Vehicle comprehensive performance analysis and improvement method, equipment and storage medium based on multi-dimensional big data analysis

Abstract

The present invention relates to the field of electronic digital processing technology, and discloses a comprehensive performance analysis and improvement method, device and storage medium for vehicle models based on multi-dimensional big data analysis. The method divides different vehicle use scenarios and population characteristics, selects target performance indicators that affect vehicle use scenarios, and evaluates vehicle models based on target performance indicators, thereby realizing a vehicle model performance evaluation system oriented to vehicle use scenarios and population characteristics; remotely and accurately improves the poor performance indicators of the vehicle model to be improved, effectively improving the comprehensive performance of the vehicle model to be improved.

Description

Technical Field

[0001] The present invention relates to the field of electronic digital processing technology, and in particular to a vehicle model comprehensive performance analysis and improvement method, device and storage medium based on multi-dimensional big data analysis. Background Art

[0002] With the development of automobile technology, users' demands for automobile products have begun to be personalized and diversified. At the same time, with the advancement of intelligent technology, automobile products have begun to carry more demands beyond driving, and the safety, comfort and convenience of products have been improved.

[0003] As more and more models are put on the market, the performance of each model varies. The vehicle performance given by traditional vehicle testing technology (such as collision test and driving range test) can no longer meet the needs of current users. How to conduct comprehensive performance evaluation of models for the market and specific groups has become an urgent problem to be solved. In addition, how to improve the performance of models is also a technical problem that car companies need to solve urgently.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a vehicle model comprehensive performance analysis and improvement method, device and storage medium based on multi-dimensional big data analysis, customizes target performance indicators for specific groups of people and specific scenarios, and then calculates the comprehensive performance value of the vehicle model, and improves the vehicle model to be improved, providing a scientific and comprehensive evaluation system, which is conducive to improving the comprehensive performance of the vehicle.

[0006] The embodiment of the present invention provides a vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis, the method comprising:

[0007] S110, collecting travel data and vehicle usage data of multiple users, and determining population characteristics and vehicle usage scenarios corresponding to each vehicle model according to the travel data and vehicle usage data; the vehicle usage scenarios include high-frequency scenarios and vehicle purchase-decisive scenarios;

[0008] S120, selecting multiple target performance indicators from the full set of performance indicators according to the vehicle usage scenario, and finally obtaining a correspondence between the vehicle model, population characteristics, vehicle usage scenario, and the target performance indicator;

[0009] S130, determining the initial weight of each target performance indicator of any vehicle model according to the type of the vehicle usage scenario;

[0010] S140, obtaining the trade-in data of the target users corresponding to the population characteristics for each vehicle model, and the physiological feeling data of the target users for each vehicle model in the vehicle use scenario; modifying the initial weights according to the trade-in data and the physiological feeling data, to obtain the final weights of each target performance indicator of any vehicle model;

[0011] S150, performing weighted summation on the performance quantization values ​​of the target performance indicators according to the final weights to obtain a comprehensive performance value of the vehicle model corresponding to the population characteristics and vehicle usage scenarios;

[0012] S160. For the same population characteristics, select excellent models whose comprehensive performance values ​​are greater than or equal to a set performance threshold and models to be improved whose comprehensive performance values ​​are less than the set performance threshold, and determine excellent target performance indicators that meet the requirements among the excellent models;

[0013] S170, improving the vehicle model to be improved according to the excellent target performance indicator by means of firmware upgrade or software update;

[0014] S180, obtaining the target user's trade-in data for the vehicle model to be improved, and the target user's physiological feeling data in the vehicle usage scenario;

[0015] S190, recalculating the final weights of the target performance indicators according to the trade-in data and the physiological feeling data obtained in S180, performing weighted summation on the target performance indicators according to the final weights, and obtaining the comprehensive performance value of the vehicle model to be improved corresponding to the population characteristics and the vehicle usage scenario;

[0016] S200. If the comprehensive performance value of the vehicle model to be improved is greater than or equal to the set performance threshold, the improvement is successful; if the comprehensive performance value of the vehicle model to be improved is less than the set performance threshold, the excellent target performance index is updated and the process returns to S170.

[0017] An embodiment of the present invention provides an electronic device, the electronic device comprising:

[0018] Processor and memory;

[0019] The processor is used to execute the steps of the vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis described in any embodiment by calling the program or instructions stored in the memory.

[0020] An embodiment of the present invention provides a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute the steps of the vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis described in any embodiment.

[0021] The embodiments of the present invention have the following technical effects:

[0022] 1. The present invention divides different vehicle usage scenarios and population characteristics, selects target performance indicators that have an impact on vehicle usage scenarios, and evaluates vehicle models based on the target performance indicators, thereby realizing a vehicle model performance evaluation system oriented to vehicle usage scenarios and population characteristics.

[0023] 2. The present invention determines the initial weight of each target performance indicator according to the type of vehicle use scenario, and corrects the initial weight according to the trade-in data and physiological perception data to obtain the final weight, and uses the final weight to perform weighted summation on the target performance indicators, thereby correcting the weight of the target performance indicators according to the performance advantages of the vehicle model in the market and the user's actual feelings about the vehicle model, so that the comprehensive performance value obtained by the weighted summation can reflect the advantages of the vehicle model and user satisfaction.

[0024] 3. The present invention selects excellent models with comprehensive performance values ​​greater than or equal to the set performance threshold and models to be improved with comprehensive performance values ​​less than the set performance threshold, and determines the excellent target performance indicators that meet the requirements among the excellent models, thereby selecting models with poor performance and excellent target performance indicators that are significantly different from the excellent models. Further, by means of firmware upgrades or software updates, the models to be improved are improved according to the excellent target performance indicators, thereby accurately improving the poor performance indicators of the models to be improved remotely, and effectively improving the comprehensive performance of the models to be improved.

[0025] 4. After improving the vehicle model, the present invention continues to track the trade-in data and physiological perception data, and re-evaluates the comprehensive performance to ensure successful improvement of the vehicle model performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 It is a flow chart of a vehicle comprehensive performance analysis and improvement method based on multi-dimensional big data analysis provided by an embodiment of the present invention;

[0028] Figure 2 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0030] Example 1

[0031] The embodiment of the present invention provides a vehicle comprehensive performance analysis and improvement method based on multi-dimensional big data analysis, which is mainly applicable to comprehensive performance evaluation of existing vehicle models and performance improvement of vehicle models. The method provided by the embodiment of the present invention can be executed by an electronic device, which can be deployed in the cloud and remotely connected to the vehicle computer.

[0032] Figure 1 is a flow chart of a vehicle comprehensive performance analysis and improvement method based on multi-dimensional big data analysis provided by an embodiment of the present invention. Figure 1 , including:

[0033] S110, collecting travel data and vehicle usage data of multiple users, and determining population characteristics and vehicle usage scenarios corresponding to each vehicle model based on the travel data and vehicle usage data; vehicle usage scenarios include high-frequency scenarios and vehicle purchase-decisive scenarios.

[0034] There are multiple models in this embodiment, each model has multiple vehicles, and multiple vehicles are put on the market and driven by users. The vehicle is equipped with a positioning system and a car system, and the vehicle reports the current time and its own position to the electronic device in the cloud in real time. When a user holds (for example, in the form of purchase or lease) a vehicle, he needs to log in to his personal account on the car system and enter the user data. Optionally, the user data includes but is not limited to: gender, age, occupation and hobbies.

[0035] Based on the user data logged in to the vehicle computers of all vehicles of a certain model, the demographic characteristics of the model are determined; specifically, user profiling can be performed based on user data, and by collecting and analyzing data such as user gender, age, occupation, and hobbies, a description and summary of user characteristics and behavioral habits, namely demographic characteristics, is formed. Crowd characteristics include, for example, age and behavioral preferences (driving habit preferences, preferences for specific areas and activities, etc.).

[0036] Determine the travel time, travel distance, destination and frequency based on the positioning data of all vehicles of a certain model. The frequency can be counted on a weekly basis. Determine high-frequency scenarios based on travel time, travel distance, destination and frequency. First, select high-frequency travel time, travel distance and destination within the statistical period, and then analyze the high-frequency scenarios. High-frequency scenarios include but are not limited to commuting scenarios, shopping scenarios and transportation scenarios. For example, if a user travels during the morning and evening rush hours on every weekday, and the high-frequency destination is an office building or an economic development zone, it is considered a commuting scenario; if the user travels between warehouses, distribution centers or sales points, it is considered a transportation scenario; if the user's high-frequency destination is a shopping mall, it is considered a shopping scenario.

[0037] For different car models, high-frequency scenarios can be the same or different. In order to reflect the differences between car models, this embodiment proposes a car purchase decisive scenario, also known as a car model's characteristic scenario, which greatly affects the user's desire to purchase the car model and becomes a scenario that can produce significant differences from other car models.

[0038] Specifically, differentiated destinations, differentiated travel times, differentiated travel frequencies and differentiated travel distances are determined based on differentiated positioning data between different models. Based on the differentiated destinations, differentiated travel times, differentiated travel frequencies and differentiated travel distances, the decisive scenarios for car purchases are determined, including but not limited to travel scenarios, off-road scenarios and business negotiation scenarios. For example, the difference between model 1 and other models is that the user travels a longer distance and the destination is a scenic spot, then model 1 belongs to the travel scenario; if the difference is that the travel time of model 1 is concentrated in non-morning and evening peaks, and the high-frequency destination is the office area, then it is considered to be a business negotiation scenario; if the difference is that the high-frequency destination of model 1 is a mountainous area, then it is considered to be an off-road scenario.

[0039] After S110, the crowd characteristics and vehicle usage scenarios corresponding to each vehicle model are obtained and stored in the database.

[0040] S120. Select multiple target performance indicators from the full set of performance indicators according to the vehicle usage scenario, and finally obtain the corresponding relationship between the vehicle model, population characteristics, vehicle usage scenario and the target performance indicator.

[0041] The full performance indicators include the various indicator ranges (can also be the value of the indicator) of each performance indicator among all the performance indicators of the vehicle model, such as cruising range of 100 km to 200 km, 200 km to 300 km, suspension height of 100 to 150 mm, and 150 mm to 200 mm.

[0042] One of the innovations of this embodiment is that multiple target performance indicators (i.e., the indicator range of multiple indicators) that support the functions required by the vehicle use scenario are selected from the full set of performance indicators, user functional requirements are divided based on the vehicle use scenario, and the differences in core functional requirements under the vehicle use scenario are analyzed to support subsequent targeted evaluation. For example, the travel scenario is more concerned with the vehicle's endurance performance, so the target performance indicators include endurance, fuel consumption per 100 kilometers, and battery capacity; the commuting scenario requires safe driving on congested roads, so the target performance indicators include vehicle headway and braking response time.

[0043] Optionally, the target performance indicators include: vehicle preparation performance indicators, assisted driving performance indicators, vehicle driving performance indicators, parking performance indicators, parking performance indicators and vehicle departure performance indicators. Vehicle preparation performance indicators include remote unlocking time and seat angle, etc. Assisted driving performance indicators include vehicle headway, braking response time, obstacle avoidance (0 or 1) and in-vehicle NVH, etc. Parking performance indicators include parking time and effective distance. Vehicle driving performance indicators include endurance, suspension height and power. Parking performance indicators include door opening and closing alarm (0 or 1) and parking time. Vehicle departure performance indicators include remote locking response time and whether sentry mode is turned on (0 or 1).

[0044] This embodiment aims to study the characteristics of the vehicle model, that is, it is necessary to obtain multiple target performance indicators corresponding to the vehicle model. A vehicle model has a fixed target performance indicator, that is, a fixed indicator range or value. For example, vehicle model 1 has a range of 200 km to 300 km, a suspension height of 100 mm to 150 mm, a braking response time of 2s to 5s, and a headway between vehicles of 2m to 2.5m. In order to facilitate subsequent calculations, each target performance indicator is mapped to performance quantification values ​​of varying sizes according to the degree of excellence, that is, the performance quantification value mapped by the performance indicator with excellent performance is high; the performance quantification value mapped by the performance indicator with poor performance is low. For example, the higher the range of endurance, the greater the performance quantification value, and the smaller the braking response time, the greater the performance quantification value. For target performance indicators that cannot measure the degree of excellence, they are mapped to the same value. For example, each range of headway between vehicles is mapped to 1.

[0045] After S120, the crowd characteristics, at least one vehicle usage scenario and multiple target performance indicators corresponding to each vehicle model are obtained and stored in the database. The target performance indicators here include a fixed indicator range and a performance quantification value.

[0046] S130: Determine the initial weight of each target performance indicator of any vehicle model according to the type of vehicle use scenario.

[0047] This embodiment requires weighted summation of each target performance indicator to obtain a comprehensive performance evaluation of a vehicle model. The weight represents the importance of the target performance indicator relative to the characteristics of the crowd and the vehicle usage scenario. This embodiment first determines the initial weight of each target performance indicator according to the type of vehicle usage scenario, and then corrects the initial weight according to the characteristics of the crowd to obtain the final weight. In this way, the performance indicators of the vehicle can be evaluated comprehensively based on the vehicle usage scenario and the crowd, which is directional and scientific.

[0048] For example, a car model corresponds to a high-frequency car use scenario: commuting scenario, and a car purchase decision scenario: travel scenario. The initial weight (for example, set to 1) of the target performance indicator that supports the functions required for the high-frequency car use scenario (commuting scenario) is less than the initial weight (for example, set to 2) of the target performance indicator that supports the functions required for the car purchase decision scenario (travel scenario). Because, compared with high-frequency scenarios, the car purchase decision scenario can better reflect the characteristics of the car model, so a higher initial weight is given. If a target performance indicator belongs to both a high-frequency car use scenario and a car purchase decision scenario, the initial weights can be superimposed (for example, set to 1+2=3).

[0049] S140, obtaining the trade-in data of target users corresponding to the population characteristics for each model, and the physiological feeling data of the target users of each model in the vehicle use scenario; modifying the initial weights according to the trade-in data and the physiological feeling data, and obtaining the final weights of the target performance indicators of any model.

[0050] For the convenience of description and distinction, users corresponding to a certain population feature are called target users. The sales data is used to count the percentage of target users who traded in other models for the model. For example, the population feature of Model 1 corresponds to 3,000 users, of which 1,500 users traded in other models for Model 1. Then, the trade-in data for Model 1 is 50%.

[0051] The physiological feeling data of the target user is obtained through sensors placed in the vehicle during driving. In order to reflect the scenario characteristics of the target performance index, this embodiment will only obtain the physiological feeling data of the target user when it detects that the vehicle is in a certain vehicle use scenario A, and then apply the physiological feeling data to the initial weight correction of the target performance index of vehicle use scenario A. The target performance index of vehicle use scenario A is the target performance index that supports the functions required by vehicle use scenario A.

[0052] Specifically, when the navigation detects that the user's destination is a mountainous area and the distance is far, the vehicle is in an off-road scene, and the corresponding target performance indicators include suspension height and 100 km / h acceleration. During the off-road period of the vehicle, the facial image of the target user is collected through the camera and the user's emotions are identified from it, and the target user's blood pressure, heart rate and other physiological data are collected through the vital signs monitoring system in the car. The user's emotions and physiological data are quantified into physiological feeling data. In actual operation, the corresponding relationship between user emotions, physiological data and physiological feeling data can be established. The more positive and active the user's emotions are, the closer the physiological data is to the health data, and the higher the physiological feeling data is. For each vehicle model in each vehicle use scenario, the physiological feeling data of the target user is summarized, and these summarized physiological feeling data are averaged and normalized to obtain a value within 0~1.

[0053] In summary, we obtained the target users' replacement data for each model, as well as the target users' physiological feeling data for different usage scenarios of each model.

[0054] Then, the adjustment coefficient is determined based on the trade-in data of each model and the physiological perception data in each car-use scenario. For each model, it has different car-use scenarios, and each car-use scenario corresponds to different target performance indicators and initial weights. This step aims to adjust these initial weights separately. Specifically, for a model, the trade-in data (essentially the proportion of the number of users) and the physiological perception data in a car-use scenario (a value between 0 and 1) are added to obtain the adjustment coefficient of the target performance indicator of the model for the car-use scenario. If a target performance indicator belongs to more than two car-use scenarios at the same time, the adjustment coefficients obtained in more than two car-use scenarios are added. In this way, each target performance indicator of the model has an adjustment coefficient. Note that the calculation of the adjustment coefficient here does not need to consider the influence of the type of car-use scenario.

[0055] Then, the initial weight is adjusted according to the adjustment coefficient to obtain the final weight of each target performance indicator. Specifically, the initial weight of the same target performance indicator is multiplied by the adjustment coefficient to obtain the final weight of each target performance indicator.

[0056] S150. Perform weighted summation on the performance quantization values ​​of the target performance indicators according to the final weights to obtain the comprehensive performance values ​​of the vehicle models corresponding to the population characteristics and vehicle usage scenarios.

[0057] The performance quantification value of the target performance indicator is obtained by mapping each target performance indicator to values ​​of different sizes according to their degree of excellence. For details, please refer to the above record.

[0058] After S150, the crowd characteristics, at least one vehicle usage scenario, multiple target performance indicators, the final weight of each target performance indicator, and the comprehensive performance value corresponding to each vehicle model are obtained and stored in the database. At this point, the comprehensive performance evaluation of the vehicle model for a specific crowd and a specific vehicle usage scenario is completed.

[0059] S160. For the same population characteristics, select excellent models whose comprehensive performance values ​​are greater than or equal to the set performance threshold and models to be improved whose comprehensive performance values ​​are less than the set performance threshold, and determine excellent target performance indicators that meet the requirements among the excellent models.

[0060] The performance comparison of different models is meaningful only under the same population characteristics. The performance threshold can be set by yourself. For a population characteristic, if the comprehensive performance value of model 1 is greater than or equal to the set performance threshold, then model 1 is an excellent model under the population characteristic; conversely, if the comprehensive performance value of model 2 is less than the set performance threshold, then model 2 is a model to be improved under the population characteristic.

[0061] The purpose of this embodiment is to improve the model to be improved by benchmarking any excellent model for the same population characteristics. This step selects at least one excellent target performance indicator whose final weight is greater than the set weight threshold from all target performance indicators of any excellent model. Among them, the set weight threshold can be set automatically. Since the final weight reflects the performance advantage of the model and the user's satisfaction, the indicator with a higher final weight is the excellent target performance indicator that the model to be improved needs to benchmark.

[0062] S170. Improve the vehicle model to be improved according to the excellent target performance indicator by means of firmware upgrade or software update.

[0063] In one embodiment, the excellent target performance indicator of vehicle type 1 is a headway between vehicles of 2m~2.5m. By improving the auxiliary driving system software of vehicle type 2, the headway between vehicles is made 2m~2.5m.

[0064] In another embodiment, the excellent target performance index of vehicle model 1 is a suspension height of 100 mm to 150 mm, and the suspension adjustment system of vehicle model 2 to be improved is upgraded with firmware to adjust the suspension height to 100 mm to 150 mm. Note that the suspension height of vehicle model 2 to be improved is adjustable by default.

[0065] Of course, there are some target performance indicators that cannot be adjusted through firmware upgrades or software updates, such as cruising range and braking response time. These target performance indicators that cannot be adjusted through firmware upgrades or software updates can be provided to vehicle manufacturers so that the vehicle manufacturers can improve the models to be improved.

[0066] S180: Obtaining the target user's trade-in data for the vehicle model to be improved, and the target user's physiological feeling data in the vehicle usage scenario.

[0067] After the improved model is improved in S170, the target users' trade-in data for the improved model is continuously collected, that is, the proportion of users who traded in other models for the improved model among the target users with the same population characteristics in S160. The physiological feeling data of the target users in the vehicle use scenario is collected.

[0068] S190. Recalculate the final weights of the target performance indicators based on the trade-in data and physiological perception data obtained in S180, perform weighted summation on the target performance indicators based on the final weights, and obtain the comprehensive performance value of the vehicle model to be improved corresponding to the population characteristics and vehicle usage scenarios.

[0069] Please refer to the records of S140 and S150 for details, which will not be repeated here.

[0070] S200: Determine whether the comprehensive performance value of the vehicle model to be improved is greater than or equal to the set performance threshold. If yes, execute S201: the improvement is successful and the operation ends; if no, execute S202: update the excellent target performance index and return to S170.

[0071] Among them, updating the excellent target performance indicators means that, in addition to the excellent target performance indicators selected by S160, other excellent target performance indicators whose final weights are greater than the set weight threshold are selected from all the target performance indicators of any excellent vehicle model; thereby improving the vehicle model to be improved from the perspective of other target performance indicators.

[0072] The embodiments of the present invention have the following technical effects:

[0073] 1. The present invention divides different vehicle usage scenarios and population characteristics, selects target performance indicators that have an impact on vehicle usage scenarios, and evaluates vehicle models based on the target performance indicators, thereby realizing a vehicle model performance evaluation system oriented to vehicle usage scenarios and population characteristics.

[0074] 2. The present invention determines the initial weight of each target performance indicator according to the type of vehicle use scenario, and corrects the initial weight according to the trade-in data and the physiological perception data to obtain the final weight, and uses the final weight to perform weighted summation on the target performance indicators, thereby correcting the weight of the target performance indicators according to the performance of the vehicle model and the user's actual perception of the vehicle model, so that the comprehensive performance value obtained by the weighted summation can reflect the performance of the vehicle model and user satisfaction.

[0075] 3. The present invention selects excellent models with comprehensive performance values ​​greater than or equal to the set performance threshold and models to be improved with comprehensive performance values ​​less than the set performance threshold, and determines the excellent target performance indicators that meet the requirements among the excellent models, thereby selecting models with poor performance and excellent target performance indicators that are significantly different from the excellent models. Further, by means of firmware upgrades or software updates, the models to be improved are improved according to the excellent target performance indicators, thereby accurately improving the poor performance indicators of the models to be improved remotely, and effectively improving the comprehensive performance of the models to be improved.

[0076] 4. After improving the vehicle model, the present invention continues to track the trade-in data and physiological perception data, and re-evaluates the comprehensive performance to ensure successful improvement of the vehicle model performance.

[0077] Example 2

[0078] Figure 2 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, the electronic device 400 includes one or more processors 401 and a memory 402 .

[0079] The processor 401 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0080] The memory 402 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement the vehicle comprehensive performance analysis and improvement method based on multi-dimensional big data analysis and / or other desired functions of any embodiment of the present invention described above. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0081] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0082] Of course, to simplify, Figure 2 Only some of the components related to the present invention in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 400 may also include any other appropriate components.

[0083] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis provided by any embodiment of the present invention.

[0084] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0085] In addition, an embodiment of the present invention may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis provided by any embodiment of the present invention.

[0086] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0087] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0088] It should also be noted that the orientations or positional relationships indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle comprehensive performance analysis and improvement method based on multi-dimensional big data analysis, characterized in that: include: S110, collecting travel data and vehicle usage data of multiple users, and determining population characteristics and vehicle usage scenarios corresponding to each vehicle model according to the travel data and vehicle usage data; the vehicle usage scenarios include high-frequency scenarios and vehicle purchase-decisive scenarios; S120, selecting multiple target performance indicators from the full set of performance indicators according to the vehicle usage scenario, and finally obtaining a correspondence between the vehicle model, population characteristics, vehicle usage scenario, and the target performance indicator; S130, determining the initial weight of each target performance indicator of any vehicle model according to the type of the vehicle usage scenario; S140, obtaining trade-in data of target users corresponding to the population characteristics for each vehicle model, and physiological feeling data of the target users for each vehicle model in the vehicle use scenario; The initial weights are modified according to the trade-in data and the physiological feeling data to obtain the final weights of the target performance indicators of any vehicle model; S150, performing weighted summation on the performance quantization values ​​of the target performance indicators according to the final weights to obtain a comprehensive performance value of the vehicle model corresponding to the population characteristics and vehicle usage scenarios; S160. For the same population characteristics, select excellent models whose comprehensive performance values ​​are greater than or equal to a set performance threshold and models to be improved whose comprehensive performance values ​​are less than the set performance threshold, and determine excellent target performance indicators that meet the requirements among the excellent models; S170, improving the vehicle model to be improved according to the excellent target performance indicator by means of firmware upgrade or software update; S180, obtaining the target user's trade-in data for the vehicle model to be improved, and the target user's physiological feeling data in the vehicle usage scenario; S190, recalculating the final weights of the target performance indicators according to the trade-in data and the physiological feeling data obtained in S180, performing weighted summation on the target performance indicators according to the final weights, and obtaining the comprehensive performance value of the vehicle model to be improved corresponding to the population characteristics and the vehicle usage scenario; S200: If the comprehensive performance value of the vehicle model to be improved is greater than or equal to the set performance threshold, the improvement is successful; If the comprehensive performance value of the vehicle model to be improved is less than the set performance threshold, the excellent target performance index is updated and the process returns to S170.

2. The method according to claim 1, characterized in that Determine the crowd characteristics and vehicle usage scenarios corresponding to each vehicle type based on the travel data and vehicle usage data, including: Determine the population characteristics of a vehicle model based on user data logged in on the vehicle computers of all vehicles of the vehicle model; Determine travel time, travel distance, destination and frequency based on the positioning data of all vehicles of a vehicle model, and determine high-frequency scenarios based on the travel time, travel distance, destination and frequency; Differentiated destinations, differentiated travel times, differentiated travel frequencies and differentiated travel distances are determined based on differentiated positioning data between different models, and the decisive scenario for car purchase is determined based on the differentiated destinations, differentiated travel times, differentiated travel frequencies and differentiated travel distances.

3. The method according to claim 1, characterized in that In S140, the physiological feeling data of the target user is acquired through sensors arranged in the vehicle during driving.

4. The method according to claim 3, characterized in that The initial weights are modified according to the trade-in data and the physiological feeling data to obtain the final weights of the target performance indicators, including: Determining an adjustment coefficient based on the trade-in data of each vehicle model and the physiological feeling data in each vehicle use scenario; The initial weight is adjusted according to the adjustment coefficient to obtain the final weight of each target performance indicator.

5. The method according to claim 1, characterized in that: In S160, the excellent target performance indicators that meet the requirements of the excellent vehicle models are determined, including: From all the target performance indicators of the excellent vehicle models, select the excellent target performance indicators whose final weights are greater than the set weight threshold.

6. The method according to any one of claims 1 to 5, characterized in that: The target performance indicators include: pre-vehicle preparation performance indicators, assisted driving performance indicators, vehicle driving performance indicators, parking performance indicators, parking performance indicators and vehicle leaving performance indicators.

7. The method according to any one of claims 1 to 5, characterized in that: The high-frequency scenarios include commuting scenarios, shopping scenarios, and transportation scenarios; the car-buying-decisive scenarios include travel scenarios, off-road scenarios, and business negotiation scenarios.

8. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The processor is used to execute the steps of the vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis as described in any one of claims 1 to 7 by calling the program or instructions stored in the memory.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, which enable the computer to execute the steps of the vehicle model comprehensive performance analysis and improvement method based on multi-dimensional big data analysis as described in any one of claims 1 to 7.

Images