A doctor-patient co-decision agent negotiation method and device based on a particle swarm algorithm

Abstract

The embodiment of the application provides a kind of doctor-patient joint decision agent negotiation method and device based on particle swarm algorithm, it is related to doctor-patient joint decision technical field.The doctor-patient joint decision agent negotiation method contains S1, obtains the trapezoidal fuzzy membership function of doctor and patient to n negotiation problems, and the weight of n negotiation problems, and according to trapezoidal fuzzy membership function and weight, constructs multi-objective optimization model.S2, according to multi-objective optimization model, based on belief-desire-intention architecture, constructs doctor agent model and patient agent model.The agent model includes opponent model, bid strategy model and acceptance strategy model.Bid strategy model is used to solve multi-objective optimization model by multi-objective particle swarm algorithm and non-dominated solution distance method, to obtain offer.S3, according to doctor agent model and patient agent model, construct agent-based negotiation model.S4, according to agent-based negotiation model, carry out simulated negotiation, obtain negotiation result.

Description

Technical Field

[0001] This invention relates to the field of collaborative decision-making technology between doctors and patients, and more specifically, to a collaborative decision-making proxy negotiation method and apparatus based on particle swarm optimization algorithm. Background Technology

[0002] "Shared decision-making between doctors and patients" is a medical decision-making model in which doctors and patients reach a consensus on issues such as how to diagnose / treat / use medication, and whether to conduct certain special examinations / surgeries after full consultation.

[0003] Traditional collaborative decision-making techniques for physicians and patients include Patient Decision Assistance Tools (PtDAs) and Clinical Decision Support Systems (CDSSs). PtDAs require patients to fully understand relevant information, consuming significant time and human resources. Furthermore, they fail to help patients integrate their values ​​and preferences with information about the benefits and risks of choices to achieve the best outcome. Clinical Decision Support Systems assist healthcare providers by analyzing patient data and using that information to help develop diagnoses. However, they suffer from high implementation costs and a lack of consideration for the user's value proposition or preferences. Traditional collaborative decision-making techniques primarily utilize conventional media to guide patients in making decisions about specific issues, without considering / balancing the values ​​and preferences of both physicians and patients, resulting in less informed treatment options.

[0004] Therefore, agent negotiation techniques have been introduced into some new collaborative decision-making technologies for doctors and patients, using agent models to negotiate and arrive at a final solution. However, traditional agent negotiation techniques are mainly used in multi-agent systems (MAS) to study the information and dynamic behavior of complex systems. Applying them to collaborative decision-making for doctors and patients presents at least the following problems: requiring complete information about the opposing parties; requiring a significant amount of time to resolve conflicts; consistently failing to address how to find the equilibrium point; and the agent being unable to search for all possible negotiation solutions.

[0005] In view of this, the applicant hereby submits this application after studying the existing technology. Summary of the Invention

[0006] This invention provides a method and apparatus for collaborative decision-making between doctors and patients based on particle swarm optimization algorithm, in order to improve at least one of the above-mentioned technical problems.

[0007] First aspect

[0008] This invention provides a method for collaborative decision-making between doctors and patients based on particle swarm optimization, comprising:

[0009] S1. Obtain feedback from doctors and patients. The trapezoidal fuzzy membership function of a negotiation problem, and The weights of each negotiation problem are determined, and a multi-objective optimization model is constructed based on the trapezoidal fuzzy membership function and the weights. The optimization objective of the multi-objective optimization model is to maximize overall satisfaction.

[0010] S2. Based on the multi-objective optimization model, construct doctor agent and patient agent models using a belief-wish-intention architecture. The agent models include an adversary model, a bidding strategy model, and an acceptance strategy model. The adversary model learns adversary preferences to update the multi-objective optimization model. The bidding strategy model uses a multi-objective particle swarm optimization algorithm and the superior-inferiority distance method to solve the multi-objective optimization model and obtain bids. The acceptance strategy model executes negotiation actions according to pre-set rules.

[0011] S3. Based on the doctor agent model and the patient agent model, construct an agent-based negotiation model.

[0012] S4. Simulate negotiation based on the agent-based negotiation model and obtain the negotiation results.

[0013] The second aspect

[0014] This invention provides a medical-patient collaborative decision-making proxy negotiation device based on particle swarm optimization algorithm, which includes:

[0015] A multi-objective optimization model building module is used to obtain feedback from doctors and patients on their performance. The trapezoidal fuzzy membership function of a negotiation problem, and The weights of each negotiation problem are determined, and a multi-objective optimization model is constructed based on the trapezoidal fuzzy membership function and the weights. The optimization objective of the multi-objective optimization model is to maximize overall satisfaction.

[0016] The agent model construction module is used to build doctor and patient agent models based on a belief-wish-intention architecture, according to a multi-objective optimization model. The agent model includes an adversary model, a bidding strategy model, and an acceptance strategy model. The adversary model learns adversary preferences to update the multi-objective optimization model. The bidding strategy model solves the multi-objective optimization model using a multi-objective particle swarm optimization algorithm and a superior-inferiority distance method to obtain bids. The acceptance strategy model executes negotiation actions according to pre-set rules.

[0017] The negotiation model building module is used to build an agent-based negotiation model based on the doctor agent model and the patient agent model.

[0018] The output module is used to simulate negotiation based on a proxy-based negotiation model and obtain the negotiation results.

[0019] By adopting the above technical solution, the present invention can achieve the following technical effects:

[0020] The doctor-patient collaborative decision-making proxy negotiation method of this invention can be effectively applied to doctors and patients with different preferences and strategies, promoting the implementation of doctor-patient collaborative decision-making. It improves the agreement satisfaction of both parties and social welfare, while reducing the time and space costs required for negotiation. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the collaborative decision-making and negotiation method between doctors and patients.

[0023] Figure 2 It is a flowchart of the process of doctors and patients transforming into agents.

[0024] Figure 3 This is a framework diagram of the doctor-patient joint decision-making agency negotiation method.

[0025] Figure 4 This is a flowchart for solving a multi-objective optimization model.

[0026] Figure 5 This is a schematic diagram using particles to represent possible quotes.

[0027] Figure 6 This is a diagram of the final quote (using 5 negotiation issues as an example).

[0028] Figure 7 This is a schematic diagram of a collaborative decision-making and negotiation device between doctors and patients. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0030] Example 1

[0031] Please see Figures 1 to 6The first embodiment of the present invention provides a method for doctor-patient collaborative decision-making negotiation based on particle swarm optimization (PSO) algorithm, which can be executed by a doctor-patient collaborative decision-making negotiation device based on PSO algorithm (hereinafter referred to as: negotiation device). Specifically, it is executed by one or more processors in the negotiation device to implement steps S1 to S4.

[0032] S1. Obtain feedback from doctors and patients. The trapezoidal fuzzy membership function of a negotiation problem, and The weights of each negotiation problem are determined, and a multi-objective optimization model is constructed based on the trapezoidal fuzzy membership function and the weights. The optimization objective of the multi-objective optimization model is to maximize overall satisfaction.

[0033] Specifically, existing technologies that use agent-based negotiation to address joint decision-making issues between doctors and patients have several drawbacks, including the need for comprehensive information about the opposing party, the significant time required to resolve conflicts, the inability to find the equilibrium point, and the inability of agents to search for all possible negotiation solutions.

[0034] Therefore, this invention views the SDM (Side-Doctor-Patient) Preference Negotiation Problem as an optimization problem seeking the satisfaction of both doctors and patients with the negotiation outcome. This transforms the existing SDM preference negotiation problem into a multi-objective optimization problem (MOO) with bilateral processing preferences. An agent-based model is then used to implement automated negotiation to solve the bilateral processing preference MOO. This approach is effectively applied to doctors and patients with different preferences and strategies, promoting the implementation of joint doctor-patient decision-making. It improves the agreement satisfaction of both parties and social welfare, while reducing the time and space costs required for negotiation.

[0035] Definition of the SDM preference negotiation problem:

[0036] The doctor-patient joint decision-making process is defined as a process comprising three main parts: (1) sharing information, (2) discussing treatment options, and reaching a mutually agreeable decision. Each negotiated aspect of the treatment option (e.g., cost, treatment duration, etc.) is defined as a negotiation topic in the SDM preference negotiation. In actual clinical settings, due to various limitations such as time, medical knowledge, and beliefs, doctors and patients cannot share much information. Therefore, it is assumed that the doctor's agent (DA) and the patient's agent (PA) are in a limited information environment and have vague and imprecise information about their own and their opponent's preferences. In this embodiment, a trapezoidal fuzzy membership function is used to represent this imprecise preference and information. The evaluation of the treatment option by doctors and patients is defined as the aggregate satisfaction value (ASV) with negotiated content, represented by the following function: In the formula, The number of issues that doctors and patients need to negotiate. It is the first Weighting coefficients for each question It is a trapezoidal fuzzy membership function. Indicate the solution The correct one The membership degree of a negotiation question is obtained directly from a set of doctors' and patients' preference data and can flexibly and effectively represent their preferences for certain questions.

[0037] Transform the SDM preference negotiation problem into a bilateral MOO problem:

[0038] Specifically, following the traditional SDM process, the SDM problem is simplified into a MOO problem with bilateral treatment preferences. The goal is to achieve a win-win agreement for both doctors and patients—that is, an agreement that maximizes the ASV for both parties. This involves a multi-objective optimization problem.

[0039] Based on the above embodiments, in an optional embodiment of the present invention, the multi-objective optimization model is as follows: In the formula, For fitness function, The optimization objective is to maximize overall satisfaction as the fitness function. The agreement reached For doctors' satisfaction scores, For patient satisfaction, For the number of issues to be negotiated, For the first Weighting coefficients for each negotiation issue For the agreement For the first The degree of membership of each negotiation issue The estimated weight of the other party. This is an estimate of the other party's fuzzy membership degree.

[0040] Specifically, fitness function There are two objectives: doctor satisfaction. and patient satisfaction The sum reaches its maximum.

[0041] In this embodiment, the SDM preference negotiation problem is transformed into a MOO problem. The goal of SDM preference negotiation is to balance the physician's ASV and the patient's ASV and maximize them. DA and PA solve the SDM preference negotiation problem by negotiating and solving the MOO problem (i.e., solving a multi-objective optimization model), resulting in a win-win negotiation outcome.

[0042] It is understood that the negotiation device may be an electronic device with computing power, such as a portable laptop computer, desktop computer, server, smartphone or tablet computer.

[0043] S2, such as Figure 2 As shown, based on the multi-objective optimization model and the belief-wish-intention architecture, a doctor agent model and a patient agent model (i.e., Figure 3 (The agent model and the adversary in the text). Among them, such as Figure 3 As shown, the proxy model includes the counterparty model, the bidding strategy model, and the acceptance strategy model.

[0044] The adversary model learns adversary preferences to update the multi-objective optimization model. The bidding strategy model solves the multi-objective optimization model using a multi-objective particle swarm optimization algorithm and the superior-inferior distance method to obtain bids. The acceptance strategy model executes negotiation actions according to pre-set rules.

[0045] Preferably, the adversary model is a Bayesian learning-based adversary model. This model can be a general framework based on Bayesian learning, or the adversary preference model in the inventor's prior patent application with application number "CN202210662212.0" entitled "Agency Negotiation Method, Apparatus, Device and Storage Medium for Shared Decision-Making between Doctors and Patients". This invention will not elaborate on this model.

[0046] Preferably, the acceptance strategy model uses a time-based or utility-based strategy. Specifically, the acceptance strategy can be utility-based, time-based, or a combination of both.

[0047] In this embodiment, the Agent's acceptance conditions (acceptance strategy model) )as follows:

[0048]

[0049] In the formula, This indicates the termination of negotiations or rejection of the other party's offer and the end of negotiations. This indicates acceptance of the other party's offer and termination of negotiations. Indicate rejection of the offer and propose a counter-offer. Indicates the negotiation period or time. Indicates the deadline, Indicates other, Indicates the r-th counter-offer, The opponent's predicted bid in the current negotiation round The efficacy, The opponent model predicts the previous negotiation round competitor's offer The efficacy, Indicates the current negotiation round, The maximum number of negotiation rounds set for the experiment and Constants set for the experiment; ; .

[0050] In this embodiment, the direct participants in SDM are considered as independent, interconnected, and environmentally retrained agents. Here, communication between the doctor and patient is considered negotiation between agents. Furthermore, the overall satisfaction of the doctor and patient with the treatment plan is considered the agent's personal utility. Therefore, the agent can support the medical decision-making process for both doctors and patients.

[0051] Specifically, the inventors generated behavioral models of the physician agent (DA) and patient agent (PA) based on the Belief-Desire-Intention (BDI) framework. Table 1 describes an example of individual behavior of the DA and PA based on BDI.

[0052] Table 1: Examples of Individual Behaviors in DA / PA Based on BDI

[0053]

[0054] S3. Based on the doctor agent model and the patient agent model, construct an agent-based negotiation model, namely the SDM Automatic Negotiation Model (PSOAN).

[0055] like Figure 3 As shown, in this embodiment, the inventors constructed an agent-based negotiation framework based on the behavioral models of DA and PA to simulate the SDM process between doctors and patients. The negotiating parties (i.e., DA and PA) calculate their offers using a bidding strategy model and determine the best offer as a counter-offer during the negotiation process.

[0056] S4. Simulate negotiation based on the agent-based negotiation model and obtain the negotiation results.

[0057] Specifically, the SDM Automatic Negotiation Model (PSOAN) used for SDM has three phases.

[0058] The first phase is the pre-negotiation phase.

[0059] This phase comprises steps S1 through S3. In this phase, DA and PA define the interval values ​​and expected intervals of their negotiation problems, and assign weights to each negotiation problem according to their preferences. It also defines negotiation characteristics such as negotiation deadlines and time losses.

[0060] The second stage is the negotiation stage.

[0061] The negotiation process follows an alternating offer agreement, comprising the following steps: 1. First, each party sends its most satisfactory target as the first round offer to the other. 2. The negotiating parties generate a near-optimal solution based on the MOO (Mean Opinion on Exchange) as an exchange offer (e.g., a counter-offer). 3. Then the two parties exchange offers until an agreement is reached or the deadline is reached.

[0062] That is, based on the opponent's bid, the estimated values ​​of the opponent's weights and the estimated values ​​of the opponent's fuzzy membership degrees in the MOO are updated through the opponent model, and then the solution is obtained to obtain the bid for this round.

[0063] The third stage is the outcome of the negotiation.

[0064] At the conclusion of the negotiation process, one action can be taken (acceptance, rejection, or meeting the deadline). If either party accepts the offer, the degree of acceptance will be determined by mutual agreement. If its fitness value is less than the minimum acceptable value, either party may reject the offer. If the negotiation deadline is reached, the negotiation concludes.

[0065] Both the second and third stages are included in step S4.

[0066] like Figure 3 As shown, the example in this embodiment is a bilateral SDM problem, and the model given is a bilateral (i.e., one-to-one) multi-problem, time-dependent function. In other embodiments, it can also be applied to multilateral negotiation, i.e., using multiple bilateral (i.e., one-to-many) negotiations.

[0067] The doctor-patient collaborative decision-making proxy negotiation method of this invention can be effectively applied to doctors and patients with different preferences and strategies, promoting the implementation of doctor-patient collaborative decision-making. It improves the agreement satisfaction of both parties and social welfare, while reducing the time and space costs required for negotiation.

[0068] Based on the above embodiments, in an optional embodiment of the present invention, the bidding strategy model is specifically used to execute steps A1 and A2.

[0069] A1. Solve the multi-objective optimization model using the multi-objective particle swarm optimization algorithm to obtain a candidate solution set.

[0070] A2. Select the best solution from the candidate solution set using the superior-inferior solution distance method to obtain a quote.

[0071] Specifically, the bilateral SDM problem involves two objective functions (i.e., the utility functions of the user and the adversary), and SDM contains imprecise information about user preferences and incomplete information about adversary preferences. Therefore, in the agent-based negotiation model, user modeling (i.e., the user utility function / MOO) uses a trapezoidal fuzzy membership function. The user needs to specify the maximum acceptable range, expected range, and weights for handling the agreement problem. During the negotiation process, adversary modeling uses a Bayesian learning-based adversary model.

[0072] Therefore, the two-sided SDM problem is solved by addressing the Motion-Oriented Problem (MOO) that generates Pareto-optimal bids. In this embodiment, a combination of the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm and the Top-and-Bottom Solution Distance (TOPSIS) method is used to generate (near) optimal solutions in the bidding strategy. This method has two phases, such as... Figure 4 As shown.

[0073] In MOO, the MOPSO group consists of a set of possible offers from each negotiating agent. Table 2 lists the negotiation mapping patterns for SDM.

[0074] Table 2: Mapping Modes for SDM Negotiation

[0075]

[0076] Based on the above embodiments, in an optional embodiment of the present invention, the basic principle of the MOPSO algorithm includes: 1. Initializing population particles in the initial population; 2. Calculating fitness values ​​to evaluate the quality of the solution when the particles have a certain velocity and position; 3. Finding the optimal solution by continuously iterating through the velocity and position equations; 4. Outputting the optimal solution when the set number of iterations or the global optimal solution is reached. These stages can be summarized as follows.

[0077] Specifically, step A1 includes steps A11 to A16.

[0078] A11. Initialize a random population and copy the non-dominated particles in the current population to the archive set. The random population contains multiple particles, each with position and velocity, represented by a d-dimensional vector.

[0079] Specifically, initialize a random population P, which contains Each particle. Each particle has a position and velocity, represented by a d-dimensional vector, as shown in the figure below. The non-dominated particles in the current population are copied to the archive set.

[0080]

[0081] like Figure 5As shown, each particle in the MOSPO swarm corresponds to a message containing all the issues to be negotiated (e.g., offers). More specifically, each particle contains the same number of problems as the negotiation problem. This setting is fixed for all negotiating parties, the number of problems per particle is... The negotiation issue is represented as For each negotiating party, the group P of MOPSO is used to represent a subset of available offers.

[0082] Figure 6 This shows an illustrative example of a quote O with 5 negotiation questions. The value for each negotiation question is generated within the acceptable range of DA / PA.

[0083] A12. Evaluate the position of each particle based on the multi-objective optimization model.

[0084] Specifically, the position of each particle is evaluated based on the fitness function of the multi-objective optimization model. 1. Compare its fitness value with the current optimal value for that individual. Compare. If compared Okay, replace the current position with the new position of the particle. Otherwise, remain unchanged. 2. Calculate the density information of particles in the archive set, and select from the archive set. .

[0085] A13, Update the velocity of each particle and location .

[0086] A14. Copy the non-dominated particles from the updated random population to the archive set to update the archive set.

[0087] A15. When the number of particles in the archive exceeds the specified size, delete the excess individuals.

[0088] Specifically, 1. Update the velocity of each particle according to the following formula. and location 2. Update the archive set by copying the non-dominated particles from the updated population P into the archive set. 3. When the number of particles in the archive set exceeds the specified size, redundant individuals need to be deleted to maintain a stable archive set size.

[0089]

[0090]

[0091] A16. When the set number of iterations or the global optimal solution is reached, output the set of non-dominated particles in the archive as a candidate solution set. Among them, the candidate solution set Include One alternative plan.

[0092] Based on the above embodiments, in an optional embodiment of the present invention, TOPSIS is used to select the optimal solution from the S set output from MOPSO. In the SDM negotiation framework of this embodiment, there are three standards ( Or the target: our own satisfaction value, the competitor's satisfaction value predicted by the competitor model, and the satisfaction gap between the two sides.

[0093] In this embodiment, step A2 specifically includes steps A21 to A25.

[0094] A21. Based on the candidate solution set and Construct an initial decision matrix from a set of standard groups. .in, In the formula, This represents the number of alternative options.

[0095] Specifically, a decision matrix consisting of n alternatives and m criteria was first established. In the formula, n = |S|, m = 3, and , , .

[0096] It is the value assigned to the j-th criterion of the i-th solution. In the formula, , .

[0097] A22. Perform positive transformation on the standard group, and then standardize the decision matrix after positive transformation to obtain the standard decision matrix.

[0098] Specifically, if the j-th standard in matrix Z is not an extremely large index, then based on the particle's velocity... The updated formula is normalized, and then the normalized matrix Z is normalized according to the following formula.

[0099]

[0100] A23. Calculate the difference between each evaluation criterion and the optimal solution based on the standard decision matrix. The gap between the best and the second-best solutions .

[0101] Specifically, the difference between each evaluation criterion and the optimal and suboptimal solutions is calculated and defined as follows: and .in and The first The maximum and minimum values ​​of each evaluation criterion.

[0102]

[0103]

[0104]

[0105]

[0106] A24. Based on the difference between each evaluation criterion and the optimal solution The gap between the best and the second-best solutions Calculate the ideal solution And rank the alternative solutions according to the ideal solution. Among them, the ideal solution for .

[0107] Specifically, each alternative is determined based on its comparison with the ideal solution. They are ranked according to their relative similarity.

[0108]

[0109] A25. Select the best solution based on the ranking and get a quote.

[0110] Specifically, the best solution is selected based on the rankings and sent to the opponent as the offer for this round.

[0111] Example 2

[0112] Please see Figure 7 The second embodiment of the present invention provides a medical-patient collaborative decision-making agent negotiation device based on particle swarm optimization algorithm, which includes a multi-objective optimization model construction module 1, an agent model construction module 2, a negotiation model construction module 3, and an output module 4.

[0113] Multi-objective optimization model building module 1 is used to obtain doctors' and patients' opinions on... The trapezoidal fuzzy membership function of a negotiation problem, and The weights of each negotiation problem are determined, and a multi-objective optimization model is constructed based on the trapezoidal fuzzy membership function and the weights. The optimization objective of the multi-objective optimization model is to maximize overall satisfaction.

[0114] Module 2, the agent model construction module, is used to construct doctor and patient agent models based on a belief-wish-intention architecture according to a multi-objective optimization model. The agent models include an adversary model, a bidding strategy model, and an acceptance strategy model. The adversary model learns adversary preferences to update the multi-objective optimization model. The bidding strategy model solves the multi-objective optimization model using a multi-objective particle swarm optimization algorithm and a superior-inferiority distance method to obtain bids. The acceptance strategy model executes negotiation actions according to pre-set rules.

[0115] Negotiation Model Construction Module 3 is used to construct an agent-based negotiation model based on the doctor agent model and the patient agent model.

[0116] Output module 4 is used to simulate negotiation based on the agent-based negotiation model and obtain the negotiation results.

[0117] Specifically, the doctor-patient collaborative decision-making agency negotiation device of this invention can be effectively applied to doctors and patients with different preferences and strategies, promoting the implementation of doctor-patient collaborative decision-making. It improves the agreement satisfaction of both parties and social welfare, while reducing the time and space costs required for negotiation.

[0118] In the several embodiments provided in this invention, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0119] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0120] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, electronic device, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0121] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0122] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0123] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0124] The use of "first" and "second" in the embodiments is merely to distinguish similar objects and does not represent a specific ordering of objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0125] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A doctor-patient collaborative decision-making proxy negotiation method based on particle swarm optimization algorithm, characterized in that, Include: Obtain doctors' and patients' opinions The trapezoidal fuzzy membership function of a negotiation problem, and The weights of each negotiation problem are determined, and a multi-objective optimization model is constructed based on the trapezoidal fuzzy membership function and the weights; wherein, the optimization objective of the multi-objective optimization model is to maximize the overall satisfaction. Based on the multi-objective optimization model, a doctor agent model and a patient agent model are constructed using a belief-wish-intention architecture. The agent model includes an adversary model, a bidding strategy model, and an acceptance strategy model. The adversary model learns adversary preferences to update the multi-objective optimization model. The bidding strategy model solves the multi-objective optimization model using a multi-objective particle swarm optimization algorithm and a superior-inferiority distance method to obtain a bid. The acceptance strategy model executes negotiation actions according to pre-set rules. Based on the doctor agent model and the patient agent model, construct an agent-based negotiation model; The negotiation is simulated based on the agent-based negotiation model to obtain the negotiation result; The multi-objective optimization model is as follows: ； ； ； In the formula, For fitness function, The optimization objective is to maximize overall satisfaction as the fitness function. The agreement reached For doctors' satisfaction scores, For patient satisfaction, For the number of issues to be negotiated, For the first Weighting coefficients for each negotiation issue For the agreement For the first The degree of membership of each negotiation issue The estimated weight of the other party. This is an estimate of the other party's fuzzy membership degree.

2. The doctor-patient collaborative decision-making proxy negotiation method based on particle swarm optimization algorithm according to claim 1, characterized in that, The multi-objective optimization model is solved using the multi-objective particle swarm optimization algorithm and the superior-inferiority distance method, specifically including: A multi-objective optimization model is solved using a multi-objective particle swarm optimization algorithm to obtain a set of candidate solutions; The best solution is selected from the candidate solution set using the superior-inferior solution distance method to obtain a quote.

3. The method for collaborative decision-making between doctors and patients based on particle swarm optimization as described in claim 2, characterized in that, A multi-objective optimization model is solved using a multi-objective particle swarm optimization algorithm to obtain a candidate solution set, specifically including: Initialize a random population and copy the non-dominated particles in the current population to the archive set; wherein the random population contains multiple particles, each of which has a position and velocity, and is represented by a d-dimensional vector; The position of each particle is evaluated based on a multi-objective optimization model; Update the velocity of each particle and location ; Copy the non-dominated particles from the updated random population to the archive set to update the archive set; When the number of particles in the archive exceeds the specified size, delete the excess individuals; When the set number of iterations or the global optimum is reached, the set of non-dominated particles in the output archive is used as the candidate solution set. Among them, the candidate solution set Include One alternative plan.

4. The doctor-patient collaborative decision-making proxy negotiation method based on particle swarm optimization algorithm according to claim 2, characterized in that, The optimal solution is selected from the candidate solution set using the superior-inferior solution distance method to obtain a quote, specifically including: Based on the candidate solution set and Construct an initial decision matrix from a set of standard groups. ;in, In the formula, The number of alternative options; The standard group is positiveized, and then the decision matrix after positiveization is standardized to obtain the standard decision matrix. The difference between each evaluation criterion and the optimal solution is calculated based on the standard decision matrix. The gap between the best and the second-best solutions ; Based on the difference between each evaluation criterion and the optimal solution The gap between the best and the second-best solutions Calculate the ideal solution And rank the alternative solutions according to the ideal solution; wherein, the ideal solution for ; Select the best solution based on the ranking and get a quote.

5. The method for collaborative decision-making between doctors and patients based on particle swarm optimization as described in claim 1, characterized in that, The acceptance strategy model uses a time- and utility-based strategy; the acceptance strategy model for: In the formula, This indicates the termination of negotiations or rejection of the other party's offer and the end of negotiations. This indicates acceptance of the other party's offer and termination of negotiations. Indicate rejection of the offer and propose a counter-offer. Indicates the negotiation period or time. Indicates the deadline, Indicates other, Indicates the r-th counter-offer, The opponent's predicted bid in the current negotiation round The efficacy, The opponent model predicts the previous negotiation round competitor's offer The efficacy, Indicates the current negotiation round, The maximum number of negotiation rounds set for the experiment and Constants set for the experiment; ; .

6. The method for collaborative decision-making between doctors and patients based on particle swarm optimization as described in any one of claims 1 to 5, characterized in that, The adversary model is a Bayesian learning-based adversary model.

7. A medical-patient collaborative decision-making proxy negotiation device based on particle swarm optimization algorithm, characterized in that, Used to execute the doctor-patient joint decision-making proxy negotiation method based on particle swarm optimization algorithm as described in any one of claims 1 to 6; The doctor-patient joint decision-making and negotiation device includes: A multi-objective optimization model building module is used to obtain feedback from doctors and patients on their performance. The trapezoidal fuzzy membership function of a negotiation problem, and The weights of each negotiation problem are determined, and a multi-objective optimization model is constructed based on the trapezoidal fuzzy membership function and the weights; wherein, the optimization objective of the multi-objective optimization model is to maximize the overall satisfaction. The agent model construction module is used to construct a doctor agent model and a patient agent model based on the belief-wish-intention architecture according to the multi-objective optimization model. The agent model includes an adversary model, a bidding strategy model, and an acceptance strategy model. The adversary model is used to learn adversary preferences to update the multi-objective optimization model. The bidding strategy model is used to solve the multi-objective optimization model using a multi-objective particle swarm optimization algorithm and a superior-inferiority distance method to obtain a bid. The acceptance strategy model is used to perform negotiation actions according to pre-set rules. The negotiation model construction module is used to construct an agent-based negotiation model based on the doctor agent model and the patient agent model. The output module is used to simulate negotiation based on the agent-based negotiation model and obtain the negotiation result.

Images