Method, device and storage medium for pushing logistics order verification information

Abstract

The present application relates to a method, device, and storage medium for pushing logistics order verification information, wherein the method for pushing logistics order verification information includes the following steps: receiving a real-time order consigned by the current customer, obtaining pre-filled order information entered by the current customer on the real-time order; judging whether the current customer belongs to an ordinary target customer based on the product information, consignment information, historical consignment behavior information of the current customer, and preset ordinary target customer conditions on the pre-filled order information; if the current customer belongs to an ordinary target customer, judging whether the type of the real-time order belongs to an ordinary standard order type based on a preset ordinary standard order classification model; when the type of the real-time order belongs to an ordinary standard order type, determining the historical ordinary standard order pre-stored by the current customer as logistics order verification information and pushing it to the recipient. The present application saves the recipient's time for checking and modifying when receiving the item, and improves the efficiency of receiving the item.

Description

Technical Field

[0001] The present application relates to the technical field of logistics business systems, and specifically to a method, device, and storage medium for pushing logistics order verification information. Background Art

[0002] The receiving operation is one of the most commonly used operations in the logistics business system. In particular, one of the main functions of the receiving and dispatching terminal of the logistics business system is to be used for the receiving operation.

[0003] The receiving operation interface of the collection and delivery terminal is usually divided into three order information pages, namely the contact information page, the consignment information page and the product information page. Among them, the contact information page has information such as the sender's name, sender's phone number, sender's address, the recipient's name, recipient's phone number, recipient's address, etc.; the consignment information page has information such as the consignment name, weight, and packaging materials; the product information has information such as product type, payment method, and value-added services. Every time the consignee uses this collection and delivery terminal to receive a parcel, he must check and modify the information on the three pages in turn to complete the receiving operation.

[0004] However, in actual delivery business scenarios, there are two regular phenomena:

[0005] (1) Within a certain historical period, the order information of a certain customer's orders is highly similar. For example, the name of the consignment, weight, packaging materials, product type, payment method, and value-added services remain unchanged during multiple fillings (however, in this case, customers are still required to fill in the order information on three pages each time they send a shipment).

[0006] (2) During a certain historical period, the order information filled in by a certain customer on all previous orders was correct and standard, that is, the name of the consignment, weight, product type, payment method, value-added services and other information filled in were in compliance with the specifications each time (however, in this case, the consignee is still required to check or modify the information on the three pages in turn).

[0007] It can be seen that for the above two regular phenomena, since the recipient still needs to check or modify the information in the three pages in turn, the efficiency of receiving is low. Summary of the invention

[0008] The purpose of this application is to disclose at least a method for pushing logistics order verification information that can improve delivery efficiency.

[0009] Therefore, the method for pushing logistics order verification information disclosed in this application mainly includes the following steps:

[0010] Receiving a real-time order placed by a current customer, and obtaining pre-filled order information entered by the current customer on the real-time order;

[0011] Based on the product information, consignment information, historical consignment behavior information of the current customer and the preset common target customer conditions in the pre-filled order information, determining whether the current customer is a common target customer;

[0012] If the current customer is a common target customer, judging whether the type of the real-time order belongs to a common standard order type based on a preset common standard order classification model;

[0013] When the type of the real-time order belongs to the ordinary standard order type, the historical ordinary standard order pre-stored by the current customer is determined as the logistics order verification information and pushed to the recipient.

[0014] Wherein, judging whether the current customer is a common target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset common target customer conditions in the pre-filled order information includes:

[0015] Based on the product information, consignment information, historical consignment behavior information of the current customer and the preset ultimate target customer conditions in the pre-filled order information, determine whether the current customer is an ultimate target customer;

[0016] If the current customer is not an extreme target customer, it is determined whether the current customer is an ordinary target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset ordinary target customer conditions on the pre-filled order information.

[0017] Wherein, judging whether the current customer is an extreme target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset extreme target customer conditions in the pre-filled order information includes:

[0018] Obtaining the identity information of the current customer;

[0019] Identify whether the current customer is a target customer based on the identity information of the current customer;

[0020] If the current customer is a target customer, determine whether the current customer is an extreme target customer based on the product information, consignment information, the current customer's historical consignment behavior information, and the preset extreme target customer conditions on the pre-filled order information.

[0021] The method for pushing the logistics order verification information further includes:

[0022] If the current customer is an extreme target customer, judging whether the type of the real-time order belongs to the extreme standard order type based on a preset extreme standard order classification model;

[0023] If the type of the real-time order is an extreme standard order type, the pre-filled order information of the current customer is determined as logistics order verification information and pushed to the recipient.

[0024] Among them, the general target customer refers to a customer whose historical consignment behavior information meets the preset general target customer conditions; the preset general target customer conditions are: within a first preset historical time period, the customer's order quantity reaches a first preset order quantity, and the proportion of similar orders in all previous orders within the first preset historical time period is greater than the first preset proportion, wherein the similar orders are orders with the same first combination information, and the first combination information is composed of at least one of the product information and at least one of the consignment information.

[0025] And / or, the extreme target customer refers to a customer whose historical consignment behavior information meets preset extreme target customer conditions; the preset extreme target customer conditions are: within a second preset historical time period, the customer's order quantity reaches a second preset order quantity, and the proportion of orders in which the second combination information has not been modified by the consignee in all previous orders within the second preset historical time period is greater than a second preset proportion, wherein the second combination information is composed of at least part of the information in the product information and at least part of the information in the consignment information.

[0026] wherein a preset ordinary standard order training set is obtained, wherein orders in the ordinary standard order training set whose customers meet the preset ordinary target customer conditions are marked as ordinary standard order types; orders in the ordinary standard order training set whose customers do not meet the preset ordinary target customer conditions are marked as non-ordinary standard order types;

[0027] Training a first preset classification model based on the common single training set to obtain the common standard single classification model;

[0028] And / or, obtaining a preset extreme standard order training set, wherein orders in the extreme standard order training set from customers that meet preset extreme target customer conditions are marked as extreme standard order types; orders in the extreme standard order training set from customers that do not meet preset extreme target customer conditions are marked as non-extreme standard order types;

[0029] The second preset classification model is trained based on the extreme single training set to obtain the extreme standard single classification model.

[0030] Among them, a plurality of push record information pushed under the conditions of a plurality of common target customers to be deduced within a third preset historical time period is obtained, wherein the push record information includes a common push accuracy rate and / or a common push coverage rate;

[0031] Acquire the optimal push record information satisfying the load balancing condition from the plurality of push record information;

[0032] The to-be-derived common target customer condition corresponding to the optimal push record information is determined as the preset common target customer condition.

[0033] The present application also discloses a device for pushing logistics order verification information, which mainly includes:

[0034] An acquisition unit, configured to receive a real-time order placed by a current customer and acquire pre-filled order information entered by the current customer on the real-time order;

[0035] A first judgment unit, configured to judge whether the current customer is a common target customer based on product information, consignment information, historical consignment behavior information of the current customer and preset common target customer conditions in the pre-filled order information;

[0036] A second judgment unit is used to judge whether the type of the real-time order belongs to the common standard order type based on a preset common standard order classification model if the current customer belongs to the common target customer;

[0037] The push unit is used to determine the historical ordinary standard order pre-stored by the current customer as logistics order verification information and push it to the recipient when the type of the real-time order belongs to the ordinary standard order type.

[0038] The first judgment unit is further used to judge whether the current customer is an extreme target customer based on the product information, consignment information, historical consignment behavior information of the current customer and the preset extreme target customer conditions in the pre-filled order information;

[0039] If the current customer is not an extreme target customer, it is determined whether the current customer is an ordinary target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset ordinary target customer conditions on the pre-filled order information.

[0040] Wherein, the first judgment unit is further used to obtain the identity information of the current customer;

[0041] Identify whether the current customer is a target customer based on the identity information of the current customer;

[0042] If the current customer is a target customer, determine whether the current customer is an extreme target customer based on the product information, consignment information, the current customer's historical consignment behavior information, and the preset extreme target customer conditions on the pre-filled order information.

[0043] Wherein, the second judgment unit is further used to judge whether the type of the real-time order belongs to the extreme standard order type based on a preset extreme standard order classification model if the current customer belongs to the extreme target customer;

[0044] If the type of the real-time order is an extreme standard order type, the pre-filled order information of the current customer is determined as logistics order verification information and pushed to the recipient.

[0045] Among them, the general target customer refers to a customer whose historical consignment behavior information meets the preset general target customer conditions; the preset general target customer conditions are: within a first preset historical time period, the customer's order quantity reaches a first preset order quantity, and the proportion of similar orders in all previous orders within the first preset historical time period is greater than the first preset proportion, wherein the similar orders are orders with the same first combination information, and the first combination information is composed of at least one of the product information and at least one of the consignment information.

[0046] And / or, the extreme target customer refers to a customer whose historical consignment behavior information meets preset extreme target customer conditions; the preset extreme target customer conditions are: within a second preset historical time period, the customer's order quantity reaches a second preset order quantity, and the proportion of orders in which the second combination information has not been modified by the consignee in all previous orders within the second preset historical time period is greater than a second preset proportion, wherein the second combination information is composed of at least part of the information in the product information and at least part of the information in the consignment information.

[0047] The acquisition unit is further used to acquire a preset common standard order training set, wherein orders in the common standard order training set whose customers meet the preset common target customer conditions are marked as common standard order types; orders in the common standard order training set whose customers do not meet the preset common target customer conditions are marked as non-common standard order types;

[0048] Training a first preset classification model based on the common single training set to obtain the common standard single classification model;

[0049] And / or, obtaining a preset extreme standard order training set, wherein orders in the extreme standard order training set from customers that meet preset extreme target customer conditions are marked as extreme standard order types; orders in the extreme standard order training set from customers that do not meet preset extreme target customer conditions are marked as non-extreme standard order types;

[0050] The second preset classification model is trained based on the extreme single training set to obtain the extreme standard single classification model.

[0051] The push unit is further used to obtain a plurality of push record information pushed under a plurality of conditions of common target customers to be deduced within a third preset historical time period, wherein the push record information includes a common push accuracy rate and / or a common push coverage rate;

[0052] Acquire the optimal push record information satisfying the load balancing condition from the plurality of push record information;

[0053] The to-be-derived common target customer condition corresponding to the optimal push record information is determined as the preset common target customer condition.

[0054] The present application also provides an electronic device, the electronic device comprising:

[0055] one or more processors;

[0056] Memory; and

[0057] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method for pushing logistics order verification information as described in any one of the first aspects.

[0058] The present application also provides a computer-readable storage medium on which a computer program is stored. The computer program is loaded by a processor to execute the steps in the method for pushing logistics order verification information as described in any one of the first aspects.

[0059] The present application has at least the following beneficial effects: The present application provides a method for pushing logistics order verification information, first judging whether the current customer is an ordinary target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset ordinary target customer conditions on the pre-filled order information; when the current customer is an ordinary target customer, judging whether the type of the real-time order belongs to the ordinary standard order type based on the preset ordinary standard order classification model; when the type of the real-time order belongs to the ordinary standard order type, determining the historical ordinary standard order pre-stored by the current customer as the logistics order verification information and pushing it to the consignee; by setting preset conditions to judge the customer type and predicting the order type through the preset ordinary standard order classification model, a two-stage confirmation of whether the order is an ordinary standard order is achieved, and ordinary standard orders can be identified quickly and accurately; and when the order is an ordinary standard order, the pre-stored historical ordinary standard order is pushed to the consignee for verification; the historical ordinary standard order is an order that has been completed for consignment and has been accurately identified; therefore, the consignee does not need to modify the order, and only needs to simply check to consign, thereby saving the consignee's time for verification and modification when receiving the goods, and improving the efficiency of receiving. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 It is a flow chart of an embodiment of a method for pushing logistics order verification information disclosed in an embodiment.

[0062] Figure 2 It is a schematic diagram of the structure of an embodiment of a device for pushing logistics order verification information disclosed in the embodiment.

[0063] Figure 3 It is a schematic structural diagram of an embodiment of an electronic device disclosed in the embodiment. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0065] In order to improve the efficiency of receiving standard orders from target customers with certain regularity, the following describes in detail the method, device, and corresponding computer-readable storage medium for pushing logistics order verification information of this embodiment in combination with relevant definitions of target customers, target customer identification models and other concepts.

[0066] See also Figure 1 This embodiment discloses a method for pushing logistics order verification information, which mainly includes the following steps:

[0067] S101: receiving a real-time order from a current customer, and obtaining pre-filled order information entered by the current customer on the real-time order.

[0068] When a customer places an order, he or she usually needs to fill in (enter) some order information, such as the sender's name, sender's phone number, sender's address, recipient's name, recipient's phone number, recipient's address and other contact information, as well as some consignment information and product information; in this embodiment, the information actively filled in by the customer needs to be identified to determine whether it is used to directly or indirectly generate the order information integration page of this embodiment or to generate a regular order information page (such as the regular three order information pages). For ease of reference, this actively filled in information is referred to as pre-filled order information.

[0069] In the pre-filled order information, customers are generally required to provide contact information, consignment information and product information. The contact information may include the sender's name, phone number, address, recipient's name, phone number, address, etc. The product information may include product type, payment method, value-added services, etc. The consignment information may include the consignment name, weight, packaging materials, etc.

[0070] S102: Based on the product information, consignment information, historical consignment behavior information of the current customer and preset common target customer conditions in the pre-filled order information, determine whether the current customer is a common target customer.

[0071] In a specific embodiment, a general target customer refers to a customer whose historical consignment behavior information meets preset general target customer conditions; the preset general target customer conditions are: within a first preset historical time period, the number of orders of the customer reaches a first preset order number, and the proportion of similar orders in all previous orders within the first preset historical time period is greater than the first preset proportion, wherein similar orders are orders with the same first combination information, and the first combination information is composed of at least one of the product information and at least one of the consignment information.

[0072] For example, the first combination information is composed of three dimensions: product type, payment method, and value-added service in the product information, and three dimensions: consignment name, weight, and packaging material in the consignment information, for a total of six dimensions. Of course, different first combination information can be set according to specific circumstances, and this application does not limit this.

[0073] Historical consignment behavior information refers to the number of orders placed by customers within a historical period of time.

[0074] Among them, the same first combination information means that the information filled in the six dimensions in the first combination information is the same, and the two orders can be identified as similar orders. Of course, similar orders include the first combination information of one order being exactly the same as the first combination information of other orders; and also include the first combination information of one order being only slightly different from the first combination information of other orders but being essentially the same.

[0075] In a specific embodiment, the first preset historical time period is 3 months, the first preset order quantity is 5, and the first preset proportion is 80%; the customer needs to meet the following requirements: looking back at the historical time period of 3 months, there are at least 5 orders, and the number of similar orders to the 5 orders accounts for more than 80% (that is, at least 4 are similar), then the customer can meet the preset general target customer conditions.

[0076] Because there is no push record information before the push method of this application is implemented, the preset general target customer conditions are mainly set manually. When the push record information is available later, the preset general target customer conditions can be adjusted according to the push record information, and the process of adjusting the preset general target customer conditions will be described later.

[0077] In a specific embodiment, judging whether the current customer is a common target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset common target customer conditions in the pre-filled order information may include:

[0078] (1) Based on the product information, consignment information, historical consignment behavior information of the current customer, and preset ultimate target customer conditions in the pre-filled order information, determine whether the current customer is an ultimate target customer.

[0079] In a specific embodiment: an extreme target customer refers to a customer whose historical consignment behavior information meets preset extreme target customer conditions; the preset extreme target customer conditions are: within a second preset historical time period, the number of orders from the customer reaches a second preset order number, and the proportion of orders in which the second combination information has not been modified by the consignee in all previous orders within the second preset historical time period is greater than the second preset proportion, wherein the first combination information is composed of at least part of the information in the product information and at least part of the information in the consignment information.

[0080] Since the dimension of packaging materials in the consignment information is generally filled in by the courier, and the consignee will not modify this dimension, this dimension is not used as the dimension of the second combination information. For example, the second combination information is composed of three dimensions of product type, payment method, and value-added service in the product information, and two dimensions of consignment name and weight in the consignment information, a total of five dimensions. Of course, different second combination information can be set according to specific circumstances, and this application does not limit this.

[0081] The order whose second combination information has not been modified by the consignee refers to the order that the consignee has consigned without modifying any information in the second combination information after obtaining the customer's order. The second combination information in the order has not been modified by the consignee, indicating that the customer has filled in the accurate information on the real-time order, and the consignee does not need to check the real-time order.

[0082] In a specific embodiment, the second preset historical time period is 4 months, the second preset order quantity is 10, and the second preset proportion is 80%; the customer needs to meet the following requirements: looking back at the historical time period of 4 months, there are at least 10 orders, and the proportion of orders in which the second combination information has not been modified by the recipient among the 10 orders is more than 80% (that is, at least 4 orders are similar), then the customer can meet the preset extreme target customer conditions.

[0083] Furthermore, before determining whether the current customer is an extreme target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset extreme target customer conditions in the pre-filled order information, the identity information of the current customer is obtained; based on the identity information of the current customer, whether the current customer is a target customer is identified; when the customer is a target customer, whether the current customer is an extreme target customer is determined based on the product information, consignment information, historical consignment behavior information of the current customer and preset extreme target customer conditions in the pre-filled order information.

[0084] The target customer is at least a customer who has placed a logistics order with a logistics carrier (logistics company) in the past. The logistics carrier has recorded the customer with a historical order as a target customer by judging the customer's historical order in previous business activities. After receiving a real-time order (i.e., the current order), the logistics carrier can identify whether the real-time order comes from a customer who has been recorded as a target customer through the identity information in the pre-filled order information of the real-time order.

[0085] Among these pre-filled information, the sender's phone number (customer phone number) is often unique across the entire network and can be used as the identification information of the customer; based on this identification information, a unique customer can usually be identified. In other embodiments, other identification information that can identify a unique customer can be used.

[0086] (2) If the current customer is not an extreme target customer, determine whether the current customer is an ordinary target customer based on the product information, consignment information, the current customer's historical consignment behavior information, and the preset ordinary target customer conditions in the pre-filled order information.

[0087] If the current customer is not an extreme target customer, determine whether the current customer is an ordinary target customer based on the product information, consignment information, the current customer's historical consignment behavior information and the preset ordinary target customer conditions on the pre-filled order information.

[0088] Since the ultimate user is a user who can fill in accurate information, if the current customer is an ultimate target customer, the consignment can be made according to the pre-filled order filled in by the current user. If the current customer is not an ultimate target customer, the consignment according to the pre-filled order filled in by the current user may result in errors. First, by presetting the ultimate target customer conditions for screening, the ultimate target customer can be consigned based on more accurate current filled information, thereby improving the push accuracy.

[0089] Furthermore, if the current customer is an extreme target customer, the type of the real-time order is determined based on the preset extreme standard order classification model to determine whether it is an extreme standard order type; if the type of the real-time order is an extreme standard order type, the current customer's pre-filled order information is determined as logistics order verification information and pushed to the recipient.

[0090] S103: If the current customer is a common target customer, determine whether the type of the real-time order belongs to a common standard order type based on a preset common standard order classification model.

[0091] Specifically, before receiving the real-time order entrusted by the current customer and obtaining the pre-filled order information entered by the current customer on the real-time order, the following may be included: obtaining a preset common standard order training set, wherein orders in the common standard order training set for customers that meet the preset common target customer conditions are marked as common standard order types; orders in the common standard order training set for customers that do not meet the preset common target customer conditions are marked as non-common standard order types. The first preset classification model is trained based on the common order training set to obtain a common standard order classification model.

[0092] Specifically, the training set of common standard orders can be data obtained by annotating the orders of users in the historical time period. For example, the order of common standard order type can specifically include the first combination information (name of consignment, weight, packaging material, product type, payment method and value-added service six-dimensional information), and can also include the sender's phone number, branch code, order time, receiver number, order channel, expected collection time, customer risk type and other auxiliary information.

[0093] The first feature information is extracted from the common standard single training set. The first feature information may specifically include the first combination information (six dimensional information of consignment name, weight, packaging material, product type, payment method and value-added service), and may also include auxiliary information such as sender's phone number, branch code, order time, receiver number, order channel, expected collection time, customer risk type, etc. The first feature information is preprocessed to obtain the first numerical feature information; the first feature information can be divided into text category information and numerical feature information, for example, the consignment name is generally text category information, and the sender's phone number and receiver's employee number are generally numerical feature information. The feature information can be converted into the specified numerical feature information by encoding. Among them, the one-hot encoding method is usually used to encode qualitative features such as the sender's phone number and the receiver's employee number, but this type of qualitative feature belongs to high cardinality qualitative features, and the one-hot encoding method will result in a large number of sparse matrices, so the mean encoding method is preferably used.

[0094] The first preset classification model can be any one of a logistic regression model, a support vector machine model, and a decision tree model, or an integrated model that integrates any two or three of the logistic regression model, the support vector machine model, and the decision tree model. The first numerical feature information is input into the selected model for training, and the optimal model or model combination is used as the final common standard single classification model.

[0095] Since the recognition results of the above-mentioned logistic regression model, support vector machine model and decision tree model all output a recognition probability, it is necessary to select an appropriate recognition probability threshold as the default value for accurate recognition. For example, when using the logistic regression model to identify the target customer, it outputs a recognition probability of 0.84, which means that the logistic regression model believes that the target customer has an 84% chance of being an ordinary target customer; if 0.84 is used as the default accurate recognition value, then all cases with a recognition probability greater than 0.84 will be directly identified as ordinary target customers.

[0096] For the setting of recognition probability threshold, it is necessary to consider recognition accuracy and recognition coverage. For example, in the recognition results of the logistic regression model in Table 1 below, when the recognition probability threshold is 0.84, its recognition accuracy reaches 92.06%, and the recognition coverage reaches 1.31%; when the recognition probability threshold is 0.85 to 0.89, the corresponding recognition accuracy and recognition coverage are different. Therefore, comprehensive consideration is made to achieve a balanced and optimal recognition accuracy and recognition coverage, so as to select the most appropriate probability threshold. The same is true for the recognition results of the support vector machine model in Table 2.

[0097] Table 1. Logistic regression model identification results

[0098]

[0099] Table 2. Support vector machine model recognition results

[0100]

[0101] Furthermore, if the current customer is an extreme target customer, the type of the real-time order is determined based on the preset extreme standard order classification model to determine whether it is an extreme standard order type; if the type of the real-time order is an extreme standard order type, the current customer's pre-filled order information is determined as logistics order verification information and pushed to the recipient.

[0102] Specifically, before receiving the real-time order entrusted by the current customer and obtaining the pre-filled order information entered by the current customer on the real-time order, the following may be included: obtaining a preset extreme standard order training set, wherein orders in the extreme standard order training set for customers that meet the preset extreme target customer conditions are marked as extreme standard order types; orders in the extreme standard order training set for customers that do not meet the preset extreme target customer conditions are marked as non-extreme standard order types. The second preset classification model is trained based on the extreme order training set to obtain an extreme standard order classification model.

[0103] Specifically, the training set of the extreme standard order can be the data obtained by annotating the orders of users in the historical time period. For example, the order of the extreme standard order type can specifically include the second combination information (the five dimensions of consignment name, weight, product type, payment method and value-added service information), and can also include the sender's phone number, branch code, order time, receiver number, order channel, expected collection time, customer risk type and other auxiliary information.

[0104] The second feature information is extracted from the extreme standard single training set. The second feature information can specifically include the second combination information (5-dimensional information of consignment name, weight, product type, payment method and value-added service), and can also include auxiliary information such as sender's phone number, branch code, order time, recipient number, order channel, expected collection time, customer risk type, etc. The second feature information is preprocessed to obtain the second numerical feature information; the second feature information can be divided into text category information and numerical feature information, for example, the consignment name is generally text category information, and the sender's phone number and recipient employee number are generally numerical feature information. The feature information can be converted into the specified numerical feature information by encoding. Among them, the one-hot encoding method is usually used to encode qualitative features such as the sender's phone number and the recipient employee number, but this type of qualitative feature belongs to high-cardinality qualitative features. The use of the one-hot encoding method will result in a large number of sparse matrices, so the mean encoding method is preferably used.

[0105] The second preset classification model can be any one of a logistic regression model, a support vector machine model, and a decision tree model, or an integrated model that integrates any two or three of the logistic regression model, the support vector machine model, and the decision tree model. The second numerical feature information is input into the selected model for training, and the optimal model or model combination is used as the final ultimate standard single classification model.

[0106] When applying the above-mentioned logistic regression model, support vector machine model, decision tree model or an integrated model that integrates two or more models, it is also necessary to set a recognition probability threshold. For details, please refer to the corresponding introduction of the ordinary standard single classification model.

[0107] S104: When the type of the real-time order belongs to the ordinary standard order type, the historical ordinary standard order pre-stored by the current customer is determined as the logistics order verification information and pushed to the recipient.

[0108] Specifically, the historical general standard order is an order that has been successfully consigned in the past and is of the general standard order type. The historical general standard order is an order stored in the system. When the type of the real-time order belongs to the general standard order type, it can be directly read. Among them, the logistics order verification information order information is a total page that integrates three pages: contact information page, consignment information page, and product information page. The consignee can check it at one time without checking the three pages separately, which further improves the efficiency of receiving. Moreover, since the order information integration page does not need to reserve space for manual editing, the page layout can be set to be more compact, so that not only the existing three order information pages can be integrated into one page, but also the size of the integrated page can be appropriately reduced, so that the consignee can quickly browse and check.

[0109] Specifically, in the previous business activities, the logistics carrier, in addition to recording the target customer in advance, also records the various order information that the customer's standard order for ordinary target customers should have (including at least the first combination information, and in the preferred solution, the various order information can be fuzzy matched) in the previous business activities, and pre-stores a historical ordinary standard order (including at least the first combination information in a standard format, and the standard format can be customized). Therefore, after identifying that the real-time order is the ordinary standard order corresponding to the customer, the pre-stored historical ordinary standard order of the customer can be obtained, and an order information integration page for the recipient to check can be generated based on the historical ordinary standard order.

[0110] The setting of preset conditions for ordinary target customers needs to consider its practicality, which is reflected in at least two aspects: push accuracy and push coverage.

[0111] Therefore, after the historical common standard order stored by the current customer is determined as the logistics order verification information and pushed to the recipient, it also includes:

[0112] (1) Acquiring a plurality of push record information of pushes performed under a plurality of conditions of common target customers to be deduced within a third preset historical time period, wherein the push record information includes a common push accuracy rate and / or a common push coverage rate.

[0113] The third preset time period can be set according to specific circumstances, such as two weeks. After the push is performed, the push record information can be obtained.

[0114] Specifically, multiple push record information pushed under multiple common target customer conditions to be deduced within the third preset historical time period is obtained according to a preset period, and the preset period can be two weeks or one month, etc., which is set according to specific circumstances. That is, the preset common target customer conditions are updated once every period of time according to the latest data.

[0115] After the logistics order verification information is pushed to the recipient, the total number of orders of all customers in the entire logistics network within the third preset time period and the number of ordinary push orders pushed to ordinary target customers within the third time period are counted. The ordinary push coverage rate refers to: the ratio of the number of ordinary push orders to the total number of orders.

[0116] Among all ordinary push orders, the orders in which the recipient has not modified the logistics order verification information are determined as ordinary standard orders that have been pushed correctly, and the orders in which the recipient has modified the logistics order verification information are determined as ordinary standard orders that have not been pushed correctly. The ordinary push accuracy rate within the third preset time period can be counted.

[0117] The accuracy rate of ordinary push with preset ordinary target customer conditions refers to the ratio of the number of correct ordinary standard orders to the number of ordinary standard orders pushed. The number of ordinary push orders pushed to ordinary target customers in the third time period is S, the number of ordinary standard orders actually pushed correctly is A, the number of ordinary standard orders that are not actually pushed correctly is B, and the accuracy rate of ordinary push with preset ordinary target customer conditions is C, then S = (A + B), C = A / S.

[0118] First, a plurality of common target customer conditions to be deduced may be determined according to a first preset historical time period, a first preset order quantity, and a first preset proportion.

[0119] For example, the first preset historical time period is divided into 3 months and 4 months, that is, the historical time period is set to be 3 months and 4 months; the first preset order quantity is more than 5 pieces and more than 10 pieces respectively; thus, it can be recorded as: the number of parcels sent in the past 3 months is ≥5 pieces, the number of parcels sent in the past 4 months is ≥5 pieces, the number of parcels sent in the past 3 months is ≥10 pieces, and the number of parcels sent in the past 4 months is ≥10 pieces; assuming that the six dimensional information of the name, weight, packaging material, product type, payment method and value-added service of the above-mentioned consignment is used as the first combination information, the first preset proportion is set to 80%, 85%, 95%, 95%, and 100% respectively. Through the traversal permutation and combination, 2*2*5=20 common target customer conditions to be deduced can be obtained. Of course, unreasonable common target customer conditions to be deduced can be screened according to actual conditions. For example, four common target customer conditions to be deduced are screened as shown in Table 3.

[0120] Secondly, we selected the real orders received by the logistics company in the past two weeks for deduction, and obtained the following results in Table 3:

[0121] Table 3. Preset general target customer condition identification test deduction results

[0122]

[0123] The first preset historical time period, the first preset order quantity and the first preset proportion may also be set in a variety of other data combinations.

[0124] (2) Obtaining optimal push record information that satisfies a load balancing condition from multiple push record information.

[0125] In the embodiment of the present application, the load balancing condition may be: the general push accuracy is greater than the preset general push accuracy, the general push coverage is greater than the preset general push coverage, and the sum of the general push accuracy and the general push coverage is greater than the general preset value. When there are multiple optimal push record information, the one with the largest sum of the general push accuracy and the general push coverage is selected.

[0126] For example, according to the comparison of the deduction results, in order to achieve a balanced optimal common push accuracy and common push coverage, the optimal push record information is that the common push accuracy and common push coverage are preset (selected) as 85.76% and 2.20% respectively.

[0127] (3) The common target customer condition to be derived corresponding to the optimal push record information is determined as the preset common target customer condition.

[0128] For example, the general push accuracy and general push coverage are preset (selected) as 85.76% and 2.20% respectively, and the data combination for setting the preset general target customer conditions is: the number of parcels sent in the past three months is ≥ 5, and the first preset proportion reaches more than 95%.

[0129] The setting of preset extreme target customer conditions also needs to consider its practicality. Practicality is also reflected in at least two aspects: extreme push accuracy and extreme push coverage.

[0130] Therefore, after the historical common standard order stored by the current customer is determined as the logistics order verification information and pushed to the recipient, it also includes:

[0131] (1) Acquiring a plurality of push record information of pushes performed under a plurality of conditions of the ultimate target customers to be deduced within a third preset historical time period, wherein the push record information includes an ultimate push accuracy rate and / or an ultimate push coverage rate.

[0132] The third preset time period can be set according to specific circumstances, such as two weeks. After the push is performed, the push record information can be obtained.

[0133] Specifically, multiple push record information pushed under multiple extreme target customer conditions to be deduced within the third preset historical time period is obtained according to a preset period, and the preset period can be two weeks or one month, etc., which is set according to specific circumstances. That is, the preset extreme target customer conditions are updated once every period of time according to the latest data.

[0134] Among them, after pushing the logistics order verification information to the recipient, the total number of orders of all customers in the entire logistics network within the third preset time period and the number of extreme push orders pushed to the extreme target customers within the third time period are counted. The extreme push coverage rate refers to: the ratio of the number of extreme push orders to the total number of orders.

[0135] Among all the extreme push orders, the orders in which the recipient has not modified the logistics order verification information are determined as the extreme standard orders that have been pushed correctly, and the orders in which the recipient has modified the logistics order verification information are determined as the extreme standard orders that have not been pushed correctly. The extreme push accuracy rate within the third preset time period can be counted.

[0136] Among them, the ultimate push accuracy rate of the preset ultimate target customer conditions refers to: the ratio of the number of correct ultimate standard orders to the number of pushed extreme standard orders.

[0137] First, multiple extreme target customer conditions to be derived can be determined according to the second preset historical time period, the second preset order quantity and the second preset proportion.

[0138] For example, the second preset historical time period is divided into 3 months and 4 months, that is, the retrospective historical time period is set to 3 months and 4 months; the second preset order quantity is 5 pieces or more and 10 pieces or more respectively; thus, it can be recorded as: the historical 3-month shipment volume ≥ 5 pieces, the historical 4-month shipment volume ≥ 5 pieces, the historical 3-month shipment volume ≥ 10 pieces, and the historical 4-month shipment volume ≥ 10 pieces; assuming that the aforementioned consignment name, weight, packaging material, product type, payment method and value-added service six-dimensional information are used as the second combination information, the second preset proportion is set to 80%, 85%, 95%, 95%, 100% respectively. Through the traversal permutation and combination, 2*2*5=20 extreme target customer conditions to be deduced can be obtained. Of course, unreasonable extreme target customer conditions to be deduced can be screened according to actual conditions. For example, four extreme target customer conditions to be deduced are screened as shown in Table 4.

[0139] Secondly, we selected the real orders received by the logistics company in the past two weeks for deduction, and obtained the following results in Table 4:

[0140] Table 4. Preset extreme target customer condition identification test deduction results

[0141]

[0142] The second preset historical time period, the second preset order quantity and the second preset proportion may also be set in a variety of other data combinations.

[0143] (2) Obtaining optimal push record information that satisfies a load balancing condition from multiple push record information.

[0144] In the embodiment of the present application, the load balancing condition may be: the ultimate push accuracy is greater than the preset ultimate push accuracy, the ultimate push coverage is greater than the preset ultimate push coverage, and the ultimate push accuracy and the ultimate push coverage are greater than the ultimate preset value. When there are multiple optimal push record information, the one with the largest sum of the ultimate push accuracy and the ultimate push coverage is selected.

[0145] For example, based on the comparison of the deduction results, in order to achieve the optimal balance between the ultimate push accuracy and the ultimate push coverage, the optimal push record information is that the ultimate push accuracy and the ultimate push coverage are preset (selected) as 68.79% and 3.82% respectively.

[0146] (3) The ultimate target customer condition to be derived corresponding to the optimal push record information is determined as the preset ultimate target customer condition.

[0147] For example, the ultimate push accuracy and ultimate push coverage are preset (selected) as 68.79% and 3.82% respectively. Then the data combination for setting the preset ultimate target customer conditions is: the number of parcels sent in the past three months is ≥5, and the second preset proportion is more than 80%.

[0148] In conventional logistics consignment activities, after a customer places an order in the logistics business system of the logistics carrier, a conventional order information page (e.g., three conventional order information pages) will be generated. The consignee of the logistics carrier will then collect the consignment from the customer based on the order information on the order information page, and check the collected consignment (or the consignor's verbal statement) with the corresponding order information on the real-time order information page. When the two are consistent, the consignment collection operation is confirmed to be completed. Since the order information on the order information integration page is correct by default, the consignee can simply check it, or even not check it.

[0149] In order to better implement the method for pushing logistics order verification information in the embodiment of the present application, on the basis of the method for pushing logistics order verification information, a device for pushing logistics order verification information is also provided in the embodiment of the present application, such as Figure 2 As shown, Figure 2 1 is a schematic diagram of a structure of an embodiment of a device for pushing logistics order verification information disclosed in an embodiment, and the device for pushing logistics order verification information includes:

[0150] The acquisition unit 201 is used to receive the real-time order sent by the current customer and acquire the pre-filled order information entered by the current customer on the real-time order;

[0151] The first judgment unit 202 is used to judge whether the current customer is a common target customer based on the product information, consignment information, historical consignment behavior information of the current customer and the preset common target customer conditions in the pre-filled order information;

[0152] The second judgment unit 203 is used to judge whether the type of the real-time order belongs to the ordinary standard order type based on the preset ordinary standard order classification model if the current customer belongs to the ordinary target customer;

[0153] The push unit 204 is used to determine the historical ordinary standard order pre-stored by the current customer as logistics order verification information and push it to the recipient when the type of the real-time order belongs to the ordinary standard order type.

[0154] The first judgment unit 202 is further used to judge whether the current customer is an extreme target customer based on the product information, consignment information, historical consignment behavior information of the current customer and the preset extreme target customer conditions in the pre-filled order information;

[0155] If the current customer is not an extreme target customer, it is determined whether the current customer is an ordinary target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset ordinary target customer conditions on the pre-filled order information.

[0156] The first judgment unit 202 is also used to obtain the identity information of the current customer;

[0157] Identify whether the current customer is a target customer based on the identity information of the current customer;

[0158] If the current customer is a target customer, determine whether the current customer is an extreme target customer based on the product information, consignment information, the current customer's historical consignment behavior information, and the preset extreme target customer conditions on the pre-filled order information.

[0159] The second judgment unit 203 is further configured to judge whether the type of the real-time order belongs to the extreme standard order type based on a preset extreme standard order classification model if the current customer belongs to the extreme target customer;

[0160] If the type of real-time order is an extreme standard order type, the current customer's pre-filled order information will be determined as logistics order verification information and pushed to the recipient.

[0161] Among them, ordinary target customers refer to customers whose historical consignment behavior information meets the preset ordinary target customer conditions; the preset ordinary target customer conditions are: within a first preset historical time period, the number of orders of the customer reaches a first preset order number, and the proportion of similar orders in all previous orders within the first preset historical time period is greater than the first preset proportion, wherein similar orders are orders with the same first combination information, and the first combination information is composed of at least one of the product information and at least one of the consignment information.

[0162] And / or, the ultimate target customer refers to a customer whose historical consignment behavior information meets the preset extreme target customer conditions; the preset extreme target customer conditions are: within a second preset historical time period, the customer's order quantity reaches a second preset order quantity, and the proportion of orders in which the second combination information has not been modified by the consignee in all previous orders within the second preset historical time period is greater than the second preset proportion, wherein the second combination information is composed of at least part of the information in the product information and at least part of the information in the consignment information.

[0163] The acquisition unit 201 is further used to acquire a preset common standard order training set, wherein orders in the common standard order training set whose customers meet the preset common target customer conditions are marked as common standard order types; orders in the common standard order training set whose customers do not meet the preset common target customer conditions are marked as non-common standard order types;

[0164] Training the first preset classification model based on a common single training set to obtain a common standard single classification model;

[0165] And / or, obtaining a preset extreme standard order training set, wherein orders in the extreme standard order training set from customers who meet preset extreme target customer conditions are marked as extreme standard order types; orders in the extreme standard order training set from customers who do not meet preset extreme target customer conditions are marked as non-extreme standard order types;

[0166] The second preset classification model is trained based on the extreme single training set to obtain the extreme standard single classification model.

[0167] The push unit 204 is further used to obtain a plurality of push record information pushed under the conditions of a plurality of common target customers to be deduced within a third preset historical time period, wherein the push record information includes a common push accuracy rate and / or a common push coverage rate;

[0168] Acquire optimal push record information satisfying a load balancing condition from multiple push record information;

[0169] The to-be-derived common target customer condition corresponding to the optimal push record information is determined as the preset common target customer condition.

[0170] The present application also provides an electronic device that integrates any of the logistics order verification information push devices provided in the present application. Figure 3 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0171] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0172] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0173] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0174] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0175] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0176] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0177] Receive the real-time order sent by the current customer, and obtain the pre-filled order information entered by the current customer on the real-time order;

[0178] Based on the product information, consignment information, historical consignment behavior information of the current customer and the preset common target customer conditions in the pre-filled order information, determine whether the current customer is a common target customer;

[0179] If the current customer is a common target customer, determine whether the type of the real-time order belongs to the common standard order type based on the preset common standard order classification model;

[0180] When the type of the real-time order belongs to the ordinary standard order type, the historical ordinary standard order pre-stored by the current customer is determined as the logistics order verification information and pushed to the recipient.

[0181] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0182] To this end, the embodiment of the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the methods for pushing logistics order verification information provided in the embodiment of the present application. For example, the computer program loaded by the processor can execute the following steps:

[0183] Receive the real-time order sent by the current customer, and obtain the pre-filled order information entered by the current customer on the real-time order;

[0184] Based on the product information, consignment information, historical consignment behavior information of the current customer and the preset common target customer conditions in the pre-filled order information, determine whether the current customer is a common target customer;

[0185] If the current customer is a common target customer, determine whether the type of the real-time order belongs to the common standard order type based on the preset common standard order classification model;

[0186] When the type of the real-time order belongs to the ordinary standard order type, the historical ordinary standard order pre-stored by the current customer is determined as the logistics order verification information and pushed to the recipient.

[0187] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0188] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous method embodiments, which will not be repeated here.

[0189] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0190] The above is a detailed introduction to a method, device, electronic device and storage medium for pushing logistics order verification information provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for pushing logistics order verification information, characterized in that: The following steps are involved: Obtaining a preset common standard order training set, wherein orders from customers in the common standard order training set that meet preset common target customer conditions are marked as common standard order types; Receiving a real-time order placed by a current customer, and obtaining pre-filled order information entered by the current customer on the real-time order; Based on the product information, consignment information, historical consignment behavior information of the current customer and the preset common target customer conditions in the pre-filled order information, determining whether the current customer is a common target customer; If the current customer is a common target customer, judging whether the type of the real-time order belongs to a common standard order type based on a preset common standard order classification model; When the type of the real-time order belongs to the common standard order type, the historical common standard order pre-stored by the current customer is determined as the logistics order verification information and pushed to the recipient; Among them, the general target customer refers to a customer whose historical consignment behavior information meets the preset general target customer conditions; the preset general target customer conditions are: within a first preset historical time period, the customer's order quantity reaches a first preset order quantity, and the proportion of similar orders in all previous orders within the first preset historical time period is greater than the first preset proportion, wherein the similar orders are orders with the same first combination information, and the first combination information is composed of at least one of the product information and at least one of the consignment information.

2. The method for pushing logistics order verification information according to claim 1, characterized in that: The determining whether the current customer is a common target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset common target customer conditions in the pre-filled order information includes: Based on the product information, consignment information, historical consignment behavior information of the current customer and the preset ultimate target customer conditions in the pre-filled order information, determine whether the current customer is an ultimate target customer; If the current customer is not an extreme target customer, judging whether the current customer is an ordinary target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset ordinary target customer conditions in the pre-filled order information; Among them, the extreme target customer refers to a customer whose historical consignment behavior information meets the preset extreme target customer conditions; the preset extreme target customer conditions are: within a second preset historical time period, the customer's order quantity reaches a second preset order quantity, and the proportion of orders in which the second combination information has not been modified by the consignee in all previous orders within the second preset historical time period is greater than the second preset proportion, wherein the second combination information is composed of at least part of the information in the product information and at least part of the information in the consignment information.

3. The method for pushing logistics order verification information according to claim 2, characterized in that: The determining whether the current customer is an extreme target customer based on the product information, consignment information, historical consignment behavior information of the current customer and preset extreme target customer conditions in the pre-filled order information includes: Obtaining the identity information of the current customer; Identify whether the current customer is a target customer based on the identity information of the current customer; If the current customer is a target customer, determine whether the current customer is an extreme target customer based on the product information, consignment information, the current customer's historical consignment behavior information, and the preset extreme target customer conditions in the pre-filled order information; The target customers are customers who have historical orders with the logistics carrier.

4. The method for pushing logistics order verification information according to claim 2, characterized in that: The method for pushing logistics order verification information also includes: Obtaining a preset extreme standard order training set, wherein orders from customers in the extreme standard order training set that meet preset extreme target customer conditions are marked as extreme standard order types; If the current customer is an extreme target customer, judging whether the type of the real-time order belongs to the extreme standard order type based on a preset extreme standard order classification model; If the type of the real-time order is an extreme standard order type, the pre-filled order information of the current customer is determined as logistics order verification information and pushed to the recipient.

5. The method for pushing logistics order verification information according to claim 4 is characterized in that: The receiving of the real-time order entrusted by the current customer and obtaining the pre-filled order information entered by the current customer on the real-time order includes: In the ordinary standard order training set, orders from customers who do not meet the preset ordinary target customer conditions are marked as non-ordinary standard order types; Training the first preset classification model based on a common single training set to obtain the common standard single classification model; Orders from customers who do not meet the preset extreme target customer conditions in the extreme standard order training set are marked as non-extreme standard order types; The second preset classification model is trained based on the extreme single training set to obtain the extreme standard single classification model.

6. The method for pushing logistics order verification information according to claim 1, characterized in that: When the type of the real-time order belongs to the type of common standard order, the historical common standard order pre-stored by the current customer is determined as the logistics order verification information and pushed to the recipient, and then includes: Acquire a plurality of push record information pushed under a plurality of conditions of common target customers to be deduced within a third preset historical time period, wherein the push record information includes a common push accuracy rate and / or a common push coverage rate; Acquire the optimal push record information satisfying the load balancing condition from the plurality of push record information; The to-be-derived common target customer condition corresponding to the optimal push record information is determined as the preset common target customer condition.

7. A device for pushing logistics order verification information, characterized in that: include: An acquisition unit, configured to receive a real-time order placed by a current customer and acquire pre-filled order information entered by the current customer on the real-time order; A first judgment unit, configured to judge whether the current customer is a common target customer based on product information, consignment information, historical consignment behavior information of the current customer and preset common target customer conditions in the pre-filled order information; A second judgment unit is used to judge whether the type of the real-time order belongs to the common standard order type based on a preset common standard order classification model if the current customer belongs to the common target customer; A push unit, used for determining the historical common standard order pre-stored by the current customer as logistics order verification information and pushing it to the consignee when the type of the real-time order belongs to the common standard order type; The acquisition unit is further used to acquire a preset common standard order training set, wherein orders from customers in the common standard order training set that meet preset common target customer conditions are marked as common standard order types; The general target customer refers to a customer whose historical consignment behavior information meets the preset general target customer conditions; the preset general target customer conditions are: within a first preset historical time period, the customer's order quantity reaches a first preset order quantity, and the proportion of similar orders in all previous orders within the first preset historical time period is greater than the first preset proportion, wherein the similar orders are orders with the same first combination information, and the first combination information is composed of at least one of the product information and at least one of the consignment information.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method for pushing logistics order verification information as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the method for pushing logistics order verification information as described in any one of claims 1 to 6.

Images