Sample data processing method and device, equipment and medium

Abstract

The invention relates to the technical field of data analysis, in particular to a sample data processing method and device, electronic equipment and a storage medium. The method comprises the following steps: a first client extracts a preset number of first samples and corresponding sample IDs from a first database, binds the first samples according to a preset binning algorithm to obtain a first binning result, maps a first binning number into a second binning number according to a preset binning number mapping algorithm to obtain a second binning result, and sends the second binning result to the first client; and then sending the sorting index value, the sample id and the second box separation result to a second client, so that the second client calculates an evidence weight corresponding to each box number in the second box number, and then calculates a required information value according to the evidence weight. According to the method and the device, the sample data of the second client is sorted and accumulated through the sorting index value, so that the calculation efficiency of the WOE and the IV is improved on the premise of ensuring the data security.

Description

Technical Field

[0001] The present invention relates to the fields of data analysis technology, relationship network analysis technology and financial technology, and in particular to a sample data processing method, device, equipment and medium. Background Art

[0002] The credit scorecard model has a wide range of applications in the fields of credit risk assessment and financial risk control, including: data cleaning, grouping, screening and regrouping, correlation analysis, modeling, and outputting charts of evaluation models. In the modeling process, the information value (IV) indicator is usually used to reflect the degree of influence of a certain variable on the overdue rate (or default rate). Usually, the IV value is calculated based on the weight of evidence (WOE). The existing calculation method in the industry is that the variable label holder sends its own label data to the non-variable label holder after homomorphic encryption. The non-variable label holder counts the encrypted labels corresponding to each column of binned feature data, performs homomorphic addition, and sends it to the variable label holder. The variable label holder then decrypts it with a private key and sends it to the non-variable label holder.

[0003] However, when the data volume is large, the above solution needs to count the encrypted labels under each bin of each feature, so its efficiency is very low and even fails to meet the usability requirements, which seriously affects the subsequent modeling process. Therefore, how to improve the calculation efficiency of WOE and IV while ensuring security has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above, it is necessary to provide a sample data processing method to solve the problem that the calculation efficiency of WOE and IV is too low when the data volume is large, which affects the subsequent modeling process.

[0005] To achieve the above object, the present invention provides a sample data processing method, which is applied to a first client, and is characterized in that the method comprises:

[0006] Extracting a preset number of first samples and corresponding sample IDs from the first database, binning the first samples according to a preset binning algorithm to obtain a first binning result, wherein the first binning result includes a first bin number and the number of samples corresponding to each bin number;

[0007] Mapping the first box number to a second box number according to a preset box number mapping algorithm to obtain a second binning result, and sorting the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value;

[0008] Sending the sample ID of the first sample, the sorting index value of the second sample, and the second binning result to the second client, so that the second client can calculate the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result;

[0009] Receive the evidence weight returned by the second client, and calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

[0010] Optionally, binning the first sample according to a preset binning algorithm to obtain a first binning result includes:

[0011] Reading a characteristic value of each sample in the first sample;

[0012] According to the predetermined mapping relationship between the characteristic value and the numerical interval, each sample is distributed to the corresponding numerical interval;

[0013] Each numerical interval is taken as a bin to obtain a first bin number, and the first bin number and the number of samples corresponding to each bin number are taken as the first bin result.

[0014] Optionally, mapping the first box number to a second box number according to a preset box number mapping algorithm to obtain a second box division result includes:

[0015] Generate a random number corresponding to the number of box numbers of the first box number by using a preset random number generation function;

[0016] The random number is used to replace the box number of each box in the first box number to obtain a second box number, and the second box number and the number of samples corresponding to each box number are used as the second binning result.

[0017] Optionally, the step of sorting the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value includes:

[0018] Get the index value of each sample in the second box number;

[0019] Sort the second box numbers in ascending order of box numbers; and

[0020] The samples of each box number in the second box number are sorted in ascending order of characteristic values ​​to obtain a sorted index value of each sample in the second box number, and the sorted index value is used as the sorting index value.

[0021] Optionally, calculating the information value of the first client according to the evidence weight corresponding to each box number in the second box number includes:

[0022] Mapping the second box number back to the first box number according to the box number mapping algorithm to obtain the evidence weight corresponding to each box number in the first box number;

[0023] The information value of the first client is calculated according to a preset information value algorithm and the evidence weight corresponding to each first box number.

[0024] Optionally, a sample data processing method is applied to a second client, characterized in that the method includes:

[0025] Receive a sample ID of a first sample, a sorting index value of a second sample, and a second binning result sent by a first client, where the sorting index value of the second sample is obtained by binning the first sample using a binning algorithm preset by the first client to obtain a first binning result, mapping a first bin number of the first binning result to a second bin number to obtain the second binning result, and sorting the second samples in the second bin number;

[0026] Calculate the weight of evidence corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second box division result;

[0027] The evidence weight is returned to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

[0028] Optionally, calculating the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second box division result includes:

[0029] Extracting a corresponding third sample in the second database according to the sample ID of the first sample, wherein the third sample includes a sample with a preset label and a sample without a preset label;

[0030] Marking the third sample according to an algorithm of marking samples with a preset label as 1 and samples without a preset label as 0, to obtain a first array;

[0031] Sorting the first array according to the sorting index value to obtain a second array, and performing accumulation processing on the second array to obtain a third array;

[0032] Obtaining, according to the third array and the number of samples corresponding to each box number in the second box number, the total number of samples with preset labels in the second box number, the total number of samples without preset labels in the second box number, the number of samples with preset labels contained in each box number in the second box number, and the number of samples without preset labels contained in each box number in the second box number;

[0033] The evidence weight corresponding to each box number in the second box number is calculated according to the preset evidence weight calculation formula, the total number of samples with preset labels and the total number of samples without preset labels in the second box number, and the number of samples with preset labels and the number of samples without preset labels contained in each box number in the second box number.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides a sample data processing device, characterized in that the device comprises:

[0035] The first client: extracts a preset number of first samples and corresponding sample IDs from the first database, bins the first samples according to a preset binning algorithm to obtain a first binning result, the first binning result includes a first box number and the number of samples corresponding to each box number, maps the first box number to a second box number according to a preset box number mapping algorithm to obtain a second binning result, sorts the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value, sends the sample ID of the first sample, the sorting index value of the second sample, and the second binning result to the second client, so that the second client calculates the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result, receives the evidence weight returned by the second client, and calculates the information value of the first client according to the evidence weight corresponding to each box number in the second box number;

[0036] The second client: receives the sample ID of the first sample, the sorting index value of the second sample, and the second binning result sent by the first client, where the sorting index value of the second sample is obtained by binning the first sample using a binning algorithm preset by the first client to obtain the first binning result, mapping the first bin number of the first binning result to the second bin number to obtain the second binning result, and sorting the second samples in the second bin number, calculates the evidence weight corresponding to each bin number in the second bin number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result, and returns the evidence weight to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each bin number in the second bin number.

[0037] In addition, to achieve the above object, the present invention further provides an electronic device, the electronic device comprising:

[0038] a memory storing at least one computer program; and

[0039] The processor executes the program stored in the memory to implement the sample data processing method described above.

[0040] In addition, to achieve the above objectives, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the sample data processing method described above.

[0041] In the above technical solution provided by the present invention, the first client extracts a preset number of first samples and corresponding sample IDs from the first database, bins the first samples according to a preset binning algorithm to obtain a first binning result, maps the first bin number to a second bin number according to a preset bin number mapping algorithm to obtain a second binning result, thereby ensuring that data of the first client and the second client will not be leaked, thereby improving the security of data transmission in federated learning, and then sorts all samples in the second bin using a preset sorting algorithm to obtain a sorting index value, and then sends the sample ID value of the first sample, the sorting index value of the second sample, and the second binning result to the second client, and the second client The client calculates the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second box division result, and returns the evidence weight to the first client. The first client calculates the information value of the first client according to the evidence weight corresponding to each box number in the second box number. The present invention sorts and accumulates the sample data of the second client by sorting index value, which improves the computer's calculation efficiency of WOE and IV compared to the homomorphic encryption method used in the prior art. Therefore, the present invention improves the calculation efficiency of WOE and IV while ensuring data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a schematic diagram of an application environment of a sample data processing method in an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of a flow chart of a sample data processing method provided by an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of an electronic device of a sample data processing device provided by a first embodiment of the present invention;

[0045] Figure 4 A schematic diagram of an electronic device of a sample data processing device provided by a second embodiment of the present invention;

[0046] Figure 5 is a functional module diagram of a sample data processing device of the present invention;

[0047] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] It should be noted that the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0050] The sample data processing method provided by the embodiment of the present invention can be applied in Figure 1In an application environment, the first client communicates with the second client through a network. The first client extracts a preset number of first samples and corresponding sample IDs from the first database, bins the first samples according to a preset binning algorithm to obtain a first binning result, the first binning result includes a first bin number and the number of samples corresponding to each bin number, maps the first bin number to a second bin number according to a preset bin number mapping algorithm to obtain a second binning result, sorts the second samples in the second bin number according to a preset sorting algorithm to obtain a sorting index value, sends the sample ID of the first sample, the sorting index value of the second sample, and the second binning result to the second client, so that the second client can calculate the evidence weight corresponding to each bin number in the second bin number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result, receive the evidence weight returned by the second client, and sort the second sample according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result. The first client calculates the information value of the first client according to the corresponding evidence weight; the second client receives the sample ID of the first sample, the sorting index value of the second sample and the second binning result sent by the first client, the sorting index value of the second sample is obtained by binning the first sample according to the binning algorithm preset by the first client to obtain the first binning result, mapping the first bin number of the first binning result to the second bin number to obtain the second binning result, and sorting the second sample in the second bin number, and calculating the evidence weight corresponding to each bin number in the second bin number according to the sample ID, the sample ID of the first sample, the sorting index value of the second sample and the second binning result, and returning the evidence weight to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each bin number in the second bin number. In the present invention, the method of sorting and accumulating the sample data of the second client according to the sorting index value of the second sample improves the computer's calculation efficiency of WOE and IV compared to the homomorphic encryption method used in the prior art. Therefore, the present invention improves the calculation efficiency of WOE and IV under the premise of ensuring data security. The first client and the second client may be, but are not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The present invention is described in detail below through specific embodiments.

[0051] Reference Figure 2 The sample data processing method provided by an embodiment of the present invention is shown as a flow chart. The sample data processing method is applied to a first client and includes the following steps S1-S4:

[0052] S1. Extract a preset number of first samples and corresponding sample IDs from a first database, and bin the first samples according to a preset binning algorithm to obtain a first binning result, wherein the first binning result includes a first bin number and the number of samples corresponding to each bin number.

[0053] In one embodiment, the first client refers to the client that initiates the vertical learning, the first database refers to the database in the first client for storing customer data, the preset number can be set according to actual needs, and the sample usually refers to the customer, so extracting the preset number of samples refers to extracting the preset number of customers. It can be understood that the initiator and the participant of the vertical federated learning have different feature data of the same sample. For example, the feature data of the initiator is the annual income of the customer, and the feature data of the participant is the default of the customer. Therefore, in the example given in this embodiment, the first client needs to calculate the information contribution of the feature variable (the default of the customer) to the construction of the financial risk control model in the process of constructing the financial risk control model, but the database of the first client does not have the data of the feature variable. Therefore, the first client calculates the WOE (weight of evidence) and IV (information value) values ​​through vertical federated learning with the help of the second client that stores the data of the feature variable. The WOE and IV values ​​are used to evaluate the information contribution of the feature variable to the prediction of the target variable.

[0054] In one embodiment, binning the first sample according to a preset binning algorithm to obtain a first binning result includes:

[0055] Reading a characteristic value of each sample in the first sample;

[0056] According to the predetermined mapping relationship between the characteristic value and the numerical interval, each sample is distributed to the corresponding numerical interval;

[0057] Each numerical interval is taken as a bin to obtain a first bin number, and the first bin number and the number of samples corresponding to each bin number are taken as the first bin result.

[0058] In one embodiment, the characteristic value refers to the value corresponding to a certain characteristic of the sample. For example, the characteristic value is the customer's annual income data or the customer's credit data, etc. The preset binning algorithm refers to mapping each sample to the corresponding bin number according to the mapping relationship between the sample characteristic value and the numerical interval. The predetermined mapping relationship between the characteristic value and the numerical interval corresponds to the characteristic value, and different characteristic values ​​have corresponding mapping relationships. For example, the numerical intervals corresponding to the customer's annual income data are [0, 50,000], [50,000, 100,000], [100,000, 150,000], etc. After each sample is distributed to the corresponding numerical interval, each numerical interval is used as a bin, for example, [0, 50,000] is bin 1, [50,000, 100,000] is bin 2, and [100,000, 150,000] is bin 3. The first bin number and the number of samples corresponding to each bin number are used as the first binning result. The first bin number includes all bin numbers. For example, bin 1 has 4 samples, bin 2 has 3 samples, and bin 3 has 3 samples.

[0059] S2. Map the first box number to a second box number according to a preset box number mapping algorithm to obtain a second box division result, and sort the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value.

[0060] In one embodiment, mapping the first box number to the second box number according to a preset box number mapping algorithm to obtain a second box division result includes:

[0061] Generate a random number corresponding to the number of box numbers of the first box number by using a preset random number generation function;

[0062] The random number is used to replace the box number of each box in the first box number to obtain a second box number, and the second box number and the number of samples corresponding to each box number are used as the second binning result.

[0063] In this embodiment, the second sample is the same as the first sample, and the random number generation function is used to generate a random integer in a preset numerical interval, for example, the integer 7 is randomly generated in the numerical interval [1, 10]. According to the number of box numbers in the first box number, a random number corresponding to the number of box numbers of the first box number is generated based on the random number generation function. For example, the first box number includes three sub-boxes 1, 2, and 3, and the random number generation function is used to generate the same number of three random numbers 7, 8, and 9. After generating the corresponding number of random numbers, the box number of each sub-box in the first box number is replaced by the random number. It can be understood that the replacement is random, for example, the box number 1 is replaced by the random number 8, the box number 3 is replaced by the random number 7, and the box number 2 is replaced by the random number 9, that is, the sub-boxes 1, 2, and 3 of the first box number are changed to sub-boxes 8, 9, and 7, thereby obtaining the second box number. After the box number of each sub-box in the first box number is replaced by the random number, a mapping relationship is established between the first box number and the second box number, that is, sub-box 1 corresponds to sub-box 8, sub-box 2 corresponds to sub-box 9, and sub-box 3 corresponds to sub-box 7. Similarly, the number of samples in bins 1, 2, and 3 becomes the number of samples in bins 8, 9, and 7.

[0064] This embodiment maps the first box number to the second box number through a preset box number mapping algorithm, thereby ensuring that the data of the first client and the second client will not be leaked, thereby improving the security of data transmission in federated learning.

[0065] In one embodiment, the step of sorting the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value includes:

[0066] Get the index value of each sample in the second box number;

[0067] Sort the second box numbers in ascending order of box numbers; and

[0068] The samples of each box number in the second box number are sorted in ascending order of characteristic values ​​to obtain a sorted index value of each sample in the second box number, and the sorted index value is used as the sorting index value.

[0069] In this embodiment, each sample has a unique index. For example, the second box number includes three boxes with box numbers 8, 9, and 7. There are a total of ten samples in the three boxes. The indexes of the ten samples are [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]. According to the above example, the index of the sample in box 8 is [1, 2, 3, 4], the index of the sample in box 9 is [5, 6, 7], and the index of the sample in box 7 is [8, 9, 10]. The samples in each second box number are sorted according to the preset sorting algorithm to obtain the sorted index value. Specifically, the box numbers are first sorted according to the numerical value of the box number in the second box number, and then the samples in each box number are sorted according to the size of the characteristic value. The sorted index value refers to the index order obtained after sorting all samples according to the preset sorting algorithm.

[0070] For example, the box number sorting is specifically that, as in the above example, the second box number contains three boxes 8, 9, and 7. The three boxes are sorted in ascending order of box number values, that is, box 7 is sorted first, box 8 is sorted in the middle, and box 9 is sorted last. The sample sorting of each box number is specifically as follows: for example, box 7 contains 3 samples A, B, and C (the indexes of the 3 samples are 8, 9, and 10), and the characteristic values ​​are 110,000, 130,000, and 120,000 respectively (referring to the annual income characteristics of the customers in the above example). After sorting according to the size of the characteristic values, the order becomes A, C, and B (the index values ​​after sorting become 8, 10, and 9); box 8 contains 3 samples D, E, F, and G (the indexes of the 3 samples are 1, 2, 3, and 4), and the characteristic values ​​are 10,000, 30,000, 20,000, and 40,000 respectively, and the order after sorting is D, F, E, and G (the index values ​​after sorting are 1, 3, 2, and 4); box 9 contains 3 samples H, I, and G (the indexes of the 3 samples are 5, 6, and 7), and the characteristic values ​​are 80,000, 90,000, and 70,000 respectively, and the order after sorting is G, H, and I (the index values ​​after sorting are 7, 5, and 6). Therefore, the index values ​​of the above ten samples after sorting are [8, 10, 9, 1, 3, 2, 4, 7, 5, 6].

[0071] This embodiment further ensures the security of data transmission by sorting the samples in the mapped second box number. Therefore, this embodiment maps the first box number to the second box number and sorts the samples in the second box number to obtain the second box data and the sorted index value, and then sends the second box data and the sorted index value to the second client for calculating the mapped WOE and IV value, which will neither leak the feature data of the first client nor the feature data of the second client, thereby ensuring the security of data transmission.

[0072] S3. Send the sample ID of the first sample, the sorting index value of the second sample and the second binning result to the second client, so that the second client can calculate the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second binning result.

[0073] In one embodiment, calculating the weight of evidence corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second box division result includes:

[0074] Extracting a corresponding third sample in the second database according to the sample ID of the first sample, wherein the third sample includes a sample with a preset label and a sample without a preset label;

[0075] Marking the third sample according to an algorithm of marking samples with a preset label as 1 and samples without a preset label as 0, to obtain a first array;

[0076] Sorting the first array according to the sorting index value to obtain a second array, and performing accumulation processing on the second array to obtain a third array;

[0077] Obtaining, according to the third array and the number of samples corresponding to each box number in the second box number, the total number of samples with preset labels in the second box number, the total number of samples without preset labels in the second box number, the number of samples with preset labels contained in each box number in the second box number, and the number of samples without preset labels contained in each box number in the second box number;

[0078] The evidence weight corresponding to each box number in the second box number is calculated according to the preset evidence weight calculation formula, the total number of samples with preset labels and the total number of samples without preset labels in the second box number, and the number of samples with preset labels and the number of samples without preset labels contained in each box number in the second box number.

[0079] In this embodiment, the second client refers to a client that includes a label corresponding to a preset variable in the vertical federated learning, that is, the second client has the label data required by the first client, for example, whether it is a defaulting customer. In vertical federated learning, the participants and the initiator have different feature data of the same sample, so the third sample extracted by the second client has the same sample ID as the first sample, for example, the third sample and the first sample are both customers A, B, C, and D. The preset label refers to the label required by the first client, such as the defaulting customer label. The second database refers to the database used to store customer data in the second client. After extracting the third sample, the samples with the preset label in the third sample are marked as 1, and the samples without the preset label are marked as 0, so as to obtain the first array, for example, the first array is [1, 1, 0, 1, 0, 1, 0, 0, 1, 0]. It can be understood that the first sample and the second sample are the same, so the index values ​​of the second sample and the third sample are also the same, that is, the index values ​​corresponding to the first array are [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]. Therefore, after obtaining the first array, the first array is sorted according to the sorting index value after the first client sorts to obtain the second array. For example, the sorting index value in the above example is [8, 10, 9, 1, 3, 2, 4, 7, 5, 6], and the second array obtained after sorting according to the sorting index value is [0, 0, 1, 1, 0, 1, 1, 0, 0, 1]. Then, the second array is accumulated, specifically, the value of each bit in the second array is added to all the previous values. For example, if the first bit is 0, it is also 0 after accumulation. If the second bit is 0, it is 0+0=0 after accumulation. If the third bit is 1, it is 0+0+1=1 after accumulation. And so on, until the last bit, and then the accumulated values ​​form the third array [0, 0, 1, 2, 2, 3, 4, 4, 4, 5].

[0080] In one embodiment, obtaining the total number of samples with preset labels in the second box number, the total number of samples without preset labels in the second box number, the number of samples with preset labels contained in each box number in the second box number, and the number of samples without preset labels contained in each box number in the second box number according to the number of samples corresponding to each box number in the third array and the second box number result includes:

[0081] According to the accumulated values ​​in the third array, the positions of the samples with preset labels in the second array and the total number of samples with preset labels in the second box number are obtained, and according to the total number of samples in the second box number and the total number of samples with preset labels in the second box number, the total number of samples without preset labels in the second box number is obtained;

[0082] Specifically, this embodiment sets the samples with preset labels to 1, and then obtains the third array after sorting and accumulation. Therefore, the total number of samples with preset labels in the second box number can be obtained through the accumulated value in the third array. For example, the last digit in the third array of the above example is 5, that is, the total number of samples with preset labels is 5. It is known that the total number of samples in the second box number is 10, so it can be calculated that the total number of samples without preset labels is 5. In addition, the position of the sample with preset labels can also be obtained according to the third array, and the position refers to the serial number in the second array. For example, according to the first 1, the first 2...the first 5 in the third array [0, 0, 1, 1, 0, 1, 1, 0, 0, 1], it can be analyzed that serial numbers 3, 4, 6, 7, and 10 in the second array [0, 0, 1, 1, 0, 1, 0, 0, 1] are samples with preset labels.

[0083] Determine the box number where the sample with the preset label is located according to the corresponding relationship between the sorting index value and each box number in the second box number and the position of the preset label sample in the second array, and obtain the number of samples with the preset label for each box number in the second box number;

[0084] Specifically, the correspondence between the sorting index value and each box number in the second box number means that the index value of the sample has a correspondence with the box number, for example, the sorting index value [8, 10, 9] corresponds to box number 7, [1, 3, 2, 4,] corresponds to box number 8, and [7, 5, 6] corresponds to box number 9. Since the second array is sorted according to the sorting index value, the sequence number [1, 2, 3] in the second array corresponds to box number 7, the sequence number [4, 5, 6, 7] corresponds to box number 8, and the sequence number [8, 9, 10] corresponds to box number 9. Therefore, according to the correspondence between the sorting index value and the box number, the box number corresponding to the sample with the preset label can be determined, so as to obtain the number of samples with the preset label in each box number, for example, box number 7 has 1 sample with the preset label, box number 8 has 3 samples with the preset label, and box number 9 has 1 sample with the preset label.

[0085] The number of samples without preset labels in each bin in the second bin number is obtained according to the number of samples corresponding to each bin number in the second bin information and the number of samples with preset labels in each bin of the second bin number.

[0086] Specifically, after obtaining the number of samples with preset labels in each box number, the number of samples without preset labels in each box number is calculated according to the number of samples corresponding to each box number in the second binning information. For example, in the above example, the number of samples in box number 7 is 3, the number of samples in box number 8 is 4, and the number of samples in box number 9 is 3. It can be calculated that box number 7 has 2 samples without preset labels, box number 8 has 1 sample without preset labels, and box number 9 has 2 samples without preset labels.

[0087] In one embodiment, the preset weight of evidence algorithm is:

[0088]

[0089] Among them, WOEi represents the evidence weight value of the i-th box of the second box number, bad i is the number of samples with preset labels in the i-th box of the second box number, bad total Indicates the total number of samples with preset labels in the second box number, good i represents the number of samples without preset labels in the i-th box of the second box number, good total Indicates the total number of samples without preset labels in the second box number.

[0090] This embodiment sorts the tag data of the second client by sorting index values ​​and accumulates them to obtain a third array. Compared with the homomorphic encryption method used in the comparison file and the prior art, the computer's calculation efficiency of WOE and IV is improved.

[0091] S4. Receive the evidence weight returned by the second client, and calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

[0092] In one embodiment, calculating the information value of the first client according to the evidence weight corresponding to each box number in the second box number includes:

[0093] Mapping the second box number back to the first box number according to the box number mapping algorithm to obtain the evidence weight corresponding to each box number in the first box number;

[0094] The information value of the first client is calculated according to a preset information value algorithm and the evidence weight corresponding to each first box number.

[0095] In this embodiment, the box number mapping algorithm refers to the correspondence between the first box number and the second box number. The second box number is mapped back to the first box number according to the box number mapping algorithm, thereby obtaining the evidence weight corresponding to each box number in the first box number. For example, box number 8 corresponds to box number 1, box number 7 corresponds to box number 2, and box number 9 corresponds to box number 3.

[0096] In one embodiment, the preset information value algorithm is:

[0097]

[0098] Among them, IV A It refers to the information value of the first client, WOEm refers to the evidence weight value of the mth box in the first box number, n represents the total number of boxes in the first box number, n is an integer greater than 1, m represents the box number in the first box number, Bad m is the number of samples with preset labels in the mth box of the first box number, Bad total Indicates the total number of samples with preset labels in the first box number, Good m Indicates the number of samples without preset labels in the mth box of the first box number, Good total Indicates the total number of samples without preset labels in the first box number.

[0099] In the above technical solution provided by the present invention, the first client extracts a preset number of first samples and corresponding sample IDs from the first database, bins the first samples according to a preset binning algorithm to obtain a first binning result, maps the first bin number to the second bin number according to a preset bin number mapping algorithm to obtain a second binning result, ensures that the data of the first client and the second client will not be leaked, and improves the security of data transmission in federated learning, and then uses a preset sorting algorithm to sort all samples in the second bin to obtain a sorting index value, and then sends the sorting index value, the sample ID and the second binning result to the second client, the second client calculates the evidence weight corresponding to each bin number in the second bin number according to the sample ID, the sorting index value and the second binning result, and returns the evidence weight to the first client, the first client calculates the information value of the first client according to the evidence weight corresponding to each bin number in the second bin number, and the present invention sorts and accumulates the sample data of the second client by the sorting index value, which improves the calculation efficiency of the computer for WOE and IV compared with the homomorphic encryption method used in the prior art. Therefore, the present invention improves the calculation efficiency of WOE and IV under the premise of ensuring data security.

[0100] like Figure 3FIG. 1 is a schematic diagram of an electronic device of a sample data processing device provided by the first embodiment of the present invention. The electronic device 1 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. The electronic device 1 can be a computer, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computer sets.

[0101] In this embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13 that can be interconnected and communicated via a system bus. The memory 11 stores a first client processing program 10 that can be executed by the processor 12. Figure 3 Only the electronic device 1 having components 11-13 and the first client processing program 10 is shown. It can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and the electronic device 1 may include fewer or more components than shown in the figure, or combine some components, or arrange the components differently.

[0102] Among them, the memory 11 includes a memory and at least one type of readable storage medium. The memory provides a cache for the operation of the electronic device 1; the readable storage medium can be volatile or non-volatile. Specifically, the readable storage medium can be a storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the readable storage medium can be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the storage medium can also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. In this embodiment, the readable storage medium of the memory 11 mainly includes a program storage area and a data storage area, wherein the program storage area is generally used to store an operating system and various application software installed on the electronic device 1, such as storing the code of the first client processing program 10 in an embodiment of the present invention; the data storage area can store data created according to the use of the blockchain node, such as various types of data that have been output or are to be output.

[0103] The processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 12 is generally used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices. In this embodiment, the processor 12 is used to run the program code stored in the memory 11 or process data, such as running the first client processing program 10.

[0104] The network interface 13 may include a wireless network interface or a wired network interface, and the network interface 13 is used to establish a communication connection between the electronic device 1 and a client (not shown in the figure).

[0105] Optionally, the electronic device 1 may further include a user interface, which may include a display (Display), an input unit such as a keyboard (Keyboard), and the optional user interface may also include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an organic light-emitting diode (Organic Light-Emitting Diode, OLED) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0106] In one embodiment of the present invention, when the first client processing program 10 is executed by the processor 12 , the following steps S11 - S14 are implemented.

[0107] S11. Extract a preset number of first samples and corresponding sample IDs from a first database, and bin the first samples according to a preset binning algorithm to obtain a first binning result, where the first binning result includes a first bin number and the number of samples corresponding to each bin number.

[0108] S12. Map the first box number to a second box number according to a preset box number mapping algorithm to obtain a second box division result, and sort the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value.

[0109] S13. Send the sample ID of the first sample, the sorting index value of the second sample and the second binning result to the second client, so that the second client can calculate the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second binning result.

[0110] S14. Receive the evidence weight returned by the second client, and calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

[0111] The specific operation steps implemented in the above steps S11-S14 are substantially the same as those in the first embodiment of the data alignment method of the present invention, and will not be repeated here.

[0112] In other embodiments, the first client processing program 10 can also be divided into one or more modules, one or more modules are stored in the memory 11, and are executed by one or more processors (processor 12 in this embodiment) to complete the present invention. The module referred to in the present invention refers to a series of computer program instruction segments that can perform specific functions, and is used to describe the execution process of the first client processing program 10 in the electronic device 1.

[0113] like Figure 4 FIG. 2 is a schematic diagram of an electronic device of a sample data processing device provided by the second embodiment of the present invention. The electronic device 2 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. The electronic device 2 can be a computer, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computer sets.

[0114] In this embodiment, the electronic device 2 includes, but is not limited to, a memory 21, a processor 22, and a network interface 23 that can be interconnected and communicated via a system bus. The memory 21 stores a second client processing program 20 that can be executed by the processor 22. Figure 4 Only the electronic device 2 having components 21-23 and the second client processing program 20 is shown. It can be understood by those skilled in the art that Figure 4 The structure shown does not constitute a limitation on the electronic device 2 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0115] Among them, the memory 21 includes a memory and at least one type of readable storage medium. The memory provides a cache for the operation of the electronic device 2; the readable storage medium can be volatile or non-volatile. Specifically, the readable storage medium can be a storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the readable storage medium can be an internal storage unit of the electronic device 2, such as a hard disk of the electronic device 2; in other embodiments, the storage medium can also be an external storage device of the electronic device 2, such as a plug-in hard disk equipped on the electronic device 2, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. In this embodiment, the readable storage medium of the memory 21 mainly includes a program storage area and a data storage area, wherein the program storage area is generally used to store an operating system and various application software installed on the electronic device 2, such as storing the code of the second client processing program 20 in an embodiment of the present invention; the data storage area can store data created according to the use of the blockchain node, such as various types of data that have been output or are to be output.

[0116] The processor 22 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 22 is generally used to control the overall operation of the electronic device 2, such as performing control and processing related to data interaction or communication with other devices. In this embodiment, the processor 22 is used to run the program code stored in the memory 21 or process data, such as running the second client processing program 20.

[0117] The network interface 23 may include a wireless network interface or a wired network interface, and the network interface 23 is used to establish a communication connection between the electronic device 2 and a client (not shown in the figure).

[0118] Optionally, the electronic device 2 may further include a user interface, which may include a display (Display), an input unit such as a keyboard (Keyboard), and the optional user interface may also include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an organic light-emitting diode (Organic Light-Emitting Diode, OLED) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 2 and to display a visual user interface.

[0119] In one embodiment of the present invention, when the second client processing program 20 is executed by the processor 22, the following steps S21-S23 are implemented.

[0120] S21, receiving the sample ID of the first sample, the sorting index value of the second sample, and the second binning result sent by the first client, where the sorting index value of the second sample is obtained by binning the first sample using a binning algorithm preset by the first client to obtain the first binning result, mapping the first bin number of the first binning result to the second bin number to obtain the second binning result, and sorting the second sample in the second bin number.

[0121] S22. Calculate the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second box division result.

[0122] S23. Return the evidence weight to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

[0123] The specific operation steps implemented in the above steps S21-S23 are substantially the same as those in the second embodiment of the data alignment method of the present invention, and will not be repeated here.

[0124] In other embodiments, the second client processing program 20 can also be divided into one or more modules, one or more modules are stored in the memory 21, and are executed by one or more processors (processor 22 in this embodiment) to complete the present invention. The module referred to in the present invention refers to a series of computer program instruction segments that can perform specific functions, and is used to describe the execution process of the second client processing program 20 in the electronic device 2.

[0125] like Figure 5 FIG. 1 is a functional module diagram of the sample data processing device of the present invention.

[0126] In the first embodiment of the present invention, the sample data processing device 100 includes a first client 101 and a second client 102. Exemplarily:

[0127] The first client 101: extracts a preset number of first samples and corresponding sample IDs from the first database, bins the first samples according to a preset binning algorithm to obtain a first binning result, the first binning result includes a first box number and the number of samples corresponding to each box number, maps the first box number to a second box number according to a preset box number mapping algorithm to obtain a second binning result, sorts the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value, sends the sample ID of the first sample, the sorting index value of the second sample and the second binning result to the second client, so that the second client calculates the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second binning result, receives the evidence weight returned by the second client, and calculates the information value of the first client according to the evidence weight corresponding to each box number in the second box number;

[0128] The second client 102: receives the sample ID of the first sample, the sorting index value of the second sample and the second binning result sent by the first client, the sorting index value of the second sample is obtained by binning the first sample using the binning algorithm preset by the first client to obtain the first binning result, mapping the first bin number of the first binning result to the second bin number to obtain the second binning result, and sorting the second samples in the second bin number, and calculating the evidence weight corresponding to each bin number in the second bin number according to the sample ID of the first sample, the sorting index value of the second sample and the second binning result, and returning the evidence weight to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each bin number in the second bin number. .

[0129] The specific operation steps implemented when the first client 101 and the second client 102 are executed are substantially the same as those in the above embodiment, and will not be repeated here.

[0130] Specifically, the specific implementation method of the processor 100 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0131] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable medium can be non-volatile or volatile. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0132] An embodiment of the present invention may further provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program may implement:

[0133] Extracting a preset number of first samples and corresponding sample IDs from the first database, binning the first samples according to a preset binning algorithm to obtain a first binning result, wherein the first binning result includes a first bin number and the number of samples corresponding to each bin number;

[0134] Mapping the first box number to a second box number according to a preset box number mapping algorithm to obtain a second binning result, and sorting the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value;

[0135] Sending the sample ID of the first sample, the sorting index value of the second sample, and the second binning result to the second client, so that the second client can calculate the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result;

[0136] Receive the evidence weight returned by the second client, and calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

[0137] Furthermore, the computer-usable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0138] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0139] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0141] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0142] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0143] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0144] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0145] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0146] It should be noted that if software tools or components other than those of our company appear in the embodiments of the present application, they are only used for illustrative purposes and do not represent actual use.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution 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 solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A sample data processing method, applied to a first client, characterized in that: The method comprises: Extracting a preset number of first samples and corresponding sample IDs from the first database, binning the first samples according to a preset binning algorithm to obtain a first binning result, wherein the first binning result includes a first bin number and the number of samples corresponding to each bin number; Mapping the first box number to a second box number according to a preset box number mapping algorithm to obtain a second binning result, and sorting the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value; Sending the sample ID of the first sample, the sorting index value of the second sample, and the second binning result to the second client, so that the second client can calculate the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result; Receive the evidence weight returned by the second client, and calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

2. The sample data processing method according to claim 1, characterized in that: The step of binning the first sample according to a preset binning algorithm to obtain a first binning result includes: Reading a characteristic value of each sample in the first sample; According to the predetermined mapping relationship between the characteristic value and the numerical interval, each sample is distributed to the corresponding numerical interval; Each numerical interval is taken as a bin to obtain a first bin number, and the first bin number and the number of samples corresponding to each bin number are taken as the first bin result.

3. The sample data processing method according to claim 1, characterized in that: The mapping of the first box number to a second box number according to a preset box number mapping algorithm to obtain a second box division result includes: Generate a random number corresponding to the number of box numbers of the first box number by using a preset random number generation function; The random number is used to replace the box number of each box in the first box number to obtain a second box number, and the second box number and the number of samples corresponding to each box number are used as the second binning result.

4. The sample data processing method according to claim 1, characterized in that: The step of sorting the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value includes: Get the index value of each sample in the second box number; Sort the second box numbers in ascending order of box numbers; and The samples of each box number in the second box number are sorted in ascending order of characteristic values ​​to obtain a sorted index value of each sample in the second box number, and the sorted index value is used as the sorting index value.

5. The sample data processing method according to claim 1, characterized in that: The calculating the information value of the first client according to the evidence weight corresponding to each box number in the second box number includes: Mapping the second box number back to the first box number according to the box number mapping algorithm to obtain the evidence weight corresponding to each box number in the first box number; The information value of the first client is calculated according to a preset information value algorithm and the evidence weight corresponding to each first box number.

6. A sample data processing method, applied to a second client, characterized in that: The method comprises: Receive a sample ID of a first sample, a sorting index value of a second sample, and a second binning result sent by a first client, where the sorting index value of the second sample is obtained by binning the first sample using a binning algorithm preset by the first client to obtain a first binning result, mapping a first bin number of the first binning result to a second bin number to obtain the second binning result, and sorting the second samples in the second bin number; Calculate the weight of evidence corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample and the second box division result; The evidence weight is returned to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each box number in the second box number.

7. The sample data processing method according to claim 6, characterized in that: Calculating the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second box division result, including: Extracting a corresponding third sample in the second database according to the sample ID of the first sample, wherein the third sample includes a sample with a preset label and a sample without a preset label; Marking the third sample according to an algorithm of marking samples with a preset label as 1 and samples without a preset label as 0, to obtain a first array; Sorting the first array according to the sorting index value to obtain a second array, and performing accumulation processing on the second array to obtain a third array; Obtaining, according to the third array and the number of samples corresponding to each box number in the second box number, the total number of samples with preset labels in the second box number, the total number of samples without preset labels in the second box number, the number of samples with preset labels contained in each box number in the second box number, and the number of samples without preset labels contained in each box number in the second box number; The evidence weight corresponding to each box number in the second box number is calculated according to the preset evidence weight calculation formula, the total number of samples with preset labels and the total number of samples without preset labels in the second box number, and the number of samples with preset labels and the number of samples without preset labels contained in each box number in the second box number.

8. A sample data processing device, characterized in that: The device comprises: The first client: extracts a preset number of first samples and corresponding sample IDs from the first database, bins the first samples according to a preset binning algorithm to obtain a first binning result, the first binning result includes a first box number and the number of samples corresponding to each box number, maps the first box number to a second box number according to a preset box number mapping algorithm to obtain a second binning result, sorts the second samples in the second box number according to a preset sorting algorithm to obtain a sorting index value, sends the sample ID of the first sample, the sorting index value of the second sample, and the second binning result to the second client, so that the second client calculates the evidence weight corresponding to each box number in the second box number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result, receives the evidence weight returned by the second client, and calculates the information value of the first client according to the evidence weight corresponding to each box number in the second box number; The second client: receives the sample ID of the first sample, the sorting index value of the second sample, and the second binning result sent by the first client, where the sorting index value of the second sample is obtained by binning the first sample using a binning algorithm preset by the first client to obtain the first binning result, mapping the first bin number of the first binning result to the second bin number to obtain the second binning result, and sorting the second samples in the second bin number, calculates the evidence weight corresponding to each bin number in the second bin number according to the sample ID of the first sample, the sorting index value of the second sample, and the second binning result, and returns the evidence weight to the first client, so that the first client can calculate the information value of the first client according to the evidence weight corresponding to each bin number in the second bin number.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the sample data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the sample data processing method according to any one of claims 1 to 7 is implemented.

Images