Vehicle archive information processing method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle archive information processing method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining archive input information of a to-be-processed vehicle; performing data matching on the basis of the archive input information and the vehicle knowledge graph of the standard vehicle, and determining a matching result of the archive input information; determining vehicle archive information of the to-be-processed vehicle based on a matching result; the vehicle knowledge graph is constructed based on vehicle combination dimensions; the vehicle combination dimension is obtained based on the combination of the vehicle classification dimension and the vehicle basic characteristics; the vehicle classification dimension comprises at least one of a vehicle model and a VIN code. According to the method provided by the invention, the vehicle combination dimension is obtained through the vehicle classification dimension and the vehicle basic characteristics, the vehicle knowledge graph is constructed, and data matching is performed on the archive input information and the vehicle knowledge graph, so that comprehensive, accurate and standardized vehicle archive information processing is realized; and more reliable vehicle archive information with higher data quality is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle information processing, and in particular to a method, device, electronic equipment and storage medium for processing vehicle file information. Background Art

[0002] Vehicle file information is the most basic part of the logistics operation process. Many application scenarios rely on the completeness and accuracy of vehicle information. The reliability of its information determines whether data reuse and application empowerment can be achieved. Existing solutions usually require drivers to enter manually or upload vehicle driving licenses. The basic information of the vehicle is obtained through OCR (Optical Character Recognition).

[0003] However, errors are prone to occur whether it is manual filling or OCR recognition. For example, when filling in manually, there may be a large number of "other" cases due to lack of reference standards; when selecting manually, the driver cannot make the correct selection due to inconsistent standards; OCR recognition is also susceptible to incomplete or mismatched uploaded certificates; the certificate is only recognized up to the previous page, resulting in the lack of key information on the second page; and even information recognition errors caused by environmental light factors. Therefore, in logistics and transportation, the currently entered vehicle information is usually missing, has incorrect information, and inconsistent standards, resulting in poor quality of vehicle file information. Summary of the invention

[0004] The present invention provides a vehicle file information processing method, device, electronic device and storage medium, which are used to solve the defects of manual or automatic input of vehicle file information and low quality of vehicle file information in the prior art.

[0005] The present invention provides a method for processing vehicle file information, comprising: Get the file entry information of the vehicle to be processed; Performing data matching based on the file entry information and the vehicle knowledge graph of the standard vehicle to determine the matching result of the file entry information; Based on the matching result, determining the vehicle file information of the vehicle to be processed; The vehicle knowledge graph is constructed based on a vehicle combination dimension; the vehicle combination dimension is constructed based on a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension; the vehicle classification dimension includes at least one of a vehicle model and a VIN code.

[0006] According to a method for processing vehicle archive information provided by the present invention, the step of obtaining the vehicle knowledge graph includes: Obtaining basic file information of the standard vehicle; Based on the vehicle classification dimension, basic vehicle features in the basic archive information are aggregated to construct a basic vehicle knowledge graph; Combining the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph to obtain the vehicle combination dimension; Based on the vehicle combination dimension, the vehicle knowledge graph is constructed.

[0007] According to a method for processing vehicle archive information provided by the present invention, the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph are combined to obtain the vehicle combination dimension, including: Fuzzy the target field results under the vehicle classification dimension to obtain a fuzzy vehicle classification field; Combining the fuzzy vehicle classification field and at least one vehicle basic feature to obtain the vehicle combination dimension; The basic characteristics of the vehicles under the target field results are the same or similar.

[0008] According to a method for processing vehicle archive information provided by the present invention, the vehicle knowledge graph is constructed based on the vehicle combination dimension, including: Based on the vehicle combination dimension, construct an initial vehicle knowledge graph; Based on the initial vehicle knowledge graph, data verification is performed on the field results corresponding to the basic characteristics of any vehicle in the dynamic background information of the vehicle to obtain a verification result; Based on the verification result and the vehicle dynamic background information set, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

[0009] According to a method for processing vehicle archive information provided by the present invention, the initial vehicle knowledge graph is updated based on the verification result and the vehicle dynamic background information set to obtain the vehicle knowledge graph, including: Based on the vehicle dynamic background information set, statistically analyzing the results of each field under the basic characteristics of the vehicle whose verification result is passed, and obtaining the confidence of the results of each field and the high-frequency field results; Based on the confidence level and the high-frequency field results, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

[0010] According to a method for processing vehicle archive information provided by the present invention, the vehicle dynamic background information set includes: at least one of driving license data and vehicle transportation business data.

[0011] The present invention also provides a vehicle file information processing device, comprising: An acquisition unit, which acquires file entry information of the vehicle to be processed; A matching unit, performing data matching based on the file input information and the vehicle knowledge graph of the standard vehicle, and determining a matching result of the file input information; A processing unit, based on the matching result, determines the vehicle file information of the vehicle to be processed; The vehicle knowledge graph is constructed based on a vehicle combination dimension; the vehicle combination dimension is constructed based on a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension; the vehicle classification dimension includes at least one of a vehicle model and a VIN code.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for processing vehicle file information as described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the vehicle file information processing method described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the vehicle file information processing method described in any one of the above is implemented.

[0015] The vehicle file information processing method, device, electronic device and storage medium provided by the present invention obtain a vehicle combination dimension through a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension, construct a vehicle knowledge graph based on the vehicle combination dimension, perform data matching between the file entry information and the vehicle knowledge graph, and determine the vehicle file information of the vehicle to be processed, thereby realizing comprehensive, accurate and standardized vehicle file information processing, and obtaining vehicle file information with higher data quality and more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the method for processing vehicle file information provided by the present invention; Figure 2 It is a flowchart of the method for constructing a vehicle knowledge graph provided by the present invention; Figure 3 It is a structural schematic diagram of a vehicle file information processing device provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be noted that vehicle file information is the most basic part of the logistics operation process. Many application scenarios rely on the completeness and accuracy of vehicle information. The reliability of its information determines whether data reuse and application empowerment can be achieved. For example, in the logistics capacity transaction scenario, vehicles and goods are not completely fixed matches. In fact, a considerable number of individual drivers and small carriers do not have fixed owners, but match goods through various channels. In order to match vehicles and goods, that is, in the capacity matching scenario, in addition to the geographic location information of vehicles and goods, the key factor in determining the selection of capacity is still the basic information of the vehicle, such as vehicle model, vehicle length, number of axles, load capacity, etc.

[0020] For example, in terms of fuel consumption management, different drive forms represent different driving capabilities and load capacities. Only by classifying and statistically analyzing vehicles with different drive forms or axle numbers can we obtain more detailed results.

[0021] However, the quality of the current vehicle file information input results is missing, erroneous information, inconsistent standards, etc., resulting in poor quality of vehicle file information. To address this problem, an embodiment of the present invention provides a method for processing vehicle file information to obtain comprehensive, accurate and standardized vehicle file information. Figure 1 FIG. 1 is a flow chart of a method for processing vehicle file information provided by the present invention, such as Figure 1 As shown, the method includes: Step 110, obtaining file entry information of the vehicle to be processed; Step 120, performing data matching based on the file input information and the vehicle knowledge graph of the standard vehicle to determine the matching result of the file input information; Step 130, determining the vehicle file information of the vehicle to be processed based on the matching result; The vehicle knowledge graph is constructed based on a vehicle combination dimension; the vehicle combination dimension is constructed based on a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension; the vehicle classification dimension includes at least one of a vehicle model and a VIN code.

[0022] Here, the vehicle classification dimension can be used for data matching when processing vehicle file information, that is, the vehicle classification dimension can be associated with other basic vehicle features to construct a vehicle knowledge graph. For example, it can be at least one of the vehicle model and VIN code. Among them, the vehicle model can reflect the basic information such as the model, configuration, manufacturer, etc. of the vehicle, and a single vehicle model can correspond to multiple different vehicles. The VIN code here refers to the unique identification code of the vehicle, and the unique target vehicle and various basic information of the vehicle can be determined based on the VIN code.

[0023] In addition, the vehicle combination dimension here can be obtained based on any vehicle classification dimension and at least one vehicle basic feature combination under the vehicle classification dimension. For example, the vehicle combination dimension can be vehicle model and vehicle load. It should be noted that the vehicle basic features here refer to the vehicle's file information, which may include: vehicle model, fuel type, vehicle length, width, height, and vehicle load information.

[0024] Specifically, before the vehicle file information processing flow is carried out, it is necessary to pre-build a vehicle knowledge graph of standard vehicles. The standard vehicle here refers to the current collection of various types of vehicles. The vehicle knowledge graph can be based on the vehicle combination dimension, and the basic vehicle features in the basic vehicle information of the standard vehicle are aggregated separately. Each basic vehicle feature is divided into a discrete value set or a continuous value interval according to the vehicle combination dimension type to construct a vehicle knowledge graph. For example, the vehicle knowledge graph here can be expressed as [ ];in, Can indicate vehicle model, Can indicate vehicle brand characteristics, It can represent the total traction mass characteristics of the vehicle; The number of axles of the vehicle can be represented.

[0025] It should be noted that by taking the vehicle model as the vehicle classification dimension and combining the vehicle classification dimension with at least one vehicle basic feature under the vehicle classification dimension, the remaining vehicle basic features aggregated based on the vehicle combination dimension are made more accurate. That is, a more accurate and clear vehicle knowledge graph is constructed, so that when matching vehicle information, more accurate information processing can be performed on the file input information, greatly improving the accuracy of the processed vehicle file information.

[0026] When processing vehicle file information, first, the vehicle file information manually filled in by the user, or the vehicle file information obtained based on the driving license image uploaded by the user, can be used as the file entry information of the vehicle to be processed.

[0027] Next, the file entry information can be matched with the vehicle knowledge graph of the standard vehicle to obtain the matching result of the file entry information. For example, the vehicle model information in the file entry information can be matched with the vehicle model classification dimension in the vehicle knowledge graph. When the vehicle model is successfully matched, the other basic information in the file entry information is then matched with the field results of the corresponding vehicle basic features in the vehicle knowledge graph to obtain the matching results of each basic information. The matching result here can be a successful match or a failed match. It can be understood that when the matching result is a failed match, it means that the basic information in the file entry information of the vehicle to be processed is blank or wrong or non-standard, that is, it does not match the standard information corresponding to the vehicle model. When the matching result is a successful match, it means that the basic information in the file entry information of the vehicle to be processed is consistent with the standard information corresponding to the vehicle model.

[0028] Finally, the vehicle file information of the vehicle to be processed can be determined through the matching results. For example, when the matching result is a successful match, the file entry information of the vehicle to be processed does not need to be modified; when the matching result is a failed match, the file entry information of the failed match can be corrected or supplemented through the corresponding vehicle information in the vehicle knowledge graph, thereby obtaining comprehensive, accurate and standardized vehicle file information.

[0029] The method provided by the embodiment of the present invention obtains a vehicle combination dimension through a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension, constructs a vehicle knowledge graph based on the vehicle combination dimension, performs data matching between the file entry information and the vehicle knowledge graph, and determines the vehicle file information of the vehicle to be processed, thereby realizing comprehensive, accurate and standardized vehicle file information processing, and obtaining vehicle file information with higher data quality and more reliability.

[0030] Based on any of the above embodiments, the step of acquiring the vehicle knowledge graph includes: Obtaining basic file information of the standard vehicle; Based on the vehicle classification dimension, basic vehicle features in the basic archive information are aggregated to construct a basic vehicle knowledge graph; Combining the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph to obtain the vehicle combination dimension; Based on the vehicle combination dimension, the vehicle knowledge graph is constructed.

[0031] Specifically, first, the basic file information of the standard vehicle can be obtained from each data source by crawling the data source containing the basic information of the vehicle related to the vehicle announcement. For example, the basic information of the vehicle can be crawled from the website, the driving license, and the logistics business data, and the crawled data can be processed. For example, if the classification standards or value lists of the same field in multiple data sources are inconsistent, data standardization is required to map the data of different standards to the same standard. For another example, for a field with multiple data sources, the field corresponding to the vehicle information can be determined by the priority of the data source. The priority of the data source can be pre-set, and the priority of the data source can be sorted from high to low as vehicle announcement, driving license, and logistics business data. For example, if the vehicle models obtained through each data source include "flat-head natural gas dump truck, heavy truck, flat-head natural gas container mixing semi-trailer tractor, van, etc.", the first-level standard vehicle model of "flat-head natural gas dump truck" can be defined as "dump truck", and its second-level standard vehicle model is "ordinary dump truck". For another example, in the case where there are multiple values ​​for the same data source, multiple fields can be retained.

[0032] Then, the basic information of the vehicle after data processing is used as the basic file information. The basic file information here can include the basic information of the vehicle model, brand, model, load, etc. For example, the basic file information can be "vehicle model (ABC1234XX1), brand (AB), energy type (diesel), vehicle length (6940), vehicle width (2500, 2550, 2524), vehicle height (3750, 3960) total traction mass (37500, 40000)".

[0033] Next, the basic vehicle features in the basic archive information can be aggregated through the vehicle classification dimension to construct a basic vehicle knowledge graph. Each basic vehicle feature is divided into a discrete value set or a continuous value interval according to the vehicle classification dimension. For example, when the vehicle classification dimension is vehicle model, the field result corresponding to the vehicle load under vehicle model A is [25, 30] tons. For another example, the length of the vehicle under vehicle model A is 4 meters or 6 meters.

[0034] It should be noted that the basic vehicle knowledge graph is constructed by aggregating the basic vehicle features in the basic file information through the vehicle classification dimension, which contains the basic vehicle information under each vehicle classification dimension, laying the foundation for comprehensive, complete and accurate vehicle file information processing.

[0035] Furthermore, a more accurate vehicle knowledge graph is constructed based on the basic vehicle knowledge graph. In detail, the vehicle classification dimension in the basic vehicle knowledge graph and at least one vehicle basic feature are combined to obtain a vehicle combination dimension. Then, based on the vehicle combination dimension and the remaining vehicle basic features, a vehicle knowledge graph is constructed. For example, the vehicle combination dimension may be vehicle model + vehicle load, and the vehicle knowledge graph may be constructed from the remaining vehicle basic features under each vehicle model + vehicle load.

[0036] The method provided by the embodiment of the present invention achieves a comprehensive and clear construction of a basic vehicle knowledge graph by acquiring basic file information of a standard vehicle, dividing it by vehicle classification dimensions, and aggregating basic vehicle features in the basic file information. On this basis, the vehicle classification dimension and at least one basic vehicle feature in the basic vehicle knowledge graph are combined to obtain a vehicle combination dimension to obtain a more accurate vehicle knowledge graph, and then when performing data matching based on the vehicle knowledge graph, a more accurate data matching result can be obtained, thereby improving the accuracy of vehicle file processing.

[0037] Based on any of the above embodiments, the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph are combined to obtain the vehicle combination dimension, including: Fuzzy the target field results under the vehicle classification dimension to obtain a fuzzy vehicle classification field; Combining the fuzzy vehicle classification field and at least one vehicle basic feature to obtain the vehicle combination dimension; The basic characteristics of the vehicles under the target field results are the same or similar.

[0038] Here, the target field result for fuzzy processing refers to vehicle models with the same or similar basic vehicle features.

[0039] Specifically, the fuzzy vehicle classification dimension can be obtained by fuzzy processing the vehicle models with the same or similar basic features. For example, the vehicle models starting with BJ1031V3JV5-AA include three real models: BJ1031V3JV5-AA1, BJ1031V3JV5-AA2, and BJ1031V3JV5-AA3. The energy type, total mass, rated load, vehicle model and other features are exactly the same, and the vehicle length is not much different. Therefore, a virtual BJ1031V3JV5-AA announcement model can be added to the map, and the features can be re-aggregated based on all the data starting with BJ1031V3JV5-AA.

[0040] In addition, the fuzzy processing here can also be performed by replacing common similar characters. For example, "S" and "3" can be replaced with each other, and "Z" and "2" can be replaced with each other. It can be understood that if the corresponding data aggregated for the basic characteristics of the vehicle is not much different after the vehicle model is replaced, it means that the replaced vehicle model does not exist, or the vehicle models before and after the replacement are similar models. The fuzzy processing methods are not listed one by one here. The vehicles corresponding to the fuzzy vehicle classification dimensions obtained after the fuzzy processing can be regarded as vehicles with the same or similar basic characteristics.

[0041] It should be noted that in some scenarios, direct full matching of vehicle models may result in missing some basic vehicle data. Therefore, when constructing a vehicle knowledge graph, by appropriately intercepting the front part of the field results corresponding to some vehicle classification dimensions and generating a virtual announcement model for matching, the practicality of the vehicle file information processing method can be greatly improved to avoid missing basic vehicle data.

[0042] In order to obtain a more standard and accurate vehicle knowledge graph, based on any of the above embodiments, the vehicle knowledge graph is constructed based on the vehicle combination dimension, including: Based on the vehicle combination dimension, construct an initial vehicle knowledge graph; Based on the initial vehicle knowledge graph, data verification is performed on the field results corresponding to the basic characteristics of any vehicle in the dynamic background information of the vehicle to obtain a verification result; Based on the verification result and the vehicle dynamic background information set, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

[0043] Specifically, first, an initial vehicle knowledge graph can be constructed through the vehicle combination dimension. The initial vehicle knowledge graph here can be used as static knowledge data to process the vehicle file information of the file entry information of the vehicle to be processed.

[0044] In order to improve the standardization, information accuracy and real-time performance of the vehicle knowledge graph, the initial vehicle knowledge graph can be used to perform data verification on the field results corresponding to the basic characteristics of any vehicle in the dynamic background information of the vehicle, and obtain the verification results of the basic characteristics of the vehicle. For example, if the vehicle model in the dynamic background information of the vehicle is A and the vehicle load is 20 tons, the basic information of the vehicle with the vehicle model A can be matched in the initial vehicle graph. If the vehicle load in the basic information of the vehicle contains 20 tons, it means that the vehicle load information verification has passed.

[0045] The vehicle dynamic background information here can be the basic information of any vehicle in the vehicle dynamic background information set. The vehicle dynamic background information set here can include at least one of the driving license data and vehicle transportation business data. It should be noted that the basic vehicle information extracted from the driving license and vehicle transportation business data here is kept updated, so that the static data in the vehicle knowledge graph can be updated.

[0046] Finally, when the verification result of the basic characteristics of the vehicle is passed, a statistical analysis can be performed on the passed verification data in the vehicle dynamic background information set to obtain the distribution probability of the verified data in the vehicle dynamic background information set, so as to obtain the confidence of the verified data. This confidence can then be updated to the initial vehicle knowledge graph to obtain the final vehicle knowledge graph. In the case where the verification result is not passed, the initial vehicle knowledge graph can be used to feed back and predict the true value of the field result that failed the data verification. It should be noted that the true value predicted here is not included in the statistical distribution probability.

[0047] The method provided by the embodiment of the present invention performs data verification on the initial vehicle knowledge graph through any vehicle dynamic background information in the vehicle dynamic background information set, so that the data of the obtained vehicle knowledge graph is integrated with new dynamic data on the basis of containing standard and accurate vehicle basic information, thereby greatly improving the practicality of the data in the vehicle background knowledge graph, and further improving the processing quality of vehicle file information.

[0048] Based on any of the above embodiments, the updating of the initial vehicle knowledge graph based on the verification result and the vehicle dynamic background information set to obtain the vehicle knowledge graph includes: Based on the vehicle dynamic background information set, statistically analyzing the results of each field under the basic characteristics of the vehicle whose verification result is passed, and obtaining the confidence of the results of each field and the high-frequency field results; Based on the confidence level and the high-frequency field results, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

[0049] Specifically, in the vehicle dynamic background information set, a statistical analysis can be performed on the results of each field under the basic characteristics of the vehicle with a verification result of passed, and the number of vehicles in each field result in the vehicle dynamic background information set can be counted. The confidence of each field result can be calculated through the number of vehicles in each field result in the vehicle dynamic background information set and the total number of vehicles. And the field result with the most occurrences is taken as the high-frequency field result. It can be understood that the high-frequency field result here can be the results of each field under the basic characteristics of the vehicle, or it can be the field result other than the results of each field under the basic characteristics of the vehicle. When the high-frequency field result is a field result other than the results of each field under the basic characteristics of the vehicle, it means that this type of vehicle is becoming more and more a mainstream vehicle in the current logistics transportation. For example, a vehicle of model A has a total traction mass of 4,000 tons. The statistical results of the field results corresponding to the total traction mass in the vehicle dynamic background information set can be: the minimum number of vehicles is 37,505 tons, and the maximum number of vehicles is 40,000 tons. The high-frequency field result here is 4,000 tons, and the confidence level of 37,505 can be obtained based on the ratio of the number of vehicles corresponding to the field result to the total number of vehicles.

[0050] Finally, the confidence of each field result and the high-frequency field result can be updated to the initial vehicle knowledge graph to obtain the vehicle knowledge graph. It should be noted that the vehicle information in the vehicle dynamic background information set is dynamically updated, so the confidence of each field result and the high-frequency field result also change dynamically.

[0051] Figure 2 It is a flow chart of the method for constructing the vehicle knowledge graph provided by the present invention, such as Figure 2 As shown, the method includes: first, in the data acquisition stage, data can be acquired through an external knowledge base and an internal knowledge base (driving license and business data). Among them, the external knowledge base can be vehicle announcement data, and the internal knowledge base contains semi-structured data and unstructured data. In the data acquisition stage, the corresponding vehicle basic information can be acquired by extracting attributes, relationships, and entities from the data in the internal knowledge base.

[0052] Next, in the knowledge fusion stage, the data obtained from the external knowledge base can be fused, and the attributes of the fused data and the data extracted from the internal knowledge base can be disambiguated, that is, the basic vehicle information can be standardized.

[0053] Then, in the knowledge processing stage, the ontology is constructed through external data, and the data of basic features of each vehicle is aggregated with the vehicle model as the dimension to construct the initial vehicle knowledge graph. Knowledge reasoning is performed through internal data, and the initial vehicle knowledge graph built based on external data is updated and strengthened to obtain the final knowledge graph. At the same time, the knowledge graph is also used for data prediction of internal data during the knowledge reasoning process.

[0054] Based on any of the above embodiments, Figure 3 Schematic diagram of the structure of the vehicle file information processing device provided by the present invention. Figure 3 As shown, the device comprises: The acquisition unit 310 acquires the file entry information of the vehicle to be processed; A matching unit 320 performs data matching based on the file input information and the vehicle knowledge graph of the standard vehicle to determine a matching result of the file input information; The processing unit 330 determines the vehicle file information of the vehicle to be processed based on the matching result; The vehicle knowledge graph is constructed based on the vehicle combination dimension; the vehicle combination dimension is constructed based on the vehicle classification dimension and at least one basic vehicle feature under the vehicle classification dimension; the vehicle classification dimension includes at least one of the vehicle model and VIN code

[0055] The device provided by the embodiment of the present invention obtains a vehicle combination dimension through a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension, constructs a vehicle knowledge graph based on the vehicle combination dimension, performs data matching between the file entry information and the vehicle knowledge graph, and determines the vehicle file information of the vehicle to be processed, thereby realizing comprehensive, accurate and standardized vehicle file information processing, and obtaining vehicle file information with higher data quality and more reliability.

[0056] Based on any of the above embodiments, the device further includes a map construction unit, and the map construction unit is specifically used for: Obtaining basic file information of the standard vehicle; Based on the vehicle classification dimension, basic vehicle features in the basic archive information are aggregated to construct a basic vehicle knowledge graph; Combining the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph to obtain the vehicle combination dimension; Based on the vehicle combination dimension, the vehicle knowledge graph is constructed.

[0057] Based on any of the above embodiments, the graph construction unit is further specifically used for: Fuzzy the target field results under the vehicle classification dimension to obtain a fuzzy vehicle classification field; Combining the fuzzy vehicle classification field and at least one vehicle basic feature to obtain the vehicle combination dimension; The basic characteristics of the vehicles under the target field results are the same or similar.

[0058] Based on any of the above embodiments, the graph construction unit is further specifically used for: Based on the vehicle combination dimension, construct an initial vehicle knowledge graph; Based on the initial vehicle knowledge graph, data verification is performed on the field results corresponding to the basic characteristics of any vehicle in the dynamic background information of the vehicle to obtain a verification result; Based on the verification result and the vehicle dynamic background information set, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

[0059] Based on any of the above embodiments, the graph construction unit is further specifically used for: Based on the vehicle dynamic background information set, statistically analyzing the results of each field under the basic characteristics of the vehicle whose verification result is passed, and obtaining the confidence of the results of each field and the high-frequency field results; Based on the confidence level and the high-frequency field results, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

[0060] Based on any of the above embodiments, the vehicle dynamic background information set includes: at least one of driving license data and vehicle transportation business data.

[0061] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the method for processing vehicle file information, the method comprising: obtaining the file entry information of the vehicle to be processed; performing data matching based on the file entry information and the vehicle knowledge graph of the standard vehicle to determine the matching result of the file entry information; determining the vehicle file information of the vehicle to be processed based on the matching result; the vehicle knowledge graph is constructed based on the vehicle combination dimension; the vehicle combination dimension is obtained based on the vehicle classification dimension and at least one vehicle basic feature combination under the vehicle classification dimension; the vehicle classification dimension includes at least one of the vehicle model and the VIN code.

[0062] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0063] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle file information processing method provided by the above-mentioned methods, and the method includes: obtaining the file entry information of the vehicle to be processed; performing data matching based on the file entry information and the vehicle knowledge graph of the standard vehicle to determine the matching result of the file entry information; based on the matching result, determining the vehicle file information of the vehicle to be processed; the vehicle knowledge graph is constructed based on the vehicle combination dimension; the vehicle combination dimension is based on the vehicle classification dimension and at least one vehicle basic feature combination under the vehicle classification dimension; the vehicle classification dimension includes at least one of the vehicle model and the VIN code.

[0064] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the vehicle file information processing method provided by the above-mentioned methods, the method comprising: obtaining the file entry information of the vehicle to be processed; performing data matching based on the file entry information and the vehicle knowledge graph of the standard vehicle to determine the matching result of the file entry information; determining the vehicle file information of the vehicle to be processed based on the matching result; the vehicle knowledge graph is constructed based on a vehicle combination dimension; the vehicle combination dimension is obtained based on a vehicle classification dimension and at least one vehicle basic feature combination under the vehicle classification dimension; the vehicle classification dimension includes at least one of a vehicle model and a VIN code.

[0065] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing vehicle file information, characterized in that: include: Get the file entry information of the vehicle to be processed; Performing data matching based on the file entry information and the vehicle knowledge graph of the standard vehicle to determine the matching result of the file entry information; Based on the matching result, determining the vehicle file information of the vehicle to be processed; The vehicle knowledge graph is constructed based on a vehicle combination dimension; the vehicle combination dimension is constructed based on a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension; the vehicle classification dimension includes at least one of a vehicle model and a VIN code.

2. The method for processing vehicle file information according to claim 1, characterized in that: The step of acquiring the vehicle knowledge graph includes: Obtaining basic file information of the standard vehicle; Based on the vehicle classification dimension, basic vehicle features in the basic archive information are aggregated to construct a basic vehicle knowledge graph; Combining the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph to obtain the vehicle combination dimension; Based on the vehicle combination dimension, the vehicle knowledge graph is constructed.

3. The method for processing vehicle file information according to claim 2, characterized in that: The combining of the vehicle classification dimension and at least one vehicle basic feature in the basic vehicle knowledge graph to obtain the vehicle combination dimension includes: Fuzzy the target field results under the vehicle classification dimension to obtain a fuzzy vehicle classification field; Combining the fuzzy vehicle classification field and at least one vehicle basic feature to obtain the vehicle combination dimension; The basic characteristics of the vehicles under the target field results are the same or similar.

4. The method for processing vehicle file information according to claim 2, characterized in that: The vehicle knowledge graph is constructed based on the vehicle combination dimension, including: Based on the vehicle combination dimension, construct an initial vehicle knowledge graph; Based on the initial vehicle knowledge graph, data verification is performed on the field results corresponding to the basic characteristics of any vehicle in the dynamic background information of the vehicle to obtain a verification result; Based on the verification result and the vehicle dynamic background information set, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

5. The method for processing vehicle file information according to claim 4, characterized in that: The updating of the initial vehicle knowledge graph based on the verification result and the vehicle dynamic background information set to obtain the vehicle knowledge graph includes: Based on the vehicle dynamic background information set, statistical analysis is performed on the results of each field under the basic characteristics of the vehicle whose verification result is passed, to obtain the confidence of the results of each field and the high-frequency field results; Based on the confidence level and the high-frequency field results, the initial vehicle knowledge graph is updated to obtain the vehicle knowledge graph.

6. The method for processing vehicle file information according to claim 5, characterized in that: The vehicle dynamic background information set includes: at least one of driving license data and vehicle transportation business data.

7. A vehicle file information processing device, characterized in that: include: An acquisition unit, which acquires file entry information of the vehicle to be processed; A matching unit, performing data matching based on the file input information and the vehicle knowledge graph of the standard vehicle, and determining a matching result of the file input information; A processing unit, based on the matching result, determines the vehicle file information of the vehicle to be processed; The vehicle knowledge graph is constructed based on a vehicle combination dimension; the vehicle combination dimension is constructed based on a vehicle classification dimension and at least one basic feature of a vehicle under the vehicle classification dimension; the vehicle classification dimension includes at least one of a vehicle model and a VIN code.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for processing vehicle file information as claimed in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing vehicle file information as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for processing vehicle file information as claimed in any one of claims 1 to 6 is implemented.

Images