Internet of Vehicles data analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses an Internet of Vehicles data analysis method and device, electronic equipment and a storage medium, and relates to the technical field of Internet of Vehicles. The method comprises the steps of determining attribute information of a target user question in response to the target user question related to Internet of Vehicles data; determining an embedded representation of the attribute information, and determining a target table structure matched with the target user question based on the embedded representation of the attribute information; based on the target table structure, reconstructing the target user question to obtain a target query statement; and in response to an execution instruction of the target query statement, obtaining target Internet of Vehicles data related to the target query statement, and determining an analysis result of each target Internet of Vehicles data based on a large model. According to the scheme provided by the embodiment of the invention, the acquired Internet of Vehicles data can be quickly and accurately analyzed, so that help is provided for research, development and design of vehicles.

Description

Technical Field

[0001] The present invention relates to the field of vehicle networking technology, and in particular to a method, device, electronic device and storage medium for analyzing vehicle networking data. Background Art

[0002] Internet of Vehicles technology provides guidance for vehicle research and development and design by acquiring Internet of Vehicles data such as vehicle location, speed, driving status or maintenance records, and analyzing these Internet of Vehicles data.

[0003] At present, the acquired Internet of Vehicles data is mainly analyzed manually, which not only consumes a lot of manpower and material resources, but also has a low accuracy rate of analysis results. How to quickly and accurately analyze the acquired Internet of Vehicles data to provide assistance for vehicle research and development and design is a key research issue in the industry. Summary of the invention

[0004] The present invention provides a method, device, electronic device and storage medium for analyzing Internet of Vehicles data, which can quickly and accurately analyze the acquired Internet of Vehicles data, thereby providing assistance for the research and development and design of vehicles.

[0005] According to one aspect of the present invention, a method for analyzing Internet of Vehicles data is provided, the method comprising:

[0006] In response to a target user question related to the Internet of Vehicles data, determining attribute information of the target user question;

[0007] Determining an embedded representation of the attribute information, and determining a target table structure matching the target user question based on the embedded representation of the attribute information;

[0008] Based on the target table structure, reconstruct the target user question to obtain a target query statement;

[0009] In response to an execution instruction of the target query statement, target Internet of Vehicles data related to the target query statement is acquired, and analysis results of each target Internet of Vehicles data are determined based on a large model.

[0010] According to another aspect of the present invention, a device for analyzing Internet of Vehicles data is provided, the device comprising:

[0011] An attribute information determination module, configured to determine attribute information of a target user question in response to a target user question related to the Internet of Vehicles data;

[0012] A target table structure determination module, used to determine the embedded representation of the attribute information, and determine the target table structure matching the target user question based on the embedded representation of the attribute information;

[0013] A target query statement determination module is used to reconstruct the target user question based on the target table structure to obtain a target query statement;

[0014] The analysis result determination module is used to respond to the execution instruction of the target query statement, obtain the target Internet of Vehicles data related to the target query statement, and determine the analysis result of each target Internet of Vehicles data based on the big model.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for analyzing Internet of Vehicles data described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for analyzing Internet of Vehicles data described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for analyzing Internet of Vehicles data described in any embodiment of the present invention.

[0021] The technical solution of the embodiment of the present invention determines the attribute information of the target user question in response to the target user question related to the Internet of Vehicles data; determines the embedded representation of the attribute information, and determines the target table structure matching the target user question based on the embedded representation of the attribute information; reconstructs the target user question based on the target table structure to obtain a target query statement; obtains the target Internet of Vehicles data related to the target query statement in response to the execution instruction of the target query statement, and determines the analysis results of each target Internet of Vehicles data based on a large model, so as to quickly and accurately analyze the acquired Internet of Vehicles data, thereby providing assistance for the research and development and design of vehicles.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a method for analyzing Internet of Vehicles data provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a method for analyzing Internet of Vehicles data provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a flow chart of a method for analyzing Internet of Vehicles data provided according to Embodiment 3 of the present invention;

[0027] Figure 4 is a schematic diagram of the structure of a vehicle networking data analysis device provided according to a fourth embodiment of the present invention;

[0028] Figure 5 It is a schematic diagram of the structure of an electronic device for implementing the method for analyzing Internet of Vehicles data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 This is a flow chart of a method for analyzing Internet of Vehicles data provided according to Embodiment 1 of the present invention. This embodiment is applicable to the case of analyzing Internet of Vehicles data. The method can be executed by an analysis device for Internet of Vehicles data. The analysis device for Internet of Vehicles data can be implemented in the form of hardware and / or software. The analysis device for Internet of Vehicles data can be configured in a computer or server, for example, a graphics processing unit (GPU) server or other electronic device. Figure 1 As shown, the method includes:

[0033] Step 110 : In response to a target user question related to the Internet of Vehicles data, determine attribute information of the target user question.

[0034] Among them, the Internet of Vehicles data may include the vehicle position, speed, driving status or maintenance records of different vehicles (for example, construction machinery vehicles, cars or buses, etc.), which are not limited in this embodiment.

[0035] In this embodiment, the target user may be a vehicle R&D personnel, for example, a staff member who analyzes the existing vehicle data and iterates and updates the vehicle; illustratively, the target user's questions may be fuel consumption, engine status, or battery status, etc., which are not limited in this embodiment.

[0036] In an optional implementation of this embodiment, after the target user questions related to the Internet of Vehicles data are obtained, the attribute information of the target user questions can be further determined; wherein the attribute information of the target user questions may include data dimensions and / or data indicators of the target user questions; for example, it may include data dimensions, data indicators, or data dimensions and data indicators of the target user questions.

[0037] Step 120: Determine an embedded representation of the attribute information, and determine a target table structure that matches the target user question based on the embedded representation of the attribute information.

[0038] In an optional implementation of this embodiment, after obtaining the attribute information of the target user's question, the embedded representation of the attribute information can be further determined, and the target user's question can be determined based on the embedded representation of the attribute information; wherein, the target table structure can be any table structure in a pre-built metadata vector library, which is not limited in this embodiment; in this embodiment, each table structure in the metadata vector library can be represented in the form of a vector, which is referred to as the embedded representation of each table structure in this embodiment.

[0039] Optionally, in this embodiment, after obtaining the embedded representation of the attribute information, the similarity between the embedded representation of the attribute information and the embedded representation of each table structure in the metadata vector library can be calculated, and the target table structure can be determined based on the similarity calculation results; for example, the table structure corresponding to the calculation result with the greatest similarity can be determined as the target table structure.

[0040] Step 130: Based on the target table structure, reconstruct the target user question to obtain a target query statement.

[0041] In an optional implementation of this embodiment, after obtaining the target table structure, the received target user question may be further reconstructed based on the target table structure to obtain a target query statement.

[0042] Optionally, in this embodiment, after obtaining the target table structure, the target table structure and the target user question may be input into a predetermined prompt word template to obtain a target query statement.

[0043] Step 140: In response to the execution instruction of the target query statement, target Internet of Vehicles data related to the target query statement is acquired, and analysis results of each target Internet of Vehicles data are determined based on the big model.

[0044] In an optional implementation of this embodiment, after obtaining the target query statement, the target query statement can be further executed to obtain the target Internet of Vehicles data; further, the obtained target query statement can be analyzed based on the big model to obtain the analysis result; further, the analysis result can be fed back to the target user to help the target user iteratively update the vehicle.

[0045] In another optional implementation of this embodiment, after the target Internet of Vehicles data is acquired, each target Internet of Vehicles data may be displayed to the target user in real time so that the target user can analyze the target Internet of Vehicles data by himself.

[0046] The technical solution of the embodiment of the present invention determines the attribute information of the target user question in response to the target user question related to the Internet of Vehicles data; determines the embedded representation of the attribute information, and determines the target table structure matching the target user question based on the embedded representation of the attribute information; reconstructs the target user question based on the target table structure to obtain a target query statement; obtains the target Internet of Vehicles data related to the target query statement in response to the execution instruction of the target query statement, and determines the analysis results of each target Internet of Vehicles data based on a large model, so as to quickly and accurately analyze the acquired Internet of Vehicles data, thereby providing assistance for the research and development and design of vehicles.

[0047] Embodiment 2

[0048] Figure 2 1 is a flow chart of a method for analyzing vehicle network data according to the second embodiment of the present invention. This embodiment is a further refinement of the above technical solution. The technical solution in this embodiment can be combined with each optional solution in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0049] Step 210: Receive target user questions related to Internet of Vehicles data.

[0050] In an optional implementation of this embodiment, the received target user questions related to the Internet of Vehicles data may be in the form of text, voice, or action instructions, etc., which are not limited in this embodiment.

[0051] Step 220: convert the target user question into a target question text, understand the target question text, and obtain a semantic understanding result; extract data dimensions and / or data indicators of the semantic understanding result to obtain attribute information of the target user question.

[0052] In an optional implementation of the present embodiment, after receiving the target user question, the target user question in different forms can be converted into question text. For example, if the target user question is in the form of text, then what is directly received is the target text question; if the target user question is in the form of voice, then the voice target user question can be converted into text content to obtain the target text question; if the target user question is in the form of action instructions, then the action instructions can be converted into text content to obtain the target text question.

[0053] Optionally, in this embodiment, after the target user question is converted into a target question text, the target question text can be further understood to obtain a semantic understanding result of the target user question; further, data dimensions, data indicators, or data dimensions and data indicators of the semantic understanding result can be extracted, and the acquired data dimensions, data indicators, or data dimensions and data indicators can be determined as attribute information of the target user question.

[0054] In an optional implementation of this embodiment, after the target user question is converted into a target question text, the target question text can be understood by a pre-trained natural language processing model, and the data dimensions, data indicators, or data dimensions and data indicators of the semantic understanding results can be extracted to obtain the attribute information of the target user question.

[0055] Step 230: input the attribute information into the first large model obtained by pre-training, and output the embedded representation of the attribute information; respectively determine the similarity between the embedded representation of the attribute information and the embedded representation of each table structure pre-stored in the database to obtain each similarity calculation result; determine the target table structure based on each similarity calculation result.

[0056] The embedded representation of each table structure records key information of each table structure.

[0057] In this embodiment, the first large model may be a semantic representation model or other large language model, which is not limited in this embodiment.

[0058] Optionally, in this embodiment, after obtaining the attribute information of the target user question, the attribute information of the target user question can be input into the first large model obtained by pre-training, and the embedded representation of the attribute information of the target user question can be output; it can be understood that the embedded representation of the attribute information of the target user question is to represent the attribute information of the target user question in the form of a vector.

[0059] Furthermore, the similarities between the embedded representation of the attribute information and the embedded representation of each table structure pre-stored in the database can be calculated respectively to obtain the similarity calculation results; wherein the database can be a predetermined metadata vector library, or other forms of databases, which are not limited in this embodiment.

[0060] Furthermore, each similarity calculation result may be sorted in a set order, for example, each similarity calculation result may be sorted in an ascending order or a descending order, and the maximum similarity calculation result may be determined according to the sorting result; further, the table structure corresponding to the maximum similarity calculation result may be determined as the target table structure.

[0061] Step 240: fill the target user question and the target table structure into a predetermined prompt word template to obtain a first query statement; verify the first query statement; if the first query statement is successfully verified, determine the first query statement as a target query statement.

[0062] In an optional implementation of the present embodiment, after determining the target table structure, the target user question and the target table structure can be further filled into a predetermined prompt word template to obtain a first query statement; in the present embodiment, the prompt word template can be used to reconstruct the target user question to construct prompt words that match the target user question, and further, the first query statement that matches the prompt words can be determined through the large model.

[0063] Optionally, in this embodiment, after obtaining the first query statement, the first query statement may be further verified; if the verification passes, the first query statement may be determined as the target query statement.

[0064] Step 250: submit the target query statement to the reference database for execution to obtain various query results; transmit each of the query results to the target area, and display each of the query results in real time in the target area.

[0065] The query result includes each target Internet of Vehicles data; the reference database includes pre-acquired Internet of Vehicles data about different vehicles; exemplarily, the reference database may be a DORIS database.

[0066] In this embodiment, the target area may be a front-end display page of the system or a designated folder under a set path, etc., which is not limited in this embodiment.

[0067] Optionally, in this embodiment, after obtaining the target query statement, the target query statement can be further submitted to the reference database for execution, so as to obtain the query results in the reference database; further, each transmission result can be transmitted to the target area, and each query result can be displayed in real time in the target area.

[0068] Step 260: Input each of the target Internet of Vehicles data into the pre-trained large model to obtain analysis results of each of the target Internet of Vehicles data; and display each of the analysis results in a target format.

[0069] The target format includes at least one of the following: text, table, bar chart and pie chart.

[0070] In an optional implementation of the present embodiment, the target query statement is submitted to a reference database for execution. After the query result is obtained in the reference database, that is, after each target Internet of Vehicles data is obtained, each target Internet of Vehicles data can be further input into a pre-trained large model, for example, a large language model, to obtain an analysis result of the target Internet of Vehicles data; further, each analysis result can be displayed in the form of text, table, bar chart or pie chart, so that R&D personnel can determine the update direction of the vehicle based on the display results, thereby assisting R&D personnel in making decisions.

[0071] The solution of this embodiment, after obtaining the target query statement, can submit the target query statement to the reference database for execution to obtain various query results; transmit each of the query results to the target area, and display each of the query results in real time in the target area; further, each of the target Internet of Vehicles data can be input into a pre-trained large model to obtain analysis results of each of the target Internet of Vehicles data; display each of the analysis results in the target format, so as to quickly and accurately analyze the acquired Internet of Vehicles data, and provide assistance to R&D personnel in vehicle research and development and design.

[0072] Embodiment 3

[0073] Figure 3 1 is a flow chart of a method for analyzing vehicle network data according to Embodiment 3 of the present invention. This embodiment is a further refinement of the above technical solution. The technical solution in this embodiment can be combined with each optional solution in one or more of the above embodiments. Figure 3 As shown, the method includes:

[0074] Step 310: In response to a target user question related to the Internet of Vehicles data, determine attribute information of the target user question.

[0075] Step 320: Determine an embedded representation of the attribute information, and determine a target table structure that matches the target user question based on the embedded representation of the attribute information.

[0076] Step 330: Fill the target user question and the target table structure into a predetermined prompt word template to obtain a first query statement.

[0077] Step 340: If it is determined that the first query statement has not passed the verification, the prompt word template is updated based on the first query statement to obtain an updated prompt word template; the target user question and the target table structure are filled into the updated prompt word template to obtain a second query statement, and the operation of verifying the second query statement is continued until the second query statement passes the verification.

[0078] In another optional implementation of the present embodiment, if it is determined that the first query statement has not passed the verification, the prompt word template is updated based on the first query statement to obtain an updated prompt word template; the target user question and the target table structure are filled into the updated prompt word template to obtain a second query statement, and the operation of verifying the second query statement is continued until the second query statement passes the verification.

[0079] Optionally, in this embodiment, when the first query statement fails to be verified, the first query statement can be added to the counterexample of the prompt word template to obtain an updated prompt word template; further, the target user question and the target table structure can be filled into the updated prompt word template to obtain a second query statement, and the second query statement is verified. If the verification passes, the second query statement is determined as the target query statement; otherwise, the operation of updating the prompt word template based on the second query statement is continued until the query statement obtained passes the verification.

[0080] Step 350: In response to the execution instruction of the target query statement, obtain target Internet of Vehicles data related to the target query statement, and determine the analysis results of each target Internet of Vehicles data based on the big model.

[0081] The solution of this embodiment is to update the prompt word template based on the first query statement when the first query statement fails to be verified, so as to avoid the problem of repeatedly constructing query statements that fail to be verified and affecting the calculation efficiency. The target query statement can be obtained quickly, providing a basis for obtaining accurate analysis results of the Internet of Vehicles data later.

[0082] In order to better understand the analysis method of the Internet of Vehicles data involved in this embodiment, a specific example is used below to explain it:

[0083] Step 1: Receive user questions and extract information such as dimensions and indicators of user questions.

[0084] In a specific implementation, the server can automatically receive the question text input by the user from the front end, and use the NER model to extract the dimensions and indicators involved in the question.

[0085] Step 2: Use the vector database to retrieve matching fields and table structures.

[0086] In a specific implementation, a pre-trained semantic representation model can be used to vectorize each field in the database and store it in a vector database; further, the dimensions and indicators of user questions can be vectorized; further, the cosine similarity of the dimension and indicator vectors Vq and each knowledge vector Vi in the database can be calculated respectively, and after retrieving the N fields with the highest similarity, the corresponding table structure can be obtained through the table name stored in the vector database.

[0087] Step 3: Construct prompt words and use the large model to generate query statements.

[0088] In a specific implementation, the user question and the retrieved table structure can be filled into a pre-set prompt word template, the generated query statement can be verified, and the generated query statement can be submitted to the database for verification. If the query statement verification fails, the wrong query statement can be added to the prompt word as a counterexample and then regenerated.

[0089] Step 4: Execute the query statement, obtain the results and display them.

[0090] In the specific implementation, the query statement can be submitted to the DORIS database for execution. After the query is completed, the front end will convert the received data into intuitive charts to provide users with clear and efficient data display.

[0091] Step 5: Use the large language model to analyze the query results and provide an analysis report.

[0092] In a specific implementation, after executing a query statement, the query result data can be quickly returned to the front end, and these data and the query question can be simultaneously input into the large language model according to a preset template; the large language model will conduct an in-depth analysis of the data and generate a detailed analysis report to provide a reference for user decision-making; the solution of this embodiment not only improves the efficiency of data processing, but also enhances the depth and breadth of data analysis.

[0093] Embodiment 4

[0094] Figure 4 Schematic diagram of a vehicle networking data analysis device according to the third embodiment of the present invention. Figure 4 As shown, the device includes: an attribute information determination module 410, a target table structure determination module 420, a target query statement determination module 430 and an analysis result determination module 440.

[0095] The attribute information determination module 410 is used to determine the attribute information of the target user question in response to the target user question related to the Internet of Vehicles data;

[0096] A target table structure determination module 420, configured to determine an embedded representation of the attribute information, and determine a target table structure matching the target user question based on the embedded representation of the attribute information;

[0097] A target query statement determination module 430 is used to reconstruct the target user question based on the target table structure to obtain a target query statement;

[0098] The analysis result determination module 440 is used to respond to the execution instruction of the target query statement, obtain the target Internet of Vehicles data related to the target query statement, and determine the analysis results of each target Internet of Vehicles data based on the big model.

[0099] The solution of this embodiment is to determine the attribute information of the target user question related to the Internet of Vehicles data by an attribute information determination module; determine the embedded representation of the attribute information by a target table structure determination module, and determine the target table structure matching the target user question based on the embedded representation of the attribute information; reconstruct the target user question based on the target table structure to obtain the target query statement by a target query statement determination module; obtain the target Internet of Vehicles data related to the target query statement by an analysis result determination module in response to the execution instruction of the target query statement, and determine the analysis results of each target Internet of Vehicles data based on a large model, so as to quickly and accurately analyze the acquired Internet of Vehicles data, thereby providing assistance for the research and development and design of vehicles.

[0100] In an optional implementation of this embodiment, the attribute information determination module 410 is specifically used to convert the target user question into a target question text, understand the target question text, and obtain a semantic understanding result;

[0101] The data dimensions and / or data indicators of the semantic understanding result are extracted to obtain the attribute information of the target user's question.

[0102] In an optional implementation of this embodiment, the target table structure determination module 420 is specifically configured to input the attribute information into a pre-trained first large model and output an embedded representation of the attribute information;

[0103] Respectively determining the similarity between the embedded representation of the attribute information and the embedded representation of each table structure pre-stored in the database, and obtaining each similarity calculation result;

[0104] Wherein, the key information of each table structure is recorded in the embedded representation of each table structure;

[0105] The target table structure is determined based on the similarity calculation results.

[0106] In an optional implementation of this embodiment, the target query statement determination module 430 is specifically configured to fill the target user question and the target table structure into a predetermined prompt word template to obtain a first query statement;

[0107] Verifying the first query statement;

[0108] If the first query statement is successfully verified, the first query statement is determined as a target query statement.

[0109] In an optional implementation of this embodiment, the vehicle network data analysis device further includes: a prompt word template updating module, which is used to update the prompt word template based on the first query statement if it is determined that the first query statement verification fails, to obtain an updated prompt word template;

[0110] The target user question and the target table structure are filled into the updated prompt word template to obtain a second query statement, and the operation of verifying the second query statement is continued until the second query statement passes the verification.

[0111] In an optional implementation of this embodiment, the analysis result determination module 440 is specifically used to submit the target query statement to the reference database for execution to obtain various query results;

[0112] Transmitting each of the query results to a target area, and displaying each of the query results in real time in the target area;

[0113] Wherein, the query result includes each of the target Internet of Vehicles data;

[0114] The reference database contains pre-acquired Internet of Vehicles data about different vehicles.

[0115] In an optional implementation of this embodiment, the analysis result determination module 440 is further specifically used to input each of the target Internet of Vehicles data into a pre-trained large model to obtain the analysis result of each of the target Internet of Vehicles data;

[0116] Displaying each of the analysis results in a target format;

[0117] The target format includes at least one of the following: text, table, bar chart, and pie chart.

[0118] The vehicle networking data analysis device provided in the embodiment of the present invention can execute the vehicle networking data analysis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0119] In the technical solutions of the embodiments of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of user information (for example, user questions) involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0120] Embodiment 5

[0121] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. 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 processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 present invention described and / or required herein.

[0122] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0123] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0124] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the analysis method of Internet of Vehicles data.

[0125] In some embodiments, the method for analyzing vehicle network data may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for analyzing vehicle network data described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for analyzing vehicle network data in any other appropriate manner (e.g., by means of firmware).

[0126] Various implementations of the systems and techniques described above 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 products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0128] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0130] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0131] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0132] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0133] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing Internet of Vehicles data, characterized in that: include: In response to a target user question related to the Internet of Vehicles data, determining attribute information of the target user question; Determining an embedded representation of the attribute information, and determining a target table structure matching the target user question based on the embedded representation of the attribute information; Based on the target table structure, reconstruct the target user question to obtain a target query statement; In response to an execution instruction of the target query statement, target Internet of Vehicles data related to the target query statement is acquired, and analysis results of each target Internet of Vehicles data are determined based on a large model.

2. The method for analyzing Internet of Vehicles data according to claim 1, characterized in that: The determining of the attribute information of the target user's question includes: Convert the target user question into a target question text, understand the target question text, and obtain a semantic understanding result; The data dimensions and / or data indicators of the semantic understanding result are extracted to obtain the attribute information of the target user's question.

3. The method for analyzing Internet of Vehicles data according to claim 1, characterized in that: The step of determining the embedded representation of the attribute information, and determining a target table structure matching the target user question based on the embedded representation of the attribute information, comprises: Inputting the attribute information into a pre-trained first large model, and outputting an embedded representation of the attribute information; Respectively determining the similarity between the embedded representation of the attribute information and the embedded representation of each table structure pre-stored in the database, and obtaining each similarity calculation result; Wherein, the key information of each table structure is recorded in the embedded representation of each table structure; The target table structure is determined based on the similarity calculation results.

4. The method for analyzing Internet of Vehicles data according to claim 1, characterized in that: The target user question is reconstructed based on the target table structure to obtain a target query statement, including: Filling the target user question and the target table structure into a predetermined prompt word template to obtain a first query statement; Verifying the first query statement; If the first query statement is successfully verified, the first query statement is determined as a target query statement.

5. The method for analyzing Internet of Vehicles data according to claim 4, characterized in that: After verifying the first query statement, the method further includes: If it is determined that the first query statement fails verification, updating the prompt word template based on the first query statement to obtain an updated prompt word template; The target user question and the target table structure are filled into the updated prompt word template to obtain a second query statement, and the operation of verifying the second query statement is continued until the second query statement passes the verification.

6. The method for analyzing Internet of Vehicles data according to claim 1, characterized in that: The acquiring target Internet of Vehicles data related to the target query statement includes: Submitting the target query statement to the reference database for execution to obtain query results; Transmitting each of the query results to a target area, and displaying each of the query results in real time in the target area; Wherein, the query result includes each of the target Internet of Vehicles data; The reference database contains pre-acquired Internet of Vehicles data about different vehicles.

7. The method for analyzing Internet of Vehicles data according to claim 1, characterized in that: The analysis results of each target Internet of Vehicles data are determined based on the large model, including: Inputting each of the target Internet of Vehicles data into a pre-trained large model to obtain analysis results of each of the target Internet of Vehicles data; Displaying each of the analysis results in a target format; The target format includes at least one of the following: text, table, bar chart, and pie chart.

8. A vehicle networking data analysis device, characterized in that: include: An attribute information determination module, configured to determine attribute information of a target user question in response to a target user question related to the Internet of Vehicles data; A target table structure determination module, used to determine the embedded representation of the attribute information, and determine the target table structure matching the target user question based on the embedded representation of the attribute information; A target query statement determination module is used to reconstruct the target user question based on the target table structure to obtain a target query statement; The analysis result determination module is used to respond to the execution instruction of the target query statement, obtain the target Internet of Vehicles data related to the target query statement, and determine the analysis result of each target Internet of Vehicles data based on the big model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for analyzing vehicle network data according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for analyzing Internet of Vehicles data according to any one of claims 1 to 7 when executed.

Images