Medical material selection method and system considering individual semantic continuous learning

Abstract

The invention discloses a medical material selection method and system considering individual semantic continuous learning, and relates to the technical field of medical material selection, and the method comprises the steps: 1, determining a value of a value scale of a personalized interval at a moment t; step 2, calculating a group consensus level at the t moment, directly entering step 4 when the group consensus level is greater than or equal to a predefined consensus threshold value, identifying a decision expert set which needs to implement information modification at the t moment when the group consensus level is less than the predefined consensus threshold value, and modifying language preference information of each expert in the decision expert set, entering the step 3; 3, if t is equal to t + 1, circulating the step 1 to the step 2 to realize personalized semantic updating at the moment t, and calculating a group consensus level at the same time; 4, selecting a finally selected brand by using an information aggregation method; according to the medical material selection method and system, quantification and real-time updating of language information of different decision-making experts are realized, so that brands can be selected more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of medical supply selection, and in particular to a medical supply selection method and system considering continuous learning of individual semantics. Background Art

[0002] There is increasing emphasis on involving various stakeholders in the medical decision-making process, promoting direct communication, and incorporating their input into the production and application of evidence. While the selection of medical supplies emphasizes value, this value is multidimensional, and different stakeholders place varying emphasis on different aspects, which can sometimes lead to conflict. Consensus-building processes aim to minimize these conflicts, promote coordination among stakeholders, and enhance decision experts' acceptance of the final decision outcome. Although numerous studies have explored consensus models for group decision-making based on linguistic information, they still have some shortcomings due to their inherent uncertainty and complexity. These limitations are primarily manifested in two aspects: Existing research addresses the personalized semantics between decision experts by designing consensus-driven optimization models. However, in actual decision-making processes, people prefer to use interval-based representations to better capture the hesitant nature of decision experts. Furthermore, individual cognitive abilities may change over time.

[0003] Chinese patent CN114819282A discloses an emergency task planning scheme evaluation method and system based on personalized consensus, including obtaining a personal decision preference matrix determined by each evaluation expert after pairwise comparison of different emergency task planning schemes based on a given number of emergency task planning schemes. The personal decision preference matrix uses a language distribution preference relationship as a form of expression for decision opinions. By quantifying language items, not only can the language items in the decision matrix be made operational, but the personalized individual semantics of the evaluation experts can also be obtained. Based on the initial group consensus, an automatic feedback algorithm is used to adjust the personal preferences of the evaluation experts, and the adjusted interval fuzzy preference relationship of each evaluation expert is obtained. The evaluation information of the planning schemes with low consensus levels corresponding to the evaluation experts with low consensus levels can also be automatically adjusted.

[0004] However, patent CN114819282A only considers the static, personalized individual semantics of decision makers, meaning their individual cognition does not change over time. In actual decision-making, however, decision makers' individual perspectives and cognitions continuously learn and dynamically adjust through interaction with other decision makers, making them unlikely to remain static. Therefore, evaluating solutions based on static, personalized individual semantics can significantly impact the final evaluation results. Summary of the Invention

[0005] Based on the technical problems existing in the background technology, the present invention proposes a medical supplies selection method and system that considers continuous learning of individual semantics, which shows greater flexibility and applicability in modeling and extracting group information, and can effectively reduce the impact of outliers.

[0006] The present invention proposes a medical supplies selection method that considers continuous learning of individual semantics, including: Step 1: Determine the consistency index of interval fuzzy preference relationship and the deviation of semantic information between decision experts. The value of the personalized interval numerical scale at each moment, wherein the personalized interval numerical scale is the interval numerical scale corresponding to the language item in the language preference relationship of each decision expert; Step 2: Use the decision-making experts Moment weight and consensus level calculation The group consensus level at the moment, when the group consensus level is greater than or equal to the predefined consensus threshold, directly go to step 4, when the group consensus level is less than the predefined consensus threshold, identify The decision expert set that needs to modify information at any time and modify the language preference information of each expert in the decision expert set, and then proceed to step 3; Step 3: , looping steps 1 and 2, updating the personalized semantics at time t based on the updated language preference information, and calculating the group consensus level at the same time, until the group consensus level reaches the pre-defined consensus threshold; Step 4: Calculate the preference information of each decision-making expert for each medical supply brand and aggregate the preference information of all experts to obtain the information particles of each medical supply brand, and select the medical supply brand that makes the median value of the information particles the largest as the final selected brand.

[0007] Furthermore, before step 1, a decision matrix of each decision expert and a personalized interval numerical scale of each expert under a language item in a language preference relationship are first obtained, wherein the decision matrix is ​​expressed in a language preference relationship.

[0008] Furthermore, in step 1, by minimizing the consistency index of interval fuzzy preference relations and the deviation of semantic information between decision experts, we can determine The numerical value of the personalized interval numerical scale at each moment, the objective function is: ; in, is the total number of decision-making experts, Index for decision-making experts, For decision-making experts exist The weight of the moment, For decision-making experts exist The variables at the moment, , For decision-making experts exist Interval fuzzy preference relation of time The consistency index, For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, Indicates distance, is the total number of medical supplies brands, They are respectively the medical supplies brand index.

[0009] Furthermore, in step 1, by minimizing the consistency index of interval fuzzy preference relations and the deviation of semantic information between decision experts, we can determine The value of the personalized interval numerical scale at each moment, with the following constraints: ; in, , for Corresponding to the left endpoint of the interval fuzzy preference relation, for Corresponding to the right endpoint of the interval fuzzy preference relation, For decision-making experts exist time The left endpoint of the personalized interval numerical scale, For decision-making experts exist time The right endpoint of the personalized interval numerical scale, For decision-making experts exist Always check medical supplies brands Relative to medical supplies brands Language preference information, Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, They are No. 1, 、 、 and Cut-off points, is the language item index, is the total number of language items, which is also the total number of cutoff points. Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, is the constraint value, For decision-making experts exist The variables at the moment, For decision-making experts The variable at time 0.

[0010] Furthermore, in step 2, The level of group consensus at the moment The calculation formula is as follows: ; in, For decision-making experts exist The weight of the moment, For decision-making experts exist The consensus level at the moment.

[0011] Furthermore, in step 2, the language preference information of each expert in the decision-making expert set is modified, and the corresponding objective function is: ; in, , For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for Corresponding to the left endpoint of the interval fuzzy preference relation, for Corresponding to the right endpoint of the interval fuzzy preference relation, is the total number of medical supplies brands, They are respectively the medical supplies brand index.

[0012] Furthermore, in step 2, the language preference information of each expert in the decision-making expert set is modified, and the corresponding constraints are: ; in, is a predefined consensus threshold, For decision-making experts exist The temporary consensus level at time t, which is based on the decision-making experts at time t The personalized interval numerical scale is based on the updated language preference information The calculated consensus level, For decision-making experts exist Always update on medical supplies brands Relative to medical supplies brands Language preference information, for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, is the weight parameter used to balance and The importance of Represents a function that converts interval-valued fuzzy preference information into linguistic information.

[0013] Furthermore, in step 4, the preference information of each decision-making expert for each medical supply brand is calculated and the preference information of all experts is aggregated to obtain the information granules of each medical supply brand. Specifically, Calculate the preference information of each decision expert for each medical supply brand ,in, , Decision-making experts For the first The left and right endpoints of the preference relationship for each brand of medical supplies; Aggregate all experts' aggregated information to obtain information particles of each medical supplies brand. ,Right now: ; in, represents the coverage of information granules, Indicates the specificity of the information particle.

[0014] A medical supplies selection system considering continuous learning of individual semantics, comprising a personalized interval numerical scale value determination module, a personalized semantic update module, a feedback adjustment module, and an aggregate selection module; The personalized interval numerical scale value determination module is used to determine the value of the interval numerical scale by minimizing the consistency index of the interval fuzzy preference relationship and the deviation of the semantic information between decision experts. The value of the personalized interval numerical scale at each moment, wherein the personalized interval numerical scale is the interval numerical scale under the language item in the language preference relationship of each decision expert; The personalized semantic update module is used to utilize the Moment weight and consensus level calculation The group consensus level at the moment, when the group consensus level is greater than or equal to the predefined consensus threshold, directly enter the aggregation selection module, when the group consensus level is less than the predefined consensus threshold, identify The decision expert set that needs to modify information is always implemented, and the language preference information of each expert in the decision expert set is modified to achieve a group consensus level that reaches a pre-defined consensus threshold.

[0015] The feedback adjustment module is used to , looping the personalized interval numerical scale value determination module to the personalized semantics update module, for updating the personalized semantics corresponding to the decision maker who has modified the language preference information until the group consensus is greater than or equal to a pre-defined consensus threshold; The aggregation selection module is used to calculate the preference information of each decision-making expert for each medical supply brand and aggregate the preference information of all experts to obtain information particles of each medical supply brand, and select the medical supply brand that makes the median value of the information particles the largest as the final selected brand.

[0016] Furthermore, in the personalized interval numerical scale value determination module, the objective function is: ; in, is the total number of decision-making experts, Index for decision-making experts, For decision-making experts exist The weight of the moment, For decision-making experts exist The variables at the moment, , For decision-making experts exist Interval fuzzy preference relation of time The consistency index, For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, Indicates distance, is the total number of medical supplies brands, They are the medical supplies brand index; In the feedback adjustment module, the language preference information of each expert in the decision-making expert set is modified, and the corresponding objective function is: ; in, , for Corresponding to the left endpoint of the interval fuzzy preference relation, for Corresponding to the right endpoint of the interval fuzzy preference relation.

[0017] The advantages of the medical supplies selection method and system provided by the present invention, which considers continuous learning of individual semantics, are that by collecting multiple rounds of language preference information and historical data generated during the consensus-building process, and by capturing the personalized expressions of decision-making experts, the language information of different decision-making experts can be quantified and updated in real time, providing a new method for solving medical supplies management problems involving language information. In addition, this embodiment introduces an information aggregation method based on information granularity, in accordance with the principle of reasonable granularity. This method intuitively explains the optimal allocation of particles in the original digital data and can effectively summarize and describe collective opinions at a higher level of abstraction. Compared with previous studies, this method demonstrates greater flexibility and applicability in modeling and extracting group information, and can effectively reduce the impact of outliers. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0019] The technical solutions of the present invention are described in detail below through specific embodiments. Numerous specific details are set forth in the following description to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways than those described herein, and those skilled in the art may make similar modifications without departing from the scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0020] In this embodiment, quantifying linguistic terms not only makes the linguistic terms in the decision matrix operational, but also allows for the personalized semantics of each decision expert. Furthermore, by combining personalized semantic updates at different times with information aggregation methods, accurate selection of medical supply brands can be achieved.

[0021] like Figure 1 As shown, the present invention proposes a medical supplies selection method considering continuous learning of individual semantics, including: Step 1: Determine the consistency index of interval fuzzy preference relationship and the deviation of semantic information between decision experts. The value of the personalized interval numerical scale at each moment, wherein the personalized interval numerical scale is the interval numerical scale corresponding to the language item in the language preference relationship of each decision expert; Step 2: Use the decision-making experts Moment weight and consensus level calculation The group consensus level at the moment, when the group consensus level is greater than or equal to the predefined consensus threshold, directly go to step 4, when the group consensus level is less than the predefined consensus threshold, identify The decision expert set that needs to be modified at any time and the language preference information of each expert in the decision expert set need to be modified to achieve Personalized semantic update at the moment, proceed to step 3; Step 3: , loop steps one to two to achieve Personalized semantic updates at each moment, while calculating the group consensus level until the group consensus level is greater than or equal to the predefined consensus threshold; Step 4: Calculate the preference information of each decision-making expert for each medical supply brand and aggregate the preference information of all experts to obtain the information particles of each medical supply brand, and select the medical supply brand that makes the median value of the information particles the largest as the final selected brand.

[0022] This embodiment aims to quantify and update the language information of different decision-makers in real time by collecting historical data generated by multiple rounds of language preference information and consensus-building processes, capturing the personalized expressions of decision-makers, and providing a new approach to solving medical supply management problems involving language information. Furthermore, this embodiment introduces an information aggregation method based on information granularity, in accordance with the principle of reasonable granularity. This method intuitively explains the optimal allocation of particles in raw digital data and can effectively summarize and describe collective opinions at a higher level of abstraction. Compared with previous research, this method demonstrates greater flexibility and applicability in modeling and extracting group information, and can effectively reduce the impact of outliers.

[0023] In one embodiment, before step 1, the decision matrix of each decision expert and the personalized interval numerical scale of each expert under the language item in the language preference relationship are first obtained. The decision matrix is ​​expressed in the language preference relationship, specifically: Unlike conventional brand selection evaluation methods, the selection process for medical supply brands often significantly impacts the public. Therefore, the decision-making process typically requires the participation of numerous expert decision-makers from diverse professional backgrounds. However, within traditional selection methods, many researchers have investigated evaluation models with varying numerical preference relationships. Notably, the evaluation of medical supply brands presents unique characteristics, making it difficult to accurately describe the individual opinions of expert decision-makers using numerical values. In contrast, in the actual evaluation process of this embodiment, decision-makers use linguistic terms to express their personal preferences. However, linguistic terms are not operational, and existing research generally assumes that decision-makers have the same understanding of the linguistic terms used. However, in daily life, people generally believe that language means different things to different people. For example, when evaluating the quality of a project, three decision-makers all agree that the quality of the project is "good." However, if the three experts are asked to adjust this "good" into a numerical value, the first decision-maker might give it 0.8 points, the second decision-maker might give it 0.85 points, and the third decision-maker might give it 0.9 points.

[0024] Therefore, in order to avoid the above technical defects, this embodiment specifically sets the following steps: A. Obtain the decision matrix of each decision expert; Pre-given Brands of medical supplies are used express, For the Medical supply brands, each decision expert makes a pairwise comparison of the given medical supply brands to provide his / her decision opinion, namely the decision matrix, which is expressed by linguistic preference relations (LPR). A decision-making expert Given LPR, where Representative decision-making experts For the first Medical supplies brands Relative to the Medical supplies brands The preference degree of a given set of language items , a set of language items The total number of language items in , and , , Representative evaluation information The subscript of the language item, Representative evaluation information The subscript of the language item, For the language items, is the total number of language items.

[0025] B. obtaining personalized interval numerical scales for each expert under the language item in the language preference relationship; pass Cutoff points composition interval , representing decision-making experts exist Moment language item The personalized interval numerical scale under , … ; in, For the Cut-off points, For the intervals, Representative decision-making experts exist Moment language item The left endpoint of the personalized interval numerical scale, Representative decision-making experts exist Moment language item The right endpoint of the personalized interval numerical scale, Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, Representative decision-making experts exist Moment language item The left endpoint of the personalized interval numerical scale, Representative decision-making experts exist Moment language item The right endpoint of the personalized interval numerical scale.

[0026] and time The cutoff points satisfy: , , , , , , Represents the constraint value, satisfying , Respectively 、 、 A cut-off point.

[0027] C. Obtaining the interval fuzzy preference relation corresponding to the language preference relation; interval-interval fuzzy preference relations , For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of is the total number of medical supplies brands, of which , , , for Corresponding to the right endpoint of the interval fuzzy preference relation, For decision-making experts exist Always use the evaluation information represented by the language item The left endpoint of the personalized interval numerical scale, For decision-making experts exist Always use the evaluation information represented by the language item The right endpoint of the personalized interval numerical scale, For decision-making experts exist Always check medical supplies brands Relative to medical supplies brands Language preference information.

[0028] In one embodiment, step 1 is to determine the consistency index of the interval fuzzy preference relationship and the deviation of the semantic information between decision experts. The numerical value of the personalized interval numerical scale at each moment, the objective function is specifically: ; The specific constraints are: ; in, is the total number of decision-making experts, Index for decision-making experts, For decision-making experts exist The weight of the moment, For decision-making experts exist The variables at the moment, , For decision-making experts exist Interval fuzzy preference relation of time The consistency index, For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, Indicates distance, is the total number of medical supplies brands, They are the medical supplies brand index, For decision-making experts exist The variables at the moment, For decision-making experts The variable at time 0, For decision-making experts exist The weight of the moment, For decision-making experts exist The consensus level at the moment, They are indexes of medical supplies brands.

[0029] in,

[0030] in, , , and They correspond to the left endpoints of interval fuzzy preference relations, For decision-making experts exist Always use the evaluation information represented by the language item The left endpoint of the personalized interval numerical scale, For decision-making experts exist Always use the evaluation information represented by the language item The left endpoint of the personalized interval numerical scale.

[0031] Weight , Representative decision-making experts exist The similarity of time, Representative decision-making experts exist The similarity of the moments, where , Represents the number of decision-making experts. Representative decision-making experts exist 0-1 variable at the moment, when Representative decision-making experts exist The consensus level at the moment is less than the pre-given consensus threshold, otherwise .when season . represent Shike Medical Supplies Brand Relative to The degree of group preference, are the left and right endpoints of the group preference degree, .

[0032] Representative decision-making experts exist Shike Medical Supplies Brand Relative to The degree to which the assessment information deviates from the group information; ; In one embodiment, step 2, using each decision expert to Moment weight and consensus level calculation The group consensus level at the moment, when the group consensus level is greater than or equal to the predefined consensus threshold, directly go to step 4, when the group consensus level is less than the predefined consensus threshold, identify The decision expert set that needs to modify information at any time and the language preference information of each expert in the decision expert set are modified to enter step three, specifically: The level of group consensus at the moment Specifically: ; in, Representative decision-making experts exist The consensus level at the moment, .

[0033] Pre-defined consensus thresholds ,if If the group reaches a satisfactory level of consensus, proceed to step 4. Otherwise, identify The decision expert set that needs to modify information is always implemented, and the language preference information of each expert in the decision expert set is modified, and then step three is entered.

[0034] Among them, identification A set of decision-making experts who need to implement information modification at any time , specifically: ; Then, modify Momentary Decision Experts The language preference information of each decision expert in is expressed as , ; For decision-making experts exist Always check medical supplies brands Relative to medical supplies brands Language preference information.

[0035] The objective function and constraints are modified based on the following Language preference information of each decision expert in: ; ; in, is the consensus threshold, For decision-making experts exist Based on the updated language preference information in the personalized interval numerical scale at all times The calculated consensus level, Representatives in decision-making experts Personalized interval numerical scale Under this circumstance, the evaluation information represented by the language item is used The left endpoint of the personalized interval numerical scale, Representatives in decision-making experts Personalized interval numerical scale Under this circumstance, the evaluation information represented by the language item is used The right endpoint of the personalized interval numerical scale. Representative decision-making experts In personalized interval numerical scale Next, based on the updated language preference information The corresponding interval fuzzy preference relation The calculated consensus level, represents the function that converts interval fuzzy preference information into language information, Superscript express time, represents the inverse function, is the weight parameter used to balance and The importance of , .make , return to step 1.

[0036] In one embodiment, step 4 is to calculate the preference information of each decision expert for each medical supply brand and aggregate the preference information of all experts to obtain information particles for each medical supply brand. The medical supply brand that maximizes the median value of the information particles is selected as the final selected brand. Specifically, During the aggregation process, decision-making experts with greater weights may manipulate opinions to achieve predetermined goals. Traditional information aggregation methods are generally difficult to effectively summarize and describe collective opinions at a higher level of abstraction, and are therefore not suitable for aggregating decision information that is agreed upon among decision-making experts.

[0037] In order to solve the above problems, the information aggregation method proposed in this embodiment is specifically as follows: (a1) Calculate the preference information of each option ,in, , Decision-making experts For the first The left and right endpoints of the preference relationship for medical supply brands.

[0038] (a2) Aggregate the aggregated information of all experts to obtain the information particles of each medical supplies brand. ， are the left and right endpoints of the information particle, that is, ; in, Indicates the coverage of information granules.

[0039] ; ; Representative evaluation information The midpoint of . Indicates the specificity of the information particle, ,in Represents the exponential function.

[0040] Therefore, this embodiment sets up the above-mentioned medical supplies selection method by taking into account the individual semantic expression and consensus reaching issues of various stakeholders in the medical supplies selection process, aiming to achieve continuous learning of individual semantic information of decision experts, while improving the satisfaction and decision quality of decision results.

[0041] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A medical supplies selection method considering continuous learning of individual semantics, characterized by: include: Step 1: Determine the consistency index of interval fuzzy preference relationship and the deviation of semantic information between decision experts. The value of the personalized interval numerical scale at each moment, wherein the personalized interval numerical scale is the interval numerical scale under the language item in the language preference relationship of each decision expert; Step 2: Use the decision-making experts Moment weight and consensus level calculation The group consensus level at the moment, when the group consensus level is greater than or equal to the predefined consensus threshold, directly go to step 4, when the group consensus level is less than the predefined consensus threshold, identify The decision expert set that needs to be modified at any time and the language preference information of each expert in the decision expert set need to be modified to achieve Personalized semantic update at the moment, proceed to step 3; Step 3: , loop through steps 1 and 2, and update based on the updated language preference information The personalized semantics at the moment and the group consensus level are calculated at the same time until the group consensus level reaches the pre-defined consensus threshold; Step 4: Calculate the preference information of each decision-making expert for each medical supply brand and aggregate the preference information of all experts to obtain the information particles of each medical supply brand, and select the medical supply brand that makes the median value of the information particles the largest as the final selected brand.

2. The medical supplies selection method according to claim 1, characterized in that: Before step 1, the decision matrix of each decision expert and the personalized interval numerical scale of each expert under the language item in the language preference relationship are first obtained, and the decision matrix is ​​expressed in the language preference relationship.

3. The medical supplies selection method according to claim 2, characterized in that: Step 1: Determine the consistency index of interval fuzzy preference relationship and the deviation of semantic information between decision experts. The numerical value of the personalized interval numerical scale at each moment, the objective function is: in, is the total number of decision-making experts, Index for decision-making experts, For decision-making experts exist The weight of the moment, For decision-making experts exist The variables at the moment, , For decision-making experts exist Interval fuzzy preference relation of time The consistency index, For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, Indicates distance, is the total number of medical supplies brands, They are respectively the medical supplies brand index.

4. The medical supplies selection method according to claim 3, characterized in that: Step 1: Determine the consistency index of interval fuzzy preference relationship and the deviation of semantic information between decision experts. The value of the personalized interval numerical scale at each moment, with the following constraints: in, , for Corresponding to the left endpoint of the interval fuzzy preference relation, for Corresponding to the right endpoint of the interval fuzzy preference relation, For decision-making experts exist time The left endpoint of the personalized interval numerical scale, For decision-making experts exist time The right endpoint of the personalized interval numerical scale, For decision-making experts exist Always check medical supplies brands Relative to medical supplies brands Language preference information, Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, They are No. 1, 、 、 and Cut-off points, is the language item index, is the total number of language items, which is also the total number of cutoff points. Decision-making experts exist Moment language item The left and right endpoints of the personalized interval numerical scale, is the constraint value, For decision-making experts exist The variables at the moment, For decision-making experts The variable at time 0.

5. The medical supplies selection method according to claim 1, characterized in that: In step 2, The level of group consensus at the moment The calculation formula is as follows: in, For decision-making experts exist The weight of the moment, For decision-making experts exist The consensus level at the moment.

6. The medical supplies selection method according to claim 1, characterized in that: In step 2, the language preference information of each expert in the decision-making expert set is modified, and the corresponding objective function is: in, , For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for Corresponding to the left endpoint of the interval fuzzy preference relation, for Corresponding to the right endpoint of the interval fuzzy preference relation, is the total number of medical supplies brands, They are respectively the medical supplies brand index.

7. The medical supplies selection method according to claim 6, characterized in that: In step 2, the language preference information of each expert in the decision-making expert set is modified, and the corresponding constraints are: in, is the consensus threshold, For decision-making experts exist Based on the updated language preference information in the personalized interval numerical scale at all times The calculated consensus level, For decision-making experts exist Always update on medical supplies brands Relative to medical supplies brands Language preference information, for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, is the weight parameter, Represents a function that converts interval-valued fuzzy preference information into linguistic information.

8. The medical supplies selection method according to claim 6, characterized in that: Step 4: Calculate the preference information of each decision-making expert for each medical supply brand and aggregate the preference information of all experts to obtain the information granules of each medical supply brand. Specifically: Calculate the preference information of each decision expert for each medical supply brand ,in, , Decision-making experts For the first The left and right endpoints of the preference relationship for medical supplies brands; Aggregate all experts' aggregated information to obtain information particles of each medical supplies brand. ,Right now: in, represents the coverage of information granules, Indicates the specificity of the information particle.

9. A medical supplies selection system considering continuous learning of individual semantics, characterized by: It includes a personalized interval numerical scale value determination module, a personalized semantic update module, a feedback adjustment module and an aggregation selection module; The personalized interval numerical scale value determination module is used to determine the value of the interval numerical scale by minimizing the consistency index of the interval fuzzy preference relationship and the deviation of the semantic information between decision experts. The value of the personalized interval numerical scale at each moment, wherein the personalized interval numerical scale is the interval numerical scale under the language item in the language preference relationship of each decision expert; The personalized semantic update module is used to utilize the Moment weight and consensus level calculation The group consensus level at the moment, when the group consensus level is greater than or equal to the predefined consensus threshold, directly enter the aggregation selection module, when the group consensus level is less than the predefined consensus threshold, identify The decision expert set that needs to be modified at any time and the language preference information of each expert in the decision expert set need to be modified to achieve Personalized semantic updates at each moment enter the feedback adjustment module; The feedback adjustment module is used to , circulates the personalized interval numerical scale value determination module to the personalized semantics update module, for updating the personalized semantics corresponding to the decision maker who has modified the language preference information until the group consensus reaches a predefined consensus threshold; The aggregation selection module is used to calculate the preference information of each decision-making expert for each medical supply brand and aggregate the preference information of all experts to obtain information particles of each medical supply brand, and select the medical supply brand that makes the median value of the information particles the largest as the final selected brand.

10. The medical supplies selection system according to claim 9, characterized in that: In the personalized interval numerical scale value determination module, the objective function is: in, is the total number of decision-making experts, Index for decision-making experts, For decision-making experts exist The weight of the moment, For decision-making experts exist The variables at the moment, , For decision-making experts exist Interval fuzzy preference relation of time The consistency index, For decision-making experts exist Always on the Medical supplies brands Relative to the Medical supplies brands The interval fuzzy preference relation of for The moment Medical supplies brands Relative to the Medical supplies brands The degree of group preference, Indicates distance, is the total number of medical supplies brands, They are the medical supplies brand index; In the personalized semantic update module, the language preference information of each expert in the decision expert set is modified, and the corresponding objective function is: in, , for Corresponding to the left endpoint of the interval fuzzy preference relation, for Corresponding to the right endpoint of the interval fuzzy preference relation.

Images