Data element service effect dynamic allocation method and system based on vehicle pile network scene

Abstract

The invention relates to the technical field of data distribution and optimization, in particular to a data element service effect dynamic distribution method and system based on a vehicle pile network scene, and the method comprises the steps: carrying out the static distribution of service effects, and determining a static distribution proportion; according to a principle of data element service effect market distribution of a'vehicle-pile-network 'scene, dynamically calculating contribution degrees of data providers in multiple subjects; implementing a dynamic allocation mechanism, and dynamically calculating the data quality of the data provider; calculating a data element service effect dynamic allocation proportion based on the business characteristics and the data characteristics; the distribution weight is dynamically adjusted by monitoring the contribution degree and quality of data in real time, fair and efficient benefit distribution is ensured, and a data provider is stimulated to continuously optimize the data quality. And through multi-agent cooperation, the utilization efficiency of data resources is improved, and healthy development of a vehicle-pile-network ecological system is promoted. Meanwhile, the block chain technology enhances the transparency and credibility of the distribution process, and ensures the fairness and reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of data allocation and optimization, and in particular to a method and system for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario. Background Art

[0002] When studying the dynamic allocation method and system of data element service effectiveness based on the vehicle-pile network scenario, the market allocation mechanism of data element service effectiveness faces many challenges, especially how to scientifically and reasonably evaluate and dynamically allocate the multi-dimensional value of data elements, which has become an urgent problem to be solved.

[0003] Traditional data distribution models are often limited to single-dimensional considerations such as data volume and data quality, ignoring key value dimensions such as the reliability of data sources, the timeliness of data circulation, the frequency of data use, and the time window. This limitation not only restricts the efficient operation of the data factor market, but also makes it difficult to meet the complex and changing market distribution needs in the vehicle-charging pile network scenario. This scenario involves the close linkage of vehicles, charging piles, and energy networks, and puts forward higher requirements for the real-time, accuracy, and multi-party collaboration of data elements.

[0004] The current technology for market-based distribution of data element value mainly includes distribution according to work, distribution according to production factors, profit distribution, and distribution based on experience negotiation. By summarizing and analyzing the advantages and disadvantages of each distribution method, distribution according to work can motivate work enthusiasm, but it is difficult to accurately measure the contributions of multiple parties; distribution according to production factors can reflect the contribution of factors, but there are challenges in data ownership and value assessment; profit distribution is conducive to reflecting the overall business results, but it cannot accurately reflect the contribution of each data element; distribution based on experience negotiation focuses on negotiation and flexibility, but is easily affected by information asymmetry and conflicts of interest, and it is difficult to ensure the fairness and justice of distribution.

[0005] In summary, the method and system for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario need to solve the following technical problems:

[0006] (1) Existing methods lack consideration of dynamic changes in data

[0007] Traditional allocation methods are often based on static data, while ignoring the dynamic changes of data and the evolution of its value over time. In the "car-pile-network" scenario, data flows rapidly, and its value may change rapidly with factors such as market demand, technological development, and policy adjustments. Therefore, static allocation methods cannot accurately reflect the true value and dynamic changes of data elements, resulting in deviations and unreasonable allocation results. An allocation method that can accurately reflect the value and dynamic changes of data elements is needed to support the optimal configuration and efficient use of data resources.

[0008] (2) Existing methods lack flexibility and adaptability

[0009] In the complex and ever-changing "car-pile-network" scenario, different entities have diverse demands and contributions for data, and these demands and contributions may change over time and in different scenarios. However, traditional allocation methods often use fixed allocation ratios or patterns, which cannot be flexibly adjusted according to actual conditions, resulting in unfair and unreasonable allocation results. A method that can be flexibly adjusted according to the actual conditions of different entities is needed to ensure that the interests of all parties are fairly and reasonably protected.

[0010] (3) Existing methods lack transparency and credibility

[0011] In the data factor market, fair, transparent and efficient allocation is the key to maintaining market order and protecting the interests of all parties. However, traditional allocation methods often lack open and transparent allocation rules and processes, resulting in unfair and unreliable allocation results. This will not only harm the interests of all parties, but also affect the healthy development of the market. An allocation method that can flexibly adapt to the needs and contributions of different entities is needed to ensure market fairness and transparency.

[0012] By solving the above-mentioned technical problems, this patent aims to provide a method and system for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario, so as to achieve fair, transparent and efficient allocation of data value in the vehicle-pile network scenario. Summary of the invention

[0013] In view of the above problems existing in the prior art, the present invention is proposed.

[0014] Therefore, the technical problem to be solved by the present invention is: fully consider the special properties of data elements, such as non-entity, reproducibility, non-competitiveness and weak exclusivity, as well as the data element service effectiveness allocation technology with the characteristics of value co-creation among multiple subjects in the "car-pile-network" scenario. This technology needs to be able to accurately measure the contributions and needs of all parties in data resources, and achieve fair, transparent and efficient allocation. At the same time, it also needs to have sufficient flexibility and scalability to adapt to the continuous changes and development of the future data element market.

[0015] To solve the above technical problems, the present invention provides the following technical solutions, a method for dynamic allocation of data element service effectiveness based on the vehicle-pile-network scenario, including: static allocation of service effectiveness and determination of the static allocation ratio; dynamically calculating the contribution of data providers among multiple subjects according to the principle of market allocation of data element service effectiveness in the "vehicle-pile-network" scenario; implementing a dynamic allocation mechanism and dynamically calculating the data quality of data providers; and calculating the dynamic allocation ratio of data element service effectiveness based on business characteristics and data characteristics.

[0016] As a preferred solution of the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario described in the present invention, the static allocation includes the overall optimal principle, the individual rational principle and the effectiveness principle;

[0017] The overall optimal principle is expressed as:

[0018]

[0019] Where N represents the number of providers, V(N) represents the revenue generated by data providers when using federated learning technology for joint research; I i It represents the revenue generated when the data provider develops the training data model independently, and i represents the data provider;

[0020] The individual rationality principle is expressed as

[0021] P i ≥I i

[0022] Among them, P i It represents the income obtained by data provider i from the joint research of data product application;

[0023] The validity principle is expressed as:

[0024]

[0025] As a preferred solution of the method for dynamically allocating the effectiveness of data element services based on the vehicle-pile-network scenario described in the present invention, the dynamic calculation of the contribution of data providers in multiple subjects includes calculating the shapely values ​​of the three model features of vehicle, pile and network and weighted summing of the shapley values ​​of the three model features of vehicle, pile and network;

[0026] The shapely values ​​of the three model features of the calculation vehicle, pile and network are expressed as:

[0027]

[0028] Among them, g represents the explanation model, M represents the number of input features, z represents the existence state of the corresponding feature, and z′ represents the existence status of the feature. represents the attributed value of the feature, represents a constant, z′j represents the existence of the jth feature;

[0029] For sample x, all features exist, expressed as:

[0030]

[0031] The weighted sum of the Shapley values ​​of the three model features of vehicle, pile and network is expressed as:

[0032]

[0033] Where S represents the subset of features used in the model, x represents the vector of feature values ​​of the samples to be explained, and x j represents the feature vector of feature j, x p represents the feature vector of the pth feature, p represents the number of features, v(S) represents the model output value under the feature combination S, p! represents that there are p! combinations of p features, |S|! (p-|S|-1)! represents a fixed feature j, {x1,...x p}\{x j} means not including {x j}, there are (p-|S|-1)S! combinations left. represents the weight of subset S.

[0034] As a preferred solution of the method for dynamically allocating the effectiveness of data element services based on the vehicle-pile network scenario described in the present invention, the dynamic allocation mechanism includes the ability to capture and quantify any changes in data quality and dynamically adjust the income distribution weight of the data provider;

[0035] The dynamic adjustment of the profit distribution weight of the data provider reflects the actual proportion of the data quality of the participant in the overall contribution.

[0036] As a preferred solution of the method for dynamic allocation of data element service effectiveness based on the vehicle-pile network scenario described in the present invention, the dynamic calculation of the data quality of the data provider includes the calculation of data accuracy, data completeness, data timeliness, data uniqueness and data accessibility.

[0037] As a preferred solution of the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario described in the present invention, wherein: the calculation of the dynamic allocation ratio of data element service effectiveness includes setting weights, calculating weighted averages, and calculating the dynamic allocation ratio of data provider service effectiveness;

[0038] The setting weight is expressed as:

[0039] Accuracy q1 = 30%

[0040] Integrity q2 = 25%

[0041] Timeliness q3 = 20%

[0042] Uniqueness q4 = 15%

[0043] Accessibility q5 = 10%.

[0044] As a preferred solution of the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario described in the present invention, the weighted average value is expressed as:

[0045] q avg =q1*30%+q2*25%+q3*20%+q4*15%+q5*10%

[0046] Among them, q avg represents the average data quality score;

[0047] The dynamic allocation ratio of the service effectiveness of the data provider is expressed as:

[0048] W vertical =q vertical / q avg

[0049] Among them, W vertical represents the distribution ratio of new energy electric vehicle service effectiveness, q vertical represents the data quality score of the car company, q avg Indicates the average data quality score of data providers;

[0050] W station =q station / q avg

[0051] Among them, W station represents the distribution ratio of charging pile enterprise service effectiveness, q station represents the data quality score of the pile enterprise, q avg Indicates the average data quality score of data providers;

[0052] W power =q power / q avg

[0053] Among them, W power represents the distribution ratio of charging pile enterprise service effectiveness, q power represents the data quality score of the pile enterprise, q avg Indicates the average data quality score of data providers.

[0054] Another object of the present invention is to provide a dynamic distribution system for data element service effectiveness based on the vehicle-pile network scenario. The system can monitor the contribution and data quality of the data subject in real time, and dynamically adjust the benefit distribution weight based on this, thereby ensuring that the interests of each data subject are synchronized with their data output, promoting continuous optimization of data quality, and achieving fair, transparent and efficient distribution.

[0055] In order to solve the above technical problems, the present invention provides the following technical solutions: a data element service effectiveness dynamic allocation system based on a vehicle-pile network scenario, comprising: a static allocation module, a contribution calculation module, a data quality assessment module and a dynamic allocation calculation module;

[0056] The static allocation module performs static allocation of service results and determines the static allocation ratio;

[0057] The contribution calculation module dynamically calculates the contribution of data providers among multiple entities based on the principle of market allocation of data element service effectiveness in the "car-pile-network" scenario;

[0058] The data quality assessment module implements a dynamic allocation mechanism to dynamically calculate the data quality of the data provider;

[0059] The dynamic allocation calculation module calculates the dynamic allocation ratio of data element service effectiveness based on business characteristics and data characteristics.

[0060] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as described above are implemented.

[0061] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario as described above are implemented.

[0062] Beneficial effects of the invention: This patent proposes a method and system for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario. Compared with the traditional static allocation mode, the innovative technology of dynamically allocating data element service effectiveness in this method and system shows significant advantages and has achieved significant improvements in many aspects. Compared with the existing technology, this patent has the following advantages:

[0063] (1) Real-time dynamic adjustment to ensure fairness and efficiency

[0064] This patent monitors the contribution and data quality of data subjects in real time, and dynamically adjusts the benefit distribution weights, ensuring that the contribution of each data subject throughout the life cycle of the data product is reasonably and fairly recognized. This dynamic adjustment mechanism not only improves the transparency of the distribution, but also effectively avoids the unfair distribution problem caused by the traditional static distribution model's inability to adapt to changes in data quality, ensuring the fairness and efficiency of data services. By dynamically adjusting the distribution weights, this technology can quickly respond to the impact of market changes, technological development, policy adjustments and other factors on the value of data elements, ensuring the rationality and effectiveness of benefit distribution.

[0065] (2) Promote continuous optimization of data quality

[0066] The dynamic allocation mechanism not only focuses on the contribution of a single data subject, but also emphasizes the collaboration among multiple subjects. By clarifying the roles and responsibilities of each data provider in the development, operation and allocation of data products, the technology promotes information sharing and collaboration among participants. This collaboration not only improves the utilization efficiency of data resources, but also promotes the healthy development and collaborative innovation of the entire "car-pile-network" ecosystem.

[0067] The implementation of the dynamic allocation mechanism has greatly motivated data providers to continuously optimize data quality. In order to obtain more profit distribution weights, data providers will pay more attention to the accuracy, completeness, timeliness, uniqueness and accessibility of data, thereby continuously improving data quality. This positive incentive mechanism not only improves the overall performance of data products, but also promotes the healthy development of the entire data ecosystem.

[0068] (3) The application of blockchain technology enhances credibility

[0069] Incorporating static and dynamic allocation ratios into the China Southern Power Grid blockchain ensures fairness and transparency in the distribution of multi-subject data element service performance. The immutability and traceability of blockchain technology make the distribution results more fair and credible, and enhance the confidence and credibility of market participants. This technological integration not only improves the reliability of the allocation mechanism, but also sets an example for the standardized development of the data element market. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0071] Figure 1 A flowchart of a method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario provided for one embodiment of the present invention.

[0072] Figure 2 A dynamic allocation diagram of data element service effectiveness based on a "car-pile-network" scenario, which is a method for dynamically allocating data element service effectiveness based on a car-pile-network scenario provided by one embodiment of the present invention.

[0073] Figure 3 A diagram of the steps for statically allocating data element service effectiveness based on a "car-pile-network" scenario, which is a method for dynamically allocating data element service effectiveness based on a car-pile-network scenario provided by one embodiment of the present invention.

[0074] Figure 4 A diagram of the steps for dynamically allocating data element service effectiveness based on a "car-pile-network" scenario, which is a method for dynamically allocating data element service effectiveness based on a car-pile-network scenario provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0076] Example 1, reference Figure 1 , is an embodiment of the present invention, which provides a method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario, including:

[0077] S1: Statically allocate service effectiveness and determine the static allocation ratio.

[0078] It should be noted that static allocation includes the overall optimal principle, the individual rational principle, and the effectiveness principle;

[0079] The overall optimal principle is that when the data provider is isolated and cannot be centralized, the federated learning technology is used to train the model. The income generated by the alliance is not less than the sum of the income when the data subject trains the data model alone and each data subject independently develops the data product, which is expressed as:

[0080]

[0081] Where N represents the number of providers, V(N) represents the revenue generated by data providers when using federated learning technology for joint research; I i It represents the revenue generated when the data provider develops the training data model independently, and i represents the data provider;

[0082] The principle of individual rationality is that when data providers jointly develop data products, the benefits ultimately allocated to each cooperating data subject should not be less than the benefits generated by their independent research and development, which can be expressed as:

[0083] P i ≥I i

[0084] Among them, P i It represents the income obtained by data provider i from the joint research of data product application;

[0085] The principle of effectiveness is that data products in the "car-pile-network" scenario are sold to data demanders such as insurance companies through the data circulation transaction sharing system of the data operator. The income generated by the data alliance needs to be distributed to all members of the relevant parties, expressed as:

[0086]

[0087] S2: Based on the principle of market allocation of data element service effectiveness in the "car-pile-network" scenario, the contribution of data providers among multiple entities is dynamically calculated.

[0088] It should be noted that the contribution of the data provider in the dynamic calculation of multiple agents includes calculating the shapely value of the three model features of the car, pile, and network and the weighted sum of the shapley values ​​of the three model features of the car, pile, and network;

[0089] The shapely values ​​of the three model features of the calculation vehicle, pile and network are expressed as:

[0090]

[0091] Among them, g represents the explanation model, M represents the number of input features, z represents the existence state of the corresponding feature, and z' represents the existence status of the feature. represents the attributed value of the feature, represents a constant, z' j Indicates the existence of the jth feature;

[0092] Furthermore, since the input of the model is structured data, for sample x, all features exist, expressed as:

[0093]

[0094] Furthermore, since the features of the model are not independent of each other, the combination of features in different orders and numbers may have a huge impact on the final model deduction results. Therefore, it is necessary to calculate the Shapley value for all possible feature groups (including different orders) and then weighted sum them. Assuming that the model has p features x1, x2, x3...x p , then the weighted sum of the Shapley values ​​of the three model features of vehicle, pile and network is expressed as:

[0095]

[0096] Where S represents the subset of features used in the model, x represents the vector of feature values ​​of the samples to be explained, and x j represents the feature vector of feature j, x prepresents the feature vector of the pth feature, p represents the number of features, v(S) represents the model output value under the feature combination S, p! represents that there are p! combinations of p features, |S|! (p-|S|-1)! represents a fixed feature j, {x1,...x p}\{x j} means not including {x j}, there are (p-|S|-1)S! combinations left. represents the weight of subset S.

[0097] S3: Implement a dynamic allocation mechanism to dynamically calculate the data quality of data providers.

[0098] It should be noted that the dynamic allocation mechanism includes the ability to capture and quantify any improvement in data quality and dynamically adjust the revenue distribution weight of data providers;

[0099] The dynamic adjustment of the profit distribution weight of the data provider reflects the actual proportion of the data quality of the participant in the overall contribution.

[0100] Furthermore, dynamically calculating the data quality of the data provider includes calculating data accuracy, data completeness, data timeliness, data uniqueness, and data accessibility;

[0101] Data accuracy can be verified through regular data verification mechanisms, by comparing historical data or third-party data sources, using data cleaning tools or writing scripts to detect and correct abnormal data, and by comparing the difference between actual values ​​and recorded values, calculating errors and accuracy;

[0102] Among them, calculation error: error = |actual value - recorded value|; calculation accuracy: accuracy = (1-error / actual value)*100%;

[0103] The pseudo code is:

[0104] Actual value = Get actual charging times ()

[0105] Record value = Get record charging times ()

[0106] Error = abs(actual value - recorded value)

[0107] Accuracy = (1-error / actual value)*100

[0108] Data integrity: Check whether data records are complete through database query statements or data integrity verification tools, set data integrity constraints, such as non-null constraints and unique constraints, to ensure data integrity. By checking whether data records are complete, calculate the missing rate and completeness rate;

[0109] Among them, the missing rate is calculated as follows: missing rate = (number of records to be recorded - actual number of records) / number of records to be recorded; the completeness rate is calculated as follows: completeness rate = 1 - missing rate;

[0110] The pseudo code is:

[0111] Number of charging piles to be recorded = Get the number of charging pile locations to be recorded ()

[0112] Actual number of records = Get the actual number of charging pile locations recorded ()

[0113] Missing rate = (number of records to be recorded - actual number of records) / number of records to be recorded

[0114] Completeness rate = 1-missing rate

[0115] Data timeliness: Set a timestamp field to record the generation and update time of data. Regularly check the update time of data and compare it with the ideal update time to ensure the timeliness of data. Evaluate the timeliness by comparing the time interval between data generation and update with the expected time interval.

[0116] Wherein, the delay time is calculated as follows: delay time = actual update time interval - expected update time interval;

[0117] The pseudo code is:

[0118] ActualUpdateInterval = GetActualDataUpdateInterval()

[0119] ExpectedUpdateInterval = GetExpectedDataUpdateInterval()

[0120] Delay time = actual update interval - expected update interval

[0121] If the delay time <= service tolerance delay range:

[0122] Timely effectiveness

[0123] otherwise:

[0124] Invalid time limit

[0125] Data uniqueness: perform data deduplication before data is stored in the database to ensure data uniqueness. When designing the database table, set unique constraints to prevent the insertion of duplicate data. Calculate the duplication rate by checking whether there are duplicate items in the data records.

[0126] Among them, the number of duplicates is calculated as follows: number of duplicates = total number of records - number of records after deduplication; the repetition rate is calculated as follows: repetition rate = number of duplicates / total number of records

[0127] The pseudo code is:

[0128] Total number of records = Get data record number ()

[0129] Number of records after deduplication = Number of records after deduplication of data records ()

[0130] Number of duplicates = total number of records - number of records after deduplication

[0131] Duplicate rate = number of duplicates / total number of records

[0132] Data accessibility: Improve data accessibility by monitoring the running status of API services, recording service unavailable time, calculating availability, setting up redundant services and load balancing;

[0133] Among them, calculate availability: Availability = (total time - unavailable time) / total time

[0134] The pseudo code is:

[0135] Total time = Get total monitoring time ()

[0136] UnavailableTime = GetServiceUnavailableTime()

[0137] Availability = (total time - unavailable time) / total time

[0138] S4: Calculate the dynamic allocation ratio of data element service effectiveness based on business characteristics and data characteristics.

[0139] It should be noted that the calculation of the dynamic allocation ratio of data element service effectiveness includes setting weights, calculating weighted averages, and calculating the dynamic allocation ratio of data provider service effectiveness;

[0140] The setting weight is expressed as:

[0141] Accuracy q1 = 30%

[0142] Integrity q2 = 25%

[0143] Timeliness q3 = 20%

[0144] Uniqueness q4 = 15%

[0145] Accessibility q5 = 10%;

[0146] Specifically, due to the real-time interactivity and high decision-making dependence of data, accuracy is given a weight of 30%, because inaccurate data may lead to wrong decisions; completeness is given a weight of 25% to ensure comprehensive data coverage and avoid the reliability of overall analysis affected by missing data; timeliness accounts for 20%, emphasizing that in a dynamically changing market environment, timely updating of data is crucial for rapid response and optimization of strategies; uniqueness accounts for 15% of the weight to prevent analysis bias caused by duplicate data, especially in big data analysis, data deduplication is the key to ensuring the effectiveness of analysis results; accessibility accounts for only 10%, ensuring that all relevant parties can obtain the required data efficiently and without obstacles is the basis for promoting information flow and collaboration.

[0147] Furthermore, the scores of each indicator are multiplied by the corresponding weights and then summed to obtain the average data quality score q avg , then the weighted average is calculated as:

[0148] q avg =q1*30%+q2*25%+q3*20%+q4*15%+q5*10%

[0149] Among them, q avg represents the average data quality score;

[0150] Divide the data quality score of each data provider by the average data quality score to get their respective proportions. The dynamic distribution ratio of the data provider's service effectiveness is calculated as follows:

[0151] W vertical =q vertical / q avg

[0152] Among them, W vertical represents the distribution ratio of new energy electric vehicle service effectiveness, q vertical represents the data quality score of the car company, q avg Indicates the average data quality score of data providers;

[0153] W station =q station / q avg

[0154] Among them, w station represents the distribution ratio of charging pile enterprise service effectiveness, q station represents the data quality score of the pile enterprise, q avg Indicates the average data quality score of data providers;

[0155] W power =q power / q avg

[0156] Among them, W power represents the distribution ratio of charging pile enterprise service effectiveness, q power represents the data quality score of the pile enterprise, q avg Indicates the average data quality score of data providers.

[0157] The above is a schematic scheme of a method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario in this embodiment. It should be noted that the technical scheme of the system for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario and the technical scheme of the method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario mentioned above belong to the same concept. For details not described in detail in the technical scheme of the system for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario in this embodiment, please refer to the description of the technical scheme of the method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario mentioned above.

[0158] The data element service effectiveness dynamic allocation system based on the vehicle-pile network scenario in this embodiment is characterized by: comprising: a static allocation module, a contribution calculation module, a data quality assessment module and a dynamic allocation calculation module;

[0159] The static allocation module performs static allocation of service results and determines the static allocation ratio;

[0160] The contribution calculation module dynamically calculates the contribution of data providers among multiple entities based on the principle of market allocation of data element service effectiveness in the "car-pile-network" scenario;

[0161] The data quality assessment module implements a dynamic allocation mechanism to dynamically calculate the data quality of the data provider;

[0162] The dynamic allocation calculation module calculates the dynamic allocation ratio of data element service effectiveness based on business characteristics and data characteristics.

[0163] This embodiment further provides a computing device, which is applicable to the case of a method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario, including:

[0164] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the dynamic allocation method of data element service effectiveness based on the vehicle-pile network scenario as proposed in the above embodiment.

[0165] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as proposed in the above embodiment is implemented.

[0166] The storage medium proposed in this embodiment and the method for dynamic allocation of data element service effectiveness based on the vehicle-pile network scenario proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0167] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0168] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0169] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0170] Example 2, reference Figure 2-Figure 4This is an embodiment of the present invention. This embodiment provides a method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0171] In the design and operation of the data product "Electricity Insurance Pricing Assistant", we focus on clarifying the static profit distribution ratio between data providers and data operators from the development and commissioning stage to ensure that the initial contributions of each participant are reasonably recognized. At the same time, to ensure long-term fairness and efficiency, we have also implemented a dynamic allocation mechanism that can sensitively capture changes in data quality and adjust the profit distribution weights accordingly. Regardless of whether it is a static or dynamic allocation ratio, we will incorporate it into the Southern Power Grid blockchain to ensure that the data element service results of multiple subjects are distributed fairly and transparently, thereby promoting the healthy development and collaborative innovation of the entire data ecosystem (such as Figure 2 shown).

[0172] In combination with the needs of the real-world scenarios of "car-pile-network", a data service effectiveness market allocation indicator system is established to provide a quantitative effectiveness allocation model for calculating the contribution of data service effectiveness and output the allocation results. Based on the results of the quantitative evaluation of the effectiveness value of the data elements that can be allocated at a time, combined with the data quality and federal contribution of the data resource providers in the "Electric Insurance Pricing Assistant", the Shapley value of each data provider is calculated, and on the basis of comprehensive consideration of the reasonable interests and contributions of the data operators, a fair dynamic allocation ratio or weight is established to ensure that the benefits are fairly distributed to each participant according to their contribution.

[0173] Considering the importance and contribution of each data subject, it is necessary to establish a corresponding weight distribution scheme. The scheme considers the distribution of effectiveness value from two levels: data operators and data providers. According to the proportion of the input cost of the data operator to the overall data product input, the service effectiveness distribution weight of the Yunnan Energy Big Data Center (data operator) is calculated (e.g. Figure 3 shown).

[0174] After deducting the necessary operating costs and profits of the data operator, the three entities of the data provider are calculated according to the contribution of the data. Since the data provider is composed of three parties, namely, the car company, the charging pile company, and Yunnan Power Grid Co., Ltd., the federated learning training model is based on the data of the three entities and the insurance company (data demander) makes a decision. Therefore, when distributing the value of service effectiveness, the distribution weights of different data entities must be considered separately. In view of the fluctuation of data quality of each entity, it may have a direct impact on the performance and effect of the data product, and thus cause the problem of uneven distribution of benefits. Therefore, when designing the market-oriented distribution mechanism of data services, the dynamic monitoring and evaluation of data quality must be taken into consideration (such as Figure 4shown).

[0175] According to the calculation and determination of the static allocation ratio and the dynamic allocation ratio, the dynamic allocation ratio of the data element service effectiveness in a specific scenario ("car-pile-network") can be calculated. When the data service is called, the system dynamically distributes the effectiveness value to the data provider according to the allocation ratio to ensure fair and transparent cooperation among data providers. The following is a table of experimental simulation data of the allocation ratio, see Table 1 for details:

[0176] Table 1 Experimental simulation data table of allocation ratio

[0177]

[0178]

[0179] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario, characterized in that: include: Statically allocate service results and determine the static allocation ratio; According to the principle of market distribution of data element service effectiveness in the "car-pile-network" scenario, the contribution of data providers among multiple entities is dynamically calculated; Implement a dynamic allocation mechanism to dynamically calculate the data quality of data providers; Based on business characteristics and data characteristics, the dynamic allocation ratio of data element service effectiveness is calculated.

2. The method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as claimed in claim 1, characterized in that: The static allocation includes the overall optimal principle, the individual rational principle and the effectiveness principle; The overall optimal principle is expressed as: Where N represents the number of providers, V(N) represents the revenue generated by the data provider when the federated learning technology is used for joint research; I represents the revenue generated by the data provider when the data provider develops the training data model independently, and i represents the data provider; The individual rationality principle is expressed as: P i ≥I i Among them, P i It represents the income obtained by data provider i from the joint research of data product application; The validity principle is expressed as:

3. The method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as claimed in claim 2, characterized in that: The dynamic calculation of the contribution of the data provider in the multi-agent includes calculating the shapely value of the three model features of the car, pile and network and weighted summing of the shapley values ​​of the three model features of the car, pile and network; The shapely values ​​of the three model features of the calculation vehicle, pile and network are expressed as: Among them, g represents the explanation model, M represents the number of input features, z represents the existence state of the corresponding feature, and z' represents the existence status of the feature. represents the attributed value of the feature, represents a constant, z' j Indicates the existence of the jth feature; For sample x, all features exist, expressed as: The weighted sum of the Shapley values ​​of the three model features of vehicle, pile and network is expressed as: Where S represents the subset of features used in the model, x represents the vector of feature values ​​of the samples to be explained, and x j represents the feature vector of feature j, x p represents the feature vector of the pth feature, p represents the number of features, v(S) represents the model output value under the feature combination S, p! represents that there are p! combinations of p features, |S|! (p-|S|-1)! represents a fixed feature j, {x1,...x p }\{x j } means not including {x j }, there are (p-|S|-1)S! combinations left. represents the weight of subset S.

4. The method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as claimed in claim 3 is characterized by: The dynamic allocation mechanism includes the ability to capture and quantify any improvement in data quality and dynamically adjust the revenue allocation weight of the data provider; The dynamic adjustment of the profit distribution weight of the data provider reflects the actual proportion of the data quality of the participant in the overall contribution.

5. The method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as claimed in claim 4 is characterized by: The dynamic calculation of the data quality of the data provider includes calculating data accuracy, data completeness, data timeliness, data uniqueness and data accessibility.

6. The method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario as claimed in claim 5, characterized in that: The calculation of the dynamic allocation ratio of the service effectiveness of data elements includes setting weights, calculating weighted averages, and calculating the dynamic allocation ratio of the service effectiveness of data providers; The setting weight is expressed as: Accuracy q1 = 30% Integrity q2 = 25% Timeliness q3 = 20% Uniqueness q4 = 15% Accessibility q5 = 10%.

7. The method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario according to claim 6 is characterized by: The calculated weighted average is expressed as: <h2 style=";text-align:left;direction:ltr">q<h2 style=";text-align:left;direction:ltr"> avg <h2 style=";text-align:left;direction:ltr"> =q1*30%+q2*25%+q3*20%+q4*15%+q5*10% Among them, q avg represents the average data quality score; The dynamic allocation ratio of the service effectiveness of the data provider is expressed as: W vertical =q vertical / q avg Among them, W vetical represents the distribution ratio of new energy electric vehicle service effectiveness, q vertical represents the data quality score of the car company, q avg Indicates the average data quality score of data providers; W station =q station / q avg Among them, W station represents the distribution ratio of charging pile enterprise service effectiveness, q station represents the data quality score of the pile enterprise, q avg Indicates the average data quality score of data providers; W power =q power / q avg Among them, W power represents the distribution ratio of charging pile enterprise service effectiveness, q power represents the data quality score of the pile enterprise, q avg Indicates the average data quality score of data providers.

8. A system based on the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario according to any one of claims 1 to 7, characterized in that: include: Static allocation module, contribution calculation module, data quality assessment module and dynamic allocation calculation module; The static allocation module performs static allocation of service results and determines the static allocation ratio; The contribution calculation module dynamically calculates the contribution of data providers among multiple entities based on the principle of market allocation of data element service effectiveness in the "car-pile-network" scenario; The data quality assessment module implements a dynamic allocation mechanism to dynamically calculate the data quality of the data provider; The dynamic allocation calculation module calculates the dynamic allocation ratio of data element service effectiveness based on business characteristics and data characteristics.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for dynamically allocating data element service effectiveness based on the vehicle-pile network scenario described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for dynamically allocating data element service effectiveness based on a vehicle-pile network scenario according to any one of claims 1 to 7 are implemented.

Images