Intelligent logistics distribution optimization method and device based on address portrait, and electronic equipment

Abstract

The invention relates to an intelligent logistics distribution optimization method and device based on an address portrait and electronic equipment, and the method comprises the steps: analyzing the original address text information of a distribution address, and obtaining the corresponding address information; generating an address portrait containing the corresponding address information, the optimal delivery time period set and the delivery difficulty coefficient for the delivery address; wherein the distribution difficulty coefficient is associated with the average distribution times, the average waiting duration, the first distribution failure rate and the penalty factor of the historical distribution waybill corresponding to the distribution address; and according to the information of the address portraits corresponding to the plurality of delivery addresses contained in the to-be-delivered task and the predicted delivery duration, constructing an optimal delivery function, and solving and generating an optimal delivery path of the to-be-delivered task. According to the invention, the address portrait is established for the distribution address, and the distribution path of the distribution task is optimized and the time period is arranged according to the portrait, so that the logistics distribution efficiency is improved, and the logistics cost is reduced.

Description

Technical Field

[0001] This application relates to the field of logistics technology, and in particular to an intelligent logistics delivery optimization method, apparatus and electronic device based on address profiling. Background Technology

[0002] With the development of the domestic internet and the rise of e-commerce platforms, the express delivery industry has gradually entered a period of rapid development. The logistics and distribution system has evolved from a traditional basic service support to a core strategic element that determines the market competitiveness of enterprises.

[0003] However, the current logistics and distribution system still has significant bottlenecks in terms of intelligence, refinement and humanization. Specifically, it ignores the spatiotemporal heterogeneity of the delivery scenario, resulting in low delivery efficiency, high cost, and the single assessment of delivery performance cannot truly reflect the labor value of delivery personnel. For example, (1) traditional delivery technology relies too much on the linear calculation of geographical distance and ignores the differences in delivery time for different delivery addresses. For example, commercial complexes have a significant "delivery window" (11:00-14:00) during weekday lunch hours, while the signing rate of residential areas is 42% higher in the evening (18:00-20:00) than on weekdays. This time and space mismatch leads to an average of 1.8 hours of invalid waiting time for delivery personnel per day, with a duplicate delivery rate as high as 17.3%; (2) For delivery orders with the delivery address in the city center office building, delivery personnel need to deal with 12 additional risks such as illegal parking monitoring, elevator queuing, and front desk collection. The time taken for a single item is 3.2 times that of delivery orders with the delivery address in the suburbs. However, the existing delivery performance assessment adopts a unified performance standard, ignoring the complex differences between different delivery orders during delivery. Summary of the Invention

[0004] To address or partially address the problems existing in related technologies, this application provides a method, apparatus, and electronic device for optimizing intelligent logistics distribution based on address profiling.

[0005] The first aspect of this application provides an intelligent logistics delivery optimization method based on address profiling, comprising: parsing the original address text information of the delivery address to obtain its corresponding address information; generating an address profile for the delivery address containing its corresponding address information, an optimal delivery time period set, and a delivery difficulty coefficient; wherein the optimal delivery time period set is associated with the delivery time distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address; constructing an optimal delivery function based on the address profile information of several delivery addresses included in the task to be delivered, and the predicted delivery time, and solving to generate the optimal delivery path for the task to be delivered.

[0006] In conjunction with the first aspect, one possible implementation of the first aspect further includes: calculating the delivery difficulty coefficient of the delivery address according to the following formula:

[0007] in, The delivery difficulty coefficient for the delivery address; The average number of times that a historical waybill for the delivery address was attempted and successfully delivered; The average waiting time after historical waybills were delivered to the delivery address; The first delivery failure rate for historical waybills to the aforementioned delivery address; A penalty factor determined for the delivery address based on special event information extracted from its address information; , , , These are the first weight parameter, the second weight parameter, the third weight parameter, and the fourth weight parameter, respectively.

[0008] In conjunction with the first aspect, one possible implementation of the first aspect further includes: fitting a Gaussian mixture model to the delivery time period dataset corresponding to the historical successful delivery orders of the delivery address to obtain at least one Gaussian distribution peak; and determining the time interval corresponding to the Gaussian distribution peak as the optimal delivery time period set for the delivery address.

[0009] In conjunction with the first aspect, in one possible implementation of the first aspect, the step of constructing an optimal delivery function based on the address profile information corresponding to several delivery addresses included in the delivery task, and the predicted delivery time, includes:

[0010]

[0011] in, The optimal delivery function seeks to minimize the planned delivery paths for the task to be delivered under the constraints, and the delivery path corresponding to the minimum value is taken as the optimal delivery path. The total predicted delivery time for the tasks to be delivered; This is the sum of the delivery difficulty coefficients corresponding to each delivery address in the task to be delivered; The sum of penalty values ​​for each delivery address in the pending delivery task deviating from its corresponding optimal delivery time set; The planned delivery time slot for the current delivery address in the task to be delivered; This refers to the optimal delivery time slot set corresponding to the current delivery address among the delivery addresses; , and These are the fifth, sixth, and seventh weight parameters, respectively.

[0012] In conjunction with the first aspect, in one possible implementation of the first aspect, parsing the original address text information of the delivery address to obtain its corresponding address information includes: performing natural language processing on the original address text information to obtain standard address text information; extracting features from the standard address text information using a preset business customer keyword library, personal customer keyword library, POI point of interest database, and target classification model to generate candidate addresses and their corresponding address information; calculating the confidence level of the candidate address based on the historical call count of the candidate address, the maximum historical call count of the candidate address, the average distance between the order location and the actual location of the historical waybill of the candidate address, and the on-time delivery rate of the historical waybill of the candidate address; determining the candidate address with a confidence level greater than a preset threshold as the delivery address, and obtaining the address information corresponding to the delivery address.

[0013] In conjunction with the first aspect, in one possible implementation of the first aspect, calculating the confidence level of the candidate address based on the historical call count of the candidate address, the maximum historical call count of the candidate address, the average distance between the order location and the actual location of the historical waybill of the candidate address, and the on-time delivery rate of the historical waybill of the candidate address includes: The confidence level of the candidate address is calculated using the following formula:

[0014] in, The confidence level of the candidate address; The number of historical calls to the candidate address; The maximum number of historical calls among the candidate addresses; This is the average distance between the reported location and the actual location of the historical waybill; The number of times the historical waybills were delivered on time; , , These are the eighth, ninth, and tenth weight parameters, respectively.

[0015] A second aspect of this application provides a performance evaluation method based on address profiling, comprising calculating the performance score of the delivery person within an evaluation period based on a performance formula constructed from the number of completed deliveries of each delivery order, the base score corresponding to each delivery order, and the delivery difficulty coefficient contained in the address profiling of each historical delivery order's delivery address; the performance formula includes:

[0016] in, The performance score of the delivery person; Complete the first The basic score corresponding to each delivery order; For the first The delivery difficulty level of each delivery order; For the first The preset difficulty reward coefficient for each delivery order; The first in the pending delivery task Penalty score for each delivery order.

[0017] A third aspect of this application provides an intelligent logistics delivery optimization device based on address profiling, comprising: an acquisition module for parsing the original address text information of a delivery address to obtain its corresponding address information; a generation module for generating an address profile for the delivery address containing its corresponding address information, an optimal delivery time period set, and a delivery difficulty coefficient; wherein the optimal delivery time period set is associated with the delivery time period distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address; and a processing module for constructing an optimal delivery function based on the address profile information of several delivery addresses included in the task to be delivered, and the predicted delivery time, and solving to generate the optimal delivery path for the task to be delivered.

[0018] A fourth aspect of this application provides an electronic device, comprising: Processor; and A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0019] A fifth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0020] The technical solution provided in this application may include the following beneficial effects: This application discloses an intelligent logistics delivery optimization method, apparatus, and electronic device based on address profiling, comprising: parsing the original address text information of the delivery address to obtain its corresponding address information; generating an address profile for the delivery address containing its corresponding address information, an optimal delivery time slot set, and a delivery difficulty coefficient; wherein, the optimal delivery time slot set is associated with the delivery time distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first-time delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address; constructing an optimal delivery function based on the address profile information of several delivery addresses included in the task to be delivered, and predicting the delivery time, and solving to generate the optimal delivery path for the task to be delivered. This scheme, by establishing address profiles for delivery addresses and optimizing the delivery path and time slot arrangement of delivery tasks based on these profiles, improves logistics delivery efficiency and reduces logistics costs.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0022] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0023] Figure 1 This is a flowchart illustrating the intelligent logistics delivery optimization method based on address profiling, as shown in an embodiment of this application. Figure 2 This is a schematic diagram of the structure of an intelligent logistics distribution optimization device based on address profiling, as shown in an embodiment of this application. Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application; Figure 4 This is a schematic block diagram of the structure of a computer storage medium provided in an embodiment of this application. Detailed Implementation

[0024] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0025] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0027] With the development of the domestic internet and the rise of e-commerce platforms, the express delivery industry has gradually entered a period of rapid development. Addresses play a crucial role in both the express delivery and e-commerce industries, containing the sender's and recipient's residential address, workplace, social and commuting information. The efficiency of package pickup and delivery in the express delivery industry is closely related to addresses.

[0028] In related technologies, common delivery tasks form a delivery route based on multiple delivery addresses. Delivery personnel deliver according to the addresses on the delivery route in sequence. However, the delivery route generation process does not take into account the delivery data of the delivery addresses themselves, resulting in low delivery efficiency of the generated delivery route.

[0029] To address the aforementioned problems, this application provides an intelligent logistics delivery optimization method, apparatus, and electronic device based on address profiling. This method can generate an address profile containing optimal delivery time and delivery difficulty coefficients by parsing address information, and construct an optimal delivery function solution path to improve logistics delivery efficiency and reduce logistics costs. The technical solutions of this application embodiment are described in detail below with reference to the accompanying drawings.

[0030] It should be noted that the acquisition of any information involved in the provided methods is in compliance with relevant regulations and is carried out with the user's consent, and will not infringe on the user's privacy or violate relevant laws and regulations.

[0031] Figure 1This is a flowchart illustrating an intelligent logistics delivery optimization method based on address profiling, as shown in an embodiment of this application. The method can be implemented using computer equipment, which can be deployed on a single server or a server cluster. It can also be deployed on handheld terminals, laptops, wearable devices, or robots, etc.

[0032] See Figure 1 A smart logistics delivery optimization method based on address profiling includes: S110: Parse the original address text information of the delivery address to obtain its corresponding address information.

[0033] Specifically, the original address text information can be unprocessed textual descriptions provided by the customer, containing the recipient's address and remarks. Depending on the recipient, delivery addresses can be categorized into Class B and Class C addresses. Class B addresses are for business customers, while Class C addresses are for individual customers. There are significant differences between Class B and Class C addresses in terms of delivery time, geographical location, and delivery process.

[0034] In one possible implementation, the original address text information of the delivery address is parsed to obtain its corresponding address information, including: performing natural language processing on the original address text information to obtain standard address text information; extracting features from the standard address text information using a preset business customer keyword library, personal customer keyword library, POI point of interest database, and target classification model to generate candidate addresses and their corresponding address information; calculating the confidence level of the candidate address based on the candidate address's historical call count, the maximum historical call count among the candidate addresses, the average distance between the order location and actual location of the candidate address's historical waybill, and the on-time delivery rate of the candidate address's historical waybill; and determining the candidate address with a confidence level greater than a preset threshold as the delivery address and obtaining the address information corresponding to the delivery address.

[0035] Specifically, the original address text information can first be preprocessed using NLP (Natural Language Processing) to perform word segmentation, part-of-speech tagging, and other processing. After removing redundant words, special symbols, names, phone numbers, and other information from the original address text information, standard address text information can be obtained.

[0036] The system performs rule matching based on regular expressions, comparing the results with a pre-defined database of business customer keywords, personal customer keywords, and Points of Interest (POI) databases. It also uses a target classification model for machine learning classification to identify and extract feature values ​​from standard address text information, generating address information. The business customer keyword database can include names of large enterprises, chain stores, office buildings, etc.; the personal customer keyword database can include names of residential communities, apartment buildings, etc.; the POI database provides detailed information on geographical locations (such as shopping malls, schools, hospitals); and the target classification model can be an SVM model, CNN model, etc. This model identifies key components of the address (such as province, city, district, street, house number, building name, etc.). The identified and extracted feature values ​​include address type labels (Class B / Class C), POI type codes, administrative division codes, street names, street numbers, buildings, industrial parks, villages, groups, and individual buildings.

[0037] The address information obtained from processing the original address text information is used as a candidate address. It must undergo a confidence assessment before being confirmed as a delivery address for subsequent address profiling. The confidence level of a candidate address is calculated based on historical delivery data, including the number of historical calls to the candidate address, the maximum number of historical calls to the candidate address, the average distance between the reported location and the actual location of historical waybills for the candidate address, and the on-time delivery rate of historical waybills for the candidate address.

[0038] In one possible implementation, the confidence level of a candidate address is calculated based on the candidate address's historical call count, the candidate address's maximum historical call count, the average distance between the declared location and actual location of historical waybills for the candidate address, and the candidate address's historical on-time delivery rate. This includes calculating the confidence level of the candidate address according to the following formula:

[0039] in, The confidence level of the candidate address; The historical call count for the candidate address; The maximum number of historical calls among the candidate addresses; This is the average distance between the reported location and the actual location of historical waybills; The number of on-time deliveries for historical waybills; , , These are the eighth, ninth, and tenth weight parameters, respectively.

[0040] Specifically, the historical call count reflects the frequency with which the address is identified and used; a higher call count generally indicates a more reliable address. The average distance between the order location and the actual location reflects the deviation between the address entered by the user when submitting the waybill and the actual delivery location; a smaller deviation indicates a more accurate address. The on-time delivery rate reflects the success rate and timeliness of delivery to that address; a higher on-time delivery rate generally indicates more accurate address information and lower delivery difficulty. Weighting parameters. , , It can be preset, for example, It can be 0.3. It can be 0.4. The confidence level can be 0.3. The confidence level is calculated using a formula and is a value between 0 and 1. The higher the value, the more reliable the candidate address. The confidence level calculated using multiple parameters can more comprehensively determine the accuracy of the candidate address.

[0041] After calculating the confidence level of candidate addresses, candidate addresses with a confidence level greater than a preset threshold are identified as delivery addresses. The preset threshold can be set in advance, for example, to 0.6.

[0042] For example, candidate address A has a history of 550 calls, the average distance between the declared location and the actual location of historical waybills is 10 meters, the number of on-time deliveries of historical waybills is 540, and the maximum number of historical calls among all candidate addresses is 600. It is 0.3. It is 0.4. If the confidence level is 0.3, then the confidence level of candidate address A is 0.602. If the preset threshold is 0.6, then the confidence level of candidate address A is greater than the preset threshold, and candidate address A can be used as the delivery address.

[0043] The embodiments of the present invention can filter out addresses with high confidence as delivery addresses, which can then be used as objects for subsequent address profiling, thereby improving the accuracy of delivery route planning.

[0044] S120: Generate an address profile for the delivery address, including its corresponding address information, optimal delivery time slot set, and delivery difficulty coefficient; wherein, the optimal delivery time slot set is associated with the delivery time distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address.

[0045] Specifically, by combining the address information corresponding to each delivery address, as well as the optimal delivery time period set and delivery difficulty coefficient, a corresponding address profile is generated for each delivery address.

[0046] The optimal delivery time period set is the set of time intervals in which historical delivery orders for the delivery address have a high success rate or efficiency, obtained by the distribution of delivery time periods of historical delivery orders corresponding to the delivery address.

[0047] In one possible implementation, a Gaussian mixture model is used to fit the dataset of delivery time periods corresponding to historical successful delivery orders for the delivery address to obtain at least one Gaussian distribution peak; the time interval corresponding to the Gaussian distribution peak is determined as the optimal delivery time period set for the delivery address.

[0048] Specifically, a dataset of delivery time slots corresponding to historical successful delivery orders for a delivery address can be obtained. Since different delivery addresses exhibit significant differences in their optimal delivery time slot sets depending on whether the user is a business or individual customer and their delivery preferences, a Gaussian Mixture Model (GMM) can be used to decompose the entire dataset into a weighted sum of several Gaussian components, each representing a potential delivery preference time slot. During the fitting process, the GMM adaptively learns the mean, variance, and weight of each Gaussian component, enabling the model to best describe the distribution of historical delivery time slots. After fitting, the GMM can identify at least one Gaussian distribution peak, each peak corresponding to a concentrated period with a high historical delivery success rate. Then, based on the mean and standard deviation of each Gaussian distribution peak, a specific time interval is determined. These time intervals are then statistically analyzed to obtain the optimal delivery time slot set for that delivery address. This optimal delivery time slot set provides reliable parameters for subsequently constructing the optimal delivery function and solving for the optimal delivery route, thereby improving delivery efficiency.

[0049] The delivery difficulty coefficient reflects the delivery complexity of the delivery address and is related to the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address.

[0050] In one possible implementation, the delivery difficulty coefficient of the delivery address is calculated according to the following formula:

[0051] in, The delivery difficulty level of the delivery address; The average number of times a historical waybill for a delivery address was attempted and successfully delivered; This represents the average waiting time after a historical waybill has been delivered to the delivery address; The first-time delivery failure rate for historical waybills at the delivery address; The penalty factor is determined for the delivery address based on special event information extracted from its address information; , , , These are the first weight parameter, the second weight parameter, the third weight parameter, and the fourth weight parameter, respectively.

[0052] Specifically, To determine the average number of delivery attempts required to successfully complete a delivery for a given historical order address, we can indirectly reflect the delivery difficulty of that address. This can be achieved by extracting the number of delivery attempts for each order from the historical order database and then calculating the average for all orders at that address. This refers to the average time a delivery person spends waiting for the recipient or completing other necessary operations (such as signing for or verifying the delivery) at the delivery address after successfully delivering the waybill. It can indirectly reflect the time consumption dimension of that delivery address. This refers to the proportion of waybills that fail on their first delivery attempt for that delivery address. For example, it represents the ratio of the number of waybills with a failed first delivery status to the total number of waybills in the historical order data. The first delivery failure rate is related to factors such as road restrictions at the delivery address, delivery company holidays, customer off-hours adjustments, and inaccurate customer location tracking. This is used to determine the penalty factor based on the extracted special event information. For example, if the delivery address is located in a traffic-controlled area, a high-risk area, or has special delivery requirements (such as requiring an appointment, delivery within a specific time period, or delivery upstairs), the penalty factor will increase accordingly. , , , The delivery difficulty coefficient of the delivery address can be calculated based on the above parameters, which can be set according to actual needs. This allows for accurate assessment and consideration of the difficulty of different delivery addresses when planning delivery routes, thereby generating the optimal delivery route with higher delivery efficiency and lower logistics costs.

[0053] For example, for a delivery address A, the average number of successful delivery attempts is 1.5, the average waiting time is 5 minutes, and the first-time delivery failure rate is 0.2. Since this address is located in an industrial park that requires advance booking, the penalty factor can be determined to be 0.3. , , , If the values ​​are 0.4, 0.2, 0.3, and 0.1 respectively, then the delivery difficulty coefficient for that delivery address can be calculated. It is 1.69.

[0054] Based on the address information corresponding to the delivery address, the optimal delivery time slot set, and the delivery difficulty coefficient, an address profile is created for each delivery address. For example, the address profile information for each delivery address can be expressed as follows: Profile = {T_location, BC_Type, T_optimal, D_score, T_aoi, building_type} In the expression, T_loccation represents the address location, which is the customer location matched by POI, street name, street number, building, park, village, and directional words in the address information; BC_Type represents the address type; T_optimal represents the optimal delivery time period set; D_score represents the delivery difficulty coefficient; T_aoi represents whether it is a park; and building_type represents the building.

[0055] This invention creates an address profile for delivery addresses, and based on the address information, it depicts the optimal delivery time slot set and delivery difficulty coefficient information. This enables refined identification and classification of delivery address attributes, effectively supporting accurate planning of delivery time slots and dynamic optimization of delivery routes, and reducing invalid deliveries and waiting times caused by address type misjudgment or information ambiguity.

[0056] In one possible implementation, a timed task is set to recalculate the optimal delivery time slot set and delivery difficulty coefficient for delivery addresses in areas affected by road segments, weather, commuting hours, and holidays, and update the address profile information.

[0057] This invention automatically monitors dynamic changes in local holidays, road restrictions, weather, and commuting times, and automatically updates the address profiles of affected delivery addresses, thereby improving the accuracy of subsequent delivery task planning and delivery efficiency.

[0058] S130: Based on the address profile information corresponding to several delivery addresses included in the task to be delivered, and the predicted delivery time, construct the optimal delivery function and solve for the optimal delivery path to generate the task to be delivered.

[0059] Specifically, a delivery task typically includes multiple delivery orders, each with a different delivery address. Delivery personnel need to deliver these orders to each address. A delivery function is constructed based on the address profile information corresponding to each delivery address and the predicted total delivery time. The optimal delivery route is then planned to minimize the calculated delivery time. The resulting optimal delivery route plan includes the delivery order, geographical navigation path, and delivery time period for each delivery order within the delivery task.

[0060] In one possible implementation, an optimal delivery function is constructed based on address profile information corresponding to several delivery addresses included in the delivery task, and the predicted delivery time, including:

[0061]

[0062] in, The optimal delivery function seeks to minimize the planned delivery paths for the task to be delivered under the constraints. The delivery path corresponding to the minimum value is taken as the optimal delivery path, which can be understood as taking the delivery path with the shortest total delivery time. The total predicted delivery time for the tasks to be delivered; This is the sum of the delivery difficulty coefficients corresponding to each delivery address in the pending delivery task; This is the sum of penalty values ​​for each delivery address in the pending delivery task whose planned delivery time deviates from its corresponding optimal delivery time set; The planned delivery time slot for the current delivery address in the pending delivery task; This is the set of optimal delivery time slots corresponding to the current delivery address in the delivery address list; , and These are the fifth, sixth, and seventh weight parameters, respectively.

[0063] In the optimal delivery function The inclusion of this means that when allocating delivery orders, there should be a tendency to distribute the more difficult orders among the delivery tasks, or to assign the delivery task to a delivery person with the appropriate ability. As a time-time deviation penalty, it means that when planning routes, the planned delivery time for each delivery address should be within the optimal delivery time period set of its address profile as much as possible; otherwise, a penalty will be imposed. The deviation penalty value can be dynamically set according to the duration of the deviation. , and This is used to balance the importance of time, difficulty, and time-segment suitability in route planning. Solving this optimal delivery function is an NP-hard problem, and can be exemplified by using metaheuristic algorithms, such as genetic algorithms or ant colony algorithms, to obtain an approximate optimal solution within a reasonable time. Since the solution method is existing technology, it will not be elaborated upon here.

[0064] This invention establishes address profiles for delivery addresses and optimizes delivery routes and time slots based on these profiles. This enables refined identification and classification of delivery address attributes, effectively supporting precise planning of delivery time slots and optimization of routes. It also reduces invalid deliveries and waiting times caused by address type misjudgments or ambiguous information, thereby increasing the average number of deliveries per person per day, significantly improving the overall logistics capacity utilization rate, and reducing logistics costs.

[0065] This application also provides a performance evaluation method based on address profiles. The method includes: calculating the delivery person's performance score within the evaluation period using a performance formula constructed from the number of completed deliveries for each delivery order, the base score corresponding to each delivery order, and the delivery difficulty coefficient contained in the address profiles of the delivery addresses for each historical delivery order; the performance formula includes:

[0066] in, For delivery personnel's performance scores; Complete the first The basic score corresponding to each delivery order; For the first The delivery difficulty level of each delivery order; For the first The preset difficulty reward coefficient for each delivery order; The first in the pending delivery task Penalty score for each delivery order.

[0067] Specifically, each delivery order can be pre-set with a base score and a preset difficulty reward coefficient based on the delivery difficulty level. This allows orders with higher delivery difficulty to receive higher reward coefficients for extra performance bonuses. This means that delivery personnel's performance evaluations are no longer solely based on the number of deliveries, but are dynamically adjusted based on the difficulty of the delivery orders. The delivery difficulty coefficient of a delivery order is derived from the delivery difficulty coefficient information in the address profile of the corresponding delivery address. For details on obtaining the address profile and delivery difficulty coefficient, please refer to the explanation of the intelligent logistics delivery optimization method based on address profiles above.

[0068] For example, if a delivery person completes 600 delivery orders, including 300 high-difficulty delivery orders (difficulty coefficient greater than 1.5), and the base score for each delivery order is set to 1 and the difficulty bonus coefficient is 0.5, their performance score can include bonus points for the high-difficulty delivery orders, thereby achieving higher performance.

[0069] In this embodiment of the invention, by introducing a delivery difficulty coefficient from the address profile, the assessment of delivery performance is transformed from a single "order volume" orientation to a comprehensive evaluation model that emphasizes both "order volume and delivery quality (difficulty)". This not only effectively improves the delivery personnel's sense of fairness, but also enhances their work enthusiasm and encourages them to take the initiative to undertake high-difficulty delivery tasks, thereby improving overall delivery efficiency.

[0070] This application discloses an intelligent logistics delivery optimization method based on address profiling, comprising: parsing the original address text information of the delivery address to obtain its corresponding address information; generating an address profile for the delivery address containing its corresponding address information, an optimal delivery time slot set, and a delivery difficulty coefficient; wherein, the optimal delivery time slot set is associated with the delivery time distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first-time delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address; constructing an optimal delivery function based on the address profile information of several delivery addresses included in the delivery task, and predicting the delivery time, and solving to generate the optimal delivery path for the delivery task. This scheme, by establishing address profiles for delivery addresses and optimizing the delivery path and time slot arrangement of delivery tasks based on these profiles, improves logistics delivery efficiency and reduces logistics costs.

[0071] Corresponding to the aforementioned application function implementation method embodiments, this application also provides an intelligent logistics distribution optimization device, electronic device, and corresponding embodiments based on address profiling.

[0072] Figure 2 This is a schematic diagram of the structure of an intelligent logistics distribution optimization device based on address profiling, as shown in an embodiment of this application.

[0073] See Figure 2 A smart logistics delivery optimization device 200 based on address profiling includes: The acquisition module 210 is used to parse the original address text information of the delivery address and obtain its corresponding address information.

[0074] The generation module 220 is used to generate an address profile for the delivery address, which includes the corresponding address information, the optimal delivery time period set, and the delivery difficulty coefficient. The optimal delivery time period set is associated with the delivery time period distribution of the historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of the historical delivery orders corresponding to the delivery address.

[0075] The processing module 230 is used to construct an optimal delivery function based on the address profile information corresponding to several delivery addresses included in the task to be delivered, as well as the predicted delivery time, and to solve for the optimal delivery path to generate the task to be delivered.

[0076] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0077] For further details regarding the implementation of the above-mentioned technical solutions by each module in the intelligent logistics distribution optimization device based on address profiling, please refer to the description in the intelligent logistics distribution optimization method based on address profiling provided in the above-mentioned embodiments of the invention, which will not be repeated here.

[0078] Based on the above-described intelligent logistics delivery optimization method based on address profiling, this invention also provides an intelligent logistics delivery optimization processing device based on address profiling, as shown in the schematic diagram below. Figure 3 As shown, the address-based intelligent logistics delivery optimization device 300 includes a processor 301 and a memory 302 coupled to the processor 301. The memory 302 stores a computer program, which, when executed by the processor 301, causes the processor 301 to perform the steps of the address-based intelligent logistics delivery optimization method in the above embodiments.

[0079] For further details regarding the implementation of the above-mentioned technical solution by the processor 301 in the intelligent logistics distribution optimization processing device based on address profiling, please refer to the description in the intelligent logistics distribution optimization method based on address profiling provided in the above-mentioned embodiments of the invention, which will not be repeated here.

[0080] The processor 301 can also be called a CPU (Central Processing Unit). The processor 301 may be an integrated circuit chip with signal processing capabilities. The processor 301 may also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor may be a microprocessor, or the processor 301 may be any conventional processor.

[0081] This invention also provides a computer-readable storage medium, the structure of which is illustrated in the following diagram: Figure 4As shown, the storage medium 400 stores a readable computer program 401. This computer program 401 can be stored in the storage medium as a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks or optical disks, ROM (Read-Only Memory), RAM (Random Access Memory), or terminal devices such as computers, servers, mobile phones, and tablets.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or modules, and may be electrical, mechanical, or other forms.

[0083] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0084] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0085] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0086] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0087] The technical solutions provided in this application have been described in detail above. Specific examples have been used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0088] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0092] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for optimizing intelligent logistics delivery based on address profiling, characterized in that, include: The original address text information of the delivery address is parsed to obtain its corresponding address information; An address profile is generated for the delivery address, including its corresponding address information, optimal delivery time slot set, and delivery difficulty coefficient; wherein, the optimal delivery time slot set is associated with the delivery time slot distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address; Based on the address profile information corresponding to several delivery addresses included in the delivery task, and the predicted delivery time, an optimal delivery function is constructed to solve for and generate the optimal delivery path for the delivery task.

2. The method according to claim 1, characterized in that, Also includes: The delivery difficulty coefficient for the delivery address is calculated using the following formula: in, The delivery difficulty coefficient for the delivery address; The average number of times that a historical waybill for the delivery address was attempted and successfully delivered; The average waiting time after historical waybills were delivered to the delivery address; The first delivery failure rate for historical waybills to the aforementioned delivery address; A penalty factor determined for the delivery address based on special event information extracted from its address information; , , , These are the first weight parameter, the second weight parameter, the third weight parameter, and the fourth weight parameter, respectively.

3. The method according to claim 1, characterized in that, Also includes: A Gaussian mixture model was used to fit the delivery time dataset corresponding to the historical successful delivery orders of the delivery address to obtain at least one Gaussian distribution peak. The time interval corresponding to the peak value of the Gaussian distribution is determined as the optimal delivery time period set for the delivery address.

4. The method according to claim 1, characterized in that, The step of constructing an optimal delivery function based on address profile information corresponding to several delivery addresses included in the delivery task, and predicted delivery time, includes: in, The optimal delivery function seeks to minimize the planned delivery paths for the task to be delivered under the constraints, and the delivery path corresponding to the minimum value is taken as the optimal delivery path. The total predicted delivery time for the tasks to be delivered; This is the sum of the delivery difficulty coefficients corresponding to each delivery address in the task to be delivered; The sum of penalty values ​​for each delivery address in the pending delivery task deviating from its corresponding optimal delivery time set; The planned delivery time slot for the current delivery address in the task to be delivered; This refers to the optimal delivery time slot set corresponding to the current delivery address among the delivery addresses; , and These are the fifth, sixth, and seventh weight parameters, respectively.

5. The method according to claim 1, characterized in that, The step of parsing the original address text information of the delivery address to obtain its corresponding address information includes: Natural language processing is performed on the original address text information to obtain standard address text information; By using a pre-set business customer keyword library, personal customer keyword library, POI point of interest database and target classification model, feature extraction is performed on the standard address text information to generate candidate addresses and the address information corresponding to the candidate addresses; The confidence level of the candidate address is calculated based on the historical call count of the candidate address, the maximum historical call count of the candidate address, the average distance between the order location and the actual location of the historical waybill of the candidate address, and the on-time delivery rate of the historical waybill of the candidate address. Candidate addresses with a confidence level greater than a preset threshold are identified as delivery addresses, and the address information corresponding to the delivery address is obtained.

6. The method according to claim 5, characterized in that, The confidence level of the candidate address is calculated based on the historical call count of the candidate address, the maximum historical call count of the candidate address, the average distance between the order location and the actual location of the historical waybill of the candidate address, and the on-time delivery rate of the historical waybill of the candidate address, including: The confidence level of the candidate address is calculated using the following formula: in, The confidence level of the candidate address; The number of historical calls to the candidate address; The maximum number of historical calls among the candidate addresses; This is the average distance between the reported location and the actual location of the historical waybill; The number of times the historical waybills were delivered on time; , , These are the eighth, ninth, and tenth weight parameters, respectively.

7. A performance appraisal method based on address profiling, characterized in that, include: The performance score of the deliveryman during the assessment period is calculated based on the number of completed deliveries of the delivery order, the base score corresponding to the delivery order, and the delivery difficulty coefficient contained in the address profile corresponding to the delivery address of each historical delivery order. The performance formula includes: in, The performance score of the delivery person; Complete the first The basic score corresponding to each delivery order; For the first The delivery difficulty level of each delivery order; For the first The preset difficulty reward coefficient for each delivery order; The first in the pending delivery task Penalty score for each delivery order.

8. A smart logistics delivery optimization device based on address profiling, characterized in that, include: The acquisition module is used to parse the original address text information of the delivery address and obtain its corresponding address information; The generation module is used to generate an address profile for the delivery address, which includes its corresponding address information, optimal delivery time slot set, and delivery difficulty coefficient; wherein, the optimal delivery time slot set is associated with the delivery time slot distribution of historical delivery orders corresponding to the delivery address, and the delivery difficulty coefficient is associated with the average number of deliveries, average waiting time, first delivery failure rate, and penalty factor of historical delivery orders corresponding to the delivery address. The processing module is used to construct an optimal delivery function based on the address profile information corresponding to several delivery addresses included in the delivery task and the predicted delivery time, and solve to generate the optimal delivery route for the delivery task.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores executable code that, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-7.

Images