Method and apparatus for determining target area work order quantity
By utilizing historical work order data and resource data to revise the preset model, the problem of low accuracy in predicting the number of work orders in migratory areas was solved, achieving accurate prediction and scheduling optimization of the number of work orders and improving user satisfaction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TELECOM CORP LTD
- Filing Date
- 2022-11-29
- Publication Date
- 2026-05-19
AI Technical Summary
Existing technologies cannot accurately capture changes in the number of work orders in migratory areas, resulting in low accuracy in predicting the number of installation and maintenance work orders. This leads to improper dispatching of support personnel, an increase in user complaints and reports, and a decline in customer satisfaction.
By acquiring historical work order data, resource deployment data, and resource usage data for the target area, the initial number of work orders is determined using a preset model and year-on-year data, and then corrected using resource deployment and usage data to improve prediction accuracy.
It enabled accurate prediction of the number of work orders in the target area, improved the effectiveness of support personnel scheduling, reduced user complaints and reports, and increased customer satisfaction.
Smart Images
Figure CN116187502B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of big data prediction technology, and more specifically, to a method and apparatus for determining the number of work orders in a target area. Background Technology
[0002] As people's lifestyles evolve, summer retreats to cooler climates and winter migrations to warmer regions have become commonplace. Consequently, network demand also exhibits migratory and regional variations, leading to changes in the demand for installation and maintenance personnel. This often results in a surge in installation and maintenance orders starting in May or November, coupled with a shortage of personnel, leading to order backlogs, prolonged repair times, and a sharp increase in user complaints and negative user experience. Because the number of installation and maintenance orders in each migratory region fluctuates quarterly and annually, and relevant technologies cannot accurately capture these changes, manual estimation and balancing methods are often used for scheduling. The low accuracy of order prediction hinders effective and precise staff deployment, resulting in continued complaints and a persistent decline in user experience and customer satisfaction.
[0003] There is currently no effective solution to the above problems. Summary of the Invention
[0004] This application provides a method and apparatus for determining the number of work orders in a target area, so as to at least solve the technical problem of low accuracy in predicting the number of work orders.
[0005] According to one aspect of the embodiments of this application, a method for determining the number of work orders in a target area is provided, comprising: acquiring historical work order data, resource deployment data, and resource usage data of the target area, wherein the resource deployment data is used to represent the resource deployment status in the target area, and the resource usage data is used to represent the resource usage status in the target area; extracting the number of work orders within a first preset period prior to the prediction period from the historical work order data, and determining year-on-year data of the number of work orders in the first preset period based on the number of work orders within the first preset period; determining the initial number of work orders in the target area within the prediction period using a preset model and the year-on-year data, wherein the preset model is used to represent the correlation between the number of work orders in the target area and the date; and correcting the initial number using the resource deployment data and the resource usage data to obtain the target number of work orders in the target area.
[0006] Optionally, the initial number of work orders in the target area within the prediction period is determined using a preset model and year-on-year data, including: determining the initial values of the model parameters of the preset model; iterating the preset model using historical work order data and the initial values to determine the target values of the model parameters of the preset model; after determining the target values of the model parameters of the preset model, determining the predicted number of work orders in the target area within the prediction period using the output results of the preset model, and determining the initial number by convolving the predicted number with the year-on-year data.
[0007] Optionally, the preset model is iterated using historical work order data and initial values to determine the model parameters of the preset model, including: extracting data of the first type of work orders and the second type of work orders from the historical work order data, wherein the first type of work orders represents work orders for equipment installation and relocation, and the second type of work orders represents work orders for equipment failure; and iterating the preset model using the data of the first type of work orders and the second type of work orders and the initial values respectively to determine the first type of model parameters and the second type of model parameters in the model parameters.
[0008] Optionally, the predicted number of work orders in the target area within the prediction period is determined using a preset model, including: determining a first preset model using a first type of parameter model, the preset model including a first preset model and a second preset model, the second preset model being used to determine the predicted number of second type work orders; and determining the predicted number of first type work orders in the target area within the prediction period using the output of the first preset model, wherein the predicted number includes the predicted number of first type work orders and the predicted number of second type work orders.
[0009] Optionally, after determining the predicted number of the first type of work orders, the method further includes: determining the first year-on-year data of the number of the first type of work orders within a first preset time period; and determining the initial number of the first type of work orders by convolving the predicted number of the first type of work orders with the first year-on-year data, wherein the initial number includes the initial number of the first type of work orders and the initial number of the second type of work orders.
[0010] Optionally, the initial quantity is corrected using resource deployment data and resource usage data to obtain the target quantity of work orders in the target area. This includes: extracting the resource rate from the resource deployment data and the dwell rate and activation rate from the resource usage data. The resource rate represents the month-on-month change rate of the number of passive fiber optic network ports in the target area within the second preset time period before the prediction period. The dwell rate represents the year-on-year change rate of the number of devices in the target area that have accessed the base station within the second preset time period before the prediction period. The activation rate represents the year-on-year change rate of the number of devices in the target area that are active within the second preset time period before the prediction period. Devices that have accessed the base station more than a preset threshold number of times within one month are identified as being in an active state. The initial quantity of the first type of work orders is corrected using the resource rate and dwell rate to obtain the target quantity of the first type of work orders. The initial quantity of the second type of work orders is corrected using the activation rate to obtain the target quantity of the second type of work orders. The target quantity of work orders in the target area includes the target quantity of the first type of work orders and the target quantity of the second type of work orders.
[0011] Optionally, obtaining historical work order data for the target area includes: obtaining historical work orders within the target area; extracting various target information from the field information of the historical work orders, wherein the various target information includes at least: work order type, work order generation date, and work order quantity; and combining the various target information into historical work order data.
[0012] According to another aspect of the embodiments of this application, an apparatus for determining the number of work orders in a target area is also provided, comprising: an acquisition module, configured to acquire historical work order data, resource deployment data, and resource usage data of a target area, wherein the resource deployment data represents the resource deployment status within the target area, and the resource usage data represents the resource usage status within the target area; a first determination module, configured to extract the number of work orders within a first preset time period prior to the prediction period from the historical work order data, and determine year-on-year data of the number of work orders within the first preset time period based on the number of work orders within the first preset time period; a second determination module, configured to determine the initial number of work orders in the target area within the prediction period using a preset model and the year-on-year data, wherein the preset model represents the correlation between the number of work orders and the date within the target area; and a correction module, configured to correct the initial number using the resource deployment data and the resource usage data to obtain the target number of work orders in the target area.
[0013] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, which stores a computer program, wherein the device where the non-volatile storage medium is located executes the method for determining the number of work orders in the target area by running the computer program.
[0014] According to another aspect of the embodiments of this application, a computer device is also provided, including a memory and a processor, the processor being used to run a program, wherein the program executes the above-mentioned method for determining the number of work orders in the target area.
[0015] In this embodiment, historical work order data, resource deployment data, and resource usage data of the target area are acquired. The resource deployment data represents the resource deployment status within the target area, and the resource usage data represents the resource usage status within the target area. The number of work orders within a first preset duration prior to the prediction period is extracted from the historical work order data, and the year-on-year data of the number of work orders within the first preset duration is determined based on the number of work orders within the first preset duration. The initial number of work orders in the target area within the prediction period is determined using a preset model and the year-on-year data, wherein the preset model represents the correlation between the number of work orders and the date within the target area. The initial number is corrected using the resource deployment data and resource usage data to obtain the target number of work orders in the target area. By introducing the year-on-year data of the number of work orders within the first preset duration as an adjustment coefficient into the preset model, and simultaneously correcting the data obtained from the prediction model using the resource deployment data and resource usage data, the purpose of repeatedly correcting the prediction data is achieved, thereby improving the technical effect of improving the accuracy of work order data prediction and solving the technical problem of low accuracy in work order quantity prediction. Attached Figure Description
[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0017] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for a method of determining the number of work orders in a target area according to an embodiment of this application.
[0018] Figure 2 This is a flowchart illustrating a method for determining the number of work orders in a target area according to this application;
[0019] Figure 3 This is a schematic diagram of an optional device for determining the number of work orders in a target area according to an embodiment of this application. Detailed Implementation
[0020] 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.
[0021] 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.
[0022] According to an embodiment of this application, an embodiment of a method for determining the number of work orders in a target area 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. Furthermore, 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.
[0023] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, cloud servers, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for determining the number of work orders in a target area is shown. Figure 1 As shown, the computer terminal 10 (or mobile device 10) 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 module 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 the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1The 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.
[0024] 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).
[0025] 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 method for determining the number of work orders in the target area in this embodiment of the application. 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 above-mentioned method for determining the number of work orders in the target area. 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 the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0026] The transmission module 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 module 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 module 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.
[0027] 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).
[0028] Among related technologies, one approach is to construct an optimal distribution model using cluster analysis and perform text mining on the work order acceptance content using natural language, but this is not suitable for predicting (seasonal) work order data. Another approach is a combined prediction method based on the dual-period Holt-Winters model (a time series analysis and forecasting method) and the SARIMA (Seasonal Differential Autoregressive Moving Average) model. This analysis method belongs to the field of wireless network traffic prediction and network optimization, and is not suitable for predicting (seasonal) work order data. Yet another approach is to directly and simply use the Holt-Winters model for prediction, which is also not suitable for predicting (seasonal) work order data.
[0029] According to an embodiment of this application, an embodiment of a method for determining the number of work orders in a target area is 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. Furthermore, 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.
[0030] Figure 2 This is a flowchart of a method for determining the number of work orders in a target area according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:
[0031] Step S202: Obtain historical work order data, resource deployment data, and resource usage data for the target area. The resource deployment data is used to represent the resource deployment status within the target area, and the resource usage data is used to represent the resource usage status within the target area.
[0032] Step S204: Extract the number of work orders within the first preset time period before the prediction period from the historical work order data, and determine the year-on-year data of the number of work orders in the first preset time period based on the number of work orders within the first preset time period.
[0033] Step S206: Determine the initial number of work orders in the target area within the forecast period using a preset model and year-on-year data, wherein the preset model is used to represent the correlation between the number of work orders and the date in the target area;
[0034] Step S208: Correct the initial quantity using resource deployment data and resource usage data to obtain the target quantity of work orders in the target area.
[0035] Through the above steps, the year-on-year data of the number of work orders in the first preset time period can be used as an adjustment coefficient to introduce into the preset model. At the same time, the data obtained from the prediction model can be corrected by using resource deployment data and resource usage data. This achieves the purpose of correcting the prediction data multiple times, thereby improving the technical effect of improving the accuracy of work order data prediction and solving the technical problem of low accuracy in work order quantity prediction.
[0036] It should be noted that the preset model in the above method can be the Holt-Winters model. The method provided in this application further proposes to improve the Holt-Winters model based on the gain coefficient, and at the same time introduce resource deployment data and resource usage data to perform secondary correction on the output of the preset model in order to improve the prediction accuracy.
[0037] It should be noted that the gain coefficient is determined based on the year-on-year data of the number of work orders in the first preset period before the forecast period. This can be understood as the ratio of the number of work orders in the first preset period within the current year to the number of work orders in the first preset period within the previous year. For example, if the first preset period is the first two months of this year's preset period, the year-on-year data is the ratio of the number of work orders in the first two months of this year's forecast period to the number of work orders in the first two months of the previous year's forecast period, which is also equal to the gain coefficient. For example, if the forecast period is from July to September 2020, then the first preset period is from May to June, and the year-on-year data of the number of work orders in the first preset period is the ratio of the sum of the number of work orders in May and June 2020 to the sum of the number of work orders in May and June 2019.
[0038] In step S206, the output of the preset model is used to show the relationship between the number of work orders and the date in the target area. For example, on May 6, 2020, the number of work orders in the target area is 400.
[0039] In some embodiments of this application, the target area may be a migratory bird area, such as an area where people periodically move around.
[0040] The following detailed embodiments illustrate steps S202 to S208.
[0041] In step S206, the initial number of work orders in the target area within the prediction period is determined using a preset model and year-on-year data. In some embodiments of this application, the model parameters of the preset model can be determined first, and the initial values of the model parameters of the preset model are determined first. The preset model is iterated using historical work order data and the initial values to determine the target values of the model parameters of the preset model. After determining the target values of the model parameters of the preset model, the predicted number of work orders in the target area within the prediction period is determined using the output results of the preset model, and the convolution of the predicted number with the year-on-year data is determined as the initial number.
[0042] Specifically, let the dataset be U = {x0, x1, ... x} t For example, x t Let x0 be the number of work orders in month t, where t is a positive integer, and x0 be the number of work orders in the initial month of the dataset. For example, if the dataset includes work orders from January to September, x0 is the number of work orders in January of the dataset.
[0043] Determine the initial values of the model parameters, for example: initial value of the horizontal component S0 = x0, initial value of the trend component... The initial value of the seasonal component is C0 = 1.
[0044] In one alternative approach, the formulas for calculating the horizontal component, trend component, and seasonal component are as follows:
[0045]
[0046] B t =β(S t -S t-1 )+(1-β)B t-1
[0047]
[0048] The above calculation formula is used to iterate and determine the data smoothing factor α, the trend smoothing factor β, and the seasonal change smoothing factor γ.
[0049] In some embodiments of this application, the initial number of work orders for the target area can be determined by the following formula:
[0050] F t+m =(S t +mB t C t-L+1+(m-1)modL ω
[0051] In the formula, S t B represents the level component of the number of work orders in month t. t C represents the trend component of work order volume in month t. t F represents the seasonal component of work order volume in month t. t+mLet ω represent the predicted work order volume for month t+m, where 0 < α < 1, 0 < β < 1, 0 < γ < 1, ω represents the year-on-year data, m represents the time length of the prediction period, and L represents the length of the period.
[0052] It should be noted that, taking the target area as a migratory area as an example, in actual application scenarios, historical work order data can exclude the special periods of the Spring Festival and summer and winter vacations in January, February and March of each year, and collect historical work orders (installation, relocation, and obstruction) from the three years prior to the first three months, as well as historical work orders from the first two months of the current year's prediction cycle as sample data.
[0053] In some embodiments of this application, the types of work orders can be divided into at least two categories. The first type of work order represents a work order for equipment installation and relocation, and the second type of work order represents a work order for equipment failure. In actual application scenarios, the first type of work order can be an installation and relocation work order, and the second type of work order can be a failure work order. It can be understood that an installation and relocation work order represents a work order for installing or moving equipment, and a failure work order represents a work order for equipment failure.
[0054] In order to predict the first type of work order and the second type of work order separately, one option is to extract the data of the first type of work order and the data of the second type of work order from historical work order data, where the first type of work order represents work orders for equipment installation and relocation, and the second type of work order represents work orders for equipment failure; and to iterate the preset model using the data of the first type of work order and the data of the second type of work order and the initial value respectively to determine the first type of model parameters and the second type of model parameters in the model parameters.
[0055] Understandably, the method involves using a first-type parameter model to determine a first preset model, which includes a first preset model and a second preset model. The second preset model is used to determine the predicted number of second-type work orders. The output of the first preset model is used to determine the predicted number of first-type work orders in the target area within the prediction period. The predicted number includes the predicted number of first-type work orders and the predicted number of second-type work orders. After determining the predicted number of first-type work orders, the method further includes: determining the first year-on-year data of the number of first-type work orders within a first preset time period; and determining the initial number of first-type work orders by convolving the predicted number of first-type work orders with the first year-on-year data. The initial number includes the initial number of first-type work orders and the initial number of second-type work orders.
[0056] It should be noted that the method for determining the initial quantity of the second type of work order is similar to that for the first type of work order, and will not be repeated here.
[0057] In some embodiments of this application, the target number of work orders in the target area is obtained by correcting the initial quantity using resource deployment data and resource usage data. This can be achieved in the following way: extracting the resource rate from the resource deployment data and the dwell rate and power-on rate from the resource usage data. The resource rate represents the month-on-month change rate of the number of passive optical network ports in the target area within the second preset time period before the prediction period. The dwell rate represents the year-on-year change rate of the number of devices in the target area that have accessed the base station within the second preset time period before the prediction period. The power-on rate represents the year-on-year change rate of the number of devices in the target area that are in an active state within the second preset time period before the prediction period. Devices that have accessed the base station more than a preset threshold number of times within one month are identified as being in an active state. The initial quantity of the first type of work orders is corrected using the resource rate and dwell rate to obtain the target number of the first type of work orders. The initial quantity of the second type of work orders is corrected using the power-on rate to obtain the target number of the second type of work orders. The target number of work orders in the target area includes the target number of the first type of work orders and the target number of the second type of work orders.
[0058] The above method of secondary correction of the initial quantity fully considers the strong resource and population distribution characteristics of work orders in the target area (migratory bird area) in the actual application scenario, and further improves the accuracy of prediction. Among them, the main factors affecting the number of installation and relocation work orders are the resource coverage of newly built communities, the increase in user visit and stay rate, and the frequency of use and power-on.
[0059] It should be noted that the second preset duration can be one month or other durations, which can be set according to actual needs. This application embodiment does not impose any limitations.
[0060] In practical application scenarios, the resource rate can be determined by the month-on-month change rate of the number of passive fiber optic network ports in the target area in the month preceding the prediction period. The dwell rate can be determined by the year-on-year change rate of the number of devices that have accessed the base station in the target area in the month preceding the prediction period. The power-on rate can be determined by the year-on-year change rate of the number of active devices in the target area in the month preceding the prediction period. Devices that have accessed the base station more than a preset threshold number of times in a month are identified as being in an active state. For example, devices that have accessed the base station more than 7 times in a month can be identified as being in an active state. It can be understood that whether a device is in an active state reflects whether the device is being used. The above example is only an illustration of the active state. Other methods that can verify whether a device is being used normally can also verify whether a device is in an active state. This application embodiment does not limit the scope of the method.
[0061] Resource rate and dwell rate fully reflect the amount of resources and the flow of people, while the uptime rate can reflect the equipment failure rate. Adding the weights of resource rate, dwell rate and uptime rate during the correction process makes the prediction accuracy higher.
[0062] Specifically, the target quantity for the first type of work order can be determined using the following formula:
[0063]
[0064] In the formula, Re represents the month-on-month change rate of the number of passive optical fiber network ports in the month preceding the forecast period, and Vi represents the year-on-year change rate of the number of residents in the month preceding the forecast period. This indicates the target quantity for the first type of work order. This indicates the initial quantity of the first type of work order.
[0065] The target quantity for the second type of work order can be determined using the following formula:
[0066]
[0067] In the formula, Bo represents the year-on-year change rate of operating capacity in the month preceding the forecast period. This indicates the target quantity for the second type of work order. This indicates the initial quantity of the second type of work order.
[0068] In one alternative approach, the historical work order data of the target area can be obtained by acquiring historical work orders within the target area; extracting multiple target information from the field information of the historical work orders, the multiple target information including at least: work order type, work order generation date and work order quantity; and combining the multiple target information into historical work order data.
[0069] In practical application scenarios, the list data for the first type of work order (installation and relocation) and the second type of work order (obstacle work order) are shown in Table 1:
[0070]
[0071]
[0072] Table 1
[0073] Extract the target information from the fields in Table 1. For example, a total of 500 work orders were generated on April 2, 2020. Among them, there were 300 first-type work orders and 200 second-type work orders. In Table 1, ADSL (Asymmetric Digital Subscriber Line) represents asymmetric digital subscriber line; LAN (Local Area Network) represents local area network; ISDN (Integrated Services Digital Network) represents integrated services digital network; EPON (Ethernet Passive Optical Network) represents Ethernet passive optical network; and IPTV represents interactive network television.
[0074] According to another aspect of the embodiments of this application, a device for determining the number of work orders in a target area is also provided, such as... Figure 3 As shown, it includes: an acquisition module 30, used to acquire historical work order data, resource deployment data, and resource usage data for the target area, wherein the resource deployment data represents the resource deployment status within the target area, and the resource usage data represents the resource usage status within the target area; a first determination module 32, used to extract the number of work orders within a first preset time period before the prediction period from the historical work order data, and determine the year-on-year data of the number of work orders within the first preset time period based on the number of work orders within the first preset time period; a second determination module 34, used to determine the initial number of work orders in the target area within the prediction period using a preset model and the year-on-year data, wherein the preset model represents the correlation between the number of work orders and the date in the target area; and a correction module 36, used to correct the initial number using the resource deployment data and the resource usage data to obtain the target number of work orders in the target area.
[0075] The second determining module 34 includes: a determining submodule, used to extract data of the first type of work orders and the second type of work orders from historical work order data, wherein the first type of work orders represents work orders for equipment installation and relocation, and the second type of work orders represents work orders for equipment failure; and to iterate the preset model using the data of the first type of work orders and the data of the second type of work orders and the initial value, respectively, to determine the first type of model parameters and the second type of model parameters in the model parameters.
[0076] The determination submodule includes: a determination unit, used to determine a first preset model using a first type of parameter model, the preset model including a first preset model and a second preset model, the second preset model being used to determine the predicted quantity of second type work orders; and using the output results of the first preset model to determine the predicted quantity of first type work orders in the target area within the prediction period, wherein the predicted quantity includes the predicted quantity of first type work orders and the predicted quantity of second type work orders.
[0077] The determining unit includes: a determining subunit, used to determine the first year-on-year data of the number of first type of work orders within a first preset time period; and to determine the initial number of first type of work orders by convolving the predicted number of first type of work orders with the first year-on-year data, wherein the initial number includes the initial number of first type of work orders and the initial number of second type of work orders.
[0078] The correction module 36 includes: a correction submodule, used to extract the resource rate from the resource deployment data and the dwell rate and power-on rate from the resource usage data. The resource rate represents the month-on-month change rate of the number of passive optical fiber network ports in the target area within the second preset time period before the prediction period. The dwell rate represents the year-on-year change rate of the number of devices in the target area that have accessed the base station within the second preset time period before the prediction period. The power-on rate represents the year-on-year change rate of the number of devices in the target area that are active within the second preset time period before the prediction period. Devices that have accessed the base station more than a preset threshold number of times within one month are identified as being in an active state. The initial number of first-type work orders is corrected using the resource rate and dwell rate to obtain the target number of first-type work orders. The initial number of second-type work orders is corrected using the power-on rate to obtain the target number of second-type work orders. The target number of work orders in the target area includes the target number of first-type work orders and the target number of second-type work orders.
[0079] The acquisition module 30 includes: an acquisition submodule, used to acquire historical work orders within a target area; extracting various target information from the field information of historical work orders, the various target information including at least: work order type, work order generation date and work order quantity; and combining the various target information into historical work order data.
[0080] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, which stores a computer program, wherein the device where the non-volatile storage medium is located executes the method for determining the number of work orders in the target area by running the computer program.
[0081] According to another aspect of the embodiments of this application, a computer device is also provided, including a memory and a processor, wherein the processor is used to run a program, wherein the program executes the aforementioned method for determining the number of work orders in a target area. The specific structure of this edge cloud server can be found in [reference needed]. Figure 1 The computer hardware structure shown is not limited to this.
[0082] 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.
[0083] 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.
[0084] 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 can be 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 couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.
[0085] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0086] 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.
[0087] 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 of 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.
[0088] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles 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 determining the number of work orders in a target area, characterized in that, include: The system acquires historical work order data, resource deployment data, and resource usage data for a target area. The resource deployment data represents the resource deployment status within the target area, and the resource usage data represents the resource usage status within the target area. The target area is a migratory region. The number of work orders within a first preset time period before the prediction period is extracted from the historical work order data, and the year-on-year data of the number of work orders in the first preset time period is determined based on the number of work orders within the first preset time period, wherein the year-on-year data is used to determine the gain coefficient of the improved preset model. The initial number of work orders in the target area within the forecast period is determined using a preset model and the year-on-year data, wherein the preset model is used to represent the correlation between the number of work orders and the date in the target area; The initial number of work orders in the target area is corrected using the resource deployment data and the resource usage data to obtain the target number of work orders in the target area.
2. The method according to claim 1, characterized in that, Determining the initial number of work orders in the target area within the prediction period using a preset model and the year-on-year data includes: Determine the initial values of the model parameters of the preset model; The preset model is iterated using the historical work order data and the initial value to determine the target values of the model parameters of the preset model; After determining the target values of the model parameters of the preset model, the predicted number of work orders in the target area within the prediction period is determined using the output of the preset model, and the convolution of the predicted number with the year-on-year data is used to determine the initial number.
3. The method according to claim 2, characterized in that, The preset model is iterated using the historical work order data and the initial value to determine the model parameters of the preset model, including: Extract the data of the first type of work order and the data of the second type of work order from the historical work order data, wherein the first type of work order represents work orders for equipment installation and relocation, and the second type of work order represents work orders for equipment failure; The preset model is iterated using the data from the first type of work order and the data from the second type of work order, along with the initial value, to determine the first type of model parameters and the second type of model parameters in the model parameters.
4. The method according to claim 3, characterized in that, The step of determining the predicted number of work orders in the target area within the prediction period using the preset model includes: A first preset model is determined using the parameters of the first type of model. The preset model includes the first preset model and a second preset model. The second preset model is used to determine the predicted number of work orders of the second type. The predicted number of the first type of work orders in the target area within the prediction period is determined using the output of the first preset model, wherein the predicted number includes the predicted number of the first type of work orders and the predicted number of the second type of work orders.
5. The method according to claim 4, characterized in that, After determining the predicted quantity of the first type of work orders, the method further includes: Determine the first year-on-year data on the number of the first type of work orders within the first preset time period; The initial quantity of the first type of work orders is determined by convolving the predicted quantity of the first type of work orders with the first year-on-year data. The initial quantity includes the initial quantity of the first type of work orders and the initial quantity of the second type of work orders.
6. The method according to claim 1, characterized in that, The initial number of work orders in the target area is corrected using the resource deployment data and the resource usage data to obtain the target number of work orders in the target area, including: Extract the resource rate from the resource deployment data and the dwell rate and power-on rate from the resource usage data. The resource rate represents the month-on-month change rate of the number of passive optical network ports in the target area within the second preset time period before the prediction period. The dwell rate represents the year-on-year change rate of the number of devices in the target area that have accessed the base station within the second preset time period before the prediction period. The power-on rate represents the year-on-year change rate of the number of devices in the target area that are in an active state within the second preset time period before the prediction period. Devices that have accessed the base station more than a preset number of times within one month are identified as being in an active state. The initial number of the first type of work orders is corrected using the resource rate and the dwell rate to obtain the target number of the first type of work orders; The initial number of the second type of work orders is corrected using the aforementioned uptime rate to obtain the target number of the second type of work orders. The target number of work orders in the target area includes the target number of the first type of work orders and the target number of the second type of work orders.
7. The method according to claim 1, characterized in that, Retrieve historical work order data for the target area, including: Obtain historical work orders within the target area; Extract various target information from the fields of the historical work orders. The various target information includes at least: work order type, work order generation date, and work order quantity. The various target information is combined to form the historical work order data.
8. A device for determining the number of work orders in a target area, characterized in that, include: The acquisition module is used to acquire historical work order data, resource deployment data, and resource usage data of a target area. The resource deployment data is used to represent the resource deployment status within the target area, and the resource usage data is used to represent the resource usage status within the target area. The target area is a migratory bird area. The first determining module is used to extract the number of work orders within a first preset time period before the prediction period from the historical work order data, and to determine the year-on-year data of the number of work orders in the first preset time period based on the number of work orders within the first preset time period, wherein the year-on-year data is used to determine the gain coefficient of the improved preset model. The second determining module is used to determine the initial number of work orders in the target area within the prediction period using a preset model and the year-on-year data, wherein the preset model is used to represent the correlation between the number of work orders and the date in the target area; The correction module is used to correct the initial number of work orders in the target area using the resource deployment data and the resource usage data, so as to obtain the target number of work orders in the target area.
9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a computer program, wherein the device containing the non-volatile storage medium executes the method for determining the number of work orders in the target area as described in any one of claims 1 to 7 by running the computer program.
10. A computer device, characterized in that, It includes a memory and a processor, the processor being used to run a program, wherein the program, when running, executes the method for determining the number of work orders in the target area as described in any one of claims 1 to 7.