Artificial intelligence assisted medication service development method and system

Abstract

The invention relates to an artificial intelligence-assisted medication service development method and system. The method comprises the following steps: creating an intelligent agent for generating medication service information; a multi-dimensional relation matrix representing the incidence relation between the intelligent agents is constructed; instantiating one or more agents based on the electronic medical record to form a user agent set; determining one or more agent processing paths based on the user agent set; determining a medication service record based on each processing path; and making a decision to obtain medication service auxiliary information. According to the method, on the basis of construction of the lightweight intelligent agents, through construction of relevance between the intelligent agents, exponential complexity is reduced into linear complexity, feasibility and medication service efficiency are improved, and development of medication service is promoted.

Description

Technical field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to an artificial intelligence-assisted medication service delivery method and system. [Background Technology]

[0002] With the increasing aging of my country's population, the prevalence of ischemic stroke is on the rise, seriously threatening patients' quality of life and placing a heavy burden on families and society. Clinical pharmacists play an indispensable role in the treatment of stroke patients. They ensure that patients correctly understand and follow their doctor's medication orders through precise medication selection and rational dosage adjustment, which is crucial for improving treatment efficacy and reducing the risk of recurrent stroke. However, faced with the enormous needs of the stroke patient population, the number of high-quality clinical pharmacists in my country is significantly insufficient, making it difficult to provide adequate medication education for every patient. Differences in patients' ability to understand medical information further highlight the urgent need for efficient and personalized medication education. This imbalance between supply and demand limits patients' understanding of disease management, impacting treatment compliance and long-term prognosis.

[0003] In recent years, generative artificial intelligence (GenAI) technology has seen increasing application in the medical field, showing great potential in the development of patient education materials. GenAI models, with their superior data processing and language generation capabilities, efficiently integrate complex medical information to generate educational content that is both scientifically accurate and accessible. They can also tailor personalized educational plans based on the patient's specific circumstances, effectively enhancing the relevance and acceptability of education. Furthermore, GenAI's expertise in language conversion enables it to translate specialized terminology into language easily understood by patients, significantly improving the readability and practicality of educational materials. The provision and application of medication information is crucial in the healthcare and artificial intelligence fields. In the niche area of medication education for stroke patients, GenAI holds broad application prospects and is expected to be a disruptive force in improving pharmacist service effectiveness and expanding the reach of pharmaceutical care. Medication care is essential for patients after discharge, and issuing medication service lists to assist with medication administration can significantly save physicians' time, improve the efficiency of medication services, and promote the development of medication services. In the prior art, when artificial intelligence technology is used for medication services, it is usually hoped that the intelligent agent constructed by artificial intelligence will provide a consistent solution for the electronic medical record when the electronic medical record is input; in fact, on the one hand, in the process of vertical application of artificial intelligence technology in the medical field, training data is a scarce resource, its labeling is difficult, and its consistency is low; therefore, it is difficult to achieve effective training of complex intelligent agents; on the other hand, the conditions of hospitalized patients are often more complicated, and the symptoms and manifestations are also complex and diverse. As the symptoms increase, the amount of training and computing required for the intelligent agent increases exponentially; therefore, in actual application, it is difficult to complete the training of such an intelligent agent and put it into actual use; based on the above problems, the present invention constructs a lightweight intelligent agent, and by constructing the correlation between intelligent agents, the exponential complexity is reduced to linear complexity, which improves the feasibility and efficiency of medication services and promotes the development of medication services. [Summary of the invention]

[0004] In order to solve the above problems in the prior art, the present invention proposes an artificial intelligence-assisted medication service development method and system, the method comprising:

[0005] Step S1: Construct an agent whose input is electronic medical records and generates medication service information in a service scenario; create a two-dimensional coordinate (x, y) as an identifier for each agent; where the x-axis is the medication type and the y-axis is the patient feature classification;

[0006] Step S2: Construct a multidimensional relationship matrix that represents the relationship between agents; the multidimensional relationship matrix [ra i，j ] in the association relationship rai，j Used to indicate the relationship between agent i and agent j; i and j are used to refer to the two-dimensional coordinate (x, y) identifier;

[0007] Step S3: Input an electronic medical record, instantiate one or more agents based on the electronic medical record to form a user agent set; determine one or more agent processing paths based on the user agent set; and determine a medication service record based on each processing path;

[0008] Step S4: making a decision on the one or more medication service records obtained by the one or more intelligent processing paths to obtain medication service auxiliary information; and presenting the medication service auxiliary information to the user.

[0009] Furthermore, the patient characteristic value division ranges for the y-coordinate are overlapping or non-overlapping.

[0010] Furthermore, when the y-coordinate divisions are non-overlapping, the same patient characteristic may fall within the patient characteristic classification range corresponding to two or more agent identifiers.

[0011] Furthermore, the agent's input includes the patient's electronic medical records, medical data, medication information, or current prescriptions.

[0012] Furthermore, the intelligent agent includes one or more of a rule-driven intelligent agent, a data-driven intelligent agent, a knowledge graph intelligent agent, an artificial intelligence intelligent agent, and a drug interaction detection intelligent agent.

[0013] Furthermore, the instantiation of one or more agents based on the electronic medical record specifically includes: obtaining characterization indicators corresponding to various drug types from the electronic medical record; when the characterization indicators in the electronic medical record meet the scope of the drug type, determining an agent identifier based on the matched drug type and patient characteristics; instantiating the agent corresponding to the agent identifier and adding it to the user agent set;

[0014] Determining one or more agent processing paths specifically includes: determining agent weights, selecting agents with weights greater than a preset value as starting agents; and determining an agent processing path starting from each starting agent such that the x-coordinate values of all agents in the processing path are different.

[0015] The method comprises the following steps: determining an agent processing path starting from each starting agent; specifically, taking the user agent set as the current agent set; taking the starting agent as the current agent and initializing the agent processing path to include only the current agent; determining, based on a multidimensional relationship matrix, an agent in the current agent set with the largest association with the current agent and having an x-coordinate value different from that of all agents in the processing path, as the next agent of the current agent; updating the current agent to the next agent; deleting the next agent from the current agent set, and repeating the process until the elements in the current agent set are empty; and connecting all the next agents determined starting from the starting agent to form a determined agent processing path.

[0016] An artificial intelligence-assisted medication service development system is used to implement the above-mentioned artificial intelligence-assisted medication service development method.

[0017] An artificial intelligence-assisted medication service delivery device, the artificial intelligence-assisted medication service delivery device is used to implement the above-mentioned artificial intelligence-assisted medication service delivery method.

[0018] An artificial intelligence-assisted medication service development platform, the artificial intelligence-assisted medication service development platform is used to implement the above-mentioned artificial intelligence-assisted medication service development method.

[0019] An artificial intelligence-assisted medication service development server, wherein the artificial intelligence-assisted medication service development server is used to implement the above-mentioned artificial intelligence-assisted medication service development method.

[0020] The beneficial effects of the present invention include:

[0021] (1) Construct lightweight intelligent agents and use them in combination by building relationships between them, thereby reducing exponential complexity to linear complexity, improving feasibility and efficiency of medication services, and promoting the development of medication services.

[0022] (2) The two-dimensional coordinates can be used to quickly locate the intelligent agent. For the same type of drug, different intelligent agents with different y-axis values can provide drug service information, which relaxes the threshold for creating, training and generating intelligent agents and provides diversity in drug service information. Based on path creation and node traversal, the relationship problem is converted into a data problem, which requires the collaboration of multiple intelligent agents, facilitates the compatibility of decision-making methods and generates and processes medication plans.

Brief Description of the Drawings

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application, but do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 Schematic diagram of the method for carrying out the artificial intelligence-assisted medication service provided by the present invention. [Specific implementation method]

[0025] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The exemplary embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0026] The present invention proposes an artificial intelligence-assisted medication service development method and system, as shown in the attached Figure 1 As shown, the method includes the following steps:

[0027] Step S1: Construct an agent whose input is an electronic medical record and generates medication service information in a service scenario; create two-dimensional coordinates (x, y) for each agent as an identifier; where: the x-axis is the drug type, and the y-axis is the patient characteristic classification, for example: drug types include antibiotics, cardiovascular drugs, psychiatric drugs, etc.; the y-axis is classified by patient characteristics: age stratification (children / elderly), liver and kidney function classification, gender, genotype, complications, etc.; service scenario classification includes dose generation, dose adjustment (drugs and their dosage), incompatibility, medication time optimization, prescription review, dose conversion, treatment course planning, etc.; when the service scenario changes, the agent function or rule is switched accordingly to meet the required service scenario;

[0028] Preferably, different coordinate values are set for each drug type and patient characteristic classification to identify agents with different functions; further, similar coordinate values are set for agents with similar functions; and further, the drug classification coordinate values are positive integers. Considering that patient characteristic classifications can overlap, the y-axis coordinate values can be set to continuous non-integer values to identify the proximity between agents. This setting method allows for rapid agent positioning.

[0029] Preferably, the patient characteristic value ranges for the y-coordinates are overlapping or non-overlapping, that is, the patient characteristic categories (patient characteristic ranges) corresponding to the y-coordinate values are overlapping or non-overlapping; the same patient characteristic category (value, value range) will correspond to different y-coordinates; therefore, for the same patient, different agents with different y-coordinates can provide medication service information for the same medication type; in this way, the threshold for creating and generating agents is relaxed, and the diversity of medication service information is provided; in this case, data from a single institution, a single clinic, and a single department can support the training of the agents;

[0030] Alternatively, the input of the intelligent agent includes the patient's medical data, medication information, current prescription, etc., and the output is one or more of medication measurement and suggestion, adjusted dosage, medication suggestion, warning, etc.;

[0031] Preferably, the x-coordinate and the y-coordinate can be set as one-dimensional or multi-dimensional elements according to specific needs; for example, patient feature classification can be set in multiple dimensions to finely describe the user; the intelligent agent used to generate medication service information can be located based on the two-dimensional coordinates, that is, the two-dimensional coordinates are unique;

[0032] Preferably: historical data that meets the agent identification restrictions is used to set rules or train the agent; based on the proportion of times the agent is instantiated and the proportion of times the drug service information generated by the agent is ultimately used, the training amount is maintained, reduced, or the agent is deleted, and software and hardware storage space is optimized by optimizing the agent; since the patient feature classifications in the agent can overlap, the data used for training different agents can obviously be the same;

[0033] Preferably: the intelligent agent includes one or more of a rule-driven intelligent agent, a data-driven intelligent agent, a knowledge graph intelligent agent, an artificial intelligence intelligent agent, and a drug interaction detection intelligent agent; the rule-driven intelligent agent generates medication service information based on the explicit knowledge of clinical guidelines / pharmacopoeia; for example: Drools rule engine, FHIR clinical pathway model, SWRL semantic reasoning; the data-driven intelligent agent performs implicit knowledge mining based on a machine learning model; for example: XGBoost / LightGBM (structured data), Transformer time series model, DeepSurv survival analysis, chemotherapy dose prediction intelligent agent; the knowledge graph intelligent agent performs association reasoning based on a medical knowledge network; for example: Neo4j graph database, TransE / KG-BERT embedding engine, SPARQL query engine; the hybrid enhanced intelligent agent performs collaborative decision-making based on multiple types of intelligent agents;

[0034] Preferably, the intelligent agent is an intelligent agent based on an artificial intelligence model; when constructing the intelligent agent, a basic model is selected based on the intelligent agent creation platform, and the basic model is further selected through the single agent mode, and a suitable plug-in is installed on the basic model, and the plug-in parameters are set; the plug-in parameter setting is specifically: adjusting parameters such as learning rate, maximum input length, response generation temperature, etc. to optimize the fluency and accuracy of the conversation; for example, setting the learning rate between 0.001 and 0.01 to avoid excessively high values that may cause training instability; setting the maximum input length according to the software and hardware resources to avoid increased resource consumption due to invalid settings; setting the response generation temperature to a temperature value (0 to 1) to control the randomness of the generated text, with a low value being more conservative and a high value being more creative, such as setting it initially to 0.7;

[0035] Step S2: Construct a multidimensional relationship matrix that represents the relationship between agents; the multidimensional relationship matrix [ra i，j ] in the association relationship ra i，j Used to indicate the association relationship between agent i and agent j; it can be understood that i and j are used to refer to two-dimensional coordinate (x, y) identifiers;

[0036] Preferred: When the x-coordinate values of two agents are the same, set their association to 0;

[0037] Alternatively: set i = hash(x, y); hash() is a two-dimensional hash code, which can be used to quickly locate the agent;

[0038] Preferably: the elements in the multidimensional relationship matrix are used to indicate the first or more of the drug use relationship, drug interaction relationship, patient characteristic similarity relationship, medical order pattern relationship, etc. between two agents; these association relationships can be indicated in the form of multiple groups or composite values; the relationship is represented by a numerical value, when the relationship is close, the numerical value is large, and when the relationship is not close, the numerical value is small; further: the numerical value is normalized to a value between [0, 1]; the two-dimensional agent matrix is responsible for the distribution and positioning of agent functional diversity, while the relationship matrix handles the association and knowledge transfer between agents; when handling a complex case, it is necessary to find related agents from the two-dimensional agent matrix, and link other related agents through the three-dimensional relationship matrix to provide service information;

[0039] Step S3: inputting an electronic medical record, instantiating one or more agents based on the electronic medical record to form a user agent set; determining one or more agent processing paths; and determining a medication service record based on each processing path;

[0040] The instantiation of one or more agents based on the electronic medical record specifically includes: obtaining characterization indicators corresponding to various drug types from the electronic medical record; when the characterization indicators in the electronic medical record meet the scope of the drug type, determining an agent identifier based on the drug type and patient characteristics; instantiating the agent corresponding to the agent identifier and adding it to the user agent set; the user agent set may contain one or more agents for the same drug type; for example, if agent A's age stratification is 10-11 years old, and agent B's age stratification is 9.5-11 years old, then when the patient is 10 years old, both agent A and agent B will be included in the patient characteristic classification;

[0041] Determining one or more agent processing paths specifically includes: determining agent weights, selecting agents with weights greater than a preset value as starting agents; and determining an agent processing path starting from each starting agent such that the x-coordinate values of all agents in the processing path are different.

[0042] Preferably, the weight value of the agent is set to a preset value; here, it can be set according to the expert experience value;

[0043] Alternatively, the weight value of the agent is determined as follows: for each agent, all the characterization indicators corresponding to its drug type are determined; the weight value of each agent is determined based on the degree of deviation between the characterization indicator and the normal indicator and the number of corresponding characterization indicators; for example, the weight value w of the agent (x, y) under the current electronic medical record is determined by the following formulas (1)-(2): x，y ; where: dn b It is the degree of deviation between the characterization index b and the normal index; w b is the weight value of the characterization index under the drug type; tdn b is the effective threshold of the characterization index b; N is the number of characterization indicators corresponding to the drug type; wb x，y is the drug type × base weight;

[0044]

[0045] Preferably: pre-set the weight value corresponding to the degree of deviation of different representation indicators for each intelligent agent;

[0046] The method comprises the following steps: determining an agent processing path from each starting agent; specifically, taking the user agent set as the current agent set; taking the starting agent as the current agent and initializing the agent processing path to include only the current agent; determining, based on the multidimensional relationship matrix, an agent in the current agent set with the largest correlation with the current agent (or randomly selecting one of the top few with the largest correlation, or randomly selecting one of the agents with a correlation greater than a threshold) and having an x-coordinate value different from that of all agents in the processing path as the next agent of the current agent (that is, constructing an edge in the path between the current agent and the next agent); updating the current agent to the next agent; deleting the next agent from the current agent set, and repeating the process until the elements in the current agent set are empty; starting from the starting agent, all the next agents determined are connected to form a determined agent processing path;

[0047] Of course, when selecting in the current agent set, you can make relatively exclusive choices based on the y-coordinate value. Within the selectable range, choose the option with the opposite y-coordinate value of the current user's agent set, or choose the y-coordinate value that makes the current user's user feature fall into the center of the range.

[0048] Alternatively, cluster the agents' weights and use all agents in the cluster with the largest cluster mean as the starting agents. Clustering can simultaneously identify typical drug types. However, when there are multiple typical drug types, the stronger the correlation between their simultaneous effects, the less meaningful it is to distinguish them.

[0049] The method of determining a medication service record based on each processing path includes: traversing each agent in the processing path to sequentially obtain medication service information, and performing decision adjustment between the medication service information based on the traversal order to obtain a medication service record corresponding to the processing path; the method includes the following steps:

[0050] Step S3A1: Initialize the current node as the starting agent; initialize the existing medication service information to empty;

[0051] Step S3A2: inputting the electronic medical record into the agent corresponding to the current node to update the medication service information; specifically: inputting the electronic medical record into the agent corresponding to the current node, obtaining the medication service information corresponding to the agent, and judging whether the medication service information satisfies the existing medication service information (there is no contradiction between the existing medication service information). If so, merging the medication service information with the existing medication information to update the medication service information; otherwise, inputting the electronic medical record into the agent corresponding to the current node to obtain the replaced medication service information corresponding to the agent; repeating this step until the existing medication service information is satisfied; since there are various treatment methods for the same type of disease, it is obvious that the agent can obtain multiple different medication service information based on the same electronic medical record; in the process of updating the medication service information, the agent needs to passively replace the medication service information because its priority is lower than that of the preceding node (the preceding agent);

[0052] Alternatively, the electronic medical record is input into the agent corresponding to the current node to update the medication service information. Specifically, a corresponding service scenario is set (set to metering adjustment), so that under the constraints of the existing medication service information, the electronic medical record is input into the corresponding agent to obtain the medication service information corresponding to the agent, and the medication service information is merged with the existing medication information to update the medication service information. This alternative method increases the complexity of the agent to a certain extent, requires additional service scenario settings, and thus requires additional agent logic.

[0053] Step S3A3: Determine whether the processing path has been traversed. If not, set the current node as the next agent of the current node and return to step S3A2; if yes, set the current medication service information as the medication service record of the processing path;

[0054] Step S4: making a decision on the one or more medication service records obtained by the one or more intelligent processing paths to obtain medication service auxiliary information; presenting the medication service auxiliary information to the user; specifically, selecting a medication record from the multiple medication service records as the medication service auxiliary information;

[0055] Alternatively, the medication service information for the same medication type x in one or more medication service records may be selected, merged, or contradictory to obtain medication service auxiliary information for all medication types x; further, the medication service auxiliary information may be manually judged and presented to the user;

[0056] Alternatively: the one or more medication service records obtained by the one or more intelligent processing paths are used to make a decision to obtain medication service auxiliary information; specifically: the medication service record corresponding to the p-th processing path is represented as Re p=(re p，k ), where: p，k It is the medication service information given by the kth agent in the processing path p; all medication service information involving drug type x re p，k , the medication service information that dominates among p=1~P is used as the medication service information for the medication type x; the medication service information of all medication types x is organized to obtain medication service auxiliary information; all medication types x is the number of all medication types involved in the user agent set; of course, since medication types are not continuous, the corresponding X is also not continuous;

[0057] Preferably: Based on the following formula (3) (4) or (3) (5), the dominant value sc of the medication service information rep,k involving the drug type x is calculated: p，k ; The medication service information with the highest dominance value is used as the medication service information for the drug type x;

[0058] sc p，k =∑ (p1＝1～P,k 1 ＝1～K ) ∧((p1,k1)≠(p，k)) tem.sc p1,k1 (3);

[0059]

[0060] The presenting of medication service auxiliary information to the user; specifically: providing one-click medication service auxiliary information presentation, presenting a one-click button when the patient is discharged, and when clicked, presenting the medication service auxiliary information to the user in a modifiable manner;

[0061] Based on the same inventive concept, the present invention also provides an artificial intelligence-assisted medication service delivery system, which is used to implement the above-mentioned artificial intelligence-assisted medication service delivery method;

[0062] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including assembly or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple collaborative files (e.g., files storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0063] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. An artificial intelligence-assisted medication service delivery method, characterized in that: The method comprises: Step S1: Construct an agent whose input is electronic medical records and generates medication service information in a service scenario; create a two-dimensional coordinate (x, y) as an identifier for each agent; where the x-axis is the medication type and the y-axis is the patient feature classification; Step S2: Construct a multidimensional relationship matrix that represents the relationship between agents; the multidimensional relationship matrix [ra i，j ] in the association relationship ra i，j Used to indicate the relationship between agent i and agent j; i and j are used to refer to the two-dimensional coordinate (x, y) identifier; Step S3: Input an electronic medical record, instantiate one or more agents based on the electronic medical record to form a user agent set; determine one or more agent processing paths based on the user agent set; and determine a medication service record based on each processing path; Step S4: making a decision on the one or more medication service records obtained by the one or more intelligent processing paths to obtain medication service auxiliary information; and presenting the medication service auxiliary information to the user.

2. The method for providing artificial intelligence-assisted medication services according to claim 1, characterized in that: The patient characteristic value division ranges for the y-coordinate are either overlapping or non-overlapping.

3. The method for providing AI-assisted medication services according to claim 2, wherein: When the y-coordinate divisions are non-overlapping, the same patient characteristic will fall into the patient characteristic classification range corresponding to two or more agent identifiers.

4. The method for providing artificial intelligence-assisted medication services according to claim 3, characterized in that: The agent's inputs include the patient's electronic medical records, medical data, medication information, or current prescriptions.

5. The method for providing artificial intelligence-assisted medication services according to claim 4, characterized in that: The intelligent agent includes one or more of a rule-driven intelligent agent, a data-driven intelligent agent, a knowledge graph intelligent agent, an artificial intelligence intelligent agent, and a drug interaction detection intelligent agent.

6. The method for providing AI-assisted medication services according to claim 5, characterized in that: The instantiation of one or more agents based on the electronic medical record specifically comprises: obtaining characterization indicators corresponding to various drug types from the electronic medical record; when the characterization indicators in the electronic medical record meet the scope of the drug type, determining an agent identifier based on the drug type and patient characteristics; instantiating the agent corresponding to the agent identifier and adding it to the user agent set; The determining of one or more agent processing paths specifically includes: determining weight values of the agents, and selecting an agent with a weight value greater than a preset value as a starting agent; Determine an agent processing path starting from each starting agent so that the x-coordinate values of all agents in the processing path are different; The method of determining an agent processing path from each starting agent is as follows: taking the user agent set as the current agent set; taking the starting agent as the current agent and initializing the agent processing path to include only the current agent; Based on the multidimensional relationship matrix, determine the agent in the current agent set that has the largest association with the current agent and has a different x-coordinate value from all agents in the processing path as the next agent of the current agent; Update the current agent to the next agent; Deleting the next agent from the current agent set, and repeating the process until the current agent set is empty; Starting from the starting agent, all the next agents determined are connected to form a determined agent processing path.

7. An artificial intelligence-assisted medication service delivery system, characterized in that: The artificial intelligence-assisted medication service delivery system is used to implement the artificial intelligence-assisted medication service delivery method described in any one of claims 1 to 6.

8. An artificial intelligence-assisted medication service delivery device, characterized in that: The artificial intelligence-assisted medication service delivery device is used to implement the artificial intelligence-assisted medication service delivery method described in any one of claims 1 to 6.

9. An artificial intelligence-assisted medication service platform, characterized in that: The artificial intelligence-assisted medication service development platform is used to implement the artificial intelligence-assisted medication service development method described in any one of claims 1 to 6.

10. An artificial intelligence-assisted medication service server, characterized in that: The artificial intelligence-assisted medication service delivery server is used to implement the artificial intelligence-assisted medication service delivery method described in any one of claims 1 to 6.

Images