Systems for optimal decision-making and methods thereof

IN605455BActive Publication Date: 2026-10-09SRM INST OF SCI & TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
IN202441028728
Authority / Receiving Office
IN · IN
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-04-08
Publication Date
2026-10-09
Estimated Expiration
2044-04-08

AI Technical Summary

Technical Problem

Existing multi-criteria decision-making (MCDM) techniques rely heavily on subjective expert knowledge for weight assignment and do not fully utilize statistical properties of data, leading to suboptimal decision-making processes.

Method used

A system with a pre-processing module for data normalization, an evaluation module for statistical weight assignment, and an assessment module for optimal decision computation, using distribution normalization and statistical transformations to derive optimal decision alternatives.

Benefits of technology

This approach enhances decision efficiency and effectiveness by providing a data-driven, objective method for weight assignment and decision-making, improving the ranking of alternatives compared to traditional methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000033_0000
    Figure 00000033_0000
Patent Text Reader

Abstract

ABSTRACT SYSTEMS FOR OPTIMAL DECISION-MAKING AND METHODS THEREOF The present disclosure discloses a system (100) and method (200) for optimal decision-making in multi-criteria decision-making (MCDM) problems. The system comprises a microprocessor (104), memory (102), and various modules for input (108), pre-processing (110), evaluation (112), assessment (114), and output (116). It receives multiple sets of input data corresponding to distinct criteria, distribution normalizes and biases the data using pre-trained models stored in a data repository (106), and evaluates the data by inverting criteria constraints and assigning weights. The assessment module (114) computes optimal decision alternatives based on statistical analysis of the criteria and their weights. The output module (116) generates results that include one or more optimal decisions. The method (200) outlines these steps, ensuring that data normalization maintains unity in statistical uniqness between criteria. Overall, this innovative approach enhances the efficiency and accuracy of decision-making processes in complex scenarios, catering to both maximization and minimization objectives.
Need to check novelty before this filing date? Find Prior Art

Description

The present disclosure relates, in general, to the field of decision science. More particularly, embodiments of the present disclosure relate to a method of decision-making for application in Geographic Information Systems (GIS) software in spatial decision-making, however, can be applied in part or entirely for Data Analysis, Artificial Intelligence, Machine Learning, and so on.BACKGROUNDThe background information herein below relates to the present disclosure but is not necessarily prior art.Multi Criteria Decision Making (MCDM) is a problem in Decision Science where there are different objectives known as criteria to be considered under the constraints of maximization or minimization in arriving at a set of plausible solutions to the problem. Each of the plausible solutions to the problem is known as a Decision Alternative (DA) and usually, there exists several such DA(s) for a given problem. The MCDM problem can be either a problem of maximization or minimization either additive or multiplicative with or without involving a utility function. There are several well-established techniques used in the decision-making process such as Analytical Hierarchical Process (AHP), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), "VlseKriterijumska Optimizacija I Kompromisno Resenje" in Serbian (VICTOR), Preference Ranking Organization Method for Enrichment of Evaluation (PROMETHEE), "ÉLimination et Choix Traduisant la REalite" in French (ELECTRE), etc.However, in many of these methods, the assignment of weights to each of the criteria relies on the knowledge of the experts in the domain or a priori knowledge which is subjective. Also, preprocessing and postprocessing of data is done such as data normalization to remove any unnecessary bias and noise that influences the decisions and its alternatives.However, these techniques do not provide a method for optimal decision-making that relies in its entirety on the statistical properties of data.Therefore, there is a requirement for a novel technique for optimal decision-making and methods thereof that alleviates the aforementioned drawbacks. OBJECTSSome of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.An object of the present disclosure is to provide a novel technique for optimal decision-making and methods thereof. Another object of the present disclosure is to provide a set of methods for optimal decision-making for a typical MCDM problem.Another object of the present disclosure is to provide a set of methods and techniques for processing data.Another object of the present disclosure is to provide a method for the assignment of weights to the multiple criteria.Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.SUMMARYThe present disclosure introduces an advanced system for optimal decision-making, which enhances decision-making processes in solving multi-criteria decision-making (MCDM) problems through its comprehensive structural design. Central to this system is a pre-processing module, designed to receive multiple sets of input data, each corresponding to distinct decision criteria, from diverse sources such as user input and external devices. This module employs pre-trained models to optimally normalize using distribution normalization the input data and remove biases, ensuring consistency by transforming data into a standardized format.Following this, the evaluation module receives the pre-processed data, classifies the criteria as either maximization or minimization, and performs statistical transformations, such as inverting constraints for criteria, to ensure proper evaluation. This module then assigns statistical weights to each criterion based on their importance in the MCDM problem, ensuring an optimal weighting scheme.Subsequently, the assessment module computes decision values for various alternatives by aggregating the weighted normalized criteria values. Using advanced MCDM techniques, the system derives a set of optimal decisions and decision alternatives, which are calculated based on the statistical analysis of the input data.The output module then receives these computed decision values and presents the final optimal decisions along with a ranked list of alternatives. This output is made available through an interface that allows users to review and, if necessary, make adjustments to the decision alternatives.Further enhancements include a data repository that stores pre-trained models and statistical techniques for pre-processing, evaluation, and decision assessment, as well as a microprocessor that controls the operations of all system modules, ensuring efficient execution of the decision-making process.The present disclosure also envisages a method for optimal decision-making and elaborates on this system by formulating the decision problem, classifying criteria, optimally normalizing data using distribution normalization, assigning optimal weights, and computing decision values, comprising the following method steps: receiving, by an input module of a system, multiple sets of input data, each set corresponding to a distinct criterion in the MCDM problem; pre-processing, by a pre-processing module, said input data through a pre-trained pre-processing model stored in a data repository to distribution normalize and remove biases from the data; evaluating, by an evaluation module, said pre-processed data using a pre-trained evaluation model, said evaluation comprising the steps of: inverting criteria constraints for criteria requiring maximization or minimization, normalizing using distribution normalization of data by applying statistical techniques, and assigning weights to the criteria based on statistical analysis; assessing, by an assessment module, optimal decision alternatives based on the criteria weights and the MCDM problem's requirements; and generating, by an output module, the results of the MCDM problem, including one or more optimal decisions and a set of optimal decision alternatives.In an aspect, the pre-processing further comprises normalizing the input data using distribution normalization to ensure that the mean of the normalized data for each criterion is unity and the covariance between the criteria is zero.In an aspect, the normalization is performed by distribution normalizing the input data based on the statistical mean of each criterion, ensuring that data points are scaled appropriately for decision-making.In an aspect, the criteria inversion for maximization or minimization is performed by converting data points requiring maximization into minimization values and vice versa, using a statistical transformation based on the relationship between the constraints.In an aspect, the assignment of weights to multiple criteria is based on the maximization or minimization of the formulated MCDM problem, such that the weight for each criterion is computed by either selecting the maximum or minimum value depending on the nature of the problem.In an aspect, the optimal decision alternatives are derived by computing the decision value for each decision alternative and selecting the N optimal decision alternatives based on the highest or lowest values, depending on whether the MCDM problem is one of maximization or minimization.This sophisticated decision-making framework of the present disclosure, integrating multiple data sources and advanced statistical analysis, offers significant improvements in evaluating and ranking decision alternatives compared to traditional methods, thereby enhancing overall decision efficiency and effectiveness. BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING A novel technique for optimal decision-making and methods thereof, of the present disclosure will now be described with the help of the accompanying drawing in which:Figure 1 illustrates a block diagram of a system for optimal decision-making, in accordance with an embodiment of the present disclosure;Figures 1A-1B illustrate a flow chart of a novel technique for optimal decision-making and methods thereof, in accordance with an embodiment of the present disclosure; and Figure 2 illustrates a flow diagram of a method for optimal decision-making, in accordance with an embodiment of the present disclosure.LIST OF REFERENCE NUMERALS100 System For Optimal Decision-Making200 Method For Optimal Decision-Making102 Memory104 Microprocessor106 Data Repository108 Input Module110 Preprocessing Module112 Evaluation Module114 Assessment Module116 Output Module118 Device InterfaceDETAIL DESCRIPTIONEmbodiments, of the present disclosure, will now be described with reference to the accompanying drawing.Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail. The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a," "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "including," and "having," are open-ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.When an element is referred to as being "engaged to," "connected to," or "coupled to" another element, it may be directly engaged, connected, or coupled to the other element. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed elements.The present disclosure is a new set of methods for optimal decision-making in solving multicriteria decision-making problems. In general, for the problems of multicriteria decision making the assignment of weights is crucial, complex, and often requires the knowledge of domain experts. It also usually requires data normalization to remove any unnecessary bias and noise that has influenced the decisions and their alternatives. The disclosure includes methods to address these problems and additionally, a formulation method to determine the decision alternative weights.The present disclosure envisages a novel technique for optimal decision-making and methods thereof (hereinafter referred to as "100"). In the present disclosure, system 100 will now be described with reference to Figure 1, and method 200 will be described with reference to Figures 1A-1B, and Figure 2. The detailed working and operating of system 100 of the novel method of optimal decision making and methods thereof are explained with reference to Figures 1A-1B and Figure 2.Referring to Figure 1 illustrates a block diagram of system 100 for optimal decision-making, in accordance with an embodiment of the present disclosure. System 100 comprises a memory 102, a microprocessor 104, a data repository 106, an input module 108, a pre-processing module 110, an evaluation module 112, an assessment module 114, and an output module 116.The microprocessor 104 is coupled to the data repository 106 to execute the set of predefined instructions for executing one or more processing units for implementing the novel method of optimal decision-making.In an embodiment, the microprocessor 104 may be a processor with a memory 102. The microprocessor may be implemented as microprocessors, microcontrollers, microcomputers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions.Among other capabilities, the processor may fetch and execute the set of predefined instructions stored in the data repository 106. In an embodiment, the data repository 106 stores pre-trained models for pre-processing, evaluation, and assessment, and said models are used to perform statistical transformations and decision-making computations. The functions of the processor may be provided through the use of dedicated hardware as well as hardware capable of executing the set of predefined instructions. The microprocessor 104 may be configured to execute functions of one or more processing units including the input module 108, the pre-processing module 110, the evaluation module 112, the assessment module 114, and the output module 116.The input unit 108 which when executed by the microprocessor 104 is configured to receive a number of sets of input data with each set belonging to an independent criteria and within each set all independent data belonging to the same source type as input along with the metadata on the MCDM problem.The preprocessing module 110, which when executed by the microprocessor 104, retrieves the pre-trained preprocessing model from the data repository 106 and implements the preprocessing model on the sets of inputs received by the input module 108 to perform any pre-processing on the input data as required by the MCDM problem definition. In an aspect, the pre-processing module 110 prepares the input data into the MCDM criteria input data for evaluation.The evaluation module 112, which when executed by the microprocessor 104, retrieves the pre-trained evaluation model from the data repository 106 and implements the evaluation model on the sets of criteria input data received to perform the necessary computations. In an embodiment, the evaluation module 112 is further configured to invert criteria constraints by converting data points requiring maximization into minimization values and vice versa, using statistical transformation. The evaluation module 112 is configured to assign weights to each criterion based on either maximization or minimization of the MCDM problem, and said weights are used to compute the optimal decisions, and decision alternatives and resolve the MCDM problem in accordance with the illustrations in Figure 1A-1B and workflow described hereunder, a method 1001 of inversion of maximization or minimization of the criteria; a method 1002 of normalization of the data using distribution normalization; a method 1003 of assignment of weights to multiple criteria; and a method 1004 thereof and any derivations thereof used in data processing for optimal decision making with optimal decision and optimal decision alternatives.The assessment module 114, which when executed by the microprocessor 104, retrieves the pre-trained assessment model from the data repository 106 and implements the assessment model on the sets of optimal decisions and optimal decision alternatives and performs the necessary filters of results of the MCDM problem (if required). The assessment module 114 is configured to compute a set of N optimal decision alternatives based on a statistical analysis of the criteria and weights.The output module 116, which when executed by the microprocessor 104, generates the presentation results of the MCDM problem for output.In an embodiment, system 100 further comprises a device interface 118, which is configured to allow external devices to communicate with the system (100) for providing input data and retrieving the output results.In an embodiment, the pre-trained evaluation module is the implementation of a novel technique for optimal decision-making and methods thereof performing all the computations in the workflow shown in Figures 1A-1B and is performed by following the method steps: designing 501 of MCDM (Multi-criteria decision-making) problem 1000; formulating 502 the type of MCDM problem 1000; evaluating 503 the type of criteria of the data based on a maximization of the formulated problem 1000; inversion 504 of criteria of the data based on a minimization of the evaluated type of criteria 1001; extracting 505 the inverted criteria of the data and further mapping in at least one scenario 1001; mapping 506 the extracted inverted criteria of the data 1001; distribution normalizing 507 the mapped criteria of the data by selecting of normalization Z factor 1002; evaluating 508 the requirement of criteria weights for the formulated problem 1003; computing 509 the criteria weights for optimal decisions and decision alternatives 1003; computations 510 for the formulated MCDM problem 1004; selecting 511 optimal decisions and selecting N number of optimal decision alternatives based on formulated MCDM problem 1004; and solution 512 of optimal decision(s) and / or optimal decision alternatives to the formulated MCDM problem 1004. Now with reference to Figure 2, a flow diagram of method 200 for optimal decision-making is illustrated. The order in which method 200 is described is not intended to be construed as a limitation, and any number of the described method steps may be combined in any order to implement method 200, or an alternative method. Furthermore, method 200 may be implemented by processing resource or computing device(s) through any suitable hardware, non-transitory machine-readable medium / instructions, or a combination thereof. The method 200 comprises the following steps: receiving 201, by an input module 108 of a system 100, multiple sets of input data, each set corresponding to a distinct criterion in the MCDM problem; pre-processing 202, by a pre-processing module 110, said input data through a pre-trained pre-processing model stored in a data repository 106 to normalize using distribution normalization and remove biases from the data; evaluating 203, by an evaluation module 112, said pre-processed data using a pre-trained evaluation model, said evaluation comprising the steps of: inverting criteria constraints for criteria requiring maximization or minimization, normalizing using distribution normalization said data by applying statistical techniques, and assigning weights to the criteria based on statistical analysis; assessing 204, by an assessment module 114, optimal decision alternatives based on the criteria weights and the MCDM problem's requirements; and generating 205, by an output module 116, the results of the MCDM problem, including one or more optimal decisions and a set of optimal decision alternatives.In an embodiment, the pre-processing 202 further comprises distribution normalizing 202a the input data to ensure that the mean of the normalized data for each criterion is unity and the covariance between the criteria is zero.In an embodiment, the normalization is performed by distribution normalizing the input data based on the statistical mean of each criterion, ensuring that data points are scaled appropriately for decision-making.In an embodiment, the criteria inversion for maximization or minimization is performed by converting data points requiring maximization into minimization values and vice versa, using a statistical transformation based on the relationship between the constraints.In an embodiment, the assignment of weights to multiple criteria is based on the maximization or minimization of the formulated MCDM problem, such that the weight for each criterion is computed by either selecting the maximum or minimum value depending on the nature of the problem.In an embodiment, the optimal decision alternatives are derived by computing the decision value for each decision alternative and selecting the N optimal decision alternatives based on the highest or lowest values, depending on whether the MCDM problem is one of maximization or minimization.In an embodiment, a method 1001 of inversion of criteria constraints of maximization to minimization and vice versa as described below,Let us consider that there are m independent criteria Ci each with k data points xj, such that i = 1,2,...,m and j = 1,2,…,kLet us consider that if the criteria Ci requires an inversion of criteria constraint from minimization to maximization under the MCDA problem of maximization, then the k data points of the Ci criteria can be inverted using the following method,Let xjmin denote the datapoint minimization constraint on the criteria, then the equivalent datapoint xjmax for maximization constraint on the criteria.Mapping Scenario 1: xjmin and xjmax belongs to R+ is given by,Equation (1)Mapping Scenario 2: xjmin belongs to R and xjmax belongs to R+ is given by,Equation (2)Mapping Scenario 3: xjmin and xjmax belongs to R is given by,Equation (3)Similarly, if xjmax denotes data points under the maximization constraint of the criteria, then the equivalent datapoints xjmin for minimization constraint on the criteria is given by,Mapping Scenario 1: xjmax and xjmin belongs to R+ is given by,Equation (4)Mapping Scenario 2: xjmax belongs to R and xjmin belongs to R+ is given by,Equation (5)Mapping Scenario 3: xjmax and xjmin belongs to R is given by,Equation (6)In an embodiment, a method 1002 of distribution normalization of the data with unique statistical properties as described below,Let us consider that there are m independent criteria Ci each with k data points xj, such that i = 1,2,...,m and j = 1,2,…,kThen, the distribution normalization for the criteria Ci is given as Ni, in equation (7) below,Equation (7)where μ_i is the statistical mean or the expectation of the set E(X_i) of k data points for the ith criteria given in equation (8) below,Equation (8)Axiom I: The distribution normalized Mean for each independent observable is reduced to unity and the normalized total mean is reduced to unity.Proof for Normalized Mean:The distribution normalized statistical mean μni or the distribution normalized expectation E(Xni) of the set of k data points for the ith criteria can be formulated from equation (8) as follows, Equation (9)Substituting equation (7),Equation (10)Equation (11)Equation (12)From equation (12) it can be seen that the distribution normalized statistical mean is reduced to unity.Proof for Normalized Total Mean:The distribution normalized statistical mean μ_n or the distribution normalized expectation of the set E(X_n) of all data points for all the m criteria can be formulated from equation (8) as follows,Equation (13)Where N is the total number of all the data points in equation (13) given as,N=m k (14)Substituting equation (9),Equation (14)Equation (15)Rewriting the above equation,Equation (17)Substituting equation (8),Equation (19)An analogy of the above equation is the relationship between the Total Mean and Mean of each criterion,Equation (20)Equation (21)Thus, it is proved that the distribution normalized total mean reduces to unity.Axiom II: The distribution normalized covariance between all of the m criterions combined is reduced to zeroProof of Normalized Covariance:The s^2 is the statistical variance of n data points is given in the following equation (21) below,Equation (22)Then, the sum of the distribution normalized variance of each criterion can be from equation (22) as follows,Equation (23)Substituting equation (12), Equation (24) Similarly, the distribution normalized total variance (dho)n2 can be written from equation (21) as follows,Equation (25)Substituting equation (20)Equation (26)Multiplying and dividing by (k-1),Equation (27)Rewriting the above equation,Equation (28)Substituting equation (23), Equation (28)From the above equation, it can be seen that distribution normalized total variance has no relation with the covariances of criteria. The rationality of the above equation can be inferred from the following derivation,Let us consider the following equation, with (dho)2 as the total variance, (dho)i^2 as the variance of ith criteria and d as a residual,Equation (29)Substituting equation (21), Equation (30)Rewriting the above equation,Equation (31)Equation (32)Equation (33)From equations (8) and (19) Equation can be written as, Equation (34)Equation (35)Equation (36) with, EquationSubstituting the above for Equation in equation (33), Equation (37)Equation (38)Equation (39)Under distribution normalization, Equation (40)Axiom III: The distribution normalization of the distribution normalized data yields the same results, thus resulting in a unique form of reduced data for a given set of data points.Proof of Complete Normalization:From equation (21), it can be deduced that there will be no change in the normalized data points when μ_i=1 for the ith criteria.All of the described methods above are applicable even if the datapoints k is variable for each criterion by filling in the variations with datapoints taking the value of 1 after applying the distribution normalization technique stated herein. Further, the optimality of the distribution normalization conditions method holds good even if the solution is multiplied by a factor z which is a constant positive real number for all i given in equation (17) such that the Pearson's correlation coefficient between the variances of all criteria with respect to distribution normalization using the equation (7) equals unity is satisfied and the equation (7) with the z factor is given in equation (67), Distribution Normalization with z factor:Equation (41)The z factor results only in a distribution normalization with a different mean instead of unity.The Biological Analogy in connection with the above Mathematical Proof is provided below as a SUPPLEMENT to augment the claims and descriptions in this disclosure. The normalization described herein above is to be referred to as "Distribution Normalization" and any Artificial Intelligence implementations of the Distribution Normalization are to be referred to as "Artificial Human Intelligence" from the biological connection.SUPPLEMENT:THE BIOLOGICAL ANALOGYThe method (1002) connected to the distribution normalizing step (507) as shown in Figure 1A describing the distribution normalization is supposedly the biological connection to the natural intelligence and natural memory that is expressed by humans. Initiation of the neuron triggers an electric pulse that is distributed and transmitted through the neural pathways controlled through the neurotransmitters in the synapses of neurons. The distribution of electric pulse along the neural pathway is essentially the distribution normalization resulting in natural intelligence. The control of neurotransmitters at the synapses is essentially the weights or reinforcements that essentially form the natural memory. The neural pathways are essentially the information flow that results in computations over the natural memory resulting in natural intelligence of that of humans or any other biological systems. In this context, the normalization method (1002) in computing the normalizing step (507) shall be referred to as distribution normalization and any Artificial Intelligence Systems based on the distribution normalization shall be referred to as Artificial Human Intelligence Systems.In an embodiment, a method 1003 of assignment of weights for the multiple criteria in MCDM:The method of assignment of weights for the multiple criteria is based on the maximization or minimization of the MCDM problem, resulting in an optimal solution and optimal decision alternatives. The details of the methodology are provided herein below,Decision Making for the MCDM Problem:Let us consider that there are m independent criteria Ci each with k data points xj, such that i = 1,2,...,m and j = 1,2,…,k and that can be assigned normalized weights wi such that Equation Equation Then, the MCDM problem can be an additive problem stated in the following equation,Equation The optimal decision is arrived by assignment of weights using the following equation (70),Equation (70)The optimal decision for the MCDM problem is derived by computing the decision value Dj from the equation (69) and the optimal decision OD from the equation (71) below,Equation (71)The optimal decision alternatives are arrived by assignment of weights using the following equation (72),Equation (72)In an embodiment, a method 1004 of optimal decision alternatives for the MCDM problem is derived by computing the decision value D_j from the equation (69) and the set of N optimal decision alternatives from the equation (73) below,Equation (73)where max_N and min_N are N maximum and N minimum values functionIn an embodiment, the present disclosure reduces the process complexity of arriving at weights based on the statistics of the data rather than a priori knowledge. On the part of normalization, the method according to the present disclosure is a statistical formulation based on the data and has unique statistical properties. The other part is a new method of deriving the weights of decision alternatives.In an embodiment, the present disclosure improves the decision-making process by reducing the complexity, a part of it has some unique statistical properties and a method of assessing decision alternatives which seems so far unavailable.In an embodiment, a novel technique for optimal decision-making and methods thereof are performed by the mathematical expressions implemented in one or more computer-usable storage media (including but not limited to a disk memory, a CD-ROM, optical memory, and the like) and / or one or more modules that include computer-usable program code.In an embodiment, the mathematical expressions herein are the same as those described above and may be implemented by using a processor. A function of the processing element may be the same as a function of the mathematical expression performed by the processor using machine learning techniques and / or artificial intelligence as described in FIGURES. 1, 1A-1B, and 2.In an embodiment, it can be learned that the mathematical expressions may perform some or all steps performed by one or more modules in a first manner, to be specific, by invoking the program stored in the storage element; or may perform some or all steps performed by the device in a second manner, to be specific, by using a hardware integrated logic circuit in the processing element in combination with instructions; or may certainly perform, by combining the first manner and the second manner, some or all steps performed by the network device.The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment but are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.TECHNICAL ADVANCEMENTSThe present disclosure described hereinabove has several technical advantages including, but not limited to, systems for optimal decision making and methods thereof, that; provides an optimal method of normalization of data using distribution normalization, provides mathematical formulation with unique statistical properties that can be directly applied and extended for different applications, can be directly applied to implementations in software, algorithms, and products of GIS systems, Decision Support Systems (DSS), Data Analysis, Artificial Intelligence, and Machine Learning Systems.In order to restrict the use of the methods and techniques stated herein for civilian applications and use, a sub-optimal Pearson's Correlation Coefficient correlation of 5 % to the optimal decision space by either data or variance is to be allowed or restricting the selection of distribution normalization factor Z > (k + 2) or explicitly written-off separately (the restriction shall be implemented in the pre-trained assessment module).The foregoing disclosure has been described with reference to the accompanying embodiments which do not limit the scope and ambit of the disclosure. The description provided is purely by way of example and illustration.The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.Any discussion of devices, articles or the like that has been included in this specification is solely for the purpose of providing a context for the disclosure. It is not to be taken as an admission that any or all of these matters form a part of the prior art base or were common general knowledge in the field relevant to the disclosure as it existed anywhere before the priority date of this application. While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.

Claims

1. A system (100) for optimal decision-making in solving multi-criteria decision-making (MCDM) problems, comprising: - a memory (102) configured to store instructions and data; and - a microprocessor (104) configured to execute said instructions to: - receive multiple sets of input data, each set corresponding to a distinct criterion in the MCDM problem, via an input module (108); - pre-process said input data, using a pre-trained pre-processing model stored in a data repository (106), via a pre-processing module (110) to distribution normalize and remove biases; - evaluate the pre-processed data, using a pre-trained evaluation model, via an evaluation module (112), wherein said evaluation includes: - inverting criteria constraints for criteria requiring maximization or minimization, - distribution normalizing said data based on statistical analysis, and - assigning weights to the criteria for optimal decision-making; - assess optimal decisions and decision alternatives, using an assessment module (114); and - generate results for the MCDM problem, including one or more optimal decisions and decision alternatives, via an output module (116).

2. The system (100) as claimed in claim 1, wherein the pre-processing module (110) is further configured to distribution normalize the input data such that the statistical mean of the distribution normalized data is unity, and the covariance between criteria is reduced to zero.

3. The system (100) as claimed in claim 1, wherein the evaluation module (112) is further configured to invert criteria constraints by converting data points requiring maximization into minimization values and vice versa, using statistical transformation.

4. The system (100) as claimed in claim 1, wherein the evaluation module (112) is configured to assign weights to each criterion based on either maximization or minimization of the MCDM problem, and said weights are used to compute the optimal decisions, and decision alternatives.

5. The system (100) as claimed in claim 1, wherein the assessment module (114) is configured to compute a set of N optimal decision alternatives based on a statistical analysis of the criteria and weights.

6. The system (100) as claimed in claim 1, further comprising a device interface (118), is configured to allow external devices to communicate with the system (100) for providing input data and retrieving the output results.

7. The system (100) as claimed in claim 1, wherein the data repository (106) stores pre-trained models for pre-processing, evaluation, and assessment, and said models are used to perform statistical transformations and decision-making computations.

8. A method (200) for optimal decision-making in solving multi-criteria decision-making (MCDM) problems, comprising: - receiving (201), by an input module (108) of a system (100), multiple sets of input data, each set corresponding to a distinct criterion in the MCDM problem; - pre-processing (202), by a pre-processing module (110), said input data through a pre-trained pre-processing model stored in a data repository (106) to distribution normalize and remove biases from the data; - evaluating (203), by an evaluation module (112), said pre-processed data using a pre-trained evaluation model, said evaluation comprising the steps of: - inverting criteria constraints for criteria requiring maximization or minimization, - distribution normalizing said data by applying statistical techniques, and - assigning weights to the criteria based on statistical analysis; - assessing (204), by an assessment module (114), optimal decision alternatives based on the criteria weights and the MCDM problem's requirements; and - generating (205), by an output module (116), the results of the MCDM problem, including one or more optimal decisions and a set of optimal decision alternatives.

9. The method (200) as claimed in claim 8, wherein the pre-processing (202) further comprises normalizing (202a) the input data to ensure that the mean of the distribution normalized data for each criterion is unity and the covariance between the criteria is zero.

10. The method (200) as claimed in claim 8, wherein the normalization is performed by distribution normalizing the input data based on the statistical mean of each criterion, ensuring that data points are scaled appropriately for decision-making.

11. The method (200) as claimed in claim 8, wherein the criteria inversion for maximization or minimization is performed by converting data points requiring maximization into minimization values and vice versa, using a statistical transformation based on the relationship between the constraints.

12. The method (200) as claimed in claim 8, wherein the assignment of weights to multiple criteria is based on the maximization or minimization of the formulated MCDM problem, such that the weight for each criterion is computed by either selecting the maximum or minimum value depending on the nature of the problem.

13. The method (200) as claimed in claim 8, wherein the optimal decision alternatives are derived by computing the decision value for each decision alternative and selecting the N optimal decision alternatives based on the highest or lowest values, depending on whether the MCDM problem is one of maximization or minimization.