A cross-role collaborative difference alignment method, device, equipment and medium

Abstract

The application discloses a cross-role cooperative difference alignment method, device, equipment and medium, and the method comprises the following steps: obtaining role state data of each role based on role agents of multiple roles; comparing the role state data to identify a target role having a cooperative difference with other related roles; pushing verified benchmark cooperative information to a target role agent corresponding to the target role according to the cooperative difference; and guiding the target role to align the difference through the target role agent based on the benchmark cooperative information. The method realizes real-time collection of role state data of each role through the role agent, can accurately capture cognitive bias and information gaps of multiple roles in task execution, and performs directional intervention in combination with benchmark cooperative information verified dynamically, so that the target role can adjust behavior and decision-making according to a unified standard in a complex cooperation scene, and dynamic balance and efficiency optimization of a cross-role cooperative state are realized.

Description

Technical Field

[0001] This invention relates to the fields of enterprise management and artificial intelligence technology, and in particular to a method, apparatus, device and medium for cross-role collaborative difference alignment. Background Technology

[0002] In existing corporate management practices, there are a variety of collaboration differences among different employees and even different departments, which mainly include: cognitive differences (different understandings of the same matter), information differences (different versions or completeness of the information they possess), execution differences (specific operations deviate from planned goals), and the resulting competitive differences (internal friction caused by conflicts of goals or resources).

[0003] Currently, existing collaborative office software mainly provides basic functions such as information storage, instant messaging, and task management. However, these tools are inherently passive, relying on employees to actively query and manually update information. They struggle to identify and eliminate the aforementioned collaboration discrepancies in real time, especially in multi-employee collaborative environments, where the inconsistency between perception and information becomes particularly prominent, leading to decreased collaboration efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for cross-role collaborative difference alignment to address the problem of inconsistent cognition and information in a multi-employee collaborative environment, which leads to a decrease in collaboration efficiency.

[0005] A cross-role collaborative difference alignment method includes the following steps: acquiring role state data for each of the multiple roles based on role agents; comparing the state data of each role to identify collaborative differences between the target role requiring difference alignment and other related roles; pushing verified benchmark collaborative information to the target role agent corresponding to the target role based on the collaborative differences; and guiding the target role to perform difference alignment through the target role agent based on the benchmark collaborative information.

[0006] A cross-role collaborative difference alignment device includes: a state acquisition module for acquiring role state data of each of the multiple roles based on role agents; a difference identification module for comparing the state data of each role and identifying collaborative differences between the target role requiring difference alignment and other related roles; a benchmark push module for pushing verified benchmark collaborative information to the target role agent corresponding to the target role based on the collaborative differences; and a difference alignment module for guiding the target role to perform difference alignment through the target role agent based on the benchmark collaborative information.

[0007] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the aforementioned cross-role collaborative difference alignment method.

[0008] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned cross-role collaborative difference alignment method.

[0009] The aforementioned cross-role collaborative difference alignment method, apparatus, device, and medium, the collaborative difference alignment method, includes the following steps: acquiring role state data for each role based on role agents of multiple roles; comparing the state data of each role to identify target roles with collaborative differences that exist with other related roles; pushing verified benchmark collaborative information to the target role agent corresponding to the target role based on the collaborative differences; and guiding the target role to perform difference alignment based on the benchmark collaborative information through the target role agent. This method achieves real-time acquisition of role state data for each role through role agents, accurately capturing cognitive biases and information gaps among multiple roles during task execution. Combined with dynamically verified benchmark collaborative information, it provides targeted intervention, ensuring that target roles adjust their behavior and decisions according to unified standards in complex collaborative scenarios, thereby achieving dynamic balance and efficiency optimization of cross-role collaborative states. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of a cross-role collaborative difference alignment method in one embodiment of the present invention; Figure 2 This is a specific flowchart of step S1 in the cross-role collaborative difference alignment method in one embodiment of the present invention; Figure 3 This is a specific flowchart of step S2 in the cross-role collaborative difference alignment method in one embodiment of the present invention; Figure 4 This is another specific flowchart of step S2 in the cross-role collaborative difference alignment method in one embodiment of the present invention; Figure 5 This is a specific flowchart of step S4 in the cross-role collaborative difference alignment method in one embodiment of the present invention; Figure 6This is a schematic diagram of a cross-role collaborative difference alignment device in one embodiment of the present invention; Figure 7 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] In one embodiment, such as Figure 1 As shown, a cross-role collaborative difference alignment method is provided, including the following steps: Step S1: Based on the role-based intelligent agent with multiple roles, obtain the role status data of each role.

[0014] It should be noted that the role-based intelligent agent is an intelligent module deployed on each role's terminal, capable of collecting and uploading role status data in real time, including behavior, permissions, task progress, and interaction logs during the collaboration process. This role status data is aggregated to a central coordination platform via an encrypted transmission channel for monitoring and coordination of the status of all roles.

[0015] like Figure 2 As shown, specifically, step S1 includes the following sub-steps: Step S11: Configure a role agent for each role to monitor role status data in real time.

[0016] In this embodiment, for cross-employee collaboration scenarios within an enterprise, one employee corresponds to one role. Each employee (e.g., employee A, employee B) is configured with a dedicated role agent. Each role agent is deployed on the terminal device of each employee and accesses various existing office tool systems within the enterprise (such as document management systems, instant messaging tools, conferencing systems, target management systems, etc.) through application programming interfaces to achieve data interaction between the role agent and various systems within the enterprise.

[0017] In this system, data interaction between the role-based intelligent agent and various internal systems of the enterprise is authenticated and encrypted through a secure authentication mechanism. Different interface technologies, such as Webhooks and message middleware, can be used depending on the actual environment.

[0018] Step S12: Collect the corresponding role status data in real time through each role's intelligent agent, and store the collected role status data in the corresponding role status database.

[0019] In this embodiment, each role-based intelligent agent monitors employees' operational behaviors, task execution progress, and permission changes across various office systems in real time, collecting multi-dimensional role status data. This data is then stored in a time-series format in the corresponding role status database, ensuring data integrity and traceability. During the data collection process, the role-based intelligent agents use preset data filtering rules to remove invalid or redundant information, retaining only key behavioral characteristics closely related to the collaborative process. This reduces data transmission load and improves subsequent analysis efficiency. Furthermore, all role status data is encrypted and stored while generating a unique data fingerprint for subsequent difference comparison and consistency verification, ensuring data trustworthiness and system robustness during cross-role collaboration.

[0020] It should be noted that the role status database includes at least the following: a personal knowledge base, a task list, expense records, a mapping relationship between business objects and key performance indicators (KPIs), and a contract list. The personal knowledge base stores the professional knowledge, project experience, and commonly used templates accumulated by the role in daily work; the task list records currently pending, ongoing, and completed tasks and is updated synchronously with the target management system; the expense records are linked to the financial system to reflect the real-time expenditure of projects involved in the role; the mapping relationship between business objects and KPIs quantifies the consistency between the role's work results and organizational goals; and the contract list maintains all electronic contracts in which the role participates or is responsible, along with their performance status. This role status database achieves high availability and elastic scalability through a distributed storage architecture, supporting real-time data synchronization and access across departments and regions.

[0021] Furthermore, the role status data in the role status database is periodically synchronized to the central coordination platform via an encrypted channel. The central coordination platform is a central processing and coordination hub that maintains communication with all role agents, continuously receives or actively polls the role status data of each role agent, thereby enabling the central coordination platform to obtain the role status data of each role for global monitoring and analysis, ensuring the security and integrity of data transmission.

[0022] In this embodiment, by configuring a dedicated, continuously running role agent for each employee, this role agent can automatically integrate and synchronize employee work context information from multiple enterprise office systems, forming a dynamic and personalized role state database, and reflecting the employee's behavioral trajectory and state changes in the organizational collaboration network in real time. Simultaneously, a central coordination platform is set up as the global collaboration hub, proactively and continuously comparing and analyzing role state data across all role agents, thereby achieving global awareness of distributed work states.

[0023] Step S2: Compare the status data of each role to identify the collaborative differences between the target role that needs to be aligned and other related roles.

[0024] It should be noted that after receiving role status data from the role status databases, the central coordination platform immediately activates a difference detection algorithm. Based on preset coordination rules, it performs a status comparison analysis of the role status data between different roles, identifies coordination differences between the target role requiring difference alignment and other related roles, and classifies and labels the types of coordination differences. If no coordination differences are found, the central coordination platform maintains a listening state and continues to receive updated role status data.

[0025] In this embodiment, each role's status database is a structured database that supports embedding data in multiple formats such as JSON and XML. The corresponding role status data is structured status data. By comparing the field-level differences of the structured status data with the timestamp sequence, the specific types of collaborative differences between the target role and other related roles can be identified.

[0026] like Figure 3 As shown, specifically, step S2 includes the following sub-steps: Step S211: Compare the structured state data corresponding to multiple roles and identify the structured state data that is inconsistent with other structured state data as the target state data.

[0027] In this embodiment, for multiple roles with related business connections, the structured state data corresponding to the multiple roles are compared at the field level to identify whether there are inconsistencies in key fields. If there are inconsistencies in key fields, the structured state data that is inconsistent with other structured state data is determined to be the target state data, and the associated role is marked as the target role that needs to be aligned.

[0028] Furthermore, by combining timestamp sequence analysis, the timing of discrepancies and data update logic are determined, eliminating false discrepancies caused by temporary synchronization delays. Through correlation analysis of the timestamp sequences, the order and dependencies of data updates are identified, ensuring that discrepancy determination is based on eventual consistency. For long-term tasks spanning multiple business cycles, a version snapshot mechanism is introduced to compare role status snapshots at different time points, accurately pinpointing the stage and scope of impact of collaborative discrepancies. Simultaneously, dynamic threshold warnings are set for highly sensitive fields; when field value differences exceed preset business tolerances, a multi-role negotiation process is automatically triggered. After discrepancy identification, a structured report containing the discrepancy type, involved roles, conflicting fields, and suggested resolution paths is generated and pushed to the collaborative decision-making module of the central coordination platform, providing data support for subsequent intelligent mediation and strategy generation.

[0029] Step S212: Based on the target state data, determine the collaborative differences between the corresponding target role and other related roles.

[0030] In this embodiment, the collaboration differences include cognitive differences and information differences between different roles. Cognitive differences manifest as inconsistent understanding of the same task objective, such as disagreements on delivery standards or execution priorities. Information differences arise from visibility biases caused by asynchronous data updates or permission isolation.

[0031] Specifically, based on the cognitive content deviations reflected in the target state data, cognitive differences between the target role and other related roles are identified. To identify these cognitive differences, the definition text of the same indicator for the target role and other roles is extracted, and the matching degree is calculated using string similarity matching (such as the Jaccard coefficient). If the matching degree is less than a preset threshold (such as 60%), it is determined that there are cognitive differences between the target role and other related roles.

[0032] In this embodiment, when discrepancies are detected between the definitions or current numerical states of a key "business object-metric" in the roles of employee A and employee B within the same project team, a cognitive difference is determined to exist. For example, if the target state data is the definition of "requirement completion" in the knowledge base, employee A defines this metric as "document delivery completion is considered as meeting the standard," while employee B believes it is "completion is only considered complete after review." The matching degree of the two definitions calculated using the Jaccard coefficient is only 48%, which is below the 60% threshold. Therefore, a cognitive difference is determined to exist between employee A and employee B.

[0033] Furthermore, based on the missing or inconsistent information reflected in the target status data, information discrepancies between the target role and other related roles are identified. The identification of these discrepancies involves checking the existence and consistency of the field values ​​corresponding to the data version numbers. If one side has a newer version while the other side has a missing / older version, then an information discrepancy is determined to exist between the target role and other related roles.

[0034] In this embodiment, when it is detected that a newly signed contract has been recorded in the knowledge base of employee A's role agent, while the contract list of employee B's role agent still contains the old version or is missing, it is determined that there is an information discrepancy. For example, if employee A holds a V2.0 contract, while employee B still holds a V1.0 contract, it is determined that there is an information discrepancy between employee B and employee A.

[0035] The difference detection algorithm of the central coordination platform can also be replaced with a time-series anomaly detection model or a graph neural network model based on deep learning, depending on specific needs. For example, when using a graph neural network model, the knowledge base state of each role is used as a node, and the collaborative interaction relationship is used as an edge. By embedding learning to capture the state propagation pattern, abnormal subgraph structures that deviate from the normal collaboration path can be identified, thereby locating cognitive or informational differences. This model has stronger generalization ability when processing high-dimensional heterogeneous data and can effectively identify implicit differences caused by communication gaps or information delays between roles.

[0036] In some embodiments, collaboration discrepancies also include execution discrepancies between different roles. Execution discrepancies can be identified by comparing the completion rate of task progress with the task content and associating task dependencies (e.g., requirements review → feature development). If a preceding task is not completed but a subsequent task has started, or if the completion deviation exceeds a preset threshold (e.g., ±20%), it is determined to be an execution discrepancy. For example, if employee A's requirements review is not complete (80%), but employee B has started feature development (50%), it is determined that there is an execution discrepancy between employee B and employee A.

[0037] In some embodiments, the role state data also includes unstructured state data. For example... Figure 4 As shown, step S2 also includes: Step S221: Perform similarity analysis on the unstructured state data corresponding to multiple related roles to obtain the data similarity between each unstructured state data.

[0038] Specifically, for multiple roles with related business connections, pairwise similarity calculations are performed on the unstructured state data of multiple roles to obtain multiple data similarities between each unstructured state data.

[0039] Step S222: Make a consistency judgment based on the similarity of each data to identify the cognitive differences between the target character and other related characters.

[0040] In this process, consistency is determined based on the data similarity among unstructured state data. Target unstructured state data with a data similarity lower than the average similarity of all unstructured state data is identified and associated with the corresponding target role. It is then determined that there is a cognitive difference between this target role and the other related roles. For example, the semantic similarity of project reports submitted by each role is calculated using a text embedding model. If the similarity between employee A's report and those of employees B and C is 0.45 and 0.48 respectively, while the group average similarity is 0.72, then employee A's cognitive expression is determined to significantly deviate from the team consensus, indicating a cognitive difference.

[0041] In this application, the dimensions of difference identification are not limited to rule-driven structured data comparison. Advanced artificial intelligence technologies such as large language models can also be introduced to perform semantic similarity analysis and consistency judgment on unstructured text content (such as document summaries, meeting minutes, and chat logs) in the role-based intelligent agent knowledge base, in order to discover more implicit and deeper semantic cognitive biases. The above method can dynamically capture information gaps caused by misunderstandings during collaboration, and by combining structured data comparison with unstructured content analysis, achieve multi-dimensional collaborative difference identification.

[0042] Step S3: Based on the collaborative differences, push the verified benchmark collaborative information to the target role's corresponding intelligent agent.

[0043] It should be noted that benchmark collaboration information serves as the basis for aligning collaboration discrepancies. Its sources include high-completeness collaboration records from historical projects, standardized process templates confirmed by expert review, and best practice documents that have been validated multiple times in the organization's knowledge base.

[0044] In this embodiment, after identifying a collaboration difference, the central coordination platform will proactively initiate an alignment operation, pushing verified benchmark collaboration information (such as unified indicator definitions and the latest contract documents) to the target role agent corresponding to the target role with collaboration differences, thereby triggering a difference warning and alignment mechanism.

[0045] For the verification of benchmark collaborative information, a multi-source verification mechanism can be adopted to ensure its accuracy and authority. The central coordination platform will compare the structured state data (such as knowledge base, contract list, and task progress) of multiple role agents. If a certain information version is consistent across most role agents, it is determined to be benchmark collaborative information. For example, if 80% of the role agents in the project team store the "requirement completion rate" as "number of requirement documents delivered / total number of requirements × 100%", then this definition is verified as the correct benchmark, i.e., this definition is benchmark collaborative information; if the contract version of most role agents is V2.0, then V2.0 is determined to be the latest version, i.e., the contract corresponding to the latest version is benchmark collaborative information.

[0046] Furthermore, benchmark collaboration information can be verified using timestamps and version numbers. For information with version attributes (such as contracts and documents), the information with the latest timestamp or the highest version number is directly selected as the benchmark collaboration information. For dynamic information without version identifiers (such as task progress), the last updated valid dynamic information is selected as the benchmark collaboration information by combining the update time and operation logs. Authoritative information sources (such as the enterprise central knowledge base, standard process documents, and officially released indicator definitions) can also be preset, and information from these sources can be directly used as benchmark collaboration information. Unified business indicator definitions (such as the official explanation of "requirement completion rate") come from enterprise standard documents and are automatically verified as benchmark collaboration information. The latest policy documents and contract templates come from official pushes from the enterprise's legal / administrative departments and can be used as benchmark collaboration information without additional verification. In addition, pre-execution information (such as task progress) is verified as baseline collaborative information through preset process rules. If the task dependency relationship is "requirements review → function development", the information "start development when requirements review is not completed" will be judged as incorrect. If the task completion rate exceeds the preset threshold (such as "requirements review completion rate > 100%)", the information will be marked as invalid and needs to be re-verified. Otherwise, state data that conforms to the process rules and is agreed upon by most role agents, such as "requirements review completion rate is 95%, start function development", is considered as valid baseline collaborative information.

[0047] In this embodiment, the information verified by the above mechanism will be marked as benchmark collaboration information and pushed by the central coordination platform to the target role agent whose role status data is lagging or incorrect, thereby guiding employees to complete the difference alignment and ensuring that the target role agent is synchronized to the latest benchmark.

[0048] Step S4: Based on the benchmark collaborative information, guide the target role to perform difference alignment through the target role agent.

[0049] It should be noted that after receiving the baseline coordination information, the target role intelligent agent sends a prompt to the corresponding target role through the human-computer interaction interface (such as chatbot pop-ups, system notifications, etc.) to guide the target role to confirm or correct, so as to achieve difference alignment and eliminate coordination differences with other roles.

[0050] like Figure 5 As shown, specifically, step S4 includes the following sub-steps: Step S41: Generate a difference alignment strategy based on benchmark collaborative information.

[0051] It should be noted that the difference alignment strategy is automatically generated by the central coordination platform based on the type of difference between the baseline collaborative information and the current status of the target role, including information update strategy, task adjustment strategy, and process correction strategy.

[0052] In this embodiment, the strategy generation process considers role permissions and context to ensure executability. The information update strategy is suitable for scenarios with lagging data; the central coordination platform automatically pushes baseline collaboration information and prompts the target role to confirm synchronization, ensuring they have the latest version. The task adjustment strategy addresses task execution deviations by replanning subsequent actions based on the correct status in the baseline collaboration information and guiding the target role to adjust their work content through an intelligent assistant. The process correction strategy corrects operations that violate preset rules; for example, if a task is initiated before preconditions are met, the abnormal operation will be frozen, and a prompt will appear to correct it according to the standard process.

[0053] For example, when a product manager fails to synchronize the latest requirement version, an information update strategy is automatically generated, reminding them to check via a pop-up window on the workbench and instant messages. If a development task starts prematurely due to unmet preconditions, a process correction strategy is generated, pausing the relevant task and guiding it back to the correct process node, thereby achieving efficient and accurate collaborative alignment. When the test environment configuration is inconsistent with the baseline deployment plan, a task adjustment strategy is generated, dynamically releasing redundant resources and reconstructing environment parameters to ensure alignment with the standard configuration.

[0054] The aforementioned strategies are generated in real time by the central coordination platform and can be further precisely delivered to the target role through natural language prompts, updates to to-do items, or process node locking via the target role intelligent agent.

[0055] Step S42: Generate guidance instructions based on the difference alignment strategy, and output the guidance instructions to the target role through the target role agent.

[0056] In this embodiment, guidance instructions are presented in the form of natural language combined with operation suggestions, and are pushed to the user interface in real time through the target role's intelligent agent. For example, a message may be sent to developers: "The current requirement review completion rate is 95%, meeting the conditions for starting development. Please confirm the task priority adjustment"; or a message may be sent to testers: "The test environment parameters have been updated. Please re-fetch the standard configuration." The content of the instructions is personalized according to the role's responsibilities, ensuring that the operation is clear and executable. For collaboration deviations on the critical path, the response level is automatically upgraded, triggering multi-channel notifications and recording the processing progress to ensure that differences are aligned in the shortest possible time, continuously maintaining the consistency and efficiency of cross-role collaboration.

[0057] Furthermore, for information updates requiring manual confirmation, mandatory reading time limits and feedback loop mechanisms are set to prevent information omissions. For task adjustments, the intelligent agent recommends the optimal execution window based on the schedule and dynamically links upstream and downstream collaborative nodes. Process corrections trigger tiered warnings, determining whether to suspend relevant operational permissions based on the severity of the violation until compliance calibration is completed, thereby ensuring the overall consistency and efficiency of the collaborative network.

[0058] Step S43: Guide the target character to complete the difference alignment according to the guidance instructions, and update the target character's target character status data.

[0059] In this embodiment, after receiving the guidance command, the target role confirms or performs corresponding operations through a human-computer interaction interface, completing actions such as information retrieval, task adjustment, or process revert. The target role's intelligent agent captures operation feedback in real time and updates the target role's status data.

[0060] Specifically, for information inconsistencies, an information update strategy is implemented, pushing benchmark collaborative information and prompting the target role to confirm receipt via guidance instructions. For task deviations, a task adjustment strategy is implemented, adjusting task priorities or reallocating resources to match the benchmark collaborative information via guidance instructions. For process violations, a process correction strategy is implemented, triggering a correction process and notifying relevant responsible parties. After all operations are executed, the target role's intelligent agent captures new target role status data in real time and stores it in the corresponding target role status database, ensuring that the status can be further traced and dynamically optimized.

[0061] Furthermore, after step S4, the process includes: returning to the role-based intelligent agent with multiple roles, obtaining the role state data of each role, re-executing the step of comparing the state data of each role, and verifying the difference alignment effect of the target role. That is, returning to step S1, re-obtaining the role state data of each role, comparing the state based on the updated target role state data, verifying the difference alignment effect of the target role, and continuously monitoring the dynamic changes in the collaborative state of each role. If the original collaborative differences still exist or new collaborative differences are triggered, the strategy generation, instruction guidance, and difference alignment operations are repeatedly executed until the baseline collaborative information is completely matched.

[0062] If, after alignment, the target role's status data still shows discrepancies with the status data of other relevant roles, the verification and push process for baseline collaboration information is re-triggered, iterating until the collaboration status reaches consistency. If, after alignment, the target role's status data is consistent with the status data of other relevant roles, the discrepancy alignment is considered successful, the collaboration process enters a stable execution phase, the central coordination platform synchronously updates the global collaboration status map, and records the entire process log of this discrepancy alignment for subsequent auditing and optimization analysis. This completes a full process of collaboration discrepancy identification, response, and closed-loop optimization.

[0063] In this embodiment, the method assigns each employee a dedicated role-based intelligent agent to represent their work status, and a central coordination platform monitors and coordinates the status of all role-based intelligent agents. The central coordination platform continuously integrates the status data of each role, performs multi-dimensional status comparisons, accurately identifies collaboration deviations, and generates executable guidance instructions based on role responsibilities to drive the target role to correct the discrepancies. By implementing this method, enterprises can achieve real-time, automatic alignment of employee cognition and information, significantly reducing efficiency losses and execution errors caused by poor communication and misunderstandings. The collaborative system composed of role-based intelligent agents and the central coordination platform operates with a high degree of automation, requiring no additional effort from employees for manual synchronization. It is particularly suitable for large-scale, fast-paced collaborative work environments, effectively improving the overall collaborative efficiency of the organization.

[0064] It should be noted that, in addition to centralized difference detection and alignment by a central coordination platform, a distributed point-to-point negotiation mechanism can also be used. For example, direct communication channels can be established between agents within the same project team to negotiate and synchronize certain role status data, thereby reducing the load on the central coordination platform.

[0065] Furthermore, the above methods are not only applicable to internal enterprise collaboration, but can also be extended to collaborative scenarios between enterprises and external partners, supply chain nodes, and even cross-industry ecosystems. Through a unified digital identity and state synchronization mechanism, efficient alignment of multiple roles in complex business processes can be achieved. For example, configuring corresponding "external intelligent agents" for customers or suppliers can automatically align information and cognition across organizational boundaries, thereby improving the collaborative efficiency of the supply chain or ecosystem.

[0066] In summary, this method achieves real-time difference identification and automated alignment in cross-role collaboration through dynamic perception, intelligent decision-making, and a closed-loop feedback mechanism. The closed-loop feedback mechanism repeatedly verifies the alignment effect, ensuring that the collaborative state dynamically converges to the baseline target. The entire process achieves global collaboration consistency and stability through continuous iteration, ultimately forming a traceable and optimizable intelligent collaboration closed-loop system, ensuring that cross-role collaboration is always in dynamic equilibrium. This method can automatically and in real-time detect and correct cognitive, informational, execution, and competitive differences among employees within an enterprise, thereby achieving automatic alignment of information and cognition across employees and improving overall enterprise collaboration efficiency and execution accuracy.

[0067] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0068] In one embodiment, a cross-role collaborative difference alignment device is provided, which corresponds one-to-one with the cross-role collaborative difference alignment method in the above embodiments. For example... Figure 6 As shown, the cross-role collaborative difference alignment device includes a status acquisition module 101, a difference recognition module 102, a baseline push module 103, and a difference alignment module 104. Detailed descriptions of each functional module are as follows: The status acquisition module 101 is used to acquire the status data of each role based on a role-based intelligent agent with multiple roles.

[0069] The difference recognition module 102 is used to compare the status data of each role and identify the collaborative differences between the target role that needs to be aligned and other related roles.

[0070] The benchmark push module 103 is used to push verified benchmark collaboration information to the target role intelligent agent corresponding to the target role based on the collaboration differences.

[0071] The difference alignment module 104 is used to guide the target role to perform difference alignment based on the benchmark collaborative information through the target role agent.

[0072] Specific limitations regarding the cross-role collaborative difference alignment device can be found in the limitations of the cross-role collaborative difference alignment method described above, and will not be repeated here. Each module in the aforementioned cross-role collaborative difference alignment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the operations corresponding to each module.

[0073] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a cross-role collaborative difference alignment method.

[0074] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the cross-role collaborative difference alignment method described in the above embodiments, for example... Figure 1 S1-S4, as shown, will not be repeated here to avoid repetition. Alternatively, the processor, when executing a computer program, implements the functions of each module / unit in this embodiment of a cross-role collaborative difference alignment device, for example... Figure 6 The functions of the status acquisition module 101, difference recognition module 102, benchmark push module 103, and difference alignment module 104 shown are not described again here to avoid repetition.

[0075] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program implements the cross-role collaborative difference alignment method described in the above embodiments, for example... Figure 1 S1-S4, as shown, will not be repeated here to avoid repetition. Alternatively, when the computer program is executed by the processor, it implements the functions of each module / unit in this embodiment of the cross-role collaborative difference alignment device, for example... Figure 6 The functions of the status acquisition module 101, difference recognition module 102, benchmark push module 103, and difference alignment module 104 shown are not described again here to avoid repetition. The computer-readable storage medium can be non-volatile or volatile.

[0076] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0078] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A cross-role collaborative difference alignment method, characterized in that, Including the following steps: Based on a role-based intelligent agent with multiple roles, obtain the role state data of each of the aforementioned roles; The state data of each role are compared to identify the collaborative differences between the target role that needs to be aligned with the other related roles. Based on the aforementioned collaborative differences, the verified benchmark collaborative information is pushed to the target role agent corresponding to the target role; Based on the benchmark collaboration information, the target role is guided by the target role agent to perform difference alignment.

2. The collaborative difference alignment method as described in claim 1, characterized in that, The role state data includes structured state data. The step of comparing the state data of each role to identify the target role requiring difference alignment and identifying collaborative differences between it and other related roles includes: By comparing the structured state data corresponding to multiple related roles, the structured state data that is inconsistent with the other structured state data is identified as the target state data; Based on the target state data, it is determined that there is a collaborative difference between the corresponding target role and other related roles.

3. The collaborative difference alignment method as described in claim 2, characterized in that, The collaborative differences include cognitive differences between different roles. Determining, based on the target state data, that there are collaborative differences between the corresponding target role and other related roles includes: Based on the cognitive content bias reflected in the target state data, the cognitive differences between the target role and other related roles are identified.

4. The collaborative difference alignment method as described in claim 2, characterized in that, The coordination differences include information differences between different roles. Determining the existence of these coordination differences between the corresponding target role and other related roles based on the target state data includes: Based on the missing or inconsistent information reflected in the target state data, the information differences between the target role and other related roles are identified.

5. The collaborative difference alignment method as described in claim 1, characterized in that, The role state data includes unstructured state data. The step of comparing the state data of each role to identify the target role requiring difference alignment and the collaborative differences between it and other related roles includes: A similarity analysis is performed on the unstructured state data corresponding to the multiple related roles to obtain the data similarity between the unstructured state data. Consistency judgment is made based on the similarity of the data to identify the cognitive differences between the target character and other related characters.

6. The collaborative difference alignment method as described in claim 1, characterized in that, The step of guiding the target role to perform difference alignment through the target role agent based on the benchmark collaborative information includes: A difference alignment strategy is generated based on the aforementioned benchmark collaborative information; A guidance instruction is generated based on the difference alignment strategy, and the guidance instruction is output to the target role through the target role agent. According to the guidance instructions, the target character is guided to complete the difference alignment and the target character's target character status data is updated.

7. The collaborative difference alignment method as described in claim 1, characterized in that, The role-based intelligent agent, which is based on multiple roles, acquires the role state data of each of the aforementioned roles, including: Configure each of the aforementioned roles with a role agent for real-time monitoring of the role's status data; Each of the aforementioned role-specific intelligent agents collects the corresponding role status data in real time and stores the collected role status data in the corresponding role status database.

8. A cross-role collaborative difference alignment device, characterized in that, include: The status acquisition module is used to acquire the role status data of each of the multiple roles in the role-based intelligent agent. The difference recognition module is used to compare the state data of each of the roles and identify the collaborative differences between the target role that needs to be aligned with the other related roles. The benchmark push module is used to push verified benchmark collaboration information to the target role intelligent agent corresponding to the target role based on the collaboration differences. The difference alignment module is used to guide the target role to perform difference alignment based on the benchmark collaboration information through the target role agent.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the cross-role collaborative difference alignment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the cross-role collaborative difference alignment method as described in any one of claims 1 to 7.

Images