End-point site location methods, devices, equipment, media and procedures products

Abstract

This disclosure provides a method, apparatus, device, storage medium, and program product for selecting a last-mile delivery station, which can be applied in the field of computer technology. The method includes: acquiring first travel characteristic data of the pickup party from a first starting point to multiple candidate stations; acquiring second travel characteristic data of the sender from a second starting point to multiple candidate stations; determining the influence coefficients corresponding to multiple sets of travel distance data and multiple sets of delivery distance data; and determining a target last-mile delivery station from multiple candidate stations based on the influence coefficients, the multiple sets of travel distance data, and the multiple sets of delivery distance data, wherein the influence coefficients are determined by a pre-trained prediction model.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically to a method, apparatus, device, medium, and program product for selecting an end site. Background Technology

[0002] With the booming development of e-commerce and the rapid changes in consumer shopping habits, express delivery stations have become a daily necessity for residents. Their spatial layout directly affects the carbon emissions from both delivery vehicles and residents' travel. Existing centralized collection and payment facility site selection models optimize for single objectives such as coverage or cost, lacking a systematic analysis of the impact on residents' behavior patterns and carbon emissions, making it difficult to balance logistics efficiency with low-carbon goals. Summary of the Invention

[0003] In view of the above problems, this disclosure provides end-site location methods, apparatus, equipment, media and program products.

[0004] According to a first aspect of this disclosure, a method for selecting a last-mile delivery station is provided, wherein the last-mile delivery station is used for the receipt and dispatch of mailed items, comprising: acquiring first travel characteristic data of a recipient from a first starting point to multiple candidate stations, the first travel characteristic data including multiple travel points passed by the recipient, the recipient's mode of transportation between the multiple travel points and the candidate stations, and multiple sets of travel distance data from the first starting point to the multiple candidate stations; acquiring second travel characteristic data of a sender from a second starting point to the multiple candidate stations, the second travel data including the sender's delivery mode, delivery frequency, and multiple sets of delivery distance data from the second starting point to the multiple candidate stations; determining the influence coefficients corresponding to each of the multiple sets of travel distance data and the multiple sets of delivery distance data, and determining a target last-mile delivery station from the multiple candidate stations based on the influence coefficients, the multiple sets of travel distance data, and the multiple sets of delivery distance data, wherein the influence coefficients are determined by a pre-trained prediction model.

[0005] According to embodiments of this disclosure, the determination of the influence coefficients corresponding to the multiple sets of travel distance data and the multiple sets of delivery distance data, and the determination of the target terminal station from the multiple candidate stations based on the influence coefficients, the multiple sets of travel distance data, and the multiple sets of delivery distance data, includes: determining a travel target evaluation index based on the sub-influence coefficients corresponding to the travel points, the transportation modes, and the multiple sets of travel distance data; determining a delivery target evaluation index based on the sub-influence coefficients corresponding to the delivery modes, delivery frequencies, and the multiple sets of delivery distance data; determining an evaluation score for each candidate station based on a preset travel evaluation table corresponding to the travel target evaluation index and a preset delivery travel evaluation table corresponding to the delivery target evaluation index; and determining at least one target terminal station from the multiple candidate stations based on the evaluation scores.

[0006] According to an embodiment of this disclosure, determining at least one target terminal station from the plurality of candidate stations based on the evaluation scores includes: merging the plurality of candidate stations to obtain a target location area when the evaluation scores corresponding to the plurality of candidate stations are greater than or equal to a preset threshold and the plurality of candidate stations are adjacent; and determining at least one target terminal station from the target location area.

[0007] According to an embodiment of this disclosure, determining at least one target terminal station from the target location area includes: calculating the geometric center point of the target location area and determining the geometric center point as the target terminal station.

[0008] According to an embodiment of this disclosure, determining at least one target terminal station from the target location area includes: determining multiple types of roads included in the target location area; performing a weighted average of the location data of the multiple roads based on preset weights for the multiple road types to determine the road network center point of the target location area, and using the road network center point as the target terminal station.

[0009] According to embodiments of this disclosure, the pre-trained prediction model is trained through the following steps: acquiring sample site user data, sample site delivery data, sample terminal site location data, sample carbon emission data, and sample link carbon emission data. The sample site user data includes sample trips and sample trip feature data. The sample trips pass through the sample terminal sites. The sample carbon emission data indicates the total carbon emission of the sample trips and the total carbon emission of the delivery trips for each sample user within a preset time period. The sample trip feature data indicates the carbon emission between each point along the sample trip. The sample site user data, sample site delivery data, and sample terminal site location data are input into an initial prediction model to obtain carbon emission data and link carbon emission data. A joint loss value is determined based on the sample carbon emission data, the sample link carbon emission data, the carbon emission data, and the link carbon emission data using a loss function. The parameters of the initial prediction model are adjusted using the joint loss value to obtain the pre-trained prediction model.

[0010] A second aspect of this disclosure provides a terminal site selection device, comprising: a first acquisition module, configured to acquire first travel characteristic data of a pickup party from a first starting point to multiple candidate sites, the first travel characteristic data including multiple travel points passed by the pickup party, the pickup party's mode of transportation between the multiple travel points and the candidate sites, and multiple sets of travel distance data from the first starting point to the multiple candidate sites; a second acquisition module, configured to acquire second travel characteristic data of a sender from a second starting point to the multiple candidate sites, the second travel data including the delivery method, delivery frequency, and multiple sets of delivery distance data from the second starting point to the multiple candidate sites; and a determination module, configured to determine a target terminal site from the multiple candidate sites based on the influence coefficients corresponding to the first travel characteristic data and the second travel characteristic data, wherein the influence coefficients are determined by a pre-trained prediction model.

[0011] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0012] A fourth aspect of this disclosure also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0013] The fifth aspect of this disclosure also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0014] According to embodiments of this disclosure, first travel feature data, including multiple travel points passed by the pickup party, the pickup party's transportation mode between multiple travel points and candidate stations, and multiple sets of travel distance data from the first starting point to multiple candidate stations, and second travel feature data, including the delivery mode, delivery frequency, and multiple sets of delivery distance data from the second starting point to multiple candidate stations, are used as standard data for measuring carbon emissions. Furthermore, an influence coefficient determined by a pre-trained prediction model is introduced to further determine the target terminal station. This comprehensively considers the travel carbon emissions from the pickup party to the target terminal station and the delivery carbon emissions from the delivery party to the target terminal station, thereby reducing the overall carbon emission level of payment and delivery behaviors while meeting operational efficiency requirements. Attached Figure Description

[0015] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0016] Figure 1 This diagram illustrates an application scenario of the terminal site selection method and apparatus according to embodiments of the present disclosure.

[0017] Figure 2 schematically illustrates a flowchart of an end-site site selection method according to an embodiment of the present disclosure;

[0018] Figure 3 A schematic diagram illustrating a resident travel chain according to an embodiment of the present disclosure is shown.

[0019] Figure 4 A schematic diagram illustrating a structural block diagram of an end-site site selection device according to an embodiment of the present disclosure; and

[0020] Figure 5 A block diagram of an electronic device suitable for implementing an end-site site location method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0021] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0022] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0023] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0024] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0025] Express delivery stations are high-frequency end-point spaces used by residents. Optimizing vehicle delivery routes through refined adjustments to the spatial layout of logistics facilities is crucial to reducing carbon emissions from truck deliveries. On the other hand, the carbon emissions from users' access to these spaces for express delivery services are influenced by facility layout patterns, manifesting in differentiated travel characteristics. Traditional methods typically rely on experience or static indicators to determine express delivery station locations, neglecting behavioral chain connections, functional mixing, and dynamic supply and demand relationships, making it difficult to balance low-carbon goals with residents' needs. Furthermore, existing technologies lack sufficient analysis of the non-linear relationship between facility spatial configuration and carbon emissions, failing to accurately identify areas with low-carbon optimization potential. How to reduce carbon emissions from using end-point spaces like express delivery stations while ensuring logistics efficiency and meeting residents' high-frequency and regular daily travel needs has become a critical issue that the express delivery industry urgently needs to address.

[0026] In view of this, embodiments of the present disclosure provide a method for selecting a last-mile delivery station, where the last-mile delivery station is used for the receipt and dispatch of mailed items. The method includes: acquiring first travel characteristic data of the recipient from a first starting point to multiple candidate stations, the first travel characteristic data including multiple travel points passed by the recipient, the recipient's mode of transportation between the multiple travel points and the candidate stations, and multiple sets of travel distance data from the first starting point to the multiple candidate stations; acquiring second travel characteristic data of the sender from a second starting point to multiple candidate stations, the second travel data including the delivery method, delivery frequency, and multiple sets of delivery distance data from the second starting point to the multiple candidate stations; determining the influence coefficients corresponding to each of the multiple sets of travel distance data and the multiple sets of delivery distance data, and determining a target last-mile delivery station from the multiple candidate stations based on the influence coefficients, the multiple sets of travel distance data, and the multiple sets of delivery distance data, wherein the influence coefficients are determined by a pre-trained prediction model.

[0027] Figure 1 The illustration shows an application scenario of the terminal site selection method and apparatus according to embodiments of the present disclosure.

[0028] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0029] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0030] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0031] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0032] It should be noted that the terminal site selection method provided in this embodiment can generally be executed by server 105. Correspondingly, the terminal site selection device provided in this embodiment can generally be located in server 105. The terminal site selection method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the terminal site selection device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0033] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0034] The following will be based on Figure 1 The described scene, through Figures 2-3 The terminal site selection method of the disclosed embodiments will be described in detail.

[0035] Figure 2 A flowchart illustrating an end-site location method according to an embodiment of the present disclosure is shown schematically.

[0036] like Figure 2 As shown, the terminal site selection method in this embodiment includes operations S210 to S230.

[0037] In operation S210, the first travel feature data of the pickup party from the first starting point to multiple candidate stations is obtained.

[0038] The first trip feature data includes multiple trip points passed by the recipient, the recipient's mode of transportation between multiple trip points and candidate stations, and multiple sets of travel distance data from the first starting point to multiple candidate stations.

[0039] According to embodiments of this disclosure, the first starting point can be the starting location from which the recipient departs to pick up the package, such as their home or workplace. The travel point can be at least one necessary location that the recipient must pass through between the first starting point and the candidate station. For example, if the recipient's journey is "home-workplace-courier station", then in the aforementioned journey, the travel point can be the workplace.

[0040] According to embodiments of this disclosure, the travel distance data between the first starting point and multiple candidate stations can be determined by querying map data, POI (Point of Interest) data, logistics enterprise management data, etc. The first travel characteristic data may also include the pickup party's travel frequency and end-point station usage preferences. The aforementioned travel points and modes of transportation can be obtained through online / offline questionnaires. Modes of transportation may include walking, bicycles, electric vehicles, cars, etc., travel frequency can represent the number of pickups within a preset time period, and end-point station usage preferences may include a preference for self-service lockers or manual courier stations. The questionnaire sample covers different age groups, occupations, and residential areas to ensure data representativeness. Furthermore, the first travel characteristic data may also include spatial data, such as population density, housing distribution information, and kilometer-grid population data of the residential (pickup party) community.

[0041] According to embodiments of this disclosure, the aforementioned first travel characteristic data may further include the demand population, which is obtained by weighting grid population data with pickup frequency, and can reflect the total demand in the region.

[0042] According to an embodiment of this disclosure, in the process of preprocessing the questionnaire to obtain the first travel feature data, the behavior chain of the recipient can be split into continuous segments (such as "home → workplace → express station"), and the distance of each path can be calculated using map software. Furthermore, the first travel feature data can be associated and stored based on the transportation methods between each travel point and the candidate stations.

[0043] In operation S220, second travel feature data of the sender from the second starting point to multiple candidate stations is obtained.

[0044] The second trip data includes the delivery method, delivery frequency, and multiple sets of delivery distance data from the second starting point to multiple candidate stations.

[0045] According to embodiments of this disclosure, the aforementioned second trip characteristic data may further include the number of delivery stations per trip, delivery route (serialized end-point route), and data such as delivery preferences (which delivery route to choose), route demand, and operating frequency (peak-hour delivery volume) determined by a questionnaire. All of the aforementioned data can be obtained from the logistics company's management system. Delivery methods may include, for example, fuel-powered vehicles, electric vehicles, etc., and delivery frequency may be the number of deliveries per day.

[0046] According to embodiments of this disclosure, in determining delivery distance data, the coordinates, corresponding road network structure, and attribute data of candidate sites can first be converted into GIS (Geographic Information System Standard Format) standard format. Then, the map application interface is called to obtain the coordinates of the candidate sites and the path planning results from the second starting point to each candidate site. The aforementioned path planning results may include the actual path distance and delivery time from the second starting point to multiple specified candidate sites using a specified delivery method. The latitude and longitude coordinates, type, and attribute information of multiple candidate sites can also be obtained through the map interface. This data is used for spatial positioning and facility distribution analysis.

[0047] According to embodiments of this disclosure, after obtaining the first trip feature data and the second trip feature data, the data can be cleaned (e.g., to remove fault data to improve the accuracy of latitude and longitude coordinates), and grouped according to any feature in the data (e.g., according to candidate station type, spatial distribution characteristics, etc.). Then, grouping and statistically analyzing delivery distance, delivery method, and operation frequency, while labeling carbon emission weights, the first trip feature data on the travel side can be transformed into population data, and a kilometer grid dataset can be established, where the pixel value of each grid m represents the number of people N per square km. m The unit is people, and the data format is grid. Furthermore, travel features, usage features, and activity association features can be standardized using Min-Max to ensure the consistency of model input.

[0048] According to embodiments of this disclosure, the daily delivery order volume can be extracted from the logistics management system, and then grouped and statistically analyzed according to facility points, and normalized to a standard frequency (times / day).

[0049] In operation S230, the influence coefficients corresponding to multiple sets of travel distance data and multiple sets of delivery distance data are determined, and the target terminal station is determined from multiple candidate stations based on the influence coefficients, multiple sets of travel distance data and multiple sets of delivery distance data.

[0050] The influence coefficient is determined by a pre-trained prediction model.

[0051] According to embodiments of this disclosure, the influence coefficient is used to quantify the impact of various data contained in the first and second travel characteristic data on carbon emissions.

[0052] According to embodiments of this disclosure, the aforementioned pre-trained prediction model may be, for example, an XG Boost (eXtremeGradient Boosting Regression) regression model, a LightGBM (LightGradient Boosting Machine), a CatBoost (Categorical Boosting) model, or a SHAP (SHapley Additive exPlanations) + Random Forest model, etc., and this disclosure does not limit it.

[0053] According to embodiments of this disclosure, first travel feature data, including multiple travel points passed by the pickup party, the pickup party's transportation mode between multiple travel points and candidate stations, and multiple sets of travel distance data from the first starting point to multiple candidate stations, and second travel feature data, including the delivery mode, delivery frequency, and multiple sets of delivery distance data from the second starting point to multiple candidate stations, are used as standard data for measuring carbon emissions. Furthermore, an influence coefficient determined by a pre-trained prediction model is introduced to further determine the target terminal station. This comprehensively considers the travel carbon emissions from the pickup party to the target terminal station and the delivery carbon emissions from the delivery party to the target terminal station, thereby reducing the overall carbon emission level of payment and delivery behaviors while meeting operational efficiency requirements.

[0054] According to embodiments of this disclosure, the above-mentioned determination of the influence coefficients corresponding to multiple sets of travel distance data and multiple sets of delivery distance data, and the determination of the target terminal station from multiple candidate stations based on the influence coefficients, multiple sets of travel distance data, and multiple sets of delivery distance data, includes: determining travel target evaluation indicators based on the sub-influence coefficients corresponding to the travel points, modes of transportation, and multiple sets of travel distance data; determining delivery target evaluation indicators based on the sub-influence coefficients corresponding to the delivery modes, delivery frequencies, and multiple sets of delivery distance data; determining the evaluation score of each candidate station based on the travel target evaluation indicators, the preset travel evaluation table corresponding to the travel target evaluation indicators, the delivery target evaluation indicators, and the preset delivery travel evaluation table corresponding to the delivery target evaluation indicators; and determining at least one target terminal station from multiple candidate stations based on the evaluation scores.

[0055] For prediction models, a tree-based SHAP value calculation method can be used to evaluate the contribution of each feature to the prediction results.

[0056] In the process of calculating the influence coefficient, the aforementioned first-stroke feature data and second-stroke feature data can be input into the pre-trained prediction model to obtain the influence coefficients of each first-stroke feature data and second-stroke feature data.

[0057] The following formula (1) shows the formula for calculating the influence coefficient according to an embodiment of the present disclosure.

[0058] (1)

[0059] in, It is the SHAP value of the j-th feature of the i-th sample. It is the prediction value of the m-th tree model for the i-th sample. It is the average of the predictions from all tree models. It is the splitting contribution of the j-th feature in the m-th tree model.

[0060] For the j-th feature, its average SHAP can be calculated as the sub-influence coefficient using formula (2).

[0061] (2)

[0062] in, is the average SHAP value (i.e., sub-influence coefficient) of the j-th feature. It is the SHAP value of the j-th feature of the i-th sample, where N is the number of samples and i is the index of the sample.

[0063] The SHAP value reflects the degree of influence of the j-th feature on the carbon emission prediction results. >0 indicates that feature j positively promotes carbon emissions. <0 indicates negative carbon emission suppression. Finally, based on the global SHAP value vector, the data contained in the first and second trip feature data are sorted. Evaluation indicators with sub-influence coefficients greater than or equal to preset thresholds (including trip points, modes of transportation, travel distance groups, number of single delivery stations, delivery routes, delivery preferences determined by questionnaires, route requirements, etc.) are determined as trip target evaluation indicators and delivery target evaluation indicators. Alternatively, evaluation indicators of the first and second trip feature data with sub-influence coefficients greater than the mean influence coefficient can be determined as trip target evaluation indicators and delivery target evaluation indicators. This disclosure does not impose any restrictions on this.

[0064] For example, for a first trip feature data containing n trip points, the trip carbon emissions (i.e. trip evaluation score) generated by the nth segment in the behavior chain can be calculated by the following formula (3).

[0065] (3)

[0066] in, This represents the total carbon emissions generated at the nth point in the resident's travel behavior chain. Indicates characteristics of residents' travel behavior. This represents the p-th mode of transportation. This represents the travel distance of the nth segment of a resident's travel behavior chain when using the pth type of transportation. Let i represent the carbon emission coefficient of the p-th mode of transportation, and i be the index of the travel behavior chain.

[0067] Furthermore, carbon emission measurement can be divided into two types based on other components of carbon emissions generated in the nth segment of the resident travel behavior chain: total emission measurement and average emission measurement. Residents generate corresponding carbon emissions when traveling to the terminal station and along the entire travel chain, resulting in four categories, which reflect the overall level of related carbon emissions. The total carbon emissions at the travel point and the total carbon emissions of the resident travel chain can be represented by the following formulas (4) and (5).

[0068] (4)

[0069] in, This represents the total carbon emissions at each point in the journey. This represents the total carbon emissions generated by the nth point in the resident travel behavior chain. Indicates the frequency of residents' travel. This indicates the population size required by the residents.

[0070] (5)

[0071] in, This represents the total carbon emissions from the resident travel chain. This represents the total carbon emissions generated in the nth segment of a resident's travel chain. Indicates the frequency of residents' travel. This indicates the population size required by the residents.

[0072] The average carbon emissions at each travel point can be calculated using the following formula (6).

[0073] (6)

[0074] in, This represents the average carbon emissions at each point in the journey. This represents the total carbon emissions at the nth travel point, where N is the number of travel points.

[0075] The average carbon emissions of the travel chain q can be calculated using the following formula (7).

[0076] (7)

[0077] in, This represents the average carbon emissions across the travel chain q. This represents the total carbon emissions of the travel chain from the first starting point to the destination q. N represents the total carbon emissions of the travel chain from travel point q back to the first starting point, where N is the number of travel points.

[0078] Figure 3 A schematic diagram of a resident travel chain according to an embodiment of the present disclosure is shown.

[0079] like Figure 3 As shown, a travel chain can include N travel points. The recipient can start from a first starting point (which could be home), travel through N travel points, and return to the first starting point. When calculating the average carbon emissions to the nth travel point in the travel chain, it is necessary to calculate the average carbon emissions of the travel chain from the first starting point to travel point 1, from travel point 1 to travel point 2, ... from travel point n-1 to travel point n, and from travel point n to the first starting point.

[0080] Delivery carbon emissions (i.e. delivery evaluation score) can be calculated using the following formula (8).

[0081] (8)

[0082] in, This represents the total carbon emissions from the delivery of the p-th route. Indicates the frequency of delivery activities. This represents the delivery distance from the second starting point u to the candidate station v via the nth type of delivery method. This represents the carbon emission coefficient corresponding to the nth type of delivery method.

[0083] According to embodiments of this disclosure, the sender's delivery method and the recipient's transportation method can correspond to different preset delivery evaluation forms and preset travel evaluation forms (which can be dynamically updated based on public databases or localized measured data). For example, the carbon emission coefficient for walking is 0, the carbon emission coefficient for cycling is 0, the carbon emission coefficient for electric vehicles is 20 gCO2 / km, and the carbon emission coefficient for gasoline vehicles is 150 gCO2 / km.

[0084] According to the embodiments of this disclosure, after determining the travel evaluation score and delivery evaluation score of each candidate station, the evaluation score of the candidate station can be further determined (which may be by adding the travel evaluation score and delivery evaluation score of the candidate station), and the candidate station with the highest evaluation score can be selected as the terminal station.

[0085] According to an embodiment of this disclosure, the above-mentioned method of determining at least one target terminal station from multiple candidate stations based on evaluation scores includes: merging multiple candidate stations to obtain a target location area when the evaluation scores corresponding to multiple candidate stations are greater than or equal to a preset threshold and the multiple candidate stations are adjacent; and determining at least one target terminal station from the target location area.

[0086] According to the embodiments of this disclosure, travel target evaluation indicators and delivery target evaluation indicators can be integrated, variables with similar characteristics can be removed, and indicators that can reflect the characteristics of residents' travel behavior and their correlation with daily activities, spatial accessibility and walking accessibility of candidate sites, delivery routes and transportation accessibility, spatial layout relationship, facility type, quantity and operation mode and other key factors can be retained as core carbon control indicators (integrating travel target evaluation indicators and delivery target evaluation indicators).

[0087] According to the embodiments of this disclosure, a hierarchical low-carbon optimization index system is constructed, which adopts a four-level structure of "target layer - criterion layer - index layer - carbon control threshold layer" to achieve a systematic and quantitative assessment of carbon emission influencing factors. First, with the technical objective of "minimizing the comprehensive carbon emission intensity of payment and delivery behaviors under the constraints of meeting service demand and operational efficiency", the top-level optimization objective G is set as the coordinated optimization of low-carbon site selection and spatial configuration of express delivery stations. Then, based on the aforementioned impact mechanism analysis, a multi-dimensional constraint criterion system is constructed, which at least covers behavioral guidance and demand response (including the spatiotemporal distribution characteristics of residents' payment, travel mode structure, and coupling degree with daily activity space), spatial accessibility and walking convenience (including the walking distance from residents to payment facilities / express delivery stations, road network connectivity, and public transportation connection efficiency), land use function and environmental attributes (involving population employment density, functional mixing, building type and spatial layout pattern), facility layout and operation organization (including the type configuration, quantity and scale, operation organization method and its relationship with centralized payment facilities and express delivery stations). The system comprises five criterion layers: the topological relationship of delivery routes, delivery efficiency, and traffic accessibility (covering the distance attenuation effect between transfer nodes, stations, and payment facilities / users, as well as the accessibility of the transportation network and the operating efficiency of delivery vehicles). Core carbon control indicators are then normalized by attribute and incorporated into these criterion layers to form a quantifiable indicator layer. This layer includes behavioral indicators, accessibility indicators, land use environment indicators, facility operation indicators, and delivery efficiency indicators. Each indicator is a spatially or statistically quantifiable technical variable with clearly defined polarity (positive or negative). Finally, based on SHAP dependency analysis, quantile statistics, and effect inflection point identification from the empirical research phase, carbon control threshold ranges are defined for each indicator, forming a hierarchical control system. The range of values ​​for each indicator is divided into several carbon control level ranges based on its marginal contribution to carbon emissions. Preferably, this includes, but is not limited to, four levels: "preferred range, suitable range, suboptimal range, and restricted range." Each level range corresponds to a differentiated carbon emission reduction contribution rate, used for subsequent spatial identification, hierarchical weighting, and optimization decisions.

[0088] According to the embodiments of this disclosure, a standardized mapping and weight determination mechanism for indicators is further constructed to achieve spatial quantitative assessment of low-carbon suitability: For each carbon control indicator, a mapping function from the original indicator value to the standardized score is constructed by combining its positive or negative attributes and the effect threshold determined by the aforementioned SHAP analysis. For monotonically favorable indicators, a monotonically increasing linear or piecewise linear function is used; for monotonically unfavorable indicators, a monotonically decreasing linear or piecewise linear function is used; and for indicators with an optimal range, a trapezoidal or peak-shaped function with the optimal range as the high value area is used. Then, for any evaluation unit (including but not limited to grid units, community center points, or potential site locations), its original measurement values ​​on each indicator are obtained and mapped to standardized scores, which are uniformly normalized to the same dimension range (preferably 0 to 1 or 0 to 100 points) to quantitatively characterize the low-carbon suitability of the unit. When the indicator value of the evaluation unit falls into a preset carbon control range, the corresponding score of that range is directly assigned, thereby achieving graded evaluation and quantitative characterization based on the influence threshold. Based on this, the weights are determined by the global importance of each indicator in the SHAP results: First, the SHAP importance of each indicator to carbon emission collection and payment and carbon emission distribution are obtained respectively. Then, according to the multi-objective optimization requirements, the two types of importance are weighted and synthesized or weight systems are constructed separately. The above importance is normalized to obtain the final weight of each indicator. If necessary, expert weighting or analytic hierarchy process can be combined for fine-tuning, but it should be kept basically consistent with the SHAP importance ranking to ensure the consistency and interpretability of the indicator system with the "spatial configuration-behavior-carbon emission" influence mechanism. Finally, a unified evaluation unit (including rule grids, road network nodes, or residential areas) was constructed on the GIS platform according to the scope of the study area. The standardized scores of all core carbon control indicators were calculated for each unit. Considering the carbon reduction targets for payment and delivery, the comprehensive low-carbon suitability index of the evaluation unit was calculated separately or in combination using a weighted overlay method. Three types of indices were selected to construct: "low-carbon suitability index for payment", "low-carbon suitability index for delivery" and "comprehensive low-carbon suitability index" to support the spatial optimization decision-making needs under different scenarios (Scenario 1: carbon emission reduction oriented towards payment behavior optimization; Scenario 2: carbon emission reduction oriented towards delivery behavior optimization).

[0089] According to an embodiment of this disclosure, determining at least one target terminal station from a target location area includes: calculating the geometric center point of the target location area and determining the geometric center point as the target terminal station.

[0090] According to embodiments of this disclosure, thresholds or quantile standards can be set based on the numerical value of the evaluation scores and the spatial distribution characteristics of the candidate sites to obtain target end sites with high suitability. Furthermore, spatial clustering and connectivity analysis methods can be used to merge spatially continuous or adjacent candidate sites with high suitability and calculate the corresponding geometric centers to determine the target end sites.

[0091] Assume the target location area is a polygonal region, and the vertices of the polygon are (x1, y1), (x2, y2), ..., (x...) in clockwise or counterclockwise order. n y n Then the geometric center coordinates (C) x C y The result can be calculated using the following formulas (9) and (10).

[0092] (9)

[0093] (10)

[0094] Where A is the directed area of ​​the polygon, n is the total number of vertices of the polygon, and i is the vertex index. The x-coordinate of the i-th vertex Let be the ordinate of the i-th vertex. Let x be the x-coordinate of the (i+1)th vertex. Let be the ordinate of the (i+1)th vertex.

[0095] According to embodiments of this disclosure, when multiple candidate sites are adjacent, multiple candidate sites are merged to obtain a target site selection area. Then, the geometric center point is calculated based on the target site selection area and the location of the target terminal site is determined, thereby avoiding excessive concentration of terminal facilities and improving land use efficiency.

[0096] According to an embodiment of this disclosure, determining at least one target terminal station from a target location area includes: determining multiple types of roads included in the target location area; performing a weighted average of the location data of multiple roads based on preset weights for multiple road types to determine the road network center point of the target location area, and using the road network center point as the target terminal station.

[0097] For example, the target location area includes three types of roads: arterial roads, secondary arterial roads, and pedestrian paths. The center point (i.e., location data) corresponding to the arterial road is (500, 500), with a weight of 0.5; the center point corresponding to the secondary arterial road is (500, 600), with a weight of 0.3; and the center point corresponding to the pedestrian path is (500, 400), with a weight of 0.2. The coordinates of the road network center point are 500×0.5+500×0.3+500×0.2=500 (x-coordinate). Similarly, the y-coordinate of the road network center point is 510, so the coordinates of the road network center point are (500, 510).

[0098] According to the embodiments of this disclosure, by performing a weighted average of multiple road types in the target location area, road location data corresponding to multiple road types, and preset weights, a balanced road network center point that can ensure better spatial distribution of the regional road network and delivery convenience can be obtained. This can overcome the defect of traditional geometric center algorithms that ignore the heterogeneity of traffic network structure and improve the path accessibility of the terminal station and the delivery efficiency of the sender.

[0099] According to embodiments of this disclosure, the pre-trained prediction model is trained through the following steps: acquiring sample site user data, sample site delivery data, sample terminal site location data, sample carbon emission data, and sample link carbon emission data. The sample site user data includes sample trips and sample trip feature data. The sample trips pass through sample terminal sites. The sample carbon emission data indicates the total carbon emission of the sample trips and the total carbon emission of the delivery trips for each sample user within a preset time period. The sample trip feature data indicates the carbon emission between each point along the sample trip. The sample site user data, sample site delivery data, and sample terminal site location data are input into the initial prediction model to obtain carbon emission data and link carbon emission data. A joint loss value is determined based on the sample carbon emission data, sample link carbon emission data, carbon emission data, and link carbon emission data using a loss function. The parameters of the initial prediction model are adjusted using the joint loss value to obtain the pre-trained prediction model.

[0100] According to embodiments of this disclosure, the pre-trained prediction model (assumed to be an XGBOOST model) guides the training of the model through an objective function. The objective function may include a loss function and a regularization term, wherein the loss function is used to measure the difference between the model's predicted values ​​and the true values. The objective function is shown in the following formula (11).

[0101] (11)

[0102] in, For loss function, For the true value, Here, n is the predicted value, and n is the sample size, usually expressed as... To describe the difference between the actual value and the predicted value, As a regularization term, it can be expanded as = Furthermore, a greedy algorithm can be used to generate CART (Classification and Regression Trees), thereby generating new weak learning trees. The objective function is to minimize the model's predicted values, where t is the number of decision trees. Let be the predicted carbon emissions for the i-th sample of the first t-1 trees. Let be the predicted carbon emissions of the i-th sample from the t-th tree. Let T be the complexity coefficient of the leaf nodes, T be the number of leaf nodes, and λ be the penalty factor. Let be the importance of the j-th leaf node.

[0103] CART trees use a greedy algorithm to select the optimal split point to minimize the objective function. The split point selection is based on the features of the samples and the gain calculated from the feature values; the greater the gain, the more the objective function decreases after the split.

[0104] The gain can be expressed by the following formula (12).

[0105] (12)

[0106] in, The first derivative of the loss function. The second derivative of the loss function. The sample set of the left child nodes after splitting. This is the sample set of the right child nodes after the split.

[0107] The XGBoost model iteratively generates decision trees to optimize model performance. Specifically, in each iteration, the algorithm generates a new decision tree and integrates its predictions with those of the existing model using a weighted ensemble. This iterative process continues until either of the following stopping conditions is met: the model performance metrics no longer show significant improvement on the validation set, or the number of generated decision trees reaches a preset upper limit. Finally, the predictions from all decision trees are weighted and summed to form a pre-trained prediction model. It can be represented by the following formula (13).

[0108] (13)

[0109] in, For pre-trained prediction models, Let K be the regressor of the k-th decision tree, where K is the number of decision trees.

[0110] According to the embodiments of this disclosure, after determining the target end-point site, the carbon reduction amount can be calculated by the following formula (14) to verify the effectiveness of the end-point site location method proposed in this disclosure.

[0111] (14)

[0112] in, Indicates the amount of carbon reduction. This represents the total carbon emissions before the location of the end-point stations was modified. This indicates the total carbon emissions after modifying the location of the end-point station.

[0113] Based on the above-described terminal site selection method, this disclosure also provides a terminal site selection device. The following will be combined with... Figure 4 The device is described in detail.

[0114] Figure 4 A schematic block diagram of an end-site location selection device according to an embodiment of the present disclosure is shown.

[0115] like Figure 4 As shown, the terminal site selection device 400 in this embodiment includes a first acquisition module 410, a second acquisition module 420, and a determination module 430.

[0116] The first acquisition module 410 is used to acquire first travel feature data of the pickup party from the first starting point to multiple candidate stations. The first travel feature data includes multiple travel points passed by the pickup party, the transportation mode of the pickup party between the multiple travel points and candidate stations, and multiple sets of travel distance data from the first starting point to the multiple candidate stations. In one embodiment, the first acquisition module 410 can be used to perform the operation S210 described above, which will not be repeated here.

[0117] The second acquisition module 420 is used to acquire second travel characteristic data of the sender from the second starting point to multiple candidate stations. The second travel data includes the delivery method, delivery frequency, and multiple sets of delivery distance data from the second starting point to the multiple candidate stations. In one embodiment, the second acquisition module 420 can be used to perform the operation S220 described above, which will not be repeated here.

[0118] The determination module 430 is used to determine the target terminal station from multiple candidate stations based on the influence coefficients corresponding to the first travel feature data and the second travel feature data, respectively. The influence coefficients are determined by a pre-trained prediction model. In one embodiment, the determination module 430 can be used to perform the operation S230 described above, which will not be repeated here.

[0119] According to embodiments of this disclosure, any plurality of modules among the first acquisition module 410, the second acquisition module 420, and the determination module 430 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the first acquisition module 410, the second acquisition module 420, and the determination module 430 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in any one of software, hardware, and firmware methods, or in a suitable combination of any of these. Alternatively, at least one of the first acquisition module 410, the second acquisition module 420, and the determination module 430 may be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0120] Figure 5 A block diagram of an electronic device suitable for implementing an end-site site location method according to an embodiment of the present disclosure is shown schematically.

[0121] like Figure 5 As shown, an electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0122] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0123] According to embodiments of this disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0124] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0125] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0126] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to enable the computer system to implement the end-site location method provided in the embodiments of this disclosure.

[0127] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0128] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0129] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0130] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0133] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for selecting the location of a terminal site, characterized in that, The terminal station is used for receiving and sending mailed items, and the method includes: Obtain first travel feature data of the pickup party from the first starting point to multiple candidate stations. The first travel feature data includes multiple travel points passed by the pickup party, the mode of transportation of the pickup party between the multiple travel points and the candidate stations, and multiple sets of travel distance data from the first starting point to the multiple candidate stations. Obtain second travel feature data from the sender to the multiple candidate stations. The second travel data includes the delivery method, delivery frequency, and multiple sets of delivery distance data from the second origin to the multiple candidate stations between the second origin and the candidate stations. The influence coefficients corresponding to the multiple sets of travel distance data and the multiple sets of delivery distance data are determined, and the target terminal station is determined from the multiple candidate stations based on the influence coefficients, the multiple sets of travel distance data and the multiple sets of delivery distance data, wherein the influence coefficients are determined by a pre-trained prediction model.

2. The method according to claim 1, characterized in that, The step of determining the influence coefficients corresponding to the multiple sets of travel distance data and the multiple sets of delivery distance data, and determining the target end station from the multiple candidate stations based on the influence coefficients, the multiple sets of travel distance data, and the multiple sets of delivery distance data, includes: Based on the sub-influence coefficients corresponding to the travel points, the mode of transportation, and the multiple sets of travel distance data, the travel target evaluation index is determined, and based on the sub-influence coefficients corresponding to the delivery method, delivery frequency, and the multiple sets of delivery distance data, the delivery target evaluation index is determined. The evaluation score for each candidate station is determined based on the travel target evaluation index, the preset travel evaluation table corresponding to the travel target evaluation index, the delivery target evaluation index, and the preset delivery travel evaluation table corresponding to the delivery target evaluation index. At least one target terminal site is determined from the plurality of candidate sites based on the evaluation score.

3. The method according to claim 1, characterized in that, The step of determining at least one target terminal station from the plurality of candidate stations based on the evaluation score includes: If the evaluation scores of the multiple candidate sites are greater than or equal to a preset threshold and the multiple candidate sites are adjacent, the multiple candidate sites are merged to obtain the target site selection area. At least one target terminal site is determined from the target location area.

4. The method according to claim 3, characterized in that, Determining at least one target terminal station from the target location area includes: Calculate the geometric center point of the target site selection area and determine the geometric center point as the target terminal station.

5. The method according to claim 3, characterized in that, Determining at least one target terminal station from the target location area includes: Identify the various types of roads included within the target site selection area; Based on preset weights for the various road types, a weighted average is performed on the location data of the various roads to determine the road network center point of the target site selection area, and the road network center point is used as the target terminal station.

6. The method according to claim 1, characterized in that, The pre-trained prediction model is obtained through the following steps: The system acquires sample site user data, sample site delivery data, sample terminal site location data, sample carbon emission data, and sample link carbon emission data. The sample site user data includes sample trips and sample trip feature data. The sample trips pass through the sample terminal sites. The sample carbon emission data indicates the total carbon emission of the sample trip and the total carbon emission of the delivery trip for each sample user within a preset time period. The sample trip feature data indicates the carbon emission between each point along the sample trip. The sample site user data, sample site delivery data, and sample terminal site location data are input into the initial prediction model to obtain carbon emission data and link carbon emission data; Using a loss function, a joint loss value is determined based on the sample carbon emission data, the sample link carbon emission data, the carbon emission data, and the link carbon emission data; The parameters of the initial prediction model are adjusted using the joint loss value to obtain a pre-trained prediction model.

7. A terminal site selection device, characterized in that, The terminal station is used for receiving and sending mailed items, and the device includes: The first acquisition module is used to acquire first travel feature data of the pickup party from the first starting point to multiple candidate stations. The first travel feature data includes multiple travel points passed by the pickup party, the mode of transportation of the pickup party between the multiple travel points and the candidate stations, and multiple sets of travel distance data from the first starting point to the multiple candidate stations. The second acquisition module is used to acquire second travel feature data of the sender from the second starting point to the multiple candidate stations. The second travel data includes the delivery method, delivery frequency and multiple sets of delivery distance data of the delivery party from the second starting point to the multiple candidate stations between the second starting point and the candidate stations. The determination module is used to determine the target terminal station from the plurality of candidate stations based on the influence coefficients corresponding to the first trip feature data and the second trip feature data, respectively, wherein the influence coefficients are determined by a pre-trained prediction model.

8. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

Images