Data arrangement method and device

Abstract

The invention discloses a data arrangement method and device, and relates to the technical field of vehicles, and the method comprises the following steps: obtaining vehicle interior data corresponding to at least two vehicles, the vehicle interior data comprising interior parameters describing vehicle interior from at least two dimensions; performing clustering analysis on the interior trim parameters in the vehicle interior trim data corresponding to the at least two types of vehicles by taking the interior trim parameters as clustering granularity to obtain clustering results corresponding to the at least two interior trim parameters; and on the basis of a preset clustering style requirement, clustering clusters in the at least two clustering results are integrated to obtain an associated data set, and the clustering clusters meeting the same clustering style requirement in the clustering results corresponding to the at least two interior trim parameters are integrated in the same associated data subset. The vehicle interior trim data can be automatically classified and integrated, the rule data set is directly generated, and the data arrangement efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle technology, and in particular to a data sorting method and device. Background Art

[0002] Car interior refers to the decoration and structure inside the car. It is not only related to the beauty and comfort of the car, but also brings a unique experience to the driver and passengers. Car interior design focuses on the use of various design elements, including the reasonable combination of color, material, shape and other elements to enhance the overall quality and value of the car.

[0003] In the related technologies, the search, organization and analysis of design elements are mainly carried out manually, and designers need to manually complete data integration and design output.

[0004] However, the above method has a large overall workload, and designers need to spend a lot of time to organize irregular data, which is a heavy burden and leads to low design efficiency. Summary of the invention

[0005] The embodiment of the present application provides a data sorting method and device, which can automatically classify and integrate vehicle interior data, directly generate a rule data set, and improve data sorting efficiency. The technical solution is as follows:

[0006] In one aspect, a data sorting method is provided, the method comprising:

[0007] Acquire vehicle interior data corresponding to at least two vehicles respectively, wherein the vehicle interior data includes interior parameters describing the vehicle interior from at least two dimensions;

[0008] Taking the interior parameters as the clustering granularity, cluster analysis is performed on the interior parameters in the vehicle interior data corresponding to the at least two vehicles, to obtain clustering results corresponding to the at least two interior parameters, wherein the target interior parameters are clustered to obtain a target clustering result, and the i-th cluster in the target clustering result includes the target interior parameters corresponding to the i-th clustering style, where i is a positive integer;

[0009] Based on the preset clustering style requirements, the clustering clusters in the at least two clustering results are integrated to obtain a related data set, wherein, in the clustering results corresponding to the at least two interior parameters, the clustering clusters that meet the same clustering style requirements are integrated into the same related data subset.

[0010] In another aspect, a data sorting device is provided, the device comprising:

[0011] An acquisition module, used to acquire vehicle interior data corresponding to at least two vehicles respectively, wherein the vehicle interior data includes interior parameters describing the vehicle interior from at least two dimensions;

[0012] A clustering module, configured to perform cluster analysis on the interior parameters in the vehicle interior data corresponding to the at least two vehicles respectively, with the interior parameters as the clustering granularity, to obtain clustering results corresponding to the at least two interior parameters respectively, wherein the target interior parameters are clustered to obtain a target clustering result, and the i-th cluster in the target clustering result includes the target interior parameters corresponding to the i-th clustering style, where i is a positive integer;

[0013] An association module is used to integrate the clustering clusters in the at least two clustering results based on a preset clustering style requirement to obtain an associated data set, wherein, in the clustering results corresponding to the at least two interior parameters, the clustering clusters that meet the same clustering style requirement are integrated into the same associated data subset.

[0014] In an optional embodiment, the acquisition module is also used to acquire a vehicle interior material library, which contains candidate data for describing vehicle interiors, and the candidate data meets preset classification processing requirements; the candidate data is classified and processed to obtain the vehicle interior data corresponding to the at least two vehicles respectively.

[0015] In an optional embodiment, the acquisition module is further used to identify the candidate data to obtain vehicle model data, wherein the vehicle model data is used to indicate vehicle models corresponding to the at least two vehicles respectively; the candidate data is divided based on the vehicle model data to obtain the vehicle interior data corresponding to the at least two vehicles respectively, and the vehicle interior data meets the preset format requirements.

[0016] In an optional embodiment, the clustering module is also used to obtain at least two clustering styles corresponding to the j-th interior parameter among the at least two interior parameters, the at least two clustering styles being used to indicate a method of performing cluster analysis on the j-th interior parameter, and j being a positive integer; analyzing the at least two clustering styles to obtain at least two clustering centers corresponding to the at least two clustering styles respectively; taking the j-th interior parameter as the clustering granularity, clustering analysis is performed on the j-th interior parameter in the vehicle interior data corresponding to the at least two vehicles respectively based on the at least two clustering centers to obtain a j-th clustering result corresponding to the j-th interior parameter; wherein the j-th clustering result includes cluster clusters corresponding to the at least two clustering styles respectively.

[0017] In an optional embodiment, the preset clustering style requirement includes a first clustering style;

[0018] The association module is further configured to integrate the clusters matching the first clustering style in the at least two clustering results to obtain a first associated data subset, wherein the first associated data subset is an associated data subset in the associated data set.

[0019] In an optional embodiment, the device further comprises:

[0020] A search module is used to receive search conditions, where the search conditions are used to search for a subset of associated data from the associated data set; perform a matching analysis based on the search conditions and the clustering style requirements to obtain a matching result; and obtain a target associated data subset corresponding to the search conditions from the associated data set based on the matching result.

[0021] In an optional embodiment, the device further comprises:

[0022] a modal conversion module, configured to perform modal conversion on the at least two modal data to obtain first modal data in response to at least two modal data included in the vehicle interior data corresponding to the at least two vehicles, wherein the at least two modal data represent interior parameters in the vehicle interior data in at least two modalities, and the first modal data is used to represent the interior parameters in the vehicle interior data in the first modality;

[0023] The clustering module is further used to perform cluster analysis on the interior parameters in the first modal data with the interior parameters as the clustering granularity, and obtain clustering results corresponding to at least two interior parameters respectively.

[0024] In an optional embodiment, the association module is further used to integrate the clustering clusters in the at least two clustering results based on a preset clustering style requirement to obtain an integrated associated data subset, wherein the data in the integrated associated data subset is the first modality;

[0025] The modality conversion module is further used to perform restoration processing on the integrated associated data subset to obtain the associated data set; the restoration processing refers to converting the data in the integrated associated data subset from the first modality to at least two modalities indicated by the at least two modality data.

[0026] In an optional embodiment, the device further comprises:

[0027] An update module is configured to perform a coincidence degree analysis on the associated data subsets in the associated dataset to obtain a coincidence result of the associated data subsets, where the coincidence result is used to indicate the similarity between the associated data subsets; in response to the coincidence result indicating that the similarity between a first associated data subset and a second associated data subset in the associated dataset meets a preset merging requirement, analyze the overlapping part of the first associated data subset and the second associated data subset to obtain an overlapping clustering style; generate a third associated data subset based on the overlapping part of the first associated data subset and the second associated data subset, where the third associated data subset corresponds to the overlapping clustering style; and add the third associated data subset to the associated dataset to obtain an updated associated dataset.

[0028] On the other hand, a computer device is provided, which includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the data sorting method as described in any one of the embodiments of the present application above.

[0029] On the other hand, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the data sorting method as described in any one of the embodiments of the present application above.

[0030] On the other hand, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the data sorting method as described in any one of the above embodiments.

[0031] The beneficial effects brought by the technical solution provided by the embodiments of the present application at least include:

[0032] By performing clustering analysis on vehicle interior data, each interior parameter can be divided into multiple clustering clusters of different styles based on different clustering styles. Based on the association relationship between the clustering clusters, the clustering cluster data is integrated into an associated dataset, realizing the automatic collection, analysis and sorting of interior data. Compared with the related art in which data is sorted manually, it can improve the data sorting efficiency, facilitate the user to directly apply the standardized dataset, and further improve the efficiency of material indexing when designing the vehicle interior. By using a computer to obtain and integrate a large amount of data, omissions can be avoided, the integrity and coverage of the integrated data can be improved, and the classification of interior parameters can be made clearer. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 is a schematic diagram of a data sorting system provided by an exemplary embodiment of the present application;

[0035] Figure 2 is a schematic diagram of a process of analyzing and organizing vehicle interior data provided by an exemplary embodiment of the present application;

[0036] Figure 3 is a flow chart of a data sorting method provided by an exemplary embodiment of the present application;

[0037] Figure 4 is a structural block diagram of a data sorting device provided by an exemplary embodiment of the present application;

[0038] Figure 5 is a structural block diagram of a data sorting device provided by another exemplary embodiment of the present application;

[0039] Figure 6 It is a structural block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0040] 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.

[0041] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0042] It should be noted that the information and data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0043] Car interior refers to the decoration and structure of the car's interior. The appearance and structure of the car's interior are related to the overall aesthetics of the vehicle and the driving comfort of the people inside the car.

[0044] In the process of car interior design, it is very important for designers to use various interior parameters reasonably. The scope of interior parameters is wide, including color, material, size, shape, process type, etc. Different interior parameters interact and coordinate with each other to jointly construct the overall design of the car interior.

[0045] In the related technologies, the search, sorting and analysis of interior parameters mainly rely on manual methods. Designers need to manually collect, filter and sort massive amounts of data from different sources. Moreover, data from different sources often have different formats, contents and focuses. Designers need to spend a lot of time and energy to standardize the data format and integrate them together to complete the design output work. In other words, the above manual operation method has a huge workload. Due to the complexity and irregularity of the data, designers need to handle various complex tasks, which is a heavy burden and has low work efficiency.

[0046] To sum up, how to complete the interior parameter data collation process through a more efficient and reasonable method to improve the quality and efficiency of automobile interior design is an urgent problem to be solved.

[0047] First, a brief introduction is given to the terms involved in the embodiments of this application:

[0048] Big data technology: is a comprehensive technical means to process and analyze large-scale and complex data sets. It extracts valuable information and knowledge from massive data through a series of advanced technologies and methods to provide decision support for enterprises and organizations. Big data technology not only focuses on data collection, but also on data storage, processing, analysis and visualization, so as to help users gain insight into the laws and trends behind the data.

[0049] In the embodiment of the present application, big data technology is used to obtain vehicle interior data corresponding to at least two vehicles from various network platforms / databases, and texts, pictures, data, etc. related to the car interior are collected and organized, laying the foundation for data organization and construction of a knowledge graph.

[0050] Artificial Intelligence (AI) Technology: Artificial Intelligence is a very broad science, including robotics, speech recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc. Artificial Intelligence technology aims to give computer systems human-like intelligence capabilities, enabling them to perceive the environment, learn knowledge, make inferences and decisions, and interact with humans through natural language.

[0051] In the embodiment of the present application, artificial intelligence technology is used to analyze and process vehicle interior data, classify vehicle interior data, extract and analyze interior parameters (such as shape, color, material, size, etc.), and provide a basis for subsequent clustering analysis to generate related data sets.

[0052] That is, a large amount of data related to vehicle interiors is obtained through big data technology, and the above data is classified and processed through artificial intelligence technology to obtain data for cluster analysis. After the cluster analysis is completed, multiple cluster cluster data are formed, and specified association relationships are added between the multiple cluster cluster data to form an associated data set, completing the sorting of vehicle interior data. The generated associated data set can be regarded as a database, in which multiple associated data subsets are used to indicate interior parameters of different styles. Entering keywords in the database can directly index the corresponding associated data subset, which is convenient for designers to obtain interior parameters of different styles as a reference and improve the efficiency of vehicle interior design.

[0053] Next, the data sorting system involved in the embodiments of the present application is described. For illustration, please refer to Figure 1 The system involves a terminal 100, in which a graph analysis tool Graphistry is deployed.

[0054] Graphistry is a GPU (Graphics Processing Unit) accelerated graph visual analysis platform that can visualize large graphs in the browser and supports GPU rendering of 100,000 to 1,000,000 nodes and relationships.

[0055] The vehicle interior data is loaded into Graphistry. The vehicle interior data includes interior parameters describing the vehicle interior from at least two dimensions. The vehicle interior data contains text modal data and image modal data. The Graphistry tool can be used to effectively analyze and extract the interior parameters represented by image modal data.

[0056] The data sorting process after the above-mentioned import step includes the following steps.

[0057] 1. Collect vehicle interior data: Use big data technology to collect and organize text, images, etc. related to car interiors in the network database; vehicle interior data contains a variety of interior parameters, such as color, size, shape, etc.

[0058] 2. Data analysis and processing: Use artificial intelligence technology to classify and process the collected vehicle interior data, extract and analyze parameters such as shape, color, material, and size, and obtain interior parameters in the vehicle interior data.

[0059] 3. Cluster analysis: Cluster analysis is performed on interior parameters in different clustering styles to generate multiple clusters. The clusters are integrated based on the specified association relationships to obtain associated data subsets and finally form an associated data set.

[0060] 4. Test analysis: Based on the associated data set, input the keywords of the relevant benchmark. The keywords are used to indicate the clustering style. The interior parameters that meet the clustering style indicated by the keywords are filtered and output from the associated data set, and the associated data subset corresponding to the interior parameters is returned.

[0061] In some embodiments, a knowledge graph is generated based on the above-mentioned associated data set through the Graphistry tool. The knowledge graph can structurally display the types and examples of interior parameters, so that designers can obtain different interior parameters as references. The vehicle interior data is updated in real time according to the keywords entered by the user and the returned results, and cluster analysis is performed again to obtain a more accurate associated data set, so that the data results obtained by dividing based on clustering style are more in line with the user's search intention.

[0062] The terminal 100 may be a mobile phone, a tablet computer, a desktop computer, a portable laptop computer, a smart TV, a vehicle-mounted terminal, a smart home device, or other terminal devices in various forms, which is not limited in the embodiments of the present application.

[0063] In some embodiments, the above process may be executed by the terminal 100, or by the server, or by both the terminal 100 and the server.

[0064] The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. In some embodiments, the above servers can also be implemented as nodes in the blockchain system.

[0065] Indicatively, Figure 2 As shown, Figure 2 It is a schematic diagram of the process of analyzing and organizing vehicle interior data.

[0066] The vehicle interior data 200 corresponding to at least two vehicles are obtained, wherein the vehicle interior data 200 includes image modal content 201 and text modal content 202 , and the above two modal contents are used to represent various interior parameters 210 in the vehicle interior data 200 .

[0067] Analyze the vehicle interior data 200 and extract the interior parameters 210 therein, such as parameters of shape, color, material, process, size, etc.

[0068] In this application, the specific value of each interior parameter 210 is called an element. For example, if one of the interior parameters 210 is color, and there are 20 specific values (such as red, blue, yellow, etc.) of this type of interior parameter 210 in the vehicle interior data 200, then when the interior parameter 210 is color, it contains 20 elements.

[0069] Obtain different clustering styles to perform clustering analysis on the interior parameters 210, and obtain the clustering analysis result. The clustering analysis result contains at least two clustering clusters corresponding to each interior parameter 210 respectively. The number of at least two clustering clusters and the elements contained in the clustering clusters both correspond to the above-mentioned clustering styles.

[0070] Based on the clustering style, add a preset association relationship to the clustering analysis result to generate an associated data set 220.

[0071] Input keywords (obtained based on the clustering style) into the associated data set 220, screen the data that meets the keywords and display the elements therein.

[0072] In summary, by performing clustering analysis on the vehicle interior data, each interior parameter can be divided into clustering clusters of multiple styles based on different clustering styles, and the clustering cluster data can be integrated into an associated data set based on the association relationship between the clustering clusters, realizing the automatic collection, analysis, and collation of interior data.

[0073] Combined with the above noun introduction and application scenarios, the data collation method provided in this application is described. This method can be executed by a server or a terminal, or jointly executed by a server and a terminal. In the embodiments of this application, an example in which this method is executed by a terminal is used for description, as Figure 3 shown, Figure 3 is a flowchart of the data collation method provided by an exemplary embodiment of this application. This method includes the following steps.

[0074] Step 310, obtain the vehicle interior data corresponding to at least two vehicles respectively.

[0075] Among them, the vehicle interior data includes interior parameters that describe the vehicle interior from at least two dimensions. That is, the interior parameters in the vehicle interior data describe the external features of the vehicle interior from different aspects. For example, the interior parameters include parameters such as the color and texture of the vehicle interior.

[0076] Vehicle interior refers to the decoration and facilities inside the vehicle, which are in direct contact with the passengers and provide driving services. For example, the types of vehicle interior include but are not limited to vehicle seats, vehicle center console, vehicle interior lighting equipment, vehicle sound insulation and noise reduction materials, vehicle safety settings, etc.

[0077] Vehicle interior data is data obtained from at least one channel such as vehicle manufacturers, automotive media, online data platforms, vehicle-related industry reports, and vehicle offline sales stores, and is used to describe the interior appearance of different models of vehicles.

[0078] The vehicle interior data contains data of at least one modality, such as text, image, audio, video, animation and other modalities, which can display and describe the vehicle interior through at least one information representation form, so that users can clearly understand the structure and appearance of the vehicle interior.

[0079] The vehicle interior data represents the interior parameters through at least one modal data. Exemplarily, one of the interior parameters is the color of the vehicle interior, and the interior parameter includes three elements (red, yellow, and green). The vehicle interior data represents the specific value of the interior parameter through text modal data and image modal data. The text modal data describes the specific color type of the interior parameter in text form, including three colors: red, yellow, and green. The image modal data includes an image of the vehicle interior with the appearance of the above three elements.

[0080] The richness of interior parameters and the way they are combined affect the appearance and comfort of the vehicle interior.

[0081] Exemplarily, the interior parameters of the vehicle interior include but are not limited to at least two of the following.

[0082] 1. Common interior parameters: refers to parameters that are commonly found in most vehicle interiors and have similar characteristics, functions and design standards. For example, interior parameters such as size, color, shape, texture, glossiness, etc. are suitable for describing most vehicle interiors.

[0083] 2. Personalized interior parameters: Compared with general interior parameters, they are unique and differentiated interior parameters designed to meet the special needs of designated users. For example, there is a personalized interior in the vehicle: the ambient light with broadcasting function, the tone of the broadcast is the personalized interior parameter of the vehicle interior, and the parameter values ​​include the following: male voice, female voice, neutral voice, children's voice, etc.

[0084] That is, the vehicle interior data corresponding to at least two vehicles respectively obtained include common interior parameters. In some embodiments, the vehicle interior data also include personalized interior parameters.

[0085] Exemplarily, the following is an example of how to obtain vehicle interior data.

[0086] Optionally, a vehicle interior material library is obtained, wherein the vehicle interior material library contains candidate data describing the vehicle interior, and the candidate data meets preset classification processing requirements.

[0087] The preset classification processing requirement means that the number of candidate data reaches a preset first threshold, or the number of vehicle models corresponding to the vehicle interiors described by the candidate data reaches a preset second threshold. The first threshold and the second threshold are positive integers greater than or equal to 2.

[0088] The candidate data in the vehicle interior material library can be data obtained from at least one channel such as vehicle manufacturers, automotive media, network data platforms, vehicle-related industry reports, and vehicle offline sales stores. For example, by using big data technology to collect candidate data in the vehicle interior material library from the Internet platform, it is possible to automatically collect materials and provide a basis for subsequent data sorting. There is no need for users to manually collect data from the Internet platform one by one, which improves the degree of automation and data sorting efficiency.

[0089] In some embodiments, the candidate data contains more content, and in addition to the data describing the vehicle interior, it may contain other content related to the vehicle field, so the format of the vehicle interior data needs to be standardized.

[0090] Optionally, the candidate data are classified to obtain vehicle interior data corresponding to at least two vehicles.

[0091] The candidate data are classified and processed through artificial intelligence technology, the content irrelevant to the vehicle interior in the candidate data is eliminated, and the candidate data are classified and organized according to preset format requirements to obtain vehicle interior data corresponding to at least two vehicles.

[0092] Exemplarily, the candidate data is identified to obtain vehicle model data, where the vehicle model data is used to indicate the vehicle models / styles corresponding to at least two vehicles.

[0093] The candidate data are divided based on the vehicle model data to obtain vehicle interior data corresponding to at least two vehicles, and the vehicle interior data meets the preset format requirements.

[0094] The preset format requirement is to classify candidate data belonging to the same model of vehicle into the same piece of data, filter duplicate content, merge different content, and obtain the vehicle interior data of the model of vehicle.

[0095] For example, the number of candidate data obtained is 100, and the vehicle model data obtained by identifying the candidate data includes 20 vehicle models. That is, the 100 candidate data describe the vehicle interiors of 20 vehicles.

[0096] Taking the first vehicle whose model is A as an example, there are 4 pieces of data in the candidate data for describing the first vehicle.

[0097] Candidate data 1 includes the following interior parameters: size; candidate data 2 includes the following interior parameters: size and color; candidate data 3 includes the following interior parameters: size, shape and material; candidate data 4 includes the following interior parameters: craftsmanship and glossiness.

[0098] Then, after classification, the vehicle interior data corresponding to the first vehicle of model A includes the following interior parameters: size, color, shape, material, craftsmanship, and glossiness.

[0099] Step 320 , using the interior parameters as clustering granularity, performs cluster analysis on the interior parameters in the vehicle interior data corresponding to at least two vehicles, and obtains clustering results corresponding to at least two interior parameters.

[0100] The target interior parameters are clustered to obtain a target clustering result, and the i-th cluster in the target clustering result includes the target interior parameters corresponding to the i-th clustering style, where i is a positive integer.

[0101] Among them, clustering style refers to the benchmark for clustering analysis of interior parameters, which is used to indicate the goal and basis for designing vehicle interiors. For example, different styling styles (tough style, business style, cute style), different brands, and different models (sedans, sports vehicles, multi-purpose vehicles) can all be used as clustering styles.

[0102] That is, when performing cluster analysis, each interior parameter is clustered based on at least two specified clustering styles to obtain a cluster cluster in which each interior parameter complies with at least two clustering styles.

[0103] In some embodiments, if there are some elements in the interior parameters that have a low degree of match with each clustering style, the clustering style can be re-determined based on the clustering results and cluster analysis can be performed again to obtain a more accurate clustering result that is more consistent with the type of interior parameters, so as to improve the classification results of the interior parameters and accurately summarize the clustering style to which the interior parameters belong.

[0104] Optionally, for the j-th interior parameter among the at least two interior parameters, at least two clustering styles corresponding to the j-th interior parameter are obtained, and the at least two clustering styles are used to indicate a method of performing cluster analysis on the j-th interior parameter, and j is a positive integer.

[0105] The at least two clustering styles are analyzed to obtain at least two clustering centers corresponding to the at least two clustering styles respectively.

[0106] Exemplarily, at least two clustering styles are analyzed and text content for expressing the at least two clustering styles is obtained, and the text content includes at least one of the following contents.

[0107] (1) Text that introduces the clustering style;

[0108] For example, one of the clustering styles is business style, and the text content is as follows: with the core of meeting the needs of business travel, it has the characteristics of comfortable driving, advanced technology, simple and elegant appearance, etc.

[0109] (2) the expression of interior parameters that match the cluster style;

[0110] For example, one of the cluster styles is business style, and the text content includes content corresponding to color interior parameters: the color has the characteristics of low-key and steady (such as black, white, and gray), warm and comfortable (such as dark brown and dark blue), etc.

[0111] Exemplarily, feature extraction is performed on the text content corresponding to the at least one clustering style, a feature representation corresponding to the text content is constructed, and a cluster center corresponding to the at least one clustering style is obtained.

[0112] That is, after analyzing and extracting the features of the clustering style, it is mapped to a point in the feature representation space, and the obtained cluster center is expressed as an n-dimensional coordinate, where n is a positive integer.

[0113] Optionally, taking the jth interior parameter as the clustering granularity, a cluster analysis is performed on the jth interior parameter in the vehicle interior data corresponding to at least two vehicles respectively based on at least two cluster centers to obtain a jth clustering result corresponding to the jth interior parameter.

[0114] The j-th clustering result includes clusters corresponding to at least two clustering styles.

[0115] Exemplarily, feature extraction is performed on each element in the j-th interior parameter to obtain the element feature representation corresponding to each element. The distance / similarity between each element feature representation and at least one cluster center is calculated, and each element is assigned to a different cluster based on the distance / similarity to obtain the j-th clustering result.

[0116] The features of each element in the j-th interior parameter are extracted in the same way and mapped into the same feature representation space. The obtained element feature representation is also expressed as an n-dimensional coordinate with the same data format as the cluster center.

[0117] The distance between the element feature representation and the cluster center (such as Euclidean distance or Manhattan distance) is calculated by each digit in the n-dimensional coordinate to determine the cluster to which each element belongs.

[0118] For example, based on the three clustering styles, cluster analysis is performed on 100 elements in the jth interior parameters. Elements with serial numbers 1 to 10 and 20 to 30 belong to cluster 1 corresponding to cluster style 1, elements with serial numbers 11 to 19 and 60 to 100 belong to cluster 2 corresponding to cluster style 2, and elements with serial numbers 31 to 59 belong to cluster 3 corresponding to cluster style 3. The jth clustering result includes cluster 1, cluster 2, and cluster 3.

[0119] Optionally, when performing cluster analysis on interior parameters, the following two clustering methods are included.

[0120] (1) Cluster analysis is performed on the interior parameters based on at least two clustering styles at the same time, and cluster clusters corresponding to each clustering style are obtained at one time.

[0121] For example, there are three clustering styles (business style, cute style, simple style), and the vehicle interior data contains three interior parameters (color, size, material) used to describe the dashboard interior. Each interior parameter contains multiple specific values. For example, the color interior parameter contains the following specific values: red, blue, yellow, etc. In the following, each specific value of the interior parameter is referred to as an element.

[0122] For the color interior parameters, cluster analysis is performed on all the elements of the color interior parameters based on the three clustering styles, and the elements of the color interior parameters are divided into three clusters, which correspond to the three clustering styles one by one.

[0123] The above process is performed on all elements included in the size interior parameters and the material interior parameters, and a total of 3*3=9 clusters are obtained.

[0124] (2) Cluster analysis is performed on the interior parameters in turn based on at least two clustering styles, and only one clustering style is used to obtain cluster clusters in each cluster analysis.

[0125] For example, there are three clustering styles (business style, cute style, simple style), and the vehicle interior data contains three interior parameters (color, size, material) used to describe the dashboard interior. Each interior parameter contains multiple specific values. For example, the color interior parameter contains the following specific values: red, blue, yellow, etc. In the following, each specific value of the interior parameter is referred to as an element.

[0126] For the color interior parameters, we first perform a cluster analysis on all the elements in the color interior parameters based on the business style, and obtain a cluster that conforms to the business style from the color interior parameters; then, we perform a cluster analysis on all the elements in the color interior parameters based on the cute style, and obtain a cluster that conforms to the cute style from the color interior parameters; finally, we perform a cluster analysis on all the elements in the color interior parameters based on the simple style, and obtain a cluster that conforms to the simple style from the color interior parameters.

[0127] The above process is performed on all elements included in the size interior parameters and the material interior parameters, and a total of 3*3=9 clusters are obtained.

[0128] With respect to the above clustering method (1), when clustering analysis is performed on the same type of interior parameters based on multiple clustering styles, the cluster to which each element belongs is determined by calculating the distances between the element feature representation of each element and multiple clustering centers. In some embodiments, there may be an element for which the distances between the element feature representation of the element and at least two clustering centers are calculated, and these distances meet the preset distance requirements (for example, the distances are the same, or the difference between the distances does not exceed a preset threshold). In this case, it is considered that the element belongs to the clusters corresponding to at least two clustering centers at the same time, that is, the element can appear in the clusters corresponding to at least two clustering styles / centers at the same time.

[0129] For the above clustering method (2), when clustering analysis is performed on the same type of interior parameters based on each clustering style, all elements in the interior parameters are performed in turn, so the same element can appear in clusters corresponding to multiple clustering styles at the same time.

[0130] In summary, there may be overlapping elements between clusters. For example, in interior parameter A, there are clusters a and b that belong to two clustering styles at the same time.

[0131] Step 330 : Based on a preset clustering style requirement, clusters in at least two clustering results are integrated to obtain a related data set.

[0132] Among them, in the clustering results corresponding to at least two interior parameters, clusters that meet the same clustering style requirements are integrated into the same associated data subset.

[0133] Exemplarily, the preset clustering style requirement refers to the existence of an association relationship between clusters clustered based on the same clustering style.

[0134] For example, cluster analysis is performed on two types of interior parameters (the first type and the second type) based on three clustering styles (A, B, and C), and the obtained clustering results include three clusters of the first type of interior parameters and three clusters of the second type of interior parameters.

[0135] The preset clustering style requirement means that there is a correlation between the clustering cluster a1 obtained by clustering the first type of interior parameters based on the clustering style A and the clustering cluster a2 obtained by clustering the second type of interior parameters based on the clustering style A.

[0136] The association relationship refers to the search association between the interior parameters within the cluster. When the user searches for one type of interior parameter based on a certain cluster style, other types of interior parameters of the same cluster style can be obtained at the same time based on the association relationship.

[0137] Exemplarily, the preset clustering style requirements include a first clustering style. For the first clustering style, clusters matching the first clustering style in at least two clustering results are integrated to obtain a first associated data subset, and an associated data set is obtained based on the first associated data subset.

[0138] The first associated data subset contains all interior parameters in the clusters matching the first cluster style. That is, the associated data subset is data obtained by merging the clusters. The associated data set stores vehicle interior data of at least two vehicles in a specified format, and divides the interior parameters in the vehicle interior data according to different styles.

[0139] In some embodiments, when clusters are integrated based on the preset clustering style requirements, all clusters matching the first clustering style may be integrated into the first associated data subset, and some clusters matching the first clustering style may be integrated into the first associated data subset. Alternatively, clusters matching different clustering styles may be integrated into the same associated data subset, which is not limited in this embodiment.

[0140] In some embodiments, the generated associated data set can be used as a database to provide users with reference materials for interior parameters.

[0141] Optionally, a search condition is received, where the search condition is used to search for a subset of associated data from the associated data set.

[0142] The search conditions have the same format as the clustering style used in cluster analysis. For example, if the clustering style is a descriptive term classified based on the vehicle interior style, the search conditions also include terms with the same part of speech.

[0143] A matching analysis is performed based on the search conditions and clustering style requirements to obtain matching results.

[0144] A target associated data subset corresponding to the search condition is obtained from the associated data set based on the matching result.

[0145] Exemplarily, feature extraction is performed on the search condition and at least one clustering style indicated by the clustering style requirement, respectively, to obtain a first feature representation corresponding to the search condition and at least one feature representation corresponding to the at least one clustering style.

[0146] A matching result is obtained based on the similarity between the first feature representation and at least one feature representation.

[0147] Exemplarily, the matching result indicates that the similarity between the first feature representation and the target feature representation in at least one feature representation is greater than a preset threshold, a target clustering style corresponding to the target feature representation is determined, and an associated data subset generated based on the target clustering style is obtained.

[0148] In some embodiments, the search condition also includes the type of interior parameter. After the corresponding associated data subset is indexed based on the search condition, partial data related to the interior parameter can be directly returned based on the type of the interior parameter. Alternatively, prompt information is returned based on the type of the interior parameter, and the prompt information is used to confirm with the user whether to push other content in the associated data subset to which the interior parameter belongs. After receiving the user's confirmation operation, the complete associated data subset is returned.

[0149] In some embodiments, the vehicle interior data contains data of multiple modalities. To facilitate data clustering and organization, the data may be modally converted into data of the same modality, and then restored to data of multiple modalities after data organization is completed.

[0150] Optionally, in response to at least two types of modal data being included in vehicle interior data corresponding to at least two vehicles, modal conversion is performed on the at least two modal data to obtain first modal data, the at least two modal data represent interior parameters in the vehicle interior data in at least two modes, and the first modal data is used to represent interior parameters in the vehicle interior data in the first mode.

[0151] Exemplarily, the vehicle interior data includes text modal data and image modal data, and the first modality refers to the text modality. The text modal data in the vehicle interior data is retained, and the image modal data in the vehicle interior data is feature analyzed, and the relevant information of the interior parameters represented by the image modal data is replaced with the text modal data to achieve modal conversion.

[0152] For example, the image modal data shows information about the vehicle interior instrument panel. The digital and text information in the image is identified to obtain the first text sub-data. The image is feature analyzed with the interior parameter type as the target, and the feature analysis results are obtained and converted into text content to obtain the second text sub-data. The first text sub-data and the second text sub-data are integrated to obtain the first modal data.

[0153] For example, the image is analyzed with color interior parameters as the target, and the image is input into the pre-trained RGB (Red, Green, Blue) color model. The RGB color model decomposes the color into three channels: red, green, and blue. The value of each channel is between 0 and 255. The RGB color model can read the RGB value of each pixel in the image to identify the color and represent the color in digital form (r, g, b). Among them, the r-bit value represents the value of the red channel, the g-bit value represents the value of the green channel, and the b-bit value represents the value of the blue channel.

[0154] A preset color comparison table is obtained, and the numerical value outputted based on the RGB color model is converted into text content to obtain the second text sub-data. For example, the RGB value is (255, 0, 0), which is converted into the text content "red" according to the comparison table.

[0155] Taking the interior parameters as clustering granularity, cluster analysis is performed on the interior parameters in the first modal data to obtain clustering results corresponding to at least two interior parameters respectively.

[0156] Based on a preset clustering style requirement, cluster clusters in at least two clustering results are integrated to obtain an integrated associated data subset, where the data in the integrated associated data subset is a first modality.

[0157] The integrated associated data subset is restored to obtain an associated data set, wherein the restoration refers to converting the data in the integrated associated data subset from a first modality to at least two modalities indicated by the at least two modal data.

[0158] That is, when performing modal conversion on the vehicle interior data, the modal type of each data before conversion is recorded. When the associated data set is generated, it is restored based on the recorded modal type. This ensures that the associated data set is accurate and well-conditioned while having a multi-modal information display effect, thereby improving the richness and intuitiveness of the interior parameter presentation method.

[0159] In some embodiments, in order to improve the accuracy of the clustering style to which each associated data subset in the associated data set belongs, and to facilitate users to search for elements in the interior parameters that better meet the requirements of the desired clustering style, after obtaining the associated data set, the associated data set can be analyzed again, and the associated data subsets can be merged according to the distribution of the interior parameters under different clustering styles, and new subsets in the associated data set can be added, so that the associated data set can be dynamically updated and the clustering styles covered are more comprehensive.

[0160] Optionally, a coincidence analysis is performed on the associated data subsets in the associated data set to obtain coincidence results of the associated data subsets, and the coincidence results are used to indicate the similarities between the associated data subsets.

[0161] Exemplarily, a coincidence analysis is performed between any two associated data subsets in the associated data set to determine the coincidence between each interior parameter in the current two associated data subsets. A weighted calculation is performed based on the coincidence corresponding to each interior parameter to obtain the coincidence result / similarity of the current associated data subset.

[0162] For example, the associated data subset 1 and the associated data set 2 respectively contain three types of interior parameters (interior parameters A, B, and C).

[0163] Taking interior parameter A as an example, the total number of elements contained in interior parameter A in associated data set 1 and associated data set 2 is counted (each element is counted only once), and the number of overlapping elements that appear in interior parameter A in both associated data set 1 and associated data set 2 is counted. Based on the quotient between the number of overlapping elements and the total number of elements, the overlap degree A between interior parameter A in associated data set 1 and associated data set 2 is obtained.

[0164] For example, the number of elements of interior parameter A in associated data set 1 is 100, the number of elements of interior parameter A in associated data set 2 is 80, and the number of overlapping elements is 60. The total number of elements is 100+80-60=120, and the calculated overlap degree A is 60 / 120=0.5.

[0165] Based on the above method, the coincidence degrees B and C corresponding to the interior parameters B and C are calculated respectively.

[0166] The preset first weight, second weight, and third weight are obtained, and the coincidence result / similarity between the associated data set 1 and the associated data set 2 is calculated based on the following formula 1.

[0167] Formula 1: first weight*overlap degree A+second weight*overlap degree B+third weight*overlap degree C=overlap result / similarity.

[0168] For example, the first weight is 0.2, the second weight is 0.3, the third weight is 0.5, the overlap degree A is 0.5, the overlap degree B is 0.4, and the overlap degree C is 0.8.

[0169] The calculated overlap result is 0.2*0.5+0.3*0.4+0.5*0.8=0.62.

[0170] In response to the overlap result indicating that there is a similarity between the first associated data subset and the second associated data subset in the associated data set that meets the preset merging requirement, the overlapped portion of the first associated data subset and the second associated data subset is analyzed to obtain the overlapped clustering style.

[0171] A third associated data subset is generated based on the overlapped portion of the first associated data subset and the second associated data subset, and the third associated data subset corresponds to the overlapped clustering style.

[0172] The third associated data subset is added to the associated data set to obtain an updated associated data set.

[0173] Exemplarily, the preset merging requirement refers to the overlapping results / similarity reaching a first similarity threshold.

[0174] For example, the first similarity threshold is 0.6, and the similarity between the first associated data subset and the second associated data subset is 0.62, which meets the preset merging requirements. The overlapping parts of the interior parameters in the first associated data subset and the second associated data subset are used as the third associated data subset. The overlapping parts are analyzed to generate overlapping clustering styles that can summarize the characteristics of the interior parameters in the third associated data subset.

[0175] When the user searches based on the updated associated data set, if the keyword input by the user matches the overlapping clustering style, the third associated data subset is returned as the search result.

[0176] By performing overlap analysis between subsets in the associated data set and updating the associated data set in real time, the accuracy of the associated data set obtained by classifying interior parameters based on clustering styles can be improved.

[0177] In summary, the data sorting method provided by the present application can divide each interior parameter into clusters of multiple styles based on different clustering styles by clustering analysis of vehicle interior data, and integrate the cluster data into a related data set based on the correlation between the clusters, thereby realizing the automatic collection, analysis and sorting of interior data. Compared with the manual sorting method in the related art, it can improve the efficiency of data sorting, facilitate users to directly apply the standardized data set, and thus improve the efficiency of material indexing when designing vehicle interiors. By acquiring and integrating a large amount of data through a computer, omissions can be avoided, the integrity and coverage of the integrated data can be improved, and the classification of interior parameters can be made clearer.

[0178] Figure 4 is a structural block diagram of a data sorting device provided by an exemplary embodiment of the present application, such as Figure 4 As shown, the device includes the following parts.

[0179] An acquisition module 410 is used to acquire vehicle interior data corresponding to at least two vehicles, wherein the vehicle interior data includes interior parameters describing the vehicle interior from at least two dimensions;

[0180] The clustering module 420 is used to perform cluster analysis on the interior parameters in the vehicle interior data corresponding to the at least two vehicles respectively, with the interior parameters as the clustering granularity, to obtain clustering results corresponding to the at least two interior parameters respectively, wherein the target interior parameters are clustered to obtain a target clustering result, and the i-th cluster in the target clustering result includes the target interior parameters corresponding to the i-th clustering style, where i is a positive integer;

[0181] The association module 430 is used to integrate the clustering clusters in the at least two clustering results based on the preset clustering style requirements to obtain an associated data set, wherein the clustering clusters that meet the same clustering style requirements in the clustering results corresponding to the at least two interior parameters are integrated into the same associated data subset.

[0182] In an optional embodiment, the acquisition module 410 is also used to acquire a vehicle interior material library, which contains candidate data for describing vehicle interiors, and the candidate data meets preset classification processing requirements; the candidate data is classified and processed to obtain the vehicle interior data corresponding to the at least two vehicles respectively.

[0183] In an optional embodiment, the acquisition module 410 is also used to identify the candidate data to obtain vehicle model data, and the vehicle model data is used to indicate the vehicle models corresponding to the at least two vehicles respectively; the candidate data is divided based on the vehicle model data to obtain the vehicle interior data corresponding to the at least two vehicles respectively, and the vehicle interior data meets the preset format requirements.

[0184] In an optional embodiment, the clustering module 420 is further used to obtain at least two clustering styles corresponding to the j-th interior parameter among the at least two interior parameters, the at least two clustering styles being used to indicate a method of performing cluster analysis on the j-th interior parameter, and j being a positive integer; analyzing the at least two clustering styles to obtain at least two clustering centers corresponding to the at least two clustering styles respectively; taking the j-th interior parameter as the clustering granularity, clustering analysis is performed on the j-th interior parameter in the vehicle interior data corresponding to the at least two vehicles respectively based on the at least two clustering centers to obtain a j-th clustering result corresponding to the j-th interior parameter; wherein the j-th clustering result includes cluster clusters corresponding to the at least two clustering styles respectively.

[0185] In an optional embodiment, the preset clustering style requirement includes a first clustering style;

[0186] The associated module 430 is further configured to integrate, for the first clustering style, the clustering clusters that match the first clustering style among the at least two clustering results, to obtain a first associated data subset, where the first associated data subset is one of the associated data subsets in the associated data set.

[0187] In an optional embodiment, as Figure 5 shown, the apparatus further includes:

[0188] A search module 440, configured to receive a search condition, where the search condition is used to search for an associated data subset from the associated data set; perform a matching analysis based on the search condition and the clustering style requirement to obtain a matching result; and obtain a target associated data subset corresponding to the search condition from the associated data set based on the matching result.

[0189] In an optional embodiment, the apparatus further includes:

[0190] A modality conversion module 450, configured to, in response to the vehicle interior data respectively corresponding to the at least two vehicles including at least two modality data, perform modality conversion on the at least two modality data to obtain first modality data, where the at least two modality data represent interior parameters in the vehicle interior data in at least two modalities, and the first modality data is used to represent the interior parameters in the vehicle interior data in a first modality;

[0191] The clustering module 420 is further configured to perform clustering analysis on the interior parameters in the first modality data with the interior parameters as the clustering granularity, to obtain clustering results respectively corresponding to at least two interior parameters.

[0192] In an optional embodiment, the associated module 430 is further configured to integrate the clustering clusters in the at least two clustering results based on a preset clustering style requirement, to obtain an integrated associated data subset, where the data in the integrated associated data subset is in the first modality;

[0193] The modality conversion module 450 is further configured to perform a reduction process on the integrated associated data subset to obtain the associated data set; the reduction process refers to converting the data in the integrated associated data subset from the first modality to the at least two modalities indicated by the at least two modality data.

[0194] In an optional embodiment, the apparatus further includes:

[0195] The updating module 460 is used to perform overlap analysis on the associated data subsets in the associated data set to obtain overlap results of the associated data subsets, wherein the overlap results are used to indicate the similarity between the associated data subsets; in response to the overlap result indicating that there is a first associated data subset and a second associated data subset in the associated data set and the similarity meets the preset merging requirement, analyze the overlapped part of the first associated data subset and the second associated data subset to obtain the overlapped clustering style; generate a third associated data subset based on the overlapped part of the first associated data subset and the second associated data subset, wherein the third associated data subset corresponds to the overlapped clustering style; and add the third associated data subset to the associated data set to obtain an updated associated data set.

[0196] In summary, the data sorting device provided by the present application can divide each interior parameter into clusters of multiple styles based on different clustering styles by clustering analysis of vehicle interior data, and integrate the cluster data into a related data set based on the correlation between the clusters, thereby realizing the automatic collection, analysis and sorting of interior data. Compared with the manual sorting method in the related technology, it can improve the efficiency of data sorting, facilitate users to directly apply the standardized data set, and thus improve the efficiency of material indexing when designing vehicle interiors. By acquiring and integrating a large amount of data through a computer, omissions can be avoided, the integrity and coverage of the integrated data can be improved, and the classification of interior parameters can be made clearer.

[0197] It should be noted that the data sorting device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data sorting device provided in the above embodiment and the data sorting method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0198] Figure 6 The block diagram of a computer device 600 provided by an exemplary embodiment of the present application is shown. The computer device 600 may be: a smart phone, a tablet computer, a Moving Picture Experts Group Audio Layer III (MP3) player, a Moving Picture Experts Group Audio Layer IV (MP4) player, a laptop computer or a desktop computer. The computer device 600 may also be called a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0199] Typically, the computer device 600 includes a processor 601 and a memory 602 .

[0200] The processor 601 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 601 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 601 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 601 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 601 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0201] The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 602 is used to store at least one instruction, which is used to be executed by the processor 601 to implement the data sorting method provided in the method embodiment of the present application.

[0202] In some embodiments, the computer device 600 further includes some other components 603, and the type and quantity of the other components 603 can be selected based on the functional requirements of the computer device 600. Those skilled in the art will appreciate that Figure 6 The structure shown in the figure does not constitute a limitation on the computer device 600, and the computer device 600 may include more or less components than those shown in the figure, or combine some components, or adopt a different arrangement of components.

[0203] Optionally, the computer readable storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), Solid State Drives (SSD) or optical disks, etc. Among them, the random access memory may include resistance random access memory (ReRAM) and dynamic random access memory (DRAM). The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0204] An embodiment of the present application also provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the data sorting method as described in any of the above embodiments of the present application.

[0205] An embodiment of the present application also provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement a data sorting method as described in any of the above embodiments of the present application.

[0206] The embodiment of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the data sorting method described in any of the above embodiments.

[0207] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0208] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data sorting method, characterized in that: The method comprises: Acquire vehicle interior data corresponding to at least two vehicles respectively, wherein the vehicle interior data includes interior parameters describing the vehicle interior from at least two dimensions; Taking the interior parameters as the clustering granularity, cluster analysis is performed on the interior parameters in the vehicle interior data corresponding to the at least two vehicles, to obtain clustering results corresponding to the at least two interior parameters, wherein the target interior parameters are clustered to obtain a target clustering result, and the i-th cluster in the target clustering result includes the target interior parameters corresponding to the i-th clustering style, where i is a positive integer; Based on the preset clustering style requirements, the clustering clusters in the at least two clustering results are integrated to obtain a related data set, wherein, in the clustering results corresponding to the at least two interior parameters, the clustering clusters that meet the same clustering style requirements are integrated into the same related data subset.

2. The method according to claim 1, characterized in that The obtaining of vehicle interior data corresponding to at least two vehicles respectively includes: Acquire a vehicle interior material library, wherein the vehicle interior material library contains candidate data describing vehicle interiors, and the candidate data meets preset classification processing requirements; The candidate data are classified to obtain the vehicle interior data corresponding to the at least two vehicles respectively.

3. The method according to claim 2, characterized in that The classifying the candidate data to obtain the vehicle interior data corresponding to the at least two vehicles respectively includes: Identify the candidate data to obtain vehicle model data, where the vehicle model data is used to indicate vehicle models corresponding to the at least two vehicles respectively; The candidate data are divided based on the vehicle model data to obtain the vehicle interior data corresponding to the at least two vehicles respectively, and the vehicle interior data meets the preset format requirements.

4. The method according to claim 1, characterized in that: The clustering analysis is performed on the interior parameters in the vehicle interior data corresponding to the at least two vehicles respectively, using the interior parameters as the clustering granularity, to obtain clustering results corresponding to the at least two interior parameters respectively, including: For a j-th interior parameter among the at least two interior parameters, obtaining at least two clustering styles corresponding to the j-th interior parameter, wherein the at least two clustering styles are used to indicate a manner of performing cluster analysis on the j-th interior parameter, where j is a positive integer; Analyzing the at least two clustering styles to obtain at least two clustering centers corresponding to the at least two clustering styles respectively; Taking the j-th interior parameter as the clustering granularity, cluster analysis is performed on the j-th interior parameter in the vehicle interior data corresponding to the at least two vehicles respectively based on the at least two clustering centers to obtain the j-th clustering result corresponding to the j-th interior parameter; wherein the j-th clustering result includes cluster clusters corresponding to the at least two clustering styles respectively.

5. The method according to any one of claims 1 to 4, characterized in that: The preset clustering style requirements include a first clustering style; The step of integrating the clusters in the at least two clustering results based on the preset clustering style requirement to obtain a related data set includes: For the first clustering style, clusters matching the first clustering style in the at least two clustering results are integrated to obtain a first associated data subset, where the first associated data subset is an associated data subset in the associated data set.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: receiving a search condition, wherein the search condition is used to search for a subset of associated data from the associated data set; Performing a matching analysis based on the search condition and the clustering style requirement to obtain a matching result; A target associated data subset corresponding to the search condition is acquired from the associated data set based on the matching result.

7. The method according to any one of claims 1 to 4, characterized in that: After obtaining the vehicle interior data corresponding to at least two vehicles respectively, the method further includes: In response to at least two modal data being included in the vehicle interior data corresponding to the at least two vehicles respectively, modal conversion is performed on the at least two modal data to obtain first modal data, wherein the at least two modal data represent interior parameters in the vehicle interior data in at least two modalities, and the first modal data is used to represent the interior parameters in the vehicle interior data in the first modality; The clustering analysis is performed on the interior parameters in the vehicle interior data corresponding to the at least two vehicles respectively, using the interior parameters as the clustering granularity, to obtain clustering results corresponding to the at least two interior parameters respectively, including: Taking the interior parameters as the clustering granularity, cluster analysis is performed on the interior parameters in the first modal data to obtain clustering results corresponding to at least two interior parameters respectively.

8. The method according to claim 7, characterized in that The step of integrating the clusters in the at least two clustering results based on the preset clustering style requirement to obtain a related data set includes: Based on a preset clustering style requirement, the cluster clusters in the at least two clustering results are integrated to obtain an integrated associated data subset, wherein the data in the integrated associated data subset is a first modality; The integrated associated data subset is restored to obtain the associated data set; the restoration refers to converting the data in the integrated associated data subset from the first modality to at least two modalities indicated by the at least two modal data.

9. The method according to any one of claims 1 to 4, characterized in that: After integrating the clusters in the at least two clustering results based on the preset clustering style requirement to obtain the associated data set, the method further includes: Performing overlap analysis on the associated data subsets in the associated data set to obtain overlap results of the associated data subsets, wherein the overlap results are used to indicate similarities between the associated data subsets; In response to the overlap result indicating that the similarity between the first associated data subset and the second associated data subset in the associated data set meets the preset merging requirement, analyzing the overlapped part of the first associated data subset and the second associated data subset to obtain the overlapped clustering style; generating a third associated data subset based on the overlapped portion of the first associated data subset and the second associated data subset, wherein the third associated data subset corresponds to the overlapped clustering style; The third associated data subset is added to the associated data set to obtain an updated associated data set.

10. A data sorting device, characterized in that: The device comprises: An acquisition module, used to acquire vehicle interior data corresponding to at least two vehicles respectively, wherein the vehicle interior data includes interior parameters describing the vehicle interior from at least two dimensions; A clustering module, configured to perform cluster analysis on the interior parameters in the vehicle interior data corresponding to the at least two vehicles respectively, with the interior parameters as the clustering granularity, to obtain clustering results corresponding to the at least two interior parameters respectively, wherein the target interior parameters are clustered to obtain a target clustering result, and the i-th cluster in the target clustering result includes the target interior parameters corresponding to the i-th clustering style, where i is a positive integer; An association module is used to integrate the clustering clusters in the at least two clustering results based on a preset clustering style requirement to obtain an associated data set, wherein, in the clustering results corresponding to the at least two interior parameters, the clustering clusters that meet the same clustering style requirement are integrated into the same associated data subset.

Images