Value contribution degree calculation method and system based on data contribution

Abstract

The invention relates to the technical field of data processing, and provides a value contribution degree calculation method and system based on data contribution, and the method comprises the steps: obtaining a data set provided by a plurality of data service providers, determining the affiliation condition of all data records in the data set, obtaining an affiliation subset of each data record, the method comprises the following steps: acquiring data records, classifying the corresponding data records, distributing a corresponding weight value for each data category, calculating a data contribution weighted sum value of each data service provider in the category to which the data service provider belongs, summarizing the data contribution weighted sum values of all the data service providers to obtain a total weight value, and calculating the contribution degree of each data service provider. According to the method, data contribution degree evaluation of multiple data service providers is achieved through attribution subset analysis, classification processing and weight value distribution rules of a data set, and the problems that in data transaction in which the multiple data service providers jointly participate, data items are overlapped, weight division is lacked, and accurate quantification cannot be conducted according to actual contribution are solved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method and system for calculating the value contribution degree based on data contribution. Background Art

[0002] With the rapid development of the data economy, data trading has gradually become an important means to promote economic growth. In modern data trading models, multiple data service providers provide services to data demanders through joint computing. This model is widely used in multiple fields such as healthcare, finance, and e-commerce. Through data integration and computing, the accuracy of services and the utilization efficiency of data have been improved, becoming an important part of the current data economy.

[0003] In related technical means, the value contribution degree of data contribution is mainly calculated by simple data statistical methods. Specifically, a statistical model based on the number of data entries is adopted to count the number of data entries provided by each data service provider, and based on this, the value contribution of each service provider is directly calculated to achieve value distribution and reflect the contribution of each service provider in data trading.

[0004] Regarding the above technical solution, although the distribution of data value in the joint computing scenario can be achieved through the statistical method based on the number of data entries, in data trading participated by multiple data service providers, there are overlapping data entries. Since the unique data and common data cannot be effectively distinguished, there are problems that the actual contribution of data service providers cannot be accurately quantified during the calculation of the value contribution degree, and the weight division of multi-party common data lacks a scientific basis, which cannot meet the requirements of fairness and transparency in complex data trading scenarios. Summary of the Invention

[0005] In order to improve the situation where there are overlapping data entries, lack of weight division, and failure to accurately quantify according to the actual contribution in data trading participated by multiple data service providers, this application provides a method and system for calculating the value contribution degree based on data contribution.

[0006] The present invention provides a method for calculating value contribution degree based on data contribution, which is applied to a joint calculation scenario involving multiple data service providers in data trading. The method includes the following steps: obtaining data sets provided by multiple data service providers, and determining the ownership of all data records in the data sets to obtain the ownership subset of each data record; classifying the corresponding data records according to the number of data service providers in the ownership subset to obtain multiple data categories, and assigning corresponding weight values to each data category according to a preset weight value assignment rule; calculating the weighted sum value of the data contribution of each data service provider in the data category to which it belongs based on the weight value, and summing up the weighted sum values of the data contributions of all data service providers to obtain the total weight value; calculating the contribution degree of each data service provider based on the total weight value, and outputting the contribution degree result of each data service provider.

[0007] As a preferred solution, the number of data service providers is the number of data service providers who hold the corresponding data records at the same time; the classifying the corresponding data records according to the number of data service providers in the ownership subset includes the following steps: classifying the data records held only by a single data service provider into the exclusive data category; classifying the data records held by two data service providers into the two-party shared data category; classifying the data records held by x data service providers into the x-party shared data category, where x≥2.

[0008] As a preferred solution, the weight value assignment rule is: The number of data service providers included in the ownership subset corresponding to each data category is inversely proportional to the assigned weight value.

[0009] As a preferred solution, the calculation formula for calculating the weighted sum value of the data contribution of each data service provider in the data category to which it belongs based on the weight value is as follows: Where represents the weighted sum value of data service provider , represents the number of data records in the category data records, represents the weight value of the category, is the total number of data categories.

[0010] As a preferred solution, the calculation formula for summing up the weighted sum values of the data contributions of all data service providers to obtain the total weight value is: Where is the total weight value in the joint calculation, represents the The weighted sum of the data service providers, The total number of service providers participating in the federation.

[0011] As a preferred solution, the calculation formula for calculating the contribution of each data service provider based on the total weight value is: in, Indicates The contribution of each data service provider, Indicates The weighted sum of the data service providers, is the total weight value in the joint calculation.

[0012] The present application also provides a value contribution calculation system based on data contribution, including: an acquisition unit, used to acquire a data set provided by multiple data service providers, and determine the attribution of all data records in the data set to obtain an attribution subset for each data record; a classification unit, used to classify the corresponding data records according to the number of data service providers in the attribution subset to obtain multiple data categories, and assign a corresponding weight value to each data category according to a preset weight value assignment rule; a first calculation unit, used to calculate the weighted sum of the data contributions of each data service provider in the category to which it belongs based on the weight value, and summarize the weighted sum of the data contributions of all data service providers to obtain a total weight value; a second calculation unit, used to calculate the contribution of each data service provider based on the total weight value, and output the contribution result of each data service provider.

[0013] Compared with the prior art, the present application has the following beneficial effects: accurate quantification. Through the technical means of the attributed subset analysis, classification processing and weight value allocation rules of the data set, the evaluation of data contribution in the joint computing scenario of multiple data service providers is realized, and then by classifying the unique data and shared data and assigning differentiated weights, the fairness and transparency of the contribution calculation are ensured, and the problem of overlapping data items, lack of weight division, and failure to accurately quantify according to actual contributions in data transactions involving multiple data service providers is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] The structures, proportions, sizes, etc. shown in the accompanying drawings of this specification are only used to cooperate with the content disclosed in the specification for those familiar with this technology to understand and read, and are not used to limit the conditions for the implementation of the present invention. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0016] Figure 1 It is a schematic flowchart of a method for calculating value contribution degree based on data contribution provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of the structure of a system for calculating value contribution degree based on data contribution provided by an embodiment of the present invention.

[0017] Explanation of reference numerals: 10. System for calculating value contribution degree based on data contribution; 11. Acquisition unit; 12. Classification unit; 13. First calculation unit; 14. Second calculation unit. Detailed implementation manners

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] The flowchart shown in the accompanying drawings is only an example, and does not necessarily include all contents and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0020] It should also be understood that the terms used in this specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0021] It should be further understood that the term " / and" as used in this specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0022] Next, the technical solutions of the present invention will be further described in conjunction with the accompanying drawings and through specific implementation manners.

[0023] Example 1: As Figure 1 shown, this application provides a method for calculating value contribution degree based on data contribution, which is applied to a joint calculation scenario involving multiple data service providers in data trading. The method includes the following steps S100 to S400.

[0024] Step S100: Obtain the data sets provided by multiple data service providers, and determine the ownership of all data records in the data sets to obtain the ownership subset of each data record.

[0025] In this step, obtain the original data sets provided by each data service provider separately, and merge the multiple data sets to form a joint data set. Specifically, by analyzing the identifier or specific field of each data record, match the data service provider to which it belongs, determine the ownership relationship of the data record, and generate the corresponding ownership subset for each data record, where the ownership subset reflects the set of one or more data service providers to which the data record belongs.

[0026] For example, in a certain joint calculation scenario, the data record R1 only belongs to the data service provider A, and its ownership subset is {A}; the data record R2 belongs to the data service providers A and B, and its ownership subset is {A, B}; the data record R3 belongs to the data service providers A, B, and C, and its ownership subset is {A, B, C}.

[0027] Step S200: Classify the corresponding data records according to the number of data service providers in the ownership subset to obtain multiple data categories, and assign corresponding weight values to each data category according to the preset weight value assignment rules.

[0028] In this step, classify the data records according to the number of data service providers included in the ownership subset of each data record. Specifically, classify the data records whose ownership subset contains only one data service provider into the unique data category; classify the data records whose ownership subset contains two data service providers into the two-party common data category; classify the data records whose ownership subset contains x data service providers into the x-party common data category (where x≥2). Further, according to the preset weight value assignment rules, assign different weight values to each data category.

[0029] For example, the weight value of the unique data category is W1, the weight value of the two-party common data category is W2, and the weight value of the x-party common data category is Wx, where W1>W2>Wx.

[0030] Step S300: Based on the weight values, calculate the weighted sum of data contributions of each data service provider in its respective data category, and aggregate the weighted sums of data contributions of all data service providers to obtain the total weight value.

[0031] In this step, for each data service provider, calculate the weighted sum of its data contributions according to the number of data records in each data category it belongs to and the weight value of that data category.

[0032] For example, the number of unique data of data service provider A is 50, and the weight value is W1 = 1.0; the number of data shared by two parties is 30, and the weight value is W2 = 0.7; the number of data shared by three parties is 20, and the weight value is W3 = 0.4. Then the weighted sum of A's data contributions is . Aggregate the weighted sum values of all data service providers to obtain the total weight value T.

[0033] Step S400: Based on the total weight value, calculate the contribution degree of each data service provider, and output the contribution degree results of each data service provider.

[0034] In this step, based on the weighted sum of data contributions of each data service provider calculated in Step S300 and the total weight value, calculate the contribution degree of each data service provider.

[0035] For example, assume the total weight value is 200, and the weighted sum value of a certain data service provider is 76. Then the contribution degree of this service provider is . Finally, output the contribution degree results of each data service provider.

[0036] In this embodiment, by obtaining data sets provided by multiple data service providers and determining the attribution of all data records in the data sets, the attribution subset of each data record is obtained. Then, according to the number of data service providers in the attribution subset, the corresponding data records are classified to obtain multiple data categories, and a corresponding weight value is assigned to each data category according to a preset weight value assignment rule. Next, based on the assigned weight value, the weighted sum of the data contribution of each data service provider in the data category to which it belongs is calculated, and the weighted sum of the data contribution of all data service providers is summarized to obtain a total weight value. Finally, based on the total weight value, the contribution of each data service provider is calculated, and the contribution result of each data service provider is output. By analyzing and classifying the attribution subset of the data set, combined with the preset weight value assignment rule, a scientific quantitative evaluation of the data contribution of each data service provider is achieved. Compared with the existing technology, this solution can more accurately reflect the different contributions of unique data and shared data to the joint computing value, effectively solve the problem of unfair contribution calculation caused by data overlap in the existing technology, and improve the situation in which data items overlap in data transactions involving multiple data service providers, lack of weight division, and fail to accurately quantify according to actual contributions.

[0037] Embodiment 2: The number of data service providers is the number of data service providers that simultaneously hold corresponding data records.

[0038] According to the number of data service providers in the belonging subset, classifying the corresponding data records includes the following steps: classifying data records held by only a single data service provider into a unique data category.

[0039] By analyzing the belonging subset of each data record in the data set, it is determined whether the belonging subset contains only one data service provider. Specifically, all data records in the data set are traversed, and for each data record, the number of elements in its belonging subset is checked. If the belonging subset contains only one data service provider, the data record is classified as a unique data category.

[0040] For example, the belonging subset of data record R1 is {A}, which means that the data record only belongs to data service provider A, so R1 is classified as a unique data category. The belonging subset of data record R2 is {B}, which means that the data record only belongs to data service provider B, and is also classified as a unique data category.

[0041] Data records held by two data service providers are classified as data shared by both parties.

[0042] By analyzing the belonging subsets of each data record in the data set, it is determined whether the belonging subset contains two data service providers. Specifically, all data records in the data set are traversed, and for each data record, the number of elements in its belonging subset is checked. If the belonging subset contains two data service providers, the data record is classified into the two-party shared data category.

[0043] For example, the belonging subset of data record R3 is {A, B}, indicating that this data record is jointly held by data service provider A and data service provider B. Therefore, R3 is classified into the two-party shared data category. The belonging subset of data record R4 is {C, D}, indicating that this data record is jointly held by data service provider C and data service provider D, and is also classified into the two-party shared data category.

[0044] Data records held by x data service providers are classified into the x-party shared data category, where x ≥ 2.

[0045] By analyzing the belonging subsets of each data record in the data set, it is determined whether the belonging subset contains x data service providers (where x ≥ 2). Specifically, all data records in the data set are traversed, and for each data record, the number of elements in its belonging subset is checked. If the belonging subset contains x data service providers, the data record is classified into the x-party shared data category.

[0046] For example, the belonging subset of data record R5 is {A, B, C}, indicating that this data record is jointly held by data service providers A, B, and C. Therefore, R5 is classified into the three-party shared data category. The belonging subset of data record R6 is {A, B, C, D}, indicating that this data record is jointly held by data service providers A, B, C, and D. Therefore, R6 is classified into the four-party shared data category.

[0047] Among them, the weight value allocation rule is: the number of data service providers contained in the belonging subset corresponding to each data category is inversely proportional to the allocated weight value.

[0048] By allocating weight values corresponding to data categories according to the number of elements in the belonging subset. Specifically, a preset weight value is allocated to each data category, and the size of the weight value is inversely proportional to the number of data service providers in the belonging subset. That is to say, the fewer the number of data service providers contained in the belonging subset, the higher the weight value.

[0049] For example, the weight value of the exclusive data category is W1 = 1.0; the weight value of the two-party shared data category is W2 = 0.7; the weight value of the three-party shared data category is W3 = 0.4; and so on. The more data service providers the belonging subset contains, the lower the weight value.

[0050] In step S300, based on the weight values, the calculation formula for the weighted sum value of the data contribution of each data service provider in its respective data category is as follows: Wherein, represents the weighted sum value of the data service provider , represents the number of data records in the category, represents the weight value of the category, is the total number of data categories.

[0051] By counting the data records of each data service provider and combining the weight values of the data categories, the weighted sum value of the data contribution is calculated.

[0052] For example, in the data of data service provider A, the number of unique data categories is 50, and the weight value is = 1.0; the number of data categories shared by two parties is 30, and the weight value is = 0.7; the number of data categories shared by three parties is 20, and the weight value is = 0.4. Then, the weighted sum value of the data contribution of data service provider A is: .

[0053] In step S300, by aggregating the weighted sum values of the data contributions of all data service providers, the calculation formula for the total weight value is: Wherein, is the total weight value in the joint calculation, represents the weighted sum value of the th data service provider, is the total number of service providers participating in the joint calculation.

[0054] By adding up the weighted sum values of the data contributions of all data service providers, the total weight value of the joint calculation is calculated.

[0055] For example, if the weighted sum values of the data contributions of data service providers A, B, and C are 76, 54, and 70 respectively, then the total weight value is: .

[0056] In step S400, based on the total weight value, the calculation formula for the contribution degree of each data service provider is: Wherein, represents the contribution degree of the th data service provider, Indicates The weighted sum of the data service providers, is the total weight value in the joint calculation.

[0057] The contribution of each data service provider is calculated by the ratio of the weighted sum value to the total weight value.

[0058] For example, if the weighted sum of data service provider A is 76 and the total weight is 200, then the contribution of A is: .

[0059] In this embodiment, an accurate quantitative assessment of the data contribution of multiple data service providers in a joint computing scenario is achieved. Based on the classification of unique data, data shared by two parties, and data shared by x parties, combined with the weight value allocation rules, the value contribution of each data category is scientifically calculated to ensure the fairness and transparency of the contribution assessment. This embodiment can effectively solve the problem of inaccurate contribution assessment caused by overlapping data records, is applicable to various joint computing scenarios (such as horizontal federation and vertical federated learning), provides an accurate and reliable value assessment mechanism for data transactions, and significantly improves the fairness and efficiency of joint computing.

[0060] Embodiment 3: like Figure 2 As shown, the present application also provides a value contribution calculation system 10 based on data contribution, including an acquisition unit 11, a classification unit 12, a first calculation unit 13 and a second calculation unit 14.

[0061] The acquisition unit 11 is mainly used to acquire data sets provided by multiple data service providers, and determine the ownership of all data records in the data sets to obtain the ownership subset of each data record.

[0062] The classification unit 12 is mainly used to classify the corresponding data records according to the number of data service providers in the belonging subset to obtain multiple data categories, and assign a corresponding weight value to each data category according to a preset weight value assignment rule.

[0063] The first calculation unit 13 is mainly used to calculate the weighted sum of data contributions of each data service provider in its category based on the weight value, and to summarize the weighted sum of data contributions of all data service providers to obtain a total weight value.

[0064] The second calculation unit 14 is mainly used to calculate the contribution of each data service provider based on the total weight value, and output the contribution result of each data service provider.

[0065] In this embodiment, through the collaborative operation of the acquisition unit 11, the classification unit 12, the first calculation unit 13, and the second calculation unit 14, a comprehensive, transparent, and efficient value contribution calculation system is provided, which can effectively solve the problem of inaccurate contribution calculation caused by data overlap in the joint calculation scenario of multiple data service providers. This system not only improves the fairness of data value distribution, but also provides reliable technical support for data transactions, and at the same time has good scalability, and can adapt to different joint calculation modes (such as horizontal federated learning, vertical federated learning) and various application scenarios.

[0066] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described system and each unit can refer to the corresponding processes in the foregoing embodiments of the value contribution calculation method based on data contribution, and will not be repeated here.

[0067] The above is the case. The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating value contribution based on data contribution, applied to a joint computing scenario involving multiple data service providers in data transactions, characterized in that: The method comprises the following steps: Obtain data sets provided by multiple data service providers, determine the ownership of all data records in the data sets, and obtain the ownership subset of each data record; According to the number of data service providers in the belonging subset, the corresponding data records are classified to obtain multiple data categories, and a corresponding weight value is assigned to each data category according to a preset weight value assignment rule; Based on the weight value, the weighted sum of the data contribution of each data service provider in the data category to which it belongs is calculated, and the weighted sum of the data contribution of all data service providers is summarized to obtain the total weight value; Based on the total weight value, the contribution of each data service provider is calculated, and the contribution result of each data service provider is output.

2. The value contribution calculation method based on data contribution according to claim 1 is characterized in that: in, The number of data service providers is the number of data service providers that simultaneously hold corresponding data records; and the classifying of corresponding data records according to the number of data service providers in the belonging subset includes the following steps: Classify data records held only by a single data service provider as unique data categories; Classify data records held by two data service providers as data shared by both parties; Data records held by x data service providers are classified as x-party common data, where x ≥ 2.

3. The value contribution calculation method based on data contribution according to claim 1 is characterized in that: The weight value allocation rule is: The number of data service providers included in the belonging subset corresponding to each data category is inversely proportional to the assigned weight value.

4. The value contribution calculation method based on data contribution according to claim 1 is characterized in that: The formula for calculating the weighted sum of data contributions of each data service provider in the corresponding data category based on the weight value is as follows: in, Indicates data service provider The weighted sum of Indicates The number of category data records, Indicates The weight of the category, is the total number of data categories.

5. The value contribution calculation method based on data contribution according to claim 1 is characterized in that: The calculation formula for summing up the weighted sum of data contributions of all data service providers to obtain the total weight value is: in, is the total weight value in the joint calculation, Indicates The weighted sum of the data service providers, is the total number of service providers participating in the federation.

6. The value contribution calculation method based on data contribution according to claim 1 is characterized in that: The calculation formula for calculating the contribution of each data service provider based on the total weight value is: in, Indicates The contribution of each data service provider, Indicates The weighted sum of the data service providers, is the total weight value in the joint calculation.

7. A value contribution calculation system based on data contribution, characterized in that: include: An acquisition unit, used to acquire data sets provided by multiple data service providers, and determine the ownership of all data records in the data sets to obtain the ownership subset of each data record; A classification unit, used to classify corresponding data records according to the number of data service providers in the belonging subset to obtain multiple data categories, and assign a corresponding weight value to each data category according to a preset weight value assignment rule; A first calculation unit is used to calculate the weighted sum of data contributions of each data service provider in the corresponding category based on the weight value, and to summarize the weighted sum of data contributions of all data service providers to obtain a total weight value; The second calculation unit is used to calculate the contribution of each data service provider based on the total weight value, and output the contribution result of each data service provider.

Images