Agile vehicle model recommendation method and system based on digital twin model

Abstract

This application discloses a method and system for agile vehicle model recommendation based on a digital twin model, belonging to the field of intelligent data processing technology. The method for agile vehicle model recommendation based on a digital twin model includes: obtaining real-time passenger vehicle data and real-time user review data, and constructing a passenger vehicle model twin model library based on the real-time passenger vehicle data and real-time user review data; obtaining real-time user demand data for vehicle model parameters and real-time user importance rating data for vehicle model attributes, and constructing a user demand twin model based on the real-time user demand data for vehicle model parameters and real-time user importance rating data for vehicle model attributes; and obtaining vehicle model recommendation results based on a two-stage recommendation algorithm, a passenger vehicle model twin model, and a user demand twin model. This method can effectively improve the real-time, accuracy, and personalization of vehicle model recommendations, and more effectively and accurately recommend passenger vehicle models that meet consumers' needs.

Description

Technical Field

[0001] The present invention relates to the field of intelligent data processing technology, and in particular to a method and system for agile vehicle model recommendation based on a digital twin model. Background Art

[0002] With the continuous development of the new energy passenger vehicle market, consumers are faced with an increasingly diverse range of vehicle options, but they also face the challenge of selecting the most suitable model from this vast array. Traditional car recommendation algorithms primarily generate recommendations through static similarity calculations. However, these algorithms rely on basic user information (such as vehicle model, price, and powertrain), failing to fully consider the individual needs of users in different areas (such as space, appearance, and interior), as well as the multi-layered changes in user needs over time. This results in low real-time, low accuracy, and low user satisfaction. These recommendations also fail to reflect changes in new car information or user reviews, leading to frequent user dissatisfaction. Summary of the Invention

[0003] The purpose of this application is to overcome the shortcomings of the existing technology and provide an agile vehicle model recommendation method and system based on a digital twin model, combining the multi-dimensional data of new energy passenger vehicles with the multi-level characteristics of user needs to achieve more personalized, accurate, and real-time updated recommendations.

[0004] In a first aspect, the present application provides a method for agile vehicle model recommendation based on a digital twin model, comprising the following steps:

[0005] Acquire real-time passenger vehicle data and real-time user review data, and construct a passenger vehicle model twin model library based on the real-time passenger vehicle data and the real-time user review data, wherein the passenger vehicle model twin model library is dynamically updated based on new passenger vehicle data and new user review data;

[0006] Acquire real-time user demand data for vehicle model parameters and real-time user importance rating data for vehicle model attributes, and build a user demand twin model based on the real-time user demand data for vehicle model parameters and real-time user importance rating data for vehicle model attributes;

[0007] The vehicle model recommendation results are obtained based on the two-stage recommendation algorithm, the passenger vehicle model twin model and the user demand twin model.

[0008] Optionally, a passenger vehicle model twin model library is constructed based on the real-time passenger vehicle data and the real-time user review data, and the passenger vehicle model twin model library is dynamically updated based on new passenger vehicle data and new user review data, including:

[0009] Performing structured processing on the real-time passenger vehicle data to obtain parameter characteristic data;

[0010] Obtaining the average sentiment of each vehicle type attribute based on the real-time user review data as word-of-mouth feature data;

[0011] vectorizing the parameter feature data and the word-of-mouth feature data, and performing vector fusion on the vectorized parameter feature data and the word-of-mouth feature data to obtain the passenger vehicle model twin model;

[0012] The passenger vehicle model twin models of all vehicle model attributes are stored in a database to obtain a passenger vehicle model twin model library, which is dynamically updated according to new passenger vehicle data and new user review data.

[0013] Optionally, performing structured processing on the real-time passenger car data to obtain parameter characteristic data includes: performing numerical standardization and category coding on the real-time passenger car data to obtain the parameter characteristic data.

[0014] Optionally, a user demand twin model is constructed based on the user's real-time demand data for vehicle model parameters and the user's real-time importance rating data for vehicle model attributes, including:

[0015] Obtaining a vehicle model parameter demand feature vector based on the user's real-time demand data for vehicle model parameters;

[0016] Normalizing the user's real-time importance rating data for vehicle model attributes to obtain a vehicle model attribute demand weight vector;

[0017] The vehicle model parameter requirement feature vector and the vehicle model attribute requirement weight vector are fused to obtain the user demand twin model.

[0018] Optionally, the formula for normalizing the user's importance score data for vehicle model attributes is:

[0019]

[0020] in, is the demand weight of the i-th vehicle model attribute, n is the total number of vehicle model attributes, Importance scoring data for the i-th vehicle model attribute.

[0021] Optionally, obtaining a vehicle model recommendation result based on the two-stage recommendation algorithm, the passenger vehicle model twin model library, and the user demand twin model includes:

[0022] Screening the passenger vehicle model twin model library in sequence according to a preset order to obtain candidate vehicle models;

[0023] Obtaining a vehicle attribute demand weight vector of the candidate vehicle model based on the user demand twin model;

[0024] Obtaining a reputation feature vector of a candidate vehicle model based on the passenger vehicle model twin model;

[0025] A weighted cosine similarity is calculated for the vehicle attribute demand weight vector and the word-of-mouth feature vector to obtain a weighted cosine similarity between the two; the candidate vehicle models are arranged in descending order according to the weighted cosine similarity, and the top several candidate vehicle models are selected as the vehicle model recommendation results.

[0026] Optionally, the preset order includes: car purchase budget, cruising range, vehicle model level, power type and charging time.

[0027] Optionally, in the process of screening the passenger vehicle model twin models in sequence in a preset order to obtain candidate models, if the number of candidate models is lower than a preset threshold, the restriction conditions are canceled in reverse order or the numerical condition threshold is relaxed according to a preset ratio until the number of candidate models reaches the preset threshold.

[0028] Optionally, a weighted cosine similarity calculation is performed on the vehicle attribute demand weight vector and the word-of-mouth feature vector based on the following formula to obtain a weighted cosine similarity between the two:

[0029]

[0030] Wherein, Similarity is the weighted cosine similarity between the vehicle attribute demand weight vector and the word-of-mouth feature vector; is the demand weight of the i-th vehicle model attribute, is the average sentiment value of the i-th vehicle model attribute, and n is the total number of vehicle model attributes.

[0031] Secondly, this application also provides an agile vehicle model recommendation system based on a digital twin model, including:

[0032] The data collection module is used to obtain real-time passenger vehicle data, real-time user review data, real-time user demand data for vehicle model parameters, and real-time user importance rating data for vehicle model attributes;

[0033] A passenger vehicle twin model construction module, configured to construct a passenger vehicle twin model based on the real-time passenger vehicle data and the real-time user review data, and store the passenger vehicle twin model in a database;

[0034] A user demand twin model construction module is used to construct a user demand twin model based on the user's demand data for vehicle model parameters and the user's importance rating data for vehicle model attributes;

[0035] The recommendation result generation module is used to obtain vehicle model recommendation results based on the two-stage recommendation algorithm, the passenger vehicle model twin model and the user demand twin model.

[0036] This application provides an agile vehicle model recommendation method and system based on a digital twin model. By collecting real-time passenger car data, real-time user review data, and real-time user demand data on vehicle model parameters, a passenger vehicle model twin model and a real-time user demand twin model are constructed. The vehicle model recommendation results are obtained based on a two-stage recommendation algorithm, a passenger vehicle model twin model, and a user demand twin model. This can reflect vehicle model characteristics and user needs in real time and accurately, improving the accuracy and timeliness of recommendations; the screening and adjustment mechanism can ensure the diversity of recommendation results, meet the personalized needs of different users, and improve users' car purchasing experience and decision-making efficiency.

[0037] In order to make the above features and advantages of the present invention more clearly understood, embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 and Figure 2 This is a flowchart of an agile vehicle model recommendation method based on a digital twin model provided in one embodiment of the present application.

[0040] Figure 3 This is a flowchart of step S10 in the agile vehicle model recommendation method based on a digital twin model provided in one embodiment of the present application.

[0041] Figure 4 This is a flowchart of step S20 in the agile vehicle model recommendation method based on a digital twin model provided in one embodiment of the present application.

[0042] Figure 5 This is a flowchart of step S30 in the agile vehicle model recommendation method based on a digital twin model provided in one embodiment of the present application.

[0043] Figure 6 This is a structural diagram of an agile vehicle model recommendation system based on a digital twin model provided in another embodiment of the present application. DETAILED DESCRIPTION

[0044] To make the purpose and technical solutions of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below in conjunction with the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] In one embodiment, see Figure 1 and Figure 2 The present application provides an agile vehicle model recommendation method based on a digital twin model. The agile vehicle model recommendation method based on a digital twin model may include the following steps: S10~S30.

[0046] S10: Acquire real-time passenger car data and real-time user review data, and construct a passenger car model twin model library based on the real-time passenger car data and the real-time user review data. The passenger car model twin model library is dynamically updated based on new passenger car data and new user review data.

[0047] S20: Obtain user demand data on vehicle model parameters and user real-time importance rating data on vehicle model attributes, and build a user demand twin model based on the user demand data on vehicle model parameters and user real-time importance rating data on vehicle model attributes.

[0048] S30: Obtain vehicle model recommendation results based on the two-stage recommendation algorithm, the passenger vehicle model twin model library and the user demand twin model.

[0049] In the digital twin model-based agile vehicle model recommendation method of this application, by obtaining real-time passenger vehicle data and real-time user review data, it is possible to accurately present the actual conditions of the vehicle model, such as various parameters and configurations, so that the basic information for recommendation is timely; by constructing a passenger vehicle model twin model and a user demand twin model, it is possible to accurately fit the user's personalized needs and avoid the blindness of general recommendations; through a two-stage recommendation algorithm, it is possible to highlight key factors and make the calculated similarity more scientific and reasonable. This application can accurately capture the actual situation of the vehicle model and the personalized needs of the user in real time, improve the fit between the recommendation results and the user's expectations, provide users with more targeted and timely vehicle model recommendations, effectively help users quickly screen out their favorite models, and improve the efficiency of car purchase decisions.

[0050] As an example, the vehicle model agile recommendation method based on the digital twin model of this application can be used to recommend vehicle models such as gasoline vehicles, electric vehicles, and new energy vehicles. Taking new energy vehicles as an example, steps S10 to S30 are introduced in detail below.

[0051] In step S10, refer to Figure 1In step S10, real-time passenger car data and real-time user review data are obtained, and a passenger car model twin model library is constructed based on the real-time passenger car data and the real-time user review data. The passenger car model twin model library is dynamically updated based on new passenger car data and new user review data.

[0052] As an example, see Figure 2 In step S10, web crawler technology can be used to obtain feature data (i.e., real-time passenger car data and real-time user review data) uploaded in real time by the physical entity of the passenger car (i.e., the passenger car); a passenger car model twin model is constructed based on the real-time passenger car data and the real-time user review data to form a passenger car model twin model library, and the twin model is iterated in real time.

[0053] As an example, in step S10, the construction of a passenger vehicle model twin model based on the real-time passenger vehicle data and the real-time user review data may include: performing structured processing on the real-time passenger vehicle data to obtain parameter feature data; obtaining the sentiment average of each vehicle model attribute based on the real-time user review data as word-of-mouth feature data; vectorizing the parameter feature data and the word-of-mouth feature data, and performing vector fusion on the vectorized parameter feature data and the word-of-mouth feature data to obtain the passenger vehicle model twin model; storing the passenger vehicle model twin models of all vehicle model attributes in a database to obtain a passenger vehicle model twin model library, and the passenger vehicle model twin model library is dynamically updated according to new passenger vehicle data and new user review data.

[0054] For details, please combine Figures 1 to 2 See Figure 3 , step S10 may include the following steps: S101~S105.

[0055] S101: Use web crawler technology to obtain real-time passenger car data and real-time user review data.

[0056] S102: Performing structured processing on the real-time passenger car data to obtain parameter characteristic data.

[0057] S103: Using a natural language algorithm to analyze the real-time user review data according to vehicle type attributes, to obtain a sentiment value of each vehicle type attribute.

[0058] S104: averaging the sentiment values ​​of the attributes of each vehicle model to obtain the average sentiment value of each vehicle model attribute as word-of-mouth feature data.

[0059] S105: Vectorize the parameter feature data and the word-of-mouth feature data, and perform vector fusion on the vectorized parameter feature data and the word-of-mouth feature data to obtain the passenger vehicle model twin model; in this step, perform multi-dimensional vector fusion on the parameter feature data and the word-of-mouth feature data to obtain the passenger vehicle model twin model.

[0060] As an example, in step S101, real-time passenger vehicle parameter data and real-time user review data can be obtained through API interfaces and web crawler technology. Specifically, data sources such as automotive vertical media, automobile company websites, and social media platforms can be searched to identify their open API interfaces. Web crawler technology can then be used to capture real-time new energy passenger vehicle data from automotive vertical media, automobile company websites, and social media platforms, and real-time user review data can be captured from social media platforms.

[0061] As an example, the user review data may include but is not limited to: vehicle model level, power type, cruising range, charging time and suggested price, etc.

[0062] As an example, in step S102, since the captured real-time passenger car data may contain a large amount of noise and non-standard information, the real-time passenger car data needs to be structured to eliminate dimensional differences. The real-time passenger car data can be parsed and converted into a structured format.

[0063] As an example, the structured processing of the real-time passenger vehicle data to obtain parameter characteristic data includes: numerical standardization and category coding of the real-time passenger vehicle data to obtain the parameter characteristic data; that is, the structured processing may include: numerical standardization and category coding. Specifically, numerical data can be standardized, for example, charging time can be standardized to hours; categorical data can be coded, for example, vehicle model level can be mapped to discrete labels.

[0064] As an example, in step S103, a pre-trained natural language algorithm is used to perform field classification and sentiment analysis on each real-time user comment data. All real-time user comment data of a single vehicle model are classified according to vehicle model attributes, and sentiment analysis is performed on each vehicle model attribute to obtain multiple sentiment values ​​for each field. The sentiment values ​​are set in the range of (0, 1) to reflect the user's satisfaction with a certain field.

[0065] As an example, the vehicle model attributes may include but are not limited to: space (i.e., interior space), battery life, appearance, interior, cost-effectiveness, driving quality, and in-vehicle intelligent system.

[0066] As an example, in step S104, the mean of the sentiment value of each vehicle type attribute is calculated respectively to obtain the average sentiment score of each vehicle type attribute as the comprehensive score of the corresponding field, that is, word-of-mouth feature data.

[0067] As an example, in step S105, the parameter feature data and the word-of-mouth feature data are written into vector form, and then vector splicing and fusion are performed to obtain the passenger vehicle model twin model.

[0068] As an example, the twin models of passenger car models with all vehicle attributes are stored in a database to obtain a twin model library of passenger car models.

[0069] As an example, the passenger car model twin model library can adopt a distributed database, the passenger car model twin model library can be dynamically updated, the passenger car model twin model library supports high-concurrency reading and writing and real-time updating, and can be dynamically updated according to new passenger car data and new user review data.

[0070] As an example, it can be set to a timed scanning mode to scan the data source regularly and detect changes in the data source. When a new model is added, the passenger car model twin model of the model is initialized; when a model is delisted, the passenger car model twin model of the corresponding model is removed; when the model parameters or comment data are updated, local recalculation is triggered to ensure that the passenger car model twin model library is synchronized with the market status.

[0071] For example, data sources such as automotive vertical media, automaker websites, and social media platforms are regularly scanned to detect parameter changes or new comments. If an update is detected, the passenger vehicle twin model of the affected model is re-determined and the old version of the passenger vehicle twin model is replaced.

[0072] As an example, for a new car model, if the initial review data is insufficient, the missing fields can be filled with the average of historical reviews of models of the same brand or price range.

[0073] In step S20, refer to Figure 1 In step S20, the real-time demand data of users for vehicle model parameters and the real-time importance rating data of users for vehicle model attributes are obtained, and a user demand twin model is constructed based on the real-time demand data of users for vehicle model parameters and the real-time importance rating data of users for vehicle model attributes.

[0074] As an example, see Figure 2 In step S20, a questionnaire can be formed based on the user's real-time demand feedback, and a user demand twin model can be constructed based on the questionnaire.

[0075] As an example, in step S20, constructing a user demand twin model based on the user's real-time demand data for vehicle model parameters and the user's importance rating data for vehicle model attributes may include: obtaining a vehicle model parameter demand feature vector based on the user's real-time demand data for vehicle model parameters; normalizing the user's real-time importance rating data for vehicle model attributes to obtain a vehicle model attribute demand weight vector; and fusing the vehicle model parameter demand feature vector with the vehicle model attribute demand weight vector to obtain the user demand twin model.

[0076] As an example, combine Figure 1 and Figure 2 See Figure 4 , step S20 may include the following steps: S201~S204.

[0077] S201: Obtaining real-time demand data of users for vehicle model parameters and real-time importance rating data of users for vehicle model attributes through real-time questionnaires.

[0078] S202: Processing (eg, vectorization) the user's real-time demand data for vehicle model parameters to obtain a vehicle model parameter demand feature vector.

[0079] S203: Processing (eg, normalizing) the user's real-time importance rating data for vehicle model attributes to obtain a vehicle model attribute requirement weight vector.

[0080] S204: Fusing the vehicle model parameter requirement feature vector with the vehicle model attribute requirement weight vector (for example, multi-dimensional vector fusion) to obtain the user requirement twin model.

[0081] As an example, in step S201, a user fills out a questionnaire through an interactive interface. The user may enter vehicle parameter requirements and vehicle attribute importance ratings. The vehicle parameter requirements may include, but are not limited to, vehicle class preferences, powertrain type preferences, minimum range, maximum charging time, and vehicle purchase budget. The vehicle attribute importance ratings may include, but are not limited to, the importance of space, battery life, exterior design, interior design, cost-effectiveness, driving quality, and in-vehicle intelligent systems, with ratings assigned on a scale of 0-10.

[0082] As an example, in step S202, the data in the questionnaire is sorted and parsed. Multiple-choice parameters can be converted into one-hot encoding, and numerical parameters can be normalized. The sorted and parsed user demand data for vehicle model parameters is written into vector form to obtain a vehicle model parameter demand feature vector.

[0083] As an example, in step S203, the sorted and analyzed user importance rating data for vehicle model attributes is normalized, the weights of each field are calculated, and the weights are written in vector form to obtain the vehicle model attribute demand weight vector.

[0084] As an example, the formula for normalizing the user's importance score data for vehicle model attributes is:

[0085]

[0086] in, is the demand weight of the i-th vehicle model attribute, n is the total number of vehicle model attributes, is the importance score data of the i-th vehicle model attribute; in this embodiment, n=7. Through normalization processing, it can be ensured that the sum of the weights of each field is 1.

[0087] As an example, in step S204, the vehicle model parameter requirement feature vector is concatenated with the vehicle model attribute requirement weight vector to obtain a user demand twin model. The user demand twin model integrates the user's requirements for specific vehicle model parameters and the importance weight information of different vehicle model attributes, allowing the user demand twin model to more comprehensively reflect the user's demand characteristics.

[0088] In step S30, refer to Figure 1 In step S30, a vehicle model recommendation result is obtained based on the two-stage recommendation algorithm, the passenger vehicle model twin model library and the user demand twin model.

[0089] As an example, see Figure 5 , step S30 may include the following steps: S301~S304.

[0090] S301: Screening the passenger vehicle model twin model library in sequence according to a preset order to obtain candidate vehicle models.

[0091] S302: Obtaining a vehicle attribute demand weight vector of the candidate vehicle model based on the user demand twin model.

[0092] S303: Obtaining a reputation feature vector of a candidate vehicle model based on the passenger vehicle model twin model.

[0093] S304: Calculate the weighted cosine similarity of the vehicle attribute demand weight vector and the word-of-mouth feature vector to obtain the weighted cosine similarity between the two; sort the candidate vehicle models in descending order according to the weighted cosine similarity, and select the top several candidate vehicle models as the vehicle model recommendation results.

[0094] As an example, in step S301, the passenger vehicle twin model library is screened in sequence according to a preset order. The preset order may be, but is not limited to, vehicle purchase budget, cruising range, vehicle model level, power type, and charging time, and the priority of the preset order decreases in sequence.

[0095] As an example, in the process of screening the passenger vehicle model twin model library in a preset order to obtain candidate models, if the number of candidate models is lower than a preset threshold, the restriction conditions are canceled in reverse order or the numerical condition threshold is relaxed according to a preset ratio until the number of candidate models reaches the preset threshold.

[0096] Specifically, after each step of screening is completed, the number of candidate models is checked in real time. If the number of candidate models is lower than the threshold x , the dynamic relaxation mechanism is triggered until the number of candidate models obtained is greater than or equal to the threshold x .

[0097] Specifically, the dynamic relaxation mechanism may include: relaxing the screening conditions in reverse priority order, or relaxing the screening conditions of numerical parameters in a preset ratio.

[0098] As an example, the vehicle type levels may include: small car, compact car, mid-size car, large car, etc.

[0099] As an example, the power type may include: fuel vehicle, pure electric vehicle, plug-in hybrid vehicle, etc.

[0100] For example, for numerical parameters, the filter conditions can be expanded according to a preset ratio. For example, for a car purchase budget, the upper limit of the budget can be increased by 10%. For category parameters, similar categories can be merged. For example, "SUV" and "crossover SUV" can be merged into the same category until the candidate model threshold is met. x Require.

[0101] In one example, the number threshold of the candidate models xThe number of vehicles can be set to 10. First, based on the user's set vehicle purchase budget, the passenger vehicle twin model library is filtered to select models within this price range. These models are then filtered based on the user's desired range. Next, the user's preferred vehicle class is filtered based on the previously filtered models, selecting those that meet that class. Finally, the models are filtered again based on the user's desired power type, retaining those that meet the required power type. Finally, for models involving charging, the user's acceptable charging time range is used to filter out models with acceptable charging times. After each filtering step, the number of candidate models is checked to see if it is less than 10. If so, the user is required to relax the current filtering criteria. For non-numeric filtering criteria, the constraints of the current filtering step are removed one by one. Specifically, after the vehicle purchase budget is filtered, 60 candidate models are obtained. Next, after the range is filtered, 30 candidates remain. After the vehicle class is filtered, 12 candidates remain. Finally, after the power type is filtered, 8 candidates remain, leaving less than 10 candidates. Since the power type is the current screening step and is a non-numerical condition, the screening restrictions on the power type are relaxed. Originally, the screening conditions only included pure electric vehicles, but after the restrictions were relaxed, fuel vehicles and hybrid vehicles can be included. After re-screening, it was found that 15 candidate models remained, which met the threshold requirements, and the screening process ended.

[0102] As an example, in step S302, the model attribute demand weight vector of the candidate model is extracted from the user demand twin model. ,in, They correspond to the normalized weight values ​​of space, battery life, appearance, interior, cost performance, driving quality and vehicle intelligent system, namely The demand weights correspond to seven vehicle attributes: space, battery life, appearance, interior, cost-effectiveness, driving quality and in-vehicle intelligent system.

[0103] As an example, in step S303, the word-of-mouth feature vector of the candidate model is extracted from the passenger car twin model. ,in The corresponding rating values ​​are space, battery life, appearance, interior, cost performance, driving quality and vehicle intelligent system, that is, the word-of-mouth rating value, that is, These correspond to the average emotions of seven vehicle attributes: space, battery life, appearance, interior, cost-effectiveness, driving quality and in-vehicle intelligent system.

[0104] As an example, in step S304, the weighted cosine similarity calculation is performed on the vehicle attribute demand weight vector and the word-of-mouth feature vector based on the following formula to obtain the weighted cosine similarity between the two, that is, the vehicle attribute demand weight vector of the candidate vehicle model is calculated. Word of mouth feature vector The weighted cosine similarity of Similarity is expressed as:

[0105]

[0106] Wherein, Similarity is the weighted cosine similarity between the vehicle attribute demand weight vector and the word-of-mouth feature vector; is the demand weight of the i-th vehicle model attribute, is the average sentiment value (i.e., word-of-mouth rating) of the i-th vehicle model attribute, and n is the total number of vehicle model attributes. In this embodiment, n=7.

[0107] Furthermore, the candidate models are sorted in descending order of similarity, and the top several candidate models are selected as the model recommendation results. Specifically, the top 10 candidate models can be selected as the model recommendation results and a recommendation list can be output.

[0108] For example, if there are less than 10 candidate models, all models will be output and their similarity rankings will be marked.

[0109] In this application's agile vehicle model recommendation method based on a digital twin model, real-time passenger vehicle data and user review data are acquired through web crawlers and API interfaces to construct a passenger vehicle model twin model library. This library comprehensively presents the actual status and reputation of vehicle models, providing a realistic and dynamic vehicle model portrait. Real-time questionnaires are used to collect user demand data on vehicle parameters and the importance ratings of vehicle attributes, constructing a user demand twin model that accurately meets users' personalized needs. Vehicle models are filtered according to a preset order, and similarity is calculated using a multi-level weighted cosine similarity matching algorithm (i.e., the formula for calculating weighted cosine similarity in the above embodiment). This method integrates multi-dimensional information to ensure the scientific nature of the recommendation results. A dynamic relaxation mechanism ensures that a sufficient number of candidate models are screened. This method can provide users with highly accurate, personalized, and timely vehicle model recommendations, significantly improving the efficiency of their car purchase decisions.

[0110] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The order of execution of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or at least a portion of the sub-steps or stages of other steps.

[0111] In another embodiment, see Figure 6 The present application also provides an agile vehicle model recommendation system based on a digital twin model, which may include: a data acquisition module 1, a passenger vehicle model twin model construction module 2, a user demand twin model construction module 3, and a recommendation result generation module 4. The data acquisition module 1 is used to obtain real-time passenger vehicle data, real-time user review data, real-time user demand data for vehicle model parameters, and real-time importance rating data of users on vehicle model attributes; the passenger vehicle model twin model construction module 2 is used to construct a passenger vehicle model twin model based on the real-time passenger vehicle data and the real-time user review data, and store the passenger vehicle model twin model in a database; the user demand twin model construction module 3 is used to construct a user demand twin model based on the user demand data for vehicle model parameters and the user demand twin model attribute importance rating data; and the recommendation result generation module 4 is used to obtain vehicle model recommendation results based on the two-stage recommendation algorithm, the passenger vehicle model twin model library, and the user demand twin model.

[0112] As an example, the vehicle model agile recommendation system based on the digital twin model in this embodiment can be used to execute the vehicle model agile recommendation method based on the digital twin model in the above embodiment.

[0113] As an example, the system of this application adopts a microservice architecture, collects data and outputs recommendation results through an API interface.

[0114] As an example, the system can be set up for scheduled updates, with the background regularly performing data collection, similarity calculations, and model maintenance to ensure that the recommendation system always runs based on the latest data.

[0115] In the aforementioned agile vehicle model recommendation system based on the digital twin model, the data acquisition module 1 acquires real-time passenger vehicle data, user review data, user demand data, and importance rating data, which can timely capture market dynamics and changes in user demand, ensuring the timeliness and comprehensiveness of the recommendation basis; the passenger vehicle model twin model construction module 2 can comprehensively depict the actual parameters, configuration, reputation, and other information of the vehicle model, provide an accurate vehicle model portrait, and make the recommendation results more in line with the actual situation of the vehicle model; the user demand twin model construction module 3 can deeply explore the personalized needs of users, ensure that the recommendation direction meets user expectations, and avoid blind recommendations; the recommendation result generation module 4 can comprehensively consider multi-dimensional information, scientifically measure the degree of match between vehicle models and user needs, and make the recommendation results more reasonable and targeted. The system of this application can comprehensively, real-timely, and accurately reflect the characteristics of vehicle models and personalized needs of users, improve the accuracy and timeliness of recommendations, provide users with higher-quality and demand-oriented vehicle model recommendation services, and enhance users' car purchasing experience and decision-making efficiency.

[0116] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] Although the present application has been disclosed above with reference to the embodiments, they are not intended to limit the present application. Anyone with ordinary knowledge in the technical field may make slight changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be determined by the scope of the appended patent application.

Claims

1. A vehicle model agile recommendation method based on digital twin model, characterized by: The following steps are involved: Acquire real-time passenger vehicle data and real-time user review data, and construct a passenger vehicle model twin model library based on the real-time passenger vehicle data and the real-time user review data, wherein the passenger vehicle model twin model library is dynamically updated based on new passenger vehicle data and new user review data; Constructing a passenger vehicle model twin model library based on the real-time passenger vehicle data and the real-time user review data, wherein the passenger vehicle model twin model library is dynamically updated based on new passenger vehicle data and new user review data, including: performing structured processing on the real-time passenger vehicle data to obtain parameter feature data; obtaining the average sentiment value of each vehicle model attribute based on the real-time user review data as word-of-mouth feature data; vectorizing the parameter feature data and the word-of-mouth feature data, and performing vector fusion on the vectorized parameter feature data and the word-of-mouth feature data to obtain the passenger vehicle model twin model; storing the passenger vehicle model twin models of all vehicle model attributes in a database to obtain a passenger vehicle model twin model library, wherein the passenger vehicle model twin model library is dynamically updated based on new passenger vehicle data and new user review data; Acquire real-time user demand data for vehicle model parameters and real-time user importance rating data for vehicle model attributes, and build a user demand twin model based on the real-time user demand data for vehicle model parameters and real-time user importance rating data for vehicle model attributes; The vehicle model recommendation result is obtained based on the two-stage recommendation algorithm, the passenger vehicle model twin model library and the user demand twin model, including: screening the passenger vehicle model twin model library in sequence according to a preset order to obtain candidate vehicle models; obtaining the vehicle model attribute demand weight vector of the candidate vehicle model based on the user demand twin model; obtaining the word-of-mouth feature vector of the candidate vehicle model based on the passenger vehicle model twin model; performing weighted cosine similarity calculation on the vehicle model attribute demand weight vector and the word-of-mouth feature vector to obtain the weighted cosine similarity between the two; arranging the candidate vehicle models in descending order according to the weighted cosine similarity, and selecting the top several candidate vehicle models as the vehicle model recommendation result.

2. The vehicle model agile recommendation method based on digital twin model according to claim 1 is characterized in that: Web crawler technology is used to obtain feature data uploaded by passenger car physical entities in real time; a passenger car model twin model is constructed based on the real-time passenger car data and the real-time user review data to form a passenger car model twin model library, and the twin model is iterated in real time.

3. The vehicle model agile recommendation method based on digital twin model according to claim 2 is characterized in that: The real-time passenger car data is subjected to structured processing to obtain parameter characteristic data, including: performing numerical standardization and category coding on the real-time passenger car data to obtain the parameter characteristic data.

4. The method for agile vehicle model recommendation based on digital twin model according to claim 2, characterized in that: A user demand twin model is constructed based on the user's real-time demand data for vehicle model parameters and the user's real-time importance rating data for vehicle model attributes, including: Obtaining a vehicle model parameter demand feature vector based on the user's real-time demand data for vehicle model parameters; Normalizing the user's real-time importance rating data for vehicle model attributes to obtain a vehicle model attribute demand weight vector; The vehicle model parameter requirement feature vector and the vehicle model attribute requirement weight vector are fused to obtain the user demand twin model.

5. The method for agile vehicle model recommendation based on digital twin model according to claim 4 is characterized in that: The formula for normalizing the user's importance score data for vehicle attributes is: in, is the demand weight of the i-th vehicle model attribute, n is the total number of vehicle model attributes, Importance scoring data for the i-th vehicle model attribute.

6. The method for agile vehicle model recommendation based on digital twin model according to claim 4 is characterized in that: The real-time demand data for vehicle parameters include: vehicle level preference, power type preference, minimum cruising range, maximum charging time and vehicle purchase budget range; the real-time importance rating data for vehicle attributes includes the importance of space, battery life, appearance, interior, cost-effectiveness, driving quality and in-vehicle intelligent system, with a score of 0-10.

7. The method for agile vehicle model recommendation based on digital twin model according to claim 6 is characterized in that: The preset order includes: car purchase budget, cruising range, vehicle model level, power type and charging time.

8. The method for agile vehicle model recommendation based on digital twin model according to claim 6, characterized in that: In the process of screening the passenger vehicle model twin models in sequence according to a preset order to obtain candidate models, if the number of candidate models is lower than a preset threshold, the restriction conditions are canceled in reverse order or the numerical condition threshold is relaxed according to a preset ratio until the number of candidate models reaches the preset threshold.

9. The method for agile vehicle model recommendation based on digital twin model according to claim 6, characterized in that: The weighted cosine similarity of the vehicle attribute demand weight vector and the word-of-mouth feature vector is calculated based on the following formula to obtain the weighted cosine similarity between the two: Wherein, Similarity is the weighted cosine similarity between the vehicle attribute demand weight vector and the word-of-mouth feature vector; is the demand weight of the i-th vehicle model attribute, is the average sentiment value of the i-th vehicle model attribute, and n is the total number of vehicle model attributes.

10. An agile vehicle model recommendation system based on a digital twin model, characterized by: Used to execute the vehicle model agile recommendation method based on the digital twin model as described in any one of claims 1 to 9; The vehicle model agile recommendation system based on the digital twin model includes: The data collection module is used to obtain real-time passenger vehicle data, real-time user review data, real-time user demand data for vehicle model parameters, and real-time user importance rating data for vehicle model attributes; A passenger vehicle twin model construction module, configured to construct a passenger vehicle twin model based on the real-time passenger vehicle data and the real-time user review data, and store the passenger vehicle twin model in a database; A user demand twin model construction module is used to construct a user demand twin model based on the user's demand data for vehicle model parameters and the user's importance rating data for vehicle model attributes; The recommendation result generation module is used to obtain vehicle model recommendation results based on the two-stage recommendation algorithm, the passenger vehicle model twin model library and the user demand twin model.

Images