Data ownership determination method for vehicle, and processor, vehicle and storage medium
By identifying the tagging information of vehicle driving data and inputting it into the order prediction model, the value attributes and ownership information are obtained, which solves the problem of low utilization of vehicle data in sharing and trading, and realizes full utilization of data and privacy protection.
Patent Information
- Application Number
- PCT/CN2025/148275
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-07-08
- Filing Date
- 2025-12-31
- Publication Date
- 2026-11-12
AI Technical Summary
Data generated during vehicle operation suffers from data silos, privacy breaches, and unclear rights allocation in sharing and trading, resulting in low data utilization.
By determining the current tag information of the demand data of the purchase object, matching the corresponding data from the vehicle driving dataset, inputting it into the target order prediction model for prediction, obtaining the value attributes of the data, and determining the ownership information when the order information has the status of executing transaction behavior.
This has enabled the full utilization of vehicle data, improved data utilization, solved the problems of data silos and privacy leaks, and clarified the allocation of rights and interests.
Smart Images

Figure CN2025148275_12112026_PF_FP_ABST
Abstract
Description
Vehicle data ownership methods, processors, vehicles, and storage media
[0001] Cross-reference
[0002] This disclosure claims priority to Chinese Patent Application No. 202510934409.9, filed on July 8, 2025, entitled "Data Ownership Method, Processor, Vehicle and Storage Medium for Vehicles", the entire contents of which are incorporated herein by reference. Technical Field
[0003] This disclosure relates to the field of vehicles, and more specifically, to a method for determining data ownership of a vehicle, a processor, a vehicle, and a storage medium. Background Technology
[0004] Currently, vehicles generate a large amount of high-value data during operation. However, the sharing and trading of this data often suffers from issues such as data silos, privacy leaks, and unclear rights allocation, thus failing to fully realize the value of this data and resulting in low utilization rates of vehicle data.
[0005] There is currently no effective solution to the technical problem of low data utilization from the aforementioned vehicles. Summary of the Invention
[0006] This disclosure provides a method for confirming vehicle data ownership, a processor, a vehicle, and a storage medium to at least address the technical problem of low utilization of vehicle data.
[0007] According to one aspect of the present disclosure, a method for determining vehicle data ownership is provided, comprising: determining current tag information of a purchaser regarding demand data, wherein the demand data represents vehicle driving data associated with an application scenario, and the current tag information represents the category to which the vehicle driving data belongs; determining first vehicle driving data matching the current tag information from a vehicle driving dataset, wherein the vehicle driving dataset includes mapping relationships between different tag information and different vehicle driving data, and the first vehicle driving data represents vehicle driving data matching the category; inputting the first vehicle driving data into a target order prediction model for prediction to obtain order information of the first vehicle driving data, wherein the order information includes at least the value attribute of the first vehicle driving data displayed to the purchaser; and determining ownership information of the first vehicle driving data in response to the current state of the order information being a state of executing a transaction, wherein the ownership information includes at least the profit attribute of a supplier for the first vehicle driving data, and the supplier is used to provide different vehicle driving data to the vehicle driving dataset.
[0008] According to another aspect of the embodiments of this disclosure, a vehicle data ownership confirmation device is also provided. The device includes: a first determining component, configured to determine current tag information of a purchaser regarding demand data, wherein the demand data represents vehicle driving data associated with an application scenario, and the current tag information represents the category to which the vehicle driving data belongs; a second determining component, configured to determine first vehicle driving data matching the current tag information from a vehicle driving dataset, wherein the vehicle driving dataset includes mapping relationships between different tag information and different vehicle driving data, and the first vehicle driving data represents vehicle driving data matching the category; a prediction component, configured to input the first vehicle driving data into a target order prediction model for prediction to obtain order information of the first vehicle driving data, wherein the order information includes at least the value attribute of the first vehicle driving data displayed to the purchaser; and a third determining component, configured to determine ownership information of the first vehicle driving data in response to the current state of the order information being a state of executing a transaction, wherein the ownership information includes at least the profit attribute of the supplying object for the first vehicle driving data, and the supplying object is configured to provide different vehicle driving data to the vehicle driving dataset.
[0009] According to another aspect of embodiments of the present disclosure, a processor is also provided. The processor is used to run a program, wherein the program, when run by the processor, performs the methods described in various embodiments of the present disclosure.
[0010] According to another aspect of the present disclosure, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present disclosure when it runs.
[0011] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of the various embodiments of the present disclosure.
[0012] According to another aspect of the embodiments of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.
[0013] According to another aspect of the embodiments of this disclosure, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.
[0014] According to another aspect of the embodiments of this disclosure, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this disclosure.
[0015] In this embodiment, when confirming ownership of vehicle data, the current tag information of the buyer regarding demand data is determined. From the vehicle driving dataset, first vehicle driving data matching the current tag information is identified. The matched first vehicle driving data is input into a target order prediction model for prediction, obtaining order information for the first vehicle driving data. In response to the current state of the order information being a state where a transaction can be executed, the ownership information of the first vehicle driving data is determined. Because in this embodiment, based on determining the buyer's current tag information regarding demand data, vehicle driving data matching the category corresponding to the current tag information is determined from the vehicle driving dataset, and the matched vehicle driving data is input into the target order prediction model for prediction, order information including value attributes is obtained. Furthermore, when the current state of the order information is determined to be a state where a transaction can be executed, the ownership information of the first vehicle driving data is determined. This achieves the goal of fully releasing the value of vehicle data, thereby solving the technical problem of low vehicle data utilization and realizing the technical effect of improving vehicle data utilization. Attached Figure Description
[0016] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:
[0017] Figure 1(a) is a schematic diagram of an application scenario of a vehicle data ownership confirmation method according to an embodiment of the present disclosure;
[0018] Figure 1(b) is a flowchart of a vehicle data ownership confirmation method according to an embodiment of the present disclosure;
[0019] Figure 2(a) is a schematic diagram of a data element-based vehicle data element identification system according to an embodiment of the present disclosure;
[0020] Figure 2(b) is a flowchart of a data element-based method for determining the rights of vehicle data elements according to an embodiment of the present disclosure;
[0021] Figure 3 is a schematic diagram of data interaction between a vehicle and a server according to an embodiment of the present disclosure;
[0022] Figure 4 is a structural block diagram of a vehicle data ownership confirmation device according to an embodiment of the present disclosure. Detailed Implementation
[0023] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.
[0024] The terms "first," "second," etc., used in this disclosure, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data are interchangeable where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or components is not necessarily limited to those explicitly listed, but may include other steps or components not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0025] According to an embodiment of the present disclosure, an embodiment of a method for determining the data ownership of a vehicle is provided. The steps shown in the flowchart in the accompanying drawings are executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described are executed in a different order than that shown here.
[0026] As an optional implementation, the above-described vehicle data ownership confirmation method is not limited to the application scenario shown in Figure 1(a). Figure 1(a) is a schematic diagram of an application scenario of a vehicle data ownership confirmation method according to an embodiment of this disclosure. As shown in Figure 1(a), in the application scenario, the terminal device 10 is not limited to communicating with the server 13 through the network 11, and the server 13 is not limited to performing operations on the database, such as writing or reading data. The terminal device 10 includes, but is not limited to, a human-computer interaction screen, a processor, and a memory. The human-computer interaction screen is not limited to displaying virtual machines on the mobile terminal 10. The vehicle 12 is not limited to responding to the above-described human-computer interaction operations, performing corresponding operations, or generating corresponding instructions and sending the generated instructions to the server 13.
[0027] The steps shown in the flowcharts of the accompanying drawings are executed in a computer system such as a set of computer-executable instructions. While a logical order is shown in the flowcharts, in some cases, the steps shown or described are executed in a different order than that presented here. The vehicle data ownership confirmation method of this disclosure includes: step S102, determining the current tag information of the purchaser regarding demand data; step S104, determining first vehicle driving data matching the current tag information from the vehicle driving dataset; step S106, inputting the first vehicle driving data into a target order prediction model for prediction to obtain order information for the first vehicle driving data; and step S108, determining the ownership information of the first vehicle driving data in response to the current state of the order information being a state of executing a transaction.
[0028] The user information (including but not limited to tag information, order information, etc.) and data (including but not limited to demand data, vehicle driving data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.
[0029] Figure 1(b) is a flowchart of a vehicle data ownership confirmation method according to an embodiment of the present disclosure. As shown in Figure 1(b), the method includes the following steps.
[0030] Step S112: Determine the current tag information of the purchasing object regarding the demand data.
[0031] In the technical solution provided in step S112 of this disclosure, the aforementioned demand data is used to represent vehicle driving data associated with an application scenario. These application scenarios include at least one of the following: intelligent traffic management scenario, insurance risk assessment scenario, vehicle maintenance scenario, charging network optimization scenario, and prediction of battery health for new energy vehicles, etc.
[0032] In this embodiment, the vehicle driving data includes at least one of the following types of data: vehicle trajectory data, driving behavior data, and sensor display data. Specifically, the vehicle trajectory data represents the trajectory changes of the vehicle during driving; the driving behavior data (also known as driving habit data) represents the user's operating habits when controlling the vehicle; and the sensor display data represents various data displayed on different sensors, such as speed sensors, radar sensors, light sensors, pressure sensors, humidity sensors, temperature sensors, and image sensors. These are illustrative examples and not specific limitations.
[0033] In this embodiment, the aforementioned current tag information is used to indicate the category to which the vehicle driving data belongs. For example, in the application scenario of predicting the battery health of new energy vehicles, if the demand data is used to represent vehicle driving data associated with the aforementioned prediction scenario, then the category corresponding to the current tag information includes charging frequency category, temperature fluctuation category, and battery usage duration category, etc. The scenarios and categories here are illustrative and not specifically limited.
[0034] In this embodiment, the current tag information of the purchaser regarding the demand data is determined. Optionally, this embodiment obtains the purchaser's demand data, performs tag parsing on the obtained demand data, and obtains the current tag information of the demand data, that is, obtains the category to which the vehicle driving data associated with the application scenario belongs.
[0035] Step S114: Determine the first vehicle driving data that matches the current label information from the vehicle driving dataset.
[0036] In the technical solution provided in step S114 of this disclosure, the vehicle driving dataset includes mapping relationships between different label information and different vehicle driving data. For example, the vehicle driving dataset is a feature label library, which includes different labels and mapping relationships between different vehicle driving data encapsulated as data elements.
[0037] In this embodiment, the first vehicle driving data is used to represent vehicle driving data that matches the category corresponding to the current tag information. For example, if the category corresponding to the current tag information is the charging frequency category, then the first vehicle driving data is vehicle driving data that matches the charging frequency category.
[0038] In this embodiment, after determining the current tag information of the purchase target regarding demand data, the first vehicle driving data matching the current tag information is determined from the vehicle driving dataset. Optionally, based on the determined current tag information, this embodiment determines the initial tag similarity between the current tag information and different tag information from the vehicle driving dataset, and determines the first vehicle driving data matching the current tag information based on the determined initial tag similarity, that is, determines the vehicle driving data matching the category corresponding to the current tag information.
[0039] For example, the determined initial label similarities are sorted, and a target label similarity is selected from the sorted initial label similarities. This target label similarity is greater than all the initial label similarities except for the target label similarity. Based on the label information corresponding to the target label similarity, the first vehicle driving data matching the current label information is determined.
[0040] Optionally, based on the tag information corresponding to the similarity with the target tag, the first vehicle driving data matching the current tag information is determined. For example, based on the tag information corresponding to the similarity with the target tag, the vehicle driving data matching the corresponding tag information is determined as the first vehicle driving data. For example, the tag information corresponding to the similarity with the target tag is determined, and the vehicle driving data that satisfies the mapping relationship with the corresponding tag information is determined as the first vehicle driving data.
[0041] Step S116: Input the first vehicle driving data into the target order prediction model for prediction to obtain the order information of the first vehicle driving data.
[0042] In the technical solution provided in step S116 of this disclosure, the order information includes at least the value attribute of the first vehicle driving data displayed to the buyer, the permission information of the first vehicle driving data, and the encapsulation information of the first vehicle driving data. Specifically, the value attribute reflects the optimal price of the first vehicle driving data, the permission information reflects the access rights, usage rights, distribution rights, and modification rights of the first vehicle driving data, and the encapsulation information reflects the version, encapsulation time, and digital signature of the first vehicle driving data.
[0043] In this embodiment, the target order prediction model is an order prediction model built based on a three-dimensional pricing model, wherein the three-dimensional pricing model is a pricing model that comprehensively considers the data quality dimension, the usage intensity dimension, and the scenario value dimension.
[0044] In this embodiment, after determining the first vehicle driving data matching the current tag information from the vehicle driving dataset, the first vehicle driving data is input into the target order prediction model for prediction to obtain the order information of the first vehicle driving data. Optionally, based on determining the first vehicle driving data matching the current tag information, this embodiment inputs the determined first vehicle driving data into the prediction layer of the target order prediction model for prediction to obtain the order information of the first vehicle driving data, and then the output layer of the target order prediction model outputs the predicted order information.
[0045] The method described above, which inputs the first vehicle's driving data into the target order prediction model for prediction to obtain the order information of the first vehicle's driving data, is merely an example and is not specifically limited here. Any process or method that, based on determining the first vehicle's driving data that matches the current tag information, inputs the first vehicle's driving data into the target order prediction model for prediction to obtain order information, is within the protection scope of this disclosure's embodiments, and will not be described in detail here.
[0046] Step S118: In response to the current status of the order information being in a state of having a transaction to be executed, determine the ownership information of the first vehicle driving data.
[0047] In the technical solution provided in step S118 of this disclosure, the ownership information includes at least the profit attributes of the supply object for the first vehicle driving data, and the relationship between the supply objects. The supply objects are used to provide different vehicle driving data to the vehicle driving dataset.
[0048] In this embodiment, the aforementioned profit attribute refers to the profit received by the contributors to the vehicle driving data for the first vehicle driving data. For example, the contributors include, but are not limited to, data source developers and model developers.
[0049] In this embodiment, after inputting the first vehicle driving data into the target order prediction model for prediction to obtain the order information of the first vehicle driving data, in response to the current state of the order information being a state with the execution of a transaction, the ownership information of the first vehicle driving data is determined. Optionally, based on the predicted order information of the first vehicle driving data, this embodiment detects the current state of the order information. If the current state of the order information is detected to be a state with the execution of a transaction, the ownership information of the first vehicle driving data is determined, that is, the profit attribute of the supply object for the first vehicle driving data and the relationship between the supply objects are determined.
[0050] Optionally, if it is detected that the current state of the above order information is not a state where a transaction can be executed, the current state of the above order information is detected to be a state where a transaction can be executed, and then the ownership information of the first vehicle driving data is determined.
[0051] In steps S112 to S118 of this disclosure, when confirming the ownership of vehicle data, the current tag information of the purchaser regarding the demand data is determined. From the vehicle driving dataset, first vehicle driving data matching the current tag information is determined. The matched first vehicle driving data is input into the target order prediction model for prediction, obtaining order information for the first vehicle driving data. In response to the current state of the order information being a state with execution of transaction behavior, the ownership information of the first vehicle driving data is determined. Because in this embodiment, based on determining the current tag information of the purchaser regarding the demand data, vehicle driving data matching the category corresponding to the current tag information is determined from the vehicle driving dataset, and the matched vehicle driving data is input into the target order prediction model for prediction, order information including value attributes is obtained. Furthermore, when the current state of the order information is determined to be a state with execution of transaction behavior, the ownership information of the first vehicle driving data is determined. This achieves the goal of fully releasing the data value of the vehicle, thereby solving the technical problem of low utilization of vehicle data and realizing the technical effect of improving the utilization rate of vehicle data.
[0052] The method described in this embodiment will be further described below.
[0053] As an optional embodiment, step S114, determining the first vehicle driving data matching the current label information from the vehicle driving dataset, includes: calculating the similarity between the current label information and different label information from the vehicle driving dataset to obtain the initial label similarity between the current label information and different label information; determining the target label similarity from the initial label similarity between the current label information and different label information, wherein the target label similarity is greater than the initial label similarity between the current label information and different label information other than the target label similarity; and determining the first vehicle driving data matching the current label information based on the target label similarity.
[0054] In this embodiment, the similarity calculation is implemented based on any one of the following algorithms: cosine similarity algorithm, random forest algorithm, and support vector machine algorithm, etc. This is for illustrative purposes only and is not specifically limited.
[0055] In this embodiment, after determining the current tag information of the purchase target regarding the demand data, similarity calculations are performed on the current tag information and different tag information from the vehicle driving dataset to obtain the initial tag similarity between the current tag information and the different tag information. Optionally, this embodiment, based on determining the current tag information, performs similarity calculations on the current tag information and different tag information from the vehicle driving dataset to obtain the initial tag similarity between the current tag information and the different tag information, thereby achieving the purpose of determining tag similarity.
[0056] In this embodiment, the target label similarity is greater than the initial label similarity between the current label information and different label information, excluding the target label similarity.
[0057] In this embodiment, after calculating the similarity between the current label information and different label information from the vehicle driving dataset to obtain the initial label similarity between the current label information and different label information, the target label similarity is determined from multiple initial label similarities. Optionally, based on the obtained initial label similarities, this embodiment sorts the initial label similarities between the current label information and different label information, and selects the target label similarity from the sorted initial label similarities, thereby achieving the purpose of determining the target label similarity.
[0058] Optionally, the initial label similarities between the current label information and different label information are sorted in ascending order. The target label similarity is then selected from the sorted initial label similarities.
[0059] Optionally, the initial label similarities between the current label information and different label information are sorted in descending order. The target label similarity is then selected from the initial label similarities sorted in descending order.
[0060] In this embodiment, after determining the target label similarity from the initial label similarity between the current label information and different label information, the first vehicle driving data matching the current label information is determined based on the target label similarity. Optionally, this embodiment, based on determining the target label similarity, determines the vehicle driving data matching the current label information as the first vehicle driving data. For example, it determines the label information corresponding to the target label similarity, and then concentrates the vehicle driving data in the vehicle driving data set that satisfies the mapping relationship with the corresponding label information, and determines the vehicle driving data as the first vehicle driving data. This achieves the purpose of determining the first vehicle driving data, thereby improving the technical effect of matching driving data.
[0061] The method for determining the first vehicle driving data that matches the current label information based on the target label similarity described in this embodiment will be further explained below.
[0062] As an optional implementation method, determining the first vehicle driving data that matches the current label information based on the target label similarity includes: determining the label information corresponding to the target label similarity as the target label information; and determining the vehicle driving data that satisfies the mapping relationship with the target label information from the vehicle driving dataset as the first vehicle driving data.
[0063] In this embodiment, after determining the target label similarity from the initial label similarity between the current label information and different label information, the label information corresponding to the target label similarity is determined as the target label information. Optionally, this embodiment, based on determining the target label similarity, determines the label information corresponding to the target label similarity as the target label information. For example, if the category corresponding to the above-mentioned label information is the temperature fluctuation category, then the category corresponding to the target label information is the temperature fluctuation category, thereby achieving the purpose of determining the target label information.
[0064] In this embodiment, after determining the tag information corresponding to the target tag similarity as the target tag information, vehicle driving data that satisfies the mapping relationship with the target tag information from the vehicle driving dataset is determined as the first vehicle driving data. For example, if the category corresponding to the target tag information is the battery usage time category, then vehicle driving data that satisfies the mapping relationship with the target tag information representing the battery usage time category from the vehicle driving dataset is determined as the first vehicle driving data. This achieves the purpose of determining the first vehicle driving data, thereby realizing the technical effect of improving the matching accuracy of driving data.
[0065] The following description further explains the method for determining the ownership information of the first vehicle driving data in response to the current state of the order information being in a state of executing a transaction.
[0066] As an optional embodiment, step S118, in response to the current state of the order information being in a state of executing a transaction, determines the ownership information of the first vehicle driving data, including: in response to the current state being in a state of executing a transaction, verifying the identification information of the purchaser; in response to the identification information being verified, authorizing the purchaser, wherein the authorized purchaser is used to access the first vehicle driving data; and determining the ownership information during the process of authorizing the purchaser.
[0067] In this embodiment, the aforementioned identification information is used to identify the purchaser. For example, the identification information may be a transaction QR code for the purchaser's data on the first vehicle's driving conditions, or a transaction order number for the purchaser's data on the first vehicle's driving conditions, etc. This is merely an example and is not intended to be specific.
[0068] In this embodiment, after inputting the first vehicle driving data into the target order prediction model for prediction to obtain the order information of the first vehicle driving data, the identification information of the purchaser is verified in response to the current state being a state where a transaction can be executed. Optionally, based on the predicted order information of the first vehicle driving data, this embodiment detects the current state of the order information. If the current state of the order information is detected to be a state where a transaction can be executed, the identification information of the purchaser is verified, thereby achieving the purpose of determining whether the purchaser has completed the transaction of the first vehicle driving data.
[0069] In this embodiment, the authorization is implemented based on dynamic access authorization. Dynamic access authorization is an attribute encryption technology whereby the purchasing entity can only decrypt and obtain the first vehicle's driving data if preset conditions are met. Simultaneously, the purchasing entity's permission information regarding the first vehicle's driving data is embedded within the data, thereby automatically executing the authorization function for verified purchasing entities.
[0070] In this embodiment, after verifying the identification information of the purchase object in response to the current state being a state with the ability to perform a transaction, and in response to the identification information being verified, the purchase object is authorized to access the first vehicle driving data, thereby achieving the purpose of enabling the verified purchase object to access the first vehicle driving data.
[0071] Optionally, if the identification information of the purchaser fails to be verified, the identification information of the purchaser continues to be verified until it is verified, and then the purchaser is authorized.
[0072] In this embodiment, after enabling the purchaser to access the first vehicle driving data, ownership information is determined during the authorization process. Optionally, during the authorization process, this embodiment obtains the supply level of at least one supplier for the first vehicle driving data. Based on the supply level, the ownership information of the first vehicle driving data is determined, that is, the profit attribute of the supplier for the first vehicle driving data and the relationship between the suppliers are determined. This achieves the goal of fully releasing the data value of the vehicle and thus realizes the technical effect of improving the utilization rate of vehicle data.
[0073] The following description further explains the method for determining ownership information during the authorization process of the purchase object in this embodiment.
[0074] As an optional implementation method, in the process of authorizing the purchase object, determining the ownership information includes: in the process of authorizing the purchase object, obtaining the supply level of at least one supplier for the first vehicle driving data; determining the proportion information corresponding to the supply level; and dividing the order information according to the proportion information to obtain the ownership information.
[0075] In this embodiment, at least one supply object is at least one contributor, and the supply level refers to the degree of contribution of at least one contributor to the first vehicle driving data.
[0076] In this embodiment, during the authorization process for the purchase object, the supply level of at least one supplier for the first vehicle driving data is obtained. For example, the contribution level of at least one contributor to the first vehicle driving data is obtained, thereby achieving the goal of fully releasing the data value of the vehicle.
[0077] For example, if the contributors to the first vehicle's driving data include a first contributor and a second contributor, and the driving data contributed by the first contributor to the first vehicle's driving data is different from the driving data contributed by the second contributor to the first vehicle's driving data, then during the authorization process for the purchase object, the degree of contribution of the first contributor to the first vehicle's driving data and the degree of contribution of the second contributor to the first vehicle's driving data are obtained. This is just an example and is not specifically limited.
[0078] In this embodiment, the aforementioned proportion information is used to represent the profit share of at least one supplier based on the first vehicle driving data. For example, the aforementioned proportion information represents the profit share of at least one contributor based on the first vehicle driving data.
[0079] In this embodiment, during the authorization process for purchasing entities, after obtaining the supply level of at least one supplier for the first vehicle's driving data, the proportion information corresponding to the supply level is determined; according to the proportion information, the order information is divided to obtain ownership information. Optionally, based on the obtained supply level, this embodiment determines the proportion information corresponding to the obtained supply level; determines the value corresponding to the value attribute in the order information, calculates the difference between the value corresponding to the value attribute and the cost of the first vehicle's driving data, and the order information includes this difference; according to the determined proportion information, the obtained difference is divided to obtain the profit attribute of the supplier for the first vehicle's driving data, thereby achieving the goal of fully releasing the data value of the vehicle and thus realizing the technical effect of improving the utilization rate of vehicle data.
[0080] The following description further explains the method for updating the target order prediction model described above in this embodiment.
[0081] As an optional embodiment, the method further includes: in response to the fact that the output of the data model of the purchased object does not meet the preset result, collecting second vehicle driving data; using the second vehicle driving data to retrain the target order prediction model; and updating the target order prediction model to the retrained target order prediction model.
[0082] In this embodiment, the time of collection of the second vehicle driving data is later than the time of collection of the first vehicle driving data.
[0083] In this embodiment, the preset result is a preset threshold.
[0084] In this embodiment, in response to the fact that the output of the data model of the purchased object does not meet the preset result, second vehicle driving data is collected. Optionally, based on determining the output result of the data model of the purchased object, this embodiment judges the relationship between the output result and the preset result. If it is determined that the output result does not meet the preset result, second vehicle driving data is collected, thereby achieving the purpose of automatically triggering incremental data collection.
[0085] In this embodiment, after collecting second vehicle driving data in response to the fact that the output of the data model of the purchase object does not meet the preset result, the target order prediction model is retrained using the second vehicle driving data. The target order prediction model is then updated to the retrained target order prediction model, thereby achieving the purpose of updating the target order prediction model and thus realizing the technical effect of improving the accuracy of the data model.
[0086] The method for determining the current tag information of the purchaser regarding demand data in this embodiment will be further explained below.
[0087] As an optional embodiment, the method further includes: extracting demand data from the demand information of the purchasing object; determining the current tag information of the purchasing object regarding the demand data, including: parsing the tags of the demand data to obtain the current tag information.
[0088] In this embodiment, the aforementioned requirement information includes requirement data. For example, the requirement information is displayed in the form of a requirement form, which records the buyer's requirements for the application scenarios of vehicle driving data, the buyer's budget range for purchasing vehicle driving data, and the buyer's quality requirements for vehicle driving data, etc. This is for illustrative purposes only and is not a specific limitation.
[0089] In this embodiment, demand data is extracted from the demand information of the purchasing object. Optionally, based on the demand information of the purchasing object, this embodiment performs keyword extraction on the obtained demand information to obtain demand data, thereby achieving the purpose of determining the purchasing object's demand for vehicle driving data.
[0090] In this embodiment, after extracting demand data from the demand information of the purchaser, the demand data is tagged to obtain the current tag information, that is, to obtain the category to which the vehicle driving data associated with the application scenario belongs. This achieves the purpose of determining the current tag information, thereby realizing the technical effect of improving the accuracy of determining the demand of the purchaser.
[0091] The method for transmitting the first vehicle driving data described in this embodiment will be further explained below.
[0092] As an optional embodiment, the method further includes: encrypting the first vehicle driving data after authorizing the purchase object; and transmitting the encrypted first vehicle driving data to the purchase object's terminal or cloud for use in constructing the purchase object's data model.
[0093] In this embodiment, the encryption described above is, but is not limited to, homomorphic encryption.
[0094] Optionally, in this embodiment, after authorizing the purchaser, the obtained first vehicle driving data is encrypted, and the encrypted first vehicle driving data is transmitted to the purchaser's terminal or the cloud. If the user needs to use the first vehicle driving data, the first vehicle driving data is downloaded from the terminal or the cloud, then decrypted, and the decrypted first vehicle driving data is used to construct the purchaser's data model. This achieves the goal of enabling the purchaser to obtain the first vehicle driving data, thereby improving the technical effect of data transmission security.
[0095] The method for determining the vehicle driving data described in this embodiment will be further explained below.
[0096] As an optional embodiment, the method further includes: acquiring initial vehicle driving data; and standardizing the initial vehicle driving data to obtain vehicle driving data.
[0097] In this embodiment, the standardization process includes data preprocessing and desensitization, as well as standardized encapsulation. Data preprocessing and desensitization include format unification, desensitization (also known as privacy enhancement), and feature extraction. Standardized encapsulation is structured encapsulation, which means appropriately encapsulating different data using a unified standard. The encapsulated data includes: data version, encapsulation time, feature fields (e.g., numeric or tagged types), and digital signature.
[0098] Optionally, this embodiment first acquires initial vehicle driving data from different vehicles, and then performs format unification processing on the acquired initial vehicle driving data. The format-unified initial vehicle driving data is then de-identified. Feature extraction is performed on the de-identified initial vehicle driving data. The feature-extracted initial vehicle driving data is then structured and encapsulated to obtain vehicle driving data, thereby achieving the goal of acquiring different vehicle driving data and thus realizing the technical effect of improving the richness of vehicle driving data.
[0099] In this embodiment, when determining ownership of vehicle data, the current tag information of the buyer regarding demand data is determined. From the vehicle driving dataset, first vehicle driving data matching the aforementioned current tag information is identified. This matched first vehicle driving data is input into a target order prediction model for prediction, yielding order information for the first vehicle driving data. Furthermore, in response to the current state of the order information being a state where a transaction can be executed, the ownership information of the first vehicle driving data is determined. Because in this embodiment, based on determining the buyer's current tag information regarding demand data, vehicle driving data matching the category is identified from the vehicle driving dataset, and this matching vehicle driving data is input into the target order prediction model for prediction, resulting in order information including value attributes, and in determining that the current state of the order information is a state where a transaction can be executed, the ownership information of the first vehicle driving data is determined, thereby achieving the goal of fully releasing the value of vehicle data and solving the technical problem of low vehicle data utilization, thus realizing the technical effect of improving vehicle data utilization.
[0100] The technical solutions of the present disclosure embodiments are illustrated below with reference to preferred embodiments.
[0101] Currently, vehicles generate a large amount of high-value data during operation. However, the sharing and trading of this data often suffers from issues such as data silos, privacy leaks, and unclear rights allocation, which prevents the full realization of the data's value and leads to the technical problem of low utilization rate of vehicle data.
[0102] However, in this embodiment, a data element-based vehicle data element ownership confirmation system is used to determine the profit attributes of the supply objects for the first vehicle's driving data and the relationships between the supply objects when the current state of the order information is determined to be a state where a transaction can be executed. For example, Figure 2(a) is a schematic diagram of a data element-based vehicle data element ownership confirmation system according to an embodiment of this disclosure. As shown in Figure 2(a), the data element-based vehicle data element ownership confirmation system 200 includes: a data element generation component 201, a transaction matching and pricing component 202, and a trusted transmission and ownership confirmation component 203.
[0103] In this embodiment, the data element generation component 201 is used to preprocess, desensitize, and model features of raw data from multiple sources to form standardized, high-value-density data components, thereby achieving decoupling of data from application scenarios.
[0104] The aforementioned multi-source raw data includes: data collected by vehicle-mounted sensors and user behavior logs, etc.
[0105] The preprocessing of the above data includes: the aggregation of raw data from multiple sources, such as integrating heterogeneous data sources such as data collected by vehicle sensors, user behavior logs, and charging piles, and using data extraction, transformation and loading (ETL) tools to unify the format of the integrated heterogeneous data sources.
[0106] The desensitization of the aforementioned data includes: data privacy enhancement processing, such as using anonymization algorithms to generalize direct identifiers (e.g., license plate numbers) and using differential privacy to protect trajectory data.
[0107] The feature modeling of the above data includes: extracting high-value feature fields through machine learning algorithms, such as driving behavior risk scores and battery health prediction values.
[0108] The aforementioned data element generation component 201 essentially acts as an "intermediate state" connecting the data supply and demand sides, preserving the value density of data elements while mitigating the risk of privacy leaks. For example, in a smart city scenario, after desensitizing and extracting features from raw data generated in the traffic environment, standardized data elements (e.g., but not limited to: congestion index models and carbon emission feature labels) are generated. These standardized data elements can be directly used for cross-departmental collaborative decision-making without exposing the details of the original data.
[0109] In this embodiment, the transaction matching and pricing component 202 is used to support intelligent pricing and efficient circulation of data elements through data fields (e.g., supply and demand matching platforms) and data networks (e.g., data networks based on cross-domain data protocols), thereby realizing the release of the economic value of data elements. The transaction matching and pricing component 202 is used to achieve precise supply and demand matching through a multimodal algorithm engine. For example, the transaction matching and pricing component 202 is used to parse buyer demand tags (e.g., "new energy vehicle battery health prediction tag"), extract keywords (e.g., "charging frequency" and "temperature fluctuation characteristics"), map the extracted keywords to the feature tag library of data elements, and combine a deep semantic matching model trained with historical transaction data. Using a cosine similarity algorithm, it calculates the matching degree between buyer demand tags and data element tags, prioritizing the recommendation of elements with high similarity.
[0110] In addition, the transaction matching and pricing component 202 introduces a reinforcement learning mechanism, thereby dynamically optimizing the recommendation strategy based on buyer feedback (e.g., clicks, purchases, and reviews) to improve the success rate of recommendations to buyers.
[0111] For example, the process begins by acquiring published demands, such as a buyer submitting a demand form that includes at least one of the following: application scenario, budget range, and data quality requirements. Next, a candidate set is filtered, for example, the platform uses a rules engine to filter out compliant components. Then, bidding and negotiation take place, supporting open bidding or one-on-one negotiation, with smart contracts automatically generating the best offer. Finally, transactions are completed in real time through in-memory matching technology, and the transaction is recorded and stored on the blockchain.
[0112] In this embodiment, the intelligent pricing of the aforementioned data elements is calculated using a pricing model. This pricing model is constructed based on standardized feature fields of the data elements and considers the following dimensions: Data quality dimension: The price of each data element is dynamically adjusted based on the completeness, accuracy, and timeliness of the feature fields. Data entropy pricing is also introduced; that is, the information density of the data element is calculated using an information entropy algorithm. The higher the entropy value, the higher the information density of the data element, and the higher the corresponding price. Usage intensity dimension: A tiered pricing strategy is set. For example, the Application Programming Interface (API) for logistics route optimization is charged based on the number of calls to encourage high-frequency use, and a subscription model is adopted, such as the buyer paying a basic access fee and revenue sharing based on performance. Scenario value dimension: Based on a game theory model, the expected differences in data value between supply and demand are analyzed, and an equilibrium price is automatically negotiated through smart contracts. Finally, a reference market method is used to compare transaction cases of similar data and adjust the premium rate of the data elements based on supply and demand.
[0113] If the accuracy of the model reported after the buyer requests the purchased data components is lower than a preset threshold, incremental data collection and feature retraining are automatically triggered to update the data components. The updated data components are then used to update the pricing model.
[0114] In this embodiment, the aforementioned trusted transmission and ownership confirmation component 203 is used to complete the secure transmission and ownership confirmation of data elements in a trusted data space based on blockchain and privacy computing, thereby achieving the purpose of ensuring that data elements are available but invisible, as well as controllable and measurable.
[0115] Optionally, the secure transmission of the aforementioned data elements includes: identity trust and access control, which is implemented through the following.
[0116] Decentralized identity verification, combined with blockchain, assigns unique identifiers to all parties involved in data transactions (e.g., car manufacturers, insurance companies, and platforms) and performs "controlled anonymity" verification.
[0117] Dynamic access authorization is based on attribute encryption technology. If it is determined that the buyer must meet the preset conditions, the data element is decrypted for the buyer. The permission tag is embedded in the data element, and the smart contract automatically executes the authorization logic for the buyer who meets the preset conditions.
[0118] Optionally, the secure transmission of the aforementioned data elements includes: secure data transmission and evidence storage, which is achieved through the following methods.
[0119] Encrypted transmission employs homomorphic encryption to transmit data elements in ciphertext, supporting computation in ciphertext mode and ensuring that "data is usable but not visible".
[0120] Blockchain-based evidence storage ensures that key information such as transaction hashes, component fingerprints, and timestamps are uploaded to the blockchain in real time, resulting in minimal timestamp errors and supporting full-process traceability.
[0121] Trusted data space technology constructs a distributed "data sandbox" where buyers can access data elements through a virtual view, and the original data does not leave the supplier's environment, thereby preventing the spread of lateral permissions for data elements.
[0122] Optionally, the ownership confirmation of the aforementioned data element is achieved through the following steps.
[0123] By separating information from data, ownership of data resources can be determined.
[0124] Adopting the principle of separation, the ownership of data elements is converged to the model developer and the operating unit, and both parties share the right to process and use the data elements.
[0125] After the buyer obtains the data components, they process them into end products such as risk control models. The operating rights belong to a single entity, achieving a simplified ownership structure of "N→2→1". When trading data components, ownership certificates are automatically generated, recording the profit-sharing ratio of contributors (e.g., data source developers and model developers), supporting profit sharing based on performance. Furthermore, a cross-chain protocol connects the car company's private chain with the public trading chain, thereby synchronizing and updating ownership information.
[0126] The data element-based vehicle data element ownership system is implemented through the following settings.
[0127] Setting 1 involves configuring secure hardware that supports homomorphic encryption and federated learning, with low latency for single-field encryption.
[0128] Option 2 employs the Practical Byzantine Fault Tolerance (PBFT) algorithm, achieving low consensus latency and supporting a scale of thousands of nodes.
[0129] Setting 3, based on the integrated batch and stream architecture, enables dynamic desensitization and access control of data elements.
[0130] Fourthly, a closed-loop verification mechanism is implemented. For example, the integrity of data elements is verified through a hash algorithm. If the characteristic fingerprint is found to be inconsistent with the on-chain record, the arbitration process is automatically triggered.
[0131] Setting five addresses ownership disputes, for example by establishing an on-chain arbitration pool where a third-party institution can quickly adjudicate disputes based on stored evidence.
[0132] In this embodiment, a data element-based vehicle data element ownership determination method is executed. If the current state of the order information is determined to be a state where a transaction can be executed, the profit attribute of the supply object for the first vehicle's driving data, and the relationship between each supply object, are determined. For example, Figure 2(b) is a flowchart of a data element-based vehicle data element ownership determination method according to an embodiment of this disclosure. As shown in Figure 2(b), the method includes the following steps.
[0133] Step S211: Generate data elements.
[0134] After generating the data element, proceed to step S212 to determine the data element that matches the current tag information and generate the order information for the matching data element.
[0135] After generating order information for matching data elements, proceed to step S213 to perform trusted transmission of the data elements and determine the ownership information of the matching data elements.
[0136] Figure 3 is a schematic diagram of data interaction between a vehicle and a server according to an embodiment of the present disclosure. As shown in Figure 3, the vehicle 300 uploads initial vehicle driving data to the server 301. The server 301 performs standardization processing on the initial vehicle driving data to obtain vehicle driving data and sends the vehicle driving data back to the vehicle 300.
[0137] In this embodiment, when determining ownership of vehicle data, the current tag information of the buyer regarding demand data is determined. From the vehicle driving dataset, the first vehicle driving data matching the current tag information is identified. This matched first vehicle driving data is input into the target order prediction model for prediction, resulting in order information for the first vehicle driving data. Given that the current state of the order information indicates a transaction execution status, the ownership information of the first vehicle driving data is determined. Because this embodiment, based on determining the buyer's current tag information regarding demand data, identifies vehicle driving data matching the category from the vehicle driving dataset, inputs this matching vehicle driving data into the target order prediction model for prediction, obtains order information including value attributes, and determines the ownership information of the first vehicle driving data when the current state of the order information indicates a transaction execution status, the purpose of fully releasing the value of vehicle data is achieved, thereby solving the technical problem of low vehicle data utilization and realizing the technical effect of improving vehicle data utilization.
[0138] According to another aspect of the present disclosure, corresponding to the embodiments of the vehicle data ownership confirmation method described above, the present disclosure also provides a vehicle data ownership confirmation device. FIG4 is a structural block diagram of a vehicle data ownership confirmation device according to an embodiment of the present disclosure. As shown in FIG4, the vehicle data ownership confirmation device 400 includes: a first determining component 402, a second determining component 404, a predicting component 406, and a third determining component 408.
[0139] The first determining component 402 is used to determine the current tag information of the purchase object regarding the demand data, wherein the demand data is used to represent vehicle driving data associated with the application scenario, and the current tag information is used to represent the category to which the vehicle driving data belongs.
[0140] The second determining component 404 is used to determine, from the vehicle driving dataset, first vehicle driving data that matches the current label information, wherein the vehicle driving dataset includes mapping relationships between different label information and different vehicle driving data, and the first vehicle driving data is used to represent vehicle driving data that matches the category.
[0141] The prediction component 406 is used to input the first vehicle driving data into the target order prediction model for prediction to obtain the order information of the first vehicle driving data, wherein the order information includes at least the value attribute of the first vehicle driving data displayed to the purchaser.
[0142] The third determining component 408 is used to determine the ownership information of the first vehicle driving data in response to the current state of the order information being a state of having a transaction to be executed. The ownership information includes at least the profit attribute of the supply object for the first vehicle driving data. The supply object is used to provide different vehicle driving data to the vehicle driving dataset.
[0143] Optionally, the second determining component 404 includes: a calculation component, used to calculate the similarity between the current label information and different label information from the vehicle driving dataset to obtain the initial label similarity between the current label information and the different label information; a first determining component, used to determine the target label similarity from the initial label similarity between the current label information and the different label information, wherein the target label similarity is greater than the initial label similarity between the current label information and the different label information other than the target label similarity; and a second determining component, used to determine the first vehicle driving data that matches the current label information based on the target label similarity.
[0144] Optionally, the second determining component includes: a first determining sub-component, used to determine the label information corresponding to the target label similarity, which is the target label information; and a second determining sub-component, used to determine the vehicle driving data that satisfies the mapping relationship with the target label information from the vehicle driving dataset as the first vehicle driving data.
[0145] Optionally, the third determining component 408 includes: a verification component, used to verify the identification information of the purchase object in response to the current state being a state with the ability to perform a transaction, wherein the identification information is used to identify the purchase object; an authorization component, used to authorize the purchase object in response to the identification information being verified, wherein the authorized purchase object is used to access the first vehicle driving data; and a third determining component, used to determine ownership information during the authorization process for the purchase object.
[0146] Optionally, the third determining component includes: an acquisition sub-component, used to acquire the supply level of at least one supplier for the first vehicle driving data during the authorization process of the purchaser; a third determining sub-component, used to determine the proportion information corresponding to the supply level, wherein the proportion information is used to represent the profit proportion of at least one supplier for the first vehicle driving data; and a division sub-component, used to divide the order information according to the proportion information to obtain ownership information.
[0147] Optionally, the vehicle data ownership confirmation device 400 further includes: a collection component, used to collect second vehicle driving data in response to the result output by the data model of the purchased object not meeting the preset result, wherein the collection time of the second vehicle driving data is later than the collection time of the first vehicle driving data; a retraining component, used to retrain the target order prediction model using the second vehicle driving data; and an update component, used to update the target order prediction model to the retrained target order prediction model.
[0148] Optionally, the vehicle data ownership confirmation device 400 further includes: an extraction component for extracting demand data from the demand information of the purchaser, wherein the demand information includes demand data; and a first determining component for: a fourth determining component for parsing the demand data to obtain current tag information.
[0149] Optionally, the vehicle data ownership confirmation device 400 further includes: an encryption component for encrypting the first vehicle driving data after authorizing the purchaser; and a transmission component for transmitting the encrypted first vehicle driving data to the purchaser's terminal or cloud for constructing the purchaser's data model.
[0150] Optionally, the vehicle data ownership confirmation device 400 further includes: an acquisition component for acquiring initial vehicle driving data; and a processing component for standardizing the initial vehicle driving data to obtain vehicle driving data.
[0151] In this embodiment, a first determining component determines the current tag information of the purchaser regarding demand data, where demand data represents vehicle driving data associated with an application scenario, and the current tag information represents the category to which the vehicle driving data belongs. A second determining component determines first vehicle driving data matching the current tag information from the vehicle driving dataset, where the vehicle driving dataset includes mapping relationships between different tag information and different vehicle driving data, and the first vehicle driving data represents vehicle driving data matching the category. A prediction component inputs the first vehicle driving data into a target order prediction model for prediction to obtain order information for the first vehicle driving data, where the order information includes at least the value attribute of the first vehicle driving data presented to the purchaser. A third determining component, in response to the current state of the order information being a state of executing a transaction, determines the ownership information of the first vehicle driving data, where the ownership information includes at least the profit attribute of the supply object for the first vehicle driving data, and the supply object is used to provide different vehicle driving data to the vehicle driving dataset. This achieves the goal of fully releasing the data value of vehicles, thereby solving the technical problem of low utilization of vehicle data and realizing the technical effect of improving the utilization rate of vehicle data.
[0152] According to another aspect of embodiments of the present disclosure, a processor is also provided. The processor is used to run a program, wherein the program, when run by the processor, performs the methods described in various embodiments of the present disclosure.
[0153] Embodiments of this disclosure also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this disclosure when it runs.
[0154] Embodiments of this disclosure also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium resides to perform the methods of the various embodiments of this disclosure.
[0155] Embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.
[0156] Embodiments of this disclosure also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods described in various embodiments of this disclosure.
[0157] Embodiments of this disclosure also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this disclosure.
[0158] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0159] In the several embodiments provided in this disclosure, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are illustrative; for example, the division of components is a logical functional division, and in actual implementation, there may be other division methods, such as multiple components being combined or integrated into another system, or some features being ignored or not executed. Furthermore, the shown or discussed mutual couplings, direct couplings, or communication connections are through some interfaces; the indirect couplings or communication connections between components are electrical or other forms.
[0160] The components described as separate parts may or may not be physically separate. The parts shown as components may or may not be physical components; that is, they may be located in one place or distributed across multiple components. Some or all of the components are selected according to actual needs to achieve the purpose of this embodiment.
[0161] Furthermore, in the various embodiments of this disclosure, the functional components are integrated into a single processing component, or each component exists physically separately, or two or more components are integrated into one component. The integrated components are implemented either in hardware or as software functional components.
[0162] If the integrated components are implemented as software functional components and sold or used as independent products, they are stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, is embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media for storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0163] The above description represents the preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure. Industrial applicability
[0164] This disclosure provides a vehicle control method. When confirming ownership of vehicle data, the method determines the current tag information of the buyer regarding demand data, identifies first vehicle driving data matching the current tag information from the vehicle driving dataset, inputs the matching first vehicle driving data into a target order prediction model for prediction, obtains order information for the first vehicle driving data, and determines the ownership information of the first vehicle driving data in response to the current state of the order information being a state with execution of transaction behavior. Because this disclosure, based on determining the current tag information of the buyer regarding demand data, identifies vehicle driving data matching the category from the vehicle driving dataset, inputs the matching vehicle driving data into the target order prediction model for prediction, obtains order information including value attributes, and determines the ownership information of the first vehicle driving data when the current state of the order information is determined to be a state with execution of transaction behavior, it achieves the goal of fully releasing the data value of the vehicle, thereby solving the technical problem of low vehicle data utilization and realizing the technical effect of improving the utilization rate of vehicle data.
Claims
1. A method for confirming vehicle data ownership, comprising: Determine the current tag information of the purchase target regarding the demand data, wherein the demand data is used to represent vehicle driving data associated with the application scenario, and the current tag information is used to represent the category to which the vehicle driving data belongs; From the vehicle driving dataset, a first vehicle driving data matching the current label information is determined, wherein the vehicle driving dataset includes a mapping relationship between different label information and different vehicle driving data, and the first vehicle driving data is used to represent driving data matching the category; The first vehicle driving data is input into the target order prediction model for prediction to obtain the order information of the first vehicle driving data, wherein the order information includes at least the value attributes of the first vehicle driving data displayed to the purchaser. In response to the current state of the order information being a state of executing a transaction, the ownership information of the first vehicle driving data is determined, wherein the ownership information includes at least the profit attribute of the supply object for the first vehicle driving data, and the supply object is used to provide different vehicle driving data to the vehicle driving dataset.
2. The method according to claim 1, wherein, Determining the first vehicle driving data that matches the current label information from the vehicle driving dataset includes: From the vehicle driving dataset, the similarity between the current label information and different label information is calculated to obtain the initial label similarity between the current label information and different label information; A target label similarity is determined from the initial label similarity between the current label information and different label information, wherein the target label similarity is greater than the initial label similarity between the current label information and different label information, excluding the target label similarity. Based on the target label similarity, the first vehicle driving data that matches the current label information is determined.
3. The method according to claim 2, wherein, Based on the target label similarity, the first vehicle driving data matching the current label information is determined, including: The tag information corresponding to the target tag similarity is determined as the target tag information; From the vehicle driving dataset, the vehicle driving data that satisfies the mapping relationship with the target label information is determined as the first vehicle driving data.
4. The method according to claim 1, wherein, In response to the current state of the order information being a state of having executed the transaction, the ownership information of the first vehicle driving data is determined, including: In response to the current state being the state of performing the transaction, the identification information of the purchase object is verified, wherein the identification information is used to identify the purchase object; In response to the successful verification of the identification information, the purchase object is authorized, wherein the authorized purchase object is used to access the first vehicle driving data; During the authorization process for the purchased object, the ownership information is determined.
5. The method according to claim 4, wherein, During the authorization process for the purchase object, determining the ownership information includes: During the authorization process for the purchase object, the supply level of at least one of the supply objects for the first vehicle driving data is obtained; Determine the proportion information corresponding to the supply level, wherein the proportion information is used to represent the profit ratio of at least one of the supply objects for the first vehicle driving data; The order information is divided according to the aforementioned proportion information to obtain the ownership information.
6. The method according to claim 4, wherein, After authorizing the purchase object, the method further includes: The driving data of the first vehicle is encrypted; The encrypted first vehicle driving data is transmitted to the terminal or cloud corresponding to the authorized purchase object, wherein the first vehicle driving data is used to construct the data model of the authorized purchase object.
7. The method according to claim 1, wherein, The method further includes: In response to the fact that the result output by the data model of the purchased object does not meet the preset result, second vehicle driving data is collected, wherein the time of collection of the second vehicle driving data is later than the time of collection of the first vehicle driving data. The target order prediction model is retrained using the second vehicle's driving data; The target order prediction model is updated to the retrained target order prediction model.
8. The method according to any one of claims 1 to 7, wherein, Determine the current tag information of the purchasing target regarding their demand data, including: The required data is parsed to obtain the current tag information.
9. The method according to claim 8, wherein, The method further includes: Extract the demand data from the demand information of the purchasing object, wherein the demand information includes at least one of the following: The purchasing entity's needs for the application scenarios of the vehicle driving data; The budget range of the purchaser for purchasing the vehicle driving data; The purchaser has specific quality requirements for the vehicle driving data.
10. The method according to claim 9, wherein, Extracting the demand data from the demand information of the purchasing object includes: Keyword extraction is performed on the demand information to obtain the demand data.
11. The method according to any one of claims 1 to 7, wherein, The method further includes: Acquire initial vehicle driving data from different vehicles respectively; The initial vehicle driving data is then processed to standardize its format. The initial vehicle driving data, after being formatted and standardized, is then anonymized. Feature extraction is performed on the initial vehicle driving data after the anonymization process; The initial vehicle driving data after feature extraction is structured and encapsulated to obtain the vehicle driving data.
12. The method according to any one of claims 1 to 7, wherein, The first vehicle's driving data is input into the target order prediction model for prediction, and the order information of the first vehicle's driving data is obtained, including: The first vehicle driving data is input into the prediction layer of the target order prediction model for prediction to obtain the order information of the first vehicle driving data; The order information of the first vehicle's driving data is output through the output layer of the target order prediction model.
13. The method according to any one of claims 1 to 7, wherein, The target order prediction model is an order prediction model built on a three-dimensional pricing model, which integrates data quality dimension, usage intensity dimension and scenario value dimension.
14. A processor for running a program, wherein, The program is executed by the processor to perform the data ownership confirmation method for the vehicle according to any one of claims 1 to 13.
15. A vehicle comprising: Memory, which stores executable programs; A processor for running the program, wherein the program executes the data ownership confirmation method for the vehicle according to any one of claims 1 to 13.
16. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the data ownership method for the vehicle according to any one of claims 1 to 13.
