WO2021135474A1

WO2021135474A1 - Method and apparatus for fusing data from multiple data sources, electronic device, and storage medium

Info

Publication number: WO2021135474A1
Application number: PCT/CN2020/119073
Authority: WO
Inventors: 喻宁; 陈克炎; 朱艳乔
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-01-02
Filing date: 2020-09-29
Publication date: 2021-07-08
Also published as: CN111191733A; CN111191733B

Abstract

A method for fusing data from multiple data sources, relating to big data technologies, and comprising: obtaining an original data set to be fused, a training feature set, and a training feature tag set from a client, and performing a data mapping operation on the original data set to be fused to obtain a standard data set to be fused (S1); training a pre-constructed original fusion model by using the training feature set and the training feature tag set to obtain a standard fusion model (S2); and inputting the standard data set to be fused into the standard fusion model to implement a fusion operation to obtain fused data, and returning the fused data to the client (S3). Also provided are an apparatus for fusing data from multiple data sources, an electronic device, and a computer readable storage medium. The problems of strong subjectivity and low fusion accuracy in a data fusion process can be solved.

Description

Data fusion method, device, electronic equipment and storage medium of multiple data sources

This application requires the priority of a Chinese patent application filed with the Chinese Patent Office on January 2, 2020, the application number is CN202010004568.6, and the invention title is "Data fusion method, device, electronic equipment and storage medium with multiple data sources". The entire content is incorporated into this application by reference.

Technical field

This application relates to the field of big data technology, and in particular to a data fusion method, device, electronic device, and readable storage medium from multiple data sources.

Background technique

With the development of big data and artificial intelligence, more and more data sources are becoming more and more complex, which brings huge challenges to data analysis work. Therefore, before data analysis work starts, it is essential to integrate data first. Measures. At present, the methods of data fusion mainly include empirical value method and unsupervised method. Both methods can complete data fusion, but the inventor realizes that the empirical value method is subjective, while the non-supervised method lacks the guidance of label data. It is easy to cause the accuracy of the fusion data to be low.

Summary of the invention

A data fusion method with multiple data sources, including:

Obtain an original data set to be fused, a training feature set, and a training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

Using the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model;

The standard to-be-fused data set is input to the standard fusion model to perform a fusion operation to obtain fused data, and the fused data is returned to the client.

A data fusion device with multiple data sources, the device comprising:

The data mapping module is used to obtain the original data set to be fused, the training feature set, and the training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

The model training module is configured to use the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model;

The data fusion module is used to input the standard to-be-fused data set into the standard fusion model to perform a fusion operation to obtain fused data, and return the fused data to the client.

An electronic device, which includes:

Memory, storing at least one instruction; and

The processor executes the instructions stored in the memory to implement the following steps:

A computer-readable storage medium storing at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the following steps:

This application can solve the problems of strong subjectivity in the data fusion process and low fusion accuracy.

Description of the drawings

FIG. 1 is a schematic flowchart of a data fusion method for multiple data sources provided by an embodiment of the application;

FIG. 2 is a detailed flowchart of S2 in a data fusion method with multiple data sources provided by an embodiment of the application;

3 is a schematic diagram of modules of a data fusion method with multiple data sources provided by an embodiment of the application;

4 is a schematic diagram of the internal structure of an electronic device of a data fusion method with multiple data sources provided by an embodiment of the application;

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

This application provides a data fusion method with multiple data sources. Referring to FIG. 1, it is a schematic flowchart of a data fusion method with multiple data sources provided by an embodiment of this application. The method can be executed by a device, and the device can be implemented by software and/or hardware.

In this embodiment, the data fusion method of multiple data sources includes:

S1. Obtain an original data set to be fused, a training feature set, and a training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused.

The main purpose of this application is to perform fusion operations on data from different channels, which has greater application value, in which data from different channels can be collected to obtain the original data set to be fused. For example, when Xiaoyu purchased car insurance pricing, Xiaoyu uploaded a lot of data on car insurance pricing, including basic information about Xiaoyu 32 years old, male, bachelor degree, urban household registration, a residential house in the urban area, and history of gastric perforation surgery. The purchase price of Toyota Motor, Toyota Motor, and Toyota Motor is 170,000, etc., I have three claims information in the insurance company (including claims for accidents in the driving car, etc.), and have purchased medical insurance, unemployment insurance, etc., the above-mentioned about Xiaoyu upload The data about auto insurance pricing is the original data set to be fused,

The purpose of this application is to solve the final fusion data according to the original data set to be fused.

Further, the data mapping operation includes data normalization. Since the data comes from different channels, the range of data values is not the same. In order to reduce the pressure of calculation, it is necessary to normalize the data of different channels, that is, the data Unified mapping to the interval [0,1] interval. The normalization method of the data used here is dispersion standardization, as shown below:

Wherein, x ^* is the standard data to be fused, min is the minimum value of the original data set to be fused, max is the maximum value of the original data set to be fused, and x is the data in the original data set to be fused.

For example, a game A is online for public beta, and now the score label data for game A is obtained from different channels, the score label of a game in the channel 1 data is 65, the score range is [0,100], and the score of the game in channel 2 is 0.46. The score range is [0,1], the score of the game in channel 3 is 0, and the score range is [-1,1]. After the above normalization, the game A in channel 1, channel 2, and channel 3 The score changes to 0.65, 0.46, and 0.50.

Preferably, the training feature set and the training feature label set are collectively referred to as a training data set. As described above, if you want to perform data fusion on the data uploaded by Xiaoyu’s purchase of auto insurance pricing, you need to pre-train the auto insurance pricing fusion model, and pre-training The auto insurance pricing fusion model requires a large number of existing training data sets, such as the data uploaded by Xiao Zhang’s auto insurance pricing and the fusion data, the data uploaded by Xiao Chi’s auto insurance pricing, and the fusion data. The training feature set is the upload The fused data is the training feature label set.

Further, the form of the training feature set is: X(x _i1 ,x _i2 ,x _i3 ,...,x _ik ), where x _i1 ,x _i2 ,x _i3 ,...,x _ik represent training features from different channels, And _{the feature dimensions of x i1} , x _i2 , x _i3 ,..., x _ik are the same, and k represents the number of training feature sets.

S2. Use the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model.

In detail, the use of the training data set to train the pre-built original fusion model to obtain the standard fusion model can be referred to as shown in the detailed flowchart of Figure 2, including:

S21: Initialize the weight coefficient to obtain the initial value of the weight, wherein the weight coefficient and the training feature set have the same feature dimension;

S22. Construct an original logistic regression model according to the initial value of the weight, and construct a loss function for solving the loss value of the original logistic regression model;

S23. Use the training feature set as the input value of the loss function, and use the training feature label set as the label value of the loss function, and minimize the loss function to obtain a weight update value;

S24. Replace the weight update value with the weight initial value of the original logistic regression model to obtain the standard fusion model.

Specifically, the original logistic regression model relies on the currently published logistic equations, and the mathematical expression of the logistic equations is as follows:

logit(y _is )=θ ₀ +θ ₁ x _i1 +θ ₂ x _i2 +…θ _s x _is +…+θ _k x _ik +e _i

Among them, y _is represents the predicted fusion value corresponding to the _{sth training feature, e i} is the preset error value, and θ ₀ , θ ₁ ,..., θ _{k are} the weight coefficients. If the dimension of each training feature in the training feature set is 3, the number of weight coefficients is also 3.

further,

The original logistic regression model obtained by combining the above formula is:

The loss function J(θ) is:

The loss function is further obtained as:

Among them, y _js represents the training feature label corresponding to the sth training feature.

In detail, the above-mentioned training feature set X (x _i1 , x _i2 , x _i3 ,..., x _ik ) and the training feature label set are substituted into the loss function to calculate the weight update value.

The S2 step is mainly to obtain the weight coefficients θ ₀ , θ ₁ , θ ₂ , and θ _k by solving the minimized loss function J(θ), where e _i represents the error of the training process.

S3. Input the standard data set to be fused into the standard fusion model to perform a fusion operation to obtain fusion data, and return the fusion data to the client.

As described in S2, the standard fusion model including the weight update value is obtained as follows:

Wherein, β ₀ , β ₁ ,..., β _s ,..., β _k represent the weight update value.

As mentioned above, a certain game A is online and the game scores obtained after normalization are 0.65 _{, 0.46, 0.50, then 0.65 represents x i1} , 0.46 represents x _i2 , and so on, and the standard fusion model is solved to obtain Fusion data y _is .

Further, this embodiment further includes: when the fusion data is successfully returned to the client, establishing a one-to-one correspondence between the fusion data and the original data set to be fused in the client, and The fusion data and the original data set to be fused are stored according to the one-to-one correspondence.

As shown in Fig. 3, it is a functional block diagram of the data fusion device with multiple data sources in this application.

The data fusion device 100 with multiple data sources described in this application can be installed in an electronic device. According to the realized functions, the data fusion device 100 with multiple data sources may include a data mapping module 101, a model training module 102, and a data fusion module 103. The module described in this application can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

In this embodiment, the functions of each module/unit are as follows:

The data mapping module 101 is configured to obtain an original data set to be fused, a training feature set, and a training feature label set from a client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

The model training module 102 is configured to use the training feature set and the training feature tag set to train a pre-built original fusion model to obtain a standard fusion model;

The data fusion module 103 is configured to input the standard to-be-fused data set into the standard fusion model to perform a fusion operation to obtain fused data, and return the fused data to the client.

In detail, when each module of the data fusion device with multiple data sources is executed by a processor of an electronic device, the following method steps can be implemented:

The data mapping module 101 obtains an original data set to be fused, a training feature set, and a training feature label set from the client, and performs a data mapping operation on the original data set to be fused to obtain a standard data set to be fused.

The model training module 102 uses the training feature set and the training feature tag set to train a pre-built original fusion model to obtain a standard fusion model.

In detail, the training of the pre-built original fusion model using the training data set to obtain the standard fusion model includes: initializing a weight coefficient to obtain an initial value of the weight, wherein the weight coefficient and the training feature set have the same feature dimension, according to The initial value of the weight constructs an original logistic regression model, a loss function for solving the loss value of the original logistic regression model is constructed, the training feature set is used as the input value of the loss function, and the training feature tag set is used as the The label value of the loss function is minimized to obtain the weight update value, and the weight update value is replaced with the weight initial value of the original logistic regression model to obtain the standard fusion model.

further,

The loss function J(θ) is:

The loss function is further obtained as:

The model training module 102 mainly obtains the weight coefficients θ ₀ , θ ₁ , θ ₂ , and θ _k by solving the minimized loss function J(θ), where e _i represents the error of the training process.

The data fusion module 103 inputs the standard to-be-fused data set into the standard fusion model to perform a fusion operation to obtain fused data, and returns the fused data to the client.

As described in the model training module 102, the standard fusion model including the weight update value is obtained as follows:

As shown in FIG. 4, it is a schematic diagram of the structure of an electronic device that implements the data fusion method of multiple data sources in this application.

The electronic device 1 may include a processor 10, a memory 11, and a bus, and may also include a computer program stored in the memory 11 and running on the processor 10, such as a data fusion program 12 from multiple data sources.

Wherein, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, for example, a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), and a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash card (Flash Card), etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can be used not only to store application software and various data installed in the electronic device 1, such as the code of a data fusion program with multiple data sources, but also to temporarily store data that has been output or will be output.

The processor 10 may be composed of integrated circuits in some embodiments, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more Combinations of central processing unit (CPU), microprocessor, digital processing chip, graphics processor, and various control chips, etc. The processor 10 is the control unit of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and runs or executes programs or modules stored in the memory 11 (such as executing Data fusion programs with multiple data sources, etc.), and call data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

The bus may be a peripheral component interconnect standard (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus and so on. The bus is configured to implement connection and communication between the memory 11 and at least one processor 10 and the like.

FIG. 4 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 4 does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure. Components, or a combination of certain components, or different component arrangements.

For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, thereby controlling power The device implements functions such as charge management, discharge management, and power consumption management. The power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

Further, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.

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

It should be understood that the embodiments are only for illustrative purposes, and are not limited by this structure in the scope of the patent application.

The data fusion 12 of multiple data sources stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can realize:

Obtain the original data set to be fused, the training feature set, and the training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused.

Using the training feature set and the training feature label set, the pre-built original fusion model is trained to obtain the standard fusion model.

Specifically, for the specific implementation method of the above-mentioned instructions by the processor 10, reference may be made to the description of the relevant steps in the embodiment corresponding to FIG. 3, which will not be repeated here.

Further, if the integrated module/unit of the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer readable storage medium, or can be stored In a volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) . The computer-readable medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

Specifically, the specific embodiment of the steps implemented when the computer program is executed by the processor is substantially the same as the description of the related steps of the foregoing embodiment, and will not be repeated here.

In another embodiment, the data fusion method with multiple data sources provided in this application further ensures the privacy and security of all the above-mentioned data, all the above-mentioned data can also be stored in a node of a blockchain. For example, general fusion data, etc., these data can be stored in the blockchain node.

It should be noted that the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.

In the several embodiments provided in this application, it should be understood that the disclosed equipment, device, and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional modules in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, 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 may be implemented in the form of hardware plus software functional modules.

For those skilled in the art, it is obvious that the present application is not limited to the details of the foregoing exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the application.

Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of this application is defined by the appended claims rather than the above description, and therefore it is intended to fall into the claims. All changes in the meaning and scope of the equivalent elements of are included in this application. Any associated diagram marks in the claims should not be regarded as limiting the claims involved.

In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The second class words are used to denote names, and do not denote any specific order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application and not to limit them. Although the application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the application can be Make modifications or equivalent replacements without departing from the spirit and scope of the technical solution of the present application.

Claims

A data fusion method with multiple data sources, wherein the method is applied to an electronic device and includes:

Obtain an original data set to be fused, a training feature set, and a training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

Using the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model;

The standard to-be-fused data set is input to the standard fusion model to perform a fusion operation to obtain fused data, and the fused data is returned to the client.
The data fusion method of multiple data sources according to claim 1, wherein said using said training feature set and said training feature label set to train a pre-built original fusion model to obtain a standard fusion model, comprising:

Initialize the weight coefficient to obtain the initial value of the weight, wherein the weight coefficient and the training feature set have the same feature dimension;

Constructing an original logistic regression model according to the initial value of the weight;

Constructing a loss function for solving the loss value of the original logistic regression model;

Using the training feature set as the input value of the loss function, using the training feature label set as the label value of the loss function, and minimizing the loss function to obtain a weight update value;

The weight update value replaces the weight initial value of the original logistic regression model to obtain the standard fusion model.
The data fusion method of multiple data sources according to claim 2, wherein the loss function comprises:

Wherein, J(θ) represents the loss function, k represents the number of training feature sets, y is represents the prediction fusion data corresponding to the sth training feature using the original logistic regression model, and y js represents the sth training feature. The training feature label corresponding to the training feature, and θ represents the weight coefficient.
The data fusion method of multiple data sources according to claim 1, wherein the data mapping operation comprises:

The following calculation method is used for data normalization operation:

Where x * is the data in the standard data set to be fused, min is the minimum value of the original data set to be fused, max is the maximum value of the original data set to be fused, and x is the original data to be fused The data in the set.
The data fusion method of multiple data sources according to claim 1, wherein the method further comprises:

When the fusion data is successfully returned to the client, establishing a one-to-one correspondence between the fusion data and the original data set to be fused in the client;

The fusion data and the original data set to be fused are stored according to the one-to-one correspondence.
The data fusion method of multiple data sources according to claim 1, wherein the training feature set is in the form of X(x i1 ,x i2 ,x i3 ,...,x ik ), where x i1 ,x i2 , x i3 ,..., x ik represent training features from different channels, and the feature dimensions of x i1 , x i2 , x i3 ,..., x ik are the same, and k represents the number of training feature sets.
The data fusion method of multiple data sources according to claim 1, wherein the standard fusion model comprises:

Among them, β 0 , β 1 ,..., β s ,..., β k represent weight update values, x i1 , x i2 , x i3 ,..., x ik represent training features from different channels, and y is represents the fusion data .
A data fusion device with multiple data sources, wherein the device includes:

The data mapping module is used to obtain the original data set to be fused, the training feature set, and the training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

The model training module is configured to use the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model;

The data fusion module is used to input the standard to-be-fused data set into the standard fusion model to perform a fusion operation to obtain fused data, and return the fused data to the client.
An electronic device, wherein the electronic device includes:

At least one processor; and,

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the following steps:

Obtain an original data set to be fused, a training feature set, and a training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

Using the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model;

The standard to-be-fused data set is input to the standard fusion model to perform a fusion operation to obtain fused data, and the fused data is returned to the client.
9. The electronic device according to claim 9, wherein said using said training feature set and said training feature label set to train a pre-built original fusion model to obtain a standard fusion model, comprising:

Initialize the weight coefficient to obtain the initial value of the weight, wherein the weight coefficient and the training feature set have the same feature dimension;

Constructing an original logistic regression model according to the initial value of the weight;

Constructing a loss function for solving the loss value of the original logistic regression model;

Using the training feature set as the input value of the loss function, using the training feature label set as the label value of the loss function, and minimizing the loss function to obtain a weight update value;

The weight update value replaces the weight initial value of the original logistic regression model to obtain the standard fusion model.
The electronic device of claim 10, wherein the loss function comprises:

Wherein, J(θ) represents the loss function, k represents the number of training feature sets, y is represents the prediction fusion data corresponding to the sth training feature using the original logistic regression model, and y js represents the sth training feature. The training feature label corresponding to the training feature, and θ represents the weight coefficient.
9. The electronic device of claim 9, wherein the data mapping operation comprises:

The following calculation method is used for data normalization operation:

Where x * is the data in the standard data set to be fused, min is the minimum value of the original data set to be fused, max is the maximum value of the original data set to be fused, and x is the original data to be fused The data in the set.
9. The electronic device according to claim 9, wherein the instructions are executed by the at least one processor, so that the at least one processor further executes the following steps:

When the fusion data is successfully returned to the client, establishing a one-to-one correspondence between the fusion data and the original data set to be fused in the client;

The fusion data and the original data set to be fused are stored according to the one-to-one correspondence.
The electronic device according to claim 9, wherein the form of the training feature set is: X(x i1 ,x i2 ,x i3 ,...,x ik ), where x i1 ,x i2 ,x i3 ,..., x ik represents training features from different channels, and the feature dimensions of x i1 , x i2 , x i3 ,..., x ik are the same, and k represents the number of the training feature sets.
9. The electronic device of claim 9, wherein the standard fusion model comprises:

Among them, β 0 , β 1 ,..., β s ,..., β k represent weight update values, x i1 , x i2 , x i3 ,..., x ik represent training features from different channels, and y is represents the fusion data .
A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the following steps:

Obtain an original data set to be fused, a training feature set, and a training feature label set from the client, and perform a data mapping operation on the original data set to be fused to obtain a standard data set to be fused;

Using the training feature set and the training feature label set to train a pre-built original fusion model to obtain a standard fusion model;

The standard to-be-fused data set is input to the standard fusion model to perform a fusion operation to obtain fused data, and the fused data is returned to the client.
15. The computer-readable storage medium according to claim 16, wherein said using said training feature set and said training feature label set to train a pre-built original fusion model to obtain a standard fusion model, comprising:

Initialize the weight coefficient to obtain the initial value of the weight, wherein the weight coefficient and the training feature set have the same feature dimension;

Constructing an original logistic regression model according to the initial value of the weight;

Constructing a loss function for solving the loss value of the original logistic regression model;

Using the training feature set as the input value of the loss function, using the training feature label set as the label value of the loss function, and minimizing the loss function to obtain a weight update value;

The weight update value replaces the weight initial value of the original logistic regression model to obtain the standard fusion model.
17. The computer-readable storage medium of claim 17, wherein the loss function comprises:

Wherein, J(θ) represents the loss function, k represents the number of training feature sets, y is represents the prediction fusion data corresponding to the sth training feature using the original logistic regression model, and y js represents the sth training feature. The training feature label corresponding to the training feature, and θ represents the weight coefficient.
The computer-readable storage medium of claim 16, wherein the data mapping operation comprises:

The following calculation method is used for data normalization operation:

Where x * is the data in the standard data set to be fused, min is the minimum value of the original data set to be fused, max is the maximum value of the original data set to be fused, and x is the original data to be fused The data in the set.
16. The computer-readable storage medium of claim 16, wherein the computer program further implements the following steps when being executed by the processor:

When the fusion data is successfully returned to the client, establishing a one-to-one correspondence between the fusion data and the original data set to be fused in the client;

The fusion data and the original data set to be fused are stored according to the one-to-one correspondence.