Scheduling information generation method and device and storage medium

Abstract

The invention discloses a scheduling information generation method and device and a storage medium. Relates to the field of artificial intelligence, and the method comprises the steps: obtaining the business information of a target business in a first time range, inputting the business information into a business volume prediction model, and outputting demand prediction information according to the business volume prediction model; skill matching information corresponding to the target business is acquired according to a skill matching knowledge graph, the skill matching knowledge graph is used for representing an association relationship between the employee skill information and a preset business, and the preset business comprises the target business; and determining an input parameter according to the demand prediction information and the skill matching information, and generating target scheduling information corresponding to the input parameter by using a linear constraint optimization algorithm. Through the method and the device, the problem of relatively low generation efficiency of the scheduling information in related technologies is solved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method, apparatus, and storage medium for generating scheduling information. Background Technology

[0002] Scheduling information assigns tasks to corresponding employees to process them efficiently and promptly, thereby improving user experience.

[0003] However, in existing technologies, the generation of shift information is usually based on human experience or pre-set simple rules (such as fixed shift order). Such static generation methods lack sensitivity to real-time data and the ability to respond to emergencies. When business is at its peak or when there are temporary changes in employees, it may take several hours or even longer to adjust the generation of shift information, which may affect the operational efficiency and service quality of the outlets.

[0004] There is currently no effective solution to the problem of low efficiency in generating scheduling information in related technologies. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, and storage medium for generating shift information, so as to solve the problem of low efficiency in generating shift information in related technologies.

[0006] To achieve the above objectives, according to one aspect of this application, a method for generating shift scheduling information is provided. The method includes: acquiring business information of a target business within a first time frame, inputting the business information into a business volume prediction model, and outputting demand prediction information based on the business volume prediction model, wherein the demand prediction information represents the predicted value of the business volume of the target business within a second time frame, which is later than the first time frame; acquiring skill matching information corresponding to the target business based on a skill matching knowledge graph, wherein the skill matching knowledge graph represents the association between employee skill information and preset businesses, and the preset businesses include the target business; determining input parameters based on the demand prediction information and the skill matching information, and generating target shift scheduling information corresponding to the input parameters using a linear constraint optimization algorithm.

[0007] Furthermore, the training steps of the traffic volume prediction model include: obtaining historical traffic processing data of the target network to which the target traffic belongs; extracting time features, environmental features, and traffic volume sequences based on the historical traffic processing data; and training the bidirectional long short-term memory neural network model using the time features, environmental features, and traffic volume sequences to obtain the traffic volume prediction model.

[0008] Furthermore, the process of determining input parameters based on demand forecasting information and skill matching information, and generating target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, includes: determining business rule information based on the project rule base of the target business, and using demand forecasting information, skill matching information, and business rule information as input parameters; using a linear constraint optimization algorithm to model according to preset constraints and input parameters to obtain a scheduling constraint model; and using a constraint programming solver to solve the scheduling constraint model to obtain the target scheduling information.

[0009] Furthermore, after generating the target scheduling information corresponding to the input parameters using the linear constraint optimization algorithm, the method also includes: obtaining the solution state of the constraint programming solver; if the solution state is not converged, using an adaptive large neighborhood search algorithm to optimize the target scheduling information to obtain the optimized target scheduling information; and outputting a scheduling Gantt chart based on the optimized target scheduling information.

[0010] Furthermore, after generating the target scheduling information corresponding to the input parameters using the linear constraint optimization algorithm, the method also includes: monitoring the data changes of the target business during the execution of the target scheduling information to obtain business change information, wherein the business change information includes employee change data and business volume change data; updating the target scheduling information based on the business change information and the skill matching knowledge graph to obtain the updated target scheduling information.

[0011] Furthermore, the target scheduling information is updated based on business change information and a skills matching knowledge graph. The updated target scheduling information includes: determining the working hours of multiple employees in the target scheduling information based on business change information, and determining the information of employees waiting to rest and the corresponding tasks to be matched based on the working hours of multiple employees. The information of employees waiting to rest is the information of employees whose working hours do not meet the preset rules; determining the information of substitute employees corresponding to the information of employees waiting to rest based on the skills matching knowledge graph, and merging the shifts of multiple sub-tasks in the target scheduling information based on the tasks to be matched to obtain the target scheduling information after shift merging; and determining the updated target scheduling information based on the substitute employee information and the target scheduling information after shift merging.

[0012] To achieve the above objectives, according to another aspect of this application, a scheduling information generation apparatus is provided. The apparatus includes: a demand forecasting unit, configured to acquire business information of a target business within a first time range, input the business information into a business volume forecasting model, and output demand forecasting information based on the business volume forecasting model, wherein the demand forecasting information represents the predicted business volume of the target business within a second time range, the second time range being later than the first time range; an information matching unit, configured to acquire skill matching information corresponding to the target business based on a skill matching knowledge graph, wherein the skill matching knowledge graph represents the association between employee skill information and preset businesses, the preset businesses including the target business; and a scheduling generation unit, configured to determine input parameters based on the demand forecasting information and the skill matching information, and generate target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm.

[0013] Furthermore, the device also includes: a historical data acquisition unit for acquiring historical business processing data of the target network to which the target business belongs; a feature extraction unit for extracting time features, environmental features, and business volume sequences based on the historical business processing data; and a model training unit for training a bidirectional long short-term memory neural network model using time features, environmental features, and business volume sequences to obtain a business volume prediction model.

[0014] Furthermore, the scheduling generation unit includes: a parameter determination module, used to determine business rule information based on the project rule base of the target business, and to determine demand forecast information, skill matching information and business rule information as input parameters; a constraint optimization module, used to model according to preset constraint conditions and input parameters using a linear constraint optimization algorithm to obtain a scheduling constraint model; and a model solving module, used to solve the scheduling constraint model using a constraint programming solver to obtain the target scheduling information.

[0015] Furthermore, the device also includes: a state acquisition unit, used to acquire the solution state of the constraint programming solver after generating target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm; an information optimization unit, used to optimize the target scheduling information using an adaptive large neighborhood search algorithm when the solution state is not converged, to obtain the optimized target scheduling information; and a Gantt chart output unit, used to output a scheduling Gantt chart from the optimized target scheduling information.

[0016] Furthermore, the device also includes: a change monitoring unit, used to monitor data changes in the target business during the execution of the target business schedule after generating the target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, and obtain business change information, wherein the business change information includes employee change data and business volume change data; and an information update unit, used to update the target scheduling information based on the business change information and the skill matching knowledge graph, and obtain the updated target scheduling information.

[0017] Furthermore, the information update unit includes: a first determination module, used to determine the working hours of multiple employees in the target shift schedule information based on business change information, and to determine the information of employees waiting to rest and the corresponding matching tasks based on the working hours of multiple employees, wherein the information of employees waiting to rest is the information of employees whose working hours do not conform to preset rules; a second determination module, used to determine the information of substitute employees corresponding to the information of employees waiting to rest based on a skill matching knowledge graph, and to merge the shifts of multiple sub-tasks in the target shift schedule information based on the matching tasks to obtain the target shift schedule information after shift merging; a third determination module, used to determine the updated target shift schedule information based on the substitute employee information and the target shift schedule information after shift merging.

[0018] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute any method for generating scheduling information.

[0019] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for performing any kind of scheduling information generation.

[0020] According to another aspect of this application, a computer program product is provided, including computer instructions, which, when executed by a processor, implement the steps of the method for generating scheduling information as described above.

[0021] In this embodiment, business information of the target business within a first time range is obtained and input into a business volume prediction model. The model then outputs demand prediction information, where the demand prediction information represents the predicted business volume of the target business within a second time range, which is later than the first time range. Skill matching information corresponding to the target business is obtained based on a skill matching knowledge graph, which represents the association between employee skill information and preset businesses, including the target business. Input parameters are determined based on the demand prediction information and skill matching information, and a linear constraint optimization algorithm is used to generate target scheduling information corresponding to the input parameters. This solves the technical problem of low generation efficiency of scheduling information in the prior art. Attached Figure Description

[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0023] Figure 1 A hardware block diagram of a computer terminal for implementing a method for generating scheduling information is shown.

[0024] Figure 2 This is a flowchart of a method for generating scheduling information according to an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of a scheduling information generation device provided according to an embodiment of this application;

[0026] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0030] Example 1

[0031] According to an embodiment of this application, a method embodiment for generating scheduling information is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a method for generating scheduling information is shown. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the scheduling information generation method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned scheduling information generation method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0036] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0037] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for generating the shift schedule information is shown. Figure 2 This is a flowchart of a method for generating scheduling information according to Embodiment 1 of this application.

[0038] Step S201: Obtain business information of the target business within the first time range, input the business information into the business volume prediction model, and output demand prediction information based on the business volume prediction model. The demand prediction information is used to represent the predicted value of the business volume of the target business within the second time range, which is later than the first time range.

[0039] Optionally, the target business can be a specific business of the target financial institution for which scheduling information is to be generated, such as customer consultation. The target business may include multiple different sub-businesses (e.g., sub-business a, sub-business b, and sub-business c). The first time frame can be the month preceding the current time. For example, business information for the previous month can be retrieved from the target financial institution's transaction system on Sunday evening (e.g., business volume information such as the number of customer consultations for different sub-businesses, average waiting time, and holiday information). The second time frame can be the next three days after the current time. The business information within the first time frame can be input into the business volume forecasting model to obtain the predicted value of the business volume within the second time frame (i.e., demand forecasting information). For example, the demand forecasting information can be the business volume of sub-business a, sub-business b, and sub-business c.

[0040] Step S202: Obtain skill matching information corresponding to the target business based on the skill matching knowledge graph. The skill matching knowledge graph is used to represent the relationship between employee skill information and preset business, and the preset business includes the target business.

[0041] Optionally, the skill matching knowledge graph stores multiple preset business nodes, employee ID nodes, and skill certificate nodes. The employee ID node also includes attributes such as skill proficiency and shift preference (e.g., a preference for processing business during a specific time period). Nodes are also entities, and different entities are connected by relational "edges." The same entity stores attributes. For example, preset business node X – Requirement – ​​Skill Certificate k, employee ID node 007 – Holding – Skill Certificate k. The relationship between "requirement" and "holding" can be a hard constraint. Preset businesses can include target businesses or sub-businesses within target businesses. Skill proficiency can be a dynamically updated value; for example, it can be updated at preset intervals (e.g., every week) based on certificate validity, certificate acquisition time, employee training scores, etc. The skill matching information corresponding to the target business can be all triples (i.e., relationships between entities and relationships between entities and attributes) associated with the target business and its sub-businesses in the skill matching knowledge graph.

[0042] Step S203: Determine the input parameters based on demand forecasting information and skill matching information, and use a linear constraint optimization algorithm to generate target scheduling information corresponding to the input parameters.

[0043] Optionally, demand forecasting information and skill matching information can be used as input parameters for a linear constraint optimization algorithm. The objective function of the linear constraint optimization algorithm can be set as minimum waiting time and minimum total working time. The linear constraint optimization algorithm can be a constraint programming algorithm (also known as a constraint optimization algorithm). By solving the problem using the linear constraint optimization algorithm, the target scheduling information can be obtained. For example, the target scheduling information shows that four employees will be scheduled to work between 14:00 and 16:00 on Monday, two of whom hold a certain certificate; each employee's working hours will not exceed 8 hours; and the scheduling information follows the employees' shift preferences as much as possible.

[0044] In summary, by outputting demand forecast information based on the business volume forecasting model and obtaining skill matching information corresponding to the target business using a skill matching knowledge graph, a data foundation for generating scheduling information is laid. Then, the target scheduling information corresponding to the input parameters is generated through a linear constraint optimization algorithm, shortening the generation cycle of scheduling information from several hours to a few minutes and improving the efficiency of scheduling information generation.

[0045] To improve the efficiency of generating scheduling information, the training steps of the business volume prediction model may optionally include: obtaining historical business processing data of the target network to which the target business belongs; extracting time features, environmental features, and business volume sequences based on the historical business processing data; and training the bidirectional long short-term memory neural network model using the time features, environmental features, and business volume sequences to obtain the business volume prediction model.

[0046] Optionally, historical business processing data of the target branch can be obtained from the target financial institution's transaction system. This historical data may include the number of customers served, processing time, number of employees, and environmental data (e.g., weather information) and time data (e.g., holiday information). By extracting features from the historical business processing data, time features corresponding to the time data, environmental features corresponding to the environmental data, and a business volume sequence sorted by time can be obtained. Furthermore, business processing features corresponding to the business volume sequence (i.e., the number of customers served, processing time, and number of employees) can be extracted. A bidirectional long-short-term neural network model for time series forecasting can be selected as the baseline model for training. For example, the business volume x, non-holiday status, sunny weather, number of customers served y, processing time z, and number of employees h on January 12th can be used as predictive factors to predict the daily business volume for the three days from February 13th to February 15th.

[0047] In summary, by collecting historical business processing data and training a bidirectional long short-term memory neural network model, a business volume prediction model was obtained, which improved the efficiency of generating scheduling information.

[0048] To improve the efficiency of generating scheduling information, optionally, the input parameters are determined based on demand forecasting information and skill matching information, and the target scheduling information corresponding to the input parameters is generated using a linear constraint optimization algorithm. This includes: determining business rule information based on the project rule base of the target business, and determining demand forecasting information, skill matching information, and business rule information as input parameters; using a linear constraint optimization algorithm to model according to preset constraints and input parameters to obtain a scheduling constraint model; and using a constraint programming solver to solve the scheduling constraint model to obtain the target scheduling information.

[0049] Optionally, the project rule base of the target business can be obtained, and business rule information can be extracted. For example, each employee's working hours should not exceed 8 hours per day, and at least two employees holding a certain certificate are required to be on duty. Demand forecast information, skill matching information, and business rule information are determined as input parameters. The business rule information is transformed into hard constraints of the model, and the objective function of the linear constraint optimization algorithm is set as minimum waiting time and minimum total working time. The constraint programming solver (i.e., CP-SAT solver, a solver based on a depth-first search strategy) is used for iteration to obtain the target scheduling information, which can be a detailed schedule.

[0050] In summary, by determining business rule information based on the project rule base of the target business, demand forecasting information, skill matching information, and business rule information are determined as input parameters; a linear constraint optimization algorithm is used to model the scheduling constraint model based on preset constraints and input parameters; and a constraint programming solver is used to solve the scheduling constraint model to obtain the target scheduling information, thereby improving the efficiency of scheduling information generation.

[0051] To improve the accuracy of the generated scheduling information, the method may optionally include, after generating the target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, obtaining the solution state of the constraint programming solver; if the solution state is not converged, using an adaptive large neighborhood search algorithm to optimize the target scheduling information to obtain the optimized target scheduling information; and outputting a scheduling Gantt chart based on the optimized target scheduling information.

[0052] Optionally, the solution status of the constraint programming solver can be obtained. If the solution status is non-converged, it indicates that there is room for further improvement in the target scheduling information. This embodiment introduces an adaptive large neighborhood search algorithm to optimize the target scheduling information from the dimension of nonlinear optimization. The adaptive large neighborhood search algorithm can disrupt a part of the arrangement in the target scheduling information. For example, it can randomly select some employees' shifts and change them to simulate changes in employee status. Then, it can find a better replacement scheme by searching the neighborhood control to repair the disrupted target scheduling information. After repair, the overall performance of the scheme (e.g., service response time) is evaluated. If the new scheme is better than the original scheme, the optimized scheduling scheme is received as the optimized target scheduling information, and a scheduling Gantt chart is generated based on the optimized target scheduling information to achieve visualization of the scheduling information.

[0053] In summary, by using an adaptive large neighborhood search algorithm to optimize the target scheduling information, a dual-engine optimization mechanism based on linear constraint optimization algorithm and adaptive large neighborhood search algorithm was implemented, thereby improving the accuracy of scheduling information generation.

[0054] To improve the efficiency of generating scheduling information, optionally, after generating the target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, the method further includes: monitoring the data changes of the target business during the execution of the target scheduling information to obtain business change information, wherein the business change information includes employee change data and business volume change data; updating the target scheduling information based on the business change information and the skill matching knowledge graph to obtain the updated target scheduling information.

[0055] Optionally, after the target scheduling information is executed, data changes can be monitored in real time. For example, business change data refers to a sudden increase in business volume, and employee change data can be employee leave or some employees adding new skill certificates. The target scheduling information can be re-optimized using business change information and skill matching knowledge graph to obtain updated target scheduling information.

[0056] In summary, by updating the target scheduling information based on business change information and skill matching knowledge graph, the updated target scheduling information is obtained. This achieves a second-level response to data changes, thereby quickly adjusting the scheduling information and improving the efficiency of scheduling information generation in a dynamically changing environment.

[0057] To improve the efficiency of generating scheduling information, optionally, the target scheduling information can be updated based on business change information and a skill matching knowledge graph. The updated target scheduling information includes: determining the working hours of multiple employees in the target scheduling information based on business change information, and determining the information of employees waiting to rest and the corresponding tasks to be matched based on the working hours of multiple employees. The information of employees waiting to rest refers to the information of employees whose working hours do not meet the preset rules; determining the information of substitute employees corresponding to the information of employees waiting to rest based on the skill matching knowledge graph, and merging the shifts of multiple sub-tasks in the target scheduling information based on the tasks to be matched to obtain the target scheduling information after shift merging; and determining the updated target scheduling information based on the substitute employee information and the target scheduling information after shift merging.

[0058] For example, if the processing requirements of the target business change, resulting in the need to add multiple sub-tasks to the target scheduling information, employees who meet the skill requirements of the aforementioned sub-businesses can be identified based on the target scheduling information. The working hours for adding the sub-tasks to the employees' work schedules are calculated, and employee IDs exceeding the preset working hours are identified as employees awaiting rest. Businesses exceeding the preset working hours are then segmented from the sub-tasks to obtain tasks to be matched. Preset rules can be rules read from the Rrools rule engine (an open-source rule engine). These preset rules specify preset working hours and may also include qualification verification rules for matching employees with business requirements. By querying the skill matching knowledge graph, alternative employee information for handling the tasks to be matched is obtained (i.e., alternative matching). The sub-tasks in the target scheduling information are then merged into shifts to generate an updated target scheduling information.

[0059] In summary, by using a skill matching knowledge graph for substitute matching and shift merging, the target shift information is updated quickly, improving the efficiency of shift information generation.

[0060] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0061] Example 2

[0062] This application also provides a scheduling information generation apparatus. It should be noted that the scheduling information generation apparatus of this application can be used to execute the scheduling information generation method provided in this application. The scheduling information generation apparatus provided in this application will be described below.

[0063] According to embodiments of this application, an apparatus for implementing the above-described method for generating scheduling information is also provided, such as... Figure 3 As shown, the device includes:

[0064] The demand forecasting unit 301 is used to acquire business information of the target business within a first time range, input the business information into the business volume forecasting model, and output demand forecasting information based on the business volume forecasting model. The demand forecasting information is used to represent the predicted value of the business volume of the target business within a second time range, which is later than the first time range.

[0065] The information matching unit 302 is used to obtain skill matching information corresponding to the target business based on the skill matching knowledge graph, wherein the skill matching knowledge graph is used to represent the association between employee skill information and preset business, and the preset business includes the target business.

[0066] The scheduling generation unit 303 is used to determine input parameters based on the demand forecast information and the skill matching information, and to generate target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm.

[0067] The scheduling information generation device provided in this application embodiment obtains business information of the target business within a first time range through a demand prediction unit 301, inputs the business information into a business volume prediction model, and outputs demand prediction information based on the business volume prediction model. The demand prediction information represents the predicted business volume of the target business within a second time range, which is later than the first time range. An information matching unit 302 obtains skill matching information corresponding to the target business based on a skill matching knowledge graph, which represents the association between employee skill information and preset businesses, including the target business. A scheduling generation unit 303 determines input parameters based on the demand prediction information and the skill matching information, and generates target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm. This solves the problem of low generation efficiency of scheduling information in related technologies, thereby improving the generation efficiency of scheduling information.

[0068] Optionally, in the scheduling information generation device provided in the embodiments of this application, the device further includes: a historical data acquisition unit, used to acquire historical business processing data of the target network to which the target business belongs; a feature extraction unit, used to extract time features, environmental features and business volume sequences based on the historical business processing data; and a model training unit, used to train a bidirectional long short-term memory neural network model using time features, environmental features and business volume sequences to obtain a business volume prediction model.

[0069] Optionally, in the scheduling information generation device provided in this application embodiment, the scheduling generation unit 303 includes: a parameter determination module, used to determine business rule information based on the project rule library of the target business, and determine demand forecast information, skill matching information and business rule information as input parameters; a constraint optimization module, used to use a linear constraint optimization algorithm to model according to preset constraint conditions and input parameters to obtain a scheduling constraint model; and a model solving module, used to use a constraint programming solver to solve the scheduling constraint model to obtain the target scheduling information.

[0070] Optionally, in the scheduling information generation device provided in the embodiments of this application, the device further includes: a state acquisition unit, used to acquire the solution state of the constraint programming solver after generating target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm; an information optimization unit, used to optimize the target scheduling information using an adaptive large neighborhood search algorithm when the solution state is not converged, to obtain the optimized target scheduling information; and a Gantt chart output unit, used to output a scheduling Gantt chart of the optimized target scheduling information.

[0071] Optionally, in the scheduling information generation device provided in this application embodiment, the device further includes: a change monitoring unit, used to monitor the data changes of the target business during the execution of the target scheduling information after generating the target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, and obtain business change information, wherein the business change information includes employee change data and business volume change data; and an information updating unit, used to update the target scheduling information based on the business change information and the skill matching knowledge graph, and obtain the updated target scheduling information.

[0072] Optionally, in the scheduling information generation device provided in this application embodiment, the information updating unit includes: a first determining module, used to determine the working hours of multiple employees in the target scheduling information based on business change information, and to determine the information of employees to be rested and the matching tasks corresponding to the information of employees to be rested based on the working hours of multiple employees, wherein the information of employees to be rested is the information of employees whose working hours do not conform to preset rules; a second determining module, used to determine the information of substitute employees corresponding to the information of employees to be rested based on a skill matching knowledge graph, and to merge the shifts of multiple sub-tasks in the target scheduling information based on the matching tasks to obtain the target scheduling information after the shifts are merged; a third determining module, used to determine the updated target scheduling information based on the information of substitute employees and the target scheduling information after the shifts are merged.

[0073] It should be noted that the aforementioned demand prediction unit 301, information matching unit 302, and scheduling generation unit 303 correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the units and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the aforementioned modules or units may be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The aforementioned modules may also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.

[0074] Example 3

[0075] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) Processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0076] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0077] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: acquiring business information of the target business within a first time frame, inputting the business information into a business volume prediction model, and outputting demand prediction information based on the business volume prediction model. The demand prediction information represents the predicted business volume of the target business within a second time frame, which is later than the first time frame. Acquiring skill matching information corresponding to the target business based on a skill matching knowledge graph, where the skill matching knowledge graph represents the association between employee skill information and preset businesses, including the target business. Determining input parameters based on the demand prediction information and skill matching information, and generating target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm.

[0078] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the historical business processing data of the target network to which the target business belongs; extract time features, environmental features and business volume sequences based on the historical business processing data; train the bidirectional long short-term memory neural network model using the time features, environmental features and business volume sequences to obtain the business volume prediction model.

[0079] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the business rule information based on the project rule base of the target business, and determine the demand forecast information, skill matching information and business rule information as input parameters; use the linear constraint optimization algorithm to model according to the preset constraint conditions and input parameters to obtain the scheduling constraint model; use the constraint programming solver to solve the scheduling constraint model to obtain the target scheduling information.

[0080] The processor can also call the information and application program stored in the memory through the transmission device to perform the following steps: obtain the solution status of the constraint programming solver; if the solution status is not converged, use the adaptive large neighborhood search algorithm to optimize the target scheduling information to obtain the optimized target scheduling information; output the scheduling Gantt chart based on the optimized target scheduling information.

[0081] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: during the execution of the target scheduling information, monitor the data changes of the target business to obtain business change information, including employee change data and business volume change data; update the target scheduling information based on the business change information and the skill matching knowledge graph to obtain the updated target scheduling information.

[0082] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the working hours of multiple employees in the target shift schedule information based on the business change information, and determine the information of employees waiting to rest and the matching tasks corresponding to the employees waiting to rest based on the working hours of multiple employees, wherein the information of employees waiting to rest is the information of employees whose working hours do not meet the preset rules; determine the information of substitute employees corresponding to the information of employees waiting to rest based on the skill matching knowledge graph, and merge the shifts of multiple sub-tasks in the target shift schedule information based on the matching tasks to obtain the target shift schedule information after the shifts are merged; determine the updated target shift schedule information based on the substitute employee information and the target shift schedule information after the shifts are merged.

[0083] This application provides a scheme for generating shift scheduling information. It obtains business information of the target business within a first time frame and inputs this information into a business volume prediction model. The model then outputs demand prediction information, where the demand prediction information represents the predicted business volume of the target business within a second time frame, which is later than the first time frame. Skill matching information corresponding to the target business is obtained based on a skill matching knowledge graph, which represents the association between employee skill information and preset businesses, including the target business. Input parameters are determined based on the demand prediction information and skill matching information, and a linear constraint optimization algorithm is used to generate target shift scheduling information corresponding to the input parameters. This solves the technical problem of low efficiency in generating shift scheduling information in existing technologies.

[0084] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0085] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0086] Example 4

[0087] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the scheduling information generation method provided in Embodiment 1.

[0088] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0089] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining business information of the target business within a first time range, inputting the business information into a business volume prediction model, and outputting demand prediction information based on the business volume prediction model, wherein the demand prediction information is used to represent the predicted value of the business volume of the target business within a second time range, the second time range being later than the first time range; obtaining skill matching information corresponding to the target business based on a skill matching knowledge graph, wherein the skill matching knowledge graph is used to represent the association between employee skill information and preset businesses, the preset businesses including the target business; determining input parameters based on the demand prediction information and skill matching information, and generating target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm.

[0090] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: obtaining historical business processing data of the target network to which the target business belongs; extracting time features, environmental features, and business volume sequences based on the historical business processing data; and training a bidirectional long short-term memory neural network model using the time features, environmental features, and business volume sequences to obtain a business volume prediction model.

[0091] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: determining business rule information based on the project rule base of the target business, and determining demand forecast information, skill matching information and business rule information as input parameters; using a linear constraint optimization algorithm to model according to preset constraints and input parameters to obtain a scheduling constraint model; and using a constraint programming solver to solve the scheduling constraint model to obtain target scheduling information.

[0092] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: obtaining the solution state of the constraint programming solver; if the solution state is not converged, optimizing the target scheduling information using an adaptive large neighborhood search algorithm to obtain optimized target scheduling information; and outputting a scheduling Gantt chart based on the optimized target scheduling information.

[0093] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: during the execution of the target scheduling information, monitoring the data changes of the target business to obtain business change information, wherein the business change information includes employee change data and business volume change data; updating the target scheduling information based on the business change information and the skill matching knowledge graph to obtain the updated target scheduling information.

[0094] Optionally, in this embodiment, the computer-readable storage medium is further configured to store program code for performing the following steps: determining the working hours of multiple employees in the target shift schedule information based on business change information, and determining the information of employees to be rested and the matching tasks corresponding to the information of employees to be rested based on the working hours of multiple employees, wherein the information of employees to be rested is the information of employees whose working hours do not conform to preset rules; determining the information of substitute employees corresponding to the information of employees to be rested based on the skill matching knowledge graph, and merging the shifts of multiple sub-tasks in the target shift schedule information based on the matching tasks to obtain the target shift schedule information after shift merging; determining the updated target shift schedule information based on the substitute employee information and the target shift schedule information after shift merging.

[0095] This application also provides a computer program product, which, when executed on a data processing device, is suitable for performing the steps of a method for generating scheduling information.

[0096] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0097] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0102] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for generating shift scheduling information, characterized in that, include: Obtain business information of the target business within a first time range, input the business information into a business volume prediction model, and output demand prediction information based on the business volume prediction model. The demand prediction information is used to represent the predicted value of the business volume of the target business within a second time range, which is later than the first time range. Skill matching information corresponding to the target business is obtained based on a skill matching knowledge graph, wherein the skill matching knowledge graph is used to represent the association between employee skill information and preset business, and the preset business includes the target business; Input parameters are determined based on the demand forecast information and the skill matching information, and target scheduling information corresponding to the input parameters is generated using a linear constraint optimization algorithm.

2. The method according to claim 1, characterized in that, The training steps for the business volume prediction model include: Obtain the historical business processing data of the target network to which the target business belongs; Based on the historical business processing data, extract time features, environmental features, and business volume sequences; The bidirectional long short-term memory neural network model is trained using the time features, the environmental features, and the traffic volume sequence to obtain the traffic volume prediction model.

3. The method according to claim 1, characterized in that, The process of determining input parameters based on the demand forecast information and the skill matching information, and generating target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, includes: Based on the project rule base of the target business, business rule information is determined, and the demand prediction information, the skill matching information, and the business rule information are determined as the input parameters; A linear constraint optimization algorithm is used to model the scheduling constraint model based on preset constraints and the input parameters. The scheduling constraint model is solved using a constraint programming solver to obtain the target scheduling information.

4. The method according to claim 3, characterized in that, After generating the target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, the method further includes: Obtain the solution status of the constraint programming solver; When the solution state is non-converged, an adaptive large neighborhood search algorithm is used to optimize the target scheduling information to obtain the optimized target scheduling information. Output a Gantt chart of the shift schedule based on the optimized target shift information.

5. The method according to claim 1, characterized in that, After generating the target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm, the method further includes: During the execution of the target scheduling information, the data changes of the target business are monitored to obtain business change information, which includes employee change data and business volume change data. The target scheduling information is updated based on the business change information and the skill matching knowledge graph to obtain the updated target scheduling information.

6. The method according to claim 5, characterized in that, The target scheduling information is updated based on the business change information and the skill matching knowledge graph, resulting in the following updated target scheduling information: Based on the business change information, determine the working hours of multiple employees in the target shift information, and determine the information of employees waiting to rest and the matching tasks corresponding to the information of employees waiting to rest based on the working hours of the multiple employees. The information of employees waiting to rest is the information of employees whose working hours do not meet the preset rules. Based on the skill matching knowledge graph, the substitute employee information corresponding to the employee information to be rested is determined, and the shifts of multiple sub-tasks in the target shift information are merged according to the task to be matched, so as to obtain the target shift information after shift merging. The updated target schedule information is determined based on the substitute employee information and the target schedule information after the shifts are merged.

7. A device for generating scheduling information, characterized in that, include: The demand forecasting unit is used to acquire business information of the target business within a first time range, input the business information into the business volume forecasting model, and output demand forecasting information based on the business volume forecasting model. The demand forecasting information is used to represent the predicted value of the business volume of the target business within a second time range, which is later than the first time range. An information matching unit is used to obtain skill matching information corresponding to the target business based on a skill matching knowledge graph, wherein the skill matching knowledge graph is used to represent the association between employee skill information and preset businesses, and the preset businesses include the target business; The scheduling generation unit is used to determine input parameters based on the demand forecast information and the skill matching information, and to generate target scheduling information corresponding to the input parameters using a linear constraint optimization algorithm.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the method for generating scheduling information as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for generating scheduling information according to any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method for generating scheduling information according to any one of claims 1 to 6.

Images