Prediction method and device of low-energy-consumption route, computer equipment and storage medium

Abstract

The invention relates to the technical field of intelligent control, and discloses a low-energy-consumption route prediction method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining at least one candidate route when a current user inputs address information; dividing the candidate route into a plurality of basic road sections, and predicting energy consumption data of the current user in the driving process on the basic road sections to obtain predicted energy consumption data; calculating the travel power consumption of each candidate route according to the predicted energy consumption data corresponding to each basic road section; and determining a target route in the candidate routes based on the travel power consumption, and after the current user completes the travel of the target route, executing an updating operation on the cloud energy consumption array according to the actual energy consumption data of the current user. According to the invention, the problem of inaccurate energy consumption prediction caused by the fact that personalized prediction is not carried out based on historical energy consumption data of a user in a specific road section in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a method, device, computer equipment and storage medium for predicting low-energy consumption routes. Background Art

[0002] With the increasing popularity of electric vehicles, users are placing higher demands on energy-efficient travel routes. Choosing low-energy routes not only reduces travel costs and extends charging intervals, but also reduces energy consumption and environmental impact. However, current electric vehicles generally suffer from inaccurate range display, making it difficult for users to accurately plan their trips. This is especially true for long-distance or interregional trips, where inaccurate battery estimates can easily lead to anxiety and negatively impact the user experience. Therefore, how to tailor route recommendations based on users' actual driving scenarios to reduce energy consumption and provide more accurate predictions has become a key issue in improving the practicality of electric vehicles.

[0003] Currently, low-energy route recommendation solutions in this field primarily rely on factors such as road conditions, ambient temperature, and cold starts, using laboratory treadmill tests to estimate vehicle energy consumption. However, these solutions rely solely on general data from fixed scenarios and fail to provide personalized predictions based on actual user driving data on specific road sections. Consequently, energy consumption differences between different users on the same road section are not effectively identified, resulting in discrepancies between energy consumption predictions and actual driving conditions, making accurate route recommendations difficult. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, computer device, and storage medium for predicting low-energy routes to address the problem that the prior art fails to perform personalized predictions based on the user's own historical energy consumption data on specific road sections, resulting in inaccurate energy consumption predictions.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting a low-energy consumption route, the method comprising:

[0006] When the current user enters address information, obtain at least one candidate route;

[0007] Dividing the candidate route into a plurality of basic road sections, and predicting energy consumption data of the current user during driving on the basic road sections to obtain predicted energy consumption data;

[0008] Calculating the travel power consumption of each candidate route according to the predicted energy consumption data corresponding to each basic road section;

[0009] A target route is determined from the candidate routes based on the travel power consumption, and after the current user completes the journey of the target route, an update operation is performed on the cloud energy consumption array according to the actual energy consumption data of the current user.

[0010] Furthermore, the energy consumption data of the current user during driving on the basic road section is predicted to obtain predicted energy consumption data, including:

[0011] Obtain the ambient temperature level, congestion level and rainfall level for each basic road section;

[0012] Binding the ambient temperature level, the congestion level, and the rainfall level with the road sign of the basic road section to obtain current operating condition parameters;

[0013] The cloud energy consumption array is used to calculate the predicted energy consumption data of the current user during driving on the basic road section.

[0014] Furthermore, the calculation of the predicted energy consumption data of the current user during driving on the basic road section using the cloud energy consumption array includes:

[0015] According to the current working condition parameters, query whether there is historical energy consumption data of the current user in the cloud energy consumption array;

[0016] If there is historical energy consumption data, the historical energy consumption data is used as the predicted energy consumption data of the current user during driving on the basic road section;

[0017] If there is no historical energy consumption data, the cloud energy consumption array is checked to see whether there is a target user set with historical energy consumption data under the current operating parameters, and a detection result is obtained. Based on the detection result, the predicted energy consumption data of the current user during driving on the basic road section is determined.

[0018] Furthermore, the detecting whether there is a target user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array to obtain a detection result includes:

[0019] Screening a set of candidate users having historical energy consumption data under the current operating parameters in the cloud energy consumption array;

[0020] Acquiring driving characteristic parameters of the current user, wherein the driving characteristic parameters include: static acceleration characteristics, dynamic acceleration characteristics, dynamic deceleration characteristics, and speed limit offset characteristics;

[0021] Calculating a matching score between the current user and a set of candidate users based on the static acceleration feature, the dynamic acceleration feature, the dynamic deceleration feature, and the speed limit offset feature;

[0022] Based on the matching score, it is determined whether there is a target user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array.

[0023] Furthermore, determining the predicted energy consumption data of the current user during driving on the basic road section according to the detection result includes:

[0024] When the detection result indicates that a target user set exists, predicting the energy consumption data of the current user based on the energy consumption data of the target user set to obtain predicted energy consumption data;

[0025] When the detection result is that the target user set does not exist, the preset supplement mechanism is triggered to obtain the section information of the basic section, and determine whether there is a similar section in the historical driving route based on the section information; if there is a similar section, the historical energy consumption data of the current user under the current operating parameters of the similar section is used as the predicted energy consumption data, or, if there is no similar section, the energy consumption data of the current user within a preset mileage range is used as the predicted energy consumption data.

[0026] Furthermore, determining whether there is a similar road section in the historical driving route based on the road section information includes:

[0027] extracting a first slope feature from the road section information;

[0028] Obtain the second slope characteristics of other sections of the current user's historical driving route;

[0029] A difference value between the first slope characteristic and the second slope characteristic is calculated, and whether a similar road section exists in the historical driving route is determined according to the difference value.

[0030] Furthermore, the updating operation on the cloud energy consumption array according to the actual energy consumption data of the current user includes:

[0031] Uploading the actual energy consumption data to the cloud energy consumption array;

[0032] In the cloud energy consumption array, weighted calculation is performed on the historical energy consumption data of the current user and the actual energy consumption data according to the time decay weight to generate updated energy consumption data;

[0033] The updated energy consumption data overwrites the historical energy consumption data under the current operating parameters in the cloud energy consumption array.

[0034] In a second aspect, an embodiment of the present invention provides a low-energy consumption route prediction device, the device comprising:

[0035] An acquisition module, configured to acquire at least one candidate route when the current user inputs address information;

[0036] a prediction module, configured to divide the candidate route into a plurality of basic road segments, and predict energy consumption data of the current user during driving on the basic road segments to obtain predicted energy consumption data;

[0037] A calculation module, configured to calculate the travel power consumption of each candidate route based on the predicted energy consumption data corresponding to each basic road segment;

[0038] An updating module is configured to determine a target route from the candidate routes based on the travel power consumption, and after the current user completes the journey along the target route, perform an updating operation on a cloud energy consumption array according to the actual energy consumption data of the current user.

[0039] In a third aspect, an embodiment of the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method of the first aspect or any corresponding embodiment thereof.

[0041] The method provided in the embodiments of the present application has the following beneficial effects:

[0042] The method provided in the embodiment of the present application obtains at least one candidate route when the user enters address information, providing a diverse selection basis for subsequent energy consumption evaluation and route screening, ensuring that the optimal energy consumption solution can be found from multiple possible driving paths, avoiding optimization limitations caused by insufficient route coverage; by dividing basic road sections and predicting energy consumption data, etc., a personalized data-driven approach replaces the traditional model that relies on general data of fixed scenarios, ensuring a strong correlation between energy consumption prediction and the user's actual driving scenario, and significantly improving prediction accuracy; by aggregating the predicted energy consumption data of each basic road section and quantifying the total energy consumption of each candidate route, an intuitive and quantifiable evaluation index is provided for route comparison, so that the low energy consumption characteristics of the route can be concretely presented, facilitating subsequent decision-making; based on the trip power consumption, the target route is screened, and the predicted results are directly converted into a low-energy travel plan available to the user, helping the user reduce travel costs, extend mileage, and alleviate power anxiety; after the trip, the cloud energy consumption array is dynamically updated using actual energy consumption data, forming a closed-loop mechanism of prediction-verification-optimization. This process can continue to evolve as user driving data accumulates, ensuring the timeliness and adaptability of the prediction model, avoiding prediction errors caused by outdated data, and ultimately achieving a spiral improvement in energy consumption prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 is a schematic flow chart of a method for predicting a low-energy consumption route according to an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram showing a comparison between a low-energy consumption route and other candidate routes according to an embodiment of the present invention;

[0046] Figure 3 is a flowchart of another low-energy consumption route prediction method according to an embodiment of the present invention;

[0047] Figure 4 is a structural block diagram of a low-energy consumption route prediction device according to an embodiment of the present invention;

[0048] Figure 5 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0050] According to an embodiment of the present invention, a method, apparatus, computer device, and storage medium for predicting a low-energy route are provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, a method for predicting a low-energy consumption route is provided. Figure 1 is a flow chart of a method for predicting a low energy consumption route according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0052] Step S11: when the current user inputs address information, obtain at least one candidate route.

[0053] In an embodiment of the present application, first, the user submits the starting and ending points of the trip through an input device (such as a mobile phone or a vehicle-mounted system). After receiving the address information, the system calls the path planning function of the navigation module. It combines road traffic rules, real-time traffic conditions (such as congestion, construction sections), user preferences (such as whether there is a high-speed priority setting), and other conditions to generate multiple differentiated candidate routes (for example, 2-5 routes are generated according to different strategies such as shortest distance, shortest time, and low energy consumption priority). Each candidate route is composed of several indivisible basic sections. These sections are identified by a unique link ID in the navigation system, providing basic data support for decomposing the sections, obtaining the operating parameters of each section (ambient temperature level, congestion level, rainfall level), and performing energy consumption prediction in subsequent steps.

[0054] It's important to note that candidate routes must be generated to ensure they cover a diverse range of road combinations, allowing for subsequent energy consumption calculations to identify the optimal route. The number and diversity of candidate routes directly impacts the accuracy and rationality of the final recommended route. This step is crucial in connecting user travel needs with subsequent energy consumption analysis. By obtaining candidate routes, a mapping relationship is established between user input and specific road data, laying the foundation for subsequent operations such as decomposing road segments and matching historical energy consumption data.

[0055] Step S12: dividing the candidate route into a plurality of basic road sections, and predicting the energy consumption data of the current user during driving on the basic road sections to obtain predicted energy consumption data.

[0056] In this embodiment, each candidate route is broken down into indivisible basic road segments (i.e., basic road segments) according to the navigation system's unique link ID. Each basic road segment corresponds to a unique road identifier (e.g., R1, R2, etc.), forming a minimal set of route units. This process, based on the navigation system's road data structure, ensures that each basic road segment has independent geographical attributes and traffic characteristics, laying the foundation for subsequent accurate analysis of each road segment's operating parameters (ambient temperature level, congestion level, rainfall level).

[0057] After the division is complete, the energy consumption prediction phase begins: the ambient temperature level (Kx), congestion level (Tx), and rainfall level (Yx) for each basic road section are obtained, and these operating condition parameters are bound to the corresponding road sign (Rx) to form a four-dimensional operating condition parameter group consisting of "road-environment-congestion-rainfall". Then, based on the user energy consumption array stored in the cloud, the current user's historical energy consumption data under the operating condition is prioritized. If the data does not exist, the predicted energy consumption data for each basic road section is finally obtained by matching user groups with similar driving habits, screening sections with similar slopes, or invoking recent average energy consumption. This process achieves accurate estimation of user driving energy consumption through refined road section decomposition and multi-dimensional data matching.

[0058] In the embodiment of the present application, the energy consumption data of the current user during driving on the basic road section is predicted to obtain the predicted energy consumption data, including the following steps A1-A3:

[0059] Step A1: Obtain the ambient temperature level, congestion level, and rainfall level of each basic road section.

[0060] Specifically, for each basic road segment (identified by a unique road link ID), the corresponding three-dimensional working condition parameters are obtained through multi-source data:

[0061] Ambient temperature level (Kx): Based on the real-time temperature of the geographical location of the road section, the temperature impact level of the road section is determined by comparing it with the preset temperature classification standard (each 10°C is a level, covering levels -3 to 5, such as below -20°C is level -3, 10°C to 30°C is level 2-3, etc.), reflecting the impact of temperature on battery performance and energy consumption.

[0062] Congestion level (Tx): The traffic status of a road section is judged by the real-time traffic data of the navigation system (such as the congestion delay index). It is divided into four levels: smooth (≤1.5), slow (1.5-2.0), congested (2.0-4.0), and severely congested (>4.0). It is used to quantify the impact of traffic congestion on energy consumption.

[0063] Rainfall level (Yx): The daily rainfall in the area where the road section is located is obtained based on meteorological data. It is divided into levels 1 (light rain <10mm) to 6 (heavy rain >250mm) to evaluate the impact of precipitation intensity on driving resistance and energy consumption.

[0064] Through the above-mentioned data interfaces (such as weather API and real-time navigation traffic conditions), the geographic coordinates or road link ID of each basic road section are matched with the real-time environmental data to generate the corresponding Kx, Tx, and Yx levels, providing basic parameters for subsequent working condition analysis.

[0065] In step A2, the ambient temperature level, congestion level, and rainfall level are bound to the road signs of the basic road section to obtain current working condition parameters.

[0066] Specifically, the three-dimensional grade parameters (Kx, Tx, Yx) are associated with the unique road identifier (Rx, i.e., the link ID) of the underlying road segment to form a four-dimensional operating condition parameter group (Rx, Kx, Tx, Yx) encompassing "road-temperature-congestion-rainfall." The binding logic is as follows: using the road identifier Rx as the core index, Kx, Tx, and Yx are integrated as attribute fields to ensure that each operating condition parameter group uniquely corresponds to a basic road segment and its specific environmental conditions (e.g., R1 corresponds to K = Level 2, T = Slow Traffic, and Y = Level 2 Light Rain). This operating condition parameter group directly matches the index field of the cloud-based energy consumption array (UX, Rx, Kx, Tx, Yx, Ex), becoming a key condition for querying a user's historical energy consumption data or matching similar user groups. For example, when user U0 travels to section Rx, (Rx, Kx, Tx, Yx) can be used to quickly locate whether a corresponding historical energy consumption record (Ex) exists, or to filter data from other users with the same operating condition parameters.

[0067] Through this binding process, discrete environmental data is structured to form standardized inputs that can be recognized and processed by system algorithms, providing accurate matching basis for energy consumption prediction.

[0068] Step A3: Calculate the predicted energy consumption data of the current user during driving on the basic road section using the cloud energy consumption array.

[0069] The method provided in the embodiment of the present application obtains the ambient temperature level, congestion level and rainfall level of the basic road section, and binds them with road signs to form the current operating condition parameters, thereby quantifying dynamic influencing factors such as weather and road conditions into calculable input indicators; prediction is performed based on the cloud-based energy consumption array, so that the energy consumption prediction model can accurately capture the energy consumption differences under different environmental conditions, avoiding the one-sidedness of traditional solutions that only rely on general data of fixed scenarios; through the fusion of multi-dimensional operating condition parameters, refined modeling of the user's actual driving scenario is achieved, laying a data foundation for subsequent personalized energy consumption prediction, and significantly improving the fit between the prediction results and the actual driving energy consumption.

[0070] In the embodiment of the present application, step A3 includes the following steps A31-A33:

[0071] Step A31: query whether there is historical energy consumption data of the current user in the cloud energy consumption array according to the current working condition parameters.

[0072] Specifically, the cloud-based energy consumption array is stored in a structure of (UX, Rx, Kx, Tx, Yx, Ex), where the first five items are query keys and Ex is the average energy consumption value under the corresponding operating conditions. By matching U0's user ID with the current operating condition parameters, it is determined whether there is a historical record (that is, whether there is an entry that completely matches (U0, Rx, Kx, Tx, Yx)). If user U0 has driven on the same road Rx and the same environmental conditions (Kx, Tx, Yx), their historical average energy consumption Ex will be pre-stored and updated. At this time, the query will directly return the Ex value; if the operating condition combination has never been driven, a no-match result will be returned, triggering the subsequent user group matching mechanism.

[0073] Step A32: If there is historical energy consumption data, the historical energy consumption data is used as the predicted energy consumption data for the current user during driving on the basic road section.

[0074] Specifically, when a matching historical record is found, the average energy consumption value Ex in the entry is directly used as the predicted energy consumption data (E1) under the current working conditions. The core logic of this process is that the user's driving habits under the same road and environmental conditions are stable, and the historical energy consumption data can directly reflect their actual energy consumption level under the working conditions. Therefore, it can be used as a reliable prediction basis without additional calculation. For example, if user U0 has generated an average energy consumption of 15kWh / 100km on the R1 section (K=level 2, T=slow driving, Y=level 2), then when the same working conditions are encountered again, this value is directly used as the prediction result. Skipping the complex external data matching process and directly using historical data not only reduces the consumption of computing resources, but also avoids potential errors introduced by user group matching or supplementary mechanisms, ensuring the efficiency of the prediction process and the reliability of the results.

[0075] In step A33, if there is no historical energy consumption data, the cloud energy consumption array is checked to see if there is a target user set with historical energy consumption data under the current operating parameters, and the detection result is obtained. The predicted energy consumption data of the current user during driving on the basic road section is determined based on the detection result.

[0076] The method provided in the embodiment of the present application prioritizes querying the historical energy consumption data of the current user in the cloud energy consumption array, and directly utilizes the personalized data of the user's own driving habits and vehicle characteristics to avoid individual deviations caused by direct prediction; when historical data is lacking, a target user set with the same operating parameters is screened, and statistical laws of group driving data are used to make inferences to solve the problem of sparse individual data; through the two-layer mechanism of "individual data priority + group data supplement", the personalized characteristics of the prediction are guaranteed, and the universality of group data is used to make up for the lack of data, so that the prediction model can output reliable results under different data conditions.

[0077] In an embodiment of the present application, detecting whether there is a target user set with historical energy consumption data under current operating parameters in a cloud energy consumption array and obtaining a detection result includes: screening a candidate user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array; obtaining driving characteristic parameters of the current user, wherein the driving characteristic parameters include: static acceleration characteristics, dynamic acceleration characteristics, dynamic deceleration characteristics, and speed limit offset characteristics; calculating a matching score between the current user and the candidate user set based on the static acceleration characteristics, the dynamic acceleration characteristics, the dynamic deceleration characteristics, and the speed limit offset characteristics; and determining whether there is a target user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array based on the matching score.

[0078] Specifically, when no historical data for user U0 is found, the "candidate user set matching" mechanism is activated: first, all candidate user sets (U1, U2, ..., Um) with valid energy consumption data under the current operating parameters (Rx, Kx, Tx, Yx) are screened from the cloud energy consumption array. That is, all user entries that meet the conditions (*, Rx, Kx, Tx, Yx, *) are screened (* represents any value; only the operating parameters need to be strictly matched). Secondly, for the initially screened candidate users, a matching score is calculated based on four driving characteristic parameters. Among them, the driving characteristic parameters include but are not limited to static acceleration (starting acceleration), dynamic acceleration (acceleration during driving), dynamic deceleration (braking intensity), and average speed and speed limit offset (speed stability). Each parameter has a maximum score of 25, with a total score of 100. The top 10 candidate users with the highest matching scores are selected as the target user set, and their driving style and energy consumption characteristics are considered to be closest to those of the current user U0.

[0079] Finally, calculate the average energy consumption value of the target user set under this working condition As the estimated energy consumption E1 of U0, the average energy consumption value is calculated as follows:

[0080]

[0081] For example, if the average energy consumption of the target user group under (R1, K2, T2, Y2) is 16 kWh / 100 km, then E1 takes this value.

[0082] It should be noted that the calculation of the matching score between the current user U0 and the matched candidate user requires starting from four driving characteristic parameters: Static acceleration: obtain the user's average accelerator pedal depth (0% to 100%) within 3 seconds from the vehicle being stationary to moving, matching score = 25×(1-|the difference between the historical static average accelerator pedal depth of user U0 and the matched user|); Dynamic acceleration: obtain the average accelerator pedal depth (0% to 100%) within 3 seconds before each re-pressing of the accelerator when the vehicle is moving, matching score = 25×(1-|the difference between the historical static average accelerator pedal depth of user U0 and the matched user|); Historical dynamic average accelerator pedal depth difference |); Dynamic deceleration: Obtains the average brake pedal depth (0% to 100%) within 3 seconds before each re-application of the brakes while the vehicle is in motion. Matching score = 25 × (1 - |Historical dynamic brake pedal depth difference|); Average speed offset relative to the road speed limit: Calculates the offset ratio of the user's average speed relative to the road speed limit (-100% to 100%, with 100% speeding as 100%). Matching score = 25 × (1 - |Historical average speed limit offset difference|). The final matching score is the sum of the above four scores, with a maximum of 25 points for each, for a total of 100 points, and is used to quantify the degree of similarity between users' driving styles.

[0083] The method provided in the embodiment of the present application calculates the matching score between the user and the candidate users by introducing driving characteristic parameters (such as acceleration habits, braking frequency, etc.), thereby screening a set of target users with highly similar driving behaviors from group data; converting the personalized differences in driving habits into quantifiable matching indicators, so that the utilization of group data is deepened from simple working condition parameter matching to precise matching at the driving behavior level; compared with screening based only on working condition parameters, the matching mechanism combined with driving characteristics can more accurately reflect the energy consumption differences of different users under the same road conditions, further improving the pertinence and accuracy of the prediction model.

[0084] In the embodiment of the present application, the predicted energy consumption data of the current user during driving on the basic road section is determined based on the detection results, including two situations:

[0085] Case 1: When the detection result shows that the target user set exists, the energy consumption data of the current user is predicted based on the energy consumption data of the target user set to obtain predicted energy consumption data.

[0086] Specifically, when the detection result shows that there is a target user set, it indicates that there are other users with driving characteristics highly similar to the current user U0 under the current working condition parameters (i.e., the top 10 candidate users with matching scores). At this time, the prediction logic is based on the assumption that "similar driving styles lead to similar energy consumption characteristics". The average energy consumption value of the target user set under this working condition is calculated as the predicted energy consumption data (E1) of the current user. First, the historical average energy consumption value Ex of each user in the target user set under the working condition (Rx, Kx, Tx, Yx) is extracted. i(i=1,2,...,n,n≤10), then for all Ex i Take the arithmetic mean, that is

[0087] This process focuses on user groups with highly matched driving characteristics, combining the statistical patterns of group data with the similarities of individual driving habits. This not only avoids the individual differences caused by directly using full user data, but also leverages the target users' actual energy consumption performance under the same driving conditions, ensuring that the prediction results are close to the users' actual energy consumption levels even when individual historical data is lacking. For example, if the energy consumption of three users in the target user group is 15kWh / 100km, 16kWh / 100km, and 17kWh / 100km, respectively, E1 is 16kWh / 100km. This value comprehensively reflects the common energy consumption of users with similar driving styles under the same environment and road conditions, providing a prediction basis that is both universal and personalized for the current user.

[0088] Case 2: When the detection result shows that the target user set does not exist, the preset supplement mechanism is triggered to obtain the section information of the basic section, and determine whether there is a similar section in the historical driving route based on the section information; if there is a similar section, the historical energy consumption data of the current user under the current operating parameters of the similar section is used as the predicted energy consumption data, or, if there is no similar section, the energy consumption data of the current user within the preset mileage range is used as the predicted energy consumption data.

[0089] In an embodiment of the present application, when the detection result is that the target user set does not exist, the preset supplement mechanism is triggered, wherein the execution link of the supplement mechanism includes: when there are similar road sections, the historical average energy consumption data of user U0 on these similar road sections is directly taken as the predicted value. For example, the current road section is R1 (K = 2 levels, T = slow driving, Y = 2 levels, slope 6%), and the energy consumption of the R2 road section (K = 2 levels, T = slow driving, Y = 2 levels, slope 6.3%) in the historical records is 16kWh / 100km, then 16kWh / 100km is used as the predicted energy consumption E1 of the current road section. This strategy is based on the assumption that "the same environmental conditions + similar slopes have similar effects on energy consumption" and uses the user's own historical data to achieve indirect matching across road sections. When there are no similar road sections, the average energy consumption of user U0 within the preset mileage range (the first 100 kilometers, if the total mileage is insufficient, the entire mileage is taken) is extracted as the predicted value. For example, if a user's average energy consumption over the past 50 kilometers is 18kWh / 100km, then E1 is 18kWh / 100km. This logic is based on the premise that driving habits are stable in the short term. By reducing the data matching dimension (relying only on mileage range), the prediction process is uninterrupted, providing a guaranteed data base for subsequent route energy consumption calculations.

[0090] In an embodiment of the present application, determining whether there is a similar road section in the historical driving route based on the road section information includes: extracting a first slope feature in the road section information; obtaining a second slope feature of other road sections in the historical driving route of the current user; calculating a difference value between the first slope feature and the second slope feature, and determining whether there is a similar road section in the historical driving route based on the difference value.

[0091] Specifically, when user U0 has neither its own historical energy consumption data nor a target user group with similar driving habits, a supplementary mechanism of "segment similarity matching" is activated: the "segment information" of the current basic segment is obtained. In addition to the three-dimensional operating condition parameters (Kx, Tx, Yx), the first slope feature is extracted, that is, the average slope of the segment (e.g., 5% uphill, 3% downhill, etc.). The average slope is calculated as follows: average slope = (total climbing height / road length) * 100%. In user U0's historical driving records, all other segments that meet the following conditions are screened: the ambient temperature level (Kx), congestion level (Tx), and rainfall level (Yx) are exactly the same as the current segment. The second slope feature of these historical segments is extracted and the difference between the second slope feature and the first slope feature of the current segment is calculated. If the slope difference is ≤5% (e.g., the slope of the current segment is 8%, and the slope of the historical segment is between 7.6% and 8.4%), the segment is determined to be similar.

[0092] It should be noted that slope is a key factor affecting vehicle energy consumption (e.g., energy consumption increases when going uphill and decreases when going downhill). In the absence of user group data, by limiting the same environmental conditions and relaxing the road uniqueness restrictions (allowing different Rx but the same working conditions + similar slopes), the secondary use of historical data can be achieved to ensure that the prediction model still has data support in extreme cases.

[0093] The method provided in the embodiment of the present application triggers a preset supplement mechanism. In extreme data-missing scenarios, similar sections in historical driving routes are mined based on section information (such as slope characteristics), or energy consumption data within a preset mileage range is used as a substitute to build a multi-level data processing strategy. The slope characteristics of the sections are extracted and the difference values are calculated to accurately locate historical sections with similar physical properties, so that predictions in data-free scenarios can still be based on the user's past driving experience rather than relying entirely on general data. This mechanism effectively improves the robustness of the prediction system, ensuring that reasonable energy consumption predictions can still be output in complex road conditions or new sections, avoiding prediction failures due to data gaps.

[0094] Step S13: Calculate the travel power consumption of each candidate route based on the predicted energy consumption data corresponding to each basic road section.

[0095] In the embodiment of the present application, the predicted energy consumption data (E1, E2, ..., En, in units such as kWh / 100km) of each basic road section and the actual distance of each road section (L1, L2, ..., Ln, in km) provided by the navigation system are used. The predicted energy consumption data is generated by matching user historical data, the average energy consumption of similar user groups, or a supplementary mechanism to ensure that each road section has a corresponding energy consumption index. The weighted summation formula is used:

[0096]

[0097] Where W is the total power consumption of a single route; L i is the distance of each basic road section; E i To predict energy consumption.

[0098] As an example, if a route contains three sections with distances of 10km, 20km, and 15km respectively, and the corresponding energy consumption is 15kWh / 100km, 18kWh / 100km, and 16kWh / 100km, then the total power consumption is W = 10×0.15+20×0.18+15×0.16=7.5kWh.

[0099] The above calculation process is then performed on each of the generated candidate routes (e.g., three different routes) to obtain the total power consumption for each route. This process ensures that the energy consumption performance of different routes is quantifiable and comparable, providing data support for subsequent selection of the route with the lowest energy consumption.

[0100] In step S14, a target route is determined from candidate routes based on the travel power consumption, and after the current user completes the journey along the target route, an update operation is performed on the cloud energy consumption array according to the actual energy consumption data of the current user.

[0101] In an embodiment of the present application, an update operation is performed on the cloud energy consumption array based on the actual energy consumption data of the current user, including: uploading the actual energy consumption data to the cloud energy consumption array; in the cloud energy consumption array, weighted calculation is performed on the current user's historical energy consumption data and actual energy consumption data according to the time decay weight to generate updated energy consumption data; and the updated energy consumption data is used to overwrite the historical energy consumption data under the current operating parameters in the cloud energy consumption array.

[0102] In an embodiment of the present application, after calculating the total power consumption of all candidate routes (such as Route A is 20kWh, Route B is 18kWh, and Route C is 22kWh), the route with the lowest total power consumption (such as Route B) is directly selected as the target route and recommended to the user. Figure 2 A schematic diagram showing the comparison between the low energy consumption route and other candidate routes, such as Figure 2The chart shows three routes from the starting point to the destination, along with their corresponding information, each displaying different route characteristics: the route with lower energy consumption (i.e., the target route) takes 3 hours and 35 minutes, covers a distance of 178 kilometers, consumes 25 kWh, and is marked as saving a maximum of 13.2% electricity; the shorter route takes 3 hours and 29 minutes, covers a distance of 183 kilometers, consumes 28.8 kWh, and the shorter route takes 3 hours and 45 minutes, covers a distance of 169 kilometers, and consumes 26.4 kWh. This information helps users choose the appropriate route based on their needs (e.g., energy saving, time saving, or short distance).

[0103] After the user completes the target route, the average energy consumption data of each basic section during the actual driving process (i.e., the actual energy consumption value) is collected, and the cloud energy consumption array is updated according to the following process: the actual energy consumption data is bound to the corresponding working condition parameters (Rx, Kx, Tx, Yx) and the user ID (U0), and uploaded to the cloud database; the time decay factor is introduced (the weight of the data in the past three months is 100%, and the weight of the data three months ago is 50%), and the historical energy consumption data and the newly uploaded actual energy consumption data are weighted averaged to calculate the total average energy consumption E x The way is:

[0104]

[0105] Among them, the weighting rule is: the data of the past three months (t i ≤90 days), W i =100%; data from 3 months ago (t i >90 days), W i =50%.

[0106] For example, if the historical data under a certain working condition is 15kWh / 100km (half a year ago, with a weight of 50%), and the current actual data is 16kWh / 100km (with a weight of 100%), the updated value is (15×0.5+16×1.0) / (0.5+1.0)=15.67kWh / 100km; the new energy consumption value after weighted calculation will overwrite the historical records under the corresponding working condition parameters in the cloud energy consumption array to ensure that the latest optimized data is used in subsequent predictions, forming a closed loop of "prediction-verification-update" to continuously improve the model's fitting accuracy of user energy consumption characteristics.

[0107] The method provided in the embodiment of the present application constructs a closed-loop optimization mechanism of "prediction-measurement-update" by uploading actual energy consumption data to the cloud and performing time-decay weighted calculation on historical data; the introduction of time-decay weights makes recent data have a greater impact on the prediction model, ensuring that the cloud energy consumption array can reflect the user's latest driving status and vehicle performance changes in real time; by dynamically overwriting historical data, prediction deviations caused by outdated data are avoided, and the system continues to self-optimize as the user's mileage increases, ultimately achieving dynamic improvement in energy consumption prediction accuracy and long-term reliability assurance.

[0108] Figure 3 FIG. 1 is a flow chart of another method for predicting a low-energy consumption route according to an embodiment of the present invention. Figure 3 As shown, the process begins by storing a user's average energy consumption (Ex) for different road conditions (Rx), ambient temperature levels (Kx), congestion levels (Tx), and rainfall levels (Yx) in the cloud, creating a data set (UX, Rx, Kx, Tx, Yx, Ex). After the user actually drives the road, they upload the average energy consumption for that section. After setting their destination, the navigation system generates accessible routes (e.g., Route 1, Route 2, ..., Route X), splitting each route into multiple road segments (R1, R2, ..., Rn). Weather data is used to obtain the ambient temperature, congestion level, and rainfall level for each road segment, forming a data set (Rn, Kn, Tn, Yn). For each working condition (such as (R1, K1, T1, Y1)), first determine whether the user has an average energy consumption E1 other than the default value: if so, directly use the cloud data as the estimated energy consumption E1; if not, filter the user group (U1, U2...Um) with similar driving habits under the working condition. If so, take the average of their energy consumption as E1. If not, obtain the average energy consumption of user U0 on other roads with the same ambient temperature level, congestion level, and rainfall level (if not, take the average energy consumption of nearly 100km) as E1. Repeatedly obtain the average energy consumption of all roads on the route, and calculate the total power consumption based on the distance of each section. After obtaining the total power consumption of all routes, select the route with the lowest total power consumption as the low-energy route recommended to the user. After the user completes the trip, upload the average energy consumption of each section of the road to update the cloud data to achieve cyclic optimization.

[0109] In this embodiment, a low-energy route prediction device is also provided. The device is used to implement the above-mentioned embodiments and preferred embodiments. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0110] This embodiment provides a low energy consumption route prediction device, such as Figure 4 Shown, including:

[0111] The acquisition module 41 is used to acquire at least one candidate route when the current user inputs address information;

[0112] The prediction module 42 is used to divide the candidate route into a plurality of basic road segments and predict the energy consumption data of the current user during driving on the basic road segments to obtain predicted energy consumption data;

[0113] A calculation module 43 is used to calculate the travel power consumption of each candidate route based on the predicted energy consumption data corresponding to each basic road segment;

[0114] The updating module 44 is configured to determine a target route from candidate routes based on the travel power consumption, and to update the cloud energy consumption array according to the actual energy consumption data of the current user after the current user completes the journey along the target route.

[0115] Furthermore, the prediction module 42 further includes: an acquisition submodule, a binding submodule, and a calculation submodule;

[0116] The acquisition submodule is used to obtain the ambient temperature level, congestion level and rainfall level of each basic road section;

[0117] The binding submodule is used to bind the ambient temperature level, congestion level and rainfall level with the road signs of the basic road section to obtain the current working condition parameters;

[0118] The calculation submodule is used to use the cloud energy consumption array to calculate the predicted energy consumption data of the current user during driving on the basic road section.

[0119] Furthermore, the calculation submodule is used to query whether there is historical energy consumption data of the current user in the cloud energy consumption array according to the current operating parameters; if there is historical energy consumption data, the historical energy consumption data is used as the predicted energy consumption data of the current user during driving on the basic road section; if there is no historical energy consumption data, it is used to detect whether there is a target user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array, obtain the detection result, and determine the predicted energy consumption data of the current user during driving on the basic road section based on the detection result.

[0120] Furthermore, the calculation submodule further includes: a detection unit and a determination unit;

[0121] The detection unit is configured to screen a set of candidate users with historical energy consumption data under current operating parameters in a cloud energy consumption array; obtain driving characteristic parameters of the current user, wherein the driving characteristic parameters include: static acceleration characteristics, dynamic acceleration characteristics, dynamic deceleration characteristics, and speed limit offset characteristics; calculate a matching score between the current user and the set of candidate users based on the static acceleration characteristics, dynamic acceleration characteristics, dynamic deceleration characteristics, and speed limit offset characteristics; and determine whether a set of target users with historical energy consumption data under current operating parameters exists in the cloud energy consumption array based on the matching score.

[0122] A determination unit is used to predict the energy consumption data of the current user based on the energy consumption data of the target user set to obtain predicted energy consumption data when the detection result shows that the target user set exists; when the detection result shows that the target user set does not exist, trigger a preset supplement mechanism, obtain the section information of the basic section, and determine whether there is a similar section in the historical driving route based on the section information; if there is a similar section, use the historical energy consumption data of the current user under the current operating parameters of the similar section as the predicted energy consumption data, or, if there is no similar section, use the energy consumption data of the current user within a preset mileage range as the predicted energy consumption data.

[0123] Furthermore, the determination unit also includes: an extraction subunit, used to extract the first slope feature in the road section information; obtain the second slope feature of other sections in the current user's historical driving route; calculate the difference value between the first slope feature and the second slope feature, and determine whether there is a similar section in the historical driving route based on the difference value.

[0124] Furthermore, the update module 44 is used to upload the actual energy consumption data to the cloud energy consumption array; in the cloud energy consumption array, the historical energy consumption data and the actual energy consumption data of the current user are weightedly calculated according to the time attenuation weight to generate updated energy consumption data; the updated energy consumption data is used to overwrite the historical energy consumption data under the current operating parameters in the cloud energy consumption array.

[0125] See also Figure 5 , Figure 5 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 5As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).

[0126] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0127] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0128] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of a computer device for displaying a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0129] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0130] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0131] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0132] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for predicting a low-energy consumption route, characterized in that: The method comprises: When the current user enters address information, obtain at least one candidate route; Dividing the candidate route into a plurality of basic road sections, and predicting energy consumption data of the current user during driving on the basic road sections to obtain predicted energy consumption data; Calculating the travel power consumption of each candidate route according to the predicted energy consumption data corresponding to each basic road section; A target route is determined from the candidate routes based on the travel power consumption, and after the current user completes the journey of the target route, an update operation is performed on the cloud energy consumption array according to the actual energy consumption data of the current user.

2. The method according to claim 1, characterized in that The step of predicting the energy consumption data of the current user during driving on the basic road section to obtain the predicted energy consumption data includes: Obtain the ambient temperature level, congestion level and rainfall level for each basic road section; Binding the ambient temperature level, the congestion level, and the rainfall level with the road sign of the basic road section to obtain current operating condition parameters; The cloud energy consumption array is used to calculate the predicted energy consumption data of the current user during driving on the basic road section.

3. The method according to claim 2, characterized in that The calculating of the predicted energy consumption data of the current user during driving on the basic road section using the cloud energy consumption array includes: According to the current working condition parameters, query whether there is historical energy consumption data of the current user in the cloud energy consumption array; If there is historical energy consumption data, the historical energy consumption data is used as the predicted energy consumption data of the current user during driving on the basic road section; If there is no historical energy consumption data, the cloud energy consumption array is checked to see whether there is a target user set with historical energy consumption data under the current operating parameters, and a detection result is obtained. The predicted energy consumption data of the current user during driving on the basic road section is determined based on the detection result.

4. The method according to claim 3, characterized in that The detecting whether there is a target user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array and obtaining a detection result includes: Screening a set of candidate users having historical energy consumption data under the current operating parameters in the cloud energy consumption array; Acquiring driving characteristic parameters of the current user, wherein the driving characteristic parameters include: static acceleration characteristics, dynamic acceleration characteristics, dynamic deceleration characteristics, and speed limit offset characteristics; Calculating a matching score between the current user and a set of candidate users based on the static acceleration feature, the dynamic acceleration feature, the dynamic deceleration feature, and the speed limit offset feature; Based on the matching score, it is determined whether there is a target user set with historical energy consumption data under the current operating parameters in the cloud energy consumption array.

5. The method according to claim 3, characterized in that The determining, based on the detection result, predicted energy consumption data of the current user during driving on the basic road section includes: When the detection result indicates that a target user set exists, predicting the energy consumption data of the current user based on the energy consumption data of the target user set to obtain predicted energy consumption data; When the detection result is that the target user set does not exist, the preset supplement mechanism is triggered to obtain the section information of the basic section, and determine whether there is a similar section in the historical driving route based on the section information; if there is a similar section, the historical energy consumption data of the current user under the current operating parameters of the similar section is used as the predicted energy consumption data, or, if there is no similar section, the energy consumption data of the current user within a preset mileage range is used as the predicted energy consumption data.

6. The method according to claim 5, characterized in that The determining whether there is a similar road section in the historical driving route according to the road section information includes: extracting a first slope feature from the road section information; Obtain the second slope characteristics of other sections of the current user's historical driving route; A difference value between the first slope characteristic and the second slope characteristic is calculated, and whether a similar road section exists in the historical driving route is determined based on the difference value.

7. The method according to claim 1, characterized in that The updating operation on the cloud energy consumption array according to the actual energy consumption data of the current user includes: Uploading the actual energy consumption data to the cloud energy consumption array; In the cloud energy consumption array, weighted calculation is performed on the historical energy consumption data of the current user and the actual energy consumption data according to the time decay weight to generate updated energy consumption data; The updated energy consumption data overwrites the historical energy consumption data under the current operating parameters in the cloud energy consumption array.

8. A low energy consumption route prediction device, characterized in that: The device comprises: An acquisition module, configured to acquire at least one candidate route when the current user inputs address information; a prediction module, configured to divide the candidate route into a plurality of basic road segments, and predict energy consumption data of the current user during driving on the basic road segments to obtain predicted energy consumption data; A calculation module, configured to calculate the travel power consumption of each candidate route based on the predicted energy consumption data corresponding to each basic road segment; An updating module is used to determine a target route among the candidate routes based on the travel power consumption, and after the current user completes the journey of the target route, perform an updating operation on the cloud energy consumption array according to the actual energy consumption data of the current user.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images