A method and apparatus for intelligent scheduling

Abstract

The application discloses a kind of intelligent scheduling method and device, it is related to computer technical field.The specific embodiment of the method includes: after receiving scheduling request, obtain scheduling data, including scheduling personnel data and scheduling parameter data, according to the individualized demand data in scheduling parameter data and scheduling personnel data calculation scheduling result initial solution, and the initial solution is searched and optimized, obtains global optimal solution, generates intelligent scheduling result based on global optimal solution.This embodiment can realize intelligent scheduling, guarantee the accuracy of scheduling while improving scheduling efficiency.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for intelligent scheduling. Background Technology

[0002] With the rapid development of e-commerce, online business is taking up an increasingly larger proportion of companies' operations. To ensure the smooth operation of online business and enhance competitiveness, companies are placing greater emphasis on the consumer shopping experience. To improve this experience, companies often provide online customer service representatives to offer consultation services, addressing various issues throughout the pre-sales and after-sales process. However, customer service resources are limited. Therefore, effectively scheduling customer service personnel to ensure that consumer inquiries are answered efficiently at all times of the day, making full use of customer service manpower and avoiding excessive waiting times or wasted resources, while simultaneously ensuring a positive work experience for customer service staff, has become a key challenge.

[0003] Currently, the allocation of customer service staff shifts mainly relies on dedicated personnel to manually allocate shifts based on factors such as enterprise needs and customer service staff characteristics. This allocation method is inefficient and makes it difficult to consider the impact of multiple factors simultaneously. The allocation results may affect customer service efficiency and resource utilization. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and apparatus for intelligent scheduling, which can improve scheduling efficiency and increase resource utilization.

[0005] To achieve the above objectives, according to one aspect of the present invention, an intelligent scheduling method is provided, comprising:

[0006] Receive scheduling requests and obtain scheduling data based on the scheduling requests. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling parameter data includes personalized requirement data.

[0007] Based on personalized demand data and scheduling personnel data, an initial solution for the scheduling result that satisfies the preset workload fitting value condition is constructed.

[0008] Based on the initial solution, preset scheduling conditions, and preset search rules, the search optimization is performed to obtain the globally optimal solution;

[0009] Intelligent scheduling results are generated based on the global optimal solution.

[0010] Alternatively, the workload fit value is calculated as follows:

[0011] Calculate the manpower for scheduling based on the scheduling personnel data;

[0012] The predicted flow value is calculated based on historical flow data obtained from scheduling parameter data;

[0013] The workload fit value is determined based on the ratio of scheduled manpower to predicted flow value.

[0014] Optionally, based on personalized demand data and scheduling personnel data, an initial solution for the scheduling result that satisfies the preset workload fitting value conditions is constructed, including:

[0015] An initial solution for the scheduling result that satisfies the preset workload fitting value condition is constructed based on the scheduling personnel data.

[0016] The initial solution is adjusted based on personalized demand data.

[0017] Optionally, before obtaining the globally optimal solution by performing search optimization based on the initial solution, preset scheduling conditions, and preset search rules, the method further includes:

[0018] Calculate scheduling complexity based on the data of the scheduled personnel;

[0019] The parameters of the preset annealing model are determined based on the scheduling complexity;

[0020] Furthermore, based on the initial solution, preset scheduling conditions, and preset search rules, search optimization is performed to obtain the globally optimal solution, including:

[0021] Based on the initial solution, preset scheduling conditions, and preset search rules, the global optimal solution is obtained by searching and optimizing through a preset annealing model.

[0022] Optionally, based on the initial solution, preset scheduling conditions, and preset search rules, a preset annealing model is used to search and optimize to obtain the globally optimal solution, including:

[0023] Using a random exchange strategy, the neighborhood solutions of the initial solution are searched based on preset scheduling conditions and preset search rules, and the target score of the neighborhood solutions is calculated. The target score is the weighted sum of the workload score, the fairness score of the scheduler, the scheduling rule score, and the corresponding weights.

[0024] Determine whether to replace the initial solution based on the objective score of the neighborhood solution and the objective score of the initial solution;

[0025] Repeat all the above search operations until the annealing model meets the iteration termination condition and the global optimal solution is obtained.

[0026] Optionally, a neighborhood solution of the initial solution is searched based on preset scheduling conditions and preset search rules using a random exchange strategy, and the target score of the neighborhood solution is calculated, including:

[0027] During each search, select a certain number of search rules from the preset search rules;

[0028] Using a random exchange strategy, the neighborhood solutions of the initial solution are searched based on preset scheduling conditions and a first set number of search rules.

[0029] Optionally, determining whether to replace the initial solution based on the objective score of the neighborhood solution and the objective score of the initial solution includes:

[0030] If the objective score of the neighborhood solution is greater than the objective score of the initial solution, it is determined to replace the initial solution with the neighborhood solution.

[0031] In response to the condition that the target score of the domain solution is not greater than the target score of the initial solution, the difference between the target score of the domain solution and the target score of the initial solution is calculated.

[0032] The acceptance probability is calculated based on the difference, and the decision on whether to replace the initial solution with the neighborhood solution is based on the acceptance probability.

[0033] According to another aspect of the present invention, an intelligent scheduling apparatus is provided, comprising:

[0034] The acquisition module is used to receive scheduling requests and acquire scheduling data based on the scheduling requests. The scheduling data includes scheduling personnel data and scheduling parameter data, and the scheduling parameter data includes personalized requirement data.

[0035] The construction module is used to construct an initial solution for the scheduling result that meets the preset workload fitting value conditions based on personalized demand data and scheduling personnel data.

[0036] The search module is used to perform search optimization based on the initial solution, preset scheduling conditions, and preset search rules to obtain the globally optimal solution.

[0037] The generation module is used to generate intelligent scheduling results based on the global optimal solution.

[0038] According to another aspect of the present invention, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent scheduling method provided in the embodiments of the present invention.

[0039] According to another aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the intelligent scheduling method provided in the embodiments of the present invention.

[0040] According to another aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the intelligent scheduling method provided in the embodiments of the present invention.

[0041] One embodiment of the above invention has the following advantages or beneficial effects: it can abstract the scheduling problem into a mathematical combinatorial optimization problem, construct an initial solution based on the acquired personalized demand data and scheduling personnel data, and further optimize the initial solution through a search optimization method based on the acquired scheduling parameter data, preset scheduling conditions and preset search rules to obtain the global optimal solution, thereby generating intelligent scheduling results, realizing intelligent scheduling, ensuring scheduling accuracy while improving efficiency.

[0042] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0043] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0044] Figure 1 This is a schematic diagram of the main steps of the intelligent scheduling method according to an embodiment of the present invention;

[0045] Figure 2 This is a customer service representative's intended meaning;

[0046] Figure 3 This is a flowchart illustrating the annealing model;

[0047] Figure 4 This is a schematic diagram of the main modules of an intelligent scheduling device according to an embodiment of the present invention;

[0048] Figure 5 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied;

[0049] Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0050] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0051] It should be noted that the technical solutions disclosed in this invention, regarding the collection, updating, analysis, processing, use, transmission, and storage of user personal information, all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0052] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations, and require notification to users and obtaining their consent or authorization. When applicable, user personal information is subjected to de-identification and / or anonymization and / or encryption technical processing.

[0053] Currently, manual scheduling methods suffer from low efficiency and poor scheduling quality. To address this issue, this invention abstracts the scheduling problem into a multi-objective data combination optimization problem, solving which yields the final scheduling solution, thus achieving intelligent scheduling.

[0054] Figure 1 This is a schematic diagram illustrating the main steps of the intelligent scheduling method according to an embodiment of the present invention, as follows: Figure 1 As shown, it includes:

[0055] Step S101: Receive a scheduling request and obtain scheduling data based on the scheduling request. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling parameter data includes personalized demand data.

[0056] After a user activates the intelligent scheduling algorithm, a corresponding scheduling request will be received. Based on the scheduling request, the algorithm will retrieve the corresponding scheduling data from the database. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling personnel data specifically refers to the data of the customer service personnel to be scheduled, including their ID number, name, etc. The scheduling parameter data includes the personalized needs data of the customer service personnel, for example, customer service personnel A requests not to work the early shift on Mondays.

[0057] Optionally, the received scheduling request includes a business identifier, and scheduling data containing that identifier is retrieved from the database based on the business identifier.

[0058] Optionally, the scheduling parameter data may also include historical scheduling data, available shift schedule data, scheduling configuration data, and predicted traffic data. Historical scheduling data primarily includes shift data for employees over the past three weeks, and calculates and saves data such as employee rest days and working hours based on historical shift schedule data. Available shift schedules, categorized by customer service representative, include the available shifts for each customer service representative this week. Scheduling configuration data includes the scheduling date, daily start and end times, traffic data dimensions, and scheduling period. Personalized demand data consists of data submitted by employees themselves, such as specifying a particular shift on a specific day. Predicted traffic data represents the manpower demand data for each time period. Specifically, the available shifts for this week are the same for each customer service representative during a weekly scheduling process, but the schedule may vary between weeks depending on demand; the traffic data dimension refers to the inbound traffic data for customer service representatives, which differs at different times.

[0059] Step S102: Based on personalized demand data and shift personnel data, construct an initial solution for the shift scheduling result that satisfies the preset workload fitting value conditions.

[0060] After obtaining the scheduling data, an initial solution is randomly constructed based on the personalized demand data and the scheduling personnel data. This initial solution must meet the preset workload fitting value conditions.

[0061] Optionally, the constructed initial solution needs to meet the individual needs of the scheduler, or the degree to which the individual needs are met is greater than a preset threshold. When the initial solution meets all the individual needs of the scheduler, the matrix position of the individual needs needs to be recorded, i.e., the shift required by the scheduler.

[0062] Specifically, shifts are randomly assigned to each scheduled employee based on the acquired scheduling data, resulting in the scheduling data for all employees. During random assignment, allocation can be based on traffic distribution or the shift requirements of the scheduled employees. Specifically, allocating based on traffic distribution means allocating the number of customer service personnel per day according to daily traffic volume; allocating based on shift requirements means allocating based on the required working hours of each customer service representative.

[0063] Step S103: Based on the initial solution, preset scheduling conditions and preset search rules, perform search optimization to obtain the global optimal solution.

[0064] After obtaining the initial solution, further search optimization is needed by combining preset scheduling conditions and preset search rules to obtain the global optimum. During the search, a neighborhood solution of the initial solution is found and replaced by a random replacement method, and the final global optimum is obtained through continuous iterative optimization.

[0065] Optionally, when replacing a solution, it is necessary to judge the degree to which different solutions satisfy the preset scheduling conditions and the fairness constraints, and use a better solution to replace it.

[0066] Step S104: Generate intelligent scheduling results based on the global optimal solution.

[0067] After obtaining the globally optimal solution, a table of the final intelligent scheduling results is generated to display the scheduling information for users to query and preview.

[0068] like Figure 2 This is an example of a customer service shift schedule. Each column represents each day of the week, and each row represents the shift schedule of a single customer service representative. For example, a customer service representative might be scheduled for the early morning shift (A0) on Mondays from 7:00 AM to 4:00 PM, and have no shifts on Tuesdays.

[0069] The intelligent scheduling method provided by the present invention can abstract the scheduling problem into a mathematical combinatorial optimization problem. It constructs an initial solution based on the acquired personalized demand data and scheduling personnel data, and further optimizes the initial solution through a search optimization method based on the acquired scheduling parameter data, preset scheduling conditions and preset search rules to obtain the global optimal solution, thereby generating an intelligent scheduling result. This realizes intelligent scheduling, ensuring scheduling accuracy while improving efficiency.

[0070] Optionally, the workload fit value is calculated as follows: Calculate the scheduled manpower based on the scheduled personnel data; calculate the predicted flow rate based on historical flow data obtained from the scheduling parameter data; and determine the workload fit value based on the ratio of the scheduled manpower to the predicted flow rate. The workload fit value can be obtained by calculating the ratio of the scheduled manpower to the predicted flow rate. The scheduled manpower is calculated based on the number of people scheduled for each time period and the output coefficient of each person. For example, if 10 people are scheduled from 7:00 to 8:00, and each person's output coefficient is 1, then the scheduled manpower for 7:00 to 8:00 is 10. Therefore, when calculating the scheduled manpower, a solution is randomly generated. It is necessary to subsequently determine whether this solution meets the preset workload fit value conditions, and then determine whether to select this solution as the initial solution. Only if the conditions are met will it be selected as the initial solution; otherwise, a new solution is generated, and the judgment is performed again. The daily flow rate within the scheduled time period is predicted based on historical flow data. The ratio of the calculated scheduled manpower to the predicted flow rate is calculated, and this ratio is determined as the workload fit value for this solution. Fitting values ​​in the range of 0.6 to 1.7 represent those that meet the standard.

[0071] Optionally, based on personalized demand data and scheduling personnel data, an initial solution for the scheduling result that satisfies the preset workload fitting value conditions is constructed. This includes: constructing an initial solution for the scheduling result that satisfies the preset workload fitting value conditions based on the scheduling personnel data; and adjusting the initial solution based on personalized demand data. When constructing the initial solution, first, an initial solution that meets the conditions is constructed using the above method. Then, the initial solution is adjusted according to the preset personalized demand data so that the adjusted initial solution can satisfy all personalized demands.

[0072] Optionally, if all personalized needs cannot be met at the same time, then as much personalized need data as possible needs to be met, that is, to ensure that the degree of satisfaction of personalized needs is not less than a preset threshold.

[0073] Optionally, before performing search optimization based on the initial solution, preset scheduling conditions, and preset search rules to obtain the global optimal solution, the method further includes: calculating the scheduling complexity based on the scheduling personnel data; and determining the parameters of the preset annealing model based on the scheduling complexity.

[0074] Furthermore, based on the initial solution, preset scheduling conditions, and preset search rules, search optimization is performed to obtain the global optimal solution, including: based on the initial solution, preset scheduling conditions, and preset search rules, search optimization is performed through a preset annealing model to obtain the global optimal solution.

[0075] The search and optimization operation can be implemented using an annealing model. Before the search, the scheduling complexity needs to be calculated based on the personnel data, thereby determining the parameters of the annealing model. The complexity calculation is based on the number of personnel; for example, a complexity of 1 corresponds to 1 for numbers between 1 and 100. Each complexity level corresponds to a set of annealing model parameters. That is, the parameters of the annealing model can be selected based on the determined complexity. For example, a higher complexity corresponds to a larger number of iterations in the annealing model parameters. The specific values ​​can be set according to the actual situation and are not restricted. After determining the parameters of the annealing model, the search and optimization are performed based on the annealing model, the initial solution, the preset scheduling conditions, and the preset search rules.

[0076] The parameters of the annealing model include the initial temperature, cooling coefficient, maximum number of iterations, and maximum number of consecutive unpromoted iterations. Different annealing model parameters corresponding to different complexities can ensure the accuracy of the algorithm under different problem complexities.

[0077] Optionally, based on the initial solution, preset scheduling conditions, and preset search rules, a preset annealing model is used for search and optimization to obtain the global optimum. This includes: using a random exchange strategy, searching for neighborhood solutions of the initial solution based on the preset scheduling conditions and preset search rules, and calculating the target score of the neighborhood solutions. The target score is the weighted sum of workload score, scheduling fairness score, scheduling rule score, and their corresponding weights. Based on the target scores of the neighborhood solutions and the initial solution, it is determined whether to replace the initial solution. All the above search operations are repeated until the annealing model meets the iteration termination condition, thus obtaining the global optimum. During the optimization process, iterative optimization through continuous search and replacement is required. Specifically, based on the initial solution, a random exchange strategy is used to obtain neighborhood solutions. By calculating the target scores of the neighborhood solutions and the initial solution, solutions with higher scores are retained as better solutions. The final global optimum is obtained through multiple iterative optimizations.

[0078] The formula for calculating the target score (objective function) is as follows:

[0079]

[0080] x, y, and z correspond to the scheduling rule score, workload score, and fairness score for scheduling personnel, respectively. w, h, and p are the preset weights for the above scores. The scheduling rule score specifically indicates whether the preset scheduling rules are met (1 if yes, 0 if no). The workload score can be the value of the workload fit. The fairness score indicates whether the fairness constraints are met (1 if yes, 0 if no). Objective function: The customer service shift schedule is designed as a two-dimensional matrix structure M, where each row represents the daily shift data of the customer service staff within the scheduling cycle. The shifts available to each customer service staff member are also a two-dimensional matrix structure.

[0081] Optionally, the preset scheduling conditions include schedule constraints, traffic fit constraints, schedule fairness constraints, and employee demand satisfaction rate conditions, as detailed below:

[0082] 1. Class schedule rules and constraints

[0083] For each customer service representative, in order to ensure employee satisfaction with the work schedule and work experience, as well as the operational rules that different business departments need to meet due to their business characteristics, it is necessary to meet these rules as much as possible based on their different priorities. For example, for an individual customer service representative, the number of consecutive working days should not exceed 6 days, and the weekly rest time should not exceed 2 days and not be less than 1 day, etc. The operational rules of different business departments are not the same, and the total number of rules is approximately between 15 and 30. Depending on the different rules of different businesses, the constraints can be freely combined or added or removed.

[0084] 2. Flow fit constraint conditions

[0085] Based on the consultation traffic forecast data provided by the business department for the following week, and combined with the daily schedule, the manpower distribution for each time period needs to be calculated to meet the consultation traffic of each time period as much as possible. The time period can be in units of 15 minutes, 30 minutes or 60 minutes. It is generally considered that a traffic fit degree R between 0.7 and 1.6 indicates that the corresponding time period of the day has met the target. In addition, the weekly schedule is divided into multiple days and multiple time periods.

[0086] R = H 排班人力 / H 预测流量

[0087] 3. Constraints on Fairness of Class Schedule

[0088] To ensure fairness in work schedules and minimize employee complaints, it's crucial to comprehensively consider factors such as employee working hours, night shifts, long shifts, and rest days. This ensures that differences in these metrics remain within a predetermined, acceptable range over a given period.

[0089] 4. Employee needs satisfaction rate conditions

[0090] Every employee has individual needs for various reasons, such as wanting a day off, not wanting to work night shifts, or wanting consecutive days off. To improve employee experience, the rate at which these individual needs are met needs to be considered during scheduling. The formula for the employee needs satisfaction rate is the number of employees whose individual needs are met divided by the number of employees who made individual needs.

[0091]

[0092] Optionally, a random exchange strategy is used to search for neighborhood solutions of the initial solution based on preset scheduling conditions and preset search rules, and the target score of the neighborhood solutions is calculated. This includes: selecting a certain number of search rules from the preset search rules during each search; and searching for neighborhood solutions of the initial solution based on the preset scheduling conditions and a first certain number of search rules using a random exchange strategy. During the search optimization process, to address the problem of too many rules making it difficult to obtain relatively good scheduling results in a short time, a random exchange search is added to the random replacement neighborhood search, and a search strategy pool is designed. For rules that are difficult to optimize, customer service data that do not meet the corresponding constraints are continuously recorded during algorithm iteration. The data is then optimized according to the search method corresponding to the rules in the strategy pool, combining the constraint conditions and the information of the current solution. Each iteration selects 1-2 rules from the strategy pool for searching, thereby obtaining neighborhood solutions based on the current solution. Simultaneously, by recording the location of personalized needs, the corresponding position of the personalized demand schedule remains unchanged.

[0093] Optionally, determining whether to replace the initial solution based on the target score of the neighborhood solution and the target score of the initial solution includes: in response to the target score of the neighborhood solution being greater than the target score of the initial solution, determining to replace the initial solution with the neighborhood solution; in response to the target score of the neighborhood solution not being greater than the target score of the initial solution, calculating the difference between the target score of the neighborhood solution and the target score of the initial solution; calculating the acceptance probability value based on the difference, and determining whether to replace the initial solution with the neighborhood solution based on the acceptance probability value. The function value Obj of the new solution and the change in the objective function compared to the original solution, ΔObj, are calculated. If the function value of the new solution is larger, the new solution is directly accepted, i.e., the original solution is replaced by the new solution; otherwise, the acceptance probability value is calculated, and the new solution is accepted with the corresponding probability value to prevent getting trapped in local optima during the iteration process. Algorithm parameters such as temperature and iteration count are updated to gradually find the global optimum. ΔObj is the difference between the function value of the new solution and the function value of the current solution, and T is the current temperature parameter of the simulated annealing model. Finally, after reaching a sufficient number of iterations or a sufficiently low temperature, the iteration process ends, and the optimal solution, i.e., the optimal shift schedule, is obtained. The calculation formula is as follows:

[0094] ΔObj(M)=Obj(M new )-Obj(M)

[0095]

[0096] Where P is the acceptance probability.

[0097] like Figure 3 The diagram shows the flow chart of the annealing model. The search optimization unit optimizes the current solution based on the available class matrix and the search rules in the search strategy pool to obtain the neighborhood solution, and calculates the gain through the objective function to determine whether to update the current solution with the neighborhood solution.

[0098] The intelligent scheduling method provided by this invention abstracts the scheduling problem into a mathematical combinatorial optimization problem, obtaining the scheduling result through a solution process. Specifically, an initial solution is constructed based on acquired personalized demand data and scheduling personnel data. Furthermore, based on acquired scheduling parameter data, preset scheduling conditions, and preset search rules, the initial solution is optimized using a search optimization method to obtain the globally optimal solution, thereby generating the intelligent scheduling result. This achieves intelligent scheduling, ensuring scheduling accuracy while improving efficiency and resource utilization. In addition, the introduced personalized demand data ensures that the needs of different scheduling personnel are met during the solution process, improving the scheduling personnel's experience.

[0099] Figure 4 This is a schematic diagram of an intelligent scheduling device 400 provided in an embodiment of the present invention, as shown below. Figure 4 As shown, it includes:

[0100] The acquisition module 401 is used to receive scheduling requests and acquire scheduling data based on the scheduling requests. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling parameter data includes personalized requirement data.

[0101] The construction module 402 is used to construct an initial solution for the scheduling result that satisfies the preset workload fitting value condition based on personalized demand data and scheduling personnel data.

[0102] Search module 403 is used to perform search optimization based on initial solution, preset scheduling conditions and preset search rules to obtain the global optimal solution;

[0103] Module 404 is used to generate intelligent scheduling results based on the global optimal solution.

[0104] The intelligent scheduling device provided in this embodiment of the invention can abstract the scheduling problem into a mathematical combinatorial optimization problem, construct an initial solution based on the acquired personalized demand data and scheduling personnel data, and further optimize the initial solution through a search optimization method based on the acquired scheduling parameter data, preset scheduling conditions and preset search rules to obtain the global optimal solution, thereby generating an intelligent scheduling result, realizing intelligent scheduling, ensuring scheduling accuracy while improving efficiency.

[0105] Optionally, the workload fit value is calculated as follows:

[0106] Calculate the manpower for scheduling based on the scheduling personnel data;

[0107] The predicted flow value is calculated based on historical flow data obtained from scheduling parameter data;

[0108] The workload fit value is determined based on the ratio of scheduled manpower to predicted flow value.

[0109] Optionally, the construction module 402 is also used to: construct an initial solution for the scheduling result that satisfies the preset workload fitting value condition based on the scheduling personnel data;

[0110] The initial solution is adjusted based on personalized demand data.

[0111] Optionally, the device further includes: a calculation module 405 (not shown in the figure) for calculating the scheduling complexity based on the scheduling personnel data; and a determination module 406 for determining the parameters of the preset annealing model based on the scheduling complexity.

[0112] The search module 403 is also used to: perform search optimization based on the initial solution, preset scheduling conditions and preset search rules, and obtain the global optimal solution through a preset annealing model.

[0113] Optionally, the search module 403 is further configured to: search for neighborhood solutions of the initial solution based on preset scheduling conditions and preset search rules through a random exchange strategy, and calculate the target score of the neighborhood solution, wherein the target score is the weighted sum of workload score, scheduling personnel fairness score, scheduling rule score and corresponding weights.

[0114] Determine whether to replace the initial solution based on the objective score of the neighborhood solution and the objective score of the initial solution;

[0115] Repeat all the above search operations until the annealing model meets the iteration termination condition and the global optimal solution is obtained.

[0116] Optionally, the calculation module 405 is also configured to: select a certain number of search rules from preset search rules during each search;

[0117] Using a random exchange strategy, the neighborhood solutions of the initial solution are searched based on preset scheduling conditions and a first set number of search rules.

[0118] Optionally, the determining module 406 is further configured to: determine to replace the initial solution with the neighborhood solution in response to the target score of the neighborhood solution being greater than the target score of the initial solution;

[0119] In response to the condition that the target score of the domain solution is not greater than the target score of the initial solution, the difference between the target score of the domain solution and the target score of the initial solution is calculated.

[0120] The acceptance probability is calculated based on the difference, and the decision on whether to replace the initial solution with the neighborhood solution is based on the acceptance probability.

[0121] The intelligent scheduling apparatus provided by the embodiments of the present invention can abstract the scheduling problem into a mathematical combinatorial optimization problem, and obtain the scheduling result through a solution. Specifically, an initial solution is constructed based on the acquired personalized demand data and scheduling personnel data. Furthermore, based on the acquired scheduling parameter data, preset scheduling conditions, and preset search rules, the initial solution is optimized through a search optimization method to obtain the globally optimal solution, thereby generating an intelligent scheduling result. This achieves intelligent scheduling, ensuring scheduling accuracy while improving efficiency and resource utilization. In addition, the introduced personalized demand data ensures that the needs of different scheduling personnel are met during the solution process, improving the experience of scheduling personnel.

[0122] Figure 5 An exemplary system architecture 500 is shown, in which the intelligent scheduling method or apparatus of embodiments of the present invention can be applied.

[0123] like Figure 5As shown, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 serves as the medium for providing communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0124] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, and 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0125] Terminal devices 501, 502, and 503 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0126] Server 505 can be a server that provides various services, such as a back-end management server that supports shopping websites browsed by users using terminal devices 501, 502, and 503 (for example only). The back-end management server can analyze and process data such as received intelligent scheduling requests, and feed back the processing results (such as scheduling results - for example only) to the terminal devices.

[0127] It should be noted that the intelligent scheduling method provided in this embodiment of the invention is generally executed by server 505, and correspondingly, the intelligent scheduling device is generally set in server 505.

[0128] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0129] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing terminal devices or servers of the present invention. Figure 6 The terminal device or server shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0130] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0131] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0132] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this invention.

[0133] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0134] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0135] The units or modules described in the embodiments of the present invention can be implemented in software or hardware. The described units or modules can also be housed in a processor; for example, a processor can be described as including an acquisition module, a construction module, a search module, and a generation module. The names of these modules do not necessarily limit the unit or module itself; for example, the acquisition module can also be described as "a module that receives scheduling requests and acquires scheduling data based on the scheduling requests."

[0136] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0137] Receive scheduling requests and obtain scheduling data based on the scheduling requests. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling parameter data includes personalized requirement data.

[0138] Based on personalized demand data and scheduling personnel data, an initial solution for the scheduling result that satisfies the preset workload fitting value condition is constructed.

[0139] Based on the initial solution, preset scheduling conditions, and preset search rules, the search optimization is performed to obtain the globally optimal solution;

[0140] Intelligent scheduling results are generated based on the global optimal solution.

[0141] According to the technical solution of the present invention, the scheduling problem can be abstracted into a mathematical combinatorial optimization problem. An initial solution is constructed based on the acquired personalized demand data and scheduling personnel data. Furthermore, based on the acquired scheduling parameter data, preset scheduling conditions and preset search rules, the initial solution is optimized through a search optimization method to obtain the global optimal solution, thereby generating intelligent scheduling results. This achieves intelligent scheduling, ensuring scheduling accuracy while improving efficiency.

[0142] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for intelligent scheduling, characterized in that, include: Receive scheduling requests and obtain scheduling data based on the scheduling requests. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling parameter data includes personalized demand data. Based on the personalized demand data and the scheduling personnel data, an initial solution for the scheduling result that satisfies the preset workload fitting value is constructed. Based on the initial solution, preset scheduling conditions, and preset search rules, a search optimization is performed to obtain the globally optimal solution; Intelligent scheduling results are generated based on the global optimal solution.

2. The method according to claim 1, characterized in that, The workload fitting value is calculated in the following way: Calculate the manpower for the shift based on the aforementioned staffing data; The predicted flow value is calculated based on the historical flow data obtained from the scheduling parameter data; The workload fitting value is determined based on the ratio of the scheduled manpower to the predicted flow value.

3. The method according to claim 2, characterized in that, The initial solution for constructing a scheduling result that satisfies the preset workload fitting value condition based on the personalized demand data and the scheduling personnel data includes: An initial solution for the scheduling result that satisfies the preset workload fitting value condition is constructed based on the scheduling personnel data. The initial solution is adjusted based on the personalized demand data.

4. The method according to claim 1, characterized in that, Before performing search optimization based on the initial solution, preset scheduling conditions, and preset search rules to obtain the globally optimal solution, the method further includes: Calculate the scheduling complexity based on the aforementioned personnel scheduling data; The parameters of the preset annealing model are determined based on the scheduling complexity. Furthermore, the search optimization based on the initial solution, preset scheduling conditions, and preset search rules to obtain the globally optimal solution includes: Based on the initial solution, preset scheduling conditions, and preset search rules, the global optimal solution is obtained by searching and optimizing using the preset annealing model.

5. The method according to claim 4, characterized in that, The process of searching and optimizing using a preset annealing model based on the initial solution, preset scheduling conditions, and preset search rules to obtain the global optimal solution includes: Using a random exchange strategy, the neighborhood solutions of the initial solution are searched based on the preset scheduling conditions and preset search rules, and the target score of the neighborhood solutions is calculated. The target score is the weighted sum of the workload score, the fairness score of the scheduler, the scheduling rule score, and the corresponding weights. Determine whether to replace the initial solution based on the target score of the neighborhood solution and the target score of the initial solution; Repeat all the above search operations until the annealing model meets the iteration termination condition and the global optimal solution is obtained.

6. The method according to claim 5, characterized in that, The step of searching for neighborhood solutions of the initial solution using a random exchange strategy based on the preset scheduling conditions and preset search rules, and calculating the target score of the neighborhood solutions, includes: During each search, select a certain number of search rules from the preset search rules; Using a random exchange strategy, neighborhood solutions of the initial solution are searched based on the preset scheduling conditions and the first set number of search rules.

7. The method according to claim 5, characterized in that, The step of determining whether to replace the initial solution based on the target score of the neighborhood solution and the target score of the initial solution includes: In response to the fact that the target score of the neighborhood solution is greater than the target score of the initial solution, it is determined to replace the initial solution with the neighborhood solution; In response to the fact that the target score of the neighborhood solution is not greater than the target score of the initial solution, the difference between the target score of the neighborhood solution and the target score of the initial solution is calculated; The acceptance probability value is calculated based on the difference, and the decision on whether to replace the initial solution with the neighborhood solution is made based on the acceptance probability value.

8. A device for intelligent scheduling, characterized in that, include: The acquisition module is used to receive scheduling requests and acquire scheduling data according to the scheduling requests. The scheduling data includes scheduling personnel data and scheduling parameter data. The scheduling parameter data includes personalized demand data. The construction module is used to construct an initial solution for the scheduling result that satisfies the preset workload fitting value condition based on the personalized demand data and the scheduling personnel data. The search module is used to perform search optimization based on the initial solution, preset scheduling conditions and preset search rules to obtain the global optimal solution; The generation module is used to generate intelligent scheduling results based on the global optimal solution.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images