Data processing method, electronic device and computer readable storage medium

Abstract

The present invention provides a data processing method, an electronic device, and a computer-readable storage medium. The data processing method receives a first operation on a data processing control on a display interface; in response to the first operation, processes the data input to a neural network model to obtain processed result data; receives a second operation on a feature processing control on the display interface; in response to the second operation, calculates the characteristic value of the result data to obtain a characteristic value result; and outputs the characteristic value result. The above method provides a technical solution for a stable and reliable artificial intelligence algorithm calculation and model management platform for the existing artificial intelligence algorithm calculation platform. The calculation solution can configure and manage the input source data, calculation process, and output form in an interface-friendly and efficient manner, and can maximize the work efficiency of existing system users.

Description

Technical Field

[0001] The present invention relates to the field of eigenvalue calculation, and in particular to a data processing method, an electronic device and a computer-readable storage medium. Background Art

[0002] The AI ​​algorithm computing platform that helps engineers build AI models, store models, train models, and use models for prediction services in the prior art relies on the input of the upstream customer data management system. The data input by the upstream customer data management system is scattered in multiple dimensions and multiple data sources, and is fragmented and lacks statistical information, which makes it impossible to guarantee the normal and stable operation of the computing platform, as well as the accuracy of training models and using models for prediction services.

[0003] In order to ensure the normal and stable operation of the computing platform, as well as the accuracy of training models and using models for predictive services, the existing artificial intelligence algorithm calculation and model management platform urgently needs a solution for input source data and eigenvalue calculation. In other words, there is currently a lack of a user-friendly, highly available and efficient configuration and management system for input data sources, calculation processes and output forms. Summary of the invention

[0004] The main purpose of the present invention is to provide a data processing method, an electronic device and a computer-readable storage medium to solve the problem in the prior art that it is impossible to ensure the normal and stable operation of the artificial intelligence algorithm computing platform, and to ensure the accuracy of training models and using models for predictive services.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present invention, there is provided a data processing method, which receives a first operation on a data processing control on a display interface; in response to the first operation, processes the data input to the neural network model to obtain processed result data; receives a second operation on a feature processing control on the display interface; in response to the second operation, calculates the feature value of the result data to obtain a feature value result; and outputs the feature value result.

[0006] Furthermore, in response to the first operation, the data input to the neural network model is processed to obtain processed result data, including: in response to the first operation, a sub-control interface including a data processing sub-control is displayed, wherein the processing sub-control includes a merging sub-control; a third operation on the merging sub-control is received; and in response to the third operation, the data input to the neural network model is merged to obtain merged data.

[0007] Further, in response to the third operation, the data input to the neural network model is merged to obtain merged data, including at least one of the following: in response to the third operation, the data is merged by migrating historical data stored in a non-local storage location to a local storage location to obtain merged data; in response to the third operation, the historical data input before the current moment is merged with the data input at the current moment to obtain merged data; in response to the third operation, data of different dimensions are merged to obtain merged data; in response to the third operation, data of different formats are merged to obtain merged data; in response to the third operation, data with different identifiers are merged to obtain merged data.

[0008] Further, in response to the second operation, the characteristic value of the result data is calculated to obtain the characteristic value result, including: in response to the second operation, obtaining configuration information for triggering the characteristic value calculation method, wherein the configuration information is obtained through the display interface configuration, and the characteristic value calculation method includes one of the following: a real-time characteristic calculation method for performing characteristic calculation when the result data is received, and a timed characteristic calculation method for performing characteristic value calculation in a time span indicated by an input instruction, wherein the input instruction is input through the display interface; according to the configuration information, the characteristic value calculation method is triggered, the characteristic value of the result data is calculated, and the characteristic value result is obtained.

[0009] Furthermore, when there are multiple eigenvalues ​​in the result data, the calculations of the multiple eigenvalues ​​are serial.

[0010] Further, in response to the second operation, the characteristic value of the result data is calculated to obtain the characteristic value result, including: in response to the second operation, the intermediate value of the result data is calculated to obtain the intermediate value result; and the characteristic value calculation is performed on the intermediate value result to obtain the characteristic value result.

[0011] Furthermore, outputting the characteristic value result includes: selecting an output control in a display interface, wherein different output controls correspond to different output methods, and the output methods include one of the following: an interface output method, a file export method; and outputting the characteristic value result according to the output method corresponding to the selected output control.

[0012] According to another aspect of the present invention, there is provided a data processing device, comprising: a first receiving module for receiving a first operation on a data processing control on a display interface; a processing module for processing data input to a neural network model in response to the first operation to obtain processed result data; a second receiving module for receiving a second operation on a feature processing control on the display interface; a calculation module for calculating a feature value of the result data in response to the second operation to obtain a feature value result; and an output module for outputting the feature value result.

[0013] According to another aspect of the present invention, there is also provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the data processing method as described above.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the data processing method as described above.

[0015] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned data processing method is implemented.

[0016] The technical solution of the present invention is applied to provide a data processing method, receiving a first operation on a data processing control on a display interface, responding to the first operation, processing the data input to the neural network model, obtaining the processed result data, receiving a second operation on a feature processing control on the display interface, responding to the second operation, calculating the characteristic value of the result data, obtaining the characteristic value result, and outputting the characteristic value result. The above method provides a stable and reliable technical solution for artificial intelligence algorithm calculation and model management platform for the existing artificial intelligence algorithm calculation platform. The calculation solution can configure and manage the input source data, calculation process and output form in a user-friendly and efficient manner, and can maximize the work efficiency of existing system users. And the calculation solution has a certain versatility, can perfectly adapt to and be compatible with the mainstream data storage methods on the market as source data input, can also adapt to the mainstream calculation and storage tools on the market, and the tools used in the implementation process can be replaced as needed, and the specific system operation logic can be adjusted as necessary according to business needs, so it has a certain flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0018] Figure 1 is a hardware structure block diagram of a computer terminal for a data processing method according to an exemplary embodiment;

[0019] Figure 2 is a flowchart of a data processing method according to an exemplary embodiment;

[0020] Figure 3 is a device block diagram of a data processing method according to Embodiment 2 of the present invention;

[0021] Figure 4 is a device block diagram of a terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Example 1

[0026] According to an embodiment of the present invention, a data processing method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] The method embodiment provided in Embodiment 1 of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a data processing method. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (shown as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0028] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the data processing method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the data processing method of the above-mentioned application program is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0032] Under the above operating environment, this application provides Figure 2 The data processing method shown, Figure 2 is a flow chart of a data processing method according to Embodiment 1 of the present invention. Figure 2 As shown, the method comprises the following steps:

[0033] Step S202, receiving a first operation on a data processing control on a display interface;

[0034] Step S204, in response to the first operation, processing the data input to the neural network model to obtain processed result data;

[0035] Step S206, receiving a second operation on the feature processing control on the display interface;

[0036] Step S208, in response to the second operation, calculating the characteristic value of the result data to obtain the characteristic value result;

[0037] Step S210, outputting the eigenvalue result.

[0038] The above method provides a technical solution for a stable and reliable artificial intelligence algorithm calculation and model management platform for the existing artificial intelligence algorithm calculation platform. The calculation solution can configure and manage the input source data, calculation process and output form in a user-friendly and efficient manner, and can maximize the work efficiency of existing system users. In addition, the calculation solution has a certain degree of versatility, and can perfectly adapt to and be compatible with the mainstream data storage methods on the market as source data input. It can also adapt to the mainstream computing and storage tools on the market, and the tools used in the implementation process can be replaced as needed, and the specific system operation logic can be adjusted as necessary according to business needs, so it has a certain degree of flexibility.

[0039] The method provided in the present application processes the input source data to obtain the user-maintained feature data, and then outputs it to the downstream model storage, training and prediction services for calculation, completing the application of this part of the feature data. The input data source of this method can be compatible with multiple forms and formats, and the source data that needs to be input includes historical and real-time event data, historical and real-time label data, and group data that already contains user information. The input source formats that the system can adapt to include not only message queue types, such as Kafka message queues, but also relational and non-relational databases, such as Mysql and PostgreSQL, and can also adapt to mature big data computing data warehouses, such as Hive or HBase.

[0040] In order to improve the data processing efficiency, the data can be merged before the input source data is processed to obtain the feature data. As an optional embodiment, in response to the first operation, the data input to the neural network model is processed to obtain the processed result data, including: in response to the first operation, a sub-control interface including a data processing sub-control is displayed, wherein the processing sub-control includes a merging sub-control; receiving a third operation on the merging sub-control; in response to the third operation, the data input to the neural network model is merged to obtain the merged data.

[0041] As some optional embodiments, in response to the third operation, the data input to the neural network model are merged to obtain merged data, including at least one of the following: in response to the third operation, the data are merged by migrating historical data stored in a non-local storage location to a local storage location to obtain merged data; in response to the third operation, the historical data input before the current moment is merged with the data input at the current moment to obtain merged data; in response to the third operation, data of different dimensions are merged to obtain merged data; in response to the third operation, data of different formats are merged to obtain merged data; in response to the third operation, data with different identifiers are merged to obtain merged data.

[0042] During the above-mentioned data merging process, the historical data of the input data source can be batch migrated to the local source data table. When the real-time data arrives, the system is also capable of merging the real-time source data into the historical source data. Considering that the input data source will have multiple dimensions or multiple tables in different formats, in order to facilitate downstream feature calculations, the system will also merge different source data according to user identifiers. This merging action can be performed when migrating batch historical data, or when importing real-time source data. The merged result can be output to a local source data table partitioned by date. Considering that the user identifiers of different data sources will be different, the system will also unify user identifiers of different formats when merging input data. At the same time, the system will retain the unified mapping relationship to facilitate reverse mapping when outputting predicted data, that is, reverse mapping the unified user identifier back to the user identifier format of each input data source.

[0043] As some optional embodiments, in response to the second operation, the characteristic value of the result data is calculated to obtain the characteristic value result, including: in response to the second operation, configuration information for triggering the characteristic value calculation method is obtained, wherein the configuration information is obtained through the display interface configuration, and the characteristic value calculation method includes one of the following: a real-time feature calculation method for performing characteristic calculation when the result data is received, and a timed feature calculation method for performing characteristic value calculation in a time span indicated by an input instruction, wherein the input instruction is input through the display interface; according to the configuration information, the characteristic value calculation method is triggered, the characteristic value of the result data is calculated, and the characteristic value result is obtained.

[0044] In the above optional embodiment, after the system inputs source data from the data source and completes the merging process of the input source data, it will use the input source data for feature calculation. The process of feature calculation can be divided into batch feature calculation and timed feature calculation. Batch feature calculation will be automatically triggered when batch source data is migrated. It can also be triggered manually, and when manually triggered, the time span and feature list involved in batch feature value calculation can be specified. Timed feature value calculation will run at a fixed time every day, and different feature value calculation tasks will be executed serially to avoid output value conflicts caused by parallel execution.

[0045] As an optional embodiment, in response to the second operation, calculating the characteristic value of the result data to obtain the characteristic value result includes: in response to the second operation, calculating the intermediate value of the result data to obtain the intermediate value result; performing characteristic value calculation on the intermediate value result to obtain the characteristic value result.

[0046] In the above optional embodiment, the feature information involved in the calculation is read from the table of the list of features to be calculated and the table of the type of features to be calculated, including but not limited to the feature type, feature name, parameter list and parameter value required for calculating the intermediate value of the feature. Considering the large number of features involved in the calculation and the massive amount of input source data, in order to reduce the amount of calculation, the calculation process of the intermediate value is introduced into the whole calculation process. The calculation module first traverses the list of features involved in the calculation, summarizes the list of intermediate values ​​to be calculated, and then reads the processed source data to start the intermediate value calculation, and saves the calculated intermediate value into the feature intermediate value table. After completing the intermediate value calculation, the list of features to be calculated is traversed again, and the corresponding feature value calculation is completed from the intermediate value required in the intermediate value table, and the calculation result is output to the feature value calculation result table. The corresponding relationship between the intermediate value calculation method and the feature type involved in the calculation has been recorded in the table of the feature type to be calculated. The feature value calculation result table is a part of the feature warehouse, and the data is recorded in the form of a partition table.

[0047] In the above optional embodiment, a calculation task metadata information record may also be created in the feature value calculation task information table, including metadata information such as the calculation start time, the calculation task type, and the feature list involved.

[0048] As an optional embodiment, outputting the characteristic value result includes: selecting an output control in a display interface, wherein different output controls correspond to different output methods, and the output methods include one of the following: an interface output method, a file export method; and outputting the characteristic value result according to the output method corresponding to the selected output control.

[0049] In the above optional embodiment, the system provides two forms of output of feature values: interface output and export to file. At the same time, the system supports customization of the time span involved in the output feature value data and the parameters of the feature list to be output. The downstream of the feature value output is connected to the model warehouse, model training module, model verification module, model batch prediction module and model real-time prediction module.

[0050] The configuration information involved in the entire feature calculation process, such as the calculation time point, the feature list involved in the calculation, the time span involved in the calculation, the calculation process and the abnormal alarm mechanism, can be managed and viewed by a unified client with a good user interface. Users can set and view configuration information on this management client, and view the calculation progress in a timely manner. At the same time, for failures and other abnormalities, they can view specific error information to diagnose the cause of the failure or abnormality.

[0051] Considering the huge amount of data involved in the calculation, and the frequent disk file reading and writing involved in the storage and reading of intermediate values ​​and final result values ​​during the calculation process, the computing tools used in the entire feature calculation process can be big data computing frameworks, such as Spark, Hive, or commercial cloud computing tools such as MaxCompute. In order to take care of frequent and high-speed read and write operations, the data storage system used in the entire feature calculation process can be Presto, HBase, or ClickHouse.

[0052] Example 2

[0053] According to an embodiment of the present invention, a device for implementing the above data processing device is also provided. Figure 3 3 is a structural block diagram of a data processing device according to Embodiment 2 of the present invention. The device includes: a first receiving module 302, a processing module 304, a second receiving module 306, a calculation module 308 and an output module 310. The device is described in detail below:

[0054] A first receiving module 302, used to receive a first operation on a data processing control on a display interface;

[0055] The processing module 304 is used to process the data input to the neural network model in response to the first operation to obtain processed result data;

[0056] A second receiving module 306, configured to receive a second operation on a feature processing control on the display interface;

[0057] A calculation module 308, configured to calculate a characteristic value of the result data in response to the second operation to obtain a characteristic value result;

[0058] The output module 310 is used to output the eigenvalue results.

[0059] It should be noted here that the above-mentioned first receiving module 302, processing module 304, second receiving module 306, calculation module 308 and output module 310 correspond to steps S202 to S210 in Example 1, and the instances and application scenarios implemented by multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1.

[0060] Example 3

[0061] An embodiment of the present invention may provide an electronic device, which may be any computer terminal device in a computer terminal group.

[0062] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0063] Optionally, Figure 4 FIG. 1 is a structural block diagram of an electronic device according to an exemplary embodiment. Figure 4 As shown, the electronic device may include: one or more (only one is shown in the figure) processors 41, and a memory 42 for storing processor executable instructions; wherein the processor is configured to execute instructions to implement any of the above data processing methods.

[0064] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the data processing method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned data processing method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0065] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receiving a first operation on the data processing control on the display interface; in response to the first operation, processing the data input to the neural network model to obtain processed result data; receiving a second operation on the feature processing control on the display interface; in response to the second operation, calculating the feature value of the result data to obtain a feature value result; and outputting the feature value result.

[0066] Optionally, the processor may also execute program code for the following steps: in response to a first operation, processing data input into the neural network model to obtain processed result data, including: in response to the first operation, displaying a sub-control interface including a data processing sub-control, wherein the processing sub-control includes a merging sub-control; receiving a third operation on the merging sub-control; in response to the third operation, merging the data input into the neural network model to obtain merged data.

[0067] Optionally, the processor may also execute program code for the following steps: in response to the third operation, merging the data input to the neural network model to obtain merged data, including at least one of the following: in response to the third operation, merging the data by migrating historical data stored in a non-local storage location to a local storage location to obtain merged data; in response to the third operation, merging historical data input before the current moment with data input at the current moment to obtain merged data; in response to the third operation, merging data of different dimensions to obtain merged data; in response to the third operation, merging data of different formats to obtain merged data; in response to the third operation, merging data of different formats to obtain merged data.

[0068] Optionally, the processor may also execute program code for the following steps: in response to the second operation, calculating the characteristic value of the result data to obtain the characteristic value result, including: in response to the second operation, obtaining configuration information for triggering the characteristic value calculation method, wherein the configuration information is obtained through the display interface configuration, and the characteristic value calculation method includes one of the following: a real-time characteristic calculation method for performing characteristic calculation when the result data is received, and a timed characteristic calculation method for performing characteristic value calculation in the time span indicated by the input instruction, wherein the input instruction is input through the display interface; according to the configuration information, the characteristic value calculation method is triggered to calculate the characteristic value of the result data to obtain the characteristic value result.

[0069] Optionally, the processor may further execute program code of the following steps: when there are multiple eigenvalues ​​of the result data, the calculation of the multiple eigenvalues ​​is serial.

[0070] Optionally, the processor may also execute program code of the following steps: responding to the second operation, calculating the characteristic value of the result data, and obtaining a characteristic value result, including: responding to the second operation, calculating the intermediate value of the result data, and obtaining an intermediate value result; performing characteristic value calculation on the intermediate value result, and obtaining a characteristic value result.

[0071] Optionally, the processor may also execute program code for the following steps: outputting characteristic value results, including: selecting an output control on a display interface, wherein different output controls correspond to different output methods, and the output methods include one of the following: interface output method, file export method; outputting characteristic value results according to the output method corresponding to the selected output control.

[0072] It can be understood by those skilled in the art that Figure 4 The structures shown are for illustration only. Figure 4 It does not limit the structure of the above electronic device. For example, it may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations shown.

[0073] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0074] Example 4

[0075] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of a terminal, the terminal is enabled to perform any of the above data processing methods. Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0076] Optionally, in this embodiment, the computer-readable storage medium may be used to store program codes executed by the data processing method provided in the first embodiment.

[0077] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the mobile terminals in a mobile terminal group.

[0078] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for performing the following steps: receiving a first operation on a data processing control on a display interface; in response to the first operation, processing the data input to the neural network model to obtain processed result data; receiving a second operation on a feature processing control on the display interface; in response to the second operation, calculating the eigenvalues ​​of the result data to obtain eigenvalue results; and outputting the eigenvalue results.

[0079] Optionally, the computer-readable storage medium is configured to store program code for performing the following steps: in response to a first operation, processing data input to the neural network model to obtain processed result data, including: in response to the first operation, displaying a sub-control interface including a data processing sub-control, wherein the processing sub-control includes a merging sub-control; receiving a third operation on the merging sub-control; in response to the third operation, merging the data input to the neural network model to obtain merged data.

[0080] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: in response to the third operation, merging the data input to the neural network model to obtain merged data, including at least one of the following: in response to the third operation, merging the data by migrating historical data stored in a non-local storage location to a local storage location to obtain merged data; in response to the third operation, merging historical data input before the current moment with data input at the current moment to obtain merged data; in response to the third operation, merging data of different dimensions to obtain merged data; in response to the third operation, merging data of different formats to obtain merged data; in response to the third operation, merging data with different identifiers to obtain merged data.

[0081] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: in response to the second operation, calculating the characteristic value of the result data to obtain the characteristic value result, including: in response to the second operation, obtaining configuration information for triggering the characteristic value calculation method, wherein the configuration information is obtained through the display interface configuration, and the characteristic value calculation method includes one of the following: a real-time feature calculation method that performs feature calculation when the result data is received, and a timed feature calculation method that performs feature value calculation in the time span indicated by the input instruction, wherein the input instruction is input through the display interface; according to the configuration information, the characteristic value calculation method is triggered to calculate the characteristic value of the result data to obtain the characteristic value result.

[0082] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: when there are multiple eigenvalues ​​of the result data, the calculations of the multiple eigenvalues ​​are serial.

[0083] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: in response to the second operation, calculating the characteristic value of the result data to obtain a characteristic value result, including: in response to the second operation, calculating the intermediate value of the result data to obtain the intermediate value result; performing characteristic value calculation on the intermediate value result to obtain a characteristic value result.

[0084] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: outputting characteristic value results, including: selecting an output control in a display interface, wherein different output controls correspond to different output methods, and the output methods include one of the following: interface output method, file export method; outputting the characteristic value results according to the output method corresponding to the selected output control.

[0085] In an exemplary embodiment, a computer program product is also provided. When a computer program in the computer program product is executed by a processor of an electronic device, the electronic device is enabled to perform any of the above data processing methods.

[0086] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0087] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or 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 software functional units.

[0091] If the integrated unit 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. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data processing method, characterized in that: receiving a first operation on a data processing control on a display interface; In response to the first operation, the data input to the neural network model is processed to obtain processed result data; receiving a second operation on a feature processing control on the display interface; In response to the second operation, calculating the characteristic value of the result data to obtain a characteristic value result; Outputting the eigenvalue result; Wherein, in response to the first operation, processing the data input to the neural network model to obtain processed result data includes: in response to the first operation, displaying a sub-control interface including a data processing sub-control, wherein the processing sub-control includes a merging sub-control; receiving a third operation on the merging sub-control; in response to the third operation, merging the data input to the neural network model to obtain merged data; Among them, in response to the third operation, the data input into the neural network model are merged to obtain merged data, including: in response to the third operation, data of different dimensions are merged to obtain merged data.

2. The processing method according to claim 1, characterized in that: In response to the third operation, the data input to the neural network model are merged to obtain merged data, and at least one of the following is also included: In response to the third operation, the historical data stored in the non-local storage location is migrated to the local storage location, thereby merging the data to obtain merged data; In response to the third operation, the historical data input before the current moment is merged with the data input at the current moment to obtain merged data; In response to the third operation, the data in different formats are merged to obtain merged data; In response to the third operation, the data with different identifiers are merged to obtain merged data.

3. The processing method according to claim 1, characterized in that: In response to the second operation, calculating the characteristic value of the result data to obtain the characteristic value result includes: In response to the second operation, configuration information for triggering a characteristic value calculation mode is obtained, wherein the configuration information is obtained by configuring the display interface, and the characteristic value calculation mode includes one of the following: a real-time characteristic calculation mode for performing characteristic calculation when the result data is received, and a timed characteristic calculation mode for performing characteristic value calculation in a time span indicated by an input instruction, wherein the input instruction is input through the display interface; According to the configuration information, a characteristic value calculation method is triggered to calculate the characteristic value of the result data to obtain a characteristic value result.

4. The processing method according to claim 1, characterized in that: In the case that the result data has multiple eigenvalues, the calculations of the multiple eigenvalues ​​are serial.

5. The processing method according to claim 1, characterized in that: In response to the second operation, calculating the characteristic value of the result data to obtain the characteristic value result includes: In response to the second operation, calculating an intermediate value of the result data to obtain an intermediate value result; Perform eigenvalue calculation on the intermediate value result to obtain the eigenvalue result.

6. The processing method according to any one of claims 1 to 5, characterized in that: Output the eigenvalue results, including: Selecting an output control in the display interface, wherein different output controls correspond to different output modes, and the output mode includes one of the following: an interface output mode, a file export mode; The characteristic value result is output according to the output mode corresponding to the selected output control.

7. A data processing device, characterized in that: include: A first receiving module, used for receiving a first operation on a data processing control on a display interface; A processing module, used for processing the data input to the neural network model in response to the first operation to obtain processed result data; A second receiving module, used for receiving a second operation on the feature processing control on the display interface; a calculation module, configured to calculate a characteristic value of the result data in response to the second operation to obtain a characteristic value result; An output module, used for outputting the eigenvalue results; The processing module is further used to: in response to the first operation, display a sub-control interface including a data processing sub-control, wherein the processing sub-control includes a merging sub-control; receive a third operation on the merging sub-control; in response to the third operation, merge the data input to the neural network model to obtain merged data; The processing module is further used to: in response to the third operation, merge data of different dimensions to obtain merged data.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the data processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the data processing method as claimed in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 6 is implemented.

Images