Method for retrieving vehicle type based on large model, storage medium, electronic equipment and product

Abstract

The invention relates to the technical field of data retrieval, and particularly provides a method for retrieving a vehicle type based on a large model, a storage medium, electronic equipment and a product, and the method can comprise the following steps: identifying content information input by a user, and obtaining retrieval parameters of a to-be-retrieved vehicle type, the retrieval parameters comprise a vehicle series, a vehicle brand or a vehicle alias corresponding to the vehicle series; retrieving a preset number of vehicle data from a vector database through the retrieval parameters; wherein the vehicle data comprises the vehicle series and the vehicle brand; and performing similarity analysis on the retrieval parameters and the vehicle data, and determining a vehicle type retrieval result matched with the content information. According to some embodiments of the invention, the accuracy of vehicle type retrieval can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data retrieval, in particular to a method for retrieving vehicle types based on a large model, a storage medium, an electronic device and a product. BACKGROUND

[0002] With the increasing number of vehicle brands and vehicle series corresponding to different vehicle brands, when a user needs to retrieve information about a vehicle type of a vehicle brand due to business needs or personal needs, the user usually uses a keyword fuzzy matching method. However, different users input different content, and the matching method has deviations. If the user inputs more or fewer words, the probability of error in the retrieval result is relatively high, and the accuracy of vehicle type retrieval is relatively low.

[0003] Therefore, how to provide a technical solution of a more accurate method for retrieving vehicle types based on a large model has become a technical problem to be solved. SUMMARY

[0004] Some embodiments of the present application aim to provide a method for retrieving vehicle types based on a large model, a storage medium, an electronic device and a product. The technical solution of the embodiments of the present application can improve the accuracy of vehicle type retrieval, is suitable for various vehicle type retrieval scenarios, and improves the user retrieval experience.

[0005] In a first aspect, some embodiments of the present application provide a method for retrieving vehicle types based on a large model, a storage medium, an electronic device and a product, comprising: identifying content information input by a user, and obtaining retrieval parameters of a vehicle type to be retrieved, wherein the retrieval parameters include a vehicle series, a vehicle brand or a vehicle alias corresponding to the vehicle series; retrieving a preset number of vehicle data from a vector database based on the retrieval parameters, wherein the vehicle data includes the vehicle series and the vehicle brand; and performing similarity analysis on the retrieval parameters and the vehicle data to determine a vehicle type retrieval result matched with the content information.

[0006] Some embodiments of the present application first identify the content information input by the user to obtain the retrieval parameters, then retrieve a preset number of vehicle data from the vector database based on the retrieval parameters, and finally perform similarity analysis on the retrieval parameters and the vehicle data to determine the vehicle type retrieval result. Some embodiments of the present application can improve the accuracy of vehicle type retrieval, are suitable for various vehicle type retrieval scenarios, meet the needs of users and businesses, and improve the user experience.

[0007] In some embodiments, the retrieving a preset number of vehicle data from the vector database according to the retrieval parameter comprises: obtaining a retrieval score between the retrieval parameter and each piece of vehicle data in the vector database; calculating a total retrieval score based on the retrieval score, a vehicle series similarity and a vehicle brand similarity, wherein the vehicle series similarity is a similarity value between a vehicle series in the retrieval parameter and a vehicle series in the vehicle data, and the vehicle brand similarity is a similarity value between a vehicle brand in the retrieval parameter and a vehicle brand in the vehicle data; and determining the preset number of vehicle data according to the total retrieval score.

[0008] Some embodiments of the present application determine a total retrieval score by combining a retrieval score between a retrieval parameter and each piece of vehicle data with a vehicle series similarity and a vehicle brand similarity, and determine a preset number of vehicle data meeting the requirements based on the total retrieval score, so as to realize accurate screening of vehicle data.

[0009] In some embodiments, the obtaining the retrieval score between the retrieval parameter and each piece of vehicle data in the vector database comprises: when the vehicle alias is included in the retrieval parameter, setting the retrieval score of the vehicle data containing the vehicle alias as a fixed value; and when the vehicle alias is not included in the retrieval parameter, taking a score value in a retrieval result between the retrieval parameter and each piece of vehicle data as the retrieval score.

[0010] Some embodiments of the present application determine a retrieval score by determining whether a vehicle alias is included in a retrieval parameter, so as to realize accurate division of retrieval data and accurate determination of the retrieval score.

[0011] In some embodiments, the calculating the total retrieval score based on the retrieval score, the vehicle series similarity and the vehicle brand similarity comprises: taking a difference value between the retrieval score and a preset value as a retrieval coefficient; and multiplying a weighted sum result of the vehicle series similarity and the vehicle brand similarity by the retrieval coefficient to obtain the total retrieval score.

[0012] Some embodiments of the present application determine a retrieval coefficient based on a preset value and a retrieval score, and then comprehensively calculate a total retrieval score based on the retrieval coefficient, a vehicle series similarity and a vehicle brand similarity, so as to realize accurate screening of vehicle data and preliminarily select vehicle data with high similarity.

[0013] In some embodiments, the similarity analysis on the search parameter and the vehicle data to determine the vehicle type search result matched with the content information comprises: obtaining a search set corresponding to the search parameter and a data set of each vehicle data in the vehicle data according to a splitting rule, wherein the splitting rule comprises: splitting Chinese characters individually and splitting continuous numbers or letters integrally; solving each similarity value between the search set and the data set of each vehicle data; and taking the vehicle data corresponding to the maximum value in all similarity values as the vehicle type search result.

[0014] Some embodiments of the present application obtain a search set and a data set through a splitting rule, and then determine a vehicle type search result through the relationship between the two, which is efficient and accurate.

[0015] In some embodiments, the solving of each similarity value between the search set and the data set of each vehicle data comprises: obtaining each intersection and each union between the search set and the data set of each vehicle data; and taking the ratio of each intersection and each union as each similarity value.

[0016] Some embodiments of the present application determine a similarity value through the intersection and union relationship between a search set and a data set, which provides a reliable reference for subsequent determination of an accurate vehicle type search result.

[0017] In some embodiments, the identification of the content information input by the user to obtain a search parameter of a vehicle type to be searched comprises: inputting the content information into a pre-trained large language model to obtain the search parameter.

[0018] Some embodiments of the present application improve the accuracy of search parameter identification through the identification of content information of a user by a large language model.

[0019] In a second aspect, some embodiments of the present application provide a device for searching a vehicle type based on a large model, comprising: an identification module configured to identify content information input by a user to obtain a search parameter of a vehicle type to be searched, wherein the search parameter comprises: a vehicle series, a vehicle brand, or a vehicle alias corresponding to the vehicle series; a search module configured to search a preset number of vehicle data from a vector database through the search parameter, wherein the vehicle data comprises: the vehicle series and the vehicle brand; and a vehicle type output module configured to perform similarity analysis on the search parameter and the vehicle data to determine a vehicle type search result matched with the content information.

[0020] In a third aspect, some embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, can implement the method according to any one of the embodiments of the first aspect.

[0021] In a fourth aspect, some embodiments of the present application provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method according to any one of the embodiments of the first aspect when running the program.

[0022] In a fifth aspect, some embodiments of the present application provide a computer program product, comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of the embodiments of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the following will briefly introduce the drawings needed to be used in some embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0024] Figure 1 System diagram for retrieving vehicle type based on large model provided by some embodiments of the present application; Figure 2 One of the method flowcharts for retrieving vehicle type based on large model provided by some embodiments of the present application; Figure 3 The second method flowchart for retrieving vehicle type based on large model provided by some embodiments of the present application; Figure 4 Device composition block diagram for retrieving vehicle type based on large model provided by some embodiments of the present application; Figure 5 Electronic device schematic diagram provided by some embodiments of the present application. DETAILED DESCRIPTION

[0025] The technical solutions of some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0026] It should be noted that: similar reference numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used for distinguishing description, and cannot be understood as indicating or implying relative importance.

[0027] The knowledge base in related technologies contains the required knowledge about brands and car series. Users can vaguely express their desired car requirements, and then use this to match the corresponding brands and car series in the knowledge base. However, this method of fuzzy keyword matching for car requirements has a low matching accuracy rate. Moreover, if the user's car requirements contain too many or too few words, the matching results are likely to be incorrect, failing to truly meet the user's actual needs and reducing the user experience.

[0028] In light of this, some embodiments of this application provide a method for retrieving vehicle types based on a large model. This method first identifies the content information entered by the user to obtain search parameters. A preset number of vehicle data items that initially match the search parameters are then determined based on the search parameters. Finally, a similarity analysis is performed between the search parameters and the vehicle data to select vehicle type search results. Some embodiments of this application can improve the accuracy of vehicle type retrieval, meet the actual needs and business requirements of users, and enhance the user experience.

[0029] The following is combined with Figure 1 The overall structure of the system for retrieving vehicle types based on large models provided by some embodiments of the present application is exemplified.

[0030] like Figure 1 As shown, some embodiments of the present application provide a system diagram for retrieving vehicle types based on a large model. The system may include a terminal 100 and a search server 200. A user may enter content information of the vehicle type to be searched on the terminal 100, which is then sent to the search server 200. Upon receiving the content information, the search server 200 first identifies it and determines search parameters. The search parameters are then used to retrieve a corresponding number of vehicle data items from a vector database. Finally, a similarity analysis is performed between the search parameters and the vehicle data to determine the final vehicle type search results.

[0031] In some embodiments of the present application, the terminal 100 may be a mobile terminal or a non-portable computer terminal, which is not specifically limited in the embodiments of the present application.

[0032] The following is combined with Figure 2 The implementation process of searching for vehicle types based on a large model and performed by the search server 200 is exemplarily described in some embodiments of the present application.

[0033] Please see the attached Figure 2 , Figure 2 A flowchart of a method for retrieving vehicle types based on a large model is provided for some embodiments of the present application. The method for retrieving vehicle types based on a large model may include: S210, identifying the content information input by the user to obtain a search parameter of a vehicle type to be searched, wherein the search parameter comprises a vehicle series, a vehicle brand, or an alias of the vehicle series corresponding to the vehicle series.

[0034] For example, in some embodiments of the present application, the content information can be in the form of text information or voice information. The search parameter is determined by feature extraction of the text information, or by text conversion of the voice information. The alias of the vehicle series is another name of the vehicle series; the vehicle brand can be referred to as the brand.

[0035] In some embodiments of the present application, S210 can comprise inputting the content information into a pre-trained large language model to obtain the search parameter.

[0036] For example, in some embodiments of the present application, the content information is input into the large language model together with a prompt input into the large language model, and the content information is identified by the large language model to output the search parameter. The large language model can be pre-trained using data in the vehicle type search scenario. It can be understood that, in addition to using the large language model to identify the content information, other trained general models or recognition algorithms can also be used for identification, and the embodiments of the present application are not limited thereto.

[0037] S220, retrieving a preset number of vehicle data from the vector database through the search parameter; wherein the vehicle data comprises the vehicle series and the vehicle brand.

[0038] For example, in some embodiments of the present application, a vector database is pre-constructed so that the vector database contains different vehicle series under various vehicle brands, and different aliases of the vehicle series. The vector database contains a vector file, which includes a vector corresponding to a string (e.g., vehicle series: brand + vehicle series) of the vehicle brand and the vehicle series of each vehicle data. The vehicle data meeting the requirements is searched in the vector database through the identified search parameter of the user. If neither the vehicle brand nor the vehicle series contained in the search parameter is in the vector database, an empty result is returned; if it is confirmed that the vehicle brand in the vector database has the vehicle series, the answer content query

vehicle series: vehicle series

vehicle series: brand + vehicle series

[0039] In some embodiments of the present application, S220 can include: S221, obtaining a search score between the search parameter and each piece of vehicle data in the vector database.

[0040] For example, in some embodiments of the present application, when searching in the vector database, the vehicle data corresponding to the vehicle series, brand and alias in the search parameter is outputted, and the search score between the search parameter and the vehicle data is also displayed. The search analysis can be used to represent the preliminary matching degree between the vehicle data and the search parameter.

[0041] In some embodiments of the present application, S221 can include: when the vehicle alias is included in the search parameter, setting the search score of the vehicle data containing the vehicle alias as a fixed value; when the vehicle alias is not included in the search parameter, setting the score value in the search result between the search parameter and each piece of vehicle data as the search score.

[0042] For example, in some embodiments of the present application, when the search parameter contains the vehicle alias, and the searched vehicle data also contains the vehicle alias, the search score is assigned a value of 0 (as a specific example of a fixed value). Before the assignment, the vehicle alias needs to be processed, i.e. the vehicle series and the vehicle alias are separated by a slash symbol. The vehicle series of a certain automobile brand is Xingyue, and the vehicle alias is Xinyue or Xinyue. The vehicle alias in the searched vehicle data is processed as Xingyue / Xinyue. When the search parameter does not contain the vehicle alias, the score value of the search output is the search score. It should be noted that the search score is less than a preset value. The preset value can be flexibly set according to actual conditions, such as 1.2.

[0043] S222, calculating a total search score based on the search score, a vehicle series similarity and a vehicle brand similarity, wherein the vehicle series similarity is a similarity value between the vehicle series in the search parameter and the vehicle series in the vehicle data, and the vehicle brand similarity is a similarity value between the vehicle brand in the search parameter and the vehicle brand in the vehicle data.

[0044] For example, in some embodiments of the present application, the similarity value between the search parameter and the vehicle series in each piece of vehicle data is calculated first to obtain the vehicle series similarity, and the similarity value between the vehicle brands is calculated to obtain the vehicle brand similarity. The similarity value calculation can implement a similarity calculation algorithm, such as a cosine algorithm, a Euclidean distance, etc. Through the search score, the vehicle series similarity and the vehicle brand similarity, the total search score between the search parameter and each piece of vehicle data is preliminarily determined.

[0045] In some embodiments of the present application, S222 can include: taking the difference between the search score and a preset value as a search coefficient; multiplying the result of weighted summation of the vehicle series similarity and the vehicle brand similarity by the search coefficient to obtain the search total score.

[0046] For example, in some embodiments of the present application, the search coefficient between the search parameter and each piece of vehicle data is calculated according to the following formula: search coefficient = M-search score, where M is a preset value, such as 1.2. Then, the vehicle series similarity and the vehicle brand similarity are assigned weight values, such as the weight value of the vehicle series similarity is x (such as x = 0.7) and the weight value of the vehicle brand similarity is y (such as y = 0.3); finally, the search total score is calculated according to the following formula: search total score = (vehicle series similarity x + vehicle brand similarity y). search coefficient.

[0047] S223 determines the preset number of vehicle data according to the search total score.

[0048] For example, in some embodiments of the present application, the search total scores are sorted from high to low, and the vehicle data with top 20 search total scores are selected; or, 20 pieces of vehicle data with search total scores exceeding a score threshold can also be selected; the embodiments of the present application are not limited specifically herein.

[0049] S230 performs similarity analysis on the search parameter and the vehicle data to determine a vehicle type search result matched with the content information.

[0050] For example, in some embodiments of the present application, similarity analysis is performed again on the search parameter and each piece of the above-mentioned 20 pieces of vehicle data to select vehicle data that can be used as the final vehicle type search result.

[0051] In some embodiments of the present application, S230 can include: obtaining a search set corresponding to the search parameter and a data set of each piece of vehicle data according to a splitting rule; wherein the splitting rule includes: splitting Chinese characters individually and splitting continuous numbers or letters integrally; solving each similarity value between the search set and the data set of each piece of vehicle data; and taking the vehicle data corresponding to the maximum value among all similarity values as the vehicle type search result.

[0052] For example, in some embodiments of the present application, the retrieval parameters and each piece of vehicle data are first split to obtain corresponding sets. For example, the retrieval parameters are: Geely Star Plus 02, the Chinese characters are split separately, and the letters are combined as a whole, i.e. the retrieval set is {“Ji” “Li” “Star” “Yue” “Plus” “02”}. The splitting method of each piece of vehicle data is consistent with the above rules, i.e. continuous letters or numbers are regarded as a whole combination. Finally, the similarity values between the sets are solved to obtain the similarity values between the retrieval set and the data set of each piece of vehicle data, and the vehicle data corresponding to the maximum value is selected as the final vehicle type retrieval result.

[0053] In some embodiments of the present application, the solving of each similarity value between the retrieval set and the data set of each piece of vehicle data comprises: obtaining each intersection and each union between the retrieval set and the data set of each piece of vehicle data; and taking the ratio of each intersection and each union as each similarity value.

[0054] For example, in some embodiments of the present application, the number of elements in the intersection and the union between the retrieval set and the data set of each piece of vehicle data is determined, and the similarity value = intersection / union (i.e. the ratio of the number of elements).

[0055] It can be understood that in another implementation, if the similarity value = union / intersection, the vehicle data corresponding to the minimum value in the similarity value is the final vehicle type retrieval result.

[0056] The specific process of retrieving the vehicle type based on the large model provided by some embodiments of the present application will be described below with reference to the accompanying drawings. Figure 3 The specific process of retrieving the vehicle type based on the large model provided by some embodiments of the present application will be described below with reference to the accompanying drawings.

[0057] Please refer to the accompanying drawings Figure 3 , Figure 3 A method flowchart for retrieving the vehicle type based on the large model provided by some embodiments of the present application.

[0058] The above process will be described below.

[0059] S310, obtaining the content information input by the user.

[0060] S320, inputting the content information into the pre-trained large language model to obtain the retrieval parameters.

[0061] S330, obtaining the retrieval scores between the retrieval parameters and each piece of vehicle data in the vector database.

[0062] S340, calculating the total retrieval score based on the retrieval score, the vehicle series similarity and the vehicle brand similarity.

[0063] S350, determining the vehicle data of the preset number of vehicle data through the total retrieval score.

[0064] S360, according to the splitting rule, obtaining a search set corresponding to the search parameter, and obtaining a data set of each vehicle data in the vehicle data.

[0065] S370, solving each similarity value between the search set and the data set of each vehicle data.

[0066] S380, taking the vehicle data corresponding to the maximum value in all similarity values as the vehicle type search result.

[0067] It should be noted that the specific implementation process of S310-S380 can refer to the method embodiments provided in the foregoing description, and the detailed description is appropriately omitted here to avoid repetition.

[0068] Please refer to Figure 4 , Figure 4 The composition block diagram of the device for retrieving vehicle type based on large model provided by some embodiments of the present application is shown. It should be understood that the device for retrieving vehicle type based on large model corresponds to the above-mentioned method embodiments, and can perform each step involved in the above-mentioned method embodiments. The specific functions of the device for retrieving vehicle type based on large model can be referred to the description in the foregoing description, and the detailed description is appropriately omitted here to avoid repetition.

[0069] Figure 4 The device for retrieving vehicle type based on large model comprises at least one software function module which can be stored in the form of software or firmware in the memory or solidified in the device for retrieving vehicle type based on large model. The device for retrieving vehicle type based on large model comprises: an identification module 410, configured to identify the content information input by a user and obtain a search parameter of a vehicle type to be searched, wherein the search parameter comprises a vehicle series, a vehicle brand, or a vehicle alias corresponding to the vehicle series; a search module 420, configured to search a preset number of vehicle data from a vector database through the search parameter; wherein the vehicle data comprises the vehicle series and the vehicle brand; and a vehicle type output module 430, configured to perform similarity analysis on the search parameter and the vehicle data, and determine a vehicle type search result matched with the content information.

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the foregoing method, and will not be described in more detail here.

[0071] Some embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the operations of the method corresponding to any of the above-mentioned embodiments provided by the above-mentioned embodiments.

[0072] Some embodiments of the present application further provide a computer program product, which comprises a computer program, wherein the computer program is used to perform the operations of the method according to any of the above embodiments when executed by a processor.

[0073] As shown in Figure 5 Some embodiments of the present application provide an electronic device 500, which comprises a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520, wherein the processor 520 reads the program from the memory 510 through a bus 530 and performs the program to implement the method according to any of the above embodiments.

[0074] The processor 520 can process digital signals and can include various computing structures, such as a complex instruction set computer structure, a reduced instruction set computer structure, or a structure implementing a combination of multiple instruction sets. In some examples, the processor 520 can be a microprocessor.

[0075] The memory 510 can be used to store instructions executed by the processor 520 or data related to the execution of the instructions. The instructions and / or data can include code for implementing some or all of the functions of one or more modules described in the embodiments of the present application. The processor 520 of the embodiments of the present disclosure can be used to execute the instructions in the memory 510 to implement the method shown above. The memory 510 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memories well known to those skilled in the art.

[0076] The above only describes the embodiments of the present application and is not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0077] The above only describes the embodiments of the present application and is not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0078] It is to be noted that, as used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component" can include a combination of two or more components. Additionally, the terms "comprise," "comprises," and "comprising," or any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Furthermore, unless otherwise indicated herein, the terms "first," "second," "third," etc., are used herein merely as labels, and are not intended to impose ordinal import.

Claims

1. A method for retrieving a vehicle type based on a large model, characterized by, The method comprises: identifying content information input by a user to obtain a search parameter of a vehicle type to be searched, wherein the search parameter comprises a vehicle series, a vehicle brand, or a vehicle alias corresponding to the vehicle series; retrieving a preset number of vehicle data from a vector database based on the search parameter, wherein the vehicle data comprises the vehicle series and the vehicle brand; performing similarity analysis on the search parameter and the vehicle data to determine a vehicle type search result matched with the content information.

2. The method of claim 1, wherein, The retrieving a preset number of vehicle data from a vector database based on the search parameter comprises: obtaining a search score between the search parameter and each piece of vehicle data in the vector database; calculating a total search score based on the search score, a vehicle series similarity, and a vehicle brand similarity, wherein the vehicle series similarity is a similarity value between the vehicle series in the search parameter and the vehicle series in the vehicle data, and the vehicle brand similarity is a similarity value between the vehicle brand in the search parameter and the vehicle brand in the vehicle data; determining the preset number of vehicle data based on the total search score.

3. The method of claim 2, wherein, The obtaining a search score between the search parameter and each piece of vehicle data in the vector database comprises: when the search parameter includes the vehicle alias, setting the search score of the vehicle data containing the vehicle alias as a fixed value; when the search parameter does not include the vehicle alias, taking a score value in a search result between the search parameter and each piece of vehicle data as the search score.

4. The method of claim 2 or 3, wherein, The calculating a total search score based on the search score, a vehicle series similarity, and a vehicle brand similarity comprises: taking a difference value between the search score and a preset value as a search coefficient; multiplying a weighted sum result of the vehicle series similarity and the vehicle brand similarity by the search coefficient to obtain the total search score.

5. The method of any one of claims 1-3, wherein, The performing similarity analysis on the search parameter and the vehicle data to determine a vehicle type search result matched with the content information comprises: obtaining a search set corresponding to the search parameter and obtaining a data set of each piece of vehicle data in the vehicle data according to a splitting rule, wherein the splitting rule comprises separately splitting Chinese characters and integrally splitting continuous numbers or letters; solving each similarity value between the search set and the data set of each piece of vehicle data; taking vehicle data corresponding to a maximum value in all similarity values as the vehicle type search result.

6. The method of claim 5, wherein, The solving each similarity value between the search set and the data set of each piece of vehicle data comprises: obtaining each intersection and each union between the search set and the data set of each piece of vehicle data; taking a ratio of each intersection to each union as each similarity value.

7. The method of any one of claims 1-3, wherein, The identifying content information input by a user to obtain a search parameter of a vehicle type to be searched comprises: inputting the content information into a pre-trained large language model to obtain the search parameter.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the computer program is run by a processor to execute the method of any one of claims 1-7.

9. An electronic device, comprising: A computer program product comprising a computer program, wherein the computer program, when executed by a processor, performs the method according to any one of claims 1-7.

10. A computer program product, characterized in that The computer program product comprises a computer program, wherein the computer program, when executed by a processor, performs the method according to any one of claims 1-7.

Images