AI-based diagnosis cost adjustment method and related apparatus

Abstract

This application provides an AI-based diagnostic fee adjustment method and related apparatus. The method includes: acquiring basic diagnostic data of a target vehicle; performing preliminary AI diagnosis on the basic diagnostic data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; determining a target diagnostic strategy based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only; determining a target diagnostic report based on the target diagnostic strategy; determining the AI ​​contribution based on the target diagnostic report; and determining the target diagnostic fee based on a preset basic fee standard and the AI ​​contribution. By constructing a differentiated human-machine collaboration process based on diagnostic confidence, quantifying the AI ​​contribution, and differentiating fees based on the AI ​​contribution, the accuracy of AI fault diagnosis applications and user engagement are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle diagnostic technology, and in particular to an AI-based diagnostic cost adjustment method and related apparatus. Background Technology

[0002] Currently, vehicle diagnostic systems have incorporated AI modules to assist human experts in completing diagnostic tasks. However, in practical applications, there is still significant room for improvement in the collaboration model between AI and humans, the quantification of contributions, and the cost adjustment mechanism. The lack of differentiated process design based on the reliability of AI diagnostic results leads to wasted expert resources or insufficient diagnostic accuracy. Furthermore, the diagnostic pricing mechanism is relatively simplistic and fails to consider the efficiency-enhancing effects of AI technology, resulting in a mismatch between user willingness to pay and service quality. This hinders both the incentive for users to utilize AI functions and the fair distribution of value between AI and human expertise.

[0003] Therefore, improving the accuracy of AI-based fault diagnosis applications and increasing user engagement is an urgent issue that needs to be addressed. Summary of the Invention

[0004] This application provides an AI-based diagnostic fee adjustment method and related apparatus. By constructing a differentiated human-machine collaboration process based on diagnostic confidence, establishing a quantifiable evaluation system for AI contribution, and designing a differentiated charging mechanism linked to AI contribution, the method improves the accuracy of AI fault diagnosis applications and increases user engagement.

[0005] In a first aspect, embodiments of this application provide an AI-based diagnostic cost adjustment method, the method comprising: Obtain basic diagnostic data for the target vehicle; A preliminary AI diagnosis is performed on the aforementioned diagnostic baseline data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; The target diagnostic strategy is determined based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only. A target diagnostic report is determined based on the aforementioned target diagnostic strategy; The AI ​​contribution is determined based on the target diagnostic report. The target diagnostic fee is determined based on the preset basic fee standard and the AI ​​contribution level.

[0006] Secondly, embodiments of this application provide an AI-based diagnostic cost adjustment device, the device comprising a data acquisition module, an AI diagnostic module, a first determination module, a second determination module, a third determination module, and a fourth determination module, wherein: The data acquisition module is used to acquire basic diagnostic data of the target vehicle; The AI ​​diagnostic module is used to perform preliminary AI diagnosis on the diagnostic basic data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; The first determining module is used to determine a target diagnostic strategy based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only; The second determining module is used to determine a target diagnostic report based on the target diagnostic strategy; The third determining module is used to determine the AI ​​contribution based on the target diagnostic report; The fourth determining module is used to determine the target diagnostic fee based on the preset basic charging standard and the AI ​​contribution.

[0007] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0009] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0010] By implementing the embodiments of this application, a differentiated human-machine collaboration process based on diagnostic confidence can be constructed, an AI contribution quantification evaluation system can be established, and a differentiated charging mechanism linked to AI contribution can be designed, thereby improving the accuracy of AI fault diagnosis applications and user enthusiasm. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a system architecture diagram of a vehicle fault remote diagnosis system provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 3 This is an application scenario diagram of a vehicle fault remote diagnosis system provided in an embodiment of this application; Figure 4 This is a flowchart illustrating an AI-based diagnostic cost adjustment method provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a target diagnostic strategy provided in an embodiment of this application; Figure 6 This is a schematic diagram of a process for determining the cost of a target diagnosis, provided in an embodiment of this application. Figure 7 This is a schematic diagram illustrating the composition of a breakdown list provided in an embodiment of this application; Figure 8 This is a functional module block diagram of an AI-based diagnostic cost adjustment device provided in an embodiment of this application. Detailed Implementation

[0013] 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. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0014] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0015] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0016] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0017] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0018] In this document, the term "embodiment" 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 this phrase 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.

[0019] Currently, vehicle diagnostic systems have incorporated AI modules to assist human experts in completing diagnostic tasks. However, in practical applications, there is still significant room for improvement in the collaboration model between AI and humans, the quantification of contributions, and the cost adjustment mechanism. The lack of differentiated process design based on the reliability of AI diagnostic results leads to wasted expert resources or insufficient diagnostic accuracy. Furthermore, the diagnostic pricing mechanism is relatively simplistic and fails to consider the efficiency-enhancing effects of AI technology, resulting in a mismatch between user willingness to pay and service quality. This hinders both the incentive for users to utilize AI functions and the fair distribution of value between AI and human expertise. Therefore, improving the accuracy and user engagement in AI-based fault diagnosis is an urgent issue that needs to be addressed.

[0020] To address the aforementioned issues, this application provides an AI-based diagnostic fee adjustment method and related apparatus. The method involves acquiring basic diagnostic data of a target vehicle; performing a preliminary AI diagnosis on the basic diagnostic data to obtain a first diagnostic result; the first diagnostic result including a preliminary diagnostic report; determining a target diagnostic strategy based on the preliminary diagnostic report; the target diagnostic strategy including any of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only; determining a target diagnostic report based on the target diagnostic strategy; determining the AI ​​contribution based on the target diagnostic report; and determining the target diagnostic fee based on a preset basic fee standard and the AI ​​contribution. By constructing a differentiated human-machine collaboration process based on diagnostic confidence, establishing a quantifiable evaluation system for AI contribution, and designing a differentiated fee mechanism linked to AI contribution, the accuracy of AI fault diagnosis applications and user engagement are improved.

[0021] For easier understanding, please refer to Figure 1 , Figure 1 This is a system architecture diagram of a remote vehicle fault diagnosis system provided in an embodiment of this application. The remote vehicle fault diagnosis system includes a data acquisition unit, an AI diagnosis unit, a strategy execution unit, and a cost settlement unit.

[0022] The data acquisition unit can collect basic vehicle information (such as vehicle model, fault codes, and vehicle operating parameters) and fault description information (such as fault symptoms and fault occurrence scenarios) from the user's terminal device. The data acquisition unit then performs integrity verification and format standardization on the collected data, removes invalid data, and outputs structured diagnostic basic data to the AI ​​diagnostic unit.

[0023] The AI ​​diagnostic unit analyzes vehicle operating parameters for anomalies and generates fault characteristics based on fault description information. It then uses a pre-defined AI diagnostic model to analyze fault codes and characteristics, obtaining a reference fault type. Simultaneously, the AI ​​diagnostic unit records the data processing volume and initial diagnostic time during the diagnostic process, generating diagnostic process data. By matching the data to a pre-defined fault type knowledge base, it determines the reference fault cause corresponding to the reference fault type. A two-dimensional similarity weighted calculation is then used to obtain the diagnostic confidence level. Finally, the AI ​​diagnostic unit generates a preliminary diagnostic report based on the reference fault type, reference fault cause, and diagnostic confidence level.

[0024] The strategy execution unit can match and execute differentiated diagnostic strategies based on the confidence level of the preliminary diagnostic report, ultimately generating the final target diagnostic report. The strategy execution unit can retrieve preset dual confidence thresholds (i.e., a first confidence threshold and a second confidence threshold), compare the diagnostic confidence level of the preliminary diagnostic report with the first and second confidence thresholds, and determine the target diagnostic strategy (e.g., AI-only diagnosis, AI-assisted human confirmation, or human-only diagnosis). If it is AI-only diagnosis, the preliminary diagnostic report is directly used as the final target diagnostic report. If it is AI-assisted human confirmation, AI-assisted information is generated based on the preliminary diagnostic report and diagnostic process data. First feedback information from human experts regarding the AI-assisted information is obtained, and the preliminary diagnostic report is then optimized based on this first feedback information to generate the target diagnostic report. If it is human-only diagnosis, standardized diagnostic data is pushed to human experts, and second feedback information is obtained based on the experts' independent diagnosis. The target diagnostic report is then generated based on this second feedback information. The strategy execution unit can record all process data, including diagnostic strategy type, human intervention duration, and report content, and synchronize this data to the fee settlement unit.

[0025] The fee settlement unit calculates the AI ​​contribution based on the target diagnostic report to achieve differentiated pricing and fee sharing. First, based on data such as the target diagnostic strategy, historical average human diagnostic time, total diagnostic time, and target human diagnostic time, the AI ​​contribution is quantified from three dimensions: diagnostic completion rate, efficiency improvement, and resource saving. Then, the basic diagnostic fee corresponding to the target fault type is matched, and combined with the AI ​​contribution and a preset diagnostic discount coefficient, the final target diagnostic fee is calculated. Finally, after deducting basic operating costs, the fee sharing between AI stakeholders and human experts is completed according to the AI ​​contribution, and the settlement and transfer are automatically executed.

[0026] It is evident that by implementing a closed-loop design encompassing data collection, AI diagnosis, strategy execution, and fee settlement, intelligent remote diagnosis of vehicle malfunctions and differentiated fee sharing can be achieved, significantly improving diagnostic efficiency, reducing labor costs, and protecting the interests of users, AI developers, and human experts.

[0027] The following is combined with Figure 2 The electronic devices in the embodiments of this application will be described. Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 2 As shown, the electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface via an internal communication bus.

[0028] The processor can be used for: Obtain basic diagnostic data for the target vehicle; A preliminary AI diagnosis is performed on the aforementioned diagnostic baseline data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; The target diagnostic strategy is determined based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only. A target diagnostic report is determined based on the aforementioned target diagnostic strategy; The AI ​​contribution is determined based on the target diagnostic report. The target diagnostic fee is determined based on the preset basic fee standard and the AI ​​contribution level.

[0029] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0030] The processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, transceiver, transceiver circuit, etc., and the storage unit can be a memory.

[0031] The memory can be volatile or non-volatile, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0032] It is understood that the electronic device may include more or fewer structural elements than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the electronic device may incorporate elements such as... Figure 1 The system architecture described above.

[0033] For easier understanding, please refer to Figure 3 , Figure 3This diagram illustrates an application scenario of a remote vehicle fault diagnosis system provided in this application. The user's terminal device initiates a remote vehicle fault diagnosis request to the system, which includes a fault description of the target vehicle. In response to the request, the system extracts the fault description information, generates a data acquisition instruction, and sends it to the target vehicle. The target vehicle, in response, sends its basic vehicle information back to the system. Based on the vehicle's basic information and the fault description, the system performs AI diagnosis, strategy execution, and cost settlement processes, generating a revenue-sharing breakdown. This breakdown is then sent back to the user's terminal device, containing information on diagnosis costs, AI-related party revenue sharing, and manual revenue sharing.

[0034] After understanding the software and hardware architecture of this application, the following will be combined with... Figure 4 This application describes an AI-based diagnostic cost adjustment method in its embodiments. Figure 4 This is a flowchart illustrating an AI-based diagnostic cost adjustment method provided in an embodiment of this application, specifically including the following steps: Step S401: Obtain basic diagnostic data for the target vehicle.

[0035] Specifically, the system can receive remote vehicle fault diagnosis requests initiated by users through terminal devices (such as in-vehicle smart terminals or mobile apps). Based on these requests, it generates data acquisition instructions and sends them to the target vehicle's on-board diagnostic system or cloud-based vehicle data platform. The on-board diagnostic system then obtains basic vehicle information, including but not limited to: vehicle model, vehicle age, fault codes, vehicle configuration parameters, vehicle operating parameters, and powertrain type. The remote fault diagnosis request includes fault description information, which includes but is not limited to: fault symptoms (e.g., engine vibration, warning light illumination), fault occurrence scenario (e.g., high-speed driving, cold start), fault duration, and fault triggering conditions. The system integrates the basic vehicle information and fault description information to obtain the target vehicle's diagnostic base data.

[0036] Step S402: Perform preliminary AI diagnosis on the diagnostic basic data to obtain the first diagnostic result.

[0037] The first diagnostic result includes a preliminary diagnostic report.

[0038] The first diagnostic result further includes diagnostic process data; the basic diagnostic data includes vehicle basic information and fault description information; the specific steps for performing preliminary AI diagnosis on the basic diagnostic data to obtain the first diagnostic result include: A1. Analyze the basic vehicle information to obtain the first fault code and vehicle operating parameters; A2. Determine the first fault characteristic based on the vehicle operating parameters and the fault description information; A3. Analyze the first fault code and the first fault characteristics according to the preset AI diagnostic model to obtain the reference fault type, data processing volume and preliminary diagnosis time. A4. Determine the diagnostic process data based on the data processing volume and the preliminary diagnosis duration; A5. Determine the reference fault cause corresponding to the reference fault type based on the preset fault type knowledge base; A6. Determine the diagnostic confidence level based on the reference fault type, the first fault code, and the first fault characteristic; A7. Determine the preliminary diagnostic report based on the reference fault type, the reference fault cause, and the diagnostic confidence level.

[0039] In a specific embodiment, firstly, the vehicle's basic information is subjected to integrity and validity verification. Invalid data (such as incorrectly formatted codes or missing key fields) and redundant data (such as vehicle decoration configuration information unrelated to fault diagnosis) are removed using preset data verification rules. Next, the first fault code (such as fault codes generated by the engine control module or transmission control module) and vehicle operating parameters are extracted from the vehicle's basic information. Then, outlier identification and temporal feature analysis are performed on the vehicle operating parameters. Abnormal fluctuation data (such as extreme values ​​caused by instantaneous sensor failures) are removed, and preset temporal sequence analysis algorithms (such as the sliding window method) are used to extract vehicle operating parameter features. Next, natural language processing is performed on the fault description information. Through algorithms such as word segmentation, entity recognition, and keyword extraction, core information is extracted from the user-input text description (or speech-to-text content) to obtain fault description keywords. The processed vehicle operating parameter features are then associated and mapped with the fault description keywords to form the first fault feature.

[0040] Next, a pre-set AI diagnostic model (which can be trained and generated based on historical fault diagnosis cases and adopts a deep learning network architecture) is invoked. The first fault code and the first fault feature are used as input to the model. The AI ​​diagnostic model outputs a reference fault type through reasoning processes such as fault code parsing and feature matching, historical case similarity comparison, and fault mechanism correlation analysis. Simultaneously, during the AI ​​diagnostic model's reasoning process, key process indicators can be statistically analyzed, namely, data processing volume (the total amount of effective data processed by the AI ​​diagnostic model during this diagnosis process, in KB / MB) and preliminary diagnosis time (the total time from receiving input data to outputting the reference fault type, in seconds). Then, data processing volume and preliminary diagnosis time are used as core indicators, supplemented with auxiliary indicators during the diagnosis process (such as the number of reasoning steps of the AI ​​diagnostic model, the number of feature matchings, and the confidence level change curve). These core and auxiliary indicators are then structurally integrated to obtain the diagnostic process data.

[0041] Next, a pre-defined fault type knowledge base is retrieved. This knowledge base is built based on vehicle fault repair manuals, historical diagnostic cases, manufacturer technical documents, and other materials, and stores the association mapping relationship between "fault type" and "fault cause." The reference fault type is used as a search keyword to perform precise matching in the fault type knowledge base, filtering out reference fault causes associated with that reference fault type. Finally, the diagnostic confidence is determined based on the reference fault type, the first fault code, and the first fault characteristic.

[0042] Finally, using the preset report template as a framework, the core content includes the reference fault type, reference fault cause, and diagnostic confidence level, while supplementing auxiliary information such as the first fault code and the first fault characteristic to generate a preliminary diagnostic report.

[0043] It is evident that by analyzing fault codes and fault characteristics through AI diagnostic models, preliminary diagnostic reports and diagnostic process data can be quickly output, providing accurate basis for subsequent differentiated diagnostic strategy selection, significantly improving diagnostic efficiency and reducing the upfront investment of human resources.

[0044] The specific steps for determining the diagnostic confidence level based on the reference fault type, the first fault code, and the first fault feature include: B1. Obtain the historical diagnostic case library corresponding to the model of the target vehicle; B2. Obtain the historical diagnostic case corresponding to the reference fault type from the historical diagnostic case library; B3. Determine the second fault code and second fault characteristic corresponding to the historical diagnostic cases; B4. Obtain the similarity between the first fault code and the second fault code to obtain the first similarity. B5. Obtain the similarity between the first fault feature and the second fault feature to obtain the second similarity. B6. Determine the diagnostic confidence level based on the first similarity and the second similarity.

[0045] In a specific embodiment, firstly, a historical diagnostic case library corresponding to the model of the target vehicle is obtained. Then, using the fault type as a search keyword, a precise matching search is performed in the historical diagnostic case library to obtain historical diagnostic cases corresponding to the reference fault type. Structured parsing and feature extraction are then performed on the historical diagnostic cases to obtain the second fault code and the second fault feature.

[0046] Next, the similarity between the first fault code and the second fault code is calculated to obtain the first similarity. Both the first fault feature and the second fault feature are converted into feature vectors, and the cosine similarity algorithm is used to calculate the similarity between the two feature vectors to obtain the second similarity.

[0047] Finally, based on the technical logic of fault diagnosis, differentiated weights are assigned to the first similarity (fault code matching) and the second similarity (fault feature matching) to obtain the first weight and the second weight. Then, the first similarity, the first weight, the second similarity, and the second weight are weighted and summed to obtain the diagnostic confidence score.

[0048] It is evident that by performing two-dimensional similarity matching on fault codes and fault characteristics of historical diagnostic cases of the same vehicle model, the reliability of preliminary AI diagnostic conclusions can be accurately quantified, providing an objective and traceable basis for the selection of differentiated diagnostic strategies.

[0049] Step S403: Determine the target diagnostic strategy based on the preliminary diagnostic report.

[0050] The target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and human determination, or human-only diagnosis.

[0051] For easier understanding, please refer to Figure 5 , Figure 5 This is a flowchart illustrating a method for determining a target diagnostic strategy according to an embodiment of this application. The specific steps for determining the target diagnostic strategy based on the preliminary diagnostic report include: C1. Obtain a preset first confidence threshold and a second confidence threshold; the first confidence threshold is greater than the second confidence threshold; C2. If the diagnostic confidence level is greater than or equal to the first confidence level threshold, then the target diagnostic strategy is determined to be the AI-only diagnosis. C3. If the diagnostic confidence level is greater than the second confidence level threshold and less than the first confidence level threshold, then the target diagnostic strategy is determined to be AI-assisted and human-determined. C4. If the diagnostic confidence level is less than or equal to the second confidence threshold, then the target diagnostic strategy is determined to be manual diagnosis only.

[0052] In a specific embodiment, firstly, based on big data analysis of historical diagnostic cases corresponding to the target vehicle model, and combined with industry standards for fault diagnosis and the experience of human experts, two levels of confidence thresholds are pre-set: a first confidence threshold and a second confidence threshold, with the first confidence threshold being greater than the second confidence threshold. The first confidence threshold corresponds to the scenario where "the AI ​​diagnostic conclusion is completely reliable and requires no human intervention," and its value is typically set at 85%. The second confidence threshold corresponds to the critical scenario where "the AI ​​diagnostic conclusion has reference value but requires human review; or the AI ​​conclusion is not reliable enough and requires human-led diagnosis," and its value is typically set at 60%. It should be noted that the two levels of confidence thresholds can be iteratively optimized based on the accuracy data of newly added diagnostic cases to ensure the matching degree between the confidence thresholds and the actual diagnostic scenarios.

[0053] Then, the diagnostic confidence level is compared with two levels of confidence thresholds. If the diagnostic confidence level is greater than or equal to the first confidence threshold (e.g., the diagnostic confidence level is 92% and the first confidence threshold is 85%), the reliability of the current preliminary diagnostic report is determined to meet the standard of "no human intervention required", and the target diagnostic strategy is directly determined to be AI-only diagnosis. If the diagnostic confidence level is greater than the second confidence threshold and less than the first confidence threshold, the current preliminary diagnostic report is determined to have high reference value, but still needs to be verified and corrected by human experts, and the target diagnostic strategy is determined to be AI-assisted and human confirmation. If the diagnostic confidence level is less than or equal to the second confidence threshold, the reliability of the current preliminary diagnostic report is determined to be low and insufficient as a diagnostic reference, and the target diagnostic strategy is determined to be human diagnosis only.

[0054] It is evident that by using a dual-threshold confidence grading mechanism, intelligent matching of diagnostic strategies can be achieved, ensuring both efficient AI diagnosis in high-confidence scenarios and precise human intervention for complex faults with low confidence, thereby optimizing the allocation of diagnostic resources.

[0055] Step S404: Determine the target diagnosis report according to the target diagnosis strategy.

[0056] The specific steps for determining the target diagnostic report based on the target diagnostic strategy include: D1. If the target diagnostic strategy is AI-only diagnosis, then the preliminary diagnostic report is determined to be the target diagnostic report; D2. If the target diagnostic strategy is AI-assisted and human-determined, then the AI-assisted information is determined based on the preliminary diagnostic report and the diagnostic process data. D3. Obtain the first feedback information from the target expert group regarding the AI-assisted information; the target expert group is any one of a preset plurality of expert groups; D4. Adjust the preliminary diagnostic report based on the first feedback information to obtain the target diagnostic report; D5. If the target diagnostic strategy is manual diagnosis only, then obtain the second feedback information of the target expert group on the diagnostic basic data. D6. Determine the target diagnostic report based on the second feedback information.

[0057] In a specific embodiment, if the target diagnostic strategy is determined to be AI-only diagnostic, then the preliminary diagnostic report generated in the preliminary AI diagnostic stage is directly determined as the final target diagnostic report.

[0058] If the target diagnostic strategy determines that it involves both AI assistance and human verification, the preliminary diagnostic report and diagnostic process data are automatically integrated to generate standardized AI-assisted information. This AI-assisted information uses a structured document format, ensuring that human experts can quickly extract core reference content without repeatedly parsing the original diagnostic data. Then, the AI-assisted information is pushed to a target expert group to support manual confirmation. This target expert group can be any one of several pre-defined expert groups. Next, the first feedback from the target expert group regarding the AI-assisted information is obtained. This feedback includes, but is not limited to, verification conclusions on the reference fault type and supplementary or corrective information on the reference fault cause. Finally, according to pre-defined adjustment rules, the expert opinions in the first feedback information are merged with the preliminary diagnostic report to obtain the target diagnostic report. For example, content verified by experts (such as reference fault types) is directly retained; content with expert correction suggestions (such as adding fault causes) is supplemented; and solutions with expert optimization suggestions (such as adjusting maintenance procedures) are iteratively updated.

[0059] If the target diagnostic strategy determines that manual diagnosis is the only option, the basic diagnostic data is directly pushed to the matched target expert group. This expert group independently conducts fault analysis, troubleshooting, and localization based on the original diagnostic data, ultimately generating a second feedback message that includes the fault type, fault cause, solution, and diagnostic basis. Then, the second feedback message from the target expert group is structured and organized according to a preset report template to generate a target diagnostic report.

[0060] It is evident that by deeply integrating the target diagnostic strategy with the report generation process, differentiated output of target diagnostic reports can be achieved, matching AI-independent diagnosis, human-machine collaborative diagnosis, and human-led diagnosis scenarios, thus balancing diagnostic efficiency and conclusion accuracy.

[0061] Step S405: Determine the AI ​​contribution based on the target diagnostic report.

[0062] The specific steps for determining the AI ​​contribution based on the target diagnostic report include: E1. Determine the diagnostic completion index based on the target diagnostic strategy; E2. Obtain multiple historical diagnostic strategies for the diagnosis of the historical diagnostic cases by the multiple expert groups; each expert group corresponds to one historical diagnostic strategy, and each historical diagnostic strategy is the manual diagnosis only. E3. Obtain the average of the duration of multiple historical manual diagnoses corresponding to the multiple historical diagnostic strategies, and obtain the average duration of historical manual diagnoses. E4. Obtain the total diagnosis time and target manual diagnosis time corresponding to the target diagnosis strategy; E5. Determine efficiency improvement indicators based on the historical average manual diagnosis time and the total diagnosis time; E6. Determine resource-saving indicators based on the historical average manual diagnosis time and the target manual diagnosis time; E7. Determine the AI ​​contribution based on the diagnostic completion index, the efficiency improvement index, and the resource saving index.

[0063] In a specific embodiment, let the diagnostic completion rate index be A. If the target diagnostic strategy is AI-only diagnosis, it means that the diagnostic task is completed entirely by AI without human intervention, so the value of diagnostic completion rate index A can be 1.0. If the target diagnostic strategy is AI-assisted and human confirmation, it means that AI completes the core work such as initial fault location, data processing, and auxiliary information generation, while humans only perform verification and optimization, so the value of diagnostic completion rate index A is 0.6-0.9 (the specific value can be dynamically adjusted according to the adoption rate of AI-assisted information, such as 0.8 if the adoption rate is 80%). If the target diagnostic strategy is human-only diagnosis, it means that AI only provides preliminary diagnostic reference, and humans independently complete the diagnosis based on the original data, so the value of diagnostic completion rate index A is 0-0.5 (the specific value can be adjusted according to the reference value of the preliminary diagnostic report, such as 0 if there is no reference value).

[0064] Then, the diagnostic execution records from historical diagnostic cases are retrieved to extract historical diagnostic strategies adopted by multiple expert groups for these cases, resulting in multiple historical diagnostic strategies. Each expert group corresponds to one historical diagnostic strategy, and each historical diagnostic strategy involves only manual diagnosis to ensure comparability with the manual diagnosis phase in the current diagnostic process. Next, the historical manual diagnosis time corresponding to each historical diagnostic strategy (manual diagnosis only) is extracted. This historical manual diagnosis time is calculated as the time difference between "the time the expert group receives the basic diagnostic data" and "the time the final historical diagnostic report is output." Finally, the arithmetic mean of all valid historical manual diagnosis times is calculated to obtain the average historical manual diagnosis time.

[0065] Next, the actual time consumption data of the diagnostic process corresponding to the target diagnostic strategy is extracted, including the total diagnostic time and the target manual diagnostic time. The total diagnostic time refers to the total time difference from "receiving the user's diagnostic request" to "outputting the target diagnostic report" in the current diagnostic process; the target manual diagnostic time refers to the time difference of the actual participation of the target expert group in the diagnosis process. It should be noted that the target manual diagnostic time for "AI-only diagnosis" is 0; the target manual diagnostic time for "AI-assisted and manual confirmation" is the time difference from "manually receiving AI-assisted information" to "outputting the first feedback information"; and the target manual diagnostic time for "manual diagnosis only" is the time difference from "manually receiving basic diagnostic data" to "outputting the second feedback information".

[0066] Then, by comparing the difference between the historical average manual diagnosis time and the total diagnosis time, an efficiency improvement index is calculated. The formula for calculating the efficiency improvement index is: B = (T0 - T1) / T0. B represents the efficiency improvement index; T0 represents the historical average manual diagnosis time; and T1 represents the total diagnosis time. It should be noted that if the total diagnosis time is less than the historical average manual diagnosis time, then B is a positive value; otherwise, B is 0 (i.e., negative values ​​are not considered).

[0067] By calculating the historical average human diagnosis time and the target human diagnosis time, a resource-saving index is obtained to evaluate the effectiveness of AI diagnosis in saving human resources. The formula for calculating the resource-saving index is: C = 1 - (T2 / T0), where C represents the resource-saving index and T2 represents the target human diagnosis time.

[0068] Next, weighting coefficients are assigned to the diagnostic completion indicator A, efficiency improvement indicator B, and resource saving indicator C, resulting in α, β, and γ. These weighting coefficients can be dynamically adjusted based on different target fault types (e.g., engine fault, electronic system fault, chassis fault, etc.), but it must be ensured that α + β + γ = 1, and α ≥ 0.5 (highlighting the core role of the diagnostic completion indicator). Then, a weighted calculation is performed on the diagnostic completion indicator A, efficiency improvement indicator B, and resource saving indicator C to obtain the AI ​​contribution. The formula for calculating the AI ​​contribution is: D = α*A + β*B + γ*C, where D represents the AI ​​contribution.

[0069] It is evident that by using quantitative evaluation across three dimensions—diagnostic completion indicators, efficiency improvement indicators, and resource conservation indicators—a scientific AI contribution calculation system has been established, providing a precise basis for value measurement in subsequent differentiated pricing and fee sharing.

[0070] Step S406: Determine the target diagnostic fee based on the preset basic fee standard and the AI ​​contribution level.

[0071] For easier understanding, please refer to Figure 6 , Figure 6 This is a flowchart illustrating a process for determining the cost of a target diagnosis, provided in an embodiment of this application. The specific steps for determining the cost of a target diagnosis based on a preset basic fee standard and the AI ​​contribution include: F1. Obtain the preset diagnostic discount factor; F2. Determine the target fault type corresponding to the target diagnostic report; F3. Determine the basic diagnostic fee corresponding to the target fault type based on the basic charging standard; F4. Determine the target diagnostic cost based on the basic diagnostic cost, the AI ​​contribution, and the diagnostic discount coefficient.

[0072] In a specific implementation, firstly, a fixed diagnostic discount coefficient (e.g., 0.5) is pre-set based on factors such as industry diagnostic service pricing rules, human expert service costs, and AI technology operation and maintenance costs. This diagnostic discount coefficient can also be set to have a positive correlation with AI contribution, meaning the higher the AI ​​contribution, the larger the corresponding diagnostic discount coefficient. Next, the target diagnostic report is structured and parsed to extract the target fault type explicitly stated in the report. Then, the basic diagnostic fees in the basic fee standard are filtered according to the target fault type to obtain the basic diagnostic fee corresponding to that fault type. The basic fee standard is formulated based on factors such as the technical difficulty of fault diagnosis, human resource costs, and industry market prices, including multiple fault types and multiple basic diagnostic fees, with different basic diagnostic fees corresponding to different fault types. Finally, the target diagnostic fee is calculated based on the basic diagnostic fee, AI contribution, and diagnostic discount coefficient. The formula for calculating the target diagnostic fee is: F = F0 - F0 * D * K, where F represents the target diagnostic fee, F0 represents the basic diagnostic fee, and K represents the diagnostic discount coefficient. It should be noted that the final target diagnostic fee F is not lower than the pre-set minimum charge standard Fmin, in order to avoid excessive discounting affecting service profitability. For example, if the target fault type is a common fault, the corresponding basic diagnostic fee F0 = 200 yuan, the diagnostic discount coefficient K = 0.5, the AI ​​contribution D = 0.967, and the minimum charge standard Fmin = 100 yuan. Then the target diagnostic fee F = 200 - 200 * 0.967 * 0.5 ≈ 200 - 96.7 = 103.3 yuan. Since this target diagnostic fee F is greater than the minimum charge standard Fmin, the final target diagnostic fee is determined to be 103.3 yuan.

[0073] It is evident that by using a pricing mechanism that matches basic fees based on fault type and links discount coefficients to AI contribution, the diagnostic fees can be dynamically and differentiated. This not only reflects the cost-reduction value of AI technology but also effectively incentivizes users to choose AI diagnostic services.

[0074] In one possible embodiment, the target diagnostic cost can be used as the calculation base. A preset percentage of basic operating costs (which account for 10%-15% of the target diagnostic cost) is deducted, and the remaining amount is the revenue sharing base. The formula for calculating the revenue sharing base is: F2 = F - F1, where F2 represents the revenue sharing base and F1 represents the basic operating cost. It should be noted that the basic operating cost covers fixed expenses such as server maintenance, system R&D iteration, customer service support, and data storage. Its percentage can be dynamically adjusted based on actual operating costs and is not specifically limited here. Then, a proportional calculation method is used to determine the AI-related party's share, with the formula: F3 = F2 * D, where F3 is the AI-related party's share. This share can be used to cover technical expenditures such as AI diagnostic model R&D amortization, computing power cost compensation, and data annotation investment, ensuring continuous iteration and optimization of the AI ​​diagnostic model. If the target diagnostic strategy is AI-assisted and human confirmation or only human diagnosis, i.e., human experts actually participate in the diagnostic work, then the formula for calculating the human expert's share is: F4 = F2 * (1 - D), where F4 is the human expert's share. If the target diagnostic strategy is AI-only diagnosis, meaning no human experts are involved in the diagnostic process, then the human expert's share is 0. This unallocated amount is automatically incorporated into the AI-related party's share to supplement AI technology R&D investment. Finally, a standardized shareholding breakdown is automatically generated based on the target diagnostic fee F, basic operating cost F1, shareholding base F2, AI-related party share F3, and human expert share F4. The AI-related party's share is included in the R&D funds according to the breakdown, and the human expert's share is transferred in real-time to the specific account of the corresponding target expert group. Simultaneously, an immutable settlement record is generated based on all settlement data to support online verification by AI-related parties, human experts, and regulatory agencies.

[0075] For easier understanding, please refer to Figure 7 , Figure 7 This is a schematic diagram of the composition of a revenue sharing breakdown provided in an embodiment of this application. First, the target diagnostic fee F, which is a preset percentage, is used as the basic operating cost F1. Then, the revenue sharing base F2 is obtained by subtracting the basic operating cost F1 from the target diagnostic fee F. Then, the revenue sharing base F2 is split according to the AI ​​contribution to obtain the AI-related party share F3 and the human expert share F4 (which is generated only when human intervention is involved in the diagnosis and is the remaining revenue sharing amount after deducting F3 from F2).

[0076] In one possible implementation, complete diagnostic data can be automatically collected, including but not limited to: basic vehicle information, fault description information, diagnostic process data (including fault code matching records and confidence calculation processes), human intervention records (including expert feedback and diagnostic duration), AI contribution, and user evaluation data. Then, a data anonymization algorithm is used to remove user privacy information (such as hiding certain fields of the vehicle identification number and encrypting user identity information) to ensure data usage complies with privacy protection standards. The anonymized data is then input into the AI ​​diagnostic model for iterative training, serving as new training samples to participate in the iterative optimization of the AI ​​diagnostic model, with a focus on improving the AI ​​diagnostic model's accuracy in identifying and diagnosing similar faults.

[0077] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0078] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0079] When dividing each function into modules according to its corresponding function. Figure 8 This is a functional module block diagram of an AI-based diagnostic cost adjustment device provided in an embodiment of this application. The AI-based diagnostic cost adjustment device 800 includes a data acquisition module 810, an AI diagnostic module 820, a first determination module 830, a second determination module 840, a third determination module 850, and a fourth determination module 860, wherein: The data acquisition module 810 is used to acquire basic diagnostic data of the target vehicle; The AI ​​diagnostic module 820 is used to perform preliminary AI diagnostics on the diagnostic basic data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report. The first determining module 830 is used to determine a target diagnostic strategy based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only; The second determining module 840 is used to determine a target diagnosis report based on the target diagnosis strategy; The third determining module 850 is used to determine the AI ​​contribution based on the target diagnostic report; The fourth determining module 860 is used to determine the target diagnostic fee based on the preset basic charging standard and the AI ​​contribution.

[0080] Optionally, the first diagnostic result further includes diagnostic process data; the basic diagnostic data includes vehicle basic information and fault description information; in terms of performing preliminary AI diagnosis on the basic diagnostic data to obtain the first diagnostic result, the AI ​​diagnostic module 820 is specifically used for: The vehicle's basic information is analyzed to obtain the first fault code and vehicle operating parameters; The first fault characteristic is determined based on the vehicle operating parameters and the fault description information; The first fault code and the first fault characteristics are analyzed according to the preset AI diagnostic model to obtain the reference fault type, data processing volume and preliminary diagnosis time. The diagnostic process data is determined based on the data processing volume and the preliminary diagnosis duration. The reference fault cause corresponding to the reference fault type is determined based on a preset fault type knowledge base; The diagnostic confidence level is determined based on the reference fault type, the first fault code, and the first fault characteristic. The preliminary diagnostic report is determined based on the reference fault type, the reference fault cause, and the diagnostic confidence level.

[0081] Optionally, in determining the diagnostic confidence level based on the reference fault type, the first fault code, and the first fault feature, the AI ​​diagnostic module 820 is further specifically used for: Obtain the historical diagnostic case library corresponding to the model of the target vehicle; Obtain historical diagnostic cases corresponding to the reference fault type from the historical diagnostic case library; Determine the second fault code and second fault characteristic corresponding to the historical diagnostic cases; Obtain the similarity between the first fault code and the second fault code to obtain the first similarity; The similarity between the first fault feature and the second fault feature is obtained to obtain the second similarity. The diagnostic confidence level is determined based on the first similarity and the second similarity.

[0082] Optionally, in determining the target diagnostic strategy based on the preliminary diagnostic report, the first determining module 830 is specifically used for: Obtain a preset first confidence threshold and a second confidence threshold; the first confidence threshold is greater than the second confidence threshold; If the diagnostic confidence level is greater than or equal to the first confidence threshold, then the target diagnostic strategy is determined to be the AI-only diagnosis. If the diagnostic confidence level is greater than the second confidence level threshold and less than the first confidence level threshold, then the target diagnostic strategy is determined to be AI-assisted and human-determined. If the diagnostic confidence level is less than or equal to the second confidence threshold, then the target diagnostic strategy is determined to be manual diagnosis only.

[0083] Optionally, in determining the target diagnostic report according to the target diagnostic strategy, the second determining module 840 is specifically used for: If the target diagnostic strategy is AI-only diagnosis, then the preliminary diagnostic report is determined to be the target diagnostic report; If the target diagnostic strategy is AI-assisted and human-determined, then the AI-assisted information is determined based on the preliminary diagnostic report and the diagnostic process data. Obtain first feedback information from the target expert group regarding the AI-assisted information; the target expert group is any one of a preset plurality of expert groups; The preliminary diagnostic report is adjusted based on the first feedback information to obtain the target diagnostic report; If the target diagnostic strategy is manual diagnosis only, then obtain the second feedback information of the target expert group on the diagnostic basic data. The target diagnostic report is determined based on the second feedback information.

[0084] Optionally, in determining the AI ​​contribution based on the target diagnostic report, the third determining module 850 is specifically used for: Determine the diagnostic completion index based on the target diagnostic strategy; Obtain multiple historical diagnostic strategies from the multiple expert groups for diagnosing the historical diagnostic cases; each expert group corresponds to one historical diagnostic strategy, and each historical diagnostic strategy is the manual diagnosis only. The average duration of multiple historical manual diagnoses corresponding to the multiple historical diagnostic strategies is obtained to obtain the average duration of historical manual diagnoses. Obtain the total diagnosis time and the target manual diagnosis time corresponding to the target diagnosis strategy; Efficiency improvement indicators are determined based on the historical average duration of manual diagnosis and the total diagnosis time. Resource conservation indicators are determined based on the historical average duration of manual diagnosis and the target duration of manual diagnosis. The AI ​​contribution is determined based on the diagnostic completion rate index, the efficiency improvement index, and the resource saving index.

[0085] Optionally, in determining the target diagnostic fee based on the preset basic fee standard and the AI ​​contribution, the fourth determining module 860 is specifically used for: Obtain the preset diagnostic discount factor; Determine the target fault type corresponding to the target diagnostic report; The basic diagnostic fee corresponding to the target fault type is determined based on the aforementioned basic fee standard. The target diagnostic cost is determined based on the basic diagnostic cost, the AI ​​contribution, and the diagnostic discount coefficient.

[0086] It is evident that by constructing a differentiated human-machine collaboration process based on diagnostic confidence, establishing a quantifiable evaluation system for AI contributions, and designing a differentiated charging mechanism linked to AI contributions, the accuracy of AI fault diagnosis applications and user engagement have been improved.

[0087] It should be noted that the specific implementation of each operation can be described in the corresponding description of the method embodiments shown above. The AI-based diagnostic cost adjustment device 800 can be used to execute the above method embodiments of this application, and will not be described again here.

[0088] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0089] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0090] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0091] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0092] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0093] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0094] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0095] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0096] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. An AI-based diagnostic cost adjustment method, characterized in that, The method includes: Obtain basic diagnostic data for the target vehicle; A preliminary AI diagnosis is performed on the aforementioned diagnostic baseline data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; The target diagnostic strategy is determined based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only. A target diagnostic report is determined based on the aforementioned target diagnostic strategy; The AI ​​contribution is determined based on the target diagnostic report. The target diagnostic fee is determined based on the preset basic fee standard and the AI ​​contribution level.

2. The method as described in claim 1, characterized in that, The first diagnostic result also includes diagnostic process data; the basic diagnostic data includes vehicle basic information and fault description information; the preliminary AI diagnosis of the basic diagnostic data to obtain the first diagnostic result includes: The vehicle's basic information is analyzed to obtain the first fault code and vehicle operating parameters; The first fault characteristic is determined based on the vehicle operating parameters and the fault description information; The first fault code and the first fault characteristics are analyzed according to the preset AI diagnostic model to obtain the reference fault type, data processing volume and preliminary diagnosis time. The diagnostic process data is determined based on the data processing volume and the preliminary diagnosis duration. The reference fault cause corresponding to the reference fault type is determined based on a preset fault type knowledge base; The diagnostic confidence level is determined based on the reference fault type, the first fault code, and the first fault characteristic. The preliminary diagnostic report is determined based on the reference fault type, the reference fault cause, and the diagnostic confidence level.

3. The method as described in claim 2, characterized in that, Determining the diagnostic confidence level based on the reference fault type, the first fault code, and the first fault characteristic includes: Obtain the historical diagnostic case library corresponding to the model of the target vehicle; Obtain historical diagnostic cases corresponding to the reference fault type from the historical diagnostic case library; Determine the second fault code and second fault characteristic corresponding to the historical diagnostic cases; Obtain the similarity between the first fault code and the second fault code to obtain the first similarity; The similarity between the first fault feature and the second fault feature is obtained to obtain the second similarity. The diagnostic confidence level is determined based on the first similarity and the second similarity.

4. The method as described in claim 3, characterized in that, The step of determining the target diagnostic strategy based on the preliminary diagnostic report includes: Obtain a preset first confidence threshold and a second confidence threshold; the first confidence threshold is greater than the second confidence threshold; If the diagnostic confidence level is greater than or equal to the first confidence threshold, then the target diagnostic strategy is determined to be the AI-only diagnosis. If the diagnostic confidence level is greater than the second confidence level threshold and less than the first confidence level threshold, then the target diagnostic strategy is determined to be AI-assisted and human-determined. If the diagnostic confidence level is less than or equal to the second confidence threshold, then the target diagnostic strategy is determined to be manual diagnosis only.

5. The method as described in claim 4, characterized in that, The step of determining the target diagnostic report according to the target diagnostic strategy includes: If the target diagnostic strategy is AI-only diagnosis, then the preliminary diagnostic report is determined to be the target diagnostic report; If the target diagnostic strategy is AI-assisted and human-determined, then the AI-assisted information is determined based on the preliminary diagnostic report and the diagnostic process data. Obtain first feedback information from the target expert group regarding the AI-assisted information; the target expert group is any one of a preset plurality of expert groups; The preliminary diagnostic report is adjusted based on the first feedback information to obtain the target diagnostic report; If the target diagnostic strategy is manual diagnosis only, then obtain the second feedback information of the target expert group on the diagnostic basic data. The target diagnostic report is determined based on the second feedback information.

6. The method as described in claim 5, characterized in that, The determination of AI contribution based on the target diagnostic report includes: Determine the diagnostic completion index based on the target diagnostic strategy; Obtain multiple historical diagnostic strategies from the multiple expert groups for diagnosing the historical diagnostic cases; each expert group corresponds to one historical diagnostic strategy, and each historical diagnostic strategy is the manual diagnosis only. The average duration of multiple historical manual diagnoses corresponding to the multiple historical diagnostic strategies is obtained to obtain the average duration of historical manual diagnoses. Obtain the total diagnosis time and the target manual diagnosis time corresponding to the target diagnosis strategy; Efficiency improvement indicators are determined based on the historical average duration of manual diagnosis and the total diagnosis time. Resource conservation indicators are determined based on the historical average duration of manual diagnosis and the target duration of manual diagnosis. The AI ​​contribution is determined based on the diagnostic completion rate index, the efficiency improvement index, and the resource saving index.

7. The method according to any one of claims 1-6, characterized in that, The process of determining the target diagnostic fee based on a preset basic fee standard and the AI ​​contribution includes: Obtain the preset diagnostic discount factor; Determine the target fault type corresponding to the target diagnostic report; The basic diagnostic fee corresponding to the target fault type is determined based on the aforementioned basic fee standard. The target diagnostic cost is determined based on the basic diagnostic cost, the AI ​​contribution, and the diagnostic discount coefficient.

8. An AI-based diagnostic cost adjustment device, characterized in that, The device includes a data acquisition module, an AI diagnosis module, a first determination module, a second determination module, a third determination module, and a fourth determination module, wherein: The data acquisition module is used to acquire basic diagnostic data of the target vehicle; The AI ​​diagnostic module is used to perform preliminary AI diagnosis on the diagnostic basic data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; The first determining module is used to determine a target diagnostic strategy based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only; The second determining module is used to determine a target diagnostic report based on the target diagnostic strategy; The third determining module is used to determine the AI ​​contribution based on the target diagnostic report; The fourth determining module is used to determine the target diagnostic fee based on the preset basic charging standard and the AI ​​contribution.

9. An electronic device, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images