Method and apparatus for acquiring abnormal data, electronic device, and storage medium

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for acquiring abnormal data, relating to the fields of computer and autonomous driving technology. It addresses at least the technical problems of high cost and low efficiency in acquiring abnormal data during autonomous vehicle operation caused by reliance on passive reception and manual acquisition methods in existing technologies. The specific implementation scheme includes: receiving a dispatch request message from a client; in response to the dispatch request message, initiating the dispatch scheduling process for the current round; acquiring dispatch scheduling data and identification information corresponding to the dispatch scheduling process, wherein the dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data; performing backtracking analysis on the dispatch scheduling data based on the identification information to acquire abnormal data, wherein the abnormal data is used to assist in optimizing the dispatch scheduling capabilities corresponding to passenger transport services.

Description

Technical Field

[0001] This disclosure relates to the fields of computer and autonomous driving technology, and in particular to methods, apparatus, electronic devices and storage media for acquiring abnormal data. Background Technology

[0002] During the operation of autonomous vehicles (such as autonomous taxis), unexpected situations frequently arise that do not meet the expected scenarios. Taking the dispatching of autonomous vehicles as an example, the main methods for obtaining the abnormal data corresponding to the above-mentioned anomalies are: collecting user feedback from customers, but this method is inefficient and results in a poor user experience; identifying problems that significantly affect operations online, but this method is ineffective, as the problem has already caused adverse effects by the time it is discovered; and manually analyzing operational log files, but this method is still inefficient and has high labor costs.

[0003] It is readily apparent that existing methods for acquiring anomalous data are labor-intensive and primarily rely on passively accepting such data. This means that using these methods may result in the omission of anomalous data. Currently, no effective solution has been proposed to address these issues. Summary of the Invention

[0004] This disclosure provides methods, apparatus, electronic devices, and storage media for acquiring abnormal data, in order to at least solve the technical problems of high cost and low efficiency in acquiring abnormal data in the operation of autonomous vehicles due to reliance on passive receiving methods and manual acquisition methods in the prior art.

[0005] According to one aspect of this disclosure, a method for obtaining abnormal data is provided, comprising: receiving a dispatch request message from a client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services; responding to the dispatch request message, initiating a dispatch scheduling process for the current round, wherein the dispatch scheduling process is used to match a target vehicle to be used for the dispatch request message; obtaining dispatch scheduling data and identification information corresponding to the dispatch scheduling process, wherein the dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data; and performing backtracking analysis on the dispatch scheduling data based on the identification information to obtain abnormal data, wherein the abnormal data is used to assist in optimizing the dispatch scheduling capabilities corresponding to the passenger transport services.

[0006] According to another aspect of this disclosure, an apparatus for acquiring abnormal data is also provided, comprising: a receiving module for receiving a dispatch request message from a client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services; an initiating module for initiating a dispatch scheduling process for the current round in response to the dispatch request message, wherein the dispatch scheduling process is used to match a target vehicle to be used for the dispatch request message; a first acquiring module for acquiring dispatch scheduling data and identification information corresponding to the dispatch scheduling process, wherein the dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data; and a second acquiring module for performing backtracking analysis on the dispatch scheduling data based on the identification information to acquire abnormal data, wherein the abnormal data is used to assist in optimizing the dispatch scheduling capabilities corresponding to the passenger transport services.

[0007] According to another aspect of this disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method for acquiring abnormal data proposed in this disclosure.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause a computer to execute the method for obtaining abnormal data proposed in this disclosure.

[0009] According to another aspect of this disclosure, a computer program product is also provided, including a computer program that is executed by a processor to obtain abnormal data as proposed in this disclosure.

[0010] In this disclosure, a dispatch request message is received from a client, which requests the dispatch of autonomous vehicles to provide passenger transport services. In response to the dispatch request message, a dispatch scheduling process for the current round is initiated. This process matches the dispatch request message with a target vehicle to be used. Furthermore, dispatch scheduling data and identification information corresponding to the dispatch scheduling process are obtained. The dispatch scheduling data is collected from multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data. Backtracking analysis is performed on the dispatch scheduling data based on the identification information to obtain abnormal data. This abnormal data is used to assist in optimizing the dispatch scheduling capability corresponding to passenger transport services. This achieves the goal of automatically and proactively obtaining abnormal data in the dispatch scheduling process of autonomous vehicle operation, realizing the technical effect of improving the efficiency of obtaining abnormal data in the dispatch scheduling process of autonomous vehicle operation and optimizing dispatch scheduling capability. It solves the technical problem of high cost and low efficiency in obtaining abnormal data in autonomous vehicle operation caused by reliance on passive receiving methods and manual acquisition methods in existing technologies.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for acquiring abnormal data, according to an embodiment of the present disclosure.

[0014] Figure 2 This is a flowchart of a method for obtaining abnormal data according to an embodiment of the present disclosure;

[0015] Figure 3 This is a schematic diagram illustrating a process for acquiring abnormal data according to an embodiment of this disclosure;

[0016] Figure 4 This is a structural block diagram of an apparatus for acquiring abnormal data according to an embodiment of the present disclosure;

[0017] Figure 5 This is a structural block diagram of an optional apparatus for acquiring abnormal data according to an embodiment of the present disclosure. Detailed Implementation

[0018] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] According to embodiments of this disclosure, a method for obtaining abnormal data is provided. It should be noted that the steps shown in the flowcharts in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0022] The method embodiments provided in this disclosure can be performed in a mobile terminal, computer terminal, or similar electronic device. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the disclosure described and / or claimed herein. Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for acquiring abnormal data, according to an embodiment of the present disclosure.

[0023] like Figure 1 As shown, the computer terminal 100 includes a computing unit 101, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 102 or a computer program loaded from storage unit 108 into random access memory (RAM) 103. The RAM 103 may also store various programs and data required for the operation of the computer terminal 100. The computing unit 101, ROM 102, and RAM 103 are interconnected via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0024] Multiple components in the computer terminal 100 are connected to the I / O interface 105, including: an input unit 106, such as a keyboard and mouse; an output unit 107, such as various types of displays and speakers; a storage unit 108, such as a hard disk and optical disk; and a communication unit 109, such as a network interface card (NIC), a modem, or a wireless transceiver. The communication unit 109 allows the computer terminal 100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0025] The computing unit 101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 101 performs the method for acquiring anomalous data described herein. For example, in some embodiments, the method for acquiring anomalous data may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 108. In some embodiments, part or all of the computer program may be loaded and / or installed on the computer terminal 100 via ROM 102 and / or communication unit 109. When the computer program is loaded into RAM 103 and executed by the computing unit 101, one or more steps of the method for acquiring anomalous data described herein may be performed. Alternatively, in other embodiments, the computing unit 101 may be configured in any other suitable manner (e.g., by means of firmware) to perform a method for acquiring abnormal data.

[0026] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a memory system, at least one input device, and at least one output device, and transferring data and instructions to the memory system, the at least one input device, and the at least one output device.

[0027] It should be noted here that, in some optional embodiments, the above... Figure 1 The electronic device shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 1 This is only one instance of a specific particular example, and is intended to illustrate the types of components that may exist in the aforementioned electronic devices.

[0028] Under the aforementioned operating environment, this disclosure provides, for example... Figure 2 The method shown can be used to obtain abnormal data. Figure 1 The computer terminal or similar electronic device shown is used for execution. Figure 2 This is a flowchart of a method for obtaining abnormal data according to an embodiment of this disclosure. Figure 2 As shown, the method may include the following steps:

[0029] Step S21: Receive a dispatch request message from the client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services;

[0030] The aforementioned client is used to assist users in requesting autonomous vehicle passenger transport services. This client connects to a server. The server can be a standalone server, a distributed server cluster, or a cloud server located in the cloud. This server provides the service of dispatching autonomous vehicles to provide passenger transport services.

[0031] In the application scenario, the user sends the dispatch request message through the aforementioned client. This dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services. For example, in the scenario of a self-driving taxi, the aforementioned client can be application software installed on a smart terminal (such as a smartphone, smartwatch, or other device). The user sends a request message to call an autonomous taxi through this client, requesting the autonomous taxi service provider (i.e., the server) to dispatch an autonomous taxi to provide passenger transport services.

[0032] As an extension of the technical solution provided by the above steps of this disclosure, the order dispatching process can also be used to request the dispatch of manually driven vehicles to provide freight services. Furthermore, the order dispatching process can also be used to request the dispatch of manually driven or autonomous vehicles to provide passenger or freight services.

[0033] Step S22: In response to the dispatch request message, initiate the dispatch scheduling process for the current round, wherein the dispatch scheduling process is used to match the target vehicle to be used for the dispatch request message.

[0034] In the application scenario, the server connected to the aforementioned client can initiate multiple rounds of dispatching and scheduling processes when dispatching autonomous vehicles to provide passenger transport services. When the server receives a dispatch request message from the client, it responds to the dispatch request message and initiates the dispatching and scheduling process for the current round.

[0035] The aforementioned dispatching process includes at least the entire process from when a user sends a dispatch request message through the client to when a target vehicle is matched to the user based on the dispatch request message. The dispatching process may also include: dispatching a target vehicle to provide passenger transport services to the user; and monitoring the completion of passenger transport services (e.g., whether the passenger transport service process is standardized, whether the service is completed, user feedback, etc.).

[0036] The dispatching process for the current round described above is used to match the corresponding dispatch request message with a target vehicle to be used. The target vehicle to be used is at least one autonomous vehicle selected from multiple autonomous vehicles. For example, when the received dispatch request message is "Two passengers require a budget autonomous vehicle for passenger transport," the target vehicle matched by the current round of dispatching will be one budget autonomous vehicle from among the multiple autonomous vehicles. As another example, when the received dispatch request message is "Two seven-seater autonomous vehicles are needed for passenger transport," the target vehicles matched by the current round of dispatching will be two seven-seater autonomous vehicles from among the multiple autonomous vehicles.

[0037] Step S23: Obtain the dispatch scheduling data and identification information corresponding to the dispatch scheduling process. The dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data.

[0038] The dispatching data corresponding to the above-mentioned dispatching process is obtained from the log data generated by multiple dispatching actions (such as dispatching actions, scheduling actions, waiting actions, detection actions, etc.) executed in the dispatching process. Specifically, data is collected based on multiple log points corresponding to the dispatching process to obtain the above-mentioned dispatching data.

[0039] The technical solution provided in this disclosure supports the customization of the aforementioned multiple log points. In other words, users can obtain dispatch data for a specified portion (such as a specified type or time) of the dispatch process by pre-setting multiple log points. It is readily understood that the technical solution provided in this disclosure offers high flexibility in data acquisition.

[0040] Because the aforementioned dispatching process often involves multiple dispatching stages in application scenarios, and each stage contains multiple dispatching actions, the dispatching data corresponding to this process is typically characterized by large volume, diverse data types, and complex data structures. Therefore, identifying the corresponding dispatching data by obtaining the identification information associated with the dispatching process can improve the efficiency of data storage, management, retrieval, and analysis related to this data.

[0041] Step S24: Perform backtracking analysis on the dispatch data based on the identification information to obtain abnormal data. The abnormal data is used to assist in optimizing the dispatch capabilities corresponding to passenger transport services.

[0042] After the dispatching process is completed, especially after multiple historical dispatching rounds when autonomous vehicles provide passenger transport services, a large amount of historical data is acquired. This historical data includes dispatching data corresponding to each historical round of the dispatching process. This historical data can characterize the dispatching capability corresponding to multiple historical rounds of the passenger transport service.

[0043] In step S24 above, the specific implementation of backtracking analysis of dispatch data based on identification information to obtain abnormal data can be as follows: based on the identification information corresponding to the current round of dispatch process, backtracking analysis is performed on the dispatch data corresponding to the current round of dispatch process to obtain abnormal data in the current round of dispatch process. This abnormal data is used to characterize the dispatch capability corresponding to the current round of dispatch process in passenger service. That is to say, the above backtracking analysis can be performed based on any single round in passenger service to obtain abnormal data for that single round.

[0044] In step S24 above, the specific implementation of backtracking analysis of dispatch data based on identification information to obtain abnormal data can also be as follows: based on the identification information corresponding to dispatch processes in multiple historical rounds, backtracking analysis is performed on the dispatch data corresponding to dispatch processes in multiple historical rounds to obtain abnormal data in the dispatch processes in multiple historical rounds. This abnormal data is used to characterize the dispatching capability corresponding to dispatch processes in multiple historical rounds in passenger transport services. In other words, the above backtracking analysis can be based on multiple historical rounds in passenger transport services to obtain abnormal data from these multiple historical rounds.

[0045] The aforementioned abnormal data is used to assist in optimizing the dispatching capabilities of passenger transport services. Specifically, the abnormal data is used as feedback information to adjust the dispatching actions executed in the dispatching process of passenger transport services, in order to optimize the corresponding dispatching capabilities, such as improving dispatching accuracy and dispatching efficiency.

[0046] It should be noted that the aforementioned abnormal data can be data with negative effects, such as order dispatch failure data, dispatch timeout data, and target vehicle matching error data. The aforementioned abnormal data can also be data with positive effects, such as order dispatch data where passenger transport services are completed ahead of schedule, or order dispatch data where the daily perfect rating rate exceeds a preset threshold (e.g., more than 90% of orders are five-star reviews).

[0047] In this embodiment of the disclosure, a dispatch request message is received from a client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services; in response to the dispatch request message, a dispatch scheduling process for the current round is initiated, wherein the dispatch scheduling process is used to process the dispatch request.

[0048] The message is matched with the target vehicle to be used, and further dispatch data and identification information corresponding to the dispatch process are obtained. The dispatch data is collected from multiple log points corresponding to the dispatch process, and the identification information is used to identify the dispatch data. Backtracking analysis is performed on the dispatch data based on the identification information to obtain abnormal data. This abnormal data is used to assist in optimizing the dispatch capabilities corresponding to passenger transport services, achieving automatic and proactive acquisition of dispatch information for autonomous vehicle operations.

[0049] The purpose of handling abnormal data in the single scheduling process is to improve the efficiency of abnormal data acquisition in the autonomous vehicle dispatching and scheduling process, optimize dispatching and scheduling capabilities, and solve the technical problems of existing technologies.

[0050] The reliance on passive reception and manual acquisition methods leads to high costs and low efficiency in acquiring abnormal data during the operation of autonomous vehicles.

[0051] The method for obtaining abnormal data described in the embodiments of this disclosure can be applied, but is not limited to, to specified...

[0052] Application scenarios for dispatching autonomous vehicles within regions (such as cities, airports, logistics warehouses, hospitals, schools, farms, factories, etc.). The following example, using the application scenario of providing passenger transport services via autonomous taxis (Robotaxi) within an urban area, further illustrates the technical solution for obtaining abnormal data disclosed above. The entire Robotaxi dispatch process (i.e., the dispatch process described above) includes the entire process from when a user places an order through the client to when the server completes the dispatch.

[0053] As an optional implementation, step S23 above, obtaining the dispatch data corresponding to dispatch data 0 in the dispatch dispatch process, further includes the following method steps:

[0054] Step S231: Obtain the log records corresponding to the dispatching process, wherein the log records are used to record all dispatching data corresponding to the dispatching process according to the preset log template.

[0055] Step S232: Perform log point processing on the log records to obtain multiple log points;

[0056] Step S233: Obtain dispatch data based on multiple log points.

[0057] 5. All scheduling data corresponding to the above-mentioned order dispatching process constitutes the total number of orders dispatching processes included in this process.

[0058] Log data generated during each dispatching phase. The aforementioned preset log template is a storage template for log data pre-defined according to application scenario requirements. The log template is used to determine the storage content, storage format, and storage relationships of the log data.

[0059] All scheduling data corresponding to the order dispatching process is recorded according to the aforementioned preset log template, resulting in the aforementioned log records. These log records are stored in a designated storage space. The log records corresponding to the aforementioned order dispatching process can be retrieved by accessing the designated storage space.

[0060] After obtaining the above log records, log points are processed according to the log point marking rules to obtain the above multiple log points. These log point marking rules are determined by technical personnel based on application scenario requirements. These rules are used to determine the above multiple log points, which are key data collection points within the above log records.

[0061] The dispatch data is collected based on the aforementioned multiple log points. This dispatch data comprises key dispatch data from all dispatch data corresponding to the above-mentioned dispatch process. In other words, the technical solution disclosed herein allows technicians to customize the log point rules to control multiple log points, thereby determining the collected dispatch data. This technical solution offers high flexibility and controllability in data collection.

[0062] Taking the application scenario of Robotaxi providing passenger transport services within an urban area as an example, the entire Robotaxi dispatch process is divided into multiple dispatch and scheduling stages, namely the central control stage, the calculation stage, the vehicle-order matching stage, and the dispatch stage.

[0063] Specifically, the log data generated during the central control phase of the above-mentioned Robotaxi dispatch process includes: time data corresponding to each dispatch scheduling phase in the above-mentioned multiple dispatch scheduling phases, such as: the start time stamp of the round corresponding to the dispatch scheduling process, the time stamp for pulling order information, the time taken to pull order information, the start time stamp for vehicle-order matching, the time taken for vehicle-order matching, and the time stamp for submitting the calculation task.

[0064] Specifically, the log data generated during the vehicle-order matching stage of the entire Robotaxi dispatch process includes: available vehicle data near the order (i.e., data of available autonomous vehicles near the current location of the client that issued the dispatch request message) and unavailable vehicle data (i.e., data of vehicles that do not meet preset conditions, such as: the seat belt is in the correct working state, the distance between the location of the autonomous vehicle and the current location of the client that issued the dispatch request message is less than a preset threshold, etc.).

[0065] Specifically, the log data generated during the calculation phase of the Robotaxi dispatch process includes: calculation data of relevant operators during vehicle-order matching. These operators include call waiting operators, order queuing operators, and Estimated Time of Arrival (ETA) operators. The calculation data includes the calculation progress and results (usually a score) of these operators.

[0066] Specifically, the log data generated during the dispatching phase of the Robotaxi dispatching process includes: dispatch verification data, such as vehicle order acceptance status verification data, current order status verification data, dispatch completion time verification, dispatch time verification, etc.

[0067] The log data generated by the above multiple dispatching stages (i.e., central control stage, calculation stage, vehicle-order matching stage and dispatching stage) are recorded according to the preset log template to obtain the log records corresponding to the dispatching process.

[0068] Specifically, the log data generated during the aforementioned multiple dispatching stages is typically in JavaScript Object Notation (JSON) format. JSON is a lightweight data exchange format, and JSON-formatted log data is easy to generate and parse. The aforementioned preset log template is a specific data table format pre-designed by technical personnel based on application scenario requirements. When recording log data according to the preset log template, the JSON-formatted log data is parsed into data fields, and then these data fields are stored in the aforementioned specific data table format to obtain the log record.

[0069] The aforementioned log records store all data fields corresponding to the scheduling data. However, when collecting and analyzing data, it is usually unnecessary to obtain all scheduling data; only key data needs to be collected based on the application scenario requirements. Therefore, log point rules are set according to the type or content of the key data to be collected, and log points are processed according to these rules to obtain multiple log points. The log point rules describe the multiple log points of the key data to be collected in the aforementioned log records. Further, dispatch scheduling data (i.e., the aforementioned key data to be collected) is collected based on these multiple log points.

[0070] Specifically, in the application scenario of Robotaxi providing passenger transport services within urban areas, the key data to be collected in the aforementioned dispatching data is typically high-frequency data from the dispatching calculation process, log data analysis process, and anomaly data mining process. For example, the key data to be collected includes, but is not limited to: exploratory data analysis (EDA) data in vehicle-order matching calculation, and call waiting time data.

[0071] As an optional implementation, the identification information includes: a first identifier, a second identifier, and a third identifier. In step S23 above, obtaining the identification information corresponding to the dispatching process further includes the following method steps:

[0072] Step S234: Obtain the current round data, order data, and vehicle data from the dispatch data. The round data is used to describe the round matching status of the dispatch process, the order data is used to describe the order matching status of the dispatch process, and the vehicle data is used to describe the vehicle matching status of the dispatch process.

[0073] Step S235: Determine a first identifier based on round data, a second identifier based on order data, and a third identifier based on vehicle data, wherein the first identifier is the round identifier, the second identifier is the order identifier, and the third identifier is the vehicle identifier.

[0074] Taking the Robotaxi passenger transport service within an urban area as an example, the dispatch data mentioned above includes at least the round data, order data, and vehicle data for the current round. Round data describes the round matching status of the dispatch process in the current round; for example, round data includes: round start timestamp, round matching time, etc. Order data describes the order matching status of the dispatch process; for example, order data includes: order release timestamp, order information retrieval timestamp, order information retrieval time, vehicle-order matching start timestamp, vehicle-order matching time, and task submission timestamp, etc. Vehicle data describes the vehicle matching status of the dispatch process; for example, vehicle data includes: available vehicle data and unavailable vehicle data near the order, etc.

[0075] Based on the current round's data, order data, and vehicle data, a first identifier is determined based on the round data, a second identifier is determined based on the order data, and a third identifier is determined based on the vehicle data. Accordingly, the first identifier is the round identifier corresponding to the order dispatch process. The second identifier is the order identifier corresponding to the order dispatch process. The third identifier is the vehicle identifier corresponding to the order dispatch process.

[0076] It is easy to understand that the first identifier is used to identify the round data in the dispatch data, the second identifier is used to identify the order data in the dispatch data, and the third identifier is used to identify the vehicle data in the dispatch data. By obtaining the first, second, and third identifiers corresponding to the dispatch process and identifying the corresponding dispatch data, it is beneficial to improve the efficiency of data storage, data management, data retrieval, and data analysis related to the dispatch data.

[0077] As an optional implementation, step S24 above, which involves backtracking the dispatch data based on the identification information to obtain abnormal data, also includes the following method steps:

[0078] Step S241: Perform backtracking analysis on the dispatch data based on at least one of the first identifier, the second identifier, and the third identifier to mine abnormal data from the dispatch data.

[0079] In the application scenario, at least one of the first, second, and third identifiers corresponding to the above-mentioned order dispatching process is selected as the identifier to be used, based on the requirements of the application scenario. Backtracking analysis is then performed on the order dispatching data corresponding to the above-mentioned order dispatching process based on the identifier to be used, yielding the backtracking analysis results. Based on the backtracking analysis results, abnormal data is extracted from the above-mentioned order dispatching data.

[0080] Specifically, by performing backtracking analysis on the dispatch data based on any one of the first, second, and third identifiers, corresponding abnormal data can be extracted from the dispatch data.

[0081] For example, application scenario A1 needs to extract abnormal data from the round data generated in the order dispatch process. In this case, backtracking analysis is performed on the order dispatch data based on the first identifier (i.e., the round identifier) ​​to extract "round abnormal data". Application scenario B1 needs to extract abnormal data from the order data generated in the order dispatch process. In this case, backtracking analysis is performed on the order dispatch data based on the second identifier (i.e., the order identifier) ​​to extract "order abnormal data". Application scenario C1 needs to extract abnormal data from the vehicle data generated in the order dispatch process. In this case, backtracking analysis is performed on the order dispatch data based on the third identifier (i.e., the vehicle identifier) ​​to extract "vehicle abnormal data".

[0082] Specifically, by performing a retrospective analysis on the dispatch data based on any two of the first, second, and third identifiers, corresponding abnormal data can be extracted from the dispatch data.

[0083] For example, application scenario A2 needs to mine abnormal matching data between rounds and orders in the order dispatch process (such as abnormal order release within a round). In this case, backtracking analysis is performed on the order dispatch data based on the first identifier (i.e., round identifier) ​​and the second identifier (i.e., order identifier) ​​to mine "round-order abnormal data". Application scenario B2 needs to mine abnormal matching data between rounds and vehicles in the order dispatch process (such as incorrect target vehicle matching within a round). In this case, backtracking analysis is performed on the order dispatch data based on the first identifier (i.e., round identifier) ​​and the third identifier (i.e., vehicle identifier) ​​to mine "round-vehicle abnormal data". Application scenario C2 needs to mine abnormal matching data between orders and vehicles in the order dispatch process (such as abnormal vehicle order acceptance). In this case, backtracking analysis is performed on the order dispatch data based on the second identifier (i.e., order identifier) ​​and the third identifier (i.e., vehicle identifier) ​​to mine "order-vehicle abnormal data".

[0084] Specifically, if more complex anomaly data mining is required on the dispatch data, in the application scenario, backtracking analysis can be performed on the dispatch data based on the first identifier (i.e., round identifier), the second identifier (i.e., order identifier), and the third identifier (i.e., vehicle identifier) ​​to mine the corresponding anomaly data.

[0085] It is readily understood that, through the technical solutions provided in the embodiments of this disclosure, the first identifier, the second identifier, and the third identifier can be flexibly combined based on different abnormal data mining needs in different application scenarios, thereby performing retrospective analysis on dispatch data to obtain target abnormal data that meets the needs of a data mining operation.

[0086] As an optional implementation, step S241 above, which involves performing a backtracking analysis on the dispatch data based on the first identifier to extract abnormal data, also includes the following method steps:

[0087] Step S2411: Perform backtracking analysis on the round data based on the first identifier to determine the time consumption information of the dispatching process;

[0088] Step S2412: Abnormal data is obtained by mining time consumption information to help optimize the dispatching calculation capability corresponding to passenger transport services.

[0089] Taking the application scenario of Robotaxi providing passenger transport services within an urban area as an example, the time consumption information of the dispatching process is determined by backtracking analysis of the round data based on the first identifier (i.e., the round identifier).

[0090] Specifically, round identifiers are used to associate attributes of round data in the order dispatching data. For example, based on the temporal relationship between multiple rounds determined by the round identifier, the round data corresponding to the order dispatching process of multiple rounds are associated, and the time consumption information of the order dispatching process (such as the time consumption of matching multiple rounds) is determined based on the association result. As another example, based on the temporal relationship between the timestamps of multiple rounds in the current round determined by the round identifier, the round data corresponding to multiple round timestamps are associated, and the time consumption information of the order dispatching process (such as the time consumption of matching in the current round) is determined based on the association result.

[0091] Abnormal data is obtained by mining the aforementioned time consumption information. For example, the time consumption information is compared with preset round-specific abnormal conditions, and the round data corresponding to the time consumption information that meets the round-specific abnormal conditions is identified as the abnormal data. This abnormal data is then used as feedback information for the Robotaxi passenger service dispatching process, which is adjusted to optimize the dispatching calculation capabilities for passenger services.

[0092] As an optional implementation, step S241 above, which involves performing backtracking analysis on the dispatch data based on the third identifier to extract abnormal data, also includes the following method steps:

[0093] Step S2413: Perform retrospective analysis on vehicle data based on the third identifier to determine the operational status information of the target vehicle;

[0094] Step S2414: Abnormal data is obtained by mining operational status information to assist in optimizing the vehicle status anomaly adjustment capability corresponding to Passenger Transport 5 service.

[0095] Taking the application scenario of Robotaxi providing passenger transport services within an urban area as an example, the vehicle data is backtracked and analyzed based on the third identifier (i.e., vehicle identifier) ​​to determine the operating status information of the target vehicle (such as accepting orders, stopping accepting orders, order taking time, etc.).

[0096] For example, vehicle identifiers can be used to perform backtracking analysis on vehicle data in dispatch data to determine the individual status of a target vehicle and the interaction status between multiple autonomous vehicles.

[0097] Based on the vehicle status and interaction status, determine the operational status information of the target vehicle.

[0098] Abnormal data is obtained by mining the operational status information of the target vehicles. For example, the operational status information is compared with preset vehicle anomaly conditions, and vehicles that meet the anomaly conditions are identified.

[0099] The vehicle data corresponding to the operational status information is considered as the aforementioned abnormal data. This abnormal data is used as feedback information in the 5Robotaxi passenger dispatching process to improve the dispatching process.

[0100] Adjustments were made to optimize the dispatching and calculation capabilities for passenger transport services.

[0101] As an optional implementation, step S241 above, which involves backtracking the dispatch data based on the second and third identifiers to extract abnormal data, further includes the following method steps: Step S2415, performing backtracking analysis on order data and vehicle data based on the second and third identifiers.

[0102] Traceability analysis to determine vehicle and order matching information;

[0103] Step S2416: Use vehicle and order matching information to mine abnormal data to help optimize the vehicle and order matching capability for passenger transport services.

[0104] Taking the application scenario of Robotaxi providing passenger transport services within an urban area as an example, the order data and vehicle data are processed based on the second identifier (i.e., order identifier) ​​and the third identifier (i.e., vehicle identifier).

[0105] Perform backtracking analysis to determine vehicle and order matching information (such as successful vehicle-order matching, vehicle-order matching timeout, vehicle-order matching error, etc.).

[0106] For example, order identifiers and vehicle identifiers can be used to perform backtracking analysis on order and vehicle data in dispatching data to determine vehicle-order matching information. This backtracking analysis can be a sequential backtracking analysis, that is, linking a first backtracking analysis of order data based on order identifiers with a second backtracking analysis of vehicle data based on vehicle identifiers. This sequential operation means that the first and second backtracking analysis processes are executed sequentially. Its purpose is to first obtain a first backtracking analysis result through the first backtracking analysis process, and then further combine the first backtracking analysis result with the vehicle identifier to perform backtracking analysis on the vehicle data to obtain a second backtracking analysis result, thereby improving the analysis efficiency and effectiveness of the entire backtracking analysis process.

[0107] Abnormal data is identified using the aforementioned vehicle-order matching information. For example, the vehicle-order matching information is compared with preset abnormal vehicle-order matching conditions, and the order data and vehicle data corresponding to vehicle-order matching information that meet these conditions are identified as abnormal data. This abnormal data is then used as feedback information for the Robotaxi passenger service dispatching process, allowing for adjustments to the dispatching process to optimize the dispatching computational capabilities for passenger services.

[0108] The abnormal data obtained by mining vehicle and order matching information can be used to assist in optimizing the order matching strategy during the order dispatching process.

[0109] Based on the above detailed description of the technical solutions of the embodiments of this disclosure, it is easy to understand that, for the log data generated in the dispatching process of autonomous vehicles providing passenger transport services, establishing a standardized, complete data storage format that can be associated with identification information (that is, dispatching data obtained through log point processing and data collection, which is stored in the form of data with corresponding identification information) can make the acquisition and mining of abnormal data in the application scenario more flexible and efficient.

[0110] As an optional implementation, a graphical user interface is provided through the order dispatch service platform. The content displayed by the graphical user interface at least partially includes an order dispatch service scenario. The above-mentioned method for obtaining abnormal data further includes the following steps:

[0111] Step S251: In response to the first touch operation applied to the graphical user interface, determine the data source of the dispatch data;

[0112] Step S252: In response to the second touch operation applied to the graphical user interface, establish a data model, wherein the data model is used to configure the abnormal indicators to be displayed for abnormal data.

[0113] Step S253: Visualize the abnormal data based on the data source and abnormal indicators.

[0114] In the above optional embodiments, the dispatching service platform is a server that provides dispatching services. This dispatching service platform can be located on a separate server, a distributed server cluster, or a cloud server in the cloud. The graphical user interface can be a visual data dashboard. The dispatching service scenario displayed in the graphical user interface can be an application scenario for dispatching autonomous vehicles within a specified area (such as a city, airport, logistics warehouse, hospital, school, farm, factory, etc.), specifically, an application scenario for Robotaxi providing passenger transport services within an urban area.

[0115] The graphical user interface also includes a first control (or a first touch area). When a first touch operation is detected on the first control (or the first touch area), the data source of the dispatch data is determined from the candidate sources. The candidate sources include, but are not limited to, data tables provided by technicians, databases associated with the server, etc.

[0116] The aforementioned graphical user interface also includes a second control (or a second touch area). When a second touch operation is detected on the second control (or the second touch area), a data model is established. This data model is used to configure the abnormal indicators to be displayed for the abnormal data. In other words, the aforementioned data model can identify and analyze the abnormal data corresponding to the dispatch data, and configure the abnormal indicators to be displayed based on the analysis results. Furthermore, data visualization tools are used to visualize the abnormal data based on the data source and abnormal indicators.

[0117] It should be noted that the above data model can be determined by technical personnel based on the needs of the application scenario. In other words, through the data model, it is possible to flexibly and controllably configure the abnormal indicators to be displayed for abnormal data, thereby achieving personalized visualization of abnormal data.

[0118] It should be noted that both the first and second touch operations described above can be performed by a user touching the display screen of the terminal device with their finger and interacting with the device. These touch operations can include single-point touch and multi-point touch, where each touch point can be interacted with by clicking, long-pressing, pressing hard, or swiping. The first and second touch operations can also be implemented using input devices such as a mouse or keyboard.

[0119] Taking the application scenario of Robotaxi providing passenger transport services within an urban area as an example, Figure 3 This is a schematic diagram illustrating a process for acquiring abnormal data according to an embodiment of this disclosure, such as... Figure 3 As shown, in the data acquisition stage: log records generated throughout the Robotaxi dispatch process are processed to obtain multiple key data points (i.e., the aforementioned multiple log points), and then key data corresponding to the dispatch scheduling process (i.e., the aforementioned dispatch scheduling data) are collected based on the multiple key data points; the round identifier, order identifier, and vehicle identifier (i.e., the aforementioned identifier information) corresponding to the Robotaxi dispatch process are obtained.

[0120] Figure 3 The data acquisition phase shown may include several key data points: Robotaxi order recall points, Robotaxi order matching points, and Robotaxi order dispatch points. Corresponding key data may include: filtering data during Robotaxi order recall, operator calculation data (including calculation process and results) during Robotaxi order matching, and order verification data during Robotaxi order dispatch. Furthermore, time consumption data for each stage of the entire Robotaxi order dispatch process can be obtained.

[0121] Still as Figure 3As shown, the acquired data is stored in a table. The data table contains: vehicle order matching data, vehicle order calculation data, dispatching time data, vehicle status data, and virtual order calculation data. Vehicle order matching data and vehicle order calculation data are associated with each other using the round identifier as the primary key (this can be a one-way or two-way association); vehicle order calculation data and dispatching time data are associated with each other using the round identifier as the primary key (this can be a one-way or two-way association); dispatching time data and vehicle status data are associated with each other using the timestamp and vehicle identifier as the primary key (this can be a one-way or two-way association).

[0122] Figure 3 The virtual order calculation data shown is the calculation data of the virtual order calculation module. The virtual order calculation module is used to schedule and adjust the entire Robotaxi dispatch process in the form of dispatch scheduling strategies to meet the specific dispatch scheduling requirements of the application scenario. The calculation process of the virtual order calculation module is relatively independent and does not need to be strongly correlated with other data.

[0123] Still as Figure 3 As shown, the data tables obtained based on the data storage can be used for data analysis, visualization dashboard construction, and anomaly data mining, which helps to optimize the dispatching capabilities of the entire Robotaxi dispatch process.

[0124] It is readily understood that, based on the method steps provided in the above embodiments of this disclosure, the beneficial effects that the technical solution of this disclosure can achieve include:

[0125] Beneficial effect (1): The log data generated by autonomous vehicles in the entire process of providing passenger transport services is standardized and stored persistently, which facilitates the traceability and analysis of historical data in application scenarios;

[0126] Beneficial effect (2): Log tagging and table storage of log data can realize the attribute association between data, improve the efficiency of data retrieval and analysis, and solve the problem that related technologies cannot meet the independent processing and joint analysis needs of log data;

[0127] Beneficial effects (3): The stored log data is standardized, persistent and has attribute associations, which facilitates data visualization. In particular, it can realize the construction of personalized dashboards for log data of dispatching process, and improve the operational efficiency of passenger transport services for autonomous vehicles.

[0128] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the above embodiments of this disclosure.

[0129] According to another embodiment of this disclosure, an apparatus for acquiring abnormal data is also provided. This apparatus is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0130] Figure 4 This is a structural block diagram of an apparatus for acquiring abnormal data according to an embodiment of the present disclosure, such as... Figure 4 As shown, the device 400 for acquiring abnormal data includes: a receiving module 401, used to receive a dispatch request message from a client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services; an initiating module 402, used to respond to the dispatch request message and initiate the dispatch scheduling process for the current round, wherein the dispatch scheduling process is used to match the target vehicle to be used for the dispatch request message; a first acquiring module 403, used to acquire dispatch scheduling data and identification information corresponding to the dispatch scheduling process, wherein the dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data; and a second acquiring module 404, used to perform backtracking analysis on the dispatch scheduling data based on the identification information to acquire abnormal data, wherein the abnormal data is used to assist in optimizing the dispatch scheduling capabilities corresponding to passenger transport services.

[0131] Optionally, the first acquisition module 403 is further configured to: acquire log records corresponding to the dispatching process, wherein the log records are used to record all dispatching data corresponding to the dispatching process according to a preset log template; perform log point processing on the log records to obtain multiple log points; and collect dispatching data based on the multiple log points.

[0132] Optionally, the first acquisition module 403 is further configured to: acquire round data, order data, and vehicle data for the current round from the dispatch data, wherein the round data is used to describe the round matching status of the dispatch process, the order data is used to describe the order matching status of the dispatch process, and the vehicle data is used to describe the vehicle matching status of the dispatch process; determine a first identifier based on the round data, a second identifier based on the order data, and a third identifier based on the vehicle data, wherein the first identifier is a round identifier, the second identifier is an order identifier, and the third identifier is a vehicle identifier.

[0133] Optionally, the second acquisition module 404 is further configured to: perform backtracking analysis on the dispatch data based on at least one of the first identifier, the second identifier, and the third identifier, and mine abnormal data from the dispatch data.

[0134] Optionally, the second acquisition module 404 is further configured to: perform backtracking analysis on the round data based on the first identifier to determine the time consumption information of the dispatching process; and use the time consumption information to mine abnormal data to assist in optimizing the dispatching calculation capability corresponding to the passenger service.

[0135] Optionally, the second acquisition module 404 is further configured to: perform retrospective analysis on vehicle data based on the third identifier to determine the operating status information of the target vehicle; and use the operating status information to mine abnormal data to assist in optimizing the vehicle status abnormality adjustment capability corresponding to passenger transport services.

[0136] Optionally, the second acquisition module 404 is further configured to: perform retrospective analysis on order data and vehicle data based on the second identifier and the third identifier to determine vehicle-order matching information; and use the vehicle-order matching information to mine abnormal data to assist in optimizing the vehicle-order matching capability corresponding to passenger transport services.

[0137] Optionally, Figure 5 This is a structural block diagram of an optional apparatus for acquiring abnormal data according to an embodiment of the present disclosure, such as... Figure 5 As shown, the device 400 for acquiring abnormal data includes, in addition to Figure 4 In addition to all the modules shown, it also includes: a display module 405, which is used to respond to the first touch operation applied to the graphical user interface to determine the data source of the dispatch data; respond to the second touch operation applied to the graphical user interface to establish a data model, wherein the data model is used to configure the abnormal indicators to be displayed for abnormal data; and visualize the abnormal data based on the data source and abnormal indicators.

[0138] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0139] According to another embodiment of this disclosure, an electronic device is also provided, including at least one processor and a memory communicatively connected to the at least one processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps in any of the above method embodiments.

[0140] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0141] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0142] Step S1: Receive a dispatch request message from the client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services;

[0143] Step S2: In response to the dispatch request message, initiate the dispatch scheduling process for the current round, wherein the dispatch scheduling process is used to match the target vehicle to be used for the dispatch request message.

[0144] Step S3: Obtain the dispatch scheduling data and identification information corresponding to the dispatch scheduling process. The dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data.

[0145] Step S4: Perform backtracking analysis on the dispatch data based on the identification information to obtain abnormal data. The abnormal data is used to assist in optimizing the dispatch capabilities corresponding to passenger transport services.

[0146] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0147] According to another embodiment of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause a computer to perform the steps in any of the above method embodiments.

[0148] Optionally, in this embodiment, the aforementioned non-transitory computer-readable storage medium may be configured to store a computer program for causing a computer to perform the following steps:

[0149] Step S1: Receive a dispatch request message from the client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services;

[0150] Step S2: In response to the dispatch request message, initiate the dispatch scheduling process for the current round, wherein the dispatch scheduling process is used to match the target vehicle to be used for the dispatch request message.

[0151] Step S3: Obtain the dispatch scheduling data and identification information corresponding to the dispatch scheduling process. The dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process, and the identification information is used to identify the dispatch scheduling data.

[0152] Step S4: Perform backtracking analysis on the dispatch data based on the identification information to obtain abnormal data. The abnormal data is used to assist in optimizing the dispatch capabilities corresponding to passenger transport services.

[0153] Optionally, in this embodiment, the aforementioned non-transitory computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any suitable combination thereof. More specific examples of readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0154] According to another embodiment of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the above-described method for acquiring abnormal data.

[0155] It should be noted that the program code used to implement the method for obtaining abnormal data disclosed herein can be written in any combination of one or more programming languages. This program code can be provided to the processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0156] In the several embodiments provided in this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0157] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0158] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0159] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0160] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0161] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for obtaining abnormal data, comprising: Receive a dispatch request message from the client, wherein the dispatch request message is used to request the dispatch of an autonomous vehicle to provide passenger transport services; In response to the dispatch request message, initiate the dispatch scheduling process for the current round, wherein the dispatch scheduling process is used to match the dispatch request message with the target vehicle to be used; Obtain the dispatch scheduling data and identification information corresponding to the dispatch scheduling process. The dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process. The identification information is used to identify the dispatch scheduling data. The identification information includes: round identifier, which is determined based on the round data of the current round obtained from the dispatch scheduling data. The round data is used to describe the round matching situation of the dispatch scheduling process. In response to the end of the dispatching process, the dispatching data is backtracked and analyzed based on the identification information to obtain abnormal data. The abnormal data is used to assist in optimizing the dispatching capability corresponding to the passenger service. Specifically, the process of backtracking and analyzing the dispatch data based on the identification information to obtain abnormal data includes: associating the round data corresponding to the multiple rounds determined by the round identifier according to the temporal relationship between the multiple rounds to obtain the association result; determining the time consumption information of the dispatch process based on the association result; and taking the round data corresponding to the time consumption information that meets the round abnormality conditions as the abnormal data to assist in optimizing the dispatch calculation capability corresponding to the passenger service.

2. The method of claim 1, wherein, Obtaining the dispatch data corresponding to the dispatch process includes: Obtain the log records corresponding to the order dispatching process, wherein the log records are used to record all dispatching data corresponding to the order dispatching process according to a preset log template; The log records are processed by logging points to obtain the multiple log points; The dispatch data is obtained based on the collection of the multiple log points.

3. The method of claim 1, wherein, The identification information further includes: a second identification and a third identification, and obtaining the identification information corresponding to the dispatching process includes: The current round's round data, order data, and vehicle data are obtained from the dispatch data, wherein the order data is used to describe the order matching status of the dispatch process, and the vehicle data is used to describe the vehicle matching status of the dispatch process. The round identifier is determined based on the round data, the second identifier is determined based on the order data, and the third identifier is determined based on the vehicle data, wherein the second identifier is the order identifier and the third identifier is the vehicle identifier.

4. The method of claim 3, wherein, The process of backtracking and analyzing the dispatch data based on the identification information to obtain the abnormal data also includes: The dispatch data is backtracked and analyzed based on at least one of the second identifier and the third identifier to extract the abnormal data.

5. The method according to claim 4, wherein, Based on the third identifier, a backtracking analysis is performed on the dispatch data, and the abnormal data mined from the dispatch data includes: Based on the third identifier, the vehicle data is back-analyzed to determine the operational status information of the target vehicle; The abnormal data is obtained by mining the operational status information to help optimize the vehicle status anomaly adjustment capability corresponding to the passenger transport service.

6. The method according to claim 4, wherein, Based on the second identifier and the third identifier, a backtracking analysis is performed on the dispatch data, and the abnormal data mined from the dispatch data includes: Based on the second identifier and the third identifier, a backtracking analysis is performed on the order data and the vehicle data to determine the vehicle and order matching information; The abnormal data is obtained by mining the vehicle and order matching information to help optimize the vehicle and order matching capability corresponding to the passenger transport service.

7. The method according to claim 1, wherein, The method further includes providing a graphical user interface (GUI) through a dispatch service platform, wherein the content displayed by the GUI at least partially includes a dispatch service scenario, and the method also includes: In response to a first touch operation applied to the graphical user interface, the data source of the dispatch data is determined; In response to a second touch operation applied to the graphical user interface, a data model is established, wherein the data model is used to configure the abnormal indicators to be displayed for the abnormal data; The abnormal data is visualized based on the data source and the abnormal indicators.

8. An apparatus for acquiring abnormal data, comprising: The receiving module is used to receive dispatch request messages from the client, wherein the dispatch request message is used to request the dispatch of autonomous vehicles to provide passenger transport services; The initiation module is used to initiate the dispatch scheduling process for the current round in response to the dispatch request message, wherein the dispatch scheduling process is used to match the target vehicle to be used for the dispatch request message. The first acquisition module is used to acquire the dispatch scheduling data and identification information corresponding to the dispatch scheduling process. The dispatch scheduling data is collected based on multiple log points corresponding to the dispatch scheduling process. The identification information is used to identify the dispatch scheduling data. The identification information includes a round identifier, which is determined based on the round data of the current round obtained from the dispatch scheduling data. The round data is used to describe the round matching situation of the dispatch scheduling process. The second acquisition module is used to perform backtracking analysis on the dispatch data based on the identification information in response to the end of the dispatch process, and to acquire abnormal data, wherein the abnormal data is used to assist in optimizing the dispatch capability corresponding to the passenger service. The second acquisition module is further configured to associate the round data corresponding to the multiple rounds based on the temporal relationship between the multiple rounds determined by the round identifier, and obtain an association result; determine the time consumption information of the dispatch scheduling process based on the association result; and take the round data corresponding to the time consumption information that meets the round abnormal conditions as the abnormal data to assist in optimizing the dispatch scheduling calculation capability corresponding to the passenger service.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images