A service recommendation method and device, electronic equipment and storage medium

Abstract

The application relates to a service recommendation method and device, electronic equipment and a storage medium, and relates to the Internet of Vehicles technical field. The method comprises the following steps: determining the energy consumption type and the trip type of a target trip, the energy consumption type being used for representing the energy consumption degree of the target trip, and the trip type being used for representing the familiarity degree of the target trip to a user; in the case that the trip type of the target trip is a first trip type and the energy consumption type of the target trip is a high energy consumption type, the first trip type being used for representing that the familiarity degree of the target trip to the user is greater than a first value, and the high energy consumption type being used for representing that the energy consumption of the target trip is greater than an energy consumption threshold, the user is recommended a driving service. Therefore, the efficiency of service recommendation and the convenience of service can be improved, the problem that the used service needs to be indicated by the user before being used, which leads to low efficiency of service recommendation and reduces the convenience of service use, can be avoided.

Description

Technical Field

[0001] This application relates to the field of vehicle networking technology, specifically to a service recommendation method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, vehicles can provide users with service information corresponding to a specific service (such as chauffeur service) based on the user's instructions.

[0003] However, in the above methods, the services that users need to indicate can only be used after the user has given their instructions, which results in low efficiency of service recommendation and reduces the convenience of using services. Summary of the Invention

[0004] This application provides a service recommendation method, apparatus, electronic device, and storage medium to at least solve the technical problem in related technologies where users need to indicate the availability of services before they can be used, resulting in low efficiency in service recommendation and reduced convenience of service use. The technical solution of this application is as follows:

[0005] According to a first aspect of this application, a service recommendation method is provided, comprising: determining the energy consumption type and trip type of a target trip, wherein the energy consumption type characterizes the energy consumption level of the target trip and the trip type characterizes the user's familiarity with the target trip, and the target trip is a trip of a target vehicle; and recommending a chauffeur service to the user when the trip type of the target trip is a first trip type and the energy consumption type of the target trip is a high energy consumption type, wherein the first trip type characterizes the user's familiarity with the target trip as greater than a first value and the high energy consumption type characterizes the energy consumption of the target trip as greater than an energy consumption threshold.

[0006] Based on the aforementioned technical means, this application can, when the user is familiar with the route of the target trip, and the energy consumption of the target trip is high and the user may experience driving fatigue, indicate that the user's safety in driving the target vehicle for the target trip is low and the user may need a designated driver service. In this case, the electronic device proactively recommends the designated driver service that the user may need and reminds the user to use the designated driver service, thereby improving the efficiency and convenience of service recommendation and further improving driving safety.

[0007] In one possible implementation, determining the trip type of the target trip includes: acquiring trip information of multiple historical trips of the target vehicle and the trip information of the target trip, wherein the trip information of one trip includes the route of the trip; performing clustering processing on the trip information of the multiple historical trips and the trip information of the target trip to obtain multiple clustering results, wherein each clustering result includes at least one trip information; determining the trip type of the target trip based on the number of trip information included in the target clustering result, wherein the target clustering result is the clustering result in which the target trip belongs among the multiple clustering results.

[0008] Based on the aforementioned technical means, this application can perform clustering processing on the historical trip information of the target vehicle and the trip information of the target trip, and can divide the trip information into multiple clustering results. Since the trip information included in a clustering result is relatively similar, the electronic device can determine the user's familiarity with the target trip based on the number of trip information included in the clustering result to which the target trip belongs, that is, determine the trip type of the target trip, thereby improving the accuracy of trip type determination.

[0009] In one possible implementation, the method further includes: the trip information of a trip includes a route, a departure point, and a destination; the service recommendation method further includes: determining multiple target stopping locations based on the departure point and destination included in each historical trip information of multiple historical trips; performing clustering processing on the multiple stopping locations to obtain at least one clustering result, wherein one clustering result includes at least one stopping location; determining at least one area based on the stopping locations included in each clustering result; determining the location information of charging piles included in each of the at least one area; and recommending a charging service to the user if the target route passes through the target area, the charging service being used to indicate the location information of charging piles included in the target area, the target area being one of the at least one area, and the target route being the route included in the target trip.

[0010] Based on the aforementioned technical means, since the target area is an area where the user frequently stays and for extended periods, if the target route passes through the target area, it indicates that the user is likely to stay in the target area. In this case, the electronic device recommends charging services to the user, enabling the user to charge their vehicle promptly when they need to stay, thereby improving the effectiveness of the charging service recommendation.

[0011] In one possible implementation, the method further includes: acquiring environmental information of the target vehicle within a target time period, the environmental information including one or more of air quality, weather, and vehicle speed, the target time period being the time between the last car wash of the target vehicle and the current time; if the duration corresponding to the target time period is greater than or equal to a duration threshold, inputting the environmental information into a target classification model to obtain a target probability, the target classification model being used to predict the probability that the target vehicle needs a car wash, the target classification model being trained based on the historical car wash information of the target vehicle, the historical car wash information including car wash frequency and environmental information of the target vehicle within the time period between two car washes; and if the target probability is greater than or equal to a probability threshold, recommending a car wash service to the user.

[0012] Based on the aforementioned technical means, this application can provide car wash services to users when the target vehicle has not been washed for a long time and the probability of the target vehicle needing a wash is high based on the target vehicle's historical car wash habits, thereby improving the effectiveness of car wash service recommendations.

[0013] In one possible implementation, the method further includes: determining M trip information based on trip information from multiple historical trips, wherein the departure time included in each of the M trip information is the same as the current time, and the location information of the departure point included in each of the trip information is the same as the current location information, where M is an integer greater than or equal to 1; determining N destinations, wherein the N destinations are destinations whose number is greater than or equal to a number threshold among the destinations included in the M trip information; generating N trip information based on the N destinations and the current location information, wherein N is an integer greater than or equal to 1, and M≥N; recommending the N trip information to the user; and, in response to a confirmation operation on the first trip information, determining the first trip information as the trip information of the target trip, wherein the first trip information is one of the N trip information.

[0014] Based on the aforementioned technical means, this application can predict N possible trips for the user at the current time and location based on the user's historical trips, and then recommend the N trips to the user. This allows the user to select only one trip from the multiple recommended trips, and the electronic device can determine the trip information selected by the user as the trip information of the target trip, thereby improving the accuracy of trip prediction. Furthermore, based on the trip information selected by the user, service recommendations can be made, thereby improving the accuracy of service recommendations.

[0015] According to a second aspect provided in this application, a service recommendation apparatus is provided, including a determining unit and a processing unit;

[0016] The determining unit is used to determine the energy consumption type and trip type of the target trip. The energy consumption type is used to characterize the energy consumption level of the target trip, and the trip type is used to characterize the user's familiarity with the target trip. The target trip is the trip of the target vehicle. The processing unit is used to recommend a designated driver service to the user when the trip type of the target trip is a first trip type and the energy consumption type of the target trip is a high energy consumption type. The first trip type is used to characterize that the user's familiarity with the target trip is greater than a first value, and the high energy consumption type is used to characterize that the energy consumption of the target trip is greater than an energy consumption threshold.

[0017] In one possible implementation, the service recommendation device further includes an acquisition unit; the acquisition unit is specifically used to acquire trip information of multiple historical trips of the target vehicle and trip information of the target trip, wherein the trip information of one trip includes the route of the trip; the processing unit is specifically used to perform clustering processing on the trip information of the multiple historical trips and the trip information of the target trip to obtain multiple clustering results, wherein each clustering result includes at least one trip information; the determining unit is specifically used to determine the trip type of the target trip based on the number of trip information included in the target clustering result, wherein the target clustering result is the clustering result in which the target trip belongs among the multiple clustering results.

[0018] In one possible implementation, the trip information of a trip includes a route, a departure point, and a destination. The determining unit is further configured to determine multiple target stopping locations based on the departure point and destination included in each of the trip information of multiple historical trips. The processing unit is further configured to perform clustering processing on the multiple stopping locations to obtain at least one clustering result, wherein one clustering result includes at least one stopping location. The determining unit is further configured to determine at least one area based on the stopping locations included in each clustering result. The determining unit is further configured to determine the location information of charging piles included in each of the at least one area. The determining unit is further configured to recommend charging services to the user when the target route passes through a target area. The charging service is used to indicate the location information of charging piles included in the target area. The target area is one of the at least one area, and the target route is the route included in the target trip.

[0019] In one possible implementation, the service recommendation device further includes an acquisition unit; the acquisition unit is configured to acquire environmental information of the target vehicle within a target time period, the environmental information including one or more of air quality, weather, and vehicle speed, the target time period being the time between the last car wash of the target vehicle and the current time; the processing unit is further configured to, when the duration corresponding to the target time period is greater than or equal to a duration threshold, input the environmental information into a target classification model to obtain a target probability, the target classification model being used to predict the probability that the target vehicle needs a car wash, the target classification model being trained based on the historical car wash information of the target vehicle, the historical car wash information including car wash frequency and environmental information of the target vehicle within the time period between two car washes; the processing unit is further configured to, when the target probability is greater than or equal to a probability threshold, recommend a car wash service to the user.

[0020] In one possible implementation, the determining unit is further configured to determine M trip information based on trip information from multiple historical trips, wherein the departure time included in each of the M trip information is the same as the current time, and the location information of the departure point included in each of the trip information is the same as the current location information, and M is an integer greater than or equal to 1; the determining unit is further configured to determine N destinations, wherein the N destinations are destinations whose number is greater than or equal to a number threshold among the destinations included in the M trip information; the processing unit is further configured to generate N trip information based on the N destinations and the current location information, wherein N is an integer greater than or equal to 1, and M≥N; the processing unit is further configured to recommend the N trip information to the user; specifically, the determining unit is configured to determine the first trip information as the trip information of the target trip in response to a confirmation operation on the first trip information, wherein the first trip information is one of the N trip information.

[0021] According to a third aspect provided in this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the first aspect described above and any possible implementation thereof.

[0022] According to a fourth aspect provided in this application, a computer-readable storage medium is provided that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the methods described in the first aspect and any possible implementation thereof.

[0023] According to the fifth aspect provided in this application, a computer program product is provided, the computer program product including computer instructions, which, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0024] According to the sixth aspect provided in this application, a vehicle is provided, including: electronic equipment as described in the third aspect above.

[0025] Therefore, the above-mentioned technical features of this application have the following beneficial effects:

[0026] (1) When the target is familiar with the route of the target trip, and the energy consumption of the target trip is high and the user may be fatigued, it indicates that the safety of the user driving the target vehicle for the target trip is low and the user may need a designated driver service. At this time, the electronic device will actively recommend the designated driver service that the user may need and remind the user to use the designated driver service, thereby improving the efficiency and convenience of service recommendation and further improving driving safety.

[0027] (2) The electronic device performs clustering processing on the historical trip information of the target vehicle and the trip information of the target trip. The trip information can be divided into multiple cluster results. Since the trip information included in a cluster result is relatively similar, the electronic device can determine the user's familiarity with the target trip based on the number of trip information included in the cluster result to which the target trip belongs, that is, determine the trip type of the target trip, thereby improving the accuracy of trip type determination.

[0028] (3) Since the target area is an area where the user frequently stays and stays for a long time, if the target route passes through the target area, it means that the user may stay in the target area. At this time, the electronic device recommends charging services to the user, which can enable the user to charge the vehicle in time when he / she needs to stay, thus improving the effectiveness of the charging service recommendation.

[0029] (4) The electronic device can provide car wash services to the user when the target vehicle has not been washed for a long time and the probability of the target vehicle needing to be washed is high based on the target vehicle’s historical car wash habits, thereby improving the effectiveness of car wash service recommendations.

[0030] (5) Based on the user's historical itinerary, the electronic device predicts N possible itineraries for the user at the current time and current location, and then recommends the N itineraries to the user so that the user only needs to select one itinerary from the multiple recommended itineraries. The electronic device can then determine the itinerary information of the user's selected itinerary as the itinerary information of the target itinerary, which can improve the accuracy of itinerary prediction. Furthermore, based on the itinerary information selected by the user, service recommendations can be made, which can improve the accuracy of service recommendations.

[0031] It should be noted that the technical effects of any of the implementation methods in aspects two through six can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here.

[0032] 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

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0034] Figure 1 This is a flowchart illustrating a service recommendation method according to an exemplary embodiment;

[0035] Figure 2 This is a flowchart illustrating yet another service recommendation method according to an exemplary embodiment;

[0036] Figure 3 This is a flowchart illustrating yet another service recommendation method according to an exemplary embodiment;

[0037] Figure 4 This is a flowchart illustrating yet another service recommendation method according to an exemplary embodiment;

[0038] Figure 5 This is a flowchart illustrating yet another service recommendation method according to an exemplary embodiment;

[0039] Figure 6 This is a block diagram illustrating a service recommendation apparatus according to an exemplary embodiment;

[0040] Figure 7 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0041] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0042] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0043] The following explains some concepts involved in a service recommendation method, apparatus, electronic device, and storage medium provided in the embodiments of this application.

[0044] H3 Algorithm: H3 is a geospatial database for hexagonal grid spatial indexing. This algorithm uses hexagons as the basic unit, achieving efficient indexing and querying of geospatial data through hierarchical and encoded hexagonal structures. The core idea of ​​the H3 algorithm is to decompose the triangular grid of the Earth's surface into a series of hexagons, and then use a hexagonal-based hierarchical structure to organize and store these hexagons. The H3 algorithm's encoding scheme maps any point on Earth to a unique hexagonal address, thus enabling efficient indexing and querying of geospatial data.

[0045] The main features of the H3 algorithm include:

[0046] I. Efficient Spatial Indexing: The H3 algorithm uses a hexagonal grid structure, which enables fast and efficient spatial indexing and querying.

[0047] Scalability: The H3 algorithm supports multi-level refinement, which can refine the hexagon step by step, thereby supporting different spatial resolutions and query requirements.

[0048] 2. High accuracy: The H3 algorithm uses a twisted hexagonal grid structure, which can improve the accuracy of spatial indexing, especially in polar regions and near coastlines.

[0049] 3. Easy to use: The H3 algorithm provides APIs and tools in multiple languages, making it easy to use in different application scenarios.

[0050] IV. The H3 algorithm has wide applications in fields such as geographic information systems, geographic data analysis, and geographic visualization.

[0051] For example, Table 1 below shows one example of the grid range for the H3 algorithm:

[0052] Table 1

[0053]

[0054] XGBoost algorithm: XGBoost, short for "Extreme Gradient Boosting", is a decision tree algorithm that uses a gradient boosting framework and is often used for supervised learning classification and regression problems.

[0055] The following are the basic steps of the XGBoost classification algorithm:

[0056] 1. Initialize the model: xgboost uses a constant prediction value to initialize the model, which is usually the average target value of the training set.

[0057] II. Tree Construction: In each iteration, the algorithm adds a new decision tree to improve the current prediction. Each tree is a model of the prediction residuals of the target value, given the predictions of other trees. The tree construction process is greedy, selecting the optimal split point to split the nodes each time. A key feature of XGBoost is that it calculates and utilizes the gain (Gini exponent or information gain) of each split.

[0058] 3. Gradient Boosting: In each step, XGBoost calculates the gradient (partial derivative with respect to the predicted value) of the loss function for each sample and uses these gradient values ​​to replace the true residual values ​​to build a new tree. This is the key step in XGBoost's enhancement capabilities compared to traditional gradient boosting methods.

[0059] IV. Pruning: To avoid overfitting, XGBoost has a parameter to control the depth of each tree (max_depth), and other parameters such as min_child_weight to further control the complexity of the tree. These parameters are used to prune the tree after it has been built.

[0060] 5. Regularization: XGBoost includes a regularization term to control model complexity and help prevent overfitting. The regularization term includes the number of leaf nodes in the tree and the L2 norm of the leaf node values.

[0061] VI. Prediction: For classification problems, the final prediction is a weighted sum of the predictions from all trees. Then, a logistic function (for binary classification) or a softmax function (for multi-class classification) is typically used to convert the prediction into probabilities.

[0062] To facilitate understanding, the following detailed description of the service recommendation method provided in this application is given in conjunction with the accompanying drawings.

[0063] Figure 1 This is a flowchart illustrating a service recommendation method according to an exemplary embodiment, such as... Figure 1 As shown, the recommended methods for this service include S101-S102.

[0064] S101, The electronic device determines the energy consumption type and travel type of the target travel.

[0065] Among them, the energy consumption type is used to characterize the energy consumption level of the target trip, the trip type is used to characterize the user's familiarity with the target trip, and the target trip is the trip of the target vehicle.

[0066] In this embodiment of the application, the trip level includes three types: frequently visited trips, general trips, and special trips.

[0067] It should be understood that this energy consumption type includes both high-energy-consumption and low-energy-consumption types.

[0068] In one alternative implementation, the electronic device may determine an energy consumption threshold, and if the target energy consumption is greater than the energy consumption threshold, the energy consumption type of the target energy consumption is determined to be a high energy consumption type, and if the target energy consumption is less than or equal to the energy consumption threshold, the energy consumption type of the target energy consumption is determined to be a low energy consumption type.

[0069] In another alternative implementation, the electronic device can use energy consumption as the dependent variable to establish a binomial regression prediction model, and then divide the energy consumption type into two categories: high energy consumption and low energy consumption, to obtain the energy consumption type of the target energy consumption.

[0070] Optionally, the trip type may include a first trip type, a second trip type, and a third trip type, wherein the first trip type indicates that the user is highly familiar with the trip, the second trip type indicates that the user is less familiar with the trip, and the third trip type indicates that the user is extremely unfamiliar with the trip.

[0071] In one alternative implementation, the electronic device can be configured to determine a user's familiarity with a trip by setting a numerical value, and then set numerical ranges corresponding to different trip types. The electronic device can determine the trip type of the target trip based on the user's familiarity with the target trip.

[0072] In one alternative implementation, the electronic device can determine the trip type of the target trip by the number of times the target vehicle has traveled the route of the target trip within a historical time period.

[0073] In one alternative implementation, the electronic device can determine trip information for a target trip, including a target energy consumption and a target route. The electronic device can then determine the energy consumption type based on the target energy consumption and the trip type based on the target route.

[0074] In one alternative implementation, the electronic device can obtain the destination input by the user at the origin of the target vehicle, then predict the target energy consumption and the target route, and predict the arrival time based on the current time.

[0075] In another alternative implementation, the electronic device can also predict the target trip based on the user's historical trip information.

[0076] S102. When the trip type of the target trip is the first trip type and the energy consumption type of the target trip is the high energy consumption type, the electronic device recommends a designated driver service to the user.

[0077] The first trip type is used to characterize that the user's familiarity with the target trip is greater than a first value, and the high energy consumption type is used to characterize that the energy consumption of the target trip is greater than the energy consumption threshold.

[0078] Understandably, if the target trip type is type 1, it means that the user is quite familiar with the target trip and may have driven the target route many times. If the target trip type is type 2, it means that the target trip is long. In this case, the user may experience driving fatigue if they drive the target vehicle themselves. Therefore, the electronic device can proactively provide a designated driver service to the user when the user is familiar with the route and the trip is long.

[0079] In one alternative implementation, the electronic device can recommend the target service to the user by displaying the target service on the display page of the electronic device.

[0080] In this embodiment, when the target is familiar with the route of the target trip, and the energy consumption of the target trip is high and the user may be fatigued while driving, it indicates that the safety of the user driving the target vehicle for the target trip is low, and the user may need a designated driver service. At this time, the electronic device actively recommends the designated driver service that the user may need and reminds the user to use the designated driver service, which improves the efficiency and convenience of service recommendation and further improves driving safety.

[0081] Combination Figure 1 ,like Figure 2 As shown, in one implementation of this application embodiment, the above-mentioned electronic device determines the trip type of the target trip, which can be specifically implemented through S1011-S1013.

[0082] S1011. The electronic device acquires trip information of multiple historical trips of the target vehicle and trip information of the target trip.

[0083] The itinerary information for a trip includes the route of that trip.

[0084] S1012. The electronic device performs clustering processing on the trip information of multiple historical trips and the trip information of the target trip to obtain multiple clustering results.

[0085] One of the clustering results includes at least one trip information.

[0086] It should be understood that the electronic device performs clustering processing on multiple trip information, which can cluster similar trips into the same cluster, with each cluster representing a clustering result.

[0087] It is understood that the number of clustering results is the same as the number of trip types. In conjunction with the description of the above embodiments, the trip types include a first trip type, a second trip type, and a third trip type. Therefore, the number of clustering results can be 3.

[0088] It should be understood that when performing clustering, the electronic device can set the number of clustering results based on the number of trip types.

[0089] Alternatively, the electronic device may employ the k-means clustering method for clustering.

[0090] The following is an example of clustering using the kmean clustering method.

[0091] Step A: Given a dataset X = (x1, x2, ..., xi).

[0092] It is understandable that the dataset X includes i data points, where X represents the trip information of the target trip and the multiple historical trip information, and xi represents the i-th trip information.

[0093] Step B: Initialization.

[0094] Specifically, k data points are randomly selected from dataset X as cluster centers Cj.

[0095] Where k represents the number of clusters, and in this embodiment, k = 3; Cj represents the center point of the j-th cluster.

[0096] In this embodiment of the application, the electronic device can select three trip information from the trip information of the target trip and the multiple historical trip information, and determine them as the initial center point.

[0097] Step C: Allocation.

[0098] Specifically, for each data point xi, calculate its distance to the center point of each cluster and assign it to the nearest cluster.

[0099] Optionally,

[0100] d ij =||x i -C j || 2

[0101] ki = argmind ij

[0102] Where, d ij Represents data point x i and center point C j The distance between them, k iRepresents data point x i The cluster to which it belongs.

[0103] Step D: Update.

[0104] For each cluster, recalculate its center point.

[0105] Optionally, the mean of all data points in the cluster can be used as the new center point of the cluster.

[0106] Repeat steps B and C until the center point of each cluster no longer changes or the maximum number of iterations is reached.

[0107] It should be understood that the goal of the K-Means clustering algorithm is to minimize the sum of squared distances between data points within each cluster and their centroids. The final output of the K-Means algorithm can be expressed as:

[0108]

[0109] Where J(C1,C2,...,C) k ) represents the center point C of k clusters. j and their corresponding cluster S j .

[0110] In one alternative implementation, the trip information may also include departure time, energy consumption, arrival time, week of the trip, time period of the trip, departure location information, and destination location information.

[0111] Optionally, the origin location information and the destination location information can also be latitude and longitude information.

[0112] In one alternative implementation, the electronic device may also preprocess the trip information of the target trip and the data included in the multiple historical trip information, specifically by normalizing the data variables and dummy variable processing of the categorical variables.

[0113] Optionally, the normalized variables are determined to satisfy the following formula:

[0114]

[0115] Among them, y t Let x represent the variable after normalization. t This represents the variable before normalization.

[0116] Alternatively, suppose the categorical variable X before the dummy variable is processed has t categories, and the value of each category is denoted as X(t). Then t-1 dummy variables can be generated.

[0117] Optionally, the categorical variable after dummy variable processing is determined to satisfy the following formula:

[0118]

[0119] Where Y(t-1) represents the variable after dummy variable processing, and X(t) represents the variable before dummy variable processing.

[0120] Optionally, the electronic device can also classify the origin location information and destination location information based on the H3 algorithm, and then perform dummy variable processing.

[0121] In this embodiment of the application, energy consumption, departure time, and arrival time are data variables, while departure location information, destination location information, target route, week of the respective trip, and time period of the respective trip are categorical variables.

[0122] In one alternative implementation, the electronic device can divide the trip information of the target trip and the multiple historical trip information into a training dataset and a test dataset in a 7:3 ratio. The electronic device can perform clustering based on the training dataset, and then verify and optimize the clustering results based on the test dataset, thereby improving the accuracy of the clustering results.

[0123] S1013. The electronic device determines the trip type of the target trip based on the amount of trip information included in the target clustering results.

[0124] Among them, the clustering result of the target is the clustering result of the target route among the multiple clustering results.

[0125] It should be understood that a large number of trips included in a cluster result indicates that the user is more familiar with the trips included in that cluster result, while a small number of trips included in a cluster result indicates that the user is less familiar with the trips included in that cluster result.

[0126] In this embodiment of the application, the electronic device can determine the type of trip represented by each cluster result based on the number of trips included in each cluster result.

[0127] In one alternative implementation, when the number of trip information included in the target clustering result is the largest, the electronic device can determine the trip type of the target trip as the first trip type.

[0128] In one alternative implementation, the electronic device may also determine the number of trips included in the target clustering result as the familiarity level of the target trip, and then, if the familiarity level of the target trip is greater than a first value, determine the trip type of the target trip as a first trip type; if the familiarity level of the target trip is less than or equal to the first value but greater than a second value, determine the trip type of the target trip as a second trip type; and if the familiarity level of the target trip is less than or equal to the second value, determine the trip type of the target trip as a third trip type.

[0129] It should be understood that the second value is less than the first value.

[0130] In this embodiment, the electronic device performs clustering processing on the historical trip information of the target vehicle and the trip information of the target trip. The trip information can be divided into multiple clustering results. Since the trip information included in a clustering result is relatively similar, the electronic device can determine the user's familiarity with the target trip based on the number of trip information included in the clustering result to which the target trip belongs, that is, determine the trip type of the target trip, thereby improving the accuracy of trip type determination.

[0131] Combination Figure 1 ,like Figure 3 As shown, in one implementation of this application embodiment, the trip information of a trip includes a route, a departure point, and a destination, and the service recommendation method further includes S103-S107.

[0132] S103. The electronic device determines multiple target stopping locations based on the departure point and destination included in each historical trip information.

[0133] It should be understood that the target location information refers to location information where the dwell time is greater than or equal to the dwell duration threshold and the number of dwells is greater than or equal to the number of dwells threshold.

[0134] It is understandable that if the dwell time at the location is greater than or equal to the dwell time threshold, it means that the target vehicle will stay at that location for a relatively long time. In this case, the target vehicle can be charged during the longer dwell time.

[0135] It should be understood that if the number of times the target vehicle stays at a location is greater than or equal to the threshold, it means that the target vehicle frequently stays at that location. In this case, the target vehicle can be charged at the frequently stayed location.

[0136] Understandably, this electronic device can determine the dwell time of the target vehicle at each dwell location and identify dwell locations where the dwell time is greater than or equal to a dwell time threshold.

[0137] Optionally, the electronic device can determine the dwell time at each stop location based on the departure time included in each historical trip information and the end time included in the previous historical trip information.

[0138] S104. The electronic device performs clustering processing on multiple target dwelling locations to obtain at least one clustering result.

[0139] One of the clustering results includes at least one dwelling location.

[0140] It should be understood that the electronic device performs clustering on at least one dwelling position to obtain at least one cluster, and a cluster is used to characterize a clustering result.

[0141] Optionally, the electronic device may use the k-means clustering method to cluster multiple target dwelling locations.

[0142] S105. The electronic device determines at least one region based on the dwelling locations included in each clustering result.

[0143] In this embodiment of the application, a region is a region composed of the positions included in each cluster.

[0144] Optionally, a region can be a range of latitude and longitude.

[0145] S106. The electronic device determines the location information of the charging piles included in each of at least one area.

[0146] Specifically, the electronic device can acquire the location information of multiple charging piles, and then, if the location information of a certain charging pile is located in a certain area, it determines the location information of that particular charging pile as the location information of the charging pile corresponding to that certain area.

[0147] S107. When the target route passes through the target area, the electronic device recommends charging services to the user.

[0148] The charging service is used to indicate the location information of charging piles included in the target area, the target area being one of the at least one area, and the target route being the route included in the target journey.

[0149] It should be understood that if the target route passes through the target area, it means that the target vehicle frequently stops in the target area and stays there for a long time. It is possible that the target vehicle will also stop in the target area this time. In this case, the electronic device can recommend charging services to the user.

[0150] In one alternative implementation, the electronic device can also recommend charging services to the user based on the target vehicle's battery level. Specifically, if the remaining battery level is less than or equal to the target energy consumption, the electronic device can identify charging stations around the departure point before the start of the target trip and then recommend charging services to the user; if the target difference (i.e., the difference between the target energy consumption and the remaining battery level) is less than or equal to a difference threshold, it can identify charging stations around the target destination and then recommend charging services to the user. This allows for timely recommendations of charging services when the battery level is low, ensuring the vehicle's performance.

[0151] In this embodiment, since the target area is an area where the user frequently stays and stays for a long time, if the target route passes through the target area, it means that the user may stay in the target area. At this time, the electronic device recommends charging services to the user, which can enable the user to charge the vehicle in time when they need to stay, thereby improving the effectiveness of the charging service recommendation.

[0152] Combination Figure 1 ,like Figure 4 As shown, in one implementation of this application embodiment, the service recommendation method further includes S108-S110.

[0153] S108. Electronic equipment acquires environmental information of the target vehicle within the target time period.

[0154] The environmental information includes one or more of air quality, weather, and vehicle speed, and the target time period is the time between the last time the target vehicle was washed and the current time.

[0155] It should be understood that the target vehicle may move during the target time period, and the electronic device can determine the environmental information of the target vehicle during the target time period based on the location of the target vehicle.

[0156] It is understandable that the environmental information within the target time period includes the environmental information that the target vehicle passes through while driving and the environmental information that it is parked.

[0157] Optionally, the environmental information may also include the driving area, the average car wash interval for the target vehicle, and the time of the last car wash.

[0158] S109. When the duration of the target time period is greater than or equal to the duration threshold, the electronic device inputs the environmental information into the target classification model to obtain the target probability.

[0159] The target classification model is used to predict the probability that the target vehicle needs to be washed. The target classification model is trained based on the historical car wash information of the target vehicle, which includes the car wash frequency and the environmental information of the target vehicle during the time period between two car washes.

[0160] Based on the description of the above embodiments, it should be understood that the target time period is the time between the last time the target vehicle was washed and the current time. If the duration of the target time period is greater than or equal to the duration threshold, it indicates that the time interval between the current time and the last car wash is relatively large, and the target vehicle has not been washed for a long time. At this time, the electronic device can further determine whether the target vehicle needs to be washed. Specifically, the electronic device can input the environmental information of the target vehicle within the target time period into the target classification model.

[0161] Understandably, the input to this target classification model is the environmental information of the target vehicle, and the output is the probability that the car needs to be washed.

[0162] Optionally, the duration threshold can be one month or a historical car wash interval.

[0163] In one alternative implementation, the target classification model includes the XGBoost classification algorithm.

[0164] Optionally, the electronic device can normalize and dummy variable processing of the data included in the environmental information.

[0165] It should be noted that in the embodiments of this application, speed, travel, and time-related data are numerical variables and are normalized, while all other data are treated as dummy variables.

[0166] S110. When the target probability is greater than or equal to the probability threshold, the electronic device recommends a car wash service to the user.

[0167] Understandably, if the target probability is greater than or equal to the probability threshold, it means that according to the target vehicle's historical car wash habits, the probability that the target vehicle needs a car wash is relatively high, and the electronic device can recommend a car wash service to the target vehicle.

[0168] For example, the probability threshold could be 70%.

[0169] In one implementation of this application, the vehicle information may further include maintenance data, including historical maintenance data, driving distance, etc. Then, the maintenance data is input into the target classification model to obtain the probability that the target vehicle needs maintenance. When the probability that the target vehicle needs maintenance is high, maintenance services can be recommended to the user, and the need for vehicle maintenance can be detected in a timely manner.

[0170] In this embodiment of the application, the electronic device can provide car wash services to the user when the target vehicle has not been washed for a long time and the probability of the target vehicle needing a car wash is high based on the target vehicle's historical car wash habits, thereby improving the effectiveness of car wash service recommendations.

[0171] Combination Figure 1 ,like Figure 5 As shown, in one implementation of this application embodiment, the service recommendation method further includes S111-S115.

[0172] S111. The electronic device determines M trip information based on trip information from multiple historical trips.

[0173] In this context, each of the M trip information entries includes the same departure time as the current time, and the departure location information included in each trip information entry is the same as the current location information. M is an integer greater than or equal to 1.

[0174] It should be understood that each of these multiple historical itinerary information entries includes the historical departure time, historical arrival time, historical departure point, and historical destination.

[0175] It is understandable that the electronic device can determine from the multiple historical travel information that the departure time is the current time and the departure location information is the current location information, and then determine the historical travel information as the M travel information.

[0176] S112. Electronic devices determine N destinations.

[0177] Here, the N destinations are those destinations included in the M trip information that have a number greater than or equal to the number threshold, N is an integer greater than or equal to 1, and M≥N.

[0178] It should be understood that each of the M trip information includes a destination. The electronic device can determine the number of each destination in the M trip information, and then determine the destinations with a number greater than or equal to the number threshold as the N destinations.

[0179] In one alternative implementation, the electronic device may also sort each destination and then determine the top N destinations by quantity as the N destinations.

[0180] S113. The electronic device generates N trip information based on N destinations and the current location information.

[0181] Where N is an integer greater than or equal to 1.

[0182] It should be understood that a trip information includes at least a route, and the electronic device can determine the route based on the destination and current location information.

[0183] In one alternative implementation, the electronic device can also determine the travel time and arrival time based on the route.

[0184] In another alternative implementation, the electronic device can also determine the energy consumption of each of the N trip information based on the historical energy consumption of the target vehicle.

[0185] S114. The electronic device recommends N trip information to the user.

[0186] Optionally, the electronic device can display the N trip information.

[0187] S115. In response to the confirmation operation of the first travel information, the electronic device determines the first travel information as the travel information of the target travel.

[0188] The first trip information is one of the N trip information.

[0189] Alternatively, the confirmation action can be a click action.

[0190] In this embodiment, the electronic device predicts N possible trips for the user at the current time and location based on the user's historical trips, and then recommends the N trips to the user. This allows the user to select only one trip from the multiple recommended trips, and the electronic device can determine the trip information selected by the user as the trip information of the target trip. This can improve the accuracy of trip prediction, and further improve the accuracy of service recommendation based on the trip information selected by the user.

[0191] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, the service recommendation device or electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0192] This application embodiment can, based on the above method, exemplarily divide a service recommendation device or electronic device into functional modules. For example, the service recommendation device or electronic device may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.

[0193] Figure 6 This is a block diagram illustrating a service recommendation apparatus according to an exemplary embodiment. (Refer to...) Figure 6 The service recommendation device 10 includes a determination unit 101 and a processing unit 102.

[0194] The determining unit 101 is used to determine the energy consumption type and trip type of the target trip. The energy consumption type is used to characterize the energy consumption level of the target trip, and the trip type is used to characterize the user's familiarity with the target trip. The target trip is the trip of the target vehicle.

[0195] The processing unit 102 is used to recommend a designated driver service to the user when the trip type of the target trip is a first trip type and the energy consumption type of the target trip is a high energy consumption type. The first trip type is used to indicate that the user's familiarity with the target trip is greater than a first value, and the high energy consumption type is used to indicate that the energy consumption of the target trip is greater than an energy consumption threshold.

[0196] The aforementioned service recommendation device 10 also includes an acquisition unit 103.

[0197] The acquisition unit 103 is specifically used to acquire the trip information of multiple historical trips of the target vehicle and the trip information of the target trip, wherein the trip information of a trip includes the route of the trip.

[0198] The processing unit 102 is specifically used to perform clustering processing on the trip information of the multiple historical trips and the trip information of the target trip to obtain multiple clustering results, and each clustering result includes at least one trip information.

[0199] The determining unit 101 is specifically used to determine the trip type of the target trip based on the number of trip information included in the target clustering result, wherein the target clustering result is the clustering result in which the target trip belongs among the multiple clustering results.

[0200] Optionally, the trip information for a trip includes the route, departure point, and destination.

[0201] The determining unit 101 is also used to determine multiple target stopping locations based on the departure point and destination included in each historical itinerary information in the itinerary information of multiple historical itineraries.

[0202] The processing unit 102 is further configured to perform clustering processing on the multiple dwelling locations to obtain at least one clustering result, wherein a clustering result includes at least one dwelling location.

[0203] The determining unit 101 is also used to determine at least one region based on the dwell locations included in each clustering result.

[0204] The determining unit 101 is also used to determine the location information of the charging piles included in each of the at least one area.

[0205] The determining unit 101 is further configured to recommend a charging service to the user when the target route passes through a target area. The charging service is used to indicate the location information of charging piles included in the target area. The target area is one of the at least one area, and the target route is the route included in the target trip.

[0206] The acquisition unit 103 is used to acquire environmental information of the target vehicle within a target time period. The environmental information includes one or more of air quality, weather, and vehicle speed. The target time period is the time between the last time the target vehicle was washed and the current time.

[0207] The processing unit 102 is further configured to input the environmental information into the target classification model to obtain the target probability when the duration corresponding to the target time period is greater than or equal to the duration threshold. The target classification model is used to predict the probability that the target vehicle needs to be washed. The target classification model is trained based on the historical car wash information of the target vehicle. The historical car wash information includes the car wash frequency and the environmental information of the target vehicle during the time period between two car washes.

[0208] The processing unit 102 is also configured to recommend a car wash service to the user if the target probability is greater than or equal to a probability threshold.

[0209] The determining unit 101 is further configured to determine M trip information based on the trip information of multiple historical trips, wherein the departure time included in each of the M trip information is the same as the current time, and the location information of the departure point included in each of the trip information is the same as the current location information, and M is an integer greater than or equal to 1.

[0210] The determining unit 101 is also used to determine N destinations, which are destinations whose number is greater than or equal to a number threshold among the destinations included in the M trip information.

[0211] The processing unit 102 is also configured to generate N trip information based on the N destinations and the current location information, where N is an integer greater than or equal to 1 and M≥N.

[0212] The processing unit 102 is also used to recommend the N trip information to the user.

[0213] The determining unit 101 is specifically used to respond to the confirmation operation of the first trip information and determine the first trip information as the trip information of the target trip, wherein the first trip information is one of the N trip information.

[0214] 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 upon here.

[0215] Figure 7 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Figure 7 As shown, the electronic device 20 includes, but is not limited to, a processor 201 and a memory 202.

[0216] The memory 202 described above is used to store the executable instructions of the processor 201. It is understood that the processor 201 is configured to execute instructions to implement the service recommendation method in the above embodiments.

[0217] It should be noted that those skilled in the art will understand that Figure 7 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 7 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.

[0218] Processor 201 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 202, and by calling data stored in memory 202, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Processor 201 may include one or more processing units. Optionally, processor 201 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 201.

[0219] The memory 202 can be used to store software programs and various data. The memory 202 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 202 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0220] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 202 including instructions, which can be executed by a processor 201 of an electronic device 20 to implement the methods in the above embodiments.

[0221] In actual implementation, Figure 6 The functions of the determining unit 101, processing unit 102, and acquiring unit 103 can all be provided by... Figure 7 The processor 201 calls the computer program stored in the memory 202 to implement the process. The specific execution process can be found in the method section of the previous embodiment, and will not be repeated here.

[0222] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0223] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a processor 201 of an electronic device to perform the methods described above.

[0224] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0225] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0226] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0227] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the constituent units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0228] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0229] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0230] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A service recommendation method, characterized in that, include: The energy consumption type and trip type of the target trip are determined. The energy consumption type is used to characterize the energy consumption level of the target trip, and the trip type is used to characterize the user's familiarity with the target trip. The target trip is the trip of the target vehicle. The trip type for determining the target trip includes: Obtain trip information of multiple historical trips of the target vehicle and trip information of the target trip, wherein the trip information of a trip includes the route of the trip; Clustering is performed on the trip information of the multiple historical trips and the trip information of the target trip to obtain multiple clustering results, and each clustering result includes at least one trip information. Based on the amount of trip information included in the target clustering result, the trip type of the target trip is determined, and the target clustering result is the clustering result in which the target trip belongs among the multiple clustering results; If the target trip's trip type is a first trip type and the target trip's energy consumption type is a high energy consumption type, a designated driver service is recommended to the user. The first trip type is used to indicate that the user's familiarity with the target trip is greater than a first value, and the high energy consumption type is used to indicate that the energy consumption of the target trip is greater than an energy consumption threshold. The method further includes: The environmental information of the target vehicle within a target time period is obtained. The environmental information includes one or more of air quality, weather, and vehicle speed. The target time period is the time between the last time the target vehicle was washed and the current time. If the duration of the target time period is greater than or equal to the duration threshold, the environmental information is input into the target classification model to obtain the target probability. The target classification model is used to predict the probability that the target vehicle needs to be washed. The target classification model is trained based on the historical car wash information of the target vehicle. The historical car wash information includes the car wash frequency and the environmental information of the target vehicle during the time period between two car washes. If the target probability is greater than or equal to the probability threshold, a car wash service is recommended to the user.

2. The service recommendation method according to claim 1, characterized in that, The itinerary information for a trip includes the route, departure point, and destination. The method further includes: Based on the departure point and destination included in each of the multiple historical itineraries, multiple target stops are determined. Clustering is performed on the multiple dwelling locations to obtain at least one clustering result, wherein each clustering result includes at least one dwelling location; Based on the dwell locations included in each clustering result, at least one region is determined; Determine the location information of the charging piles included in each of the at least one region; If the target route passes through the target area, a charging service is recommended to the user. The charging service is used to indicate the location information of charging piles included in the target area. The target area is one of the at least one area, and the target route is the route included in the target trip.

3. The service recommendation method according to any one of claims 1-2, characterized in that, The method further includes: Based on the travel information of multiple historical trips, M travel information pieces are determined. The departure time included in each of the M travel information pieces is the same as the current time, and the location information of the departure point included in each travel information piece is the same as the current location information. M is an integer greater than or equal to 1. N destinations are determined, wherein the number of destinations included in the M trip information is greater than or equal to a certain threshold; Based on the N destinations and the current location information, generate N itinerary information, where N is an integer greater than or equal to 1, and M≥N; Recommend the N trip information to the user; In response to the confirmation operation of the first trip information, the first trip information is determined as the trip information of the target trip, and the first trip information is one of the N trip information.

4. A service recommendation device, characterized in that, Includes a determining unit and a processing unit; The determining unit is used to determine the energy consumption type and trip type of the target trip. The energy consumption type is used to characterize the energy consumption level of the target trip, and the trip type is used to characterize the user's familiarity with the target trip. The target trip is the trip of the target vehicle. The service recommendation device also includes an acquisition unit; The acquisition unit is specifically used to acquire trip information of multiple historical trips of the target vehicle and trip information of the target trip, wherein the trip information of a trip includes the route of the trip; The processing unit is specifically used to perform clustering processing on the trip information of the multiple historical trips and the trip information of the target trip to obtain multiple clustering results, and each clustering result includes at least one trip information. The determining unit is specifically used to determine the trip type of the target trip based on the number of trip information included in the target clustering result, wherein the target clustering result is the clustering result in which the target trip is located among the multiple clustering results; The processing unit is configured to recommend a designated driver service to the user when the trip type of the target trip is a first trip type and the energy consumption type of the target trip is a high energy consumption type. The first trip type is used to indicate that the user's familiarity with the target trip is greater than a first value, and the high energy consumption type is used to indicate that the energy consumption of the target trip is greater than an energy consumption threshold. The acquisition unit is further configured to acquire environmental information of the target vehicle within a target time period. The environmental information includes one or more of air quality, weather, and vehicle speed. The target time period is the time period between the last time the target vehicle was washed and the current time. The processing unit is further configured to input the environmental information into a target classification model to obtain a target probability when the duration corresponding to the target time period is greater than or equal to a duration threshold. The target classification model is used to predict the probability that the target vehicle needs to be washed. The target classification model is trained based on the historical car wash information of the target vehicle. The historical car wash information includes the car wash frequency and the environmental information of the target vehicle during the time period between two car washes. The processing unit is also configured to recommend car wash services to the user if the target probability is greater than or equal to a probability threshold.

5. The service recommendation device according to claim 4, characterized in that, A trip's itinerary information includes the route, departure point, and destination. The determining unit is further configured to determine multiple target stopping locations based on the departure point and destination included in each historical itinerary information in the itinerary information of multiple historical itineraries; The processing unit is further configured to perform clustering processing on the plurality of dwelling locations to obtain at least one clustering result, wherein a clustering result includes at least one dwelling location; The determining unit is further configured to determine at least one region based on the dwell positions included in each clustering result; The determining unit is further configured to determine the location information of the charging piles included in each of the at least one region; The determining unit is further configured to recommend a charging service to the user when the target route passes through a target area. The charging service is used to indicate the location information of charging piles included in the target area. The target area is one of the at least one area, and the target route is the route included in the target trip.

6. The service recommendation device according to any one of claims 4-5, characterized in that, The determining unit is further configured to determine M pieces of itinerary information based on the itinerary information of multiple historical itineraries, wherein the departure time included in each of the M pieces of itinerary information is the same as the current time, and the location information of the departure point included in each of the itinerary information is the same as the current location information, and M is an integer greater than or equal to 1; The determining unit is further configured to determine N destinations, wherein the N destinations are destinations whose number is greater than or equal to a number threshold among the destinations included in the M trip information; The processing unit is further configured to generate N trip information based on the N destinations and the current location information, wherein N is an integer greater than or equal to 1, and M≥N; The processing unit is also used to recommend the N trip information to the user; The determining unit is specifically used to determine the first trip information as the trip information of the target trip in response to the confirmation operation of the first trip information, wherein the first trip information is one of the N trip information.

7. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is capable of performing the method as described in any one of claims 1 to 3.

9. A vehicle, characterized in that, Including the electronic device as described in claim 7.

Images