20 results about "Assignment methods" patented technology

The embodiment of the invention provides an annotation task allocation method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a plurality of annotation tasks to be distributed; determining task portraits of the plurality of to-be-distributed annotation tasks according to the plurality of to-be-distributed annotation tasks; obtaining capability portraits of a plurality of annotation personnel and capability portraits of a plurality of data annotation models, wherein the data annotation models are used for data annotation; according to the task portrait, the ability portraits of the plurality of annotation personnel and the ability portraits of the plurality of data annotation models, constructing an optimization model used for determining an allocation relationship among the to-be-allocated annotation task, the annotation personnel and the data annotation models; and solving the optimization model by using a solving algorithm to generate a target task allocation scheme.

The invention discloses a task assignment method for a multi-role employment mode, and relates to the technical field of intelligent scheduling, and the method comprises the following steps: building a responsibility chain topological structure, extracting cross-role responsibility elements according to a task target, task input, task output, a task preposition constraint and a task postposition constraint, generating a responsibility vector, and carrying out the task assignment of the multi-role employment mode. And a verifiable responsibility map is constructed. According to the method, a verifiable task responsibility chain is constructed, and responsibility visualization, contract verifiability, semantic alignment and time sequence closed loop of the whole task disassembly and handover process are realized through responsibility graph modeling and contract fingerprint binding; the method combines consistency verification and shadow path calculation, dynamically identifies and repairs the risk of chain breakage, improves the scheduling stability and the task execution credibility, and solves the problem that the breakage of the chain of responsibility is difficult to identify and repairs in the prior art.

The embodiment of the invention provides an automatic order sending method of a platform and related equipment, and belongs to the technical field of computers. The method comprises the following steps: acquiring work order information needing to be dispatched; inputting the work order information into a large language model based on cue word engineering to obtain a first-level prediction result; if the first-level prediction result contains a preset value, starting an auxiliary model, and inputting the work order information and the first-level prediction result into the auxiliary model to obtain a second-level prediction result; and fusing the first-level prediction result and the second-level prediction result to obtain an order sending result. According to the invention, order sending prediction is carried out through the large language model and the auxiliary model, so that the accuracy of order sending prediction is improved.

The embodiment of the invention relates to the technical field of information, in particular to a basic-level event intelligent dispatching method and system based on a business portrait. The method comprises the following steps: according to current and historical work data of a grassroots department, obtaining a capability graph and a current load of the grassroots department, and establishing a department portrait; reading grid data, obtaining grid basic information and historical event probability distribution, and establishing a grid portrait; obtaining event basic information, event description and historical information according to the event work order, and constructing an event portrait; according to the event portrait, the department portrait, the grid portrait and a preset distribution strategy, obtaining a distribution result; and obtaining execution feedback of the dispatching result, and optimizing the distribution strategy according to the execution feedback.

Methods and systems for entity assignment to assign an entity of a plurality of entities to a lead resource of at least two lead resources may include receiving a score for each entity of the plurality of entities. The method may further include determining a ranking of the plurality of entities based upon the score for each entity and receiving a distance between each entity of the plurality of entities and each lead resource of the at least two lead resources, wherein the plurality of entities are greater in number than the at least two lead resources. The method may also include applying an optimization algorithm based on the ranking and the distance between each entity and each lead resource and updating the optimization algorithm in real-time until each entity of the plurality of entities is paired to one of the at least two lead resources.

The invention relates to a task allocation method based on a dynamic rotation priority mechanism, and belongs to the technical field of crowdsourcing task allocation. The method comprises the following steps: defining a task set, a volunteer set, a round counter, an allocated task number, a task assignment state, a volunteer task preference sequence and a maximum acceptable task number; screening and randomly sorting the volunteer set according to the allocated task number and the maximum acceptable task number to obtain a task allocation sequence; based on the task allocation sequence and the task set, obtaining the most preferred task in the current unallocated volunteer task preference sequence; and according to whether other volunteers select the most preferred task to perform distribution of the current round of tasks, updating the task assignment state of the current round of tasks, and simultaneously performing next round of task distribution until all task distribution is completed or no distributable volunteers exist, ending the task distribution. The objective of the invention is to solve the technical problems of poor preference consistency and low satisfaction of volunteers in the prior art.

The invention relates to the technical field of artificial intelligence and human resource management, and discloses an agent-based task allocation method, device and equipment and a storage medium, a post agent reflecting the dependency relationship of each post in an organization is constructed, tasks can be comprehensively allocated from the dependency relationship of each post when the post agent allocates the tasks, and the task allocation efficiency is improved. Therefore, the task cannot be executed due to the conflict after the task is allocated, and the matching degree between the task and the post is improved.

This invention provides a method, apparatus, device, and readable storage medium for sorting assigned services. The method includes: acquiring service location information within a preset time period; establishing a service scatter map based on the service location information; generating a first sub-path on the service scatter map based on preset start and end points; changing the start and end points, and generating a second sub-path on the service scatter map based on the changed start and end points; acquiring fault tolerance information of the second sub-path, and generating an optimal sub-path on the service scatter map based on the fault tolerance information. This solves the problem of low assignment efficiency caused by existing service assignment methods that do not consider the global context.

The invention relates to the technical field of engineering order assignment, and discloses an engineering order dynamic assignment method and system based on voice semantic multi-dimensional analysis, and the method comprises the steps: receiving task condition change information fed back by field personnel, combining preset knowledge contents, and precisely determining the technical capability and material demands needed by a task. On this basis, the system can generate a plurality of subsequent resource allocation schemes, and innovatively regards the investment generated by the first dispatch as the generated cost, so that the sinking cost is fully considered in the subsequent decision, and the resource waste is avoided.

The invention relates to a seat dispatching method based on task nesting and a related device. The invention discloses a seat dispatching method based on task nesting. The method comprises the following steps: acquiring seat information; task nesting information is obtained, the task nesting information comprises a plurality of tasks which can be executed by the same seat in the same round of dispatching, and the task nesting information comprises a plurality of tasks which can be executed by the same seat in the same round of dispatching; the task nesting information indicates a plurality of task nesting as a subsequent task nesting for starting the virtual task nesting and as a preceding task nesting for ending the virtual task nesting, and indicates a preceding and / or subsequent task nesting set of each task nesting in the plurality of task nesting; the multiple task nesting sets comprise a work starting task nesting set and a work stopping task nesting set; constructing a first integer programming model by setting constraints and a target function; and solving the first integer programming model by using the acquired information to determine a task nested sequence of which the seats are allocated, and determining a dispatching scheme based on the task nested sequence.

The present invention relates to a layer assignment method that simultaneously considers the optimization of slew and the number of vias. The layer assignment method proposes the following four effective strategies: 1) net adjustment strategy; 2) rewiring order adjustment and via optimization strategy; 3) late optimization adjustment strategy; 4) dynamic programming objective parameter optimization strategy. The method of the present invention can reduce the number of vias and the number of net slew violations in the final routing scheme, thereby obtaining a high-quality layer assignment result.

The invention discloses an intelligent drive page parameter automatic assignment method based on a code-free platform, relates to an intelligent drive metadata modeling automatic generation method and system, and aims to automatically process page parameter assignment through a large model, reduce manual intervention, improve efficiency and reduce the use threshold of non-technical personnel. According to the technical scheme, the method comprises the steps that 1, a user selects a parameter assignment tool in a visual interface of a code-free platform; 2, the user places the tool at a specified process node; and 3, selecting parameters needing to be assigned, wherein the parameters can be parameters obtained from the current level or the superior process. 4, an AI assignment button is clicked, the context content is automatically analyzed by the system, and corresponding parameter values are generated. And 5, automatically filling the parameter values into a specified value box. According to the method, the problems that the efficiency of manual parameter assignment in a code-free platform is low, a certain technical threshold exists during use, and low-level errors caused by human factors are likely to occur are solved.

The challenge is to optimize the allocation of workers to specific tasks. [Solution] The information processing device includes an estimation unit that estimates the future elapsed time and processing speed of a target worker by inputting the target worker's past elapsed time and processing speed into an estimation model trained on the elapsed time since the worker started work and the processing speed that indicates the amount of work per unit time, and an assignment unit that assigns the target worker to the target work based on the elapsed time and processing speed of the target worker estimated by the estimation unit and the total amount of work for the target work.

The invention discloses an intelligent dispute dispatching method and system based on a cosine similarity algorithm, and relates to the technical field of event classification. In order to solve the problems of low manual dispute case dispatching efficiency and insufficient matching precision in the prior art, the scheme adopted by the invention comprises the following steps: establishing a case feature acquisition form containing a specified structured field; after filling and submitting the case feature acquisition form by a checker, automatically extracting field information reflecting case core features in the form, and converting the field information into vector representation; constructing a department capability evaluation model, and designing an exclusive quantification rule for five preset core dimensions by the model to generate a department capability vector; calculating the similarity between the case feature vector and the department capability vector based on a cosine similarity algorithm, and matching three optimal processing departments for the case according to a calculation result; and carrying out load detection on the three matched processing departments and automatically assigning a new case to an optimal matching department.

The invention provides a task allocation method and device, a storage medium and equipment. The task allocation method comprises the steps of obtaining task information of a first task and a second task and capability information of multiple agents; determining at least one allocation combination of the first task and the second task in the plurality of agents based on the task information of the first task and the second task and the capability information of the plurality of agents; determining the distribution combination with the highest execution efficiency from the at least one distribution combination as a target distribution combination; and the first task and the second task are allocated according to the target allocation combination, so that overall planning of multi-task allocation is realized, and the overall execution efficiency of multiple tasks can be improved.

The invention relates to a seat dispatching method based on task nesting and a related device. The seat dispatching method based on task nesting comprises the following steps: acquiring seat information; task nesting information, conflict information between task nesting, work starting task nesting information and work stopping task nesting information are obtained, and the task nesting information comprises a plurality of tasks which can be executed by the same seat in the same round of dispatching; constructing a first integer programming model through the following operations: setting a first constraint which requires that each seat cannot execute task nesting which conflicts with each other, setting a second constraint which requires that each seat execute work starting task nesting, and setting a third constraint which requires that each seat execute work stopping task nesting; setting a target function based on a target for optimizing the task coverage rate; and solving the first integer programming model by using the acquired information to determine a corresponding relationship between the seat and the task nesting, and determining a dispatching scheme based on the corresponding relationship.

The present disclosure relates to the technical field of warehousing, and provides an order assignment method and apparatus. One specific implementation of the method comprises: receiving an order comprising at least one commodity to be picked; for each workstation in at least one workstation, determining a warehouse exit circulating box of the workstation in warehouse exit carrying; according to articles in the warehouse exit circulating box, detecting whether a first article matched with the order is present; in response to the detection that the first article matched with the order is present, detecting whether the first article is all commodities to be picked in the order; and in response to the detection that the first article is all the commodities to be picked in the order, binding the order with the warehouse exit circulating box corresponding to the first article, and assigning the order to the workstation. The implementation improves the order assignment efficiency.

Methods and systems for entity assignment to assign an entity of a plurality of entities to a lead resource of at least two lead resources may include receiving a score for each entity of the plurality of entities. The method may further include determining a ranking of the plurality of entities based upon the score for each entity and receiving a distance between each entity of the plurality of entities and each lead resource of the at least two lead resources, wherein the plurality of entities are greater in number than the at least two lead resources. The method may also include applying an optimization algorithm based on the ranking and the distance between each entity and each lead resource and updating the optimization algorithm in real-time until each entity of the plurality of entities is paired to one of the at least two lead resources.

In an assignment device (10), an acquisition unit (15a) acquires a task questionnaire answer (14a) for a questionnaire regarding the similarity of the content of each task to be processed by an employee, and a preference questionnaire answer (14b) for a questionnaire regarding the employee's preferences for the tasks. A generation unit (15b) uses the acquired task questionnaire answer (14a) for the questionnaire regarding the similarity of the content of each task to generate a task map representing similarity between the tasks. A synthesis unit (15c) uses the acquired preference questionnaire answer (14b) for the questionnaire regarding the employee's preferences for the tasks to synthesize, on the task map, a preference vector representing the preference tendency of each employee. An assignment unit (15e) assigns, to each employee, the tasks of the task map in order of proximity between the tasks and the preference vector.