Troubleshooting system, troubleshooting device, and troubleshooting method

Abstract

To convert a variety of types of data into data in a format that is easier to use so that malfunctions can be diagnosed more efficiently using the data.SOLUTION: A malfunction diagnosis system comprises: an edge system that is an electronic system; a malfunction diagnosis device for diagnosing malfunctions of the edge system; and a computer that is an external device. The malfunction diagnosis device is configured to: discriminate between data acquired from the edge system and the computer in accordance with the type thereof; extract data elements included in the data on the basis of prescribed interpretation processing on the data; convert the data elements to a prescribed data code corresponding to an item in a common data format not pertaining to the type of the data; generate intermediate diagnostic data assigning the data code to the corresponding item; and use the intermediate diagnostic data to perform diagnostic analysis of malfunctions in the edge system.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a defect diagnosis system, a defect diagnosis apparatus, and a defect diagnosis method.

Background Art

[0002] In recent years, electronic systems (sometimes referred to as edge systems) such as autonomous vehicles and robots have been used in various places and scenes. Also, it has been found that defects occurring in edge systems are not only caused by failures of the system itself, but are also affected by the situations and environmental conditions in the usage scene. However, since it is difficult to reproduce the situations and environmental conditions of the usage scene, it is very difficult to identify specific defect causes.

[0003] Therefore, in order to identify the defect causes that occurred in the edge system, it is considered necessary to collect various types and various forms of data such as, for example, the internal state of the system, anomaly detection, diagnostic information, data output from sensors, environmental information, user information, etc., and comprehensively analyze and analyze these data.

[0004] On the other hand, when using various types of data, these data have differences in data format and data representation for each data provider such as the manufacturing manufacturer that is the data source. Therefore, there is a problem that it is difficult to efficiently perform statistical processing, machine learning, etc. for identifying defect causes using these collected data as they are.

[0005] Note that Patent Document [Prior art documents] [Patent Documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2020-8918 [Overview of the Initiative] [Problems that the invention aims to solve]

[0007] The technology described in Patent Document 1 involves collecting and analyzing data from various sensors when monitoring the condition of plant equipment, etc. Furthermore, this technology converts the analysis procedures and know-how into a common data format (intermediate format) and stores it in a database. However, this technology relies on manually inputting the data analysis procedures and then converting those procedures into a common format to improve reusability. Therefore, this technology does not consider unifying data in different formats into a common format and using that unified data for fault diagnosis of electronic systems.

[0008] This invention has been made in view of the above problems, and aims to enable more efficient fault diagnosis using various types of data by converting them into a more user-friendly format. [Means for solving the problem]

[0009] The present invention includes several means for solving at least some of the above problems, but an example is as follows. A malfunction diagnosis system according to one aspect of the present invention for solving the above problems is a malfunction diagnosis system comprising an edge system which is an electronic system, a malfunction diagnosis device for diagnosing malfunctions in the edge system, and a computer which is an external device, wherein the malfunction diagnosis device discriminates data acquired from the edge system and the computer according to its type, extracts data elements contained in the data based on a predetermined interpretation process for the data, converts the data elements into predetermined data codes corresponding to items of a common data format regardless of the type of data, generates diagnostic intermediate data by assigning the data codes to the corresponding items, and performs a diagnostic analysis of malfunctions in the edge system using the diagnostic intermediate data. [Effects of the Invention]

[0010] According to the present invention, by converting various types of data into a more user-friendly format, it is possible to perform malfunction diagnosis more efficiently using that data.

[0011] Other issues, configurations, and effects will be clarified in the following description of the embodiments. [Brief explanation of the drawing]

[0012] [Figure 1] This figure shows an example of the schematic configuration of a malfunction diagnosis system according to the first embodiment. [Figure 2] This figure shows an example of a format (data type) for diagnostic intermediate data. [Figure 3] This diagram shows an example of a definition corresponding to the code for each item in the format. [Figure 4] This diagram shows the definitions regarding data details and data classification code conversion when the data type (TYP) is VID (Vehicle Internal Data). [Figure 5]This diagram shows the definitions regarding data details and data classification code conversion when the data type (TYP) is VPD (Probe Data). [Figure 6] This diagram shows the definitions regarding data details and data classification code conversion when the data type (TYP) is EVD (Environmental Data). [Figure 7] This diagram schematically shows sorted and merged diagnostic intermediate data. [Figure 8] This diagram shows an example of a troubleshooting process. [Figure 9] This figure shows an example of a schematic configuration of a malfunction diagnosis system according to the second embodiment. [Figure 10] This diagram shows an example of the degree of impact. [Figure 11] This diagram shows an example of the hardware configuration of a fault diagnosis device. [Modes for carrying out the invention]

[0013] Embodiments of the present invention will be described below with reference to the drawings. Note that these embodiments are illustrative examples for explaining the present invention, and have been omitted and simplified as appropriate for clarity of explanation. The present invention can also be implemented in various other forms. Unless otherwise specified, each component may be singular or plural.

[0014] Furthermore, the position, size, shape, and range of each component shown in the drawings may not represent the actual position, size, shape, and range in order to facilitate understanding of the invention. For this reason, the present invention is not necessarily limited to the position, size, shape, and range disclosed in the drawings.

[0015] In addition, as examples of various types of information, expressions such as "table" may be used for explanation, but the various types of information may be represented by other data structures. For example, the various types of information such as "**table" may be "**information". Also, when explaining identification information, expressions such as "identification information", "identifier", "name", "ID", "number", etc. are used, but these can be mutually substituted.

[0016] In addition, when there are a plurality of components having the same or similar functions, they may be described with the same reference numeral and different subscripts. Also, when it is not necessary to distinguish these plurality of components, the subscripts may be omitted in the description.

[0017] In addition, in the embodiments, there may be cases where the processes performed by executing a program are described. Here, the computer executes the program by a processor (for example, CPU, GPU), and performs the processes defined by the program while using storage resources (for example, memory) and interface devices (for example, communication ports), etc. Therefore, the subject of the processes performed by executing the program may be the processor. Similarly, the subject of the processes performed by executing the program may be a controller, a device, a system, a computer, or a node having a processor. The subject of the processes performed by executing the program may be an arithmetic unit, and may include a dedicated circuit for performing a specific process. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a CPLD (Complex Programmable Logic Device), etc.

[0018] Furthermore, the program may be installed on the computer from the program source. The program source may be, for example, a program distribution server or a storage medium readable by the computer. If the program source is a program distribution server, the program distribution server includes a processor and storage resources for storing the program to be distributed, and the processor of the program distribution server may distribute the program to other computers. Also, in the embodiment, two or more programs may be implemented as one program, or one program may be implemented as two or more programs.

[0019] <First Embodiment> Figure 1 shows an example of the schematic configuration of the fault diagnosis system 1000 according to this embodiment. As shown in the figure, the fault diagnosis system 1000 includes a fault diagnosis device 100, a manufacturer server 200, an environmental data provision server 210, an SNS (Social Networking Service) server 220, an edge system 230, and a connected service data output device 240 (hereinafter, these devices may be referred to individually or collectively as "external devices"). Furthermore, each of these devices is connected to communicate with each other via a predetermined network N, such as a public network like the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network).

[0020] The following explanation will take as an example the case in which the edge system 230 of this embodiment is mounted on a mobile object (for example, an automobile) and is a system that electronically controls the drive of the mobile object.

[0021] The malfunction diagnosis device 100 is a computer that converts various types and formats of data acquired from external devices into a unified data format and uses the converted data to diagnose malfunctions and failures in the edge system 230. Specifically, the malfunction diagnosis device 100 acquires (collects) various types of data from the manufacturer server 200, the environmental data provision server 210, the SNS server 220, the edge system 230, and the connected service data output device 240. Furthermore, the malfunction diagnosis device 100 converts this data into a unified data format according to a predetermined format, thereby converting data of different types and formats into a single format and generating diagnostic intermediate data in a unified data format.

[0022] Furthermore, the malfunction diagnosis device 100 rearranges each data point in time series based on the time element contained in the diagnostic intermediate data, and merges these data points to generate a dataset that is easy to use for malfunction diagnosis and analysis, as well as for machine learning of information models used in diagnosis.

[0023] Furthermore, the malfunction diagnosis device 100 uses sorted and merged diagnostic intermediate data to perform diagnostic analysis to identify the cause of the malfunction in the edge system 230.

[0024] The manufacturer server 200 is a computer used by a manufacturer or dealer of an automobile equipped with the edge system 230, and provides various data to the malfunction diagnosis device 100. For example, the manufacturer server 200 provides the malfunction diagnosis device 100 with user data, which includes product data such as product model number and product configuration (e.g., components of the ECU), and customer interview data regarding malfunctions.

[0025] The environmental data provision server 210 is a computer used by a company that provides environmental data related to weather, such as temperature and weather conditions, and provides various data to the malfunction diagnosis device 100. For example, the environmental data provision server 210 provides the malfunction diagnosis device 100 with environmental data including weather conditions such as weather, temperature and humidity, and road surface conditions such as freezing and unevenness.

[0026] The SNS server 220 is a computer used by a company that provides social networking services, and it provides various data to the malfunction diagnosis device 100. For example, the SNS server 220 provides the malfunction diagnosis device 100 with user comment data, including user comments or dealer comments, regarding mobile devices (automobiles) equipped with the edge system 230.

[0027] The edge system 230 is a system that provides internal data of a moving object to the fault diagnosis device 100. Specifically, the edge system 230 provides vehicle internal data and probe data to the fault diagnosis device 100. More specifically, the edge system 230 provides vehicle internal data, including fault diagnosis data and register information, and probe data, including temperature, vibration, and driving history, to the fault diagnosis device 100.

[0028] The connected service data output device 240 is a computer that provides various types of connected services and provides connected service data to the malfunction diagnosis device 100. Specifically, this device is a computer that communicates with and manages data from infrastructure equipment such as a management device for managing smartphones or electric vehicle charging stations.

[0029] For example, when a car and a smartphone are linked for tasks such as opening and closing the car doors, the connected service data output device 240 receives a request from the smartphone, generates a door opening and closing control instruction for the target car, and transmits it. Fault information (e.g., communication logs) in the communication path from the smartphone to the car is acquired by the connected service data output device 240. The connected service data output device 240 also provides the acquired fault information to the fault diagnosis device 100. Furthermore, if the connected service data output device 240 is a charging station management device, it provides log data collected via the charging station to the fault diagnosis device 100.

[0030] These external devices may be included singly or in multiples, or multiple external devices of a specific type may be included. Furthermore, the fault diagnosis system 1000 does not need to have all of these external devices; for example, it may consist of an edge system 230, a fault diagnosis device 100, and an environmental data provision server 210. In other words, the edge system 230 and the fault diagnosis device 100 are essential components of the fault diagnosis system 1000, and there are no particular limitations on the combination of other external devices included in the system.

[0031] The above describes the general configuration of the malfunction diagnosis system 1000.

[0032] The data provider devices that supply various types of data to the malfunction diagnosis device 100 are not limited to the examples above, and any data provider devices (computers) that are considered useful for malfunction diagnosis of the target edge system 230 may be included.

[0033] Next, we will describe an example of the general configuration of the malfunction diagnosis device 100.

[0034] As shown in Figure 1, the malfunction diagnosis device 100 includes a processing unit 110, a storage unit 120, an input unit 130, an output unit 140, and a communication unit 150.

[0035] The processing unit 110 is a functional unit that performs various processing tasks performed by the malfunction diagnosis device 100. Specifically, the processing unit 110 includes a data type classification unit 111, a data element extraction unit 112, a diagnostic intermediate data generation unit 113, a sort merge unit 114, a diagnostic analysis unit 115, and a diagnostic result output unit 116.

[0036] The data type classification unit 111 is a functional unit that classifies various types of data acquired from external devices. Specifically, the data type classification unit 111 distinguishes the type of data based on the source address of the acquired data and IDs assigned to the data (for example, the sender's identification ID, the external device's identification ID, or an ID representing the data type that is assigned to the data in general communication).

[0037] More specifically, the data type classification unit 111 distinguishes, based on the ID, whether the data is user data obtained from the manufacturer server 200, environmental data obtained from the environmental data provision server 210, user comment data obtained from the SNS server 220, vehicle internal data or probe data obtained from the edge system 230, or data obtained from the connected service data output device 240.

[0038] Furthermore, the data type classification unit 111 outputs the classified data, along with information identifying its type, to the data element extraction unit 112.

[0039] The data element extraction unit 112 is a functional unit that extracts data elements from each discriminated data. Specifically, the data element extraction unit 112 identifies data structures corresponding to different data formats depending on the data type and data provider, as well as lexical and terminology rules, based on the rule information stored in the individual analysis rule DB 121. The data element extraction unit 112 also performs data interpretation processing (e.g., syntactic analysis, natural language analysis, etc.) according to the rule information. As a result, the data element extraction unit 112 extracts predetermined data elements (e.g., data details, data classification, data acquisition time or event occurrence time, event duration or period, event occurrence location, state data, etc.) for each data type according to the data provider from the data acquired from the external device.

[0040] Furthermore, parser generators such as YACC (Yet Another Compiler Compiler) may be used for interpretation processes such as syntactic analysis and natural language processing.

[0041] The diagnostic intermediate data generation unit 113 is a functional unit that converts data of different types and formats into a single format and generates diagnostic intermediate data in a unified data format. Specifically, the diagnostic intermediate data generation unit 113 converts data types and extracted data elements into data codes (hereinafter sometimes referred to as "codes") according to predetermined format rules. The diagnostic intermediate data generation unit 113 also assigns the converted codes to the corresponding data fields (hereinafter sometimes referred to as "items") in the format. However, the diagnostic intermediate data generation unit 113 assigns the event occurrence time and actual data values ​​to the corresponding items without coding them.

[0042] In this way, the diagnostic intermediate data generation unit 113 converts the extracted data elements into predetermined data codes corresponding to items in a common data format regardless of the data type, and generates diagnostic intermediate data by assigning these codes to the corresponding items.

[0043] Figure 2 shows an example of the format (data format) of diagnostic intermediate data. As shown in the figure, the format of the diagnostic intermediate data has predetermined items to which converted codes and actual data values ​​are assigned. Specifically, the format has multiple items: TYP, DCD, IED, OTM, EOD, DCT, LOC, and STD. In addition, the data collected from the edge system 230 may have a separate identification code for the edge system 230 (for example, in the case of an automobile, the vehicle identification number VIN: Vehicle Identification Number) attached to it. This identification code can be used to identify which automobile the data was obtained from. Therefore, although this identification code is not an essential element of the diagnostic intermediate data, it may be attached to the diagnostic intermediate data as appropriate.

[0044] Figure 3 shows an example of the definitions corresponding to the codes for each item in the format. As shown in the figure, TYP is defined as an item to which a code indicating the type of data is assigned.

[0045] DCD is defined as an item to which a code indicating data details is assigned. Data details will be described later.

[0046] IED is defined as an item to which a value indicating the degree of impact on the system based on the data content is assigned. The degree of impact will be explained in detail in the second embodiment described later.

[0047] OTM is defined as an item to which data acquisition time or event occurrence time is assigned.

[0048] EOD is defined as an item to which a code is assigned that converts the duration of an event or the frequency of its occurrence.

[0049] DCT is defined as an item to which a data classification code is assigned. Details of data classification will be described later. Note that DCT is used as an element when interpreting the contents of STD, to which the actual values ​​of state data are assigned.

[0050] LOC is defined as an item to which a code is assigned that indicates the affected part where the malfunction is occurring (for example, the part where the issue occurred, such as the processor or memory, or the part where data is acquired).

[0051] STD is defined as an item to which the actual value of the state data is assigned.

[0052] In this embodiment, which describes the case where the edge system 230 is installed in a vehicle, TYP is assigned codes indicating data types such as VID, VPD, UID, EVD, SNS, and CSD. Here, VID is a code indicating vehicle internal data. VPD is a code indicating probe data. UID is a code indicating user data. EVD is a code indicating environmental data. SNS is a code indicating user comment data. CSD is a code indicating connected service data.

[0053] Figure 4 shows the definitions for data details and data classification code conversion when the data type (TYP) is VID (Vehicle Internal Data). The diagnostic intermediate data generation unit 113 codes the contents of the extracted data elements according to these definitions and assigns them to the corresponding items in the data format.

[0054] For example, if the diagnostic intermediate data generation unit 113 finds that the information contained in the extracted data elements, specifically the information indicating a power supply abnormality, it converts this information into a code called PWF and assigns it to the DCD item in the format.

[0055] Furthermore, power supply anomalies included in the electronic fault diagnosis information correspond to register information obtained from registers. Therefore, the diagnostic intermediate data generation unit 113 identifies record 301 of the electronic fault diagnosis information table 300, where register information is associated with the state data. The diagnostic intermediate data generation unit 113 also converts the fault diagnosis information corresponding to the data classification of the identified record into a code = FDID defined in the mnemonic of that record, and assigns it to the DCT item in the format.

[0056] Furthermore, the diagnostic intermediate data generation unit 113 identifies state data, which is register information, from the extracted data elements and assigns the actual value of the state data to STD in the format. Note that the state data may also be converted into the trouble code itself indicated by the corresponding DCT (fault diagnosis information in this example), or into a data code that represents the state or functional defect that the trouble code signifies, and then assigned to STD.

[0057] Furthermore, if, for example, the DCT mnemonic corresponding to the extracted data element is FFLD, the diagnostic intermediate data generation unit 113 assigns the extracted data itself, or the storage address link of the extracted data, to the STD format. This makes it possible, for example, to read the data or change the processing procedure during the diagnostic analysis process.

[0058] In this way, the diagnostic intermediate data generation unit 113 assigns the codes or actual values ​​of the extracted data elements to the corresponding items (DCD, DCT, and STD) in the format.

[0059] Furthermore, if the DCT identified by the extracted data element is the IRID in the recording information table 310, it indicates that the data element is from the unit (CDR or EDR) that acquired the log at the time of the accident. In diagnostic analysis using this diagnostic intermediate data, it is determined, based on this information, that accident analysis processing different from normal operation is required.

[0060] Furthermore, if the DCT identified by the extracted data element is the AVRD in the recorded information table 310, it indicates that the data element is state information (DSSA information) during autonomous driving. It also indicates that the diagnostic intermediate data assigned to the DCT as AVRD is available for use in diagnostic analysis processing during both normal operation and accidents.

[0061] Furthermore, if the DCT identified by the extracted data element is VIND or VSID in the configuration information table 320, it indicates that the data element is data relating to a vehicle-specific identification ID code or configuration information. Diagnostic intermediate data to which such a DCT is assigned is used as an identifier (ID) when performing diagnostic analysis processing specific to the target vehicle.

[0062] Thus, the data codes assigned to the items of the diagnostic intermediate data serve as control information used by the diagnostic analysis unit 115 (described later) to determine the processing content and order, and to control the processing when it performs a diagnostic analysis of a malfunction.

[0063] Let's return to Figure 2 for explanation. The diagnostic intermediate data generation unit 113 identifies the data acquisition time or event occurrence time from the data elements and assigns this to the OTM format.

[0064] Furthermore, the diagnostic intermediate data generation unit 113 identifies the duration of an event, such as an anomaly, and the event occurrence period from the data elements, and assigns these to the EOD format. Note that the event duration is not coded, and the actual value is assigned to the EOD as is. For the period, a code obtained by converting a predetermined category (time attribute) according to the length of the period is assigned to the EOD. Specifically, short periods (seconds to minutes) are designated as Category 1, medium periods (minutes to hours) as Category 2, long periods (hours or more) as Category 3, and discrete (point process data) as Category 4, and codes obtained by converting these categories are assigned to the EOD.

[0065] The coded period in this way is used in the diagnostic analysis processing by the diagnostic analysis unit 115, for example, when executing a time series analysis algorithm, to interpolate the period between various data.

[0066] Furthermore, the diagnostic intermediate data generation unit 113 identifies the target part where the malfunction is occurring (for example, the event occurrence part or data acquisition part such as the processor or memory) from the data elements. The diagnostic intermediate data generation unit 113 also converts the identified target part into a corresponding code and assigns it to the LOC of the format.

[0067] Thus, the diagnostic intermediate data generated based on the data elements of the vehicle's internal data is assigned a data code that indicates the state of the vehicle, which is a moving object.

[0068] Figure 5 shows the definitions regarding the code conversion of data details and data classification when the data type (TYP) is VPD (probe data). The diagnostic intermediate data generation unit 113 codes the contents of the extracted data elements according to these definitions and assigns them to the corresponding items in the data format.

[0069] For example, if the information contained in the extracted data elements that indicates data details represents the driving history, the diagnostic intermediate data generation unit 113 converts that information into a code called DRL and assigns it to the DCD item in the format.

[0070] In this case, the diagnostic intermediate data generation unit 113 identifies record 331 of the driving information table 330, in which the driving history is associated with the status data. The diagnostic intermediate data generation unit 113 also converts the driving information corresponding to the data classification of the identified record into the code = DRID defined in the mnemonic of that record, and assigns it to the DCT item of the format.

[0071] Furthermore, the diagnostic intermediate data generation unit 113 identifies the state data of the driving history from the extracted data elements and assigns the actual value of the state data to the STD format.

[0072] Since probe data is acquired periodically, STD stores the actual value of each acquired data point. STD may also be assigned an address link to the storage location of continuous data acquired over a certain period. The period in question is assigned to the EOD field in the format.

[0073] Furthermore, although a detailed explanation will be omitted to avoid repetition, the recorded information and corresponding video information are processed in the same manner. As a result, diagnostic intermediate data corresponding to the data elements of the probe data is generated.

[0074] In this way, the diagnostic intermediate data generated based on the data elements of the probe data is assigned a data code that indicates the driving status of the vehicle, which is a moving object.

[0075] Figure 6 shows the definitions for data details and data classification code conversion when the data type (TYP) is EVD (Environmental Data). The diagnostic intermediate data generation unit 113 codes the contents of the extracted data elements according to these definitions and assigns them to the corresponding items in the data format.

[0076] For example, if the diagnostic intermediate data generation unit 113 contains information that indicates data details and is related to weather, it converts that information into an ECD code and assigns it to the DCD item in the format.

[0077] In this case, the diagnostic intermediate data generation unit 113 identifies record 341 of the weather information table 340, in which temperature and humidity indicating weather conditions are associated with state data. The diagnostic intermediate data generation unit 113 also converts the temperature and humidity corresponding to the data classification of the identified record into the code =ETHD defined in the mnemonic of that record, and assigns it to the DCT item in the format.

[0078] Furthermore, the diagnostic intermediate data generation unit 113 identifies temperature and humidity state data from the extracted data elements and assigns the actual values ​​of the state data to the STD format.

[0079] Furthermore, although a detailed explanation will be omitted to avoid repetition, road surface information and map information, such as road surface freezing conditions and map location information, are processed in the same manner. As a result, diagnostic intermediate data showing environmental data elements is generated.

[0080] Thus, the diagnostic intermediate data generated based on the data elements of the environmental data is assigned a data code that indicates the environmental conditions around the vehicle, which is a moving object.

[0081] Furthermore, the diagnostic intermediate data generation unit 113 generates diagnostic intermediate data relating to user data, user comment data, and connected service data in the same manner as described above.

[0082] Specifically, the data element extraction unit 112 extracts data elements from product data included in user data. The diagnostic intermediate data generation unit 113 then converts the extracted data elements into predetermined data codes indicating the state of the components using the same method as described above, and assigns them to the corresponding items in the diagnostic intermediate data. In this way, the diagnostic intermediate data generated based on the data elements of the product data is assigned data codes indicating the state of the components of the mobile body.

[0083] Furthermore, the data element extraction unit 112 performs interpretation processing, such as natural language analysis, on natural language descriptions that are frequently found in the defect hearing data included in the user data, and in the user comments and dealer comments included in the user comment data. In addition, through this interpretation processing, the data element extraction unit 112 identifies data details, data classifications, and state data corresponding to the content of the hearing data and user comments that indicate the state evaluation of the mobile body equipped with the edge system 230.

[0084] More specifically, the data element extraction unit 112 uses natural language processing to extract natural language data elements representing the status evaluation of the target vehicle and malfunction status from user data and user comment data. The diagnostic intermediate data generation unit 113 identifies the correspondence between the extracted data elements and DCD, DTC, and STD based on the rule information stored in the individual analysis rule DB 121. The diagnostic intermediate data generation unit 113 then converts the identified DCD and DTC into codes and assigns them to the corresponding items in the format to generate diagnostic intermediate data. As for the actual value of the status data, STD can be assigned, for example, the content of the interview or the user comment itself.

[0085] In this way, the diagnostic intermediate data generated based on data elements such as defect hearing data included in user data and user comments included in user comment data is assigned a data code that indicates the state evaluation of the mobile object.

[0086] Furthermore, if the acquired data is connected data, the data element extraction unit 112 interprets the communication logs between the vehicle and the smartphone (or infrastructure equipment such as a charging station) contained in the data based on syntactic analysis and extracts data elements indicating a malfunction. The diagnostic intermediate data generation unit 113 then codes the extracted data elements in the same manner as described above and generates diagnostic intermediate data by assigning these to the corresponding items in the format.

[0087] Thus, the diagnostic intermediate data generated based on the data elements of connected data is assigned a data code indicating a malfunction in the coordination between the mobile edge system 230, the connected service data output device 240, and the various devices used for connected services.

[0088] The sort-merge unit 114 is a functional unit that rearranges each data point in time series according to the time element (OTM) included in the diagnostic intermediate data. Furthermore, by merging this data, the sort-merge unit 114 generates a dataset that is easy to use for defect diagnosis analysis and machine learning of information models used in defect diagnosis.

[0089] Figure 7 schematically shows sorted and merged diagnostic intermediate data. As shown in the figure, various data acquired from external devices, such as vehicle internal data, probe data, and environmental data, are processed by the data element extraction unit 112, and data elements are extracted through syntactic analysis and natural language processing. Based on the extracted data elements, diagnostic intermediate data is generated in which time information such as event occurrence time and time attributes related to the period are assigned to OTM and EOD.

[0090] Furthermore, the sort-merge unit 114 processes these diagnostic intermediate data to rearrange them in chronological order according to the time information of the data. In the illustrated example, the sort-merge unit 114 rearranges the vehicle internal data A, probe data a and b, and environmental data 1 and 2 so that they are in the order of probe data a, environmental data 1, vehicle internal data A, probe b, and environmental data 2, respectively.

[0091] Furthermore, the sort-merge unit 114 generates a dataset by combining the sorted diagnostic intermediate data into one or more sets.

[0092] Furthermore, the merge sort unit may rearrange diagnostic intermediate data that has been assigned a long-period category so that it appears multiple times within a single dataset as data with a shorter period (e.g., short-period) than the long-period data. Such rearrangement makes it easier to link short-period diagnostic intermediate data (e.g., vehicle internal data) with long-period diagnostic intermediate data (e.g., environmental data) that indicates the environment of the edge system 230 at each timing, for example, in diagnostic analysis processing using short-period diagnostic intermediate data (e.g., vehicle internal data).

[0093] The diagnostic analysis unit 115 is a functional unit that diagnoses and analyzes malfunctions in the edge system 230. Specifically, the diagnostic analysis unit 115 uses a dataset of diagnostic intermediate data to perform diagnostic analysis processing for malfunctions in the edge system 230. More specifically, the diagnostic analysis unit 115 determines the processing content and processing order of the diagnostic analysis based on the data codes and actual values ​​assigned to each item of the diagnostic intermediate data (for example, DCD, DCT, and STD mentioned above), and performs the diagnostic analysis processing for malfunctions in the edge system 230 accordingly.

[0094] The diagnostic result output unit 116 is a functional unit that outputs diagnostic results. Specifically, the diagnostic result output unit 116 outputs the diagnostic results to an output device provided by the malfunction diagnosis device 100, such as a display or printer.

[0095] Next, the memory unit will be described. The memory unit 120 is a functional unit that stores various information used in the processing performed by the malfunction diagnosis device 100. The memory unit 120 also stores information generated by the malfunction diagnosis device 100. Specifically, the memory unit 120 has an individual analysis rule DB 121 and a diagnostic intermediate data storage DB 122.

[0096] The Individual Analysis Rule DB121 is a database that stores rule information used for analyzing various types of data acquired from external devices. Specifically, the Individual Analysis Rule DB121 stores rule information including individual data structures and lexical / terminological rules for analyzing data in different formats (syntactic analysis or natural language analysis) depending on the data type and data source.

[0097] The diagnostic intermediate data storage DB122 is a functional unit that stores the generated diagnostic intermediate data. Specifically, the diagnostic intermediate data storage DB122 stores multiple diagnostic intermediate data generated by the diagnostic intermediate data generation unit 113.

[0098] Next, the input unit 130, output unit 140, and communication unit 150 will be described. The input unit 130 is a functional unit that receives various instructions and information from the operator of the malfunction diagnosis device 100.

[0099] Furthermore, the output unit 140 is a functional unit that outputs information generated by the malfunction diagnosis device 100. For example, the output unit 140 outputs (transmits) the generated diagnostic analysis results to a predetermined device via the communication unit 150.

[0100] Furthermore, the communication unit 150 is a functional unit that communicates information with external devices. Specifically, the communication unit 150 acquires user data, environmental data, vehicle internal data, probe data, user comment data, and connected service data from external devices. The communication unit 150 also transmits information such as generated diagnostic analysis results to a predetermined external device based on instructions from the output unit 140.

[0101] The above describes an example of the functional configuration of the malfunction diagnosis device 100.

[0102] [Explanation of operation] Next, we will describe the fault diagnosis process performed by the fault diagnosis device 100.

[0103] Figure 8 shows an example of a fault diagnosis process. This process is started, for example, when the input unit 130 receives an execution instruction from the operator of the fault diagnosis device 100. Alternatively, this process may be started, for example, when the fault diagnosis device 100 is started up.

[0104] Once processing begins, the communication unit 150 receives various data from external devices (step S10). Specifically, the communication unit 150 receives user data, environmental data, user comment data, vehicle internal data, probe data, and connected service data from the manufacturer server 200, the environmental data provision server 210, the SNS server 220, the edge system 230, and the connected service data output device 240, respectively.

[0105] Next, the data type classification unit 111 discriminates the type of acquired data (step S20). Specifically, the data type classification unit 111 discriminates the type of each data based on the ID assigned to each data. The data type classification unit 111 also outputs the discriminated data, along with information identifying its type, to the data element extraction unit 112.

[0106] Next, the data element extraction unit 112 extracts data elements from each discriminated data (step S30). Specifically, based on the rule information stored in the individual analysis rule DB 121, the data element extraction unit 112 identifies data structures and lexical / terminology rules that correspond to different data formats depending on the data type and data provider, and performs data interpretation processing according to the rule information.

[0107] As a result, the data element extraction unit 112 extracts data elements from the data acquired from the external device, according to the data provider for each data type.

[0108] Next, the diagnostic intermediate data generation unit 113 generates diagnostic intermediate data (step S40). Specifically, as described above, the diagnostic intermediate data generation unit 113 converts the extracted data elements into predetermined data codes corresponding to items in a common data format regardless of data type, and generates diagnostic intermediate data by assigning these codes to the corresponding items.

[0109] More specifically, the diagnostic intermediate data generation unit 113 generates diagnostic intermediate data by converting the data types and extracted data elements into data codes according to predetermined format rules and assigning them to the corresponding items in the format. The diagnostic intermediate data generation unit 113 also stores the generated diagnostic intermediate data in the diagnostic intermediate data storage DB 122 (step S50).

[0110] Next, the sort-merge unit 114 rearranges and merges the diagnostic intermediate data (step S60). Specifically, the sort-merge unit 114 rearranges the order of each data based on the time information assigned to the diagnostic intermediate data and merges them to generate one or more datasets.

[0111] Next, the diagnostic analysis unit 115 performs diagnostic analysis using the generated dataset of diagnostic intermediate data (step S70). Specifically, the diagnostic analysis unit 115 performs diagnostic analysis on the data elements contained in various types of data using the diagnostic intermediate data, whose data format is unified into the same format.

[0112] Furthermore, the diagnostic analysis method is not particularly limited; any known diagnostic analysis technique can be applied as long as the diagnosis uses diagnostic intermediate data in which data elements are coded according to a predetermined definition.

[0113] Furthermore, for diagnostic analysis, an information model may be used that takes intermediate diagnostic data as input and outputs the diagnostic results. In this case, an information model for defect diagnosis generated by machine learning on a mathematical model such as a neural network may be used.

[0114] Next, the diagnostic result output unit 116 outputs the diagnostic results from the diagnostic analysis unit 115 (step S80). Specifically, the diagnostic result output unit 116 outputs information indicating the diagnostic results to an output device such as a display provided by the malfunction diagnosis device 100.

[0115] Furthermore, the diagnostic result output unit 116 terminates the processing of this flow after outputting the diagnostic results.

[0116] The malfunction diagnosis system 1000 according to this embodiment has been described above.

[0117] Such a fault diagnosis system allows for more efficient fault diagnosis by converting various types of data into a more user-friendly format.

[0118] In particular, the fault diagnosis device can convert data in different formats depending on the data provider into a unified data format by replacing it with a predetermined code, and then use the converted data to perform fault diagnosis analysis. Therefore, the fault diagnosis device can absorb the differences in data providers and improve the processing efficiency and speed of the diagnostic process.

[0119] Furthermore, the malfunction diagnosis device 100 can perform malfunction diagnosis analysis using data of various types and fields with standardized data formats, thereby improving the accuracy of the analysis.

[0120] Furthermore, by using data with a standardized data format for defect diagnosis analysis, it becomes easier to generate the information model for performing said analysis.

[0121] <Second Embodiment> The malfunction diagnosis system 1000 according to the second embodiment of the present invention calculates the degree of influence of factors that may indirectly affect the function of vehicle equipment, such as weather conditions and vibrations during driving, on malfunctions, and improves the accuracy of the diagnostic analysis by including this influence information in the diagnostic intermediate data.

[0122] Figure 9 is a diagram showing an example of the schematic configuration of the malfunction diagnosis system 1000 according to this embodiment. As shown in the figure, the malfunction diagnosis device 100 further includes an information model generation unit 117, an impact calculation unit 118, an impact calculation model 123, and a diagnostic analysis result history DB 124, in addition to the functional units of the malfunction diagnosis device 100 in the first embodiment. Note that the other configurations of the malfunction diagnosis system 1000 are the same as in the first embodiment, so the following explanation will focus on the configurations that differ from the first embodiment.

[0123] The information model generation unit 117 is a functional unit that generates an impact calculation model 123, which is an information model for calculating the impact of a defect. Specifically, the information model generation unit 117 generates the impact calculation model 123 by performing machine learning on a mathematical model such as a neural network, using, for example, past diagnostic intermediate data stored in the diagnostic intermediate data storage unit DB 122 as an initial model.

[0124] In this way, by using diagnostic intermediate data in machine learning, the information model generation unit 117 can perform machine learning without considering differences in data type or data format depending on the data provider, thereby speeding up the information model generation process.

[0125] Furthermore, the type of information model is not limited to neural networks; for example, it may be defined by a causal relationship graph. Also, the data used in machine learning is not limited to diagnostic intermediate data; it may also include environmental data or probe data acquired from external devices.

[0126] Furthermore, the information model generation unit 117 updates the impact calculation model 123 by obtaining diagnostic analysis results corresponding to the diagnostic intermediate data used for machine learning from the diagnostic analysis result history DB 124 and using this as feedback data for machine learning. Specifically, the information model generation unit 117 obtains diagnostic analysis results corresponding to the diagnostic intermediate data used when generating the initial model from the diagnostic analysis result history DB 124. The information model generation unit 117 also updates the impact calculation model 123 by performing machine learning using the obtained diagnostic analysis results at predetermined timings (for example, when a predetermined number of diagnostic analysis results have been accumulated, or periodically such as weekly or monthly). One example of a method for updating is covariance structure analysis.

[0127] In this way, the information model generation unit 117 updates the impact calculation model 123, which shows the causal relationship with the defect, by using the diagnostic analysis results as feedback data. Furthermore, updating the impact calculation model 123 in this way can improve the accuracy of impact calculation.

[0128] The impact calculation model 123 is an information model that calculates the degree of impact, which indicates the degree of causal relationship between the operating environment and driving conditions of the edge system 230 and malfunctions (failures) of components within the equipment. Specifically, when data elements extracted from information not directly related to the function of the equipment in the edge system 230, such as environmental data and probe data, are input to the impact calculation model 123 outputs the degree of impact that the operating environment and driving conditions indicated by the data elements have on the malfunctions (or failures) of the components.

[0129] The Diagnostic Analysis Result History DB124 is a database that stores the results of diagnostic analysis using diagnostic intermediate data. The Diagnostic Analysis Result History DB124 contains multiple records of the results of past diagnostic analysis processes using diagnostic intermediate data.

[0130] The impact calculation unit 118 is a functional unit that calculates the impact of a malfunction in the edge system 230 using the impact calculation model 123. Specifically, the impact calculation unit 118 obtains data elements extracted from information not directly related to the function of the equipment in the edge system 230, such as environmental data and probe data, from the data element extraction unit 112, and inputs this into the impact calculation model 123.

[0131] Furthermore, the impact calculation unit 118 outputs the values ​​output from the impact calculation model 123 to the diagnostic intermediate data generation unit 113. The diagnostic intermediate data generation unit 113 then assigns the values ​​obtained from the impact calculation unit 118 (values ​​indicating the degree of impact) to the IED items in the diagnostic intermediate data format.

[0132] Figure 10 shows an example of the degree of influence. In the example shown, the degree of influence of ambient temperature, a data element extracted from environmental data, on the microcontroller, memory, and power supply components of the edge system 230 is 0.81, 0.73, and 0.32, respectively. It also shows that the degree of influence of internal temperature, a data element extracted from probe data, on the microcontroller, memory, and power supply components of the edge system 230 is 0.80, 0.70, and 0.41, respectively.

[0133] The malfunction diagnosis system 1000 according to the second embodiment has been described above.

[0134] According to this malfunction diagnosis system 1000, factors that may indirectly affect the function of vehicle equipment, such as weather conditions and vibrations during driving, can be assigned to diagnostic intermediate data based on their impact on malfunctions. As a result, the amount of information in the diagnostic intermediate data used in the diagnostic analysis process can be increased, and the accuracy of the diagnostic analysis can be improved.

[0135] Figure 11 shows an example of the hardware configuration of a fault diagnosis device 100. The fault diagnosis device 100 is a computer such as a cloud server. As shown in the figure, the fault diagnosis device 100 has an input device 410, an output device 420, a processing device 430, a main memory 440, an auxiliary memory 450, a communication device 460, and a bus 470 that electrically connects each of these devices.

[0136] The input device 410 is a device for the operator to input information and instructions to the malfunction diagnosis device 100. Specifically, the input device 410 is, for example, a touch panel, keyboard, mouse, or voice input device such as a microphone.

[0137] The output device 420 is a device that outputs information generated by the fault diagnosis device 100. Specifically, the output device 420 is a display, printer, or speaker.

[0138] The processing unit 430 is, for example, a device that performs arithmetic processing. Specifically, the processing unit 430 is a CPU (Central Processing Unit), a microprocessor, a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), or other semiconductor device capable of performing calculations.

[0139] The main memory 440 consists of memory devices such as RAM (Random Access Memory) for temporarily storing various read information, and ROM (Read Only Memory) for storing programs executed by the processing unit 430, application programs, and various other information. The auxiliary storage device 450 consists of non-volatile storage devices such as HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory that can store digital information.

[0140] The communication device 460 is a device that performs wireless or wired information communication with external devices.

[0141] The hardware configuration of the malfunction diagnosis device 100 has been described above.

[0142] The processing unit 110 of the malfunction diagnosis device 100 is implemented by a program that causes the processing unit 430 (for example, the CPU) to perform processing. These programs are stored, for example, in the main memory 440 or auxiliary memory 450, and are loaded onto the main memory 440 for execution and executed by the processing unit 430. The storage unit 120 may also be implemented by the main memory 440 or auxiliary memory 450, or by a combination of these. The communication unit 150 is implemented by the communication device 460.

[0143] Furthermore, each functional block of the malfunction diagnosis device 100 is classified according to its main processing content in order to facilitate understanding of each function realized in this embodiment. Therefore, the present invention is not limited by the way each function is classified or its name. In addition, each component of the malfunction diagnosis device 100 can be further classified into many more components according to the processing content. Alternatively, a single component can be classified to perform even more processing.

[0144] Furthermore, all or part of each functional unit may be constructed using hardware (such as integrated circuits like ASICs) implemented in a computer. Also, the processing of each functional unit may be performed on one piece of hardware or on multiple pieces of hardware.

[0145] Furthermore, the present invention is not limited to the embodiments and modifications described above, but includes a variety of other embodiments and modifications. For example, the embodiments described above are described in detail to make the present invention easier to understand, and are not necessarily limited to those having all the configurations described. Also, it is possible to replace parts of the configuration of one embodiment with the configurations of other embodiments or modifications, and it is also possible to add configurations from other embodiments to the configuration of one embodiment. In addition, it is possible to add, delete, or replace parts of the configuration of each embodiment with other configurations.

[0146] Furthermore, the control lines and information lines shown above are those deemed necessary for the explanation, and do not necessarily represent all control lines and information lines present in the actual product. In reality, it is safe to assume that almost all components are interconnected. [Explanation of Symbols]

[0147] 1000... Troubleshooting system, 100... Troubleshooting device, 110... Processing unit, 111... Data type classification unit, 112... Data element extraction unit, 113... Intermediate data generation unit for diagnosis, 114... Sort merge unit, 115... Diagnostic analysis unit, 116... Diagnostic result output unit, 117... Information model generation unit, 118... Impact calculation unit, 120... Storage unit, 121... Individual analysis rule DB, 122... Intermediate data storage DB for diagnosis, 123... Impact calculation model, 124...Diagnostic analysis result history DB, 130...Input unit, 140...Output unit, 150...Communication unit, 200...Manufacturer server, 210...Environmental data provision server, 220...SNS server, 230...Edge system, 240...Connected service data output device, 410...Input device, 420...Output device, 430...Processing unit, 440...Main memory, 450...Auxiliary memory, 460...Communication device, 470...Bus, N...Network

Claims

1. A fault diagnosis system comprising an edge system which is an electronic system, a fault diagnosis device for diagnosing faults in the edge system, and a computer which is an external device, The aforementioned malfunction diagnostic device is The data acquired from the edge system and the computer is classified according to its type. Based on a predetermined interpretation process for the aforementioned data, the data elements contained in the data are extracted. The data elements are converted into predetermined data codes corresponding to items in a common data format regardless of the type of data, and diagnostic intermediate data is generated by assigning the data codes to the corresponding items. Using the aforementioned diagnostic intermediate data, a diagnostic analysis of malfunctions in the edge system is performed. A malfunction diagnosis system characterized by the following features.

2. A malfunction diagnosis system according to claim 1, The data format of the aforementioned diagnostic intermediate data is: It includes an item to which a data code indicating the type of data is assigned, an item to which a data code indicating the details of the data is assigned, an item to which the data acquisition time or the time of occurrence of a malfunction event in the edge system is assigned, an item to which a classification code for the data is assigned, and an item to which the actual value of the data indicating the state is assigned. A malfunction diagnosis system characterized by the following features.

3. A malfunction diagnosis system according to claim 2, The aforementioned malfunction diagnostic device is Based on the data acquisition time or the event occurrence time, a dataset is generated in which the diagnostic intermediate data is rearranged chronologically. A malfunction diagnosis system characterized by the following features.

4. A malfunction diagnosis system according to claim 2, The edge system is mounted on a mobile body and electronically controls the drive of the mobile body. A malfunction diagnosis system characterized by the following features.

5. A malfunction diagnosis system according to claim 4, The aforementioned diagnostic intermediate data includes: A data code indicating the state of the mobile body is assigned, which is converted based on the data elements extracted from the internal data of the mobile body. A malfunction diagnosis system characterized by the following features.

6. A malfunction diagnosis system according to claim 4, The aforementioned diagnostic intermediate data includes: A data code indicating the movement status of the mobile body is assigned, which is converted based on the data elements extracted from the probe data of the mobile body. A malfunction diagnosis system characterized by the following features.

7. A malfunction diagnosis system according to claim 4, The aforementioned diagnostic intermediate data includes: A data code indicating the environmental conditions around the moving object is assigned, which is converted based on the data elements extracted from environmental data, including weather and road surface conditions. A malfunction diagnosis system characterized by the following features.

8. A malfunction diagnosis system according to claim 4, The aforementioned diagnostic intermediate data includes: Based on the data elements extracted from the product data of the mobile body, a data code indicating the state of the components of the mobile body is assigned. A malfunction diagnosis system characterized by the following features.

9. A malfunction diagnosis system according to claim 4, The aforementioned diagnostic intermediate data includes: A data code indicating a state evaluation for the mobile object is assigned, which is converted based on the data elements extracted from user data. A malfunction diagnosis system characterized by the following features.

10. A malfunction diagnosis system according to claim 4, The aforementioned diagnostic intermediate data includes: A data code indicating a malfunction in the said linked service is assigned, which is converted based on the data elements extracted from the data related to the linked service with the said edge system. A malfunction diagnosis system characterized by the following features.

11. A malfunction diagnosis system according to claim 2, The aforementioned malfunction diagnostic device is Based on the data codes assigned to the aforementioned items, the processing content and processing order of the diagnostic analysis are determined. A malfunction diagnosis system characterized by the following features.

12. A malfunction diagnosis system according to claim 1, The aforementioned malfunction diagnostic device is By inputting the data elements into an impact calculation model generated by machine learning using the aforementioned diagnostic intermediate data, the degree of impact of the operating environment of the edge system on malfunctions in the edge system is calculated. The calculated impact level is assigned to the corresponding item in the diagnostic intermediate data. A malfunction diagnosis system characterized by the following features.

13. A malfunction diagnosis system according to claim 12, The aforementioned malfunction diagnostic device is The impact calculation model is updated based on the processing results of the diagnostic analysis using the aforementioned diagnostic intermediate data. A malfunction diagnosis system characterized by the following features.

14. A fault diagnosis device for diagnosing malfunctions in edge systems, which are electronic systems, The aforementioned malfunction diagnostic device is A data type classification unit that distinguishes data acquired from the edge system and external devices according to their type, A data element extraction unit extracts data elements contained in the data based on a predetermined interpretation process for the data, A diagnostic intermediate data generation unit converts the aforementioned data elements into predetermined data codes corresponding to items in a common data format regardless of the type of data, and generates diagnostic intermediate data by assigning the data codes to the corresponding items. The system includes a diagnostic analysis unit that performs a diagnostic analysis of malfunctions in the edge system using the aforementioned diagnostic intermediate data. A malfunction diagnosis device characterized by the following features.

15. A fault diagnosis method performed by a fault diagnosis device for diagnosing malfunctions in an edge system, which is an electronic system, The aforementioned malfunction diagnostic device is A data type classification step that distinguishes data acquired from the edge system and external devices according to their type, A data element extraction step in which data elements included in the data are extracted based on a predetermined interpretation process for the data, A diagnostic intermediate data generation step involves converting the aforementioned data elements into predetermined data codes corresponding to items in a common data format regardless of the type of data, and generating diagnostic intermediate data by assigning the said data codes to the corresponding items. A diagnostic analysis step is performed to perform a diagnostic analysis of defects in the edge system using the aforementioned diagnostic intermediate data. A method for diagnosing malfunctions characterized by the following features.

Images