Vehicle detection report interpretation method, device, equipment and medium

Abstract

The embodiment of the invention provides a vehicle detection report interpretation method and device, equipment and a medium, and the method comprises the steps: obtaining the detection data and attribute data of a target vehicle, and enabling the attribute data to comprise basic attribute data, vehicle historical data and market dynamic data; according to the detection data, constructing a structured detection association relationship of the detection classification, the risk weight and the detection description; determining a context semantic vector according to the attribute data; and generating target vehicle detection report abstract data according to the structured detection association relationship and the context semantic vector. Fusion reasoning is carried out on the structured detection association relationship and the context semantic vector, and a vehicle detection report abstract in a natural language form is generated.

Description

Technical Field

[0001] This invention relates to the field of vehicle performance testing technology and related technical fields, specifically to a method, apparatus, equipment, and medium for interpreting vehicle testing reports. Background Technology

[0002] With the rapid development of the used car market, the demand for "quality transparency" in the vehicle resale process has become increasingly prominent. To ensure the right to know and the scientific basis of decision-making for both parties in the transaction, vehicle inspection, as a key step in assessing vehicle value and safety, has become one of the core links in the used car transaction process. Regardless of whether it is a C2C or B2C transaction model, vehicles almost always undergo a professional inspection process before entering the trading platform, resulting in a corresponding vehicle condition inspection report.

[0003] Currently, major used car platforms both domestically and internationally have established relatively standardized inspection and evaluation systems. These platforms primarily collect vehicle condition data across various dimensions through manual on-site inspections and some automated inspection tools, ultimately generating structured inspection reports. However, due to the highly specialized content, dense technical terminology, and large volume of information in these reports, ordinary consumers often struggle to understand the actual meaning of the inspection results in a short time. For example, the phrase "left front longitudinal beam sheet metal repair" might be difficult for users without vehicle structural knowledge to assess its impact on safety or vehicle price; similarly, terms like "severe carbon buildup on the throttle body" lack intuitive understanding. Existing technologies have developed preliminary solutions for summarizing vehicle condition reports, mainly through template generation and keyword suggestions. While these methods have some practicality, especially in rapidly deploying during platform expansion, they exhibit significant shortcomings in semantic expression, contextual understanding, personalized suggestions, and interactivity.

[0004] Given the problems with existing technologies, there is an urgent need for a method to interpret vehicle inspection reports. Summary of the Invention

[0005] The embodiments described herein provide a method, apparatus, device, and medium for interpreting vehicle inspection reports, enabling the fusion and reasoning of structured inspection correlations with contextual semantic vectors to generate a vehicle inspection report summary in natural language form.

[0006] Firstly, based on the content of this disclosure, a method for interpreting vehicle inspection reports is provided, including: Acquire detection data and attribute data of the target vehicle, wherein the attribute data includes basic attribute data, vehicle historical data, and market dynamic data; Based on the detection data, a structured detection association relationship is constructed, consisting of detection classification, risk weight, and detection description. Based on the attribute data, determine the context semantic vector; Based on the structured detection association and the contextual semantic vector, a target vehicle detection report summary data is generated.

[0007] In some embodiments of this disclosure, constructing a structured detection association relationship based on the detection data, including detection classification, risk weight, and detection description, includes: Based on the detection data, determine the detection items under different detection categories and the detection information corresponding to each detection item; Based on the detection information of each detection item under different detection categories, a structured detection association relationship is constructed, consisting of detection categories, risk weights, and detection descriptions.

[0008] In some embodiments of this disclosure, the step of constructing a structured detection association relationship of detection classification, risk weight, and detection description based on the detection information of each detection item under different detection classifications includes: Based on the detection information of each detection item under different detection categories, determine the sub-risk weights of each detection item under different detection categories; Based on the sub-risk weights of each test item under the same test category, determine the risk weights and test descriptions for each test category; Based on the risk weights and detection descriptions of different detection categories, a structured detection association relationship is constructed between detection categories, risk weights, and detection descriptions.

[0009] In some embodiments of this disclosure, determining the risk weight and detection description of each detection category based on the sub-risk weights of each detection item under the same detection category includes: Based on the sub-risk weights of each detection item under the same detection category, select the target detection item whose sub-risk weight is greater than or equal to the preset sub-risk weight; The risk weight of the detection category is determined based on the sub-risk weight of the target detection item; A detection description is generated based on the sub-risk weights of the target detection item and the detection information of the target detection item.

[0010] In some embodiments of this disclosure, determining the context semantic vector based on the attribute data includes: Based on the data information of the data items included in the attribute data under the different attribute categories, the wear information, cost-effectiveness information and power information of the target vehicle are determined. The wear information includes wear weight information and wear description information, the cost-effectiveness information includes cost-effectiveness weight information and cost-effectiveness description information, and the power information includes power weight information and power description information. Based on the wear information, cost-effectiveness information, and power information, a contextual semantic vector is determined, wherein the contextual semantic vector includes vehicle condition description information and usage scenario suggestion information.

[0011] In some embodiments of this disclosure, determining the wear information, cost-effectiveness information, and power information of the target vehicle based on the data information of the data items included in the attribute data under the different attribute classifications includes: Based on the data items included in the attribute data under different attribute categories, determine multiple first data item groups that are related to wear information, multiple second data item groups that are related to cost-effectiveness information, and multiple third data item groups that are related to power information. Based on the data information of each first data item included in each first data item group, determine the wear weight information and wear description information corresponding to each first data item group; Based on the data information of the second data items included in each second data item group, determine the cost-performance weight information and cost-performance description information corresponding to each second data item group; Based on the data information of the third data items included in each third data item group, determine the power weight information and power description information corresponding to each third data item group.

[0012] In some embodiments of this disclosure, generating target vehicle detection report summary data based on the structured detection association and the context semantic vector includes: The target detection category is determined based on the risk weight of each detection category in the structured detection association. Based on the sub-risk weights of each detection item in the target detection classification, generate vehicle condition problem description data for the target vehicle; Based on the vehicle condition problem description data and contextual semantic vector, a summary data of the detection report for the target vehicle is generated.

[0013] Secondly, according to the content of this disclosure, a vehicle inspection report interpretation device is provided, comprising: The data acquisition module is used to acquire the detection data and attribute data of the target vehicle, wherein the attribute data includes basic attribute data, vehicle historical data and market dynamic data; The association construction module is used to construct structured detection associations of detection classification, risk weight and detection description based on the detection data; A semantic vector determination module is used to determine a context semantic vector based on the attribute data; The report data generation module is used to generate target vehicle detection report summary data based on the structured detection association and the context semantic vector.

[0014] Thirdly, according to this disclosure, a computer device is provided, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any of the first aspects.

[0015] Fourthly, according to this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods described in any of the first aspects.

[0016] The vehicle inspection report interpretation method, apparatus, device, and medium provided in this disclosure first acquire the inspection data and attribute data of the target vehicle; then, based on the inspection data, construct a structured inspection association relationship of inspection classification, risk weight, and inspection description; and determine the contextual semantic vector based on the attribute data; finally, generate the target vehicle inspection report summary data based on the structured inspection association relationship and the contextual semantic vector. This achieves the fusion and reasoning of the structured inspection association relationship and the contextual semantic vector to generate a vehicle inspection report summary in natural language form, ensuring that the output language content meets high-quality standards in terms of accuracy, professionalism, and user readability, effectively enhancing user trust and platform compliance.

[0017] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments will be briefly described below. It should be understood that the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure, wherein: Figure 1 This is a flowchart illustrating a method for interpreting a vehicle inspection report provided in this embodiment of the disclosure; Figure 2 This is a schematic diagram of the structure of a vehicle inspection report interpretation device provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure.

[0019] In the accompanying diagram, markers with the same last two digits correspond to the same elements. It should be noted that the elements in the diagram are schematic and not drawn to scale. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are also within the scope of protection of this disclosure.

[0021] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this subject matter pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the specification and in the relevant art, and shall not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, the statement of “connecting” or “coupling” two or more parts together shall mean that these parts are directly joined together or joined through one or more intermediate components.

[0022] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of the phrase "embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] In this article, the term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists, A and B exist simultaneously, or B exists. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0024] Furthermore, in all embodiments of this disclosure, terms such as “first” and “second” are used only to distinguish one component (or part of a component) from another component (or another part of a component).

[0025] In the description of this application, unless otherwise stated, "multiple" means two or more (including two), and similarly, "multiple groups" means two or more (including two groups).

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0027] In view of the problems existing in the prior art, this disclosure provides a method for interpreting vehicle inspection reports. Figure 1 This is a flowchart illustrating a vehicle report interpretation method provided in this embodiment of the disclosure, such as... Figure 1 As shown, the methods for interpreting vehicle reports include: S110. Obtain the detection data and attribute data of the target vehicle.

[0028] The attribute data includes basic attribute data, vehicle historical data, and market dynamic data.

[0029] In a specific implementation, the inspection data of the target vehicle includes inspection data corresponding to different inspection categories. Specifically, the inspection data categories include inspection data of the frame and structural components, inspection data of the exterior, inspection data of the interior, inspection data of the operating condition, and inspection data of special inspection items. Among them, the inspection items of the frame and structural components inspection data include A-pillar, B-pillar, C-pillar, longitudinal beams, anti-collision beams, and chassis crossbeams; the inspection items of the exterior inspection data include paint defects, clear coat marks, paint discoloration, and local paint peeling; the inspection items of the interior inspection data include seats, steering wheel, dashboard, and door panel buttons; the inspection items of the operating condition inspection data include engine, transmission, chassis, suspension, and brakes; and the inspection items of the special inspection data include water damage, fire damage, suspected odometer tampering, and accident traces.

[0030] The target vehicle's attribute data includes attribute data under different attribute categories. Specifically, it includes basic attribute data, vehicle historical data, and market dynamic data. Among them, basic attribute data includes brand, model, launch date, vehicle class, engine displacement, fuel type, drive type, vehicle age, odometer reading, national emission standards, and whether it is subject to transfer restrictions. Vehicle historical data includes the number of ownership transfers (reflecting the frequency of vehicle turnover), operating nature (commercial vehicle, ride-hailing vehicle, non-commercial vehicle), and the previous owner's maintenance patterns (inferred from maintenance records). Market dynamic data includes the current model's search popularity on the platform, the average transaction price and number of similar vehicles for sale, the average time platform users spend on the model and the proportion of users who favorite it, as well as user profiles (such as novice drivers, commercial users, and family users).

[0031] To enable the parsing of test reports provided by different testing institutions, the vehicle test report interpretation method provided in this disclosure can parse test data from different testing institutions, different equipment, and different formats. That is, it can be understood that the test data received in this disclosure includes, but is not limited to: structured data such as JSON, XML, and CSV; semi-structured data such as Excel and PDF OCR recognition results; real-time data streams pushed by APIs; and data output by image recognition systems (such as paint thickness gauge readings and chassis image analysis results).

[0032] After receiving test reports from different testing institutions, the system uses a field normalization method based on rule matching and semantic vector similarity calculation to automatically identify and standardize the meaning of fields from different testing institutions (for example, "Front_Left_Frame", "Left Front Longitudinal Beam", "FL_Frame", etc. can be identified as the same type of field), thereby significantly improving the access capability of multi-source heterogeneous data and achieving unified adaptation across platforms and standards.

[0033] Therefore, in this embodiment of the disclosure, after obtaining the detection data of the target vehicle, the detection data is subjected to field identification and standardization processing by a field normalization method based on rule matching and semantic vector similarity calculation. This embodiment of the disclosure does not provide specific details on this process.

[0034] S120. Based on the detection data, construct a structured detection association relationship of detection classification, detection items, risk weights and detection descriptions.

[0035] After obtaining the detection data of the target vehicle, the sub-risk weights of each detection item included in each detection category are determined based on the detection data of each detection category. Then, based on the sub-risk weights of the detection items belonging to the same detection category, the risk weights and detection descriptions of each detection category are determined. Finally, based on the risk weights and detection descriptions of different detection categories, a structured detection association relationship of detection categories, risk weights, and detection descriptions is constructed.

[0036] In a specific implementation, a structured detection association relationship of detection classification, risk weight and detection description is constructed based on the detection data, including: determining the detection items under different detection classifications and the detection information corresponding to each detection item based on the detection data; and constructing a structured detection association relationship of detection classification, risk weight and detection description based on the detection information of each detection item under different detection classifications.

[0037] Specifically, based on the detection information of each detection item under different detection categories, a structured detection association relationship of detection category, risk weight, and detection description is constructed, including: determining the sub-risk weight of each detection item under different detection categories based on the detection information of each detection item under different detection categories; determining the risk weight and detection description of each detection category based on the sub-risk weight of each detection item under the same detection category; and constructing a structured detection association relationship of detection category, risk weight, and detection description based on the risk weight and detection description of different detection categories.

[0038] In one possible implementation, the risk weight and detection description of each detection category are determined based on the sub-risk weights of each detection item under the same detection category. This includes: selecting a target detection item whose sub-risk weight is greater than or equal to a preset sub-risk weight based on the sub-risk weights of each detection item under the same detection category; determining the risk weight of the detection category to which the target detection item belongs based on the sub-risk weights of the target detection item; and generating a detection description of the detection category to which the target detection item belongs based on the sub-risk weights of the target detection item and the target detection item.

[0039] In a specific example, firstly, the detection information corresponding to each detection item in the detection category of skeleton and structural components is obtained. Then, based on the detection information corresponding to each detection item in the detection category of skeleton and structural components, the sub-risk weight of each detection item under the detection category is determined. Then, based on the sub-risk weight of each detection item under the detection category, target detection items with sub-risk weights greater than or equal to preset sub-risk weights are selected. Finally, based on the detection information of the target detection items determined under the detection category and the sub-risk weights corresponding to each target detection item, the detection description of the detection category is determined, and based on the sub-risk weights of the target detection items under the detection category, the risk weight of the detection category is determined.

[0040] For example, based on the inspection information of the A-pillar, B-pillar, C-pillar, longitudinal beam, anti-collision beam, and chassis crossbeam (the inspection information includes information on disassembly, welding, sheet metal repair, structural deformation, stress marks, etc.), the sub-risk weight of each inspection item can be determined. Then, target inspection items with sub-risk weights greater than or equal to preset sub-risk weights are selected. The average of the sub-risk weights of the selected target inspection items is then calculated to determine the risk weight of the inspection category. Finally, based on the sub-risk weights of each target inspection item and the inspection information of each target inspection item, an inspection description for the inspection category is generated.

[0041] For example, if the detection information for the longitudinal beam in the skeleton and structural component detection category is sheet metal repair, and only the sub-risk weight of the longitudinal beam is greater than the preset sub-risk weight, then the risk weight corresponding to the skeleton and structural component detection category is the sub-risk weight of the longitudinal beam, and the detection description corresponding to the skeleton and structural component detection category is "structural component repair is a high-risk problem".

[0042] Furthermore, the specific process of determining the sub-risk weights of each test item under different test categories based on the test information of each test item under different test categories is as follows: standard sub-risk weights of each test item under different test information are pre-set in the risk weight database. After obtaining the test data of the target vehicle, the sub-risk weights corresponding to the test information under the test category and test item are obtained from the risk weight database based on the test information of each test item under different test categories. This disclosure embodiment does not provide a specific description of this.

[0043] S130. Determine the context semantic vector based on the attribute data.

[0044] In a specific implementation, the context semantic vector is determined based on the attribute data, including: determining the wear information, cost-effectiveness information, and power information of the target vehicle based on the data information of the data items included in the attribute data under different attribute categories; and determining the context semantic vector based on the wear information, cost-effectiveness information, and power information, wherein the context semantic vector includes vehicle condition description information and usage scenario suggestion information.

[0045] Specifically, based on the data information of the data items included in the attribute data under different attribute categories, the wear information, cost-effectiveness information, and power information of the target vehicle are determined. This includes: determining multiple first data item groups that are related to wear information, multiple second data item groups that are related to cost-effectiveness information, and multiple third data item groups that are related to power information, based on the data items included in the attribute data under different attribute categories; determining wear weight information and wear description information corresponding to each first data item group based on the data information of each first data item group; determining cost-effectiveness weight information and cost-effectiveness description information corresponding to each second data item group based on the data information of each second data item group; and determining power weight information and power description information corresponding to each third data item group based on the data information of each third data item group.

[0046] Specifically, the target vehicle's attribute data includes basic attribute data, vehicle history data, and time-based dynamic data. In other words, the attribute data of the target vehicle is categorized into basic attribute data, vehicle history data, and time-based dynamic data, with different data items under each category. Basic attribute data items include brand, model, launch date, vehicle class, engine displacement, fuel type, drive type, vehicle age, odometer reading, national emission standards, and whether there are restrictions on vehicle transfer. Vehicle history data items include the number of ownership transfers, operating nature, and maintenance patterns of previous owners. Market dynamic data items include the current model's search popularity on the platform, the average transaction price and number of similar vehicles for sale, the average time platform users spend on the model, the proportion of users who favorite it, and user profiles.

[0047] In a specific example, the mileage data item in the basic attribute data and the operational nature data item in the vehicle history data are correlated with the power information of the target vehicle; the vehicle age data item in the basic attribute data and the maintenance pattern data item of the previous owner in the vehicle history data are correlated with the wear and tear information of the target vehicle; the search popularity data item of the current model on the platform in the market dynamics data and the brand data item, vehicle age data item, and mileage data item in the basic attribute data are correlated with the cost-effectiveness information of the target vehicle.

[0048] Therefore, by classifying the data items included in the attribute data under different attribute categories, multiple first data item groups that are related to wear information, multiple second data item groups that are related to cost-effectiveness information, and multiple third data item groups that are related to power information are identified.

[0049] It should be noted that the first data item group that is related to wear information may include one group or multiple groups. Each first data item group may include two first data items or multiple first data items. This disclosure does not specifically limit this. Similarly, the second data item group that is related to cost-effectiveness information may include one group or multiple groups, and the third data item that is related to power information may also include one group or multiple groups.

[0050] After identifying the first data item group related to wear information, the second data item group related to cost-effectiveness information, and the third data item group related to power information, the sub-wear weight information of the first data item group is first determined based on the data information of each first data item included in the first data item group. The average of the sub-wear weight information of each first data item included in the first data item group is then calculated to obtain the wear weight information of the first data item group. Based on the first data item included in the first data item group and the wear weight information of the first data item group, the wear description information of the first data item group is generated. This process is repeated to determine the wear weight information and wear description information of the second data item group. After determining the wear weight information and wear description information of each first data item group, the cost-effectiveness weight information and cost-effectiveness description information corresponding to each second data item group, as well as the power weight information and power description information corresponding to each third data item group, are determined using the same method described above.

[0051] Furthermore, by pre-setting standard sub-risk weights for each data item under different attribute categories and under different data information in the risk weight database, after obtaining the attribute data of the target vehicle, the sub-risk weights corresponding to the data information under the attribute category and data item are obtained from the risk weight database based on the data information of each data item under different attribute categories. This embodiment of the present disclosure will not provide specific details on this.

[0052] Finally, based on wear and tear information, cost-effectiveness information, and power information, a contextual semantic vector is determined. The contextual semantic vector includes vehicle condition description information and usage scenario suggestion information.

[0053] Specifically, determining the context semantic vector based on wear information, cost-effectiveness information, and power information includes: selecting the first target data item group with the largest wear weight, the second target data item group with the largest cost-effectiveness weight, and the third target data item group with the largest power weight based on the wear weight information of each first data item group, the cost-effectiveness weight information of each second data item group, and the power weight information of each third data item group; then determining the target data item group (the target data item group is the data item group with the largest weight information among the first, second, and third target data item groups) based on the wear weight information corresponding to the first target data item group, the cost-effectiveness weight information corresponding to the second target data item group, and the power weight information corresponding to the third target data item group; and finally generating the context semantic vector based on the target data item group and the data items included in the target data item group.

[0054] In a specific example, a first data item group that is associated with wear information includes a vehicle age data item and a previous owner's maintenance pattern data item. If the vehicle age data item indicates a 10-year-old vehicle and the previous owner's maintenance pattern data item indicates 3 maintenance records, the determined sub-wear weight information of the vehicle age data item is the first sub-wear weight information, and the determined sub-wear weight information of the previous owner's maintenance pattern data item is the second sub-wear weight information. In this case, the wear weight information of the first data item group is the average of the first and second sub-wear weight information. Then, based on the first data items included in the first data item group and the wear weight information of the first data item group, wear description information of the first data item group is generated. For example, if the wear weight information of the first data item group is high wear weight information, then the generated wear description information of the first data item group is: the vehicle's power system has a lot of wear, and it is not recommended to buy it.

[0055] S140. Generate target vehicle detection report summary data based on structured detection associations and contextual semantic vectors.

[0056] In a specific implementation, target vehicle inspection report summary data is generated based on structured detection associations and contextual semantic vectors, including: determining the target detection category based on the risk weights of each detection category in the structured detection associations; generating vehicle condition problem description data of the target vehicle based on the sub-risk weights of each detection item in the target detection category; and generating target vehicle inspection report summary data based on the vehicle condition problem description data and contextual semantic vectors.

[0057] The structured detection associations generated in step S120 include risk weights and detection descriptions corresponding to different detection categories. Step S130 determines the contextual semantic vector based on the attribute data. Then, step S140 generates the target vehicle detection report summary data based on the structured detection associations and the contextual semantic vector. The specific process of generating the target vehicle detection report summary data based on the structured detection associations and the contextual semantic vector includes: First, based on the risk weights of each detection category in the structured detection association, the target detection category with the highest risk weight value is determined. Then, based on the sub-risk weights of each detection item in the target detection category, vehicle condition problem description data of the target vehicle is generated. That is, based on the sub-risk weights of each detection item in the target detection category, the vehicle condition problem description data of the detection item with the highest sub-risk weight value is generated. Finally, based on the vehicle condition problem description data and the context semantic vector, the detection report summary data of the target vehicle is generated.

[0058] A specific example, if the detection data of the target vehicle: The engine has a slight oil leak, the right front fender has undergone sheet metal repairs, and the interior has normal wear and tear.

[0059] The results generated when the attribute data is different are completely different: The attribute data is: vehicle age 2 years, mileage 20,000, non-commercial, high market demand; At this point, the generated target vehicle inspection report summary data is: "Minor oil seepage is normal wear and tear, the vehicle is in good overall condition and suitable as a daily commuter vehicle." The attribute data is: vehicle age 8 years, mileage 160,000 km, and it is an operational vehicle; At this point, the generated target vehicle inspection report summary data is: "The vehicle has multiple areas of wear and tear, and engine oil leakage requires close attention. Prolonged high-load use is not recommended." The vehicle inspection report interpretation method provided in this disclosure first obtains the inspection data and attribute data of the target vehicle; then, based on the inspection data, it constructs a structured inspection association relationship of inspection classification, risk weight, and inspection description; and determines the contextual semantic vector based on the attribute data; finally, it generates the target vehicle inspection report summary data based on the structured inspection association relationship and the contextual semantic vector. This method achieves fusion reasoning between the structured inspection association relationship and the contextual semantic vector, generating a vehicle inspection report summary in natural language form. This ensures that the output language content meets high-quality standards in terms of accuracy, professionalism, and user readability, effectively enhancing user trust and platform compliance.

[0060] Based on the above embodiments, this disclosure also provides a vehicle inspection report interpretation device. Figure 2 This is a schematic diagram of the structure of a vehicle inspection report interpretation device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, the vehicle inspection report interpretation device includes: The data acquisition module 210 is used to acquire the detection data and attribute data of the target vehicle, wherein the attribute data includes basic attribute data, vehicle historical data and market dynamic data; The association construction module 220 is used to construct structured detection associations of detection classification, risk weight and detection description based on the detection data; The semantic vector determination module 230 is used to determine the context semantic vector based on the attribute data; The report data generation module 240 is used to generate target vehicle detection report summary data based on structured detection correlations and contextual semantic vectors.

[0061] The vehicle inspection report interpretation device provided in this embodiment first acquires the inspection data and attribute data of the target vehicle; then, based on the inspection data, it constructs a structured inspection association relationship of inspection classification, risk weight, and inspection description; and determines the contextual semantic vector based on the attribute data; finally, it generates the target vehicle inspection report summary data based on the structured inspection association relationship and the contextual semantic vector. This device achieves fusion reasoning between the structured inspection association relationship and the contextual semantic vector, generating a vehicle inspection report summary in natural language form. This ensures that the output language content meets high-quality standards in terms of accuracy, professionalism, and user readability, effectively enhancing user trust and platform compliance.

[0062] In a specific implementation, the step of constructing a structured detection association relationship based on the detection data, including detection classification, risk weight, and detection description, includes: Based on the detection data, determine the detection items under different detection categories and the detection information corresponding to each detection item; Based on the detection information of each detection item under different detection categories, a structured detection association relationship is constructed, consisting of detection categories, risk weights, and detection descriptions.

[0063] In a specific implementation, the step of constructing a structured detection association relationship based on the detection information of each detection item under different detection categories, including: Based on the detection information of each detection item under different detection categories, determine the sub-risk weights of each detection item under different detection categories; Based on the sub-risk weights of each test item under the same test category, determine the risk weights and test descriptions for each test category; Based on the risk weights and detection descriptions of different detection categories, a structured detection association relationship is constructed between detection categories, risk weights, and detection descriptions.

[0064] In a specific implementation, determining the risk weight and detection description of each detection category based on the sub-risk weights of each detection item under the same detection category includes: Based on the sub-risk weights of each detection item under the same detection category, select the target detection item whose sub-risk weight is greater than or equal to the preset sub-risk weight; The risk weight of the detection category is determined based on the sub-risk weight of the target detection item; A detection description is generated based on the sub-risk weights of the target detection item and the detection information of the target detection item.

[0065] In a specific implementation, determining the context semantic vector based on the attribute data includes: Based on the data information of the data items included in the attribute data under the different attribute categories, the wear information, cost-effectiveness information and power information of the target vehicle are determined. The wear information includes wear weight information and wear description information, the cost-effectiveness information includes cost-effectiveness weight information and cost-effectiveness description information, and the power information includes power weight information and power description information. Based on the wear information, cost-effectiveness information, and power information, a contextual semantic vector is determined, wherein the contextual semantic vector includes vehicle condition description information and usage scenario suggestion information.

[0066] In a specific implementation, determining the wear information, cost-effectiveness information, and power information of the target vehicle based on the data information of the data items included in the attribute data under the different attribute categories includes: Based on the data items included in the attribute data under different attribute categories, determine multiple first data item groups that are related to wear information, multiple second data item groups that are related to cost-effectiveness information, and multiple third data item groups that are related to power information. Based on the data information of each first data item included in each first data item group, determine the wear weight information and wear description information corresponding to each first data item group; Based on the data information of the second data items included in each second data item group, determine the cost-performance weight information and cost-performance description information corresponding to each second data item group; Based on the data information of the third data items included in each third data item group, determine the power weight information and power description information corresponding to each third data item group.

[0067] In a specific implementation, generating target vehicle detection report summary data based on the structured detection association and the context semantic vector includes: The target detection category is determined based on the risk weight of each detection category in the structured detection association. Based on the sub-risk weights of each detection item in the target detection classification, generate vehicle condition problem description data for the target vehicle; Based on the vehicle condition problem description data and contextual semantic vector, a summary data of the detection report for the target vehicle is generated.

[0068] This application also provides a computer device, please refer to the following for details. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0069] The computer device includes a memory 510 and a processor 520 that are interconnected via a system bus. It should be noted that only a computer device with components 510-520 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components may be implemented alternatively. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0070] Computer devices can include desktop computers, laptops, handheld computers, and cloud servers. These devices allow for human-computer interaction with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0071] The memory 510 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. RAM may include static RAM or dynamic RAM. In some embodiments, the memory 510 may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory 510 may also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card equipped on the computer device. Of course, the memory 510 may include both internal storage units and external storage devices of the computer device. In this embodiment, the memory 510 is typically used to store the operating system and various application software installed on the computer device, such as the program code of the method described above. In addition, the memory 510 may also be used to temporarily store various types of data that have been output or will be output.

[0072] The processor 520 is typically used to perform the overall operation of a computer device. In this embodiment, the memory 510 is used to store program code or instructions, including computer operation instructions. The processor 520 is used to execute the program code or instructions stored in the memory 510 or to process data, such as program code that runs the methods described above.

[0073] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus system can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0074] Another embodiment of this application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method; and to generate means for implementing the functional actions specified in each block or combination of blocks in the block diagram.

[0075] Computer-readable media include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any suitable combination thereof, wherein the memory is used to store program code or instructions, the program code including computer operation instructions, and the processor is used to execute the program code or instructions of the above-described methods stored in the memory.

[0076] The definitions of memory and processor can be found in the description of the foregoing computer device embodiments, and will not be repeated here.

[0077] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0078] In the various embodiments of this application, the functional units or modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0079] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] Unless otherwise expressly indicated by the context, the singular form of words used herein and in the appended claims includes the plural form, and vice versa. Thus, when referring to the singular, the plural form of the corresponding term is generally included. Similarly, the terms “comprising” and “including” shall be interpreted as including rather than exclusively. Likewise, the terms “including” and “or” shall be interpreted as including unless such interpretation is expressly prohibited herein. Where the term “example” is used herein, particularly when it follows a set of terms, the “example” is merely exemplary and illustrative and should not be considered exclusive or extensive.

[0081] Further aspects and scope of adaptation become apparent from the description provided herein. It should be understood that various aspects of this application may be implemented individually or in combination with one or more other aspects. It should also be understood that the descriptions and specific embodiments herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0082] Several embodiments of this disclosure have been described in detail above. However, it is obvious that those skilled in the art can make various modifications and variations to the embodiments of this disclosure without departing from the spirit and scope of this disclosure. The scope of protection of this disclosure is defined by the appended claims.

Claims

1. A vehicle detection report interpretation method, characterized by, include: Acquire detection data and attribute data of the target vehicle, wherein the attribute data includes basic attribute data, vehicle historical data, and market dynamic data; Based on the detection data, a structured detection association relationship is constructed, consisting of detection classification, risk weight, and detection description. Based on the attribute data, determine the context semantic vector; Based on the structured detection association and the contextual semantic vector, a target vehicle detection report summary data is generated.

2. The method according to claim 1, characterized in that, The step of constructing a structured detection association relationship based on the detection data, including detection classification, risk weight, and detection description, includes: Based on the detection data, determine the detection items under different detection categories and the detection information corresponding to each detection item; Based on the detection information of each detection item under different detection categories, a structured detection association relationship is constructed, consisting of detection categories, risk weights, and detection descriptions.

3. The method according to claim 2, characterized in that, The process of constructing a structured detection association relationship based on the detection information of each detection item under different detection categories, including: Based on the detection information of each detection item under different detection categories, determine the sub-risk weights of each detection item under different detection categories; Based on the sub-risk weights of each test item under the same test category, determine the risk weights and test descriptions for each test category; Based on the risk weights and detection descriptions of different detection categories, a structured detection association relationship is constructed between detection categories, risk weights, and detection descriptions.

4. The method according to claim 3, characterized in that, The process of determining the risk weight and detection description for each detection category based on the sub-risk weights of each detection item under the same detection category includes: Based on the sub-risk weights of each detection item under the same detection category, select the target detection item whose sub-risk weight is greater than or equal to the preset sub-risk weight; The risk weight of the detection category is determined based on the sub-risk weight of the target detection item; A detection description is generated based on the sub-risk weights of the target detection item and the detection information of the target detection item.

5. The method according to claim 1, characterized in that, Determining the context semantic vector based on the attribute data includes: Based on the data information of the data items included in the attribute data under the different attribute categories, the wear information, cost-effectiveness information and power information of the target vehicle are determined. The wear information includes wear weight information and wear description information, the cost-effectiveness information includes cost-effectiveness weight information and cost-effectiveness description information, and the power information includes power weight information and power description information. Based on the wear information, cost-effectiveness information, and power information, a contextual semantic vector is determined, wherein the contextual semantic vector includes vehicle condition description information and usage scenario suggestion information.

6. The method according to claim 5, characterized in that, The process of determining the wear information, cost-effectiveness information, and power information of the target vehicle based on the data information of the data items included in the attribute data under the different attribute categories includes: Based on the data items included in the attribute data under different attribute categories, determine multiple first data item groups that are related to wear information, multiple second data item groups that are related to cost-effectiveness information, and multiple third data item groups that are related to power information. Based on the data information of each first data item included in each first data item group, determine the wear weight information and wear description information corresponding to each first data item group; Based on the data information of the second data items included in each second data item group, determine the cost-performance weight information and cost-performance description information corresponding to each second data item group; Based on the data information of the third data items included in each third data item group, determine the power weight information and power description information corresponding to each third data item group.

7. The method according to claim 1, characterized in that, The step of generating target vehicle detection report summary data based on the structured detection association and the context semantic vector includes: The target detection category is determined based on the risk weight of each detection category in the structured detection association. Based on the sub-risk weights of each detection item in the target detection classification, generate vehicle condition problem description data for the target vehicle; Based on the vehicle condition problem description data and contextual semantic vector, a summary data of the detection report for the target vehicle is generated.

8. A vehicle inspection report interpretation device, characterized in that, include: The data acquisition module is used to acquire the detection data and attribute data of the target vehicle, wherein the attribute data includes basic attribute data, vehicle historical data and market dynamic data; The association construction module is used to construct structured detection associations of detection classification, risk weight and detection description based on the detection data; A semantic vector determination module is used to determine a context semantic vector based on the attribute data; The report data generation module is used to generate target vehicle detection report summary data based on the structured detection association and the context semantic vector.

9. A computer device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 7.

Images