Method, device and electronic device for estimating time
By using preset rules and model correction technology in Internet services, combining the service provider's personalized coefficients and service area historical deviation information, the accuracy of time prediction is improved, and the problem of inaccurate time prediction in the prior art is solved.
Patent Information
- Application Number
- CN201910108700.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-02-03
- Publication Date
- 2024-12-27
- Estimated Expiration
- 2039-02-03
AI Technical Summary
The prior art has low accuracy in Internet-based services, and is greatly affected by the service provider's itinerary, resulting in inaccurate time prediction.
By estimating the itinerary completion time of the target order using preset rules, determine the personalized coefficient of the service provider, the maximum order holding volume and the historical estimation deviation information of the service area, and enter this information into the pre-trained model, and correct it Initial estimate of the results to improve accuracy.
By considering potential factors in the service provider and service area, the initial estimation results are revised, which significantly improves the accuracy of time prediction.
Smart Images
Figure CN109934387B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet application technology, and in particular to a method, device and electronic device for estimating time. Background Art
[0002] With the continuous development of Internet technology, many Internet-based services have emerged. In Internet-based services, it is usually necessary to estimate the time in order to push it to users for reference, or to allocate service resources based on the estimated time. Therefore, it is very important to estimate the time. Taking instant delivery as an example, it is generally necessary to estimate the pickup time or the delivery time. At present, the time is generally estimated based on the planned route and the approximate running speed of the service provider. However, since the itinerary of the service provider will be affected by many factors, the time estimated by the above method is less accurate. Summary of the invention
[0003] In order to solve one of the above technical problems, the present application provides a method, device and electronic device for estimating time.
[0004] According to a first aspect of an embodiment of the present application, a method for estimating time is provided, comprising:
[0005] Use the preset rules to estimate the completion time of the trip corresponding to the target order and obtain an initial estimation result;
[0006] Determine target information corresponding to the target order, the target information including a personalized coefficient of a service provider corresponding to the target order, a maximum order holding quantity of the service provider, and historical estimation deviation information of a service area corresponding to the target order;
[0007] Inputting the target information into a pre-trained model;
[0008] The initial estimation result is corrected using the data output by the model to obtain a target estimation result.
[0009] Optionally, the personalization coefficient of the service provider corresponding to the target order is determined in the following manner:
[0010] Determining first historical order data corresponding to the service provider within a first preset time period;
[0011] Based on the first historical order data, determining an actual completion time and an estimated completion time of each first historical trip in a plurality of first historical trips involved in the first historical order data, wherein the estimated completion time is determined based on the preset rule;
[0012] Determine a target ratio corresponding to each of the first historical trips, wherein the target ratio corresponding to any first historical trip is a ratio of an actual completion time to an estimated completion time of the first historical trip;
[0013] The personalized coefficient of the service provider is determined according to the target ratio corresponding to each of the first historical trips.
[0014] Optionally, the personalization coefficient of the service provider is determined by the following formula:
[0015]
[0016]
[0017] Wherein, A represents the personalization coefficient of the service provider; N is a positive integer, representing the number of days corresponding to the first preset period; T is a positive integer, α T represents the average target ratio corresponding to the Tth day in the first preset period; M T is a positive integer, indicating the number of times the service provider completed the first historical trip on the Tth day of the first preset period; β i T It represents the target ratio corresponding to the i-th first historical trip completed by the service provider on the T-th day of the first preset period.
[0018] Optionally, the maximum order holding quantity of the service provider is determined by:
[0019] If it is determined that the accumulated service time corresponding to the service provider is less than or equal to the preset threshold, the pre-specified quantity is determined as the maximum order holding quantity of the service provider;
[0020] If it is determined that the cumulative service time corresponding to the service provider is greater than a preset threshold, the number of orders completed by the service provider is determined, and the preset number corresponding to the number of completed orders is determined as the maximum order holding of the service provider.
[0021] Optionally, the historical estimation deviation information of the service area corresponding to the target order is determined in the following manner:
[0022] Determine second historical order data corresponding to the service area in a second preset time period;
[0023] Based on the second historical order data, determining a plurality of second historical trips involved in the second historical order data and actual completion times and estimated completion times of each second historical trip, wherein the estimated completion time is determined based on the preset rule;
[0024] Determine an estimated deviation corresponding to each of the second historical trips, wherein the estimated deviation corresponding to any second historical trip is a difference between an actual completion time and an estimated completion time of the second historical trip;
[0025] The historical estimated deviation information is determined according to the estimated deviation corresponding to each of the second historical trips.
[0026] Optionally, the historical estimation deviation information includes: average deviation and average absolute deviation;
[0027] The average deviation is determined by the following formula:
[0028]
[0029] The mean absolute deviation is determined by the following formula:
[0030]
[0031] Wherein, ME represents the mean deviation; MAE represents the mean absolute deviation; n is a positive integer, representing the number of second historical trips involved in the orders generated in the service area within the second preset time period; j is a positive integer, Δ j It represents the estimated deviation corresponding to the j-th second historical trip involved in the orders generated in the service area within the second preset time period.
[0032] Optionally, the target information also includes one or more of the following:
[0033] The dispatching time corresponding to the target order;
[0034] The consumption amount corresponding to the target order;
[0035] The distance of the trip corresponding to the target order;
[0036] The estimated completion time of the target order based on the preset rule;
[0037] The order acceptance time corresponding to the target order;
[0038] The dispatch attribute of the target order, wherein the dispatch attribute includes a direct dispatch attribute and a re-dispatch attribute;
[0039] The order generation volume of the service area corresponding to the target order within a preset historical period;
[0040] An estimated generation volume of orders in the service area corresponding to the target order within the current time slice;
[0041] The estimated per capita load of orders in the service area corresponding to the target order in the current time slice;
[0042] The average estimated time when the order trips in the service area corresponding to the target order are completed within the current time slice.
[0043] According to a second aspect of an embodiment of the present application, there is provided a device for estimating time, including:
[0044] An estimation module, used to estimate the completion time of the trip corresponding to the target order using preset rules to obtain an initial estimation result;
[0045] a determination module, configured to determine target information corresponding to the target order, wherein the target information includes a personalized coefficient of a service provider corresponding to the target order, a maximum order holding quantity of the service provider, and historical estimation deviation information of a service area corresponding to the target order;
[0046] An input module, used for inputting the target information into a pre-trained model;
[0047] The correction module is used to correct the initial estimation result using the data output by the model to obtain a target estimation result.
[0048] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects is implemented.
[0049] According to a fourth aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the first aspects is implemented.
[0050] The technical solution provided by the embodiments of the present application may have the following beneficial effects:
[0051] The method and device for estimating time provided by the embodiment of the present application estimate the completion time of the trip corresponding to the target order by using preset rules, obtain the initial estimation result, determine the target information corresponding to the target order, the target information includes the personalized coefficient of the service provider corresponding to the target order, the maximum order holding of the service provider, and the historical estimation deviation information of the service area corresponding to the target order, input the target information into the pre-trained model, and use the data output by the model to correct the initial estimation result to obtain the target estimation result. Since this embodiment at least uses the personalized coefficient of the service provider corresponding to the target order, the maximum order holding of the service provider, and the historical estimation deviation information of the service area corresponding to the target order as the target information, the influence of some potential factors of the service provider corresponding to the target order and the service area corresponding to the target order on the initial estimation result is fully considered, and the initial estimation result is corrected, so that the corrected target estimation result is more accurate.
[0052] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0054] Figure 1 is a flow chart of a method for estimating time according to an exemplary embodiment of the present application;
[0055] Figure 2 is a flow chart of another method for estimating time according to an exemplary embodiment of the present application;
[0056] Figure 3 is a flow chart of another method for estimating time according to an exemplary embodiment of the present application;
[0057] Figure 4 is a block diagram of a device for estimating time according to an exemplary embodiment of the present application;
[0058] Figure 5 is a block diagram of another device for estimating time according to an exemplary embodiment of the present application;
[0059] Figure 6 is a block diagram of another device for estimating time according to an exemplary embodiment of the present application;
[0060] Figure 7is a block diagram of another device for estimating time according to an exemplary embodiment of the present application;
[0061] Figure 8 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0062] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0063] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0064] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0065] like Figure 1 As shown, Figure 1 This is a flow chart of a method for estimating time according to an exemplary embodiment. The method can be applied to a terminal device or a server. The method includes the following steps:
[0066] In step 101, the completion time of the trip corresponding to the target order is estimated using preset rules to obtain an initial estimation result.
[0067] In this embodiment, the service involved can be an online-to-offline service based on the Internet, such as an instant delivery service, etc. It can be understood that the present application does not limit the specific type of the service involved. The target order can be an order with a service request that has been issued by the customer, and the itinerary corresponding to the target order can be the itinerary involved in the target order. Taking the instant delivery service as an example, the itinerary corresponding to the target order can be the pickup itinerary involved in the target order, or the delivery itinerary involved in the target order, etc. Therefore, the completion time of the itinerary corresponding to the target order can be the time when the target order is picked up and delivered to the store, or the time when the goods corresponding to the target order are delivered.
[0068] In this embodiment, the preset rules can be used to first estimate the completion time of the trip corresponding to the target order to obtain an initial estimation result. The preset rules can be any rules for estimating the completion time of the trip. For example, the preset rules can be rules for estimating the completion time of the trip based on the planned path and the approximate running speed of the service provider, or they can be rules for estimating the completion time of the trip based on the starting and ending points of the trip corresponding to the target order through statistical calculations of historical data. It can be understood that the preset rules can also be any other reasonable rules, and the present application does not limit the specific content of the preset rules.
[0069] In step 102, target information corresponding to the target order is determined, and the target information includes a personalization coefficient of the service provider corresponding to the target order, a maximum order holding quantity of the service provider, and historical estimation deviation information of the service area corresponding to the target order.
[0070] In this embodiment, the target information corresponding to the target order can be determined, and the target information can at least include the personalized coefficient of the service provider corresponding to the target order, the maximum order holding of the service provider, and the historical estimated deviation information of the service area corresponding to the target order. Among them, the service provider corresponding to the target order can be a service provider that receives the target order and provides services to customers. Taking the instant delivery service as an example, the service provider corresponding to the target order can be a delivery person who receives the target order and delivers goods to customers. The service area corresponding to the target order can be the service area where the merchant corresponding to the target order is located. Taking the instant delivery service as an example, some service areas can be pre-divided for the merchant, and each service area is responsible for a designated delivery person. The service area corresponding to the target order is the pre-divided service area where the merchant involved in the target order is located.
[0071] In this embodiment, the personalized coefficient of the service provider can be any coefficient that can reflect the personal service efficiency characteristics of the service provider, and can be determined by analyzing and calculating the historical service data corresponding to the service provider. It can be understood that the present application does not limit the specific determination method of the personalized coefficient of the service provider.
[0072] In this embodiment, the maximum order holding of the service provider may be the upper limit of the number of orders that the service provider can hold, which can reflect the experience characteristics of the service provider. The maximum order holding of the service provider is related to the accumulated service time and the number of completed service orders of the service provider. It can be understood that the present application does not limit the specific method for determining the maximum order holding of the service provider.
[0073] In this embodiment, the historical estimation deviation information of the service area corresponding to the target order may be characteristic information that can reflect the accuracy of the estimated time for the service area through the above-mentioned preset rule. The historical estimation deviation information of the service area may be determined based on the historical order data of the service area corresponding to the target order. It is understood that the present application does not limit the specific method for determining the historical estimation deviation information of the service area.
[0074] Optionally, the target information may also include one or more of the following: the dispatch time corresponding to the target order; the consumption amount corresponding to the target order; the distance of the trip corresponding to the target order; the estimated completion time of the trip of the target order based on preset rules; the order receiving time corresponding to the target order; the dispatch attribute of the target order, which can be a direct dispatch attribute (if the target order is an order that is directly dispatched, it belongs to the direct dispatch attribute) or a re-dispatch attribute (if the target order is an order that is re-dispatched, it belongs to the re-dispatch attribute); the order generation volume of the service area corresponding to the target order within a preset historical period; the estimated order generation volume of the service area corresponding to the target order in the current time slice; the estimated per capita load of orders in the service area corresponding to the target order in the current time slice (such as the average number of orders received by each delivery person); the average estimated time for completion of the order trip in the service area corresponding to the target order in the current time slice.
[0075] Among them, each day can be divided into multiple time slices in advance, and the length of each time slice can be equal. The current time slice can be the time slice corresponding to the current moment, and the estimated generation volume of orders, the estimated per capita load of orders, and the average estimated time of order journey completion in the current time slice can all be determined by statistics of historical data. For example, the order generation volume, the per capita load of orders, and the average time of order journey completion in the same time slice as the time slice corresponding to the current moment in the previous week can be weighted averaged, so as to obtain the estimated generation volume of orders, the estimated per capita load of orders, and the average estimated time of order journey completion in the current time slice.
[0076] In step 103, the target information is input into the pre-trained model.
[0077] In this embodiment, a model may be pre-trained, and the model may be any reasonable regression model, for example, the model may include but is not limited to a linear regression model, a logistic regression model, a polynomial regression model, etc. It is understood that the present application does not limit the specific type of the model.
[0078] Specifically, when training the model, historical order data can be collected first, and the historical information corresponding to each historical order can be determined based on the historical order data. The historical information may at least include the personalization coefficient of the service provider corresponding to the historical order, the maximum order holding of the service provider, and the historical estimated deviation information of the service area corresponding to the historical order. Then, the difference between the actual completion time and the estimated time (the time estimated using preset rules) of the trip corresponding to each historical order can be determined. The historical information corresponding to each historical order is taken as a set of sample data, and the above-mentioned difference is used as a label to label each set of sample data, thereby obtaining a sample set, which can be used to train the model. It can be understood that any method for training the model known in the art and that may appear in the future can be applied to the present application, and the present application does not limit the specific process of training the model.
[0079] In step 104, the initial estimation result is corrected using the data output by the model to obtain a target estimation result.
[0080] In this embodiment, the target information is input into the pre-trained model, and the data output by the model is the adjustment parameter used to correct the initial estimation result. By adding the adjustment parameter to the initial estimation result, a target estimation result with higher accuracy can be obtained.
[0081] The method for estimating time provided by the above-mentioned embodiment of the present application estimates the completion time of the trip corresponding to the target order by using preset rules, obtains an initial estimation result, determines the target information corresponding to the target order, and the target information includes the personalized coefficient of the service provider corresponding to the target order, the maximum order holding of the service provider, and the historical estimation deviation information of the service area corresponding to the target order, inputs the target information into a pre-trained model, and uses the data output by the model to correct the initial estimation result to obtain the target estimation result. Since this embodiment at least uses the personalized coefficient of the service provider corresponding to the target order, the maximum order holding of the service provider, and the historical estimation deviation information of the service area corresponding to the target order as the target information, the influence of some potential factors of the service provider corresponding to the target order and the service area corresponding to the target order on the initial estimation result is fully considered, and the initial estimation result is corrected, so that the corrected target estimation result is more accurate.
[0082] like Figure 2 As shown, Figure 2 According to a flowchart of another method for estimating time shown in an exemplary embodiment, the embodiment describes a process of determining a personalized coefficient of a service provider. The method can be applied to a terminal device or a server, and includes the following steps:
[0083] In step 201, first historical order data corresponding to a service provider corresponding to a target order within a first preset time period is determined.
[0084] In this embodiment, the first preset period may be any preset historical period, for example, the first preset period may be a week before the current time, or a month before the current time, or a year before the current time, etc. It is understood that the present application does not limit the specific setting of the first preset period.
[0085] In this embodiment, the first historical order data may be order data of a plurality of historical orders received and processed by the service provider corresponding to the target order within a first preset time period.
[0086] In step 202, based on the first historical order data, the actual completion time and the estimated completion time of each first historical trip in the multiple first historical trips involved in the first historical order data are determined, and the estimated completion time is determined based on a preset rule.
[0087] In this embodiment, the first historical trip may be a historical trip (for example, a pickup trip or a delivery trip, etc.) involved in a historical order received and processed by the service provider corresponding to the target order within the first preset period of time. Figure 1 The preset rules involved in the embodiments are the same.
[0088] In step 203 , a target ratio corresponding to each first historical trip is determined, wherein the target ratio corresponding to any first historical trip is a ratio of the actual completion time to the estimated completion time of the first historical trip.
[0089] In step 204, the personalized coefficient of the service provider is determined according to the target ratio corresponding to each first historical trip.
[0090] In this embodiment, the personalized coefficient of the service provider can be determined according to the target ratio corresponding to each first historical trip. For example, the target ratio corresponding to each first historical trip can be averaged to obtain the personalized coefficient of the service provider.
[0091] Optionally, the personalization coefficient of the service provider may also be determined by the following formula:
[0092]
[0093]
[0094] Where A represents the personalization coefficient of the service provider; N is a positive integer, representing the number of days corresponding to the first preset period; T is a positive integer, α T represents the average target ratio corresponding to the Tth day in the first preset period; M T is a positive integer, indicating the number of times the service provider completed the first historical trip on the Tth day of the first preset period; β i T It represents the target ratio corresponding to the i-th first historical trip completed by the service provider on the T-th day of the first preset period.
[0095] The method for estimating time provided by the above-mentioned embodiment of the present application determines the first historical order data corresponding to the service provider corresponding to the target order within the first preset time period, and based on the first historical order data, determines the actual completion time and estimated completion time of each first historical trip in the multiple first historical trips involved in the first historical order data, the estimated completion time is determined based on a preset rule, and the target ratio corresponding to each first historical trip is determined, wherein the target ratio corresponding to any first historical trip is the ratio of the actual completion time to the estimated completion time of the first historical trip, and the personalized coefficient of the service provider is determined according to the target ratio corresponding to each first historical trip. Thereby, the personalized coefficient of the service provider can more accurately reflect the characteristics of the personal service efficiency of the service provider.
[0096] In some optional implementations, the maximum order holding quantity of the service provider can be determined in the following manner: first, determine whether the cumulative service time corresponding to the service provider is less than or equal to a preset threshold value. If it is determined that the cumulative service time corresponding to the service provider is less than or equal to the preset threshold value, the pre-specified number can be determined as the maximum order holding quantity of the service provider. If it is determined that the cumulative service time corresponding to the service provider is greater than the preset threshold value, the number of orders completed by the service provider can be determined, and the preset number corresponding to the number of completed orders can be determined as the maximum order holding quantity of the service provider.
[0097] This embodiment determines the maximum order holding of the service provider based on the service provider's accumulated service time and the number of completed orders, so that the maximum order holding of the service provider can more accurately reflect the experience characteristics of the service provider.
[0098] like Figure 3 As shown, Figure 3 According to a flowchart of another method for estimating time shown in an exemplary embodiment, the embodiment describes in detail the process of determining the historical estimation deviation information of the service area corresponding to the target order. The method can be applied to a terminal device or a server, and includes the following steps:
[0099] In step 301, second historical order data corresponding to a service area corresponding to a target service in a second preset time period is determined.
[0100] In this embodiment, the second preset period may be any preset historical period, for example, the second preset period may be one day before the current time, two days before the current time, or one week before the current time, etc. It is understood that the present application does not limit the specific setting of the second preset period.
[0101] In this embodiment, the second historical order data may be order data of a plurality of historical orders generated in the service area corresponding to the target order within the second preset time period.
[0102] In step 302, based on the second historical order data, multiple second historical trips involved in the second historical order data and actual completion times and estimated completion times of each second historical trip are determined, and the estimated completion time is determined based on the preset rule.
[0103] In this embodiment, the second historical trip may be a historical trip involved in a historical order generated in the service area corresponding to the target order within the second preset period (for example, a pickup trip or a delivery trip, etc.). Figure 1 The preset rules involved in the embodiments are the same.
[0104] In step 303, an estimated deviation corresponding to each second historical trip is determined, wherein the estimated deviation corresponding to any second historical trip is the difference between the actual completion time and the estimated completion time of the second historical trip.
[0105] In step 304, historical estimated deviation information is determined according to the estimated deviation corresponding to each second historical trip.
[0106] In this embodiment, the historical estimated deviation information of the service area corresponding to the target order includes: an average deviation and an average absolute deviation.
[0107] Alternatively, the above average deviation can be determined by the following formula:
[0108]
[0109] The above mean absolute deviation can be determined by the following formula:
[0110]
[0111] Wherein, ME represents the above average deviation; MAE represents the above average absolute deviation; n is a positive integer, which represents the number of second historical trips involved in the orders generated in the above service area within the second preset time period; j is a positive integer, Δ j It represents the estimated deviation corresponding to the j-th second historical trip involved in the orders generated in the above service area within the second preset time period.
[0112] The method for estimating time provided by the above-mentioned embodiment of the present application determines the second historical order data corresponding to the service area corresponding to the target service in the second preset time period, and based on the second historical order data, determines the multiple second historical trips involved in the second historical order data and the actual completion time and estimated completion time of each second historical trip, the estimated completion time is determined based on the preset rule, and the estimated deviation corresponding to each second historical trip is determined, wherein the estimated deviation corresponding to any second historical trip is the difference between the actual completion time and the estimated completion time of the second historical trip, and the historical estimated deviation information is determined according to the estimated deviation corresponding to each second historical trip. Thereby, the historical estimated deviation information of the service area can more accurately reflect the accuracy characteristics of the estimated time for the service area through the above-mentioned preset rules.
[0113] It should be noted that although the operations of the method of the present application are described in a specific order in the above embodiments, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be changed in the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.
[0114] Corresponding to the aforementioned method embodiment for estimating time, the present application also provides an embodiment of an apparatus for estimating time.
[0115] like Figure 4 As shown, Figure 4 4 is a block diagram of a device for estimating time according to an exemplary embodiment of the present application. The device may include: an estimation module 401, a determination module 402, an input module 403 and a correction module 404.
[0116] Among them, the estimation module 401 is used to estimate the completion time of the trip corresponding to the target order by using preset rules to obtain an initial estimation result.
[0117] The determination module 402 is used to determine the target information corresponding to the target order, where the target information includes the personalized coefficient of the service provider corresponding to the target order, the maximum order holding quantity of the service provider, and the historical estimation deviation information of the service area corresponding to the target order.
[0118] The input module 403 is used to input the target information into the pre-trained model.
[0119] The correction module 404 is used to correct the initial estimation result using the data output by the above model to obtain the target estimation result.
[0120] like Figure 5 As shown, Figure 5 is another device block diagram for estimating time according to an exemplary embodiment of the present application. Figure 4 On the basis of the illustrated embodiment, the determination module 402 may include: a first determination submodule 501 .
[0121] Among them, the first determination submodule 501 is configured to: determine the first historical order data corresponding to the above-mentioned service provider within the first preset time period. Based on the first historical order data, determine the actual completion time and estimated completion time of each first historical trip in the multiple first historical trips involved in the first historical order data, and the estimated completion time is determined based on a preset rule. Determine the target ratio corresponding to each first historical trip, wherein the target ratio corresponding to any first historical trip is the ratio of the actual completion time to the estimated completion time of the first historical trip. According to the target ratio corresponding to each of the first historical trips, determine the personalization coefficient of the service provider.
[0122] In some optional implementations, the personalization coefficient of the service provider may be determined using the following formula:
[0123]
[0124]
[0125] Where A represents the personalized coefficient of the service provider; N is a positive integer, representing the number of days corresponding to the first preset period; T is a positive integer, α T represents the average target ratio corresponding to the Tth day in the first preset period; M T is a positive integer, indicating the number of times the service provider completed the first historical trip on the Tth day of the first preset period; β i T It represents the target ratio corresponding to the i-th first historical trip completed by the service provider on the T-th day of the first preset period.
[0126] like Figure 6 As shown, Figure 6 is another device block diagram for estimating time according to an exemplary embodiment of the present application. Figure 4 On the basis of the illustrated embodiment, the determination module 402 may include: a second determination submodule 502 .
[0127] The second determination submodule 502 is configured to: if it is determined that the cumulative service duration corresponding to the service provider is less than or equal to the preset threshold, determine the pre-specified quantity as the maximum order holding quantity of the service provider. If it is determined that the cumulative service duration corresponding to the service provider is greater than the preset threshold, determine the number of orders completed by the service provider, and determine the preset number corresponding to the number of completed orders as the maximum order holding quantity of the service provider.
[0128] like Figure 7 As shown, Figure 7 is another device block diagram for estimating time according to an exemplary embodiment of the present application. Figure 4On the basis of the illustrated embodiment, the determination module 402 may include: a third determination submodule 503 .
[0129] Among them, the third determination submodule 503 is configured to be configured to: determine the second historical order data corresponding to the service area in the second preset time period. Based on the second historical order data, determine the actual completion time and estimated completion time of multiple second historical trips involved in the second historical order data and each second historical trip, and the estimated completion time is determined based on the preset rule. Determine the estimated deviation corresponding to each second historical trip, wherein the estimated deviation corresponding to any second historical trip is the difference between the actual completion time and the estimated completion time of the second historical trip. According to the estimated deviation corresponding to each second historical trip, determine the above-mentioned historical estimated deviation information.
[0130] In other optional implementations, the above-mentioned historical estimation deviation information may include: average deviation and average absolute deviation.
[0131] The average deviation can be determined by the following formula:
[0132]
[0133] The mean absolute deviation can be determined by the following formula:
[0134]
[0135] Wherein, ME represents the above average deviation; MAE represents the above average absolute deviation; n is a positive integer, which represents the number of second historical trips involved in the orders generated in the above service area within the second preset time period; j is a positive integer, Δ j It represents the estimated deviation corresponding to the j-th second historical trip involved in the orders generated in the above service area within the second preset time period.
[0136] In other optional embodiments, the target information may also include one or more of the following: the dispatch time corresponding to the target order; the consumption amount corresponding to the target order; the distance of the trip corresponding to the target order; the estimated completion time of the target order trip based on preset rules; the order receiving time corresponding to the target order; the dispatch attribute of the target order, which can be a direct dispatch attribute (if the target order is a directly dispatched order, it belongs to the direct dispatch attribute) or a re-dispatch attribute (if the target order is a re-dispatched order, it belongs to the re-dispatch attribute); the order generation volume of the service area corresponding to the target order within a preset historical period; the estimated order generation volume of the service area corresponding to the target order in the current time slice; the estimated per capita load of orders in the service area corresponding to the target order in the current time slice (such as the average number of orders received by each delivery person); the average estimated time for completion of the order trip in the service area corresponding to the target order in the current time slice.
[0137] It should be understood that the above device can be pre-set in the terminal device or server, or loaded into the terminal device or server by downloading, etc. The corresponding modules in the above device can cooperate with the modules in the terminal device or server to implement the solution for estimating time.
[0138] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.
[0139] The present application also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figures 1 to 3 Any embodiment provides a method for estimating time.
[0140] Corresponding to the above-mentioned method for estimating time, the present application embodiment also proposes Figure 8 The schematic structural diagram of an electronic device according to an exemplary embodiment of the present application is shown in FIG. Figure 8At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for estimating time at the logical level. Of course, in addition to software implementations, this application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0141] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0142] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for estimating time, characterized in that The method comprises: Use the preset rules to estimate the completion time of the trip corresponding to the target order and obtain an initial estimation result; Determine target information corresponding to the target order, the target information including a personalized coefficient of a service provider corresponding to the target order, a maximum order holding quantity of the service provider, and historical estimation deviation information of a service area corresponding to the target order; Inputting the target information into a pre-trained model; Correcting the initial estimation result using the data output by the model to obtain a target estimation result; The personalization coefficient of the service provider corresponding to the target order is determined in the following manner: Determining first historical order data corresponding to the service provider within a first preset time period; Based on the first historical order data, determining an actual completion time and an estimated completion time of each first historical trip in a plurality of first historical trips involved in the first historical order data, wherein the estimated completion time is determined based on the preset rule; Determine a target ratio corresponding to each of the first historical trips, wherein the target ratio corresponding to any first historical trip is a ratio of an actual completion time to an estimated completion time of the first historical trip; determining a personalized coefficient of the service provider according to a target ratio corresponding to each of the first historical trips; The maximum order holding quantity of the service provider is determined as follows: If it is determined that the accumulated service time corresponding to the service provider is less than or equal to the preset threshold, the pre-specified quantity is determined as the maximum order holding quantity of the service provider; If it is determined that the accumulated service time corresponding to the service provider is greater than a preset threshold, the number of orders completed by the service provider is determined, and the preset number corresponding to the number of completed orders is determined as the maximum order holding quantity of the service provider; The historical estimation deviation information of the service area corresponding to the target order is determined in the following manner: Determine second historical order data corresponding to the service area in a second preset time period; Based on the second historical order data, determining a plurality of second historical trips involved in the second historical order data and actual completion times and estimated completion times of each second historical trip, wherein the estimated completion time is determined based on the preset rule; Determine an estimated deviation corresponding to each of the second historical trips, wherein the estimated deviation corresponding to any second historical trip is a difference between an actual completion time and an estimated completion time of the second historical trip; The historical estimated deviation information is determined according to the estimated deviation corresponding to each of the second historical trips.
2. The method according to claim 1, characterized in that The personalization coefficient of the service provider is determined using the following formula: Wherein, A represents the personalization coefficient of the service provider; N is a positive integer, representing the number of days corresponding to the first preset period; T is a positive integer, α T represents the average target ratio corresponding to the Tth day in the first preset period; M T is a positive integer, indicating the number of times the service provider completed the first historical trip on the Tth day of the first preset period; β i T It represents the target ratio corresponding to the i-th first historical trip completed by the service provider on the T-th day of the first preset period.
3. The method according to claim 1, characterized in that The historical estimation deviation information includes: average deviation and average absolute deviation; The average deviation is determined by the following formula: The mean absolute deviation is determined by the following formula: Wherein, ME represents the mean deviation; MAE represents the mean absolute deviation; n is a positive integer, representing the number of second historical trips involved in the orders generated in the service area within the second preset time period; j is a positive integer, Δ j It represents the estimated deviation corresponding to the j-th second historical trip involved in the orders generated in the service area within the second preset time period.
4. The method according to any one of claims 1 to 3, characterized in that: The target information may also include one or more of the following: The dispatching time corresponding to the target order; The consumption amount corresponding to the target order; The distance of the trip corresponding to the target order; The estimated completion time of the target order based on the preset rule; The order acceptance time corresponding to the target order; The dispatch attribute of the target order, wherein the dispatch attribute includes a direct dispatch attribute and a re-dispatch attribute; The order generation volume of the service area corresponding to the target order within a preset historical period; An estimated generation volume of orders in the service area corresponding to the target order within the current time slice; The estimated per capita load of orders in the service area corresponding to the target order in the current time slice; The average estimated time when the order trips in the service area corresponding to the target order are completed within the current time slice.
5. A device for estimating time, characterized in that: The device comprises: An estimation module, used to estimate the completion time of the trip corresponding to the target order using preset rules to obtain an initial estimation result; a determination module, configured to determine target information corresponding to the target order, wherein the target information includes a personalized coefficient of a service provider corresponding to the target order, a maximum order holding quantity of the service provider, and historical estimation deviation information of a service area corresponding to the target order; An input module, used for inputting the target information into a pre-trained model; A correction module, used to correct the initial estimation result using the data output by the model to obtain a target estimation result; The personalization coefficient of the service provider corresponding to the target order is determined in the following manner: Determining first historical order data corresponding to the service provider within a first preset time period; Based on the first historical order data, determining an actual completion time and an estimated completion time of each first historical trip in a plurality of first historical trips involved in the first historical order data, wherein the estimated completion time is determined based on the preset rule; Determine a target ratio corresponding to each of the first historical trips, wherein the target ratio corresponding to any first historical trip is a ratio of an actual completion time to an estimated completion time of the first historical trip; determining a personalized coefficient of the service provider according to a target ratio corresponding to each of the first historical trips; The maximum order holding quantity of the service provider is determined as follows: If it is determined that the accumulated service time corresponding to the service provider is less than or equal to the preset threshold, the pre-specified quantity is determined as the maximum order holding quantity of the service provider; If it is determined that the cumulative service time corresponding to the service provider is greater than a preset threshold, the number of orders completed by the service provider is determined, and the preset number corresponding to the number of completed orders is determined as the maximum order holding of the service provider. The historical estimation deviation information of the service area corresponding to the target order is determined in the following manner: Determine second historical order data corresponding to the service area in a second preset time period; Based on the second historical order data, determining a plurality of second historical trips involved in the second historical order data and actual completion times and estimated completion times of each second historical trip, wherein the estimated completion time is determined based on the preset rule; Determine an estimated deviation corresponding to each of the second historical trips, wherein the estimated deviation corresponding to any second historical trip is a difference between an actual completion time and an estimated completion time of the second historical trip; The historical estimated deviation information is determined according to the estimated deviation corresponding to each of the second historical trips.
6. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.