system behavioral data is quantified by preset event urgency and preset event sensitivity.

[0039] The formula for the cognitive load index is:

[0040] Cognitive load index = α × (operating system behavior data) + β × (calendar status data) + δ × (historical approval record data) - η × (holiday / festival gain)

[0041] Where α represents the weighting of operating system behavior data, β represents the weighting of calendar status data, δ represents the weighting of historical approval record data, and η represents the weighting of holiday and festival gains.

[0042] This application utilizes a dynamic weighting algorithm to quantify the cognitive load index of approvers, which can clearly distinguish between delays caused by system process defects and human factors, providing a basis for subsequent targeted problem-solving. Simultaneously, as input to a hybrid causal inference model, a dynamic Bayesian network + LSTM-Transformer hybrid model is used to further subdivide the attribution of approval delays into factors such as process design defects, cross-departmental collaboration bottlenecks, and Friday delay peaks for specific approvers, thereby improving the accuracy of attribution.

[0043] S102: Input the cognitive load index into a preset hybrid causal reasoning model to generate a root cause map of approval timeout.

[0044] It should be noted that the hybrid causal reasoning model in this application consists of a dynamic Bayesian network and an LSTM-Transformer model.

[0045] In some embodiments of this application, the cognitive load index reflects the workload of the approver. After obtaining the cognitive load index, the cognitive load index is input into a preset hybrid causal inference model. The cross-departmental collaboration delay matrix of the cognitive load index is analyzed by dynamic Bayesian network. After Bayesian calculation, the matrix analysis result is determined.

[0046] Furthermore, the temporal pattern of the cognitive load index is analyzed using the LSTM-Transformer model to capture the temporal sequence of the cognitive load index and determine the temporal analysis results.

[0047] Finally, the matrix analysis results are fused with the time series analysis results to determine the root cause probability distribution and generate a root cause map. Then, the root cause with the highest probability value in the root cause probability distribution is displayed in the map.

[0048] By analyzing the cognitive load index and combining it with other data (such as organizational-level data flow and cross-departmental collaboration delay matrices), the dynamic Bayesian network and LSTM-Transformer model in the hybrid causal inference model can more accurately determine whether approval delays are caused by process design flaws, cross-departmental collaboration blockages, or specific approver's personal issues (such as time management problems like Friday delay peaks). For example, if the cognitive load index is consistently high during a specific time period (such as Friday) and approval delays also exist, the model can consider the Friday delay peak of a specific approver as one of the possible root causes and incorporate it into the root cause mapping process.

[0049] S103: Determine the approval decision corresponding to the timed-out document based on the root causes shown in the root cause map.

[0050] In some embodiments of this application, after obtaining the root cause map, the approval decision corresponding to the timed-out document is determined based on the root causes shown in the root cause map. The specific steps are as follows:

[0051] When the root cause graph shows that the root cause is a flaw in the process design, a "confirmation-approval" sandbox pre-approval mechanism is executed. This means that through a virtual execution engine, the content of the timed-out document is compared with the preset approval standards. If the content of the timed-out document meets the preset approval standards, a security check is performed on the content of the timed-out document. If the security check passes, the timed-out document is approved according to the preset approval specifications, and the process knowledge base is updated synchronously. If the security check fails, a timed-out document anomaly alarm is sent to the client.

[0052] When the root cause graph shows that the root cause is the approver's poor time management, a pre-authorization decision mechanism of "automatic-approval-blockchain notarization" is executed. That is, when it is determined that the root cause is the approver's poor time management, the overdue document is approved according to the preset approval specifications and the approval record is recorded. Then, the approval record is verified through a preset smart contract. If the verification is successful, the approval record is notarized on the blockchain node and an approval summary report is sent to the client. If the verification fails, the parameters of the preset hybrid causal reasoning model are readjusted.

[0053] When the root cause graph shows that the root cause is blocked by cross-departmental collaboration, a conversational document confirmation and approval mechanism is executed. That is, through the communication adaptation layer, a multimodal document confirmation instruction is sent to the approver. After receiving the approver's confirmation request, the overdue document is approved according to the preset approval specifications and the approval record is recorded. Finally, the overdue approval process is reconstructed according to the preset reconstruction rules.

[0054] This application establishes corresponding approval mechanisms for each root cause, enabling the system to automatically provide processing solutions based on the root cause results, thereby optimizing the approval process, improving work efficiency, and significantly reducing the waiting time for manual approval.

[0055] S104: Synchronize approval decisions to the original approval system through a communication enhancement architecture and generate a counterfactual audit report that includes biometric verification.

[0056] In some embodiments of this application, after determining the approval decision corresponding to the timed-out document and approving it, the approval decision is synchronized to the original approval system by means of a communication enhancement architecture, and a counterfactual audit report with biometric verification (such as fingerprint or facial unlock) is generated.

[0057] It's worth noting that the synchronization engine in the communication enhancement architecture utilizes the WebSocket protocol to build long-lived connections, enabling real-time monitoring of decision commands. Through protocol converters and communication gateways, it allows systems with different interface protocols to achieve compatible communication. Simultaneously, the circuit breaker controller and heartbeat detection mechanism within the architecture ensure the stability of the synchronization process, triggering circuit breakers and caching data through local transaction logs in case of anomalies.

[0058] The counterfactual audit report covers key approval information, verification results, root cause analysis, etc., supports visualization, provides a basis for process optimization, and achieves the reliability of synchronous approval decisions, the compliance of audit traceability, and data support for process optimization.

[0059] It should be noted that, although the embodiments in this application are based on... Figure 1 Steps S101 to S104 will be described sequentially, but this does not mean that steps S101 and S104 must be performed in a strict order. The reason this embodiment follows this order is... Figure 1 The order in which steps S101 to S104 are described is provided to facilitate understanding of the technical solutions of the embodiments of this application by those skilled in the art. In other words, in the embodiments of this application, the order of steps S101 to S104 can be appropriately adjusted according to actual needs.

[0060] pass Figure 1 This application utilizes multimodal causal reasoning to automatically identify the causes of approval delays, achieving accurate attribution of these delays. Simultaneously, the AI-powered deep processing-based automatic approval triggering mechanism automatically provides solutions based on root cause results, thereby optimizing the approval process, improving work efficiency, significantly reducing waiting time for manual approvals, and enhancing the automation and adaptability of the approval process. This brings significant convenience and benefits to enterprise operations and management.

[0061] Figure 2 A cognitive load index generation diagram for an approval timeout handling method provided in this application embodiment.

[0062] exist Figure 2 The document demonstrates how to receive and process approver operating system behavior data, calendar status, and historical approval trajectories, and quantify the approver's cognitive load index in real time using a dynamic weighting algorithm.

[0063] Figure 3 This is a root cause graph generation diagram for an approval timeout handling method provided in this application embodiment.

[0064] exist Figure 3 The paper demonstrates how a hybrid causal reasoning model combines dynamic Bayesian networks and LSTM-Transformer to analyze organizational bottlenecks and capture temporal patterns of individual behavior, generating timeout root cause maps.

[0065] Figure 4 This is a flowchart illustrating the intelligent processing mechanism of an approval timeout handling method provided in this application embodiment.

[0066] exist Figure 4The document demonstrates the triggering process of the intelligent processing mechanism, including the "confirmation-approval" sandbox pre-approval mode, the "automatic-approval + blockchain evidence storage" pre-authorization decision, and the implementation process of "conversational document confirmation and approval".

[0067] Figure 5 A counterfactual audit report generation diagram for an approval timeout handling method provided in this application embodiment.

[0068] exist Figure 5 The paper demonstrates how a communication-enhanced architecture can synchronize processing decisions to the original approval system in real time and generate counterfactual audit reports that include biometric verification.

[0069] Figure 6 A schematic diagram of an approval timeout processing device provided in this application embodiment includes:

[0070] At least one processor; and,

[0071] A memory that is communicatively connected to at least one processor; wherein,

[0072] An approval timeout handling method is provided in which the memory stores instructions that can be executed by at least one processor, such that the at least one processor is able to perform any of the above-mentioned actions.

[0073] Some embodiments of this application provide an approval timeout processing non-volatile computer storage medium storing computer-executable instructions that can execute any of the above-described approval timeout processing methods.

[0074] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0075] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0076] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0078] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0079] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0081] Memory may include non-persistent storage in computer-readable media, random access memory (RAM), and non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0082] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0083] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0084] The above are merely embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the technical principles of this application should fall within the protection scope of this application.

Claims

1. A method for handling approval timeouts, characterized in that, The method includes: The approver's behavioral data is quantified using a dynamic weighting algorithm to determine the approver's cognitive load index; the behavioral data includes the approver's operating system behavior data, calendar status, and historical approval records. The cognitive load index is input into a preset hybrid causal inference model to generate a root cause map of approval timeouts; the hybrid causal inference model includes a dynamic Bayesian network and an LSTM-Transformer model; the root causes include process design defects, cross-departmental collaboration blockages, and improper time management by approvers. Based on the root causes shown in the root cause map, determine the approval decision corresponding to the overdue document; The communication-enhanced architecture synchronizes approval decisions to the original approval system and generates counterfactual audit reports that include biometric verification.

2. The method according to claim 1, characterized in that, The step of determining the approval decision corresponding to the timed-out document based on the root causes shown in the root cause map specifically includes: When the root cause graph shows that the root cause is a flaw in the process design, a confirmation-approval sandbox pre-audit mechanism is executed; When the root cause graph shows that the root cause is due to the approver's poor time management, an automatic-approval-blockchain-documented pre-authorization decision-making mechanism is implemented; When the root cause graph shows that the root cause is blocked by cross-departmental collaboration, a conversational document confirmation and approval mechanism is implemented.

3. The method according to claim 2, characterized in that, When the root cause mapping reveals a flaw in the process design, a "confirmation-approval" sandbox pre-screening mechanism is implemented, specifically including: The virtual execution engine compares the contents of overdue documents with preset approval standards. If the content of the overdue document meets the preset approval criteria, a security check will be performed on the content of the overdue document. If the security check passes, approve the timed-out documents according to the preset approval specifications and update the process knowledge base simultaneously; If the security check fails, a timeout document error alarm will be sent to the client.

4. The method according to claim 2, characterized in that, When the root cause graph reveals that the root cause is due to the approver's poor time management, an automatic-approval-blockchain-based pre-authorization decision-making mechanism is implemented, specifically including: When the root cause is determined to be the approver's poor time management, approve overdue documents according to the preset approval specifications and record the approval record; The approval records are verified through a pre-set smart contract. If the verification is successful, the approval records are stored on a blockchain node and an approval summary report is sent to the client. If the verification fails, readjust the parameters of the preset hybrid causal reasoning model.

5. The method according to claim 2, characterized in that, When the root cause graph shows that the root cause is blocked by cross-departmental collaboration, a dialog-based document confirmation and approval mechanism is executed, specifically including: A multimodal document confirmation instruction is sent to the approver through the communication adaptation layer; Upon receiving a request for confirmation from the approver, approve the overdue document according to the preset approval specifications and record the approval record; Based on the preset restructuring rules, the timed-out approval process is restructured.

6. The method according to claim 1, characterized in that, The step of inputting the cognitive load index into a preset hybrid causal inference model to generate a root cause map of approval timeout specifically includes: The cross-departmental collaboration delay matrix of the cognitive load index is analyzed using dynamic Bayesian networks to determine the matrix analysis results; The temporal pattern of the cognitive load index was analyzed using an LSTM-Transformer model to determine the temporal analysis results. The matrix analysis results are fused with the time series analysis results to determine the root cause probability distribution and generate a root cause map. The root cause with the highest probability value in the root cause probability distribution is displayed in the graph.

7. The method according to claim 1, characterized in that, The step of quantifying the approver's behavioral data using a dynamic weighting algorithm to determine the approver's cognitive load index specifically includes: Based on the matching degree between the approver's real-time behavior flow and historical approval efficiency, the operating system behavior data, calendar status, and historical approval records are quantified to obtain the weight ratio of the operating system behavior data, calendar status, and historical approval records; the higher the matching degree between the real-time behavior flow and historical approval efficiency, the higher the corresponding weight ratio. Based on the weighting percentages, the approver's cognitive load index is determined using a preset cognitive load index formula.

8. The method according to claim 7, characterized in that, The method of quantifying operating system behavior data, calendar status, and historical approval records based on the matching degree between the approver's real-time behavior flow and historical approval efficiency specifically includes: Quantify calendar status data through calendar event correlation and GPS location analysis; Quantify historical approval records using approval system operation logs and HR-related data; The system behavior data is quantified by preset event urgency and preset event sensitivity.

9. An approval timeout processing device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform an approval timeout processing method as described in any one of claims 1-8.

10. An approval timeout processing storage medium, storing computer-executable instructions, characterized in that, The computer-executable instructions are capable of executing an approval timeout processing method as described in any one of claims 1-8.

Images