Data processing method for power conversion operation and maintenance, computing device and readable storage medium

Abstract

The invention discloses a data processing method for power conversion operation and maintenance, computing equipment and a computer readable storage medium. The method comprises the steps of performing intention recognition on a power conversion operation and maintenance problem; according to an identification result of the intention identification, determining a processing path for processing the power conversion operation and maintenance problem; and correspondingly requesting a target service interface according to the processing path so as to obtain target data information based on the target service interface. Thus, intention recognition is performed on the power conversion operation and maintenance problem to correspondingly determine the processing path and the service interface, and the processing efficiency of the power conversion operation and maintenance problem is improved.

Description

Technical Field

[0001] This application relates to the field of large models, and particularly to a data processing method, a computing device, and a readable storage medium for battery swapping operation and maintenance. Background Art

[0002] With the popularization of electric vehicles, battery swapping stations, as a new mode of electric vehicle charging, have gradually become important infrastructure. However, in the daily operation and maintenance of battery swapping stations, many bottlenecks in business processes are often encountered, which may involve system problems. When maintenance personnel handle these problems, they often need to contact technical personnel for troubleshooting. The whole process requires multiple confirmations and interactions, which takes a long time.

[0003] In the prior art, some battery swapping stations adopt a rule-based fault troubleshooting system to guide maintenance personnel to troubleshoot problems through preset rules. However, these solutions often lack flexibility and cannot adapt to changing actual situations, resulting in low efficiency in handling problems. Summary of the Invention

[0004] The purpose of this application is to provide a data processing method, a computing device, and a computer-readable storage medium for battery swapping operation and maintenance, which improve the processing efficiency of battery swapping operation and maintenance problems.

[0005] To achieve the above object: In a first aspect, an embodiment of this application provides a data processing method for battery swapping operation and maintenance, including: Performing intent recognition on battery swapping operation and maintenance problems; Determining a processing path for handling the battery swapping operation and maintenance problem according to the recognition result of the intent recognition; Correspondingly requesting a target service interface according to the processing path to obtain target data information based on the target service interface.

[0006] In an embodiment, the performing intent recognition on battery swapping operation and maintenance problems includes: Inputting the obtained battery swapping operation and maintenance problem into a first model to obtain the problem type of the battery swapping operation and maintenance problem, and determining it as the recognition result of the intent recognition; The first training process of the first model includes: Determining multiple problem types of battery swapping operation and maintenance, and determining a preset number of query languages based on each problem type; Determining the multiple problem types and the corresponding query languages as the first training data set for training the first model; Training the first model according to the first training data set.

[0007] In one embodiment, determining a processing path for processing the battery swapping operation and maintenance problem according to the recognition result of the intention recognition includes: Determining corresponding proprietary business terms in the preset battery swapping data according to the recognition result of the intention recognition and the battery swapping operation and maintenance problem; Determining a processing path for processing the battery swapping operation and maintenance problem according to the proprietary business terms and the recognition result.

[0008] In one embodiment, determining corresponding proprietary business terms in the preset battery swapping data according to the recognition result of the intention recognition and the battery swapping operation and maintenance problem includes: Determining a second model according to the problem type of the recognition result; Inputting the battery swapping operation and maintenance problem into the second model to obtain the proprietary business terms of the battery swapping operation and maintenance problem; The second training process of the second model includes: Obtaining all the proprietary business terms corresponding to the problem type, and respectively making annotation descriptions for the proprietary business terms; Determining the proprietary business terms and the corresponding annotation descriptions as the second training data set for the second model; Training the second model according to the second training data set.

[0009] In one embodiment, determining a processing path for processing the battery swapping operation and maintenance problem according to the proprietary business terms and the intention type of the recognition result includes: Determining at least one call interface information corresponding to the battery swapping operation and maintenance problem by means of preset text matching according to the proprietary business terms; Obtaining a processing path for processing the battery swapping operation and maintenance problem according to the at least one call interface information and the battery swapping operation and maintenance problem.

[0010] In one embodiment, corresponding to requesting a target service interface according to the processing path to obtain target data information based on the target service interface includes: Determining a target service interface according to the processing path; Integrating the battery swapping operation and maintenance problem, the proprietary business terms, and the processing path, and correspondingly generating request information for the service interface based on the integrated information; Initiating a request to the target service interface based on the request information to obtain target data information.

[0011] In one embodiment, the method further includes: Define multiple service interfaces for battery swapping operation and maintenance respectively, determine the type of each service interface and the label information for explaining the data information in the service interface; the types of the service interfaces include operation and maintenance interfaces and repair interfaces.

[0012] In one embodiment, after corresponding to request a target service interface according to the processing path to obtain target data information based on the target service interface, it further includes: Obtain the context information of the battery swapping operation and maintenance problem, and determine the analysis result of the battery swapping operation and maintenance problem according to the battery swapping operation and maintenance problem, the context information, and the target data information; Output the analysis result.

[0013] In a second aspect, an embodiment of the present application provides a computing device, specifically including: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the instructions to execute the data processing method for battery swapping operation and maintenance as described in the first aspect.

[0014] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the instructions in the computer-readable storage medium are executed by a processor of a computing device, the computing device can implement the data processing method for battery swapping operation and maintenance as described in the first aspect.

[0015] A data processing method, a computing device, and a computer-readable storage medium for battery swapping operation and maintenance provided by an embodiment of the present application include: performing intent recognition on a battery swapping operation and maintenance problem; determining a processing path for processing the battery swapping operation and maintenance problem according to the recognition result of the intent recognition; corresponding to request a target service interface according to the processing path to obtain target data information based on the target service interface. In this way, by performing intent recognition on the battery swapping operation and maintenance problem to correspondingly determine the processing path and service interface, the processing efficiency of the battery swapping operation and maintenance problem is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of the data processing method for battery swapping operation and maintenance provided by an embodiment of the present invention Figure 1 ; Figure 2 is a flowchart of the data processing method for battery swapping operation and maintenance provided by an embodiment of the present invention Figure 2 ; Figure 3 is a schematic structural diagram of the computing device provided by an embodiment of the present invention; Processor 210, memory 211, network interface 212, bus system 213. Detailed implementation

[0017] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0018] It should be noted that in this document, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including that element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined based on their explanations in the specific embodiments or further in combination with the context of the specific embodiments.

[0019] It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this document, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining". Furthermore, as used in this document, the singular forms "a", "an", and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising", "including" indicate the presence of the stated features, steps, operations, elements, components, items, kinds, and / or groups, but do not preclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" as used herein are interpreted inclusively, or mean any one or any combination. Thus, "A, B, or C" or "A, B, and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B, and C". An exception to this definition occurs only when the combination of elements, functions, steps, or operations are mutually exclusive in some way.

[0020] It should be understood that although the steps in the flowcharts in the embodiments of this application are shown sequentially in the direction of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a part of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0021] It should be noted that in this document, step codes such as S101, S102, etc. are used. The purpose is to more clearly and briefly express the corresponding content and do not constitute a substantial limitation in order. Those skilled in the art may execute S102 first and then S101, etc. during specific implementation, but these should all be within the protection scope of this application.

[0022] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0023] In the following description, suffixes such as "module", "component", or "unit" used to represent elements are only for the convenience of explaining the present application, and have no specific meaning in themselves. Therefore, "module", "component", or "unit" can be used interchangeably.

[0024] Referring to Figure 1 , an embodiment of the present application provides a data processing method for battery swapping operation and maintenance. The data processing method for battery swapping operation and maintenance can be implemented in software and / or hardware. In this embodiment, taking the data processing method for battery swapping operation and maintenance applied to a computing device as an example, the data processing method for battery swapping operation and maintenance provided in this embodiment includes: Step S101: Identify the intention of battery swapping operation and maintenance problems.

[0025] Among them, battery swapping operation and maintenance refers to the operation and maintenance of electric vehicle battery swapping stations. Common problems include order anomalies, equipment failures, location queries, etc. Optionally, through natural language processing technology, identify the battery swapping operation and maintenance problems expressed in natural language by users (such as voice / text) to determine the user's intention based on the battery swapping operation and maintenance problems.

[0026] Optionally, in the scenario of battery swapping operation and maintenance, it is first necessary to identify the intention of battery swapping operation and maintenance problems through means such as natural language processing technology and semantic analysis algorithms, including the identification and analysis of keywords, phrases, sentence structures, and context.

[0027] In one embodiment, identifying the intention of battery swapping operation and maintenance problems includes: Input the obtained battery swapping operation and maintenance problem into the first model to obtain the problem type of the battery swapping operation and maintenance problem, and determine it as the recognition result of intention recognition; The first training process of the first model includes: Determine multiple problem types of battery swapping operation and maintenance, and determine a preset number of inquiry languages based on each problem type; Determine the multiple problem types and the corresponding inquiry languages as the first training data set for training the first model; Train the first model according to the first training data set.

[0028] Optionally, based on the trained first model, determine the corresponding problem type according to the obtained battery swapping operation and maintenance problem to complete the problem recognition of battery swapping operation and maintenance. Here, the first training process of the first model includes: Optionally, relevant problem types of power swap operation and maintenance problems occurring during the operation and maintenance of the power swap station are collected or defined in advance. Here, the power swap operation and maintenance problems include those in two fields: the power swap operation and maintenance field and the repair field. In different fields, they can be further divided into various different power swap operation and maintenance types, including: abnormal power swap order settlement problems, power swap station location query problems, abnormal number of power swap batteries problems, etc. This can be based on the problems that have occurred during the actual business operation, that is, the relevant problems that have occurred during the operation of the power swap station, and the relevant data information is collected accordingly.

[0029] Optionally, for each problem type, some natural language samples of these business problems are collected correspondingly as the query language for this problem type. The preset number of query languages is generally set to 5 - 10 to ensure the diversity of the samples and make them more in line with the expression of natural questions.

[0030] Optionally, a first model with the ENCODER and DECODER architectures of the Transformer framework based on deep learning is used for model training, and the weighted average processing is performed on the output results after training to determine the final user intention. Here, when performing intention recognition based on the first model, the context content of the user's power swap operation and maintenance problems can be considered to improve the accuracy of intention recognition in complex environments.

[0031] Step S102: Determine the processing path for handling the power swap operation and maintenance problem according to the recognition result of intention recognition.

[0032] Optionally, according to the recognition result of intention recognition, operations such as task assignment and path planning are performed to ensure the effective execution of the power swap operation and maintenance problem. For example, in the order problem, the task path can be planned according to the recognition of intention recognition, optimizing resource allocation, reducing manual intervention, and improving work efficiency and response speed.

[0033] In an implementation manner, determining the processing path for handling the power swap operation and maintenance problem according to the recognition result of intention recognition includes: Determine the corresponding proprietary business terms in the preset power swap data according to the recognition result of intention recognition and the power swap operation and maintenance problem; [[ID=IG=19]]Determine the processing path for handling the power swap operation and maintenance problem according to the proprietary business terms and the recognition result.

[0034] Optionally, a large amount of historical data and business knowledge will usually be accumulated in the preset battery swapping data, including problems that may occur in the field of battery swapping operation and maintenance and their corresponding solutions, professional terms, etc. Optionally, the preset battery swapping data is systematically sorted and classified for quick retrieval and matching. For example, the data related to charging may include the performance parameters of different models of charging devices, common fault types and codes, battery charging curve standards, etc.

[0035] Optionally, through algorithms of keyword and semantic matching, the recognition result of intent recognition and the battery swapping operation and maintenance problem are used to find the most matching proprietary business terms in the preset battery swapping data. For example, for the problem of "abnormal charging speed", after searching and comparison analysis, proprietary business terms such as "charging rate deviation" and "charging device efficiency failure" are determined. These proprietary business terms are accurate descriptions of the problem and can more accurately reflect the essence and characteristics of the problem.

[0036] Optionally, according to the obtained proprietary business terms and recognition results, the processing path for handling the battery swapping operation and maintenance problem is determined, including performing tasks corresponding to the battery swapping operation and maintenance problem or obtaining relevant data information based on the battery swapping operation and maintenance problem. In this way, when processing based on the battery swapping operation and maintenance problem, at least one service interface for obtaining data information is determined based on the proprietary business terms and the recognition result of intent recognition, and the corresponding processing path is determined.

[0037] In one embodiment, determining the corresponding proprietary business terms in the preset battery swapping data according to the recognition result of intent recognition and the battery swapping operation and maintenance problem includes: Determining a second model according to the problem type of the recognition result; Inputting the battery swapping operation and maintenance problem into the second model to obtain the proprietary business terms of the battery swapping operation and maintenance problem; The second training process of the second model includes: Obtaining all the proprietary business terms corresponding to the problem type and respectively making annotation descriptions for the proprietary business terms; Determining the proprietary business terms and the corresponding annotation descriptions as the second training data set for the second model; Training the second model according to the second training data set.

[0038] Optionally, all proprietary business terms used in the operation and maintenance of battery swap stations are collected, and these proprietary business terms are annotated in the collected text to facilitate the training of these terms through the second model. In this way, the proprietary business terms and the corresponding annotations are determined as the second training data set for the second model, that is, the annotations are used as input features for model training, and the proprietary business terms are trained as output features for the second model. Here, after obtaining the proprietary business terms, the professional business terms can also be classified based on different types of questions. Here, the same proprietary business term can correspond to different types of questions.

[0039] Optionally, a large autoregressive architecture model with 720B parameters can be used as the second model, and the second model can be fine-tuned and trained based on the currently acquired second training data set. Through multiple rounds of training, the model can achieve high-precision recognition of proprietary business terms under few-shot conditions, that is, use Few-Shot Learning (ProtoNetworks) to deal with the situation where there are insufficient samples in the second training data set.

[0040] Here, while inputting the battery swap operation and maintenance problem into the second model, the context associated with the battery swap operation and maintenance problem is obtained, and the battery swap operation and maintenance problem and the context are simultaneously input into the second model to determine the corresponding proprietary business terms based on the output of the second model. Here, the professional business terms output based on the second model may be one or more proprietary business terms associated with the battery swap operation and maintenance problem. The specific number of proprietary business terms output by the second model is not limited here. Optionally, after obtaining the proprietary business terms of the battery swap operation and maintenance problem, the proprietary business terms may be returned / output using a Json structure.

[0041] In one embodiment, a processing path for handling battery swap operation and maintenance issues is determined based on the proprietary business term and the intent type of the recognition result, including: Based on proprietary business terms, at least one call interface information corresponding to the battery swap operation and maintenance problem is determined through a preset text matching method; Based on at least one calling interface information and the battery swap operation and maintenance problem, a processing path for handling the battery swap operation and maintenance problem is obtained.

[0042] Optionally, obtain the database file of the preset solutions corresponding to the problems that occur during the operation and maintenance of the battery swapping station. Generally, the database file records the detailed problem-solving steps. Optionally, based on proprietary business terms, recall and match through keyword and semantic matching algorithms to determine at least one call interface information that matches the professional business terms. At the same time, input the recalled information and the battery swapping operation and maintenance problems into the large model. The large model outputs the complete path planning steps for processing the battery swapping operation and maintenance problems according to the input at least one call interface information and the battery swapping operation and maintenance problems, that is, determine the detailed information such as which business interfaces need to be queried.

[0043] Step S103: According to the processing path, correspond to request the target business interface to obtain the target data information based on the target business interface.

[0044] Optionally, after determining the target business interface, construct the corresponding request parameters according to the interface information of the target business interface. Different business interfaces have different request parameters. These request parameters are the input information required for the interface to execute the business logic. These request parameters need to be accurately set according to the format and data type specified by the interface to ensure that the target business interface can correctly understand and process the request.

[0045] In one embodiment, according to the processing path, corresponding to request the target business interface to obtain the target data information based on the target business interface, including: Determine the target business interface according to the processing path; Integrate the battery swapping operation and maintenance problems, proprietary business terms, and processing paths, and generate the request information for the business interface based on the integrated information; Initiate a request to the target business interface based on the request information to obtain the target data information.

[0046] Optionally, according to the processing path, determine the target business interface for information query. After constructing the request parameters, send a request to the target business interface. Here, when the target business interface receives the request information, the target business interface will process the request parameters according to the preset business logic and generate the corresponding response result. The response result includes: the status code indicating whether the request is successful, and the target data information or task execution result requested by the request information.

[0047] Optionally, according to the processing path information, the business interface calls can be carried out in an orderly manner. Here, when obtaining the data information based on the target business interface, the valid information returned by the target business interface is used as the target data information.

[0048] In one embodiment, the method further includes: Define multiple service interfaces for battery swapping operation and maintenance respectively, determine the type of each service interface and the label information for explaining the data information in the service interface; the types of service interfaces include operation and maintenance interfaces and repair interfaces.

[0049] Optionally, in order to ensure efficient and accurate collaborative work, it is necessary to clearly and explicitly define each service interface and determine the label information for the service interface. In this way, based on the data information associated with the service interface, a reasonable definition can be made to clarify the responsibilities and interaction methods between each service interface. Here, the label information is a summary label for explaining the data information that the service interface can provide. In this way, the data information that can be obtained from the service interface can be directly determined based on the label information of each service interface, and setting the label information can help improve the efficiency of data processing.

[0050] Optionally, determine the label information of each service interface, and perform a matching calculation on the proprietary business terms and the label information of each service interface based on a preset text matching method to determine the target service interface corresponding to the proprietary business term. Taking the text similarity matching as an example of the preset text matching method, perform a similarity matching on the proprietary business term and the label information of each interface one by one, and determine the service interface with a similarity greater than the preset similarity threshold and the maximum similarity to the proprietary business term as the target service interface.

[0051] It can be understood that determine at least one proprietary service interface corresponding to the proprietary business term, and integrally connect the determined at least one proprietary service interface based on a large model, that is, the large model effectively connects the implementation logic of the battery swapping operation and maintenance problem based on multiple proprietary service interfaces to obtain a processing path for processing the battery swapping operation and maintenance problem, improving the efficiency and quality of the battery swapping operation and maintenance work.

[0052] In one embodiment, after corresponding to request the target service interface according to the processing path to obtain the target data information based on the target service interface, it further includes: Obtain the context information of the battery swapping operation and maintenance problem, and determine the analysis result of the battery swapping operation and maintenance problem according to the battery swapping operation and maintenance problem, the context information, and the target data information; Output the analysis result.

[0053] Optionally, perform a fusion analysis on the target data information obtained by the interface, the battery swapping operation and maintenance problem, and the context information of the battery swapping operation and maintenance problem, and return the analysis result to the user to form a final execution plan or calculation result. In one embodiment, for the operations directly performed through the battery swapping station service interface, information that can be perceived and explained can be directly returned.

[0054] Specifically, the problems of battery swapping operation and maintenance, the context information of the battery swapping operation and maintenance problems in the user conversation, and the target data information returned by the battery swapping station business interface are combined as inputs and input into the large model, and the large model analyzes and returns according to the results of solving the battery swapping operation and maintenance problems.

[0055] Optionally, the returned types are distinguished and displayed according to the query information or the control of the battery swapping service instruction, etc., which is more flexible in the user interaction experience.

[0056] In summary, the data processing method for battery swapping operation and maintenance provided by the above embodiments improves the processing efficiency of battery swapping operation and maintenance problems by identifying the intentions of battery swapping operation and maintenance problems to correspondingly determine the processing paths and business interfaces.

[0057] It can be understood that the first model, the second model, and the large model proposed in this application are uniformly managed and scheduled based on the gateway interface as the middle layer. In this way, the upper-layer application does not need to directly interact with each model, but calls through the gateway. In this way, when replacing the model, only the gateway part needs to be adjusted, and other code data does not need to be modified.

[0058] Based on the same inventive concept as the foregoing embodiments, a specific example is used below to elaborate in detail on a data processing method for battery swapping operation and maintenance provided by this application. Specifically, the data processing method for battery swapping operation and maintenance is applied to a large model. Through the collaborative work of multiple core parts such as intention recognition, entity extraction, path planning, business interface and information fusion, and solution modules, it can effectively meet the needs of enterprises in complex business environments, be flexibly applied to battery swapping operation and maintenance problems in different business scenarios, and improve the overall operation efficiency, specifically as Figure 2 shown.

[0059] I. Intention Recognition Module Perform intention recognition on the obtained battery swapping operation and maintenance problems. For the battery swapping operation and maintenance business of the battery swapping station, the battery swapping operation and maintenance problems should focus on the fields of battery swapping station operation and maintenance and repair, including the types of battery swapping station services, the types of battery swapping station repair problems, etc. These data need to be collected and defined in advance. The specific processing steps include: A. Collect or define in advance the types of problems in the battery swapping operation and maintenance process, such as: abnormal settlement of battery swapping orders, query problems of the geographical location of the battery swapping station, abnormal number of battery swapping batteries, etc.

[0060] B. According to each type of problem, collect some natural language samples. It is best to have 5-10 samples of each type to ensure the diversity of the samples and conform to the expression of natural problems.

[0061] C. Two types of ENCODER and DECODER architecture models based on the deep learning Transformer framework are used for model training. The weighted average technique is utilized based on the results of the trained model to determine the final user intent. Meanwhile, the content of the user's current context can also be incorporated during model intent recognition to improve the accuracy of intent recognition in complex user environments.

[0062] D. After the trained model outputs the final intent category, determine the problem type of the current battery swapping operation and maintenance issue.

[0063] II. Entity Extraction Module Based on the determined problem type of the battery swapping operation and maintenance issue, determine the corresponding entity extraction module to further perform entity extraction operations. This module is to ensure real-time access to information in the business system by requesting the interfaces of the business system under the premise of conforming to the business system interface specifications, providing guarantee for real-time resolution of user problems. To implement this functional module, the specific steps are as follows: A. Through the recognition results of intent recognition, the dedicated entity extraction module can be locked. There are multiple professional entity extraction module types corresponding to different scenarios and problem categories.

[0064] B. Pre-collect all proprietary business terms during the operation and maintenance and repair of the battery swapping station, and at the same time label these proprietary business terms in the collected text to facilitate the training of this part of the terms by the model and enable the model to accurately recognize them.

[0065] C. Use a large autoregressive architecture model with 720B parameters to perform fine-tuning training in the current corpus. Through multiple rounds of training, enable the model to achieve high-precision recognition of proprietary business terms under few-shot conditions.

[0066] D. Combine the current user problem and the context of the problem, use the fine-tuned large model to perform entity extraction operations, and return the extraction results in the Json structure for the use of the next module.

[0067] III. Path Planning Module The path planning module is responsible for converting the intelligent decision into specific operations, that is, according to the results of the intelligent decision, automatically perform task allocation, path planning and other operations to ensure effective handling of battery swapping operation and maintenance issues. For example, in the case of order problems, the path planning module can plan the task path according to the results of intent recognition and the types of entities, optimizing resource allocation. The automated execution at this level greatly reduces manual intervention, improves work efficiency and response speed, and is the core of the automated execution of the intelligent agent.

[0068] A. Solutions to problems that arise during the operation and maintenance of a battery swap station correspond to pre-set solution documents, which record detailed problem-solving steps.

[0069] B. Intent is identified through the user's question and context, and information is recalled from the solution document using text matching of the question and context to obtain a complete solution path.

[0070] C. Input recall solution information and battery swap operation and maintenance issues into the vertical big model. Based on the input, the vertical big model can plan the complete path steps and determine detailed information such as which business interfaces need to be queried.

[0071] D. Combined with the JSON output of the entity extraction module and the planning information of the current path planning module, business interface calls can be made in order to obtain the necessary real-time business results for use by subsequent modules.

[0072] 4. Business Interface Module The business interface module is a collection of various business systems currently being used in the battery swap business at battery swap stations. In order to facilitate the operation and calling of the entire intelligent body, these modules can be classified and encapsulated here to meet the identification and management of the intelligent body.

[0073] A. Classify services based on the two areas of battery swap station operation and maintenance. First, split the service interfaces into two major categories: battery swap operation and maintenance, and maintenance. Then, perform a secondary classification based on the details and problem types of each service. This classification can be mapped to the intent recognition type described earlier.

[0074] B. Accurately define all business interfaces in advance so that they can be effectively connected during the model's path planning process to solve user problems.

[0075] C. Encapsulate the entity information extracted from the entity extraction module with the business interface request URL, request header, and other information, and then perform a business interface request to obtain the interface information.

[0076] D. For interfaces that obtain information, feedback information can be obtained directly from the interfaces, and for interfaces that issue operating instructions to the battery swap station business system, instruction execution and control management can be completed directly through the interfaces.

[0077] 5. Information Fusion and Solution Module This module is designed to integrate the information obtained from the interface with the contextual information. The integrated information can be returned to the user to form a final feasible execution plan. At the same time, for operations directly executed through the battery swap station business interface, information that can be perceived and interpreted by the user is returned, including: A. Combine the user's question, the context in the user's conversation, and the valid information returned by the battery swapping station service interface as input, and input it into the large model. Let the model analyze and return according to the result of problem solving.

[0078] B. The returned types are differentiated and displayed according to the query information returned or the control of the battery swapping service instruction, etc., which is more flexible in the user's interaction experience.

[0079] Exemplarily, in order settlement, there is settlement by degree of electricity and settlement by mileage. When the user has an objection to the amount of the order settlement and raises a battery swapping operation and maintenance problem of "there is a problem with the settlement amount of a certain order", the corresponding path planning of intention recognition can identify that this is the intention of an order problem, and the path is planned to require an order solving agent to solve it. In this way, knowing that it is to solve the abnormal order amount, the list of service interfaces to be queried is clear. If the queried service interface is clear, then the query parameters to be provided are clear. Then, by extracting the entities in the user's question and collecting the user's basic information, it is completed into the json data format, and the service interfaces are called sequentially, and the returned results are comprehensively analyzed and sorted, and finally the reasons and solutions for the abnormal order amount are returned to the user.

[0080] In summary, the data processing method for battery swapping operation and maintenance provided by the above embodiments improves the processing efficiency of battery swapping operation and maintenance problems by performing intention recognition on battery swapping operation and maintenance problems to correspondingly determine the processing path and service interface.

[0081] Based on the same inventive concept as the foregoing embodiments, an embodiment of the present invention provides a computing device, as Figure 3 shown, the computing device includes: a processor 210 and a memory 211 storing a computer program; wherein, Figure 3 The processor 210 shown in is not used to refer to the number of processors 210 being one, but only to refer to the positional relationship of the processor 210 relative to other devices. In actual applications, the number of processors 210 can be one or more; similarly, Figure 3 The memory 211 shown in also has the same meaning, that is, it only refers to the positional relationship of the memory 211 relative to other devices. In actual applications, the number of memories 411 can be one or more. When the processor 210 runs the computer program, the data processing method for battery swapping operation and maintenance described above is implemented.

[0082] The computing device may further include: at least one network interface 212. Each component in the computing device is coupled together through a bus system 213. It can be understood that the bus system 213 is used to realize the connection and communication between these components. In addition to including a data bus, the bus system 213 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clear illustration, in Figure 3 all kinds of buses are labeled as the bus system 213.

[0083] Among them, the memory 211 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory), an electrically erasable programmable read-only memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), a ferromagnetic random access memory (FRAM, ferromagnetic random access memory), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM, Compact Disc Read-Only Memory); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM, Random Access Memory), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as a static random access memory (SRAM, Static Random Access Memory), a synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory), a dynamic random access memory (DRAM, Dynamic Random Access Memory), a synchronous dynamic random access memory (SDRAM, Synchronous Dynamic Random Access Memory), a double data rate synchronous dynamic random access memory (DDR SDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), an enhanced synchronous dynamic random access memory (ESDRAM, Enhanced Synchronous Dynamic Random Access Memory), a sync link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), a direct rambus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 211 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memories.

[0084] The memory 211 in the embodiments of the present invention is used to store various types of data to support the operation of the computing device. Examples of such data include: any computer programs for operating on the computing device, such as operating systems and application programs; contact data; phone book data; messages; pictures; videos, etc. Among them, the operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application programs can include various application programs, such as a media player, a browser, etc., for implementing various application services. Here, the program for implementing the method of the embodiments of the present invention can be included in the application programs.

[0085] Based on the same inventive concept as the foregoing embodiments, this embodiment also provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. The computer-readable storage medium can be a ferromagnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it can also be various devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc. When the computer program stored in the computer-readable storage medium is run by a processor, it implements the data processing method for battery swapping operation and maintenance applied to the above computing device. For the specific step flow implemented when the computer program is executed by the processor, please refer to Figure 1 the description of the illustrated embodiments, which will not be repeated here.

[0086] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0087] In this document, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, in addition to the elements listed, and may also include other elements not expressly listed.

[0088] As described above, it is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A data processing method for battery swapping operation and maintenance, characterized in that Including: Performing intention recognition on the battery swapping operation and maintenance problems; Determining a processing path for handling the battery swapping operation and maintenance problems according to the recognition result of the intention recognition; Correspondingly requesting a target service interface according to the processing path to obtain target data information based on the target service interface.

2. The method according to claim 1, characterized in that, The performing intention recognition on the battery swapping operation and maintenance problems includes: Inputting the obtained battery swapping operation and maintenance problems into a first model to obtain the problem types of the battery swapping operation and maintenance problems, and determining them as the recognition results of the intention recognition; The first training process of the first model includes: Determining multiple problem types of battery swapping operation and maintenance, and determining a preset number of inquiry languages based on each problem type; Determining the multiple problem types and the corresponding inquiry languages as the first training dataset for training the first model; Training the first model according to the first training dataset.

3. The method according to claim 1, characterized in that, The determining a processing path for handling the battery swapping operation and maintenance problems according to the recognition result of the intention recognition includes: Determining corresponding proprietary service names in the preset battery swapping data according to the recognition result of the intention recognition and the battery swapping operation and maintenance problems; Determining a processing path for handling the battery swapping operation and maintenance problems according to the proprietary service names and the recognition result.

4. The method according to claim 3, characterized in that, The determining corresponding proprietary service names in the preset battery swapping data according to the recognition result of the intention recognition and the battery swapping operation and maintenance problems includes: Determining a second model according to the problem type of the recognition result; Inputting the battery swapping operation and maintenance problems into the second model to obtain the proprietary service names of the battery swapping operation and maintenance problems; The second training process of the second model includes: Obtaining all the proprietary service names corresponding to the problem type, and respectively making annotation descriptions for the proprietary service names; Determining the proprietary service names and the corresponding annotation descriptions as the second training dataset for training the second model; Training the second model according to the second training dataset.

5. The method according to claim 3, characterized in that, The determining a processing path for handling the battery swapping operation and maintenance problems according to the proprietary service names and the intention type of the recognition result includes: Determining at least one call interface information corresponding to the battery swapping operation and maintenance problems by means of preset text matching according to the proprietary service names; Obtaining a processing path for handling the battery swapping operation and maintenance problems according to the at least one call interface information and the battery swapping operation and maintenance problems.

6. The method according to any one of claims 1 to 5, characterized in that, The correspondingly requesting a target service interface according to the processing path to obtain target data information based on the target service interface includes: Determining a target service interface according to the processing path; Integrating the battery swapping operation and maintenance problems, the proprietary service names, and the processing path, and correspondingly generating request information for the service interface based on the integrated information; Initiating a request to the target service interface based on the request information to obtain target data information.

7. The method according to claim 1, characterized in that The method further includes: Defining multiple service interfaces for battery swapping operation and maintenance respectively, and determining the type of each service interface and the label information for explaining the data information in the service interface; the types of the service interfaces include operation and maintenance interfaces and repair interfaces.

8. The method according to claim 1, wherein After corresponding to the requested target service interface according to the processing path and obtaining target data information based on the target service interface, it further includes: Obtaining the context information of the battery swapping operation and maintenance problem, and determining the analysis result of the battery swapping operation and maintenance problem according to the battery swapping operation and maintenance problem, the context information, and the target data information; Outputting the analysis result.

9. A computing device, characterized in that, It includes: A processor and a memory for storing executable instructions; wherein, the processor is configured to execute the instructions to implement the data processing method for battery swapping operation and maintenance as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor, the data processing method for battery swapping operation and maintenance as described in any one of claims 1-8 is implemented.

Images