Vehicle type configuration proportion prediction method and device, equipment and medium

Abstract

The invention relates to a vehicle type configuration proportion prediction method and device, equipment and a medium, and belongs to the field of vehicle technologies. The method comprises the steps that configuration combination information of a vehicle is acquired; constructing a configuration proportion prediction model based on the configuration combination information; obtaining to-be-analyzed configuration combination information; determining a configuration proportion of the configuration combination information to be analyzed based on the configuration proportion prediction model; and displaying the configuration proportion. The method solves the problems that the configuration proportion of the vehicle type and the version is directly related to the market competitiveness and the sales performance of the product, if the configuration proportion is not reasonable, part of the version is possibly supplied beyond the demand, and the other part of the version is not supplied beyond the demand, so that the timeliness of the overall sales profit and the market share is influenced. The method has the effect of reasonably predicting and adjusting the vehicle type configuration proportion.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle configuration ratio prediction method, device, equipment and medium. Background Art

[0002] With the development of the economy and the improvement of people's living standards, the per capita car ownership is also gradually increasing. Car manufacturers produce different models of cars to meet the needs of different users.

[0003] During the planning of new automobile products, automobile manufacturers will develop multiple versions for each model. There are configuration differences between each version. For example, model A includes a comfort type and a fashion type. There are certain differences in the configuration of the comfort type and the fashion type. Among them, the configuration ratio of the model version is directly related to the market competitiveness and sales performance of the product. If the configuration ratio is unreasonable, it may lead to an oversupply of some versions and a shortage of other versions, which will affect the overall sales profit and market share.

[0004] Therefore, how to reasonably predict and adjust the configuration ratio of vehicle models to maximize market demand and enhance product competitiveness has become one of the urgent issues that automobile manufacturers need to solve. Summary of the invention

[0005] In order to reasonably predict and adjust the vehicle configuration ratio, the present application provides a vehicle configuration ratio prediction method, device, equipment and medium.

[0006] In the first aspect, the present application provides a vehicle model configuration ratio prediction method, which adopts the following technical solution:

[0007] A vehicle model configuration ratio prediction method, comprising:

[0008] Obtain vehicle configuration combination information;

[0009] Constructing a configuration ratio prediction model based on the configuration combination information;

[0010] Get the configuration combination information to be analyzed;

[0011] Determining the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model;

[0012] The configuration ratio is displayed.

[0013] By adopting the above technical solution, a configuration ratio prediction model is constructed through the collected configuration combination information, and the configuration combination information to be analyzed is input into the trained configuration ratio prediction model to obtain the configuration ratio of the configuration combination information to be analyzed, thereby predicting the potential demand and sales potential of the configuration combination to be analyzed in the market. Car manufacturers can formulate and adjust production plans based on this to ensure that the configuration of the produced models can meet the market demand to the greatest extent, thereby improving sales efficiency and profitability.

[0014] Optionally, constructing a configuration ratio prediction model based on the configuration combination information includes:

[0015] Dividing the configuration combination information into a plurality of data groups according to preset classification information, wherein the preset classification information includes brand, model and price;

[0016] Constructing a logistic regression model for each of the data groups;

[0017] The configuration combination information in each data group is used to train the corresponding logistic regression model to obtain a trained logistic regression model, and the trained logistic regression model is used as the configuration ratio prediction model.

[0018] By adopting the above technical solution, the configuration combination information is divided into multiple data groups by brand, model and price, and a logistic regression model is constructed for each data group to reduce the interference between different brands, models and price ranges. Therefore, the obtained configuration ratio prediction model can better adapt to the market demand characteristics of different brands, models and price ranges, and improve the accuracy of the prediction.

[0019] Optionally, the configuration combination information includes power level, interior level, intelligent driving level, space size and cockpit intelligence level, and the logistic regression model for each data group is constructed, including:

[0020] Based on the formula Constructing the logistic regression model;

[0021] Among them, P(Y=k|X) is the probability that the dependent variable Y belongs to category k given the independent variable X, where k represents a specific configuration belonging to a certain brand, model category or price range, X1 represents the power level, X2 represents the interior level, X3 represents the intelligent driving level, X4 represents the space size, X5 represents the cockpit intelligence level, β1 represents the influence coefficient of the power level, β2 represents the influence coefficient of the interior level, β3 represents the influence coefficient of the intelligent driving level, β4 represents the influence coefficient of the space size, and β5 represents the influence coefficient of the cockpit intelligence level.

[0022] By adopting the above technical solution, β1, β2, β3, β4, and β5 are determined through the logistic regression model, power level, interior level, intelligent driving level, space size, and cockpit intelligence level, so as to better predict the configuration ratio of the configuration combination information to be analyzed.

[0023] Optionally, before constructing the logistic regression model for each of the data groups, the method further includes:

[0024] Obtain an eigenvalue conversion model, where the power level, interior level, intelligent driving level, space size, and cockpit intelligence level each correspond to an eigenvalue conversion model;

[0025] The power level, interior grade, intelligent driving grade, space size and cockpit intelligence level are converted into eigenvalues ​​based on the eigenvalue conversion model;

[0026] The characteristic value is input into the corresponding logistic regression model.

[0027] By adopting the above technical solution, the eigenvalue conversion model can standardize the configuration information of different dimensions and different value ranges, so that these data are consistent and comparable when input into the logistic regression model. To a certain extent, the logistic regression model can more accurately capture the impact of different configuration information on market demand and improve the accuracy of the prediction.

[0028] Optionally, after displaying the configuration ratio, the method further includes:

[0029] Determine whether the preset period has been reached;

[0030] If the preset period is reached, the inventory information of each configuration combination of each vehicle model is obtained;

[0031] Calculating the ratio of the remaining quantities of all vehicle models based on the inventory information;

[0032] Determining whether the ratio meets a preset ratio;

[0033] If the preset ratio is not met, the eigenvalue conversion model is adjusted based on the ratio.

[0034] By adopting the above technical solution, by checking inventory information when the preset cycle is reached, the manufacturer can ensure that the manufacturer has a real-time understanding of the inventory status and avoid inventory backlogs or shortages; by calculating the ratio of the remaining quantities of all models and comparing it with the preset ratio, the manufacturer can clearly see whether the proportion of each model in the inventory is reasonable; if the ratio does not meet the preset standard, the manufacturer can take prompt measures to ensure a more reasonable inventory structure to meet market demand.

[0035] Optionally, the determining the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model includes:

[0036] Inputting the configuration combination information to be analyzed into the configuration ratio prediction model, and calculating the configuration probability of the configuration combination information to be analyzed in each brand, each vehicle type or each price range based on the configuration ratio prediction model;

[0037] The configuration probability is used as the configuration ratio.

[0038] Optionally, after dividing the configuration combination information into a plurality of data groups according to preset classification information, the method further includes:

[0039] Dividing the configuration combination information in each of the data groups into a training set and a test set;

[0040] The training set is used to train the corresponding logistic regression model to obtain a trained configuration ratio prediction model, and the test set is used to verify the trained configuration ratio prediction model.

[0041] In a second aspect, the present application provides a vehicle configuration ratio prediction device, which adopts the following technical solution:

[0042] A vehicle type configuration ratio prediction device, comprising:

[0043] The first acquisition module is used to acquire configuration combination information of the vehicle;

[0044] A construction module, used to construct a configuration ratio prediction model based on the configuration combination information;

[0045] The second acquisition module is used to acquire the configuration combination information to be analyzed;

[0046] A determination module, used to determine the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model;

[0047] A display module is used to display the configuration ratio.

[0048] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0049] An electronic device comprises a processor and a memory, wherein the processor is coupled to the memory;

[0050] The processor is used to execute the computer program stored in the memory so that the electronic device performs the method as described in any one of the first aspects.

[0051] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0052] A computer-readable storage medium comprises a computer program or an instruction, and when the computer program or the instruction is executed on a computer, the computer is caused to execute the method as described in any one of the first aspects.

[0053] In summary, the present application includes at least one of the following beneficial technical effects:

[0054] 1. Construct a configuration ratio prediction model through the collected configuration combination information, input the configuration combination information to be analyzed into the trained configuration ratio prediction model, and obtain the configuration ratio of the configuration combination information to be analyzed, so as to predict the potential demand and sales potential of the configuration combination to be analyzed in the market. Car manufacturers can formulate and adjust production plans based on this to ensure that the configuration of the produced models can meet the market demand to the greatest extent, thereby improving sales efficiency and profitability. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a method for predicting vehicle configuration ratio in an embodiment of the present application.

[0056] Figure 2 It is a structural block diagram of a vehicle type configuration ratio prediction device in an embodiment of the present application.

[0057] Figure 3 It is a structural block diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The present application is further described in detail below in conjunction with the accompanying drawings.

[0059] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0060] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in 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 embodiments in 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.

[0061] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0062] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0063] The embodiment of the present application provides a method for predicting vehicle configuration ratio, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0064] like Figure 1 As shown, a vehicle configuration ratio prediction method is provided, and the main process of the method is described as follows (steps S101 to S105):

[0065] Step S101, obtaining configuration combination information of the vehicle;

[0066] In this embodiment, consumers' real needs and preferences for vehicle configuration combination information can be collected through consumer survey data, and consumers' real needs and preferences for vehicle configuration combination information can also be collected through vehicle sales information, without specific limitation. The vehicle configuration combination information can include multiple configuration combination information for each model of multiple brands, or can only include multiple configuration combination information for one model of one brand, determined according to user needs, without specific limitation.

[0067] Step S102, constructing a configuration ratio prediction model based on the configuration combination information;

[0068] Specifically, the configuration combination information is divided into multiple data groups according to preset classification information, and the preset classification information includes brand, model and price; a logistic regression model is constructed for each data group; the configuration combination information in each data group is used to train the corresponding logistic regression model to obtain a trained logistic regression model, and the trained logistic regression model is used as a configuration ratio prediction model

[0069] In this embodiment, in order to study consumers' preferences and real needs for configuration combination information of each brand, each model and different price ranges, each model of each brand corresponds to a logistic regression model, and each price range corresponds to a logistic regression model, wherein the price range can be determined according to user needs and is not specifically limited.

[0070] In this embodiment, when the configuration combination information of the vehicle is obtained, the configuration combination information is divided into multiple data groups according to preset classification information to construct a logistic regression model for each data group, wherein the preset classification information includes but is not limited to brand, model and price.

[0071] After the configuration combination information is divided into a plurality of data groups, the configuration combination information in each data group is further divided.

[0072] Specifically, the configuration combination information in each data group is divided into a training set and a test set; wherein the training set is used to train the corresponding logistic regression model to obtain a trained configuration ratio prediction model, and the test set is used to verify the trained configuration ratio prediction model.

[0073] In this embodiment, after obtaining multiple data groups, the configuration combination information in the data groups is further divided to obtain a training set and a test set, wherein the ratio of the training set to the test set can be 7:3 or 8:2, which is not specifically limited.

[0074] The configuration combination information includes power level, interior level, intelligent driving level, space size and cockpit intelligence level. A logistic regression model is constructed for each data group, including:

[0075] Specifically, based on the formula Construct a logistic regression model; where P(Y=k|X) is the probability that the dependent variable Y belongs to category k given the independent variable X, belonging to a specific configuration in a certain brand, model category or price range, X1 represents the power level, X2 represents the interior level, X3 represents the intelligent driving level, X4 represents the space size, X5 represents the cockpit intelligence level, β1 represents the influence coefficient of the power level, β2 represents the influence coefficient of the interior level, β3 represents the influence coefficient of the intelligent driving level, β4 represents the influence coefficient of the space size, and β5 represents the influence coefficient of the cockpit intelligence level.

[0076] Among them, the power level includes but is not limited to the power level of the main power unit, such as the power of the engine and the motor; the interior level includes but is not limited to comfort equipment and luxury equipment. Comfort equipment includes automatic seats and automatic air conditioning. Luxury equipment includes leather seats and leather door panels. The intelligent driving level includes but is not limited to the computing power and type of sensor equipment and intelligent driving chips. Sensor equipment includes but is not limited to lidar, cameras and millimeter-wave radars, sensor parameters, and the computing power and type of intelligent driving chips; the space size includes but is not limited to the longitudinal and forward space for the driver and the first and second row passengers of the vehicle; the intelligence level of the cabin includes but is not limited to the screen type, screen size, quantity, computing chips and computing power.

[0077] In this embodiment, β 1、 β 2、 β 3、 β4 and β5 are obtained by fitting the data of the training set using the least square method, maximum likelihood method, etc. according to the given dependent and independent variables. 1、 β 2、 β 3、 β4 and β 5， Among them, the configuration sales ratio of each model is the dependent variable, the configuration combination information is the independent variable, and the configuration sales ratio is determined by data statistics in the training set.

[0078] In this embodiment, before constructing the logistic regression model for each data group, it also includes: obtaining a eigenvalue conversion model, wherein the power level, interior level, intelligent driving level, space size and cockpit intelligence level each correspond to an eigenvalue conversion model; based on the eigenvalue conversion model, the power level, interior level, intelligent driving level, space size and cockpit intelligence level are converted into eigenvalues; and the eigenvalues ​​are input into the corresponding logistic regression model.

[0079] In this embodiment, the eigenvalue conversion model corresponding to the power level is: a normalization model, which establishes an array of data on the maximum power (engine, motor, etc.) of the models on sale, and establishes a mapping for the existing data: x′=log10(x)log10(max), thereby achieving normalization.

[0080] The eigenvalue conversion model corresponding to the interior grade, intelligent driving grade and cockpit intelligence level is the evaluation scale.

[0081] Table 1 is the evaluation scale

[0082] Table 1

[0083]

[0084] The eigenvalue conversion model corresponding to the spatial dimension is: normalized model.

[0085] For spatial dimensions, independent variables that are generally supported by more indicators, such as spatial level, are generally required. Several different indicators are summarized and comprehensively judged. For example, the spatial level is decomposed into four items: wheelbase, head space, knee space, and trunk space; that is, Xa, Xb, Xc, and Xd. These four items are normalized separately to obtain Xa1, Xb1, Xc1, and Xd1, and then the four items are used with equal weights to obtain the eigenvalue of the spatial level X = (Xa1+Xb1+Xc1+Xd1) / 4.

[0086] Among them, non-quantifiable equipment information, such as the presence or absence of relevant configurations, or high-end and low-end solutions, is based on the value that consumers can perceive, and is sorted and converted into characteristic values ​​​​of 0 to 1.

[0087] Step S103, obtaining configuration combination information to be analyzed;

[0088] In this embodiment, the user inputs the configuration combination information to be analyzed through the mouse, keyboard and other input devices of the electronic device, wherein the configuration combination information to be analyzed is the configuration information that the user wants to combine for a certain vehicle model. The electronic device obtains the configuration combination information to be analyzed input by the user, and obtains the feature conversion model corresponding to the configuration combination information, and converts the configuration combination information to be analyzed into feature values ​​to be analyzed through the feature value conversion model.

[0089] Step S104, determining the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model;

[0090] Specifically, the configuration combination information to be analyzed is input into the configuration ratio prediction model, and the configuration probability of the configuration combination information to be analyzed in each brand, each vehicle type or each price range is calculated based on the configuration ratio prediction model; the configuration probability is used as the configuration ratio.

[0091] In this embodiment, when the electronic device obtains the configuration combination information to be analyzed, it matches the configuration ratio prediction model corresponding to the configuration combination information to be analyzed, and inputs the characteristic value to be analyzed into the corresponding configuration ratio prediction model to calculate the configuration ratio.

[0092] When the combination information to be analyzed includes preset classification information, the corresponding configuration ratio prediction model is selected according to the corresponding preset classification information. When there is no preset classification information, the configuration ratio of the configuration combination information to be analyzed is calculated for each brand, each model and different price ranges.

[0093] Among them, when the combination information to be analyzed includes preset classification information, the corresponding configuration ratio prediction model is selected according to the corresponding preset classification information, including: when the electronic device obtains the configuration combination information to be analyzed, the preset classification information in the configuration combination information to be analyzed is extracted, and the preset classification information includes brand, model and price, and then the configuration ratio prediction model that matches the preset classification information is matched.

[0094] Step S105, displaying the configuration ratio.

[0095] In this embodiment, the electronic device displays the calculated configuration ratio so that the user can produce the corresponding vehicle model according to the configuration ratio.

[0096] In the present technical solution, after the configuration ratio is displayed, it also includes: judging whether the preset period has been reached; if the preset period has been reached, obtaining the inventory information of each configuration combination of each vehicle model; calculating the ratio of the remaining quantity of all vehicle models based on the inventory information; judging whether the ratio meets the preset ratio; if it does not meet the preset ratio, adjusting the characteristic value conversion model based on the ratio.

[0097] In this embodiment, the electronic device determines in real time whether a preset period has been reached. When the preset period is reached, the inventory information of each configuration combination of each vehicle model is obtained, wherein the inventory information is the remaining quantity of each configuration combination of each vehicle model, and the ratio of the remaining quantities of all vehicle models is calculated, such as configuration combination a: configuration combination b: configuration combination c = 1:2:1. In this embodiment, the preset ratio is 1:1:1. At this time, it is determined that the production quantity of configuration combination c is large, and the production ratio of configuration combination c needs to be adjusted.

[0098] In this embodiment, the eigenvalue conversion model adjusted based on the ratio can be: determining the configuration combination that does not meet the preset ratio, and determining the difference configuration between the configuration combination and other configuration combinations, such as power level, interior level, intelligent driving level, space size and cockpit intelligence level; adjusting the eigenvalue conversion model according to the ratio, multiplying the parameters output by the ratio-adjusted eigenvalue conversion model by the reciprocal of the ratio to obtain adjusted parameters, using the adjusted parameters as a training set, and fitting the data according to the given dependent variable and independent variable through the least squares method, the maximum likelihood method, etc., to obtain β 1、 β 2、 β 3、 β4 and β 5， The eigenvalue conversion model is adjusted so that the obtained β 1、 β 2、 β 3、 The β4 and β5 values ​​are more accurate, which improves the accuracy of the prediction.

[0099] Among them, the preset period can be determined by: obtaining the influencing factors of vehicle purchase, wherein the influencing factors include vehicle sales, preferential policies and per capita income, each influencing factor corresponds to a weight value, and the adjustment score is calculated based on the vehicle sales, preferential policies and per capita income and the corresponding weight values, and the preset period is determined by the adjustment score.

[0100] Among them, the weight value of each influencing factor is preset in advance, and the adjustment score = influencing factor 1*corresponding weight + influencing factor 2*corresponding weight + influencing factor 3*corresponding weight; if there is a preferential policy, the value is 1, and if there is no preferential policy, the value is 0.

[0101] It should be noted that a plurality of adjustment score intervals are preset in the electronic device, and each adjustment score interval corresponds to a preset period.

[0102] When the adjustment score is obtained, the adjustment value interval of the adjustment score is determined, and the preset period is determined according to the adjustment score.

[0103] Figure 2 This is a structural block diagram of a vehicle configuration ratio prediction device 200 provided in this application. Figure 2 As shown, the vehicle configuration ratio prediction device 200 mainly includes:

[0104] The first acquisition module 201 is used to acquire configuration combination information of the vehicle;

[0105] A construction module 202 is used to construct a configuration ratio prediction model based on the configuration combination information;

[0106] The second acquisition module 203 is used to acquire the configuration combination information to be analyzed;

[0107] A determination module 204, configured to determine the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model;

[0108] The display module 205 is used to display the configuration ratio.

[0109] As an optional implementation of this embodiment, the construction module 202 includes:

[0110] A division submodule, used to divide the configuration combination information into a plurality of data groups according to preset classification information, wherein the preset classification information includes brand, model and price;

[0111] Model building module, used to build a logistic regression model for each data group;

[0112] The training module is used to train the corresponding logistic regression model using the configuration combination information in each data group to obtain a trained logistic regression model, and use the trained logistic regression model as a configuration ratio prediction model.

[0113] In this optional embodiment, the model building module is specifically used to:

[0114] Based on the formula Construct a logistic regression model; where P(Y=k|X) is the probability that the dependent variable Y belongs to category k given the independent variable X, belonging to a specific configuration in a certain brand, model category or price range, X1 represents the power level, X2 represents the interior level, X3 represents the intelligent driving level, X4 represents the space size, X5 represents the cockpit intelligence level, β1 represents the influence coefficient of the power level, β2 represents the influence coefficient of the interior level, β3 represents the influence coefficient of the intelligent driving level, β4 represents the influence coefficient of the space size, and β5 represents the influence coefficient of the cockpit intelligence level.

[0115] As an optional implementation of this embodiment, the vehicle type configuration ratio prediction device 200 further includes:

[0116] A model acquisition module is used to obtain a eigenvalue conversion model before constructing a logistic regression model for each data group, wherein each of the power level, interior level, intelligent driving level, space size, and cockpit intelligence level corresponds to a eigenvalue conversion model;

[0117] A conversion module, which is used to convert the power level, interior grade, intelligent driving grade, space size and cockpit intelligence level into characteristic values ​​based on the characteristic value conversion model;

[0118] Input module, used to input feature values ​​into the corresponding logistic regression model.

[0119] As an optional implementation of this embodiment, the vehicle type configuration ratio prediction device 200 further includes:

[0120] The first judgment module is used to judge whether a preset period has been reached after the configuration ratio is displayed; if the preset period has been reached, the inventory information of each configuration combination of each vehicle model is obtained;

[0121] A calculation module, used for calculating the ratio of the remaining quantities of all vehicle models based on the inventory information;

[0122] The second judgment module is used to judge whether the ratio meets the preset ratio; if it does not meet the preset ratio, the characteristic value conversion model is adjusted based on the ratio.

[0123] As an optional implementation of this embodiment, the determination module 204 is specifically configured to:

[0124] The configuration combination information to be analyzed is input into the configuration ratio prediction model, and the configuration probability of the configuration combination information to be analyzed in each brand, each vehicle type or each price range is calculated based on the configuration ratio prediction model; the configuration probability is used as the configuration ratio.

[0125] As an optional implementation of this embodiment, the vehicle type configuration ratio prediction device 200 further includes:

[0126] The data partitioning module is used to divide the configuration combination information into multiple data groups according to preset classification information, and then divide the configuration combination information in each data group into a training set and a test set; wherein the training set is used to train the corresponding logistic regression model to obtain a trained configuration ratio prediction model, and the test set is used to verify the trained configuration ratio prediction model.

[0127] The functional modules in the embodiments of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for an electronic device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of a vehicle configuration ratio prediction method in each embodiment of the present application.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0129] Figure 3 FIG. 1 is a structural block diagram of an electronic device 300 provided in an embodiment of the present application. Figure 3 As shown, the electronic device 300 includes a memory 301, a processor 302 and a communication bus 303; the memory 301 and the processor 302 are connected via the communication bus 303. The memory 301 stores a vehicle configuration ratio prediction method provided in the above embodiment that can be loaded and executed by the processor 302.

[0130] The memory 301 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 301 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing a vehicle configuration ratio prediction method provided in the above embodiment, etc.; the data storage area can store data involved in a vehicle configuration ratio prediction method provided in the above embodiment, etc.

[0131] The processor 302 may include one or more processing cores. The processor 302 executes various functions and processes data of the present application by running or executing instructions, programs, code sets or instruction sets stored in the memory 301, calling the data stored in the memory 301. The processor 302 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller and a microprocessor. It is understandable that for different devices, the electronic device used to implement the above-mentioned processor 302 function may also be other, and the embodiment of the present application is not specifically limited.

[0132] The communication bus 303 may include a path to transmit information between the above components. The communication bus 303 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus 303 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one double arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0133] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute a vehicle model configuration ratio prediction method as provided in the above embodiment.

[0134] In this embodiment, the computer-readable storage medium may be a tangible device that holds and stores instructions used by the instruction execution device. The computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0135] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0136] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A vehicle configuration ratio prediction method, characterized in that: include: Get the configuration combination information of the vehicle; Constructing a configuration ratio prediction model based on the configuration combination information; Get the configuration combination information to be analyzed; Determining the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model; The configuration ratio is displayed.

2. The method according to claim 1, characterized in that The constructing a configuration ratio prediction model based on the configuration combination information includes: Dividing the configuration combination information into a plurality of data groups according to preset classification information, wherein the preset classification information includes brand, model and price; Constructing a logistic regression model for each of the data groups; The configuration combination information in each data group is used to train the corresponding logistic regression model to obtain a trained logistic regression model, and the trained logistic regression model is used as the configuration ratio prediction model.

3. The method according to claim 2, characterized in that The configuration combination information includes power level, interior level, intelligent driving level, space size and cockpit intelligence level, and the logistic regression model for each data group is constructed, including: Based on the formula Constructing the logistic regression model; Among them, P(Y=k|X) is the probability that the dependent variable Y belongs to category k given the independent variable X, where k represents the specific model configuration of a certain brand, model or price range, X1 represents the power level, X2 represents the interior level, X3 represents the intelligent driving level, X4 represents the space size, X5 represents the intelligence level of the cockpit, β1 represents the influence coefficient of the power level, β2 represents the influence coefficient of the interior level, β3 represents the influence coefficient of the intelligent driving level, β4 represents the influence coefficient of the space size, and β5 represents the influence coefficient of the intelligence level of the cockpit.

4. The method according to claim 2, characterized in that: Before constructing the logistic regression model for each of the data groups, the method further includes: Obtain an eigenvalue conversion model, where the power level, interior level, intelligent driving level, space size, and cockpit intelligence level each correspond to an eigenvalue conversion model; The power level, interior grade, intelligent driving grade, space size and cockpit intelligence level are converted into eigenvalues ​​based on the eigenvalue conversion model; The characteristic value is input into the corresponding logistic regression model.

5. The method according to claim 4, characterized in that After displaying the configuration ratio, the method further includes: Determine whether the preset period has been reached; If the preset period is reached, the inventory information of each configuration combination of each vehicle model is obtained; Calculating the ratio of the remaining quantities of all vehicle models based on the inventory information; Determining whether the ratio meets a preset ratio; If the preset ratio is not met, the eigenvalue conversion model is adjusted based on the ratio.

6. The method according to claim 1, characterized in that The determining the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model includes: Inputting the configuration combination information to be analyzed into the configuration ratio prediction model, and calculating the configuration probability of the configuration combination information to be analyzed in each brand, each vehicle type or each price range based on the configuration ratio prediction model; The configuration probability is used as the configuration ratio.

7. The method according to claim 2, characterized in that After dividing the configuration combination information into a plurality of data groups according to the preset classification information, the method further includes: Dividing the configuration combination information in each of the data groups into a training set and a test set; The training set is used to train the corresponding logistic regression model to obtain a trained configuration ratio prediction model, and the test set is used to verify the trained configuration ratio prediction model.

8. A vehicle type configuration ratio prediction device, characterized in that: include: A first acquisition module, used to acquire configuration combination information of a vehicle; A construction module, used to construct a configuration ratio prediction model based on the configuration combination information; The second acquisition module is used to acquire the configuration combination information to be analyzed; A determination module, used to determine the configuration ratio of the configuration combination information to be analyzed based on the configuration ratio prediction model; A display module is used to display the configuration ratio.

9. An electronic device, characterized in that: comprising a processor and a memory, wherein the processor is coupled to the memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Images