Vehicle model trend analysis method and device, equipment and storage medium

Abstract

The invention discloses a vehicle type trend analysis method, device and equipment and a computer readable storage medium. The method comprises the following steps: based on a preset label classification model, according to a to-be-predicted user text, obtaining a label of the to-be-predicted user text output by the preset label classification model; generating a user portrait according to the label and the to-be-predicted user text; according to the user portrait and a preset semantic analysis model, a probability value of each label in the user portrait is obtained, the user portrait comprises a basic feature, a driving feature, a behavior feature, an interest feature, a car purchase factor feature and a label, and the label comprises a look-ahead type user, a following type user or a demand-free type user; according to the probability value of each label, a vehicle type trend analysis table is generated to analyze the vehicle type trend, and the technical problem that a correct basis cannot be provided for vehicle type positioning due to the fact that a vehicle investigation method cannot be well mastered in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of data analysis, and specifically to a vehicle model trend analysis method, system, device and computer-readable storage medium. Background Art

[0002] The classification construction and trend analysis method of new energy household automobile user groups is a study of the process of individuals or groups recognizing, selecting, purchasing, and using new energy automobile products and services to meet their own travel needs. User classification research and trend analysis can effectively help automobile companies understand user behavior, vehicle demand and vehicle values, provide scientific decision-making basis for enterprises to formulate new vehicle product positioning and marketing strategies, and ensure good economic benefits.

[0003] With the advancement of the new four modernizations, the share of new energy vehicles in the automobile market has gradually increased. More and more consumers have a deeper understanding of new energy vehicles, and their willingness to choose new energy vehicles when purchasing cars is also increasing.

[0004] However, in the process of contacting a large number of automobile manufacturers, we found that the actual situation is that new energy automobile manufacturers have realized the importance of user research and will do a lot of seed user research, but some automobile companies still lack in-depth understanding of this aspect of user research, usually only verbally attach importance to it, but not really implement it. Some companies also do not know how to investigate the automobile market and use improper investigation methods. For automobile manufacturers, only by properly mastering the methods of automobile investigation can they better obtain accurate information and provide the correct basis for vehicle model positioning. Summary of the invention

[0005] The present application provides a vehicle model trend analysis method, device, equipment and computer-readable storage medium, which can solve the technical problem that the prior art cannot master the method of automobile investigation and thus cannot provide a correct basis for vehicle model positioning.

[0006] In a first aspect, an embodiment of the present application provides a vehicle model trend analysis method, the vehicle model trend analysis method comprising:

[0007] Based on a preset label classification model, according to the user text to be predicted, obtaining a label of the user text to be predicted output by the preset label classification model;

[0008] Generate a user portrait according to the label and the user text to be predicted;

[0009] According to the user portrait and the preset semantic analysis model, the probability value of each label in the user portrait is obtained, wherein the user portrait includes basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and labels, and the labels include forward-looking leading users, following users or non-demand users;

[0010] According to the probability values ​​of the various tags, a vehicle model trend analysis table is generated to analyze the vehicle model trend.

[0011] In combination with the first aspect, in one implementation, generating a vehicle model trend analysis table according to the probability values ​​of each of the tags to analyze the vehicle model trend includes:

[0012] Sort the probability values ​​of the labels in descending order;

[0013] Selecting a target tag from the sorted multiple tags according to a preset extraction ratio;

[0014] Determine whether the target tag contains a vehicle model keyword, wherein the vehicle model keyword includes driving style and family status;

[0015] If it is determined that the target tag contains a vehicle type keyword, a vehicle type trend analysis table is generated to analyze the vehicle type trend.

[0016] In combination with the first aspect, in one implementation, the label includes a forward-looking leading user, and generating a user portrait according to the label and the user text to be predicted includes:

[0017] Determine whether the tag is a forward-looking leading user;

[0018] If it is determined that the label is the forward-looking leading user, the forward-looking leading user is used as the label of the user text to be predicted, and a user portrait is generated.

[0019] In combination with the first aspect, in one implementation, before obtaining the label of the user text to be predicted output by the preset label classification model based on the user text to be predicted, the method further includes:

[0020] Obtaining a user text data set to be trained, wherein the user text data set to be trained includes multiple groups of user texts to be trained, and the user texts to be trained include basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics, and labels of users, and the labels include forward-looking leading users, following users, or non-demand users;

[0021] Preset a neural network for training the user text data set to be trained;

[0022] Determine whether the trained preset neural network is in a convergence state;

[0023] If it is determined that the preset neural network after training is in a convergence state, a label classification model is generated.

[0024] In combination with the first aspect, in one implementation, determining whether the trained preset neural network is in a convergence state includes:

[0025] Get the training times of the preset neural network after training;

[0026] If the number of training times is greater than or equal to the preset number of training times, it is determined that the trained preset neural network is in a convergence state.

[0027] In combination with the first aspect, in one implementation, determining whether the trained preset neural network is in a convergence state includes:

[0028] Get the loss value of the pre-set neural network after training;

[0029] If the loss value is less than or equal to the preset loss value, it is determined that the trained preset neural network is in a convergence state.

[0030] In combination with the first aspect, in one implementation, the preset semantic analysis model is obtained by pre-training a preset network with training data, and the training data includes user portraits to be trained and probability values ​​annotated for the user portraits to be trained.

[0031] In a second aspect, an embodiment of the present application provides a vehicle model trend analysis device, the vehicle model trend analysis device comprising:

[0032] A first acquisition module is used to acquire, based on a preset label classification model and according to the user text to be predicted, a label of the user text to be predicted output by the preset label classification model;

[0033] A generating module, used for generating a user portrait according to the label and the user text to be predicted;

[0034] A second acquisition module is used to acquire the probability value of each label in the user portrait according to the user portrait and the preset semantic analysis model, wherein the user portrait includes basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and labels, and the labels include forward-looking leading users, follower users or non-demand users;

[0035] The analysis module is used to generate a vehicle model trend analysis table according to the probability value of each of the tags to analyze the vehicle model trend.

[0036] In a third aspect, an embodiment of the present application provides a vehicle model trend analysis device, the vehicle model trend analysis device comprising a processor, a memory, and a vehicle model trend analysis program stored in the memory and executable by the processor, wherein when the vehicle model trend analysis program is executed by the processor, the steps of the vehicle model trend analysis method as described above are implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a vehicle model trend analysis program is stored, wherein when the vehicle model trend analysis program is executed by a processor, the steps of the above-mentioned vehicle model trend analysis method are implemented.

[0038] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0039] Based on a preset label classification model, according to the user text to be predicted, the label of the user text to be predicted output by the preset label classification model is obtained; according to the label and the user text to be predicted, a user portrait is generated; according to the user portrait and a preset semantic analysis model, the probability value of each label in the user portrait is obtained, wherein the user portrait includes basic features, driving features, behavior features, interest features, car purchase factor features and labels, and the labels include forward-looking leading users, following users or non-demand users; according to the probability values ​​of each label, a vehicle model trend analysis table is generated to analyze the vehicle model trend, thereby solving the technical problem that the method of automobile investigation cannot be mastered in the related technology, and thus the correct basis cannot be provided for vehicle model positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a first embodiment of a vehicle model trend analysis method of the present application;

[0041] Figure 2 A schematic diagram of a flow chart of a second embodiment of a vehicle model trend analysis method of the present application;

[0042] Figure 3 This is a schematic diagram of the functional modules of an embodiment of a vehicle model trend analysis device of the present application;

[0043] Figure 4 This is a schematic diagram of the hardware structure of a vehicle model trend analysis device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the solution of the present application, 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 only 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.

[0045] First, some technical terms in the present application are explained to facilitate those skilled in the art to understand the present application.

[0046] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0047] In a first aspect, an embodiment of the present application provides a vehicle model trend analysis method.

[0048] In one embodiment, referring to Figure 1 , Figure 1 FIG. 1 is a flow chart of the first embodiment of the vehicle model trend analysis method of the present application. Figure 1 As shown, the vehicle model trend analysis method includes:

[0049] Step S10: Based on a preset label classification model, according to the user text to be predicted, obtaining a label of the user text to be predicted output by the preset label classification model;

[0050] Exemplarily, the user text to be predicted is obtained, and the user text to be predicted includes the basic characteristics of the user: gender, age, region, education, occupation, income, marital status, and family status; driving characteristics include: driving experience, whether there is a car, the brand, model, price, driving frequency, and vehicle status of the current car; behavioral characteristics: frequency of using assisted driving functions, driving style (aggressive / peaceful / conservative / easily affected by road conditions), frequently used assisted driving functions, and frequently used HMI functions. Marital status includes married and unmarried, family status includes no children, one child, two children, and more than two children, vehicle status includes first purchase, additional purchase, and replacement, frequency of using assisted driving functions includes never, occasionally, and often, and driving style includes aggressive, peaceful, conservative, and easily affected by road conditions. The obtained user text to be predicted is input into the preset label classification model to obtain the label output by the preset label classification model, which includes forward-looking leading users, following users, and non-demand users.

[0051] Step S20: generating a user portrait according to the label and the user text to be predicted;

[0052] Exemplarily, when obtaining a label, the label is used as the label of the user text to be predicted to generate a user portrait. For example, if the label is a forward-looking leading user, the forward-looking leading user is used as the label of the user text to be predicted to generate a user portrait.

[0053] Specifically, the label includes a forward-looking leading user, and generating a user portrait based on the label and the user text to be predicted includes: determining whether the label is a forward-looking leading user; if it is determined that the label is the forward-looking leading user, then using the forward-looking leading user as the label of the user text to be predicted, and generating a user portrait.

[0054] Exemplarily, determine whether the tag is a forward-looking leading user. If it is determined that the tag is a forward-looking leading user, use the forward-looking leading user as a tag for the user text to be predicted to generate a user portrait.

[0055] Step S30: According to the user portrait and the preset semantic analysis model, the probability value of each label in the user portrait is obtained, wherein the user portrait includes basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and labels, and the labels include forward-looking leading users, following users or non-demand users;

[0056] Exemplarily, the user portrait is input into the preset semantic analysis model to obtain the probability value of each user portrait output by the preset semantic analysis model. The user portrait includes the basic characteristics of the user: gender, age, region, education, occupation, income, marital status, and family status; driving characteristics include: driving experience, whether there is a car, the brand, model, price, driving frequency, and vehicle status of the current car; behavioral characteristics: frequency of using assisted driving functions, driving style (aggressive / peaceful / conservative / easily affected by road conditions), frequently used assisted driving functions, and frequently used HMI functions. Marital status includes married and unmarried, family status includes no children, one child, two children, and more than two children, vehicle status includes first purchase, additional purchase, and replacement, frequency of using assisted driving functions includes never, occasionally, and often, driving style includes aggressive, peaceful, conservative, easily affected by road conditions, as well as automobile market sales trends, distribution of new energy vehicle companies, factors that consumers look at when buying cars, consumer market consumption habits, social and technological development, cultural development, and policy changes.

[0057] Step S40: generating a vehicle model trend analysis table according to the probability values ​​of the respective tags to analyze the vehicle model trend.

[0058] Exemplarily, multiple user portrait probability values ​​are obtained; multiple probability values ​​are compared to obtain a target user portrait with a maximum probability value; the target user portrait is analyzed to obtain vehicle model keywords in the target user portrait, wherein the vehicle model keywords include driving style and family status; a vehicle model trend analysis table is generated based on the vehicle model keywords to analyze vehicle model trends.

[0059] In this embodiment, based on a preset label classification model, the label output by the user portrait prediction model is obtained according to the user text to be predicted; a user portrait is generated according to the label and the user text to be predicted; according to the user portrait and a preset semantic analysis model, the probability value of each semantic label of the text is obtained, wherein the user portrait includes basic features, driving features, behavioral features, interest features, car purchase factor features and labels, and the labels include forward-looking leading users, following users or non-demand users; according to the probability value and the user portrait, a vehicle model trend analysis table is generated to analyze the vehicle model trend, thereby solving the technical problem that the related technology cannot master the method of automobile investigation, and thus cannot provide a correct basis for vehicle model positioning.

[0060] In one embodiment, referring to Figure 2 , Figure 2 FIG. 2 is a flow chart of the second embodiment of the vehicle model trend analysis method of the present application. Figure 2 As shown, the vehicle model trend analysis method includes:

[0061] Step S11: obtaining a user text data set to be trained, wherein the user text data set to be trained includes multiple groups of user texts to be trained, and the user texts to be trained include basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and labels of users, and the labels include forward-looking leading users, following users or non-demand users;

[0062] Step S12: training a preset neural network with the user text data set to be trained;

[0063] Step S13: determining whether the trained preset neural network is in a convergence state;

[0064] Step S14: If it is determined that the preset neural network after training is in a convergence state, a label classification model is generated.

[0065] Step S15: Based on the preset label classification model, and according to the user text to be predicted, obtain the label output by the user portrait prediction model;

[0066] Exemplarily, the user text to be predicted is obtained, and the user text to be predicted includes the basic characteristics of the user: gender, age, region, education, occupation, income, marital status, and family status; driving characteristics include: driving experience, whether there is a car, the brand, model, price, driving frequency, and vehicle status of the current car; behavioral characteristics: frequency of using assisted driving functions, driving style (aggressive / peaceful / conservative / easily affected by road conditions), frequently used assisted driving functions, and frequently used HMI functions. Marital status includes married and unmarried, family status includes no children, one child, two children, and more than two children, vehicle status includes first purchase, additional purchase, and replacement, frequency of using assisted driving functions includes never, occasionally, and often, and driving style includes aggressive, peaceful, conservative, and easily affected by road conditions. The obtained user text to be predicted is input into the preset label classification model to obtain the label output by the preset label classification model, which includes forward-looking leading users, following users, and non-demand users.

[0067] Step S16: generating a user portrait according to the label and the user text to be predicted;

[0068] Exemplarily, when obtaining a tag to be predicted, the tag is used as the tag of the user text to be predicted to generate a user portrait. For example, if the tag is a forward-looking leading user, the forward-looking leading user is used as the tag of the user text to be predicted to generate a user portrait.

[0069] Specifically, the label includes a forward-looking leading user, and generating a user portrait based on the label and the user text to be predicted includes: determining whether the label is a forward-looking leading user; if it is determined that the label is the forward-looking leading user, then using the forward-looking leading user as the label of the user text to be predicted, and generating a user portrait.

[0070] Exemplarily, determine whether the tag is a forward-looking leading user. If it is determined that the tag is a forward-looking leading user, use the forward-looking leading user as a tag for the user text to be predicted to generate a user portrait.

[0071] Step S17: Obtaining probability values ​​of various semantic tags of the text according to the user portrait and the preset semantic analysis model, wherein the user portrait includes basic features, driving features, behavior features, interest features, car purchase factor features and tags, and the tags include forward-looking leading users, following users or non-demand users;

[0072] Exemplarily, the user portrait is input into the preset semantic analysis model to obtain the probability value of each user portrait input into the preset semantic analysis model. The user portrait includes the basic characteristics of the user: gender, age, region, education, occupation, income, marital status, family status; driving characteristics include: driving experience, whether there is a car, the brand, model, price, driving frequency, and vehicle status of the current car; behavioral characteristics: frequency of using assisted driving functions, driving style (aggressive / peaceful / conservative / easily affected by road conditions), frequently used assisted driving functions, and frequently used HMI functions. Marital status includes married and unmarried, family status includes no children, one child, two children, and more than two children, vehicle status includes first purchase, additional purchase, and replacement, frequency of using assisted driving functions includes never, occasionally, and often, driving style includes aggressive, peaceful, conservative, easily affected by road conditions, as well as automobile market sales trends, distribution of new energy vehicle companies, factors that consumers consider when buying cars, consumer market consumption habits, social and technological development, cultural development, and policy changes.

[0073] Step S18: Generate a vehicle model trend analysis table based on the probability value and the user portrait to analyze the vehicle model trend.

[0074] Exemplarily, multiple user portrait probability values ​​are obtained; multiple probability values ​​are compared to obtain a target user portrait with a maximum probability value; the target user portrait is analyzed to obtain vehicle model keywords in the target user portrait, wherein the vehicle model keywords include driving style and family status; a vehicle model trend analysis table is generated based on the vehicle model keywords to analyze vehicle model trends.

[0075] In this embodiment, the trained model is used to predict the label of the user text to be predicted and the probability value of the user portrait, so as to quickly obtain the probability value of the car model in the user portrait.

[0076] In a second aspect, an embodiment of the present application also provides a vehicle model trend analysis device.

[0077] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of a vehicle model trend analysis device of the present application. Figure 3 As shown, the vehicle model trend analysis device includes:

[0078] A first acquisition module 10 is used to acquire, based on a preset label classification model and according to the user text to be predicted, a label of the user text to be predicted output by the preset label classification model;

[0079] A generating module 20, configured to generate a user portrait according to the label and the user text to be predicted;

[0080] A second acquisition module 30 is used to acquire the probability value of each semantic tag of the text according to the user portrait and the preset semantic analysis model, wherein the user portrait includes basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and tags, and the tags include forward-looking leading users, follower users or non-demand users;

[0081] The analysis module 40 is used to generate a vehicle model trend analysis table according to the probability value and the user portrait to analyze the vehicle model trend.

[0082] Furthermore, in one embodiment, the analysis module 40 is used to:

[0083] Sort the probability values ​​of the labels in descending order;

[0084] Selecting a target tag from the sorted multiple tags according to a preset extraction ratio;

[0085] Determine whether the target tag contains a vehicle model keyword, wherein the vehicle model keyword includes driving style and family status;

[0086] If it is determined that the target tag contains a vehicle type keyword, a vehicle type trend analysis table is generated to analyze the vehicle type trend.

[0087] Furthermore, in one embodiment, the generating module 20 is used to:

[0088] Determine whether the tag is a forward-looking leading user;

[0089] If it is determined that the label is the forward-looking leading user, the forward-looking leading user is used as the label of the user text to be predicted, and a user portrait is generated.

[0090] Furthermore, in one embodiment, the vehicle model trend analysis device further includes a new module for:

[0091] Obtaining a user text data set to be trained, wherein the user text data set to be trained includes multiple groups of user texts to be trained, and the user texts to be trained include basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics, and labels of users, and the labels include forward-looking leading users, following users, or non-demand users;

[0092] Preset a neural network for training the user text data set to be trained;

[0093] Determine whether the trained preset neural network is in a convergence state;

[0094] If it is determined that the preset neural network after training is in a convergence state, a label classification model is generated.

[0095] Furthermore, in one embodiment, the vehicle model trend analysis device further includes a new module for:

[0096] Get the training times of the preset neural network after training;

[0097] If the number of training times is greater than or equal to the preset number of training times, it is determined that the trained preset neural network is in a convergence state.

[0098] Furthermore, in one embodiment, the vehicle model trend analysis device further includes a new module for:

[0099] Get the loss value of the pre-set neural network after training;

[0100] If the loss value is less than or equal to the preset loss value, it is determined that the trained preset neural network is in a convergence state.

[0101] Among them, the functional implementation of each module in the above-mentioned vehicle model trend analysis device corresponds to the various steps in the above-mentioned vehicle model trend analysis method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0102] In a third aspect, an embodiment of the present application provides a vehicle model trend analysis device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0103] Reference Figure 4 , Figure 4 The hardware structure diagram of the vehicle model trend analysis device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the vehicle model trend analysis device may include a processor, a memory, a communication interface, and a communication bus.

[0104] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0105] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the vehicle model trend analysis device, and the interface used to realize the interconnection of the vehicle model trend analysis device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0106] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0107] The processor may be a general-purpose processor, which may call the vehicle model trend analysis program stored in the memory and execute the vehicle model trend analysis method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle model trend analysis program is called may refer to the various embodiments of the vehicle model trend analysis method of the present application, which will not be repeated here.

[0108] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0109] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0110] The computer-readable storage medium of the present application stores a vehicle model trend analysis program, wherein when the vehicle model trend analysis program is executed by a processor, the steps of the vehicle model trend analysis method as described above are implemented.

[0111] Among them, the method implemented when the vehicle model trend analysis program is executed can refer to the various embodiments of the vehicle model trend analysis method of the present application, and will not be repeated here.

[0112] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0113] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0114] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0115] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0116] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0118] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle model trend analysis method, characterized in that: The vehicle model trend analysis method comprises: Based on a preset label classification model, according to the user text to be predicted, obtaining a label of the user text to be predicted output by the preset label classification model; Generate a user portrait according to the label and the user text to be predicted; According to the user portrait and the preset semantic analysis model, the probability value of each label in the user portrait is obtained, wherein the user portrait includes basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and labels, and the labels include forward-looking leading users, following users or non-demand users; According to the probability values ​​of the various tags, a vehicle model trend analysis table is generated to analyze the vehicle model trend.

2. The vehicle model trend analysis method according to claim 1, characterized in that: Generating a vehicle model trend analysis table according to the probability values ​​of each of the tags to analyze the vehicle model trend includes: Sort the probability values ​​of the labels in descending order; Selecting a target tag from the sorted multiple tags according to a preset extraction ratio; Determine whether the target tag contains a vehicle model keyword, wherein the vehicle model keyword includes driving style and family status; If it is determined that the target tag contains a vehicle type keyword, a vehicle type trend analysis table is generated to analyze the vehicle type trend.

3. The vehicle model trend analysis method according to claim 1, characterized in that: The label includes a forward-looking leading user, and generating a user portrait according to the label and the user text to be predicted includes: Determine whether the tag is a forward-looking leading user; If it is determined that the label is the forward-looking leading user, the forward-looking leading user is used as the label of the user text to be predicted, and a user portrait is generated.

4. The vehicle model trend analysis method according to claim 1, characterized in that: Before obtaining the label of the user text to be predicted output by the preset label classification model based on the user text to be predicted, the method further includes: Obtaining a user text data set to be trained, wherein the user text data set to be trained includes multiple groups of user texts to be trained, and the user texts to be trained include basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics, and labels of users, and the labels include forward-looking leading users, following users, or non-demand users; Preset a neural network for training the user text data set to be trained; Determine whether the trained preset neural network is in a convergence state; If it is determined that the preset neural network after training is in a convergence state, a label classification model is generated.

5. The vehicle model trend analysis method according to claim 4, characterized in that: The step of determining whether the trained preset neural network is in a convergence state comprises: Get the training times of the preset neural network after training; If the number of training times is greater than or equal to the preset number of training times, it is determined that the trained preset neural network is in a convergence state.

6. The vehicle model trend analysis method according to claim 4, characterized in that: The step of determining whether the trained preset neural network is in a convergence state comprises: Get the loss value of the pre-set neural network after training; If the loss value is less than or equal to the preset loss value, it is determined that the trained preset neural network is in a convergence state.

7. The vehicle model trend analysis method according to claim 1, characterized in that: The preset semantic analysis model is obtained by pre-training a preset network with training data, wherein the training data includes a user portrait to be trained and a probability value annotated for the user portrait to be trained.

8. A vehicle model trend analysis device, characterized in that: The vehicle model trend analysis device comprises: A first acquisition module is used to acquire, based on a preset label classification model and according to the user text to be predicted, a label of the user text to be predicted output by the preset label classification model; A generating module, used for generating a user portrait according to the label and the user text to be predicted; A second acquisition module is used to acquire the probability value of each label in the user portrait according to the user portrait and the preset semantic analysis model, wherein the user portrait includes basic characteristics, driving characteristics, behavior characteristics, interest characteristics, car purchase factor characteristics and labels, and the labels include forward-looking leading users, follower users or non-demand users; The analysis module is used to generate a vehicle model trend analysis table according to the probability value of each of the tags to analyze the vehicle model trend.

9. A vehicle model trend analysis device, characterized in that: The vehicle model trend analysis device includes a processor, a memory, and a vehicle model trend analysis program stored in the memory and executable by the processor, wherein when the vehicle model trend analysis program is executed by the processor, the steps of the vehicle model trend analysis method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle model trend analysis program, wherein when the vehicle model trend analysis program is executed by a processor, the steps of the vehicle model trend analysis method according to any one of claims 1 to 7 are implemented.

Images