Order receiving area determination method and device and storage medium

Abstract

The embodiment of the invention provides an order receiving area determination method and device, and a storage medium. The method comprises the steps of obtaining multiple pieces of historical order data of each area in a target city for a target service; according to the historical order data corresponding to each region, the preference information corresponding to the potential user set and the time information of the future time period, predicting the total order amount of the target service corresponding to each region in the future time period; determining a target service account corresponding to the target service and a target service level of the target service account; determining the target order quantity of the target service account corresponding to each region according to the total order quantity of the target service corresponding to each region, the target service level and the available order quantity of the target service corresponding to different service levels in each region; and according to the target order quantity of each region corresponding to the target service account, determining an order receiving area of the target service account, so as to allocate orders for the client logged in with the target service account according to the order receiving area, and completing scheduling in advance.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device and storage medium for determining an order receiving area. Background Art

[0002] In recent years, with the accelerating pace of life, the demand for domestic services has also been growing. More and more people choose to make appointments for domestic services on weekends or in their spare time. For example, users can use applications to raise various domestic needs. For each need raised by the user, the APP will generate an order. The order allocation system will assign a domestic service staff to this order in real time based on the service address, service time, and service staff rating, location, skills, and availability entered by the user. The domestic service staff will provide domestic services to the user. However, this order allocation method is mainly affected by the restrictions of the order-taking area. When orders surge during peak demand periods, service staff in area A may be idle and waiting, while service staff in area B are busy and overloaded, causing customers in area B to wait for service for a long time.

[0003] Therefore, how to accurately determine the order-taking area corresponding to the service personnel becomes a technical problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present invention provide a method, device and storage medium for determining an order receiving area, so as to accurately determine the order receiving area of ​​a service personnel in a future time period, so as to complete the personnel scheduling.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining an order receiving area, comprising:

[0006] In response to an order volume prediction request for a target service, obtaining a plurality of historical order data for the target service in various regions within a target city;

[0007] Predicting a potential user set in each region based on the order user feature data in the plurality of historical order data;

[0008] Predicting the total order volume of the target service in each region in the future time period based on the multiple historical order data corresponding to each region, the preference information corresponding to the potential user set, and the time information of the future time period;

[0009] Determine a target service account corresponding to the target service and a target service level corresponding to the target service account, different service personnel have different service accounts, and the target service account belongs to the target city;

[0010] Determine the target order volume corresponding to the target service account in each region according to the total order volume corresponding to the target service in each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region;

[0011] According to the target order volume corresponding to the target service account in each region, the order receiving area corresponding to the target service account is determined, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0012] In a second aspect, an embodiment of the present invention provides a device for determining an order receiving area, the device comprising:

[0013] An acquisition module, configured to respond to an order volume prediction request for a target service and acquire a plurality of historical order data for the target service from various regions in a target city;

[0014] A first prediction module, configured to predict a potential user set in each region based on the order user feature data in the plurality of historical order data;

[0015] A second prediction module is used to predict the total order volume of the target service in each region in a future time period according to a plurality of historical order data corresponding to each region, preference information corresponding to the potential user set, and time information of a future time period;

[0016] A first determination module is used to determine a target service account corresponding to the target service and a target service level corresponding to the target service account. Different service personnel have different service accounts, and the target service account belongs to the target city.

[0017] A second determination module is used to determine the target order volume corresponding to the target service account in each region according to the total order volume corresponding to the target service in each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region;

[0018] The third determination module is used to determine the order receiving area corresponding to the target service account according to the target order volume corresponding to the target service account in each region, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0019] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the order receiving area determination method in the first aspect. The electronic device may also include a communication interface for communicating with other devices or communication systems.

[0020] In a fourth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the method for determining an order receiving area as described in the first aspect above.

[0021] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the processor is enabled to implement the method for determining an order receiving area as described in the first aspect above.

[0022] In the method for determining the order receiving area provided by the embodiment of the present invention, when predicting the order receiving area for each service personnel in the target city, first, in response to the order quantity prediction request for the target service, multiple historical order data of the target service in each region of the target city are obtained. Then, according to the order user feature data in the multiple historical order data, the potential user set of each region is predicted. And according to the multiple historical order data corresponding to each region, the preference information corresponding to the potential user set and the time information of the future time period, the total order volume of the target service corresponding to each region in the future time period is predicted. Next, the target service account corresponding to the target service and the target service level corresponding to the target service account are determined. Among them, different service personnel correspond to different service accounts, and the target service account belongs to the target city. Then, according to the total order volume corresponding to the target service in each region, the target service level and the total order volume corresponding to the target service of different service levels in each region, the target order volume corresponding to the target service account in each region is determined. Finally, according to the target order volume corresponding to the target service account in each region, the order receiving area corresponding to the target service account is determined, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0023] In the above scheme, the order user characteristic data in the historical order data corresponding to the target service in each region is analyzed to identify the potential user set in each region, and the order demand corresponding to each region is determined in combination with the historical order data corresponding to each region, the potential user's preference information for the target service and the time information of the future time period, so as to accurately predict the total order volume corresponding to each region in the future time period, and then determine the target order volume corresponding to the target service account in each region according to the predicted total order volume corresponding to each region, the target service level corresponding to the target service account and the total number of orders that can be received for the target service at different service levels in each region, and then determine the order receiving area corresponding to the target service account, so as to adjust the order receiving area corresponding to the service personnel, complete the scheduling in advance, and avoid situations such as no order allocation or order congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A flowchart of a method for determining an order receiving area provided by an embodiment of the present invention;

[0026] Figure 2 A flow chart of determining the target order volume corresponding to the target service account in each region provided by an embodiment of the present invention;

[0027] Figure 3 A flowchart is provided for the implementation of the present invention to determine the order receiving area corresponding to the target service account according to the target order volume corresponding to the target service account in each area;

[0028] Figure 4 A schematic diagram of a user interaction interface provided by an embodiment of the present invention;

[0029] Figure 5 A schematic diagram of an application of an order system provided by an embodiment of the present invention;

[0030] Figure 6 A schematic diagram of the structure of a device for determining an order receiving area provided by an embodiment of the present invention;

[0031] Figure 7 For Figure 6 A schematic diagram of the structure of an electronic device corresponding to the order receiving area determination device provided in the illustrated embodiment. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0034] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the case where there is no conflict between the embodiments, the following embodiments and the features and steps in the embodiments can be combined with each other. In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0035] Figure 1 A flowchart of a method for determining an order receiving area provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the execution subject corresponding to the method may be an order receiving area determination device, which may be applied to a server. Specifically, the method includes the following steps:

[0036] 101. In response to an order volume prediction request for a target service, obtain a plurality of historical order data for the target service in various regions within a target city.

[0037] 102. Predict the potential user set in each region based on order user feature data in multiple historical order data.

[0038] 103. Predict the total number of orders for the target service in each region in the future time period based on multiple historical order data corresponding to each region, preference information corresponding to the potential user set, and time information of the future time period.

[0039] 104. Determine a target service account corresponding to the target service and a target service level corresponding to the target service account. Different service personnel have different service accounts. The target service account belongs to the target city.

[0040] 105. Determine the target order volume corresponding to the target service account in each region based on the total order volume of the target service corresponding to each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region.

[0041] 106. Determine the order receiving area corresponding to the target service account according to the target order volume corresponding to the target service account in each region, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0042] The method for determining the order receiving area provided in the embodiment of the present invention can be used to predict the order receiving areas of service personnel corresponding to target services in various regions in the future time period, so as to complete the dispatch of service personnel in advance and avoid the problem of uneven dispatch of personnel caused by a sudden increase in orders in a certain region. For example, the order receiving areas corresponding to each service personnel corresponding to the cleaning service and the order receiving areas corresponding to each service personnel corresponding to the cooking service in various regions in the next day are predicted.

[0043] In specific implementation, in response to an order volume prediction request for a target service, historical order data corresponding to the target service in each region of the target city can be obtained. The order volume prediction request can be initiated by an order dispatcher or a target service account corresponding to the target service. The target city can be any city corresponding to any country. The target service can be a cleaning service, a car service, a moving service, etc. The historical order data includes the order volume, order type, service time, service score, service completion status, etc. in each region within a certain period of time in the past.

[0044] Since the prediction of order volume is affected by time information, for example, Saturday to Sunday is a rest period, and most users will choose to book cleaning services on Saturday or Sunday. Therefore, in order to make the predicted total order volume closer to the actual situation, when obtaining historical order data, it is preferred to obtain historical order data corresponding to the future time period to be predicted. For example, if you want to predict the order volume for the next day, and the next day is Tuesday, you can obtain the historical order data corresponding to Tuesday in the past six months.

[0045] After obtaining the historical order data, the order user feature data in the historical order data can be analyzed to predict the potential user sets corresponding to each region. In this way, the potential order demand in each region can be more accurately analyzed based on the potential user sets in each region, so as to improve the accuracy of the prediction results of the total target service orders in each region in the future time period.

[0046] Regarding the specific implementation method of determining the potential user set corresponding to each region, in an optional embodiment, the historical user set corresponding to each region may be determined based on the historical order data, and then the potential user set corresponding to each region may be determined based on the order user feature data in the historical user set corresponding to each region by using association rule analysis.

[0047] The historical user set refers to the set of users who have been served in the past, the set of users who have booked the target service in the past but have not completed the corresponding service, the set of users who have consulted about the corresponding service in the past but have not immediately placed an order, etc. The potential user set refers to the set of users who have potential demand for the target service.

[0048] When determining the potential user sets corresponding to each region, the association relationship between the historical user set and the order demand can be determined through association rule analysis, and then the potential user sets corresponding to each region can be identified based on the association relationship. By identifying the potential user sets corresponding to each region, it is possible to clearly understand which groups of people in each region have a demand for the target service. In the specific implementation, the Apriori algorithm, FP-Growth algorithm, etc. can be used for association rule analysis.

[0049] In another optional embodiment, a pre-trained customer identification model may be used to analyze the historical user sets corresponding to each region to determine the potential user sets corresponding to each region.

[0050] After determining the potential user sets corresponding to each region, the preference information corresponding to the potential user sets in each region is determined. The preference information may include the preference of the user set for a specific service when faced with multiple service options, and the demand characteristics of the user cluster for the target service in different occasions and aspects. For example, the demand information corresponding to customer A is that the user tends to book housekeeping services on weekends or seek cleaning services on holidays.

[0051] It can be seen that preference information reflects the characteristics of customer needs and embodies the personalized needs of customers. When making order predictions, combining the preference information of potential users can better predict whether potential users are likely to book the target service in the future time period.

[0052] The target customer category corresponding to the target area can be determined by classifying the potential user set corresponding to the target area, where the target area is any one of multiple areas in the target city. According to the target customer category, the preference information of each potential user in the potential user set of the target area for the target service is determined. The potential user set corresponding to the target area can be classified by using methods such as cluster analysis to obtain at least one corresponding target customer category.

[0053] Then, based on the historical order data corresponding to each region, the preference information of each potential user in the potential user set corresponding to each region, and the time information of the future time period, the total order volume corresponding to the target service in each region in the future time period is predicted.

[0054] Among them, the historical order volume, the preference information of the potential user set, the time information corresponding to the future time period to be predicted, the geographical location information, etc. will directly affect the predicted order volume. Therefore, when predicting the order volume corresponding to the target service in each region, we first determine the degree of influence of the historical order volume on the order volume in the future time period, the correspondence between the user's preference information and the order volume, and the degree of influence of the time information and geographical location on the order volume in the future time period. In this way, based on the degree of influence of the historical order volume on the order volume in the future time period, the correspondence between the potential user's preference information and the order volume, and the degree of influence of the time information and geographical location on the order volume in the future time period, the historical order data corresponding to each region currently obtained, the preference information of each potential user in the potential user set corresponding to each region, and the time information of the future time period can be analyzed to determine the total order volume corresponding to the target service in each region in the future time period.

[0055] In order to more accurately determine the impact of historical order volume, time information and geographic location on the order volume in future time periods, the corresponding relationship between the preference information of each potential user and the order volume, etc., a machine learning model can be used to determine the impact of historical order volume, time information and geographic location on the order volume in future time periods, and the corresponding relationship between the preference information of each potential user and the order volume.

[0056] Specifically, the historical order data, preference information, and time information of future time periods corresponding to each region are input into a pre-trained order volume prediction model, and the order volume prediction model is used to analyze the historical order data, preference information, and time information of future time periods corresponding to each region to predict the total order volume corresponding to each region in the future time period. The order volume prediction model is used to learn the mapping relationship between time information, geographic location information, and user preference information and service requirements.

[0057] When predicting the order volume corresponding to the target service in each region, the historical order volume, the influence of time information and geographical location on the order volume in the future time period, and the correspondence between the preference information of potential users and the order volume are taken into consideration to predict the order volume. This can make the predicted order volume more accurate, and then, based on the predicted order volume, each service personnel can be helped to set the intended order-taking area, so that service personnel can be deployed in advance to the order-taking areas with higher demand, and can respond to the scheduling of orders in a timely manner.

[0058] In addition, in actual applications, it is found that the performance of service personnel during the service process will also directly affect the prediction of the order volume. In an optional embodiment, the total order volume can also be predicted in combination with the corresponding relationship between the performance of service personnel and the order volume. Specifically, the service data corresponding to multiple service personnel of the target service in the target city is obtained, and the service data is used to reflect the overall quality and ability level shown by the service personnel in the service work. Using the pre-trained order volume prediction model, the historical order data, preference information, time information of the future time period and service data corresponding to multiple service personnel of the target service corresponding to each region are analyzed to predict the total order volume corresponding to each region in the future time period. Among them, the order volume prediction model here is used to learn the mapping relationship between time information, geographic location information, service personnel performance, preference information of potential users and service needs.

[0059] In addition, the operational activities corresponding to the target service will also affect the prediction of the order volume. Therefore, the operational activities corresponding to the target service can also be combined to predict the total order volume corresponding to each region in the future time period.

[0060] Among them, with the continuous growth of the domestic service market, consumers' requirements for service quality and efficiency are constantly increasing. The current scheduling of domestic service personnel is mainly based on the service personnel's rating, geographical location, skills and availability to allocate orders. However, this method often fails to effectively utilize the potential of high-quality service personnel. At the same time, it may also be due to the geographical restrictions of the service personnel's permanent intended order-taking location, and the failure to consider the different characteristics of each potential user in each region, resulting in many high-quality service personnel receiving low orders, and the high service demand outside this area cannot be met.

[0061] For example, during peak demand periods, the number of orders in area B often surges, making the service personnel in area B busy and overloaded, while the service personnel in area A may be idle and waiting, causing customers in area B to wait for a long time for service. If there are not enough local service personnel, they need to be deployed from other areas, which increases the non-working time cost of the service personnel.

[0062] Therefore, after predicting the total number of orders for the target service in each region in the future time period, the order-taking areas corresponding to each target service personnel corresponding to the target service are predicted based on the total number of orders for the target service in each region. This allows service personnel to be dispatched in advance to avoid the problem of insufficient dynamic scheduling capabilities during peak demand periods.

[0063] Specifically, the target service account corresponding to the target service and the target service level corresponding to the target service account are determined. Different service personnel have different service accounts, and the target service account belongs to the target city and is a service account held by any service personnel corresponding to the target service.

[0064] Next, the target order volume corresponding to the target service account in each region is determined based on the total number of orders for the target service in each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region. Then, based on the target order volume corresponding to the target service account in each region, the order receiving area corresponding to the target service account is determined, so that orders are allocated to the client logged in with the target service account according to the order receiving area.

[0065] Among them, when determining the order-taking areas corresponding to the service accounts held by each service personnel, the service accounts can be divided into service gradients according to the service scores corresponding to each service account. Then, in order from high to low service gradient levels, the order-taking areas corresponding to each service account at each service gradient level are determined in sequence. In addition, when determining the order-taking areas of the service accounts corresponding to the service personnel at each service gradient level, the total number of orders that can be received by the service accounts at the high service gradient level in each region corresponding to the target service can be combined to determine in which area each service account at the low service gradient level is more likely to obtain more orders, and the order-taking areas that are more likely to obtain more orders are determined as the order-taking areas corresponding to each service account. In this way, the predicted order-taking areas will not affect the order-taking situation of high-quality service personnel, and can also ensure the service quality of the orders.

[0066] In summary, the order user feature data in the historical order data corresponding to the target service in each region is analyzed to identify the potential user set in each region, and the order demand corresponding to each region is determined by combining the historical order data corresponding to each region, the potential user's preference information for the target service and the time information of the future time period, so as to accurately predict the total order volume corresponding to each region in the future time period, and then determine the target order volume corresponding to the target service account in each region according to the predicted total order volume corresponding to each region, the target service level corresponding to the target service account and the total number of orders that can be received for the target service at different service levels in each region, and then determine the order receiving area corresponding to the target service account, so as to adjust the order receiving area corresponding to the service personnel, complete the scheduling in advance, and avoid situations such as no order allocation or order congestion.

[0067] The specific implementation process of determining the target order volume corresponding to the target service account in each region is described in detail in conjunction with the following embodiments.

[0068] Figure 2 A flow chart of determining the target order volume corresponding to the target service account in each region provided by an embodiment of the present invention; Figure 2 As shown, the method may specifically include the following steps:

[0069] 201. In order of service gradient levels from high to low, obtain in sequence the total number of orders for the target service in each region for each service gradient level higher than the target service gradient level, and the total number of orders that can be received for the target service in each region for each service gradient level higher than the target service gradient level.

[0070] 202. Determine the target order volume for each region corresponding to the target service account based on the total order volume of the target service corresponding to each region, the order volume of each service gradient level higher than the target service gradient level corresponding to the target service in each region, and the total number of orders that can be received for each service gradient level higher than the target service gradient level corresponding to the target service in each region.

[0071] Among them, in order to dispatch multiple service personnel to the service demand area faster and better, complete orders with high quality, and improve customer satisfaction with the services provided, in an embodiment of the present invention, the target order volume corresponding to each service personnel in each region in the future time period can be predicted in turn according to the service capabilities corresponding to each service personnel.

[0072] Specifically, first, multiple service accounts that can provide the target service in the target city are obtained, and the multiple service accounts of the target service in the target city are classified into service levels to determine the service gradient levels corresponding to each of the multiple service accounts.

[0073] When classifying the service levels of all service accounts that can provide the target service, the multiple service accounts corresponding to the target service can be classified into service gradient levels according to the order-taking behavior score, fulfillment behavior score, service feedback score, abnormal behavior score, and category service score corresponding to each service account.

[0074] After determining the service gradient levels corresponding to multiple service personnel, the target order volumes corresponding to multiple service personnel at each service gradient level in each region are determined in turn according to the service gradient levels, based on the order volumes corresponding to the target services in each region in the future time period and the available order volumes corresponding to multiple service personnel at each service gradient level.

[0075] Among them, in order to avoid the impact of the order acceptance situation of low-quality service personnel on the order acceptance situation of high-quality service personnel when predicting the target order volume of service accounts at each service gradient level corresponding to each region, that is, the impact of the order volume corresponding to service accounts with low service gradient levels on the order volume corresponding to service accounts with high service gradient levels in the future time period, the order volume corresponding to multiple service accounts with different service gradient levels in each region can be determined in sequence according to the level of service gradient levels. In other words, the order volume corresponding to multiple service accounts at the previous service gradient level will determine the target order volume corresponding to multiple service accounts at the current service gradient level in each region. Then in actual applications, the target order volume corresponding to each service account in each region can be determined in sequence according to the order of service gradient levels.

[0076] Among them, in the specific implementation, the specific implementation process of determining the target order volume corresponding to each service account in each region is roughly the same. Here, taking the target service account as an example, the specific implementation process of determining the target order volume corresponding to each region is described in detail.

[0077] First, in order of service gradient levels from high to low, obtain in turn the total number of orders for the target service in each region for each service gradient level higher than the target service gradient level, as well as the total number of orders that can be received for the target service in each region for each service gradient level higher than the target service gradient level.

[0078] In an optional embodiment, the specific implementation process of sequentially obtaining the total order volume of the target service corresponding to each service gradient level in each region at each service gradient level higher than the target service gradient level may include: for the first service gradient level, determining the number of orders that can be accepted in each region for all service accounts in the second service gradient level, the first service gradient level being any one of the service gradient levels higher than the target service gradient, and the second service gradient level being the service gradient level immediately preceding the first service gradient level. Based on the number of orders that can be accepted in each region for all service accounts in the second service gradient level, determine the total number of orders that can be accepted in each region for the second service gradient level. The difference between the total number of orders for the target service corresponding to the second service gradient level in each region and the total number of orders that can be accepted for the second service gradient level in each region is determined as the total number of orders for the target service corresponding to the first service gradient level in each region.

[0079] Among them, when determining the number of orders that can be accepted in each region for all service accounts in the second service gradient level, the intended order-receiving area corresponding to each service account in the second service gradient level can be determined first. And the order-receiving capacity value of each service account in the second service gradient level in the future time period can be determined. Then, based on the intended order-receiving area corresponding to each service account in the second service gradient level and the order-receiving capacity value of each service account in the second service gradient level in the future time period, the number of orders that can be accepted in each region for each service account in the second service gradient level is determined.

[0080] Regarding the specific implementation method of determining the intended order receiving area corresponding to each service account of the second service gradient level, in an optional embodiment, for the service account to be evaluated, based on the order volume corresponding to the service account to be evaluated in each region in the future time period and the common order receiving area corresponding to the service account to be evaluated, the intended order receiving area corresponding to the service account to be evaluated is determined; or the order receiving area set by the service account to be evaluated in the order receiving area interface is determined as the intended order receiving area corresponding to the service account to be evaluated. The service account to be evaluated is any one of the multiple service accounts at the second service gradient level.

[0081] Among them, the order-taking capacity value is used to represent the order-taking capacity of the service personnel corresponding to the service account. Then, the order-taking capacity value of each service account of the second service gradient level in the future time period can be determined based on the historical order-taking situation of each service account of the second service gradient level. In order to more accurately determine the order-taking capacity value of each service account in the future time period, the order-taking energy value of each service account of the second service gradient in the future time period can be determined by obtaining the historical order volume in the same time period as the future time period or the historical order volume of the same time information.

[0082] The target order volume of the target service corresponding to each service gradient level in each region and the total number of orders that can be received for the target service corresponding to each service gradient level in each region can be determined in sequence in the above manner, which will not be elaborated herein.

[0083] After determining in turn the total number of orders for the target service in each region corresponding to each service gradient level higher than the target service gradient and the total number of orders that can be accepted for the target service in each region corresponding to each service gradient level higher than the target service gradient level, then, determine the target order volume for the target service account corresponding to each region based on the total number of orders for the target service in each region, the number of orders for the target service in each region corresponding to each service gradient level higher than the target service gradient level, and the total number of orders that can be accepted for the target service in each region corresponding to each service gradient level higher than the target service gradient level.

[0084] For example, assuming that the target service gradient corresponding to the target service account is at the third service gradient level, there are 50 service accounts at the third service gradient level, and the predicted total order volume corresponding to region A on the next day is 800, the total order volume corresponding to the target service of the first service gradient level in region A is 800, the total number of orders that can be accepted for the target service of the first service gradient level in region A is 200, the total number of orders corresponding to the target service of the second service gradient level in region A is 600, and the total number of orders that can be accepted for the target service of the second service gradient level in region A is 150. Then, it can be determined that the total order volume corresponding to region A of the third service gradient level is 450, and the target order volume corresponding to region A for the target service account is 9 orders.

[0085] In summary, the embodiment of the present invention obtains the total number of orders for the target service corresponding to each service gradient level higher than the target service gradient level in each region, and the total number of orders that can be received for each service gradient level higher than the target service gradient level in each region, in order from high to low service gradient levels. The target order volume for each region corresponding to the target service account is determined based on the total number of orders for the target service corresponding to each region, the order volume for each service gradient level higher than the target service gradient level in each region corresponding to the target service, and the total number of orders that can be received for each service gradient level higher than the target service gradient level in each region. In this way, the target order volume for each region corresponding to the target service account can be accurately determined, so that the predicted order-receiving area will not affect the order-receiving situation of high-quality service personnel, and the service quality of the order can also be guaranteed.

[0086] After determining the target order volume corresponding to each region of the target service account, then, according to the target order volume corresponding to each region of the target service account, determine the order receiving area corresponding to the target service account. In an optional embodiment, after determining the target order volume corresponding to each region of the target service account, combine the intended order receiving area set by the client logged in with the target service account to determine the order receiving area corresponding to each region of the target service account. This process is described in detail in conjunction with the following embodiments.

[0087] Figure 3 A flowchart is provided for the implementation of the present invention to determine the order receiving area corresponding to the target service account according to the target order volume corresponding to the target service account in each region; Figure 3 As shown, the method may specifically include the following steps:

[0088] 301. In response to an order quantity prediction request sent by a client, determine a target service account corresponding to the client.

[0089] 302. Send the predicted target order volume corresponding to the target service account in each region to the client, so that the client sets an order receiving area based on the target order volume corresponding to each region.

[0090] 303. In response to the order receiving area setting operation triggered by the client, determine the order receiving area corresponding to the target service account.

[0091] In actual applications, it is also possible to help each service personnel set their intended order-taking area based on the target order volume corresponding to each region. In this way, when allocating orders, service personnel can be dispatched to areas with more orders in advance to avoid order allocation or order congestion.

[0092] In specific implementation, service personnel can be allowed to set corresponding intended order-taking areas in order of service gradient levels, and then determine the order-taking areas corresponding to multiple service accounts of each service gradient level according to the intended order-taking areas set by the service personnel. The following takes the target service personnel based on the target service account as an example to illustrate the specific implementation process of setting the intended order-taking area.

[0093] Among them, the target service personnel can set the order receiving area corresponding to the target service account based on the predicted target order volume corresponding to the target service account in each region in the future time period. Specifically, the target service personnel can first use the client to send an order volume prediction request to the server. The server determines the target service account corresponding to the client in response to the order volume prediction request sent by the client. The predicted target order volume corresponding to the target service account in each region is sent to the client, so that the client sets the intended order receiving area based on the target order volume corresponding to the target service account in each region. In response to the order receiving area setting operation triggered by the client, the order receiving area corresponding to the target service account is determined.

[0094] Through the above method, the target service personnel can be made to obtain more orders more easily in that area within the predicted future time period. By setting the order receiving area corresponding to the target service account, the order receiving area corresponding to the target service personnel can be adjusted in advance to avoid situations such as no order allocation or order congestion.

[0095] Among them, in response to the order area setting operation triggered by the client, the specific implementation method of determining the order area corresponding to the target service account is: obtaining the intended order area entered by the client in the order management interface, and determining the intended order area entered by the client as the intended order area corresponding to the target service account. It should be noted that: when the client enters the intended order area in the future time period in the order management interface, the target order volume corresponding to each region in the future time period of the target service account has been predicted. The target service account can obtain the order volume corresponding to each region in the future time period of the target service account in the order management interface by triggering the order volume prediction request. In this way, the target service account can set the intended order area in the future time period in the order management interface through the predicted target order volume corresponding to each region in the future time period. The intended order area set in this way can enable the target service account to receive more order allocations in the future.

[0096] Among them, combined with Figure 4 The interactive diagram shown illustrates the implementation process of the intended order receiving area input by the target service account in the order receiving management interface. The client sends a request for obtaining the order volume forecast for the future time period to the order receiving area determination device through the order receiving management interface. The order receiving area determination device responds to the order volume forecast request triggered by the client through the order receiving management interface, and obtains the target order volume corresponding to each region in the future time period for the target service account. The target order volume corresponding to each region in the future time period is displayed in the order receiving management interface. In response to the intended order receiving area input by the client in the order receiving management interface, the input intended order receiving area is displayed in the input box corresponding to the intended order receiving area in the order receiving management interface, and the control is grayed out, that is, the client can no longer set the intended order receiving area in the future time period.

[0097] In order to facilitate the understanding of the above implementation process, it is explained in combination with specific application scenarios. For example, service personnel are divided into service gradient levels according to the following scoring levels: 100 points, 95 to 100 points, 90 to 95 points, 85 to 90 points, 80 to 85 points, and 70 to 80 points. Service personnel with a score below 70 points need to receive retraining to improve service quality, and can only obtain the prediction function of the order receiving area after the score is improved. Service personnel at a higher service gradient level can set the order receiving area in the order management interface first. For example, multiple service personnel with 100 points can set the next day's intended order receiving area in the order receiving management interface from 9:00 to 10:00. After the time is exceeded, they are locked and cannot be changed. If you need to change, you need to contact the customer service staff. Service personnel with 95-100 points can set the next day's intended order receiving area from 10:00 to 11:00, and so on, so that multiple service accounts at each service gradient level can set the next day's intended order receiving area respectively. The specific implementation process of the service personnel setting the intended order receiving area for the next day through the order receiving management interface is described above and will not be repeated here. This method of setting the intended order receiving area for each service personnel in sequence according to the service gradient level can ensure that the adjustment of the intended order receiving area set by the low-rated service personnel will not affect the order receiving rate of the high-rated service personnel. This can not only increase the order receiving rate of the high-rated service personnel, but also improve the service quality, thereby improving customer satisfaction.

[0098] Moreover, when the service accounts of each service gradient level set the intended order receiving area for the next day, the target order volume corresponding to the service account of the service gradient level in each region in the future time period has been predicted. For example, first, the historical order data, preference information, time information corresponding to the next day, and service data corresponding to multiple service accounts of the target service corresponding to each region are input into the order volume prediction model to predict the target order volume corresponding to each region on the next day. For multiple service personnel with 100 points, the target order volume corresponding to multiple service accounts with 100 points on the next day is determined according to the order volume corresponding to each region on the next day output by the order volume prediction model and the number of multiple service accounts at 100 points. After predicting the target order volume corresponding to multiple service accounts with 100 points in each region on the next day, multiple service accounts with 100 points can set the intended order receiving area for the next day in the order receiving management interface according to the predicted target order volume corresponding to each region on the next day, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0099] Next, predict the order volume corresponding to the service accounts with scores of 95-100 in each region the next day. For service accounts with scores of 95-100, determine the target order volume corresponding to each region the next day based on the target order volume corresponding to multiple service accounts with scores of 100 in each region the next day, the intended order-taking area set for each service account with scores of 100, and the number of orders that can be received by each service account with scores of 100. And so on, predict the target order volume corresponding to each service account of each service gradient in each region the next day. And based on the predicted target order volume corresponding to each service gradient service account in each region the next day, set the intended order-taking area corresponding to the next day, and determine the intended order-taking area as the order-taking area corresponding to each service account, and allocate orders to clients logged in with the service account based on the order-taking area.

[0100] In summary, the embodiment of the present invention determines the target order volume corresponding to multiple service accounts of each service gradient level in each region in accordance with the total order volume corresponding to the target service in each region in the future time period and the available order volume corresponding to multiple service accounts of each service gradient level in turn, and can deploy high-quality service personnel to areas with higher demand in advance, thereby improving the order acceptance rate of each excellent service personnel, ensuring that customers receive more satisfactory services.

[0101] The service level division mentioned in the above embodiment is described in detail in combination with the following embodiment for dividing the service levels of multiple service accounts of the target service.

[0102] Before classifying multiple service accounts into service levels, the order-taking behavior scores, contract-fulfilling behavior scores, service feedback scores, abnormal behavior scores, and category service scores corresponding to each of the multiple service accounts may be determined first.

[0103] Among them, the order acceptance behavior score is used to characterize the order acceptance and reassignment of the service account. Then, the order acceptance behavior score corresponding to each service account can be determined based on the order rejection rate and order reassignment rate of each service account in the first preset time (nearly 30 days, nearly half a year), the order rejection rate and order reassignment rate of each service account in the second preset time (nearly 7 days), and the order volume of each service account in the second preset time.

[0104] Among them, the performance score is mainly used to characterize the performance of the service account in fulfilling the order. The performance score corresponding to each service account can be determined based on the communication rate of each service account within the first preset time (the proportion of communication with customers before completing the order service), the check-in rate within the first preset time (the proportion of service personnel arriving at the service place and checking in on time before completing the order service), the on-time check-in rate within the first preset time (the proportion of checking in at the agreed time), the proportion of service personnel photos uploaded before completing the order service within the first preset time, the tool photo upload rate within the first preset time, the proportion of orders completed within the first preset time, and the proportion of photos uploaded after completing the order service within the first preset time.

[0105] The service feedback score is mainly used to represent the customer's evaluation and feedback on the service personnel. The service feedback score corresponding to each service account can be determined based on the number of positive reviews actively given by customers within the first preset time (the past 30 days and the past six months), the number of positive reviews given by the system by default, the number of medium reviews given by customers within the second preset time, the number of negative reviews given by customers, and the number of confirmed complaints and the number of interceptions by the system due to violations within the third preset time (the past 15 days).

[0106] The abnormal behavior score is mainly used to characterize the negative behavior of service personnel. The abnormal behavior score corresponding to each service account can be determined based on the proportion of order reassignments and the proportion of orders that were not fulfilled on time within the second preset time for each service account.

[0107] Category service points are mainly used to characterize the performance of service personnel in different service categories. The category service points corresponding to each service account can be determined based on the 30-day retention rate of new users, the 30-day retention rate of old users, the number of new users served, the number of old users served in the past 30 days, the new user retention rate in each city, and the old user retention rate in each city.

[0108] After determining the order-taking behavior scores, fulfillment behavior scores, service feedback scores, abnormal behavior scores and category service scores corresponding to each of the multiple service accounts, determine the service grade scores corresponding to each of the multiple service accounts based on the order-taking behavior scores, fulfillment behavior scores, service feedback scores, abnormal behavior scores and category service scores corresponding to each of the multiple service accounts, and compare the service grade scores corresponding to each of the multiple service accounts with the preset scores corresponding to each of the preset multiple service gradient grades to determine the service gradient grades corresponding to each of the multiple service accounts.

[0109] In addition, in practical applications, an embodiment of the present invention also provides an order allocation method. After predicting the corresponding order volumes in various regions within a future time period for service accounts of various service gradient levels, the predicted order volumes can be combined to carry out order allocation during actual order allocation.

[0110] Figure 5 A schematic diagram of an application of an order system provided by an embodiment of the present invention, such as Figure 5 As shown, the order system includes a data integration service module, an order prediction module, an order allocation module, and a service personnel work end management module.

[0111] Among them, the data integration service module mainly collects data and analyzes the collected data to explore the corresponding hidden relationships. Specifically, the data integration service module can collect real-time information corresponding to the service account in real time. Through real-time location tracking and activity records, the service personnel's service details, including start time, service time, and service personnel status information (stop accepting orders, exit order acceptance), are synchronized to ensure that all service data is updated to the data integration module in real time.

[0112] The data integration service module can collect customer feedback. The data integration service module can integrate the customer feedback system to automatically collect customer ratings and text feedback from the service app or through customer service follow-up visits. In addition, the data integration service module can also apply natural language processing (NLP) technology to extract key indicators of service quality reported by users (for example, service attitude, carefulness, work attitude, and work seriousness) to accurately evaluate the service performance of service personnel. Specifically, the collected customer text feedback generates processing instructions, and the customer text feedback and processing instructions are input into the large language model to extract key indicator information from the customer text feedback. Furthermore, based on the extracted key indicator information, the corresponding service quality score of the service personnel is determined.

[0113] The data integration module can also maintain a comprehensive historical service database, recording in detail the key information of each order, such as order category, service time, completion rate, rejection rate and cost, etc., to provide data support for service quality analysis and optimization.

[0114] After the data integration module collects various data, it can clean the collected data and analyze the data after cleaning to explore hidden relationships. Among them, the advanced data cleaning script based on Python uses Pandas and NumPy libraries to automatically correct data errors, remove duplicate records and handle outliers. Then, set up a periodic data verification flow program, use SQL and Python (tools for database management and data analysis) to ensure the consistency, completeness and accuracy of the data to support high-quality data analysis and decision making. Then, mine the data.

[0115] In the embodiment of the present invention, the data integration module is mainly used to mine the preference information of customers in different time periods, the corresponding relationship between the performance of service personnel and the order volume, etc. Specifically, the support vector machine (SVM) is applied to classify the service categories of service personnel according to the technical performance of the service personnel (for example, cooking, organizing and storing, babysitting, cleaning), and the Scikit-learn library is used for efficient model training and verification to distinguish service personnel of different service categories. Service personnel are classified according to service categories, and service personnel of the same service category are scored.

[0116] Using the K-means algorithm, we segmented the user set based on the customer's historical order data to obtain multiple customer categories, and used the SciPy library to identify the demand and preference information of different customer categories. We used the FP-growth algorithm to perform association analysis on large-scale data sets to quickly and effectively identify the potential user sets corresponding to each region.

[0117] In addition, the data integration module can also use Google BigQuery data warehouse technology to achieve big data storage and complex query operations, supporting data-driven decision making.

[0118] Through data mining, the features input into the order volume prediction model are obtained. In this way, the model can be trained and constructed based on the features obtained after data mining, and the trained order volume prediction model can be obtained more quickly and accurately.

[0119] Among them, the order prediction module is mainly used to build and train the order volume prediction model, and use the pre-trained order volume prediction model to predict the order volume corresponding to each region in the future time period, and according to the predicted total order volume corresponding to each region in the future time period and the intended order-taking area and the order volume that can be accepted in the future time period set by each service account of each service gradient level, determine the target order volume in each region in the future time period for the service accounts of each service gradient level.

[0120] Specifically, the order prediction module extracts historical order data from a comprehensive database, including the time, location, service type, service staff rating, customer feedback, and order status of the order. These data provide the model with rich context and user behavior pattern references, helping to understand the historical trends and changes in service demand. In addition, the order prediction module also integrates a real-time data module that can capture and process the completion status of orders for the day, the current location of service staff, status updates, and instant customer feedback. Real-time data enables the prediction model to respond to the latest market trends and improve the timeliness and accuracy of predictions. The collected data is cleaned through automated scripts, including correcting data errors, eliminating duplicate records, and handling outliers. In addition, a periodic data verification process is set up to ensure the consistency, completeness, and accuracy of the data, thereby providing a reliable data foundation for analysis and prediction.

[0121] Next, build an order volume prediction model. Determine the input of the order volume prediction model based on the corresponding relationships and corresponding rules obtained by the data integration module through data mining. Construct model features based on factors such as the service personnel's historical performance, user demand information and preference information for the target service, order time (including differences between weekdays, weekends and holidays) and geographical location. Use the random forest algorithm in machine learning for model training to predict order volumes at different times and locations. In addition, continuously optimize and adjust the model through cross-validation and real-time data feedback to adapt to market changes and improve the accuracy of predictions. For example, based on real-time order flow and service personnel feedback, the system dynamically adjusts the prediction model. This continuous learning and adjustment mechanism ensures that the model can continue to provide high-accuracy predictions in the face of market changes.

[0122] From this, we can see that data mining can reveal the laws and patterns in the data through various algorithm clustering and association rules. The laws can be converted into features and input into the prediction model to help the model improve the prediction accuracy. The prediction model can use this information to predict the order volume or work arrangement of service personnel in different regions by identifying the service performance of specific service personnel in certain time periods or regions, or the service demand characteristics of different user groups. In addition, data mining helps the prediction model to be continuously optimized. By analyzing the actual performance of service personnel and the changing trends of customer demand, new demand information or errors are discovered and fed back to the prediction model for adjustment. The prediction strategy is adaptively adjusted according to new data and laws.

[0123] Among them, the order allocation module is mainly used to allocate orders in order to dispatch service personnel to complete the corresponding orders. Among them, when allocating orders, the order allocation module can combine the service personnel's score, intended order-taking location, current location, service personnel's skills, whether the service personnel is currently available and other information to allocate orders. It should be noted that when allocating orders, the service personnel's intended order-taking area is determined based on the prediction results. In this way, when allocating orders, not only the order volume in each region is considered, but also high-quality service personnel are allocated to the required areas first.

[0124] Among them, the service personnel work-side management module is mainly used to provide service personnel with order forecasting, order allocation and other related services. Among them, the order volume forecasting, order allocation and other operations are mainly realized by providing service personnel with an order management interface.

[0125] Based on Figure 5 The structure of the order volume forecasting system shown in the figure, the specific process of order volume forecasting is as follows:

[0126] First, obtain historical order data and service personnel data corresponding to multiple service personnel of target services in each region, time information or time factors corresponding to future time periods, geographical locations corresponding to each region, and user behavior data corresponding to potential user sets. Among them, historical order data includes order volume, order type, service time, etc. in each region in a certain period of time in the past. Service personnel data includes information such as the rating, work experience, and completion rate of each service personnel. Time factors include factors such as dates, weekends, and holidays, because the order volume in different time periods will vary significantly.

[0127] Next, based on the historical order data, the potential user sets in each region are determined, and the preference information of each potential user in the potential user sets in each region for the target service is determined.

[0128] The historical order data and the service personnel data corresponding to the multiple service personnel of the target service in each region, the time information or time factor corresponding to the future time period, the geographical location corresponding to each region, the user behavior data corresponding to the potential user set, and the preference information corresponding to each potential user in the potential user set of each region are input into the order volume prediction model to output the order volume corresponding to each region in the future time period. That is, the total order volume of the target service in different regions in a certain period of time in the future (such as the next day) is predicted.

[0129] The prediction model mainly learns the relationship between historical order data, service personnel data, time factors, and regional order volume. Specifically, the model captures this relationship in the following ways: the relationship between time and geographic location and demand, the relationship between service personnel performance and order volume, user preference information, and the impact of holidays and special events.

[0130] In addition, for the contents not described in detail in this embodiment and the technical effects that can be achieved, please refer to the relevant descriptions in the above embodiments, and will not be repeated here.

[0131] The following will describe in detail the order receiving area determination device of one or more embodiments of the present invention. Those skilled in the art will appreciate that these order receiving area determination devices can be configured using commercially available hardware components through the steps taught in this solution.

[0132] Figure 6 Schematic diagram of a structure of a device for determining an order receiving area provided by an embodiment of the present invention. Figure 6 As shown, the device includes: an acquisition module 11, a first prediction module 12, a second prediction module 13, a first determination module 14, a second determination module 15, and a third determination module 16.

[0133] The acquisition module 11 is used to obtain a plurality of historical order data of the target service in each region within the target city in response to an order volume prediction request for the target service.

[0134] The first prediction module 12 is used to predict the potential user set in each region according to the order user feature data in the plurality of historical order data.

[0135] The second prediction module 13 is used to predict the total order volume of the target service in each region in a future time period based on multiple historical order data corresponding to each region, preference information corresponding to the potential user set, and time information of the future time period.

[0136] The first determination module 14 is used to determine a target service account corresponding to the target service and a target service level corresponding to the target service account. Different service personnel have different service accounts, and the target service account belongs to the target city.

[0137] The second determination module 15 is used to determine the target order volume corresponding to the target service account in each region according to the total order volume corresponding to the target service in each region, the target service level and the total number of orders that can be received for the target service at different service levels in each region.

[0138] The third determination module 16 is used to determine the order receiving area corresponding to the target service account according to the target order volume corresponding to the target service account in each region, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0139] Optionally, the third determination module 16 is specifically used to: determine the target service account corresponding to the client in response to an order quantity prediction request sent by the client; send the predicted target order quantity corresponding to the target service account in each region to the client, so that the client sets the order receiving area based on the target order quantity corresponding to each region; determine the order receiving area corresponding to the target service account in response to the order receiving area setting operation triggered by the client.

[0140] Optionally, the second determination module 15 is specifically used to: obtain, in order from high to low service gradient levels, the total order volume of the target service corresponding to each service gradient level in each region, and the total number of orders that can be accepted for the target service corresponding to each service gradient level in each region that is higher than the target service gradient level; determine the target order volume of the target service account corresponding to each region based on the total order volume of the target service corresponding to each region, the order volume of the target service corresponding to each service gradient level in each region that is higher than the target service gradient level, and the total number of orders that can be accepted for the target service corresponding to each service gradient level in each region that is higher than the target service gradient level.

[0141] Optionally, the second determination module 15 is specifically used to: determine, for the first service gradient level, the quantity of orders that can be accepted in each region corresponding to all service accounts in the second service gradient level, where the first service gradient level is any one of the service gradient levels higher than the target service gradient, and the second service gradient level is the service gradient level immediately preceding the first service gradient level; determine the total quantity of orders that can be accepted in each region corresponding to the second service gradient level based on the quantity of orders that can be accepted in each region corresponding to all service accounts in the second service gradient level; and determine the difference between the total quantity of orders for the target service corresponding to the second service gradient level in each region and the total quantity of orders that can be accepted in each region corresponding to the second service gradient level as the total quantity of orders for the target service corresponding to the first service gradient level in each region.

[0142] Optionally, the second determination module 15 is specifically used to: determine the intended order-taking area corresponding to each service account of the second service gradient level; determine the order-taking capacity value of each service account of the second service gradient level in the future time period, the order-taking capacity value being used to represent the order-taking capacity of the service personnel corresponding to the service account; determine the number of orders that can be accepted in each region for each service account in the second service gradient level based on the intended order-taking area corresponding to each service account of the second service gradient level and the order-taking capacity value of each service account of the second service gradient level in the future time period.

[0143] Optionally, the second determination module 15 is specifically used to: determine, for the service account to be evaluated, the intended order receiving area corresponding to the service account to be evaluated based on the order volume corresponding to the service account to be evaluated in each region in the future time period and the commonly used order receiving area corresponding to the service account to be evaluated; or determine the order receiving area set by the service account to be evaluated in the order receiving area interface as the intended order receiving area corresponding to the service account to be evaluated; wherein, the service account to be evaluated is any one of the multiple service accounts located at the second service gradient level.

[0144] Optionally, the first prediction module 12 is specifically used to: determine the historical user set corresponding to each region based on the multiple historical order data; and determine the potential user set corresponding to each region based on the historical user set corresponding to each region using association rule analysis.

[0145] Optionally, the first prediction module 12 is also used to: classify the potential user set corresponding to the target area and determine the target category corresponding thereto, wherein the target area is any one of the multiple areas; and determine the preference information of each potential user in the potential user set of the target area for the target service based on the target category.

[0146] Optionally, the second prediction module 13 is specifically used to: obtain service data corresponding to each service account that belongs to the target city and provides the target service, the service data being used to reflect the overall quality and ability level demonstrated by the service personnel corresponding to the service account in the service work; using a pre-trained order volume prediction model to analyze multiple historical order data corresponding to each region, preference information corresponding to the potential user set and time information of future time periods, and service data corresponding to each service account that belongs to the target city and provides the target service, to predict the total order volume of the target service in each region in the future time period.

[0147] Figure 6 The device shown can perform Figures 1 to 5For the method of the embodiment shown in the figure, the part not described in detail in this embodiment can be referred to Figures 1 to 5 The implementation process and technical effects of this technical solution refer to Figures 1 to 5 The description in the illustrated embodiment will not be repeated here.

[0148] In a possible design, the order quantity prediction method provided by the above embodiments can be applied in an electronic device, such as Figure 7 As shown, the electronic device may include: a processor 21 and a memory 22. The memory 22 is used to store the electronic device to perform the above Figure 1 to Figure 5 The program of the distributed cache processing method provided in the illustrated embodiment, the processor 21 is configured to execute the program stored in the memory 22 .

[0149] The program includes one or more computer instructions, wherein when the one or more computer instructions are executed by the processor 21, the following steps can be implemented:

[0150] In response to an order volume prediction request for a target service, obtaining a plurality of historical order data for the target service in various regions within a target city;

[0151] Predicting a potential user set in each region based on the order user feature data in the plurality of historical order data;

[0152] Predicting the total order volume of the target service in each region in the future time period based on the multiple historical order data corresponding to each region, the preference information corresponding to the potential user set, and the time information of the future time period;

[0153] Determine a target service account corresponding to the target service and a target service level corresponding to the target service account, different service personnel have different service accounts, and the target service account belongs to the target city;

[0154] Determine the target order volume corresponding to the target service account in each region according to the total order volume corresponding to the target service in each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region;

[0155] According to the target order volume corresponding to the target service account in each region, the order receiving area corresponding to the target service account is determined, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

[0156] Optionally, the processor 21 is further configured to execute the aforementioned Figure 1 to Figure 5 All or part of the steps in the illustrated embodiments.

[0157] The structure of the electronic device may further include a communication interface 23 for the electronic device to communicate with other devices or communication systems.

[0158] In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by the above electronic device, which includes instructions for executing the above Figure 1 to Figure 5 The procedures involved in the method of determining the order receiving area shown.

[0159] In addition, an embodiment of the present invention provides a computer program product. The computer program product includes a computer program or an instruction. When the computer program or the instruction is executed by a processor, the processor is enabled to implement the above Figure 1 to Figure 5 The steps or functions of the method shown.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining an order receiving area, characterized in that: Applied to the server, the method includes: In response to an order volume prediction request for a target service, obtaining a plurality of historical order data for the target service in various regions within a target city; Predicting a potential user set in each region based on the order user feature data in the plurality of historical order data; Predicting the total order volume of the target service in each region in the future time period based on the multiple historical order data corresponding to each region, the preference information corresponding to the potential user set, and the time information of the future time period; Determine a target service account corresponding to the target service and a target service level corresponding to the target service account, different service personnel have different service accounts, and the target service account belongs to the target city; Determine the target order volume corresponding to the target service account in each region according to the total order volume corresponding to the target service in each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region; According to the target order volume corresponding to the target service account in each region, the order receiving area corresponding to the target service account is determined, so as to allocate orders to the client logged in with the target service account according to the order receiving area.

2. The method according to claim 1, characterized in that The determining, according to the target order volume corresponding to the target service account in each region, the order receiving area corresponding to the target service account includes: In response to the order volume prediction request sent by the client, determine a target service account corresponding to the client; sending the predicted target order volume corresponding to the target service account in each region to the client, so that the client sets an order receiving area based on the target order volume corresponding to each region; In response to the order receiving area setting operation triggered by the client, the order receiving area corresponding to the target service account is determined.

3. The method according to claim 1, characterized in that Determining the target order volume corresponding to the target service account in each region according to the total order volume corresponding to the target service in each region, the target service level, and the total number of orders that can be received for the target service at different service levels in each region includes: Obtain, in descending order of service gradient levels, the total number of orders for the target service in each region for each service gradient level higher than the target service gradient level, and the total number of orders that can be received for the target service in each region for each service gradient level higher than the target service gradient level; The target order volume for each region corresponding to the target service account is determined based on the total order volume of the target service in each region, the order volume of each service gradient level higher than the target service gradient level corresponding to the target service in each region, and the total number of orders that can be accepted for the target service in each region corresponding to each service gradient level higher than the target service gradient level.

4. The method according to claim 3, characterized in that The step of sequentially obtaining the total number of orders corresponding to the target service in each region for each service gradient level higher than the target service gradient level includes: For a first service gradient level, determining the number of orders that can be received in each region for all service accounts in a second service gradient level, wherein the first service gradient level is any one of the service gradient levels higher than the target service gradient, and the second service gradient level is a service gradient level above the first service gradient level; Determine the total amount of orders that can be received in each region corresponding to the second service gradient level according to the amount of orders that can be received in each region corresponding to all service accounts in the second service gradient level; The difference between the total number of orders for the target service corresponding to the second service gradient level in each region and the total number of orders that can be accepted corresponding to the second service gradient level in each region is determined as the total number of orders for the target service corresponding to the first service gradient level in each region.

5. The method according to claim 4, characterized in that The step of determining the number of orders that can be received by all service accounts in the second service gradient level in each region includes: Determine the intended order receiving area corresponding to each service account of the second service gradient level; Determine an order-taking capability value of each service account of the second service gradient level in the future time period, wherein the order-taking capability value is used to represent the order-taking capability of the service personnel corresponding to the service account; Based on the intended order-taking area corresponding to each service account of the second service gradient level and the order-taking capacity value of each service account of the second service gradient level in the future time period, the number of orders that can be accepted in each region corresponding to each service account in the second service gradient level is determined.

6. The method according to claim 5, characterized in that The determining of the intended order receiving area corresponding to each service account of the second service gradient level includes: For the service account to be evaluated, based on the order volume corresponding to the service account to be evaluated in each region in the future time period and the common order receiving area corresponding to the service account to be evaluated, determine the intended order receiving area corresponding to the service account to be evaluated; or Determine the order receiving area set by the service account to be evaluated in the order receiving area interface as the intended order receiving area corresponding to the service account to be evaluated; The service account to be evaluated is any one of a plurality of service accounts at the second service gradient level.

7. The method according to claim 1, characterized in that The step of predicting a potential user set in each region based on the order user feature data in the plurality of historical order data includes: Determine a historical user set corresponding to each region according to the plurality of historical order data; By utilizing association rule analysis, the potential user set corresponding to each region is determined according to the historical user set corresponding to each region.

8. The method according to claim 7, characterized in that The method further comprises: Classifying a set of potential users corresponding to a target region to determine a target category corresponding thereto, wherein the target region is any one of the multiple regions; According to the target category, preference information of each potential user in the set of potential users in the target area for the target service is determined.

9. The method according to claim 1, characterized in that: The method of predicting the total order volume of the target service in each region in the future time period according to the plurality of historical order data corresponding to each region, the preference information corresponding to the potential user set, and the time information of the future time period includes: Acquire service data corresponding to each service account belonging to the target city and providing the target service, wherein the service data is used to reflect the overall quality and ability level of the service personnel corresponding to the service account in their service work; By using a pre-trained order volume prediction model, the multiple historical order data corresponding to each region, the preference information corresponding to the potential user set and the time information of the future time period, and the service data corresponding to each service account belonging to the target city and providing the target service are analyzed to predict the total order volume of the target service in each region in the future time period.

10. An electronic device, characterized in that: include: A memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the order receiving area determination method as described in any one of claims 1 to 9.

11. A non-transitory machine-readable storage medium, characterized in that: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method for determining an order receiving area as described in any one of claims 1 to 9.

Images