Complaint work order processing method and device, electronic equipment and storage medium
Through the combination of NLP and AIGC models, the automatic handling of online car-hailing complaint work orders has been solved, and the problems of cumbersome complaint handling procedures and unreasonable results in the existing technology have been solved, and the rapid and fair complaint handling has been achieved, which has improved user satisfaction.
Patent Information
- Application Number
- CN202411071506.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-11-15
AI Technical Summary
The existing online car-hailing complaint handling process is cumbersome and requires 1-2 hours of communication. The processing results are unreasonable due to information concealment and lack fairness.
The NLP model is used to analyze the complaint work order, generate standardized scene parameters, combine the AIGC model for scene analysis, automatically generate processing results and descriptions, and scene identification is carried out through objective data uploaded by the on-board terminal, and the complaint processing process is optimized to ensure the fairness and accuracy of the results. sex.
The complaint handling process is simplified, the customer service labor costs are reduced, the processing speed and user satisfaction are improved, and the rationality and fairness of the processing results are ensured.
Smart Images

Figure CN118967046A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of work order processing, and in particular to a method, device, electronic device, and storage medium for processing complaint work orders. Background Art
[0002] As the number of online ride-hailing vehicles increases, while it has made travel more convenient for people, it has also generated many complaints about the process of taking online ride-hailing vehicles.
[0003] The existing processing process is that passengers report problems through the online car-hailing app or customer service phone, and then wait for customer service to communicate with the online car-hailing driver to understand the situation or retrieve in-car video information, online car-hailing driving information, etc. Then give feedback and conclusions based on the actual situation and reply to the customer with the processing results. This process requires at least 1-2 hours of communication. In addition, the driver and the passenger concealed some information, resulting in unreasonable processing results. Summary of the invention
[0004] The embodiments of the present application provide a method, device, electronic device, and storage medium for processing complaint tickets to optimize the processing flow of complaint tickets and ensure the fairness of the complaint ticket determination results.
[0005] The present application embodiment adopts the following technical solutions:
[0006] In a first aspect, an embodiment of the present application provides a method for processing a complaint work order, wherein the method comprises:
[0007] Receiving parameter information uploaded by the vehicle terminal, wherein the parameter information is used to record objective data generated during driving;
[0008] Receive complaint tickets and convert them into standardized scenario parameters using NLP model analysis, where the scenario parameters include complaint scenario elements and processing requirements;
[0009] Perform scene analysis based on the parameter information to obtain a scene recognition result;
[0010] The AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order, where the processing description is used as a subjective description of the processing result;
[0011] The processing result and the processing description are sent to the passenger to determine the passenger's satisfaction with the processing result.
[0012] In some embodiments, the AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order, where the processing description is used as a subjective description of the processing result, including:
[0013] Generate a first discrimination parameter based on the complaint scenario element and the processing demand in the scenario parameter;
[0014] Based on the parameter information uploaded by the vehicle in the order period corresponding to the complaint work order, a large model is used to generate a second discrimination parameter in the scene recognition result, and the second discrimination parameter and the first discrimination parameter are both used to characterize the current judgment scene and the confidence of the scene;
[0015] Calculating a matching value between the first discrimination parameter and the second discrimination parameter;
[0016] If the matching value meets the preset conditions, the AIGC model is used to generate the processing result and processing description of the complaint work order;
[0017] If the matching value does not meet the preset condition, the scene parameter is re-identified or the scene recognition result is evaluated.
[0018] In some embodiments, sending the processing result and the processing description to the passenger to determine the passenger's satisfaction with the processing result includes:
[0019] According to the processing result of the complaint work order, select the corresponding preset processing plan;
[0020] Calling the customer service module to send the preset processing solution and the processing description to the passenger;
[0021] Determining whether to end the processing of the complaint ticket based on the passenger's satisfaction with the processing result;
[0022] When receiving a satisfactory response from the passenger, the processing of the complaint ticket is terminated;
[0023] In the case of receiving an unsatisfactory response from the passenger, continue to receive new feedback descriptions from the passenger and continue to process the complaint ticket in combination with the context information in the customer service module.
[0024] In some embodiments, the method further comprises:
[0025] Collect complaint handling records for each complaint ticket;
[0026] Analyze the effectiveness of the standardized scenarios and the user's satisfaction with the handling results based on the complaint handling records;
[0027] The effectiveness of the standardized scenarios and the user's satisfaction with the processing results are input into the AIGC model to continuously optimize the identification of scenarios and the response to complaint determinations.
[0028] In some embodiments, the receiving of parameter information uploaded by the vehicle-mounted terminal, wherein the parameter information is used to record objective data generated during driving, includes:
[0029] After the trip order is confirmed, parameter information uploaded by the vehicle terminal is received, and the parameter information includes at least one of the following: vehicle audio and video monitoring information, vehicle real-time data, and image data inside and outside the vehicle.
[0030] In some embodiments, the receiving of the complaint ticket and converting it into standardized scenario parameters using an NLP model for parsing, wherein the scenario parameters include complaint scenario elements and processing demands, including:
[0031] Receive the complaint scenario described in natural language in the complaint ticket and handle the request;
[0032] Use the NLP model to parse and convert the complaint scenario and processing requirements described in natural language in the complaint ticket into standardized scenario parameters;
[0033] The complaint scenario elements include at least one of the following: failure to arrive at the agreed time, taking a detour, the driver being rude to passengers, unreasonable fares, strange smells in the car, and the air conditioning not being turned on;
[0034] The handling of the demands includes at least one of the following: refund, compensation, and complaint against the driver.
[0035] In some embodiments, performing scene analysis based on the parameter information to obtain a scene recognition result includes:
[0036] Based on the image recognition results, speech recognition results, vehicle status analysis results, and traffic situation prediction results in the parameter information, a large model analysis is used to obtain an objective recognition result of the scene.
[0037] In a second aspect, an embodiment of the present application further provides a complaint work order processing device, wherein the device comprises:
[0038] A receiving module, used to receive parameter information uploaded by the vehicle terminal, wherein the parameter information is used to record objective data generated during driving;
[0039] A receiving and processing module, which is used to receive complaint tickets and convert them into standardized scenario parameters using an NLP model. The scenario parameters include complaint scenario elements and processing demands.
[0040] An identification module, used to perform scene analysis based on the parameter information to obtain a scene identification result;
[0041] A generation module, used to analyze the scenario parameters and the scenario recognition results using an AIGC model, and generate a processing result and a processing description of the complaint work order, wherein the processing description is used as a subjective description of the processing result;
[0042] The sending module is used to send the processing result and the processing description to the passenger to determine the passenger's satisfaction with the processing result.
[0043] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the above method.
[0044] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.
[0045] At least one of the above technical solutions adopted in the embodiment of the present application can achieve the following beneficial effects: by receiving the parameter information uploaded by the vehicle terminal, the parameter information is used to record the objective data generated during the driving process. Receive the complaint work order and use the NLP model to parse and convert it into standardized scene parameters, in which the scene parameters include the complaint scene elements and processing demands. Then, based on the parameter information, the scene analysis is performed to obtain the scene recognition result. Then, the AIGC model is used to analyze the scene parameters and the scene recognition results to generate the processing results and processing description of the complaint work order, and the processing description is used as a subjective description of the processing result. Finally, the processing result and the processing description are sent to the passenger to determine the passenger's satisfaction with the processing result. The user semantic information in the complaint work order is parsed by the NLP model and converted into standardized scene parameters to further realize the automated processing process. The processing results and processing description of the complaint work order generated by the AIGC model can simplify the processing process of the complaint work order processing scene and reduce the labor input cost of customer service. At the same time, the work order processing speed and user satisfaction can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0047] Figure 1 This is a flowchart of the method for handling a complaint work order in an embodiment of the present application;
[0048] Figure 2This is a schematic diagram of the structure of the complaint work order processing device in an embodiment of the present application;
[0049] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0051] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0052] This application embodiment provides a method for processing a complaint work order, such as Figure 1 As shown, a flowchart of a method for handling a complaint work order in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S150:
[0053] Step S110, receiving parameter information uploaded by the vehicle-mounted terminal, wherein the parameter information is used to record objective data generated during the driving process.
[0054] The vehicle terminal can be connected to multiple sensors to collect information inside and outside the vehicle. At the same time, the sensor can also collect audio and video information and real-time vehicle information. The vehicle terminal can store the information collected by the sensor and upload it to the cloud for storage.
[0055] It is understood that after each order trip starts and is confirmed, the vehicle terminal will start recording and uploading parameter information. These parameter information are used as objective data generated during the driving process.
[0056] Step S120, receiving the complaint ticket and converting it into standardized scenario parameters using the NLP model analysis, wherein the scenario parameters include complaint scenario elements and processing requirements.
[0057] Complaint tickets usually include voice or text messages from passengers. After receiving the complaint tickets, the NLP model is used to parse and convert them into standardized scenario parameters. It can be understood that the NLP model (Natural Language Process) is a sub-field of computer science, information engineering and artificial intelligence, focusing on human-computer language interaction and exploring how to process and use natural language.
[0058] The scenario parameters include complaint scenario elements as the smallest unit for distinguishing different scenarios. It is understandable that the complaint scenario elements can be labeled and distinguished at different granularities. In addition, the scenario parameters also include processing demands, and there is a corresponding relationship between each complaint scenario element and the processing demand.
[0059] It should be noted that the complaint ticket can be directed at the online ride-hailing service and is usually generated after the trip is completed. The complaint ticket can be submitted through the online ride-hailing service app, online customer service, customer service phone, etc. The complaint ticket will be saved in the cloud.
[0060] Step S130: performing scene analysis based on the parameter information to obtain a scene recognition result.
[0061] Based on the parameter information uploaded by the vehicle terminal, further scene analysis is performed to obtain a true and reliable result of scene recognition. In the process of scene analysis based on the parameter information, the vehicle audio and video monitoring information and vehicle real-time data uploaded by the complaint vehicle during the order period are mainly used, and the large model technology is introduced for scene analysis.
[0062] The large model used is the Large Language Model (LLM), which refers to a deep learning model trained with a large amount of text data that can generate natural language text or understand the meaning of language text.
[0063] Preferably, the scene recognition result can also be comprehensively evaluated with the help of vehicle status analysis technology and traffic situation monitoring technology.
[0064] Preferably, the more technologies are used, the more accurate the recognition result will be.
[0065] Step S140, using the AIGC model to analyze the scenario parameters and the scenario recognition results, and generate a processing result and a processing description of the complaint work order, wherein the processing description is used as a subjective description of the processing result.
[0066] The AIGC model is used to process the scene recognition results and scene parameters again to generate the processing results and processing description of the complaint ticket. It should be noted that the processing description is used as a subjective description of the processing result. The processing result here is usually a language description result.
[0067] It can be understood that the AIGC model (AI-Generated Content) is a generative artificial intelligence model. AIGC uses artificial intelligence technology to generate content, including text, voice, code, image, video and other formats, and is a representative of a new content creation method. By analyzing the scene parameters and the scene recognition results through the AIGC model, the processing results and processing descriptions for the complaint work order can be generated instead of the manual generation method.
[0068] Preferably, one of the scene parameters and the scene recognition results is based on the complaint ticket and converted into standardized scene parameters using the NLP model, and the other is based on the parameter information to perform scene analysis to obtain the scene recognition result. Therefore, there is a similarity or correlation between the two. For example, the scene parameter is a detour, and the scene recognition result is that the vehicle is stuck in traffic so the detour is taken, so there is a correlation between the two. For another example, the scene parameter is not arriving at the agreed time, and the scene recognition result is that the driver is late, so there is a similarity between the two, and the specific degree of similarity can be calculated.
[0069] Step S150, sending the processing result and the processing description to the passenger to determine the passenger's satisfaction with the processing result.
[0070] The processing description mainly serves as a supplementary explanation for the processing results and is a necessary feedback result of the complaint work order. The processing description can help passengers understand the processing results of the response.
[0071] After the processing result is obtained, the processing result and the corresponding processing description will be sent to the passenger, and it can be determined whether the passenger is satisfied with the processing result. If the passenger is satisfied, the complaint ticket processing is considered to be completed. If not, the complaint ticket needs to be continued.
[0072] Through the above method, the parameter information uploaded by the vehicle terminal is retained and used as a record of objective data generated during the driving process. The NLP model is used to convert the complaint work order analysis into standardized scenario parameters. The scenario parameters include complaint scenario elements and processing demands, which can be used to distinguish different complaint scenarios and corresponding processing demands. Based on the parameter information, a scene analysis is performed to obtain a scene recognition result as an objective result of the scene analysis. When determining the results and replying to passengers, the AIGC model is used to analyze the scene parameters and the scene recognition results, so as to automatically generate the processing results and processing description of the complaint work order. Finally, the processing results and the processing description are sent to the passenger, which greatly simplifies the processing flow of the online car-hailing complaint work order processing scenario, reduces the labor input cost of customer service, and improves the work order processing speed and user satisfaction.
[0073] Through the above method, the NLP model is used to parse the complaint ticket to obtain the complaint scenario elements and processing demands, and a large model is used to perform scenario analysis based on the parameter information to obtain the scenario recognition result. The AIGC model is used to further analyze the scenario parameters and the scenario recognition results, and generate the processing results and processing description of the complaint ticket, which can replace manual judgment and automatically generate processing results. By continuously collecting feedback information from passengers on complaint tickets, the accuracy of scenario parameters and scenario recognition results can be optimized. Compared with the manual processing mode in related technologies, it can reduce manual intervention and improve the processing efficiency of complaint tickets.
[0074] Through the above method, the entire complaint ticket processing time can be saved, manual intervention can be reduced, and the accuracy of the processing results and the rationality of the processing description of the generated complaint ticket can be guaranteed. The processing description can usually replace manual processing, so that the judgment after the processing result is sent to the passenger is more reasonable and more in line with the complaint processing requirements. Compared with the manual generation method in the related technology, the content can be automatically generated and the passenger can be given a reasonable reply to the judgment result.
[0075] In one embodiment of the present application, an AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order, and the processing description is used as a subjective description of the processing result, including: generating a first discrimination parameter based on the complaint scenario elements and the processing demands in the scenario parameters; using a large model to generate a second discrimination parameter in the scene recognition result based on the parameter information uploaded by the vehicle in the order period corresponding to the complaint work order, the second discrimination parameter and the first discrimination parameter are both used to characterize the current judgment scenario and the confidence of the scenario; calculating the matching value of the first discrimination parameter and the second discrimination parameter; if the matching value meets the preset conditions, using the AIGC model to generate the processing result and processing description of the complaint work order; if the matching value does not meet the preset conditions, re-identifying the scenario parameters or re-evaluating the scene recognition results.
[0076] When determining the processing results and responding to passengers, it is necessary to obtain a comprehensive judgment result based on the comparison results of the scene parameters and scene recognition results, and combine the AIGC model to generate the processing results and processing description of the complaint work order.
[0077] The first discrimination parameter mainly includes the current judgment scenario and the confidence of the scenario, that is, the current judgment scenario and the possibility of the judgment scenario can be generated based on the complaint scenario elements in the scenario parameters and the comprehensive judgment of the processing demands. It can be understood that the higher the confidence, the greater the possibility of the current judgment scenario.
[0078] Furthermore, due to the uncertainty of the parameter information uploaded by the vehicle in the order period corresponding to the complaint work order, a large model is used to generate the current judgment scene and the possibility of the judgment scene in the scene recognition result.
[0079] The matching calculation method is used to determine the matching value of the first discrimination parameter and the second discrimination parameter. If the matching value meets the preset conditions, the current judgment scene is similar or the same, and it is considered that the AIGC model can be used to generate the processing result and processing description of the complaint work order. If the matching value does not meet the preset conditions, the current judgment scene is different or dissimilar, and the scene parameters are re-identified or the scene recognition results are re-evaluated.
[0080] Whether the preset condition is met can be determined based on a threshold value of the matching value, or based on a specific indicator of the matching value.
[0081] It can be understood that the above-mentioned first discrimination parameter and second discrimination parameter are only examples and are not used to limit the process of generating the processing results and processing descriptions of the complaint work order. That is to say, as long as the scene parameters converted into standardized scene parameters using the NLP model can match the scene recognition results obtained by scene analysis based on the parameter information, it is considered that the AIGC model can be used to further generate processing results and processing descriptions. If the scene parameters converted into standardized scene parameters using the NLP model and the scene recognition results obtained by scene analysis based on the parameter information cannot match, re-parsing or analysis is required. This can ensure the accuracy and objectivity of the generated processing results and the processing description.
[0082] In one embodiment of the present application, the processing result and the processing description are sent to the passenger to determine the passenger's satisfaction with the processing result, including: selecting a corresponding preset processing plan based on the processing result of the complaint worksheet; calling the customer service module to send the preset processing plan and the processing description to the passenger; judging whether to end the processing of the complaint worksheet based on the passenger's satisfaction with the processing result; ending the processing of the complaint worksheet when a satisfactory response from the passenger is received; and continuing to receive new feedback descriptions from the passenger and continuing to process the complaint worksheet in combination with the context information in the customer service module when an unsatisfactory response from the passenger is received.
[0083] In order to better realize the optimization cycle and improve the efficiency of data feedback. By analyzing the effectiveness of the scenario and user satisfaction and continuously optimizing the AIGC model. First, according to the processing result of the complaint work order, dynamically select through the preset processing plan, and then call the customer service module to send the preset processing plan and the processing description to the passenger. By calling the system customer service feedback module, the final processing result is communicated to the passenger. If the passenger is satisfied with the processing result, the work order is terminated. If the passenger is not satisfied, the judgment operation is repeated in combination with the passenger's new feedback description or previous context information.
[0084] When a satisfactory response is received from the passenger, it is considered that the processing of the complaint ticket can be completed.
[0085] In the case of receiving an unsatisfactory response from a passenger, it is necessary to continue to receive new feedback descriptions from the passenger and continue to process the complaint ticket in combination with the context information in the customer service module. The context information is mainly used as the basis for judgment, which is convenient for judging together with continuing to receive new feedback descriptions from passengers.
[0086] In one embodiment of the present application, the method also includes: collecting complaint handling records for each complaint ticket; analyzing the effectiveness of the standardized scenario and the user's satisfaction with the processing result based on the complaint handling record; inputting the effectiveness of the standardized scenario and the user's satisfaction with the processing result into the AIGC model to continuously optimize the identification of scenarios and the response to complaint judgments.
[0087] In order to better optimize the identification of scenarios and the response to complaint decisions, the complaint handling records of each complaint ticket are collected, and then based on the complaint handling records, the effectiveness of the standardized scenarios and the user's satisfaction with the handling results are analyzed.
[0088] Next, the effectiveness of the standardized scenarios and the user's satisfaction with the processing results need to be input into the AIGC model to continuously optimize the recognition of scenarios. At the same time, corresponding replies need to be generated for complaint judgments based on the AIGC model. In order to make the generated complaint judgment reply content reasonable, it is necessary to continuously analyze and obtain the user's satisfaction with the processing results. In order to make the recognition of the generated scenarios more reasonable, it is necessary to continuously optimize the recognition results of the scenarios.
[0089] In one embodiment of the present application, the parameter information uploaded by the vehicle-mounted terminal is received, and the parameter information is used to record objective data generated during the driving process, including: after the travel order is confirmed, the parameter information uploaded by the vehicle-mounted terminal is received, and the parameter information includes at least one of the following: vehicle audio and video monitoring information, vehicle real-time data, and image data inside and outside the vehicle.
[0090] The image data inside and outside the vehicle mainly includes wide-angle inside the vehicle and 360 degrees outside the vehicle. The vehicle audio and video monitoring information mainly includes the audio and video information collection of the driver's position. The real-time vehicle data mainly includes real-time vehicle information collection data, including but not limited to longitude and latitude, speed, fuel / battery level, tire pressure, temperature inside the vehicle, humidity, air quality, etc.
[0091] It can be understood that the parameter information is used to record the objective data generated during the driving process, and can be used as a basis for subsequent complaint work order identification.
[0092] In one embodiment of the present application, the complaint work order is received and converted into standardized scenario parameters using an NLP model for parsing, and the scenario parameters include complaint scenario elements and processing demands, including: receiving the complaint scenario and processing demands described in natural language in the complaint work order; using the NLP model to parse the complaint scenario and processing demands described in natural language in the complaint work order and convert them into standardized scenario parameters; the complaint scenario elements include at least one of the following: failure to arrive at the agreed time, taking a detour, the driver being rude to passengers, unreasonable fees, odor in the car, and not turning on the air conditioning; the processing demands include at least one of the following: refund, compensation, and complaining to the driver.
[0093] NLP is used to process the complaint scenarios and handling requests described in natural language in the complaint ticket. The deep learning model is mainly used to understand the context and semantics. The elements of the identified complaint scenarios include but are not limited to: failure to arrive at the agreed time, detours, drivers being rude to passengers, unreasonable fees, odor in the car, and not turning on the air conditioner. The identified handling requests include but are not limited to: refunds, compensation, complaints about drivers, etc.
[0094] In one embodiment of the present application, the scene analysis is performed based on the parameter information to obtain a scene recognition result, including: based on the image recognition result, speech recognition result, vehicle status analysis result, and traffic situation prediction result in the parameter information, a large model analysis is used to obtain an objective recognition result of the scene.
[0095] The server, i.e. the cloud, will use the big model technology to analyze the scene based on the audio and video monitoring information and real-time data of the vehicle uploaded during the order period of the complained vehicle. The big model combines image recognition technology, speech recognition technology, vehicle status analysis technology, and traffic situation monitoring technology to comprehensively evaluate a true and reliable result. For example, based on the image recognition results, speech recognition results, vehicle status analysis results, and traffic situation prediction results in the parameter information, the big model is used to objectively analyze whether the scene driving path is reasonable and whether there are other problems.
[0096] The present application embodiment also provides a complaint work order processing device 200, such as Figure 2As shown, a schematic diagram of the structure of the complaint work order processing device in an embodiment of the present application is provided, and the complaint work order processing device 200 at least includes: a receiving module 210, a receiving processing module 220, an identification module 230, a generating module 240 and a sending module 250, wherein:
[0097] In one embodiment of the present application, the receiving module 210 is used to receive parameter information uploaded by the vehicle-mounted terminal, and the parameter information is used to record objective data generated during the driving process.
[0098] The vehicle terminal can be connected to multiple sensors to collect information inside and outside the vehicle. At the same time, the sensor can also collect audio and video information and real-time vehicle information. The vehicle terminal can store the information collected by the sensor and upload it to the cloud for storage.
[0099] It is understood that after each order trip starts and is confirmed, the vehicle terminal will start recording and uploading parameter information. These parameter information are used as objective data generated during the driving process.
[0100] In one embodiment of the present application, the receiving and processing module 220 is used to: receive a complaint ticket and convert it into standardized scenario parameters using an NLP model for parsing, wherein the scenario parameters include complaint scenario elements and processing demands.
[0101] Complaint tickets usually include voice or text messages from passengers. After receiving the complaint tickets, the NLP model is used to parse and convert them into standardized scenario parameters. It can be understood that the NLP model (Natural Language Process) is a sub-field of computer science, information engineering and artificial intelligence, focusing on human-computer language interaction and exploring how to process and use natural language.
[0102] The scenario parameters include complaint scenario elements as the smallest unit for distinguishing different scenarios. It is understandable that the complaint scenario elements can be labeled and distinguished at different granularities. In addition, the scenario parameters also include processing demands, and there is a corresponding relationship between each complaint scenario element and the processing demand.
[0103] It should be noted that complaint tickets can be directed at online ride-hailing vehicles and are usually generated after the trip is completed.
[0104] In one embodiment of the present application, the recognition module 230 is used to perform scene analysis based on the parameter information to obtain a scene recognition result.
[0105] Based on the parameter information uploaded by the vehicle terminal, further scene analysis is performed to obtain a true and reliable result of scene recognition. In the process of scene analysis based on the parameter information, the vehicle audio and video monitoring information and vehicle real-time data uploaded by the complaint vehicle during the order period are mainly used, and the large model technology is introduced for scene analysis.
[0106] The large model used is the Large Language Model (LLM), which refers to a deep learning model trained with a large amount of text data that can generate natural language text or understand the meaning of language text.
[0107] Preferably, the scene recognition result can also be comprehensively evaluated with the help of vehicle status analysis technology and traffic situation monitoring technology.
[0108] In one embodiment of the present application, the generation module 240 is used to: use the AIGC model to analyze the scenario parameters and the scenario recognition results, generate the processing results and processing description of the complaint work order, and the processing description is used as a subjective description of the processing results.
[0109] The AIGC model is used to process the scene recognition results and scene parameters again to generate the processing results and processing description of the complaint ticket. It should be noted that the processing description is used as a subjective description of the processing result. The processing result here is usually a language description result.
[0110] It can be understood that the AIGC model (AI-Generated Content) is a generative artificial intelligence model. AIGC uses artificial intelligence technology to generate content, including text, voice, code, image, video and other formats, and is a representative of a new content creation method. By analyzing the scene parameters and the scene recognition results through the AIGC model, the processing results and processing descriptions for the complaint work order can be generated instead of the manual generation method.
[0111] Preferably, one of the scene parameters and the scene recognition results is based on the complaint ticket and converted into standardized scene parameters using the NLP model, and the other is based on the parameter information to perform scene analysis to obtain the scene recognition result. Therefore, there is a similarity or correlation between the two. For example, the scene parameter is a detour, and the scene recognition result is that the vehicle is stuck in traffic so the detour is taken, so there is a correlation between the two. For another example, the scene parameter is not arriving at the agreed time, and the scene recognition result is that the driver is late, so there is a similarity between the two, and the specific degree of similarity can be calculated.
[0112] In one embodiment of the present application, the sending module 250 is used to send the processing result and the processing description to the passenger to determine the passenger's satisfaction with the processing result.
[0113] After the processing result is obtained, the processing result and the corresponding processing description will be sent to the passenger, and it can be determined whether the passenger is satisfied with the processing result. If the passenger is satisfied, the complaint ticket processing is considered to be completed. If not, the complaint ticket needs to be continued.
[0114] In one embodiment of the present application, the generating module 240 is further used to
[0115] Generate a first discrimination parameter based on the complaint scenario element and the processing demand in the scenario parameter;
[0116] Based on the parameter information uploaded by the vehicle in the order period corresponding to the complaint work order, a large model is used to generate a second discrimination parameter in the scene recognition result, and the second discrimination parameter and the first discrimination parameter are both used to characterize the current judgment scene and the confidence of the scene;
[0117] Calculating a matching value between the first discrimination parameter and the second discrimination parameter;
[0118] If the matching value meets the preset conditions, the AIGC model is used to generate the processing result and processing description of the complaint work order;
[0119] If the matching value does not meet the preset condition, the scene parameter is re-identified or the scene recognition result is evaluated.
[0120] In one embodiment of the present application, the sending module 250 is also used to
[0121] According to the processing result of the complaint work order, select the corresponding preset processing plan;
[0122] Calling the customer service module to send the preset processing solution and the processing description to the passenger;
[0123] Determining whether to end the processing of the complaint ticket based on the passenger's satisfaction with the processing result;
[0124] When receiving a satisfactory response from the passenger, the processing of the complaint work order is terminated;
[0125] In the case of receiving an unsatisfactory response from the passenger, continue to receive new feedback descriptions from the passenger and continue to process the complaint ticket in combination with the context information in the customer service module.
[0126] In one embodiment of the present application, an optimization module is also included for
[0127] Collect complaint handling records for each complaint ticket;
[0128] Analyze the effectiveness of the standardized scenarios and the user's satisfaction with the handling results based on the complaint handling records;
[0129] The effectiveness of the standardized scenarios and the user's satisfaction with the processing results are input into the AIGC model to continuously optimize the identification of scenarios and the response to complaint determinations.
[0130] In one embodiment of the present application, the receiving module is also used
[0131] After the trip order is confirmed, parameter information uploaded by the vehicle terminal is received, and the parameter information includes at least one of the following: vehicle audio and video monitoring information, vehicle real-time data, and image data inside and outside the vehicle.
[0132] In one embodiment of the present application, the receiving and processing module is further used to receive the complaint scenario and processing demands described in natural language in the complaint work order;
[0133] Use the NLP model to parse and convert the complaint scenario and processing requirements described in natural language in the complaint ticket into standardized scenario parameters;
[0134] The complaint scenario elements include at least one of the following: failure to arrive at the agreed time, taking a detour, the driver being rude to passengers, unreasonable fares, strange smells in the car, and the air conditioning not being turned on;
[0135] The handling of the demands includes at least one of the following: refund, compensation, and complaint against the driver.
[0136] In one embodiment of the present application, the identification module is also used to
[0137] Based on the image recognition results, speech recognition results, vehicle status analysis results, and traffic situation prediction results in the parameter information, a large model analysis is used to obtain an objective recognition result of the scene.
[0138] It can be understood that the above-mentioned complaint ticket processing device can implement the various steps of the complaint ticket processing method provided in the aforementioned embodiment, and the relevant explanations on the complaint ticket processing method are applicable to the complaint ticket processing device and will not be repeated here.
[0139] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0140] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0141] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0142] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a complaint ticket processing device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:
[0143] Receiving parameter information uploaded by the vehicle terminal, wherein the parameter information is used to record objective data generated during driving;
[0144] Receive complaint tickets and convert them into standardized scenario parameters using NLP model analysis, where the scenario parameters include complaint scenario elements and processing requirements;
[0145] Perform scene analysis based on the parameter information to obtain a scene recognition result;
[0146] The AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order, where the processing description is used as a subjective description of the processing result;
[0147] The processing result and the processing description are sent to the passenger to determine the passenger's satisfaction with the processing result.
[0148] The above application Figure 1 The method performed by the complaint work order processing device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0149] The electronic device may also perform Figure 1 The method executed by the complaint work order processing device in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0150] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method executed by the complaint work order processing device in the illustrated embodiment is specifically used to execute:
[0151] Receiving parameter information uploaded by the vehicle terminal, wherein the parameter information is used to record objective data generated during driving;
[0152] Receive complaint tickets and convert them into standardized scenario parameters using NLP model analysis, where the scenario parameters include complaint scenario elements and processing requirements;
[0153] Perform scene analysis based on the parameter information to obtain a scene recognition result;
[0154] The AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order, where the processing description is used as a subjective description of the processing result;
[0155] The processing result and the processing description are sent to the passenger to determine the passenger's satisfaction with the processing result.
[0156] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0157] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0158] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0160] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0161] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0162] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0163] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0164] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0165] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for handling a complaint work order, wherein: The method comprises: Receiving parameter information uploaded by the vehicle terminal, wherein the parameter information is used to record objective data generated during driving; Receive complaint tickets and convert them into standardized scenario parameters using NLP model analysis, where the scenario parameters include complaint scenario elements and processing requirements; Perform scene analysis based on the parameter information to obtain a scene recognition result; The AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order, where the processing description is used as a subjective description of the processing result; The processing result and the processing description are sent to the passenger to determine the passenger's satisfaction with the processing result.
2. The method of claim 1, wherein: The AIGC model is used to analyze the scenario parameters and the scenario recognition results to generate a processing result and a processing description of the complaint work order. The processing description is used as a subjective description of the processing result, including: Generate a first discrimination parameter based on the complaint scenario element and the processing demand in the scenario parameter; Based on the parameter information uploaded by the vehicle in the order period corresponding to the complaint work order, a large model is used to generate a second discrimination parameter in the scene recognition result, and the second discrimination parameter and the first discrimination parameter are both used to characterize the current judgment scene and the confidence of the scene; Calculating a matching value between the first discrimination parameter and the second discrimination parameter; If the matching value meets the preset conditions, the AIGC model is used to generate the processing result and processing description of the complaint work order; If the matching value does not meet the preset condition, the scene parameter is re-identified or the scene recognition result is evaluated.
3. The method of claim 2, wherein: The sending of the processing result and the processing description to the passenger to determine the passenger's satisfaction with the processing result includes: According to the processing result of the complaint work order, select the corresponding preset processing plan; Calling the customer service module to send the preset processing solution and the processing description to the passenger; Determining whether to end the processing of the complaint ticket based on the passenger's satisfaction with the processing result; When receiving a satisfactory response from the passenger, the processing of the complaint work order is terminated; In the case of receiving an unsatisfactory response from the passenger, continue to receive new feedback descriptions from the passenger and continue to process the complaint ticket in combination with the context information in the customer service module.
4. The method of claim 3, wherein: The method further comprises: Collect complaint handling records for each complaint ticket; Analyze the effectiveness of the standardized scenarios and the user's satisfaction with the handling results based on the complaint handling records; The effectiveness of the standardized scenarios and the user's satisfaction with the processing results are input into the AIGC model to continuously optimize the identification of scenarios and the response to complaint determinations.
5. The method of claim 1, wherein: The receiving of parameter information uploaded by the vehicle-mounted terminal, wherein the parameter information is used to record objective data generated during driving, includes: After the trip order is confirmed, parameter information uploaded by the vehicle terminal is received, and the parameter information includes at least one of the following: vehicle audio and video monitoring information, vehicle real-time data, and image data inside and outside the vehicle.
6. The method of claim 1, wherein: The receiving of the complaint ticket and converting it into standardized scenario parameters using the NLP model analysis, wherein the scenario parameters include complaint scenario elements and processing demands, including: Receive the complaint scenario described in natural language in the complaint ticket and handle the request; Use the NLP model to parse and convert the complaint scenario and processing requirements described in natural language in the complaint ticket into standardized scenario parameters; The complaint scenario elements include at least one of the following: failure to arrive at the agreed time, taking a detour, the driver being rude to passengers, unreasonable fares, strange smells in the car, and the air conditioning not being turned on; The handling of the demands includes at least one of the following: refund, compensation, and complaint against the driver.
7. The method of claim 1, wherein: The performing scene analysis based on the parameter information to obtain a scene recognition result includes: Based on the image recognition results, speech recognition results, vehicle status analysis results, and traffic situation prediction results in the parameter information, a large model analysis is used to obtain an objective recognition result of the scene.
8. A complaint work order processing device, wherein: The device comprises: A receiving module, used to receive parameter information uploaded by the vehicle terminal, wherein the parameter information is used to record objective data generated during driving; A receiving and processing module, which is used to receive complaint tickets and convert them into standardized scenario parameters using an NLP model. The scenario parameters include complaint scenario elements and processing demands. An identification module, used to perform scene analysis based on the parameter information to obtain a scene identification result; A generation module, used to analyze the scenario parameters and the scenario recognition results using an AIGC model, and generate a processing result and a processing description of the complaint work order, wherein the processing description is used as a subjective description of the processing result; The sending module is used to send the processing result and the processing description to the passenger to determine the passenger's satisfaction with the processing result.
9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.
10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.
Citation Information
Cited By
Complaint processing method and system
CN122470715A
