Data processing method and device for assisting decision making

Abstract

The present application discloses a data processing method and device for assisting decision making. The method includes: in the present application, obtaining evaluation data to be processed, performing preprocessing based on data analysis on the evaluation data to be processed, obtaining standard evaluation data, using the VIKOR algorithm to perform auxiliary decision parameter determination processing on the standard evaluation data, and obtaining auxiliary decision parameters; constructing an auxiliary decision model according to the auxiliary decision parameters, performing decision processing on multiple schemes to be decided according to the auxiliary decision model, obtaining the output result of the target decision scheme, and outputting the output result of the target decision scheme through a network card. The VIKOR algorithm is used to perform decision evaluation on multiple schemes to be decided, and an evaluation decision based on multiple indicators is realized for multiple schemes to be decided, thereby improving the accuracy of the data corresponding to the decision scheme provided by business procurement, and coordinating with the server to perform data processing for assisting business procurement decisions.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular, to a data processing method and device for assisting decision making. Background Art

[0002] With the continuous development of information technology, users' requirements for server functions are becoming increasingly stringent. The increasing number of Gigabit network ports has increased the workload of servers, which in turn affects the speed of server operation. The network card is the computer hardware that computers use to communicate on the computer network. It is difficult for the network card to perform front-end processing on the data received by the server, and there is a situation where it is difficult to work with the server, resulting in slow data processing.

[0003] The inventors discovered that by adding an AI chip to the network card, it is possible to collaborate with the server to perform data processing. In the process of selecting business procurement suppliers, a neural network algorithm can be used to assist business procurement decisions. The construction of the neural network model has high requirements for the selection of parameters, and there are defects in the convergence speed, which can easily lead to local suboptimal convergence results and inaccuracy.

[0004] Therefore, the data corresponding to the decision-making solutions provided by network cards that add AI chips for business procurement has a low accuracy problem, and no effective solution has been proposed yet. Summary of the invention

[0005] The main purpose of this application is to provide a data processing method and device for auxiliary decision-making, so as to solve the problem of low accuracy of data corresponding to the decision-making scheme provided by the network card with an AI chip for business procurement, realize auxiliary decision-making for business procurement through the AI ​​network card, improve the accuracy of the data corresponding to the decision-making scheme provided by business procurement, and coordinate with the server to perform data processing for auxiliary decision-making for business procurement.

[0006] In order to achieve the above-mentioned purpose, in a first aspect of the present application, a data processing method for auxiliary decision-making is proposed, which is applied to a network card integrated with an AI chip. The data processing method includes:

[0007] Acquire evaluation data to be processed, wherein the evaluation data to be processed is a plurality of indicator data for evaluating a plurality of solutions to be decided, and any one of the plurality of solutions to be decided corresponds to a plurality of indicators;

[0008] Performing preprocessing based on data analysis on the evaluation data to be processed to obtain standard evaluation data, wherein the standard evaluation data is evaluation data corresponding to a plurality of evaluation indicators converted to have the same evaluation data value;

[0009] Using the VIKOR algorithm to perform auxiliary decision-making parameter determination processing on the standard evaluation data to obtain auxiliary decision-making parameters;

[0010] An auxiliary decision model is constructed according to the auxiliary decision parameters, and decision processing is performed on multiple decision-making schemes according to the auxiliary decision model to obtain a target decision scheme output result, wherein the target decision scheme output result is output through the network card.

[0011] Optionally, the VIKOR algorithm is used to perform auxiliary decision-making parameter determination processing on the standard evaluation data, and the auxiliary decision-making parameters obtained include:

[0012] Performing a first indicator evaluation process on the standard evaluation data to obtain a plurality of first process decision data, wherein the plurality of first process decision data are decision data of a plurality of solutions to be decided evaluated by the first indicator, and the plurality of first process decision data correspond to the plurality of solutions to be decided;

[0013] Performing a second indicator evaluation process on the standard evaluation data to obtain a plurality of second process decision data, wherein the plurality of second process decision data are decision data of a plurality of solutions to be decided evaluated by the second indicator, and the plurality of second process decision data correspond to the plurality of solutions to be decided;

[0014] The decision parameter optimization processing is performed on the plurality of first process decision data and the plurality of second process decision data to obtain the auxiliary decision parameters.

[0015] Optionally, performing decision parameter optimization processing on the plurality of first process decision data and the plurality of second process decision data to obtain the auxiliary decision parameters includes:

[0016] Acquire first process decision data and second process decision data, wherein the first process decision data and the second process evaluation data correspond to a first solution to be decided, and the first solution to be decided is any one of the multiple solutions to be decided;

[0017] Determine weight data corresponding to the first process decision data and the second process decision data to obtain a first weight and a second weight, wherein the first process decision data corresponds to the first weight and the second process decision data corresponds to the second weight; and

[0018] The first process decision data is weighted based on the first weight, and the second process decision data is weighted based on the second weight to obtain the auxiliary decision parameter.

[0019] Optionally, determining weight data corresponding to the first process decision data and the second process decision data to obtain the first weight and the second weight comprises:

[0020] Identifying the evaluation indicators of the first process decision data and the second process decision data to obtain evaluation characteristic data, wherein the evaluation indicator characteristic data is characteristic data used to characterize the evaluation indicator;

[0021] Matching a decision parameter optimization model corresponding to the evaluation feature data in a preset auxiliary decision database;

[0022] The first process decision data and the second process decision data are weighted according to the decision parameter optimization model to obtain the first weight and the second weight.

[0023] Optionally, the evaluation data to be processed is preprocessed based on data analysis to obtain standard evaluation data including:

[0024] Identify the data features of the evaluation data to be processed to obtain quantitative evaluation data and qualitative evaluation data, wherein the quantitative evaluation data is used to represent evaluation index data for quantitatively evaluating the solutions to be decided, and the qualitative evaluation data is used to represent the scoring data of the experts on the multiple solutions to be decided based on the qualitative evaluation index;

[0025] Constructing a process decision matrix according to the quantitative evaluation index data and the qualitative evaluation index data; and

[0026] The process decision matrix is ​​normalized to obtain a standard decision matrix, and the standard evaluation data is obtained. The standard evaluation data is the standard decision matrix obtained after the normalization process.

[0027] Optionally, constructing an auxiliary decision model according to the auxiliary decision parameters, performing decision processing on a plurality of decision-making schemes according to the auxiliary decision model, and obtaining a target decision scheme includes:

[0028] Performing auxiliary decision prediction processing on the multiple decision-making schemes according to the auxiliary decision model to obtain multiple auxiliary decision data, wherein the multiple auxiliary decision data correspond to the multiple decision-making schemes;

[0029] Sorting the plurality of auxiliary decision data to obtain target auxiliary decision data, wherein the target auxiliary decision data is auxiliary decision data corresponding to a minimum auxiliary decision value; and

[0030] The target decision plan is obtained, where the target decision plan is a decision plan to be made corresponding to the target auxiliary decision data.

[0031] According to a second aspect of the present application, a data processing device for assisting decision making is provided, which is applied to a network card integrated with an AI chip, and the data processing device includes:

[0032] A data acquisition module, used for acquiring evaluation data to be processed, wherein the evaluation data to be processed is a plurality of indicator data for evaluating a plurality of solutions to be decided, and any one of the plurality of solutions to be decided corresponds to a plurality of indicators;

[0033] A preprocessing module, used for preprocessing the evaluation data to be processed based on data analysis to obtain standard evaluation data, wherein the standard evaluation data is evaluation data corresponding to a plurality of evaluation indicators converted to have the same evaluation data value;

[0034] An auxiliary decision parameter determination module is used to perform auxiliary decision parameter determination processing on the standard evaluation data using a VIKOR algorithm to obtain auxiliary decision parameters;

[0035] The result output module is used to construct an auxiliary decision model according to the auxiliary decision parameters, perform decision processing on multiple decision-making schemes according to the auxiliary decision model, and obtain a target decision scheme output result, wherein the target decision scheme output result is output through the network card.

[0036] Optionally, the auxiliary decision parameter determination module includes:

[0037] A first decision module is used to perform a first indicator evaluation process on the standard evaluation data to obtain a plurality of first process decision data, wherein the plurality of first process decision data are decision data of a plurality of solutions to be decided evaluated by the first indicator, and the plurality of first process decision data correspond to the plurality of solutions to be decided;

[0038] A second decision module is used to perform a second indicator evaluation process on the standard evaluation data to obtain a plurality of second process decision data, wherein the plurality of second process decision data are decision data of a plurality of solutions to be decided evaluated by the second indicator, and the plurality of second process decision data correspond to the plurality of solutions to be decided;

[0039] The decision parameter optimization module is used to perform decision parameter optimization processing on the multiple first process decision data and the multiple second process decision data to obtain the auxiliary decision parameters.

[0040] According to a third aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned data processing method for assisting decision making.

[0041] According to the fourth aspect of the present application, an electronic device includes: 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 computer program is executed by the at least one processor so that the at least one processor executes the above-mentioned data processing method for assisting decision making.

[0042] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0043] In the present application, the evaluation data to be processed is obtained, and the evaluation data to be processed includes multiple indicator data for evaluating multiple schemes to be decided. By preprocessing the evaluation data to be processed based on data analysis, the evaluation data corresponding to multiple evaluation indicators with the same evaluation data value are obtained, and the standard evaluation data is obtained. The VIKOR algorithm is used to perform auxiliary decision parameter determination processing on the standard evaluation data to obtain auxiliary decision parameters; an auxiliary decision model is constructed according to the auxiliary decision parameters, and decision processing is performed on multiple schemes to be decided according to the auxiliary decision model to obtain the output result of the target decision scheme, and the output result of the target decision scheme is output through the network card. The decision evaluation of multiple schemes to be decided is performed through the VIKOR algorithm, and the evaluation decision based on multiple indicators of multiple schemes to be decided is realized. The decision data of multiple indicators are optimized, and the accuracy of the evaluation decision of the decision scheme to be decided is improved. The problem of low accuracy of the data corresponding to the decision scheme provided by the network card for adding AI chips for business procurement is solved, and auxiliary decision-making for business procurement is realized through the AI ​​network card, which improves the accuracy of the data corresponding to the decision scheme provided by business procurement, and the collaborative server performs data processing for auxiliary decision-making for business procurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0045] Figure 1 A schematic flow chart of a data processing method for assisting decision making provided in this application;

[0046] Figure 2 A schematic flow chart of a data processing method for assisting decision making provided in this application;

[0047] Figure 3 A schematic diagram of the structure of a data processing device for assisting decision making provided in this application;

[0048] Figure 4A schematic diagram of the structure of another data processing device for assisting decision making provided in this application. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0050] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0051] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0052] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0053] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0054] When conducting business procurement, there are multiple procurement options, such as the selection of suppliers and products. There are multiple evaluation indicators that affect the selection of procurement options. It is necessary to make decisions on the multiple evaluation indicators that affect the multiple procurement options to improve the accuracy of the decision-making plan selection.

[0055] Figure 1 A flowchart of a data processing method for assisting decision making provided in this application is shown in FIG. Figure 1 As shown, the method comprises the following steps:

[0056] S101: Obtaining evaluation data to be processed;

[0057] The evaluation data to be processed includes multiple indicator data for evaluating multiple decision-making plans. Any one of the multiple decision-making plans corresponds to multiple indicators. When making auxiliary decisions, it is necessary to obtain multiple data for evaluating the decision-making plans. In the process of evaluating each decision-making plan, each plan has multiple evaluation indicators. According to the characteristics of the evaluation indicators, the evaluation indicators include quantitative evaluation indicators and qualitative evaluation indicators. Determine the attributes and dimensions of the evaluation indicators according to the decision-making plans. For example, if the multiple decision-making plans are the evaluation of computer products, the quantitative evaluation indicators include price, CPU, graphics card, and power, etc., and the qualitative evaluation indicators include product quality, fan heat effect, brand evaluation, etc. The evaluation data of the qualitative evaluation indicators is the data obtained by experts scoring based on the above qualitative evaluation indicators.

[0058] S102: Preprocessing the evaluation data to be processed based on data analysis to obtain standard evaluation data;

[0059] The standard evaluation data is evaluation data converted into a plurality of evaluation indicators having the same evaluation data value;

[0060] The evaluation data of the scheme to be decided includes the evaluation data of the first indicator, the evaluation data of the second indicator and the evaluation data of the third indicator. The evaluation standards of the first indicator, the second indicator and the third indicator are different. For example, the evaluation standard of the first indicator is the value of the corresponding price, the evaluation standard of the second evaluation indicator is the value of the corresponding battery capacity, and the evaluation standard of the third evaluation indicator is the value of the expert score of the product quality. The data dimensions of the evaluation data of the first indicator, the evaluation data of the second indicator and the evaluation data of the third indicator are different. A first decision matrix is ​​constructed according to the evaluation data of multiple indicators of multiple schemes to be decided in the evaluation data to be processed. The first decision matrix is ​​normalized by using any one of the range transformation method, the vector normalization method, the weight transformation method and the linear transformation method. After the first decision matrix is ​​normalized, standard evaluation data is obtained. The standard evaluation data is data whose evaluation values ​​corresponding to the evaluation data of each indicator of any scheme to be decided fall within [0, 1].

[0061] In an optional embodiment of the present application, data features of the evaluation data to be processed are identified to obtain quantitative evaluation data and qualitative evaluation data, wherein the quantitative evaluation data is used to represent evaluation index data for quantitatively evaluating the decision-making schemes, and the qualitative evaluation data is used to represent the scoring data of the experts for multiple decision-making schemes based on the qualitative evaluation indexes; a process decision matrix is ​​constructed according to the quantitative evaluation index data and the qualitative evaluation index data; and the process decision matrix is ​​normalized to obtain a standard decision matrix and obtain standard evaluation data, wherein the standard evaluation data is the standard decision matrix obtained after normalization.

[0062] S103: using the VIKOR algorithm to perform auxiliary decision parameter determination processing on the standard evaluation data to obtain auxiliary decision parameters;

[0063] Figure 2 A flowchart of a data processing method for assisting decision making provided in this application is shown in FIG. Figure 2 As shown, the method comprises the following steps:

[0064] S201: Performing first indicator evaluation processing on standard evaluation data to obtain a plurality of first process decision data;

[0065] The plurality of first process decision data are decision data of a plurality of solutions to be decided evaluated by the first indicator, and the plurality of first process decision data correspond to the plurality of solutions to be decided;

[0066] S202: Performing second indicator evaluation processing on the standard evaluation data to obtain a plurality of second process decision data;

[0067] The plurality of second process decision data are decision data of a plurality of solutions to be decided evaluated by the second indicator, and the plurality of second process decision data correspond to the plurality of solutions to be decided;

[0068] S203: Optimizing the decision parameters of the plurality of first process decision data and the plurality of second process decision data to obtain auxiliary decision parameters.

[0069] In an optional embodiment of the present application, a data processing method for auxiliary decision-making is provided, which obtains first process decision data and second process decision data, wherein the first process decision data and the second process evaluation data correspond to a first plan to be decided, and the first plan to be decided is any one of a plurality of plans to be decided; determines weight data corresponding to the first process decision data and the second process decision data, obtains a first weight and a second weight, the first process decision data corresponds to the first weight, and the second process decision data corresponds to the second weight; and performs weighted processing on the first process decision data based on the first weight, and performs weighted processing on the second process decision data based on the second weight, to obtain auxiliary decision parameters.

[0070] In another optional embodiment of the present application, a data processing method for auxiliary decision-making is provided, which identifies evaluation indicators of first process decision data and second process decision data to obtain evaluation feature data, wherein the evaluation indicator feature data is feature data used to characterize the evaluation indicator; matches a decision parameter optimization model corresponding to the evaluation feature data in a preset auxiliary decision database; and performs weighted processing on the first process decision data and the second process decision data according to the decision parameter optimization model to obtain a first weight and a second weight.

[0071] When calculating the decision-making options through the VIKOR algorithm, calculate the VIKOR value Q of each option i ,

[0072]

[0073] in, Among them, the group benefit value Ed i and individual regret value EH i .Q i is the comprehensive evaluation value of the ith solution, Q i The smaller the value of is, the better the solution is. x1,x2∈[0,1] are decision coefficients, and x1+x2=1, which is used to represent the personal preference of expert evaluation. In the prior art, when calculating the VIKOR value of the solution to be decided, x1=x2=0.5 is selected, resulting in a low decision accuracy for each decision solution.

[0074] In the optional embodiment of the present application, by performing decision parameter optimization processing on a plurality of first process decision data and a plurality of second process decision data, the decision coefficient corresponding to each scheme is optimized, and modeling is performed by a deviation maximization method, including the VIKOR value of the i-th scheme,

[0075]

[0076] The VIKOR value of the lth solution is,

[0077]

[0078] The distance between the two solutions is,

[0079] The decision coefficient optimized by the method of maximizing the deviation is obtained, which improves the accuracy compared with the solution of directly determining the decision coefficient in the prior art to evaluate the decision solution. After obtaining the optimized decision coefficient, the decision weights of different experts are calculated, and the weight data corresponding to the individual expert is determined based on the similarity of the preferences of the individual expert and the expert group.

[0080] When the kth expert adopts the parameters (x1, x2), the VIKOR value for the i-th decision plan is Q i k ,

[0081]

[0082] Among them, the group benefit value of the VIKOR value of the kth expert for the i-th decision plan is and the individual regret value is After optimizing the decision parameters, we get the weight data corresponding to different experts. The weight data of the kth expert is ξ k , the final VIKOR value for the i-th decision plan is Where p is the total number of experts.

[0083] In an embodiment of the present application, by optimizing the auxiliary decision parameters in the VIKOR algorithm processing, the corresponding decision coefficients and the weights of expert evaluation are optimized according to the schemes to be decided, and the optimized VIKOR values ​​corresponding to each scheme are obtained. Multiple schemes to be decided are selected according to the optimized VIKOR values, thereby improving the accuracy of scheme decision-making.

[0084] S104: constructing an auxiliary decision model according to the auxiliary decision parameters, performing decision processing on multiple decision-making schemes according to the auxiliary decision model, and obtaining a target decision scheme output result, wherein the target decision scheme output result is output through a network card.

[0085] According to the auxiliary decision model, auxiliary decision prediction processing is performed on multiple decision-making schemes to obtain multiple auxiliary decision data, wherein the multiple auxiliary decision data correspond to the multiple decision-making schemes to be decided; the multiple auxiliary decision data are sorted to obtain target auxiliary decision data, which is the auxiliary decision data corresponding to the lowest auxiliary decision value; and the target decision scheme is obtained, which is the decision-making scheme to be decided corresponding to the target auxiliary decision data.

[0086] Figure 3 A schematic diagram of a data processing device for assisting decision making provided in this application is shown in FIG. Figure 3 As shown, the device comprises:

[0087] The data acquisition module 31 is used to acquire the evaluation data to be processed, wherein the evaluation data to be processed is a plurality of indicator data for evaluating a plurality of solutions to be decided, and any one of the plurality of solutions to be decided corresponds to a plurality of indicators;

[0088] A preprocessing module 32 is used to perform preprocessing on the evaluation data to be processed based on data analysis to obtain standard evaluation data, wherein the standard evaluation data is evaluation data corresponding to a plurality of evaluation indicators converted to have the same evaluation data value;

[0089] The auxiliary decision parameter determination module 33 is used to perform auxiliary decision parameter determination processing on the standard evaluation data using the VIKOR algorithm to obtain auxiliary decision parameters;

[0090] The result output module 34 is used to construct an auxiliary decision model according to the auxiliary decision parameters, perform decision processing on multiple decision-making schemes according to the auxiliary decision model, and obtain the target decision scheme output result, wherein the target decision scheme output result is output through the network card.

[0091] Figure 4 A schematic diagram of the structure of another data processing device for assisting decision making provided in this application is shown in FIG. Figure 4 As shown, the device comprises:

[0092] A first decision module 41 is used to perform a first indicator evaluation process on the standard evaluation data to obtain a plurality of first process decision data, wherein the plurality of first process decision data are decision data of a plurality of to-be-decided solutions evaluated by the first indicator, and the plurality of first process decision data correspond to the plurality of to-be-decided solutions;

[0093] A second decision module 42 is used to perform a second indicator evaluation process on the standard evaluation data to obtain a plurality of second process decision data, wherein the plurality of second process decision data are decision data of a plurality of to-be-decided solutions evaluated by the second indicator, and the plurality of second process decision data correspond to the plurality of to-be-decided solutions;

[0094] The decision parameter optimization module 43 is used to perform decision parameter optimization processing on a plurality of first process decision data and a plurality of second process decision data to obtain auxiliary decision parameters.

[0095] The specific manner of executing the operation of each unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0096] In summary, in the present application, the evaluation data to be processed is obtained, and the evaluation data to be processed includes multiple indicator data for evaluating multiple schemes to be decided. By preprocessing the evaluation data to be processed based on data analysis, the evaluation data corresponding to multiple evaluation indicators with the same evaluation data value are obtained, and the standard evaluation data is obtained. The VIKOR algorithm is used to perform auxiliary decision parameter determination processing on the standard evaluation data to obtain auxiliary decision parameters; an auxiliary decision model is constructed according to the auxiliary decision parameters, and decision processing is performed on multiple schemes to be decided according to the auxiliary decision model to obtain the output result of the target decision scheme, and the output result of the target decision scheme is output through the network card. The decision evaluation of multiple schemes to be decided is performed through the VIKOR algorithm, and the evaluation decision based on multiple indicators of multiple schemes to be decided is realized. The decision data of multiple indicators are optimized, and the accuracy of the evaluation decision of the decision scheme to be decided is improved. The problem of low accuracy of the data corresponding to the decision scheme provided by the network card for adding AI chips for business procurement is solved, and auxiliary decision-making for business procurement is realized through the AI ​​network card, which improves the accuracy of the data corresponding to the decision scheme provided by business procurement, and the collaborative server performs data processing for auxiliary decision-making for business procurement.

[0097] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0098] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0099] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method for assisting decision making, characterized in that: Applied to a network card integrated with an AI chip, the data processing method includes: Acquire evaluation data to be processed, wherein the evaluation data to be processed includes a plurality of indicator data for evaluating a plurality of solutions to be decided, and any one of the plurality of solutions to be decided corresponds to a plurality of indicators; Performing preprocessing based on data analysis on the evaluation data to be processed to obtain standard evaluation data, wherein the standard evaluation data is evaluation data corresponding to a plurality of evaluation indicators converted to have the same evaluation data value; The VIKOR algorithm is used to perform auxiliary decision-making parameter determination processing on the standard evaluation data to obtain auxiliary decision-making parameters, including: Performing a first indicator evaluation process on the standard evaluation data to obtain a plurality of first process decision data, wherein the plurality of first process decision data are decision data of a plurality of schemes to be decided evaluated by the first indicator, and the plurality of first process decision data correspond to the plurality of schemes to be decided; performing a second indicator evaluation process on the standard evaluation data to obtain a plurality of second process decision data, wherein the plurality of second process decision data are decision data of a plurality of schemes to be decided evaluated by the second indicator, and the plurality of second process decision data correspond to the plurality of schemes to be decided; performing decision parameter optimization process on the plurality of first process decision data and the plurality of second process decision data to obtain the auxiliary decision parameters; An auxiliary decision model is constructed according to the auxiliary decision parameters, and decision processing is performed on multiple decision-making schemes according to the auxiliary decision model to obtain a target decision scheme output result, wherein the target decision scheme output result is output through the network card, and the network card is integrated with an AI chip.

2. The data processing method according to claim 1, characterized in that: The decision parameter optimization processing is performed on the plurality of first process decision data and the plurality of second process decision data to obtain the auxiliary decision parameters, including: Acquire first process decision data and second process decision data, wherein the first process decision data and the second process decision data correspond to a first solution to be decided, and the first solution to be decided is any one of the multiple solutions to be decided; Determine weight data corresponding to the first process decision data and the second process decision data to obtain a first weight and a second weight, wherein the first process decision data corresponds to the first weight and the second process decision data corresponds to the second weight; and The first process decision data is weighted based on the first weight, and the second process decision data is weighted based on the second weight to obtain the auxiliary decision parameter.

3. The data processing method according to claim 2, characterized in that: Determining weight data corresponding to the first process decision data and the second process decision data to obtain the first weight and the second weight includes: Identifying the evaluation indicators of the first process decision data and the second process decision data to obtain evaluation indicator feature data, wherein the evaluation indicator feature data is feature data used to characterize the evaluation indicator; Matching a decision parameter optimization model corresponding to the evaluation index characteristic data in a preset auxiliary decision database; The first process decision data and the second process decision data are weighted according to the decision parameter optimization model to obtain the first weight and the second weight.

4. The data processing method according to claim 1, characterized in that: The evaluation data to be processed is preprocessed based on data analysis to obtain standard evaluation data including: Identify the data features of the evaluation data to be processed to obtain quantitative evaluation data and qualitative evaluation data, wherein the quantitative evaluation data is used to represent evaluation index data for quantitatively evaluating the solutions to be decided, and the qualitative evaluation data is used to represent the scoring data of the experts on the multiple solutions to be decided based on the qualitative evaluation index; constructing a process decision matrix according to the quantitative evaluation data and the qualitative evaluation data; and The process decision matrix is ​​normalized to obtain a standard decision matrix, and the standard evaluation data is obtained. The standard evaluation data is the standard decision matrix obtained after the normalization process.

5. The data processing method according to claim 1, characterized in that: Constructing an auxiliary decision model according to the auxiliary decision parameters, performing decision processing on multiple decision-making schemes according to the auxiliary decision model, and obtaining a target decision scheme includes: Performing auxiliary decision prediction processing on the multiple decision-making schemes according to the auxiliary decision model to obtain multiple auxiliary decision data, wherein the multiple auxiliary decision data correspond to the multiple decision-making schemes; Sorting the plurality of auxiliary decision data to obtain target auxiliary decision data, wherein the target auxiliary decision data is auxiliary decision data corresponding to a minimum auxiliary decision value; and The target decision plan is obtained, where the target decision plan is a decision plan to be made corresponding to the target auxiliary decision data.

6. A data processing device for assisting decision making, characterized in that: Applied to a network card integrated with an AI chip, the data processing device includes: A data acquisition module, used for acquiring evaluation data to be processed, wherein the evaluation data to be processed is a plurality of indicator data for evaluating a plurality of solutions to be decided, and any one of the plurality of solutions to be decided corresponds to a plurality of indicators; A preprocessing module, used for preprocessing the evaluation data to be processed based on data analysis to obtain standard evaluation data, wherein the standard evaluation data is evaluation data corresponding to a plurality of evaluation indicators converted to have the same evaluation data value; An auxiliary decision parameter determination module is used to perform auxiliary decision parameter determination processing on the standard evaluation data using the VIKOR algorithm to obtain auxiliary decision parameters; The auxiliary decision parameter determination module includes: A first decision module is used to perform a first indicator evaluation process on the standard evaluation data to obtain a plurality of first process decision data, wherein the plurality of first process decision data are decision data of a plurality of solutions to be decided evaluated by the first indicator, and the plurality of first process decision data correspond to the plurality of solutions to be decided; A second decision module is used to perform a second indicator evaluation process on the standard evaluation data to obtain a plurality of second process decision data, wherein the plurality of second process decision data are decision data of a plurality of solutions to be decided evaluated by the second indicator, and the plurality of second process decision data correspond to the plurality of solutions to be decided; A decision parameter optimization module, used for performing decision parameter optimization processing on the plurality of first process decision data and the plurality of second process decision data to obtain the auxiliary decision parameters; The result output module is used to construct an auxiliary decision model according to the auxiliary decision parameters, perform decision processing on multiple decision-making schemes according to the auxiliary decision model, and obtain a target decision scheme output result, wherein the target decision scheme output result is output through the network card, and the network card is integrated with an AI chip.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the data processing method for assisting decision-making as described in any one of claims 1-5.

8. An electronic device, characterized in that: include: 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 computer program is executed by the at least one processor so that the at least one processor executes the data processing method for assisting decision making as described in any one of claims 1-5.

Images