Method, platform and storage medium for intelligent matching and recommendation of medical product services

Abstract

The present application relates to the technical field of data processing, and especially relates to a medical product service intelligent matching recommendation method, platform and storage medium, the method comprises the following steps: collecting user data and task publishing data; storing the task publishing data and analyzing the task difficulty coefficient, analyzing the task complexity adaptability of the user according to the task difficulty coefficient and the user data; constructing a user feature vector based on the user data and the task complexity adaptability, and constructing a task feature vector based on the task publishing data and the task difficulty coefficient; constructing a task matching model based on the user feature vector and the task feature vector to obtain the demand fit degree and the ability adaptation degree; formulating a recommendation list according to the demand fit degree and pushing it to the user, and formulating a candidate list according to the ability adaptation degree and pushing it to the task source unit; collecting the interaction data of the user after receiving the recommendation list, and optimizing the task matching model. The present application realizes accurate recommendation of task data between the user and the hospital.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a medical product service intelligent matching recommendation method and platform and a storage medium. BACKGROUND

[0002] In the digital era, task publishing platforms are constantly emerging. In the digital service and collaboration scenario, the two-way matching between task publishing and users is crucial. With the development of technology, user skills and preferences are analyzed by means of big data, task demand characteristics are combined, and efficient and accurate matching is achieved by using algorithm models, thereby improving resource utilization and service delivery quality.

[0003] Existing medical service matching systems mostly recommend based on static rules or single indicators, lacking quantitative analysis of task complexity and user skill dynamic adaptability. In addition, traditional models do not fully combine the urgency of published tasks and user ability adaptability, resulting in a large deviation between recommended results and actual needs, making it difficult to meet the efficient and accurate resource scheduling needs. The existing technology has the following problems: the task difficulty coefficient and user complex adaptability dynamic analysis are not introduced, resulting in a lack of objectivity and flexibility of the recommended results; only user needs or hospital needs are considered, without achieving two-way matching; the model is not dynamically optimized based on user interaction data, and the system cannot continuously improve the recommendation accuracy; the user authentication skills and task essential skills are not structurally associated, resulting in the key skill demand not being effectively met; and the weight is not dynamically adjusted according to the task urgency, and the high-urgency task recommendation priority is insufficient. SUMMARY

[0004] The present application aims to provide a medical product service intelligent matching recommendation method and platform and a storage medium to solve at least one of the problems in the prior art.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0006] A medical product service intelligent matching recommendation method, comprising:

[0007] Collecting user data and task publishing data;

[0008] Storing the task publishing data and analyzing the task difficulty coefficient, and analyzing the user's task complex adaptability based on the task difficulty coefficient and the user data;

[0009] Constructing a user feature vector based on the user data and the task complex adaptability, and constructing a task feature vector based on the task publishing data and the task difficulty coefficient;

[0010] Constructing a task matching model based on the user feature vector and the task feature vector to obtain the demand fit degree and the ability adaptability;

[0011] According to the demand fitting degree, a recommended list is formulated and pushed to the user, and according to the ability adaptation degree, a candidate list is formulated and pushed to the task source unit;

[0012] Interaction data of the user after receiving the recommended list is collected, and the task matching model is optimized.

[0013] Further, task completion condition data corresponding to the task publishing data with the same task content is extracted as difficulty analysis data, the task time consumption in the difficulty analysis data is normalized, the number of difficulty analysis data with a successful task state is counted as the number of successful data, the number of difficulty analysis data with a failed task state is counted as the number of failed data, and the task difficulty coefficient is analyzed according to the difficulty analysis data, the number of successful data and the number of failed data, and the expression of the task difficulty coefficient is TD = 0.6 x μ (DT1) + 0.4 x N2 / (N1+N2), wherein TD represents the task difficulty coefficient, DT1 represents the normalized task time consumption, μ() represents the average value of the data in the parentheses, N1 represents the number of successful data, and N2 represents the number of failed data.

[0014] According to the task difficulty coefficient and the completed task, the task complexity adaptation degree of the user is analyzed, and the average value of the task difficulty coefficient corresponding to the completed task of the user is taken as the task complexity adaptation degree.

[0015] Further, different authentication skills and essential skills are extracted as a skill set, and each skill in the skill set is numbered to obtain a skill number, so that each skill corresponds to a unique skill number, and the skills are sorted in ascending order of the skill number to obtain a skill sequence, a multi-element vector is constructed as a skill vector, and the number of elements in the skill vector is the same as and corresponds one by one to the number of skills in the skill sequence.

[0016] Further, a user feature vector is constructed according to the task completion degree, response speed, task complexity adaptation degree, user score and skill vector of the user, the response speed of the user is taken to the power and normalized to obtain a response speed parameter, a four-element vector is constructed, each element in the four-element vector corresponds one by one to the task completion degree, response speed parameter, task complexity adaptation degree and user score of the user, the skill vector is filled according to the authentication skill of the user, the filled skill vector is taken as the user skill vector, and the four-element vector and the filled skill vector are spliced to obtain the user feature vector.

[0017] A task feature vector is constructed according to the emergency degree, the task difficulty coefficient, the necessary skills and the skill vector, a three-element vector is constructed, each element in the three-element vector corresponds to the emergency degree, the task difficulty coefficient and the preset matching parameter one by one, the skill vector is filled according to the necessary skills, the filled skill vector is taken as a task skill vector, and the three-element vector and the filled skill vector are spliced to obtain the task feature vector.

[0018] Further, the skill matching parameter is analyzed based on the skill vectors in the user feature vector and the task feature vector;

[0019] The demand fit degree is analyzed based on the user feature vector, the task feature vector and the skill matching parameter, and an expression of the demand fit degree is: In the formula, MAB represents the demand fit degree, w1 represents the first fit degree weight, w2 represents the second fit degree weight, w3 represents the third fit degree weight, w4 represents the fourth fit degree weight, CS represents the skill matching parameter, F represents the task complexity adaptability, E represents the emergency degree, T represents the response speed parameter, and MS represents the preset matching parameter.

[0020] The ability adaptation degree is analyzed based on the user feature vector, the task feature vector and the skill matching parameter, and an expression of the ability adaptation degree is: In the formula, MBA represents the ability adaptation degree, α1 represents the first adaptation degree weight, α2 represents the second adaptation degree weight, α3 represents the third adaptation degree weight, α4 represents the fourth adaptation degree weight, CR represents the task completion degree, and UR represents the user score.

[0021] Further, the analysis process of the ability adaptation degree is updated according to the emergency degree and the task difficulty coefficient. When the emergency degree is greater than or equal to a first update threshold, the first adaptation degree weight is increased and the third adaptation degree weight is reduced to update the analysis process of the ability adaptation degree. When the task difficulty coefficient is greater than or equal to a second update threshold, the first adaptation degree weight and the second adaptation degree weight are reduced and the third adaptation degree weight is increased to update the analysis process of the ability adaptation degree.

[0022] Further, a recommendation list is formulated according to the demand fit degree, task contents corresponding to the demand fit degree greater than or equal to a fit degree threshold are extracted as candidate tasks, and the candidate tasks are sorted in descending order of the demand fit degree, and the first Y candidate tasks are taken as the recommendation list, wherein Y represents a recommendation quantity parameter.

[0023] A recommendation list is formulated according to the ability adaptation degree, users whose task completion degree is greater than or equal to a completion degree threshold and whose user score is greater than or equal to a score threshold are extracted as candidate users, and the candidate users are sorted in descending order of the ability adaptation degree, and the first Y candidate users are taken as a candidate list.

[0024] Further, the construction process of the task feature vector is optimized according to the interaction data, the recommendation list and the candidate list, so as to optimize the task matching model, the number of users accepting the recommendation in the interaction data corresponding to the same task content is extracted as the number of accepting users, the number of users ignoring the recommendation in the interaction data corresponding to the same task content is extracted as the number of ignoring users, the number of interaction data of the users in the candidate list corresponding to the same task content is extracted as the number of effective users, the recommendation matching parameter is analyzed according to the number of accepting users, the number of ignoring users and the number of effective users, and when the recommendation matching parameter is less than 1, the value of the preset matching parameter is updated to be equal to the recommendation matching parameter.

[0025] In another aspect, the present application also provides a medical product service intelligent matching recommendation platform, comprising:

[0026] A data acquisition module acquires user data and task publishing data;

[0027] A parameter analysis module stores the task publishing data and analyzes the task difficulty coefficient, and analyzes the task complexity adaptability of the user according to the task difficulty coefficient and the user data;

[0028] A vector construction module constructs a user feature vector based on the user data and the task complexity adaptability, and constructs a task feature vector based on the task publishing data and the task difficulty coefficient;

[0029] A model construction module constructs a task matching model based on the user feature vector and the task feature vector, so as to obtain the demand fit degree and the ability adaptation degree;

[0030] A recommendation analysis module formulates a recommendation list according to the demand fit degree and pushes it to the user, and formulates a candidate list according to the ability adaptation degree and pushes it to the task source unit;

[0031] A feedback optimization module acquires interaction data after the user receives the recommendation list, and optimizes the task matching model.

[0032] In another aspect, the present application also provides a storage medium, characterized in that it stores instructions which, when executed on a computer, cause the computer to execute the medical product service intelligent matching recommendation method according to any one of the above.

[0033] The present application has the following beneficial effects: through multi-dimensional data modeling and dynamic optimization mechanism, efficient bidirectional matching of users and published tasks is realized, the recommendation result is highly matched with the demand by combining task difficulty, user adaptability and skill matching, the model is optimized in real time based on interaction data, the task urgency and user ability change are adapted, the decision-making time is shortened and the resource allocation efficiency is improved through threshold screening and priority sorting. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0035] Figure 1 The flow chart of the method for intelligent matching recommendation of medical product service in the embodiment.

[0036] Figure 2 The flow chart of the method for constructing feature vector in the embodiment.

[0037] Figure 3 The flow chart of the method for constructing task matching model in the embodiment.

[0038] Figure 4 The structural schematic diagram of the intelligent matching recommendation platform for medical product service in the embodiment. DETAILED DESCRIPTION

[0039] In order to more clearly illustrate the present application, the present application will be further described below in combination with preferred embodiments and drawings. In the drawings, similar components are denoted by the same reference numerals. Those skilled in the art should understand that the following specific description is illustrative rather than limiting, and the protection scope of the present application should not be limited by this.

[0040] It should be noted that although the terms first, second, third, etc. may be used in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, the first can also be called the second without departing from the scope of the embodiments of the present application, and similarly, the second can also be called the first.

[0041] Please refer to Figure 1 The method for intelligent matching recommendation of medical product service in the embodiment shown in the figure, which comprises:

[0042] Step S1, collect user data and task publishing data, the user data including task completion degree, response speed, authentication skill, completed task and user score, the task completion degree being the ratio of the number of tasks completed by the user to the number of tasks accepted by the user, the response speed being the average time from task publishing to user acceptance, the unit being hours, the authentication skill being the skill and skill level of the user passing authentication, including but not limited to first aid nursing, medical record input, etc., the skill level including primary, intermediate and advanced, the user score being the average of the score of the user's completion quality given by the hospital after the user completes the task, the user score ranging from [1, 5], the task publishing data being the task data published by the hospital, including task content, essential skill, emergency degree and task completion data, the task publishing data being the data obtained after the task publishing unit publishes the task in the platform, which can be the task data published by multiple hospitals, in this embodiment, only the published task data is analyzed, the task essential skill matches the authentication skill, the emergency degree being the emergency degree of the task set by the hospital, divided into 1-5 levels, level 1 indicating a regular task, and level 5 indicating an emergency task, the task completion data including task time and task status, the task status including success and failure, the user data and task publishing data are collected by importing the database of the medical product service intelligent matching recommendation platform.

[0043] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of the country and region.

[0044] Specifically, in step S1 of the present embodiment, user data and task publishing data are collected to ensure the comprehensiveness and real-time nature of the data source, providing a foundation for subsequent analysis and avoiding recommendation bias caused by data loss.

[0045] Please continue to refer to Figure 1 The medical product service intelligent matching recommendation method further includes:

[0046] Step S2, store the task publishing data and analyze the task difficulty coefficient, and analyze the task complexity adaptability of the user according to the task difficulty coefficient and the user data.

[0047] Specifically, in step S2 of the present embodiment, the task completion data corresponding to the task publishing data with the same task content is extracted as the difficulty analysis data, the task time in the difficulty analysis data is normalized, and the normalization formula used is: X = (x min ) / (xmax x min ), wherein X represents normalized data, x represents data before normalization, x min represents the minimum value in the data before normalization, x max represents the maximum value in the data before normalization, the number of difficulty analysis data with a successful task state is taken as the number of successful data, the number of difficulty analysis data with a failed task state is taken as the number of failed data, and the task difficulty coefficient is analyzed according to the difficulty analysis data, the number of successful data, and the number of failed data, and the expression of the task difficulty coefficient is TD = 0.6 x μ(DT1) + 0.4 x N2 / (N1+N2), wherein D represents the task difficulty coefficient, DT1 represents the normalized task time consumption, μ() represents the average value of data in the parentheses, N1 represents the number of successful data, and N2 represents the number of failed data.

[0048] Specifically, in the step S2, the task complexity adaptability of the user is analyzed according to the task difficulty coefficient and the completed task, and the average value of the task difficulty coefficient corresponding to the completed task of the user is taken as the task complexity adaptability.

[0049] Specifically, in the step S2, the objectivity of the recommendation is enhanced by quantifying the task difficulty and the user ability, and subjective judgment errors are avoided.

[0050] Please continue to refer to Figure 1 As shown in the figure, the intelligent matching and recommendation method of the medical product service further comprises:

[0051] Step S3, constructing a user feature vector based on the user data and the task complexity adaptability, and constructing a task feature vector based on the task publishing data and the task difficulty coefficient.

[0052] Please refer to Figure 2 As shown in the figure, it is a construction method of the feature vector, which comprises:

[0053] Step S31, constructing a skill vector based on the authentication skills and the essential skills.

[0054] Specifically, in the step S31, different authentication skills and essential skills are extracted as a skill set, and each skill in the skill set is numbered to obtain a skill number, so that each skill corresponds to a unique skill number, and the skills are sorted in ascending order of the skill number to obtain a skill sequence, a multi-dimensional vector is constructed as a skill vector, and the number of elements in the skill vector is the same as and corresponds to the number of skills in the skill sequence.

[0055] Specifically, the skill vector in the embodiment is a multi-element vector, the skill sequence is {first-aid nursing, medical record entry, venous blood sampling}, and the skill vector is a three-element vector, denoted as S, S=[s1, s2, s3], s1, s2, and s3 correspond to the first-aid nursing, medical record entry, and venous blood sampling in the skill sequence in sequence.

[0056] Please continue to refer to Figure 2 As shown in the figure, the method for constructing the feature vector further includes:

[0057] Step S32, constructing a user feature vector based on the skill vector, user data, and task complexity fitness.

[0058] Specifically, in step S32 of the embodiment, the user feature vector is constructed according to the user's task completion degree, response speed, task complexity fitness, user score, and skill vector. The response speed of the user is taken to the power and normalized to obtain a response speed parameter. A four-element vector is constructed, and each element in the four-element vector corresponds to the user's task completion degree, response speed parameter, task complexity fitness, and user score in sequence. The skill vector is filled according to the user's authentication skills, the filled skill vector is taken as the user skill vector, the user skill vector is set as AS, AS=[as1, as2,..., as n ], the values of the elements in the skill vector that do not correspond to the user's authentication skills are set to 0, the values of the elements in the skill vector that correspond to the user's authentication skills are set according to the skill level, if the skill level is primary, it is set to 1; if the skill level is intermediate, it is set to 2; if the skill level is advanced, it is set to 3; the four-element vector and the filled skill vector are spliced to obtain the user feature vector, the user feature vector is set as A, A=[CR, T, F, UR, AS], wherein CR represents the task completion degree, T represents the response speed parameter, F represents the task complexity fitness, UR represents the user score, and [as1, as2,..., as n ] represents the value corresponding to each element of the user skill vector, and the value of the nth element in the user skill vector is set as as n .

[0059] Please continue to refer to Figure 2 As shown in the figure, the method for constructing the feature vector further includes:

[0060] Step S33, constructing a task feature vector based on the skill vector, task publishing data, and task difficulty coefficient.

[0061] Specifically, in step S33, a task feature vector is constructed according to the emergency degree, the task difficulty coefficient, the essential skill and the skill vector, a three-element vector is constructed, each element in the three-element vector corresponds to the emergency degree, the task difficulty coefficient and the preset matching parameter one by one, the skill vector is filled according to the essential skill, the filled skill vector is taken as a task skill vector, the task skill vector is set as BS, BS = [bs1, bs2, …, bs n ], the value of the element corresponding to the essential skill in the skill vector is set to 1, the value of the element not corresponding to the essential skill in the skill vector is set to 0, the three-element vector is spliced with the filled skill vector to obtain the task feature vector, the task feature vector is set as B, B = [E, TD, MS, BS], wherein E represents the emergency degree, TD represents the task difficulty coefficient, MS represents the preset matching parameter, [bs1, bs2, …, bs n ] represents the value corresponding to each element in the task skill vector, the value of the nth element in the task skill vector is set as bs n .

[0062] Specifically, the preset matching parameter in the embodiment is set to 1, the value of the preset matching parameter is not specifically limited in the embodiment, and the value of the preset matching parameter can be freely set by the person skilled in the art, and the setting of the preset matching parameter should satisfy [0.8, 1].

[0063] Specifically, in step S3, the multi-dimensional data is structured to improve the interpretability and matching efficiency of the model.

[0064] Please continue to refer to Figure 1 The method for intelligently matching and recommending medical product services further comprises the following steps:

[0065] Step S4: constructing a task matching model based on the user feature vector and the task feature vector to obtain a demand fit degree and an ability adaptation degree.

[0066] Please refer to Figure 3 , which is a method for constructing a task matching model, comprising the following steps:

[0067] Step S41: analyzing a skill matching parameter based on the user feature vector and the task feature vector.

[0068] Specifically, in step S41, the skill matching parameter is analyzed based on the skill vectors in the user feature vector and the task feature vector, and the expression of the skill matching parameter is as follows: In the formula, CS represents the skill matching parameter, and N represents the number of elements in the skill vector.

[0069] Specifically, in the embodiment, if the required skill is not set in the task publishing data, the skill matching parameter is set to be equal to 1.

[0070] Please continue to refer to Figure 3 As shown in the figure, the method for constructing the task matching model further comprises:

[0071] In step S42, the demand fit degree is analyzed based on the user feature vector, the task feature vector and the skill matching parameter.

[0072] Specifically, in step S42 of the embodiment, the demand fit degree is analyzed based on the user feature vector, the task feature vector and the skill matching parameter, and the expression of the demand fit degree is: In the formula, MAB represents the demand fit degree, w1 represents the first fit degree weight, w2 represents the second fit degree weight, w3 represents the third fit degree weight, w4 represents the fourth fit degree weight, w1+w2+w3+w4=1, and ε represents a smoothing factor.

[0073] Specifically, in the embodiment, the first fit degree weight is set to be 0.4, the second fit degree weight is set to be 0.3, the third fit degree weight is set to be 0.2, the fourth fit degree weight is set to be 0.1, and the smoothing factor is set to be 0.1. In the embodiment, the values of the fit degree weights and the smoothing factor are not specifically limited, and can be freely set by those skilled in the art. The smoothing factor is set to prevent the denominator from being 0, and the setting of the smoothing factor should satisfy that it belongs to [0.1, 0.2].

[0074] Please continue to refer to Figure 3 As shown in the figure, the method for constructing the task matching model further comprises:

[0075] In step S43, the ability adaptation degree is analyzed based on the user feature vector, the task feature vector and the skill matching parameter.

[0076] Specifically, in step S43 of the embodiment, the ability adaptation degree is analyzed based on the user feature vector, the task feature vector and the skill matching parameter, and the expression of the ability adaptation degree is: In the formula, MBA represents the ability adaptation degree, α1 represents the first adaptation degree weight, α2 represents the second adaptation degree weight, α3 represents the third adaptation degree weight, and α4 represents the fourth adaptation degree weight.

[0077] Specifically, in the embodiment, the first adaptation degree weight is set to be 0.3, the second adaptation degree weight is set to be 0.3, the third adaptation degree weight is set to be 0.3, and the fourth adaptation degree weight is set to be 0.1. In the embodiment, the setting of the adaptation degree weights is not specifically limited, and can be freely set by those skilled in the art.

[0078] Please continue to refer to Figure 3As shown, the method for constructing the task matching model further comprises:

[0079] In step S44, the analysis process of the ability adaptation degree is updated according to the emergency degree and the task difficulty coefficient.

[0080] Specifically, in step S44, if the emergency degree is greater than or equal to the first update threshold, the first adaptation weight is increased and the third adaptation weight is reduced to update the analysis process of the ability adaptation degree, and the increase amount of the first adaptation weight is equal to the reduction amount of the third adaptation weight, which is L1; if the emergency degree is less than the first update threshold, the analysis process of the ability adaptation degree is not updated; if the task difficulty coefficient is greater than or equal to the second update threshold, the first adaptation weight and the second adaptation weight are reduced and the third adaptation weight is increased to update the analysis process of the ability adaptation degree, the reduction amount of the first adaptation weight and the second adaptation weight is equal, and the sum of the reduction amount of the first adaptation weight and the second adaptation weight is equal to the increase amount of the third adaptation weight, which is L2; if the task difficulty coefficient is less than the second update threshold; wherein L1 represents the first change parameter, 0.1≤L1≤0.2, and L2 represents the second change parameter, 0.05≤L1≤0.1.

[0081] Specifically, in the embodiment, the first update threshold is set to 4 and the second update threshold is set to 0.8. The values of the update threshold and the change parameter are not specifically limited in the embodiment, and can be freely set by those skilled in the art. The setting of the second update threshold should satisfy: the second update threshold = the first update threshold x 0.2.

[0082] Specifically, in step S4, the task matching model is constructed, the demand fit degree and the ability adaptation degree are calculated, and the linear weight and the dynamic parameter adjustment mechanism are combined to realize precise personalized recommendation and meet the bidirectional needs of the user and the hospital.

[0083] Please continue to refer to Figure 1 As shown, the method for constructing the task matching model further comprises:

[0084] In step S5, a recommendation list is formulated according to the demand fit degree and is pushed to the user, and a candidate list is formulated according to the ability adaptation degree and is pushed to the task source unit.

[0085] Specifically, in step S5, the recommendation list is formulated according to the demand fit degree, the task content corresponding to the demand fit degree greater than or equal to the fit degree threshold is extracted as a candidate task, and the candidate tasks are sorted in descending order of the demand fit degree, and the first Y candidate tasks are taken as the recommendation list, wherein Y represents the recommendation quantity parameter.

[0086] Specifically, in the embodiment, the recommended quantity parameter is set to 5, and the fitting degree threshold is set to 0.7. In the embodiment, the values of the recommended quantity parameter and the fitting degree threshold are not specifically limited, and a person skilled in the art can freely set them. The recommended quantity parameter should be set to belong to [3, 5], and the fitting degree threshold should be set to belong to [0.6, 0.9].

[0087] Specifically, in the step S5 of the embodiment, the recommended list is formulated according to the capability adaptation degree, candidate users whose task completion degree is greater than or equal to the completion degree threshold and whose user score is greater than or equal to the score threshold are extracted, and the candidate users are sorted in descending order of the capability adaptation degree, and the first Y candidate users are taken as the candidate list.

[0088] Specifically, in the embodiment, the completion degree threshold is set to 0.8, and the score threshold is set to 4. In the embodiment, the values of the completion degree threshold and the score threshold are not specifically limited, and a person skilled in the art can freely set them. The completion degree threshold should be set to belong to [0.8, 0.9], and the score threshold should be set to belong to [3.5, 4].

[0089] Specifically, in the step S5 of the embodiment, the threshold screening and sorting optimization are performed to ensure the priority and practicability of the recommended result and improve the decision efficiency of the user and the hospital.

[0090] Please continue to refer to Figure 1 As shown in the figure, the intelligent matching and recommendation method for the medical product service further includes:

[0091] In step S6, interaction data of the user after receiving the recommended list is collected, and a task matching model is optimized. The interaction data includes accepting the recommendation and ignoring the recommendation.

[0092] Specifically, in the step S6 of the embodiment, the construction process of the task feature vector is optimized according to the interaction data, the recommended list and the candidate list to optimize the task matching model. The number of users who accept the recommendation in the interaction data corresponding to the same task content is extracted as the number of accepted users, the number of users who ignore the recommendation in the interaction data corresponding to the same task content is extracted as the number of ignored users, and the number of users in the candidate list corresponding to the same task content whose interaction data is the number of accepted recommendations is extracted as the number of effective users. The recommendation matching parameter is analyzed according to the number of accepted users, the number of ignored users and the number of effective users. The expression of the recommendation matching parameter is Q = (n1 + n3) / (n1 + n2), wherein Q represents the recommendation matching parameter, n1 represents the number of accepted users, n2 represents the number of ignored users, and n3 represents the number of effective users. The preset matching parameter is updated according to the recommendation matching parameter. If the recommendation matching parameter is greater than or equal to 1, the preset matching parameter is not updated. Otherwise, the value of the preset matching parameter is updated to be equal to the recommendation matching parameter.

[0093] Specifically, in step S6, the model parameters are dynamically adjusted by introducing a feedback mechanism to enhance the adaptive ability of the system and continuously improve the recommendation accuracy.

[0094] Referring to FIG. 1, which is a schematic diagram of a medical product service intelligent matching recommendation platform according to an embodiment of the present application, the medical product service intelligent matching recommendation platform comprises: Figure 4

[0095] a data acquisition module configured to acquire user data and task publishing data;

[0096] a parameter analysis module configured to store the task publishing data and analyze a task difficulty coefficient, and analyze a task complexity adaptability of the user according to the task difficulty coefficient and the user data;

[0097] a vector construction module configured to construct a user feature vector based on the user data and the task complexity adaptability, and construct a task feature vector based on the task publishing data and the task difficulty coefficient;

[0098] a model construction module configured to construct a task matching model based on the user feature vector and the task feature vector, so as to obtain a demand fit degree and an ability adaptation degree;

[0099] a recommendation analysis module configured to formulate a recommendation list according to the demand fit degree and push the recommendation list to the user, and formulate a candidate list according to the ability adaptation degree and push the candidate list to a task source unit;

[0100] a feedback optimization module configured to acquire interaction data of the user after receiving the recommendation list, and optimize the task matching model.

[0101] The embodiment of the present application also provides a computer readable storage medium, which stores instructions, when the instructions are executed on a computer, the computer executes the medical product service intelligent matching recommendation method as described in the above method embodiment.

[0102] ​As will be appreciated by one of ordinary skill in the art, all or some of the steps, systems, and techniques disclosed herein can be embodied in software, firmware, hardware, or any suitable combination thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application- specific integrated circuit. Such software can be distributed on computer readable media, which can comprise computer storage media (or non-transitory media), and communication media (or transitory media). As is well known to those of ordinary skill in the art, the term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Further, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

[0103] Obviously, the above-described embodiments of the present application are only examples for clearly illustrating the present application, and are not intended to limit the implementation of the present application. Based on the above description, other different forms of changes or variations can be made by those of ordinary skill in the art, and it is impossible to enumerate all the embodiments here. Any obvious changes or variations derived from the technical solutions of the present application are still within the protection scope of the present application.

Claims

1. A method for intelligent matching and recommendation of pharmaceutical products and services, characterized in that, include: Collect user data and task release data; Store task release data and analyze task difficulty coefficients; analyze user task complexity adaptability based on task difficulty coefficients and user data. User feature vectors are constructed based on user data and task complexity adaptability, and task feature vectors are constructed based on task release data and task difficulty coefficients. A task matching model is constructed based on user feature vectors and task feature vectors to obtain the degree of demand matching and capability adaptation. Create a recommendation list based on the degree of demand matching and push it to users; create a candidate list based on the degree of capability matching and push it to the task source unit. Collect user interaction data after receiving the recommendation list and optimize the task matching model; Extract task completion data corresponding to task release data with the same task content as difficulty analysis data. Normalize the task time in the difficulty analysis data. Count the number of difficulty analysis data with a successful task status as the number of successful data and the number of difficulty analysis data with a failed task status as the number of failed data. Analyze the task difficulty coefficient based on the difficulty analysis data, the number of successful data, and the number of failed data. The expression for the task difficulty coefficient is TD=0.6×μ(DT1)+0.4×N2 / (N1+N2), where TD represents the task difficulty coefficient, DT1 represents the normalized task time, μ() represents the average value of the data in parentheses, N1 represents the number of successful data, and N2 represents the number of failed data. Based on the task difficulty coefficient and the completed tasks, the user's task complexity fitness is analyzed, and the average task difficulty coefficient corresponding to the user's completed tasks is taken as the task complexity fitness. A user feature vector is constructed based on the user's task completion rate, response speed, task complexity adaptability, user rating, and skill vector. The user's response speed is normalized to obtain the response speed parameter. A four-element vector is constructed, in which each element corresponds one-to-one with the user's task completion rate, response speed parameter, task complexity adaptability, and user rating. The skill vector is filled based on the user's certified skills. The filled skill vector is used as the user's skill vector. The four-element vector is concatenated with the filled skill vector to obtain the user feature vector. Based on the urgency, task difficulty coefficient, required skills, and skill vector, a task feature vector is constructed. A ternary vector is constructed, in which each element corresponds to the urgency, task difficulty coefficient, and preset matching parameters. The skill vector is filled according to the required skills. The filled skill vector is used as the task skill vector. The ternary vector is concatenated with the filled skill vector to obtain the task feature vector. Skill matching parameters are analyzed based on skill vectors in user feature vectors and task feature vectors; The demand fit is analyzed based on user feature vectors, task feature vectors, and skill matching parameters. The expression for the demand fit is: In the formula, MAB represents the demand fit, w1 represents the first fit weight, w2 represents the second fit weight, w3 represents the third fit weight, w4 represents the fourth fit weight, CS represents the skill matching parameter, F represents the task complexity adaptability, E represents the urgency level, T represents the response speed parameter, MS represents the preset matching parameter, and ε represents the smoothing factor. Capability fit is analyzed based on user feature vectors, task feature vectors, and skill matching parameters. The expression for capability fit is: In the formula, MBA represents the ability fit, α1 represents the first fit weight, α2 represents the second fit weight, α3 represents the third fit weight, α4 represents the fourth fit weight, CR represents the task completion rate, and UR represents the user rating. The analysis process of updating capability suitability based on urgency and task difficulty coefficient is as follows: when the urgency is greater than or equal to the first update threshold, the weight of the first suitability is increased and the weight of the third suitability is decreased to update the capability suitability analysis process. When the task difficulty coefficient is greater than or equal to the second update threshold, the weights of the first and second fit are reduced and the weight of the third fit is increased to update the capability fit analysis process.

2. The intelligent matching and recommendation method for pharmaceutical products and services according to claim 1, characterized in that, Different certified skills and required skills are extracted as skill sets, and each skill in the skill set is numbered to obtain a skill number, so that each skill corresponds to a unique skill number. The skills are sorted in ascending order of skill numbers to obtain a skill sequence. A multi-dimensional vector is constructed as the skill vector, and the number of elements in the skill vector is the same as the number of skills in the skill sequence and corresponds one-to-one.

3. The intelligent matching and recommendation method for pharmaceutical products and services according to claim 2, characterized in that, A recommendation list is created based on the degree of demand matching. Tasks with a degree of demand matching greater than or equal to the degree of matching threshold are extracted as candidate tasks and sorted in descending order of degree of demand matching. The top Y candidate tasks are selected as the recommendation list, where Y represents the number of recommendations. A recommendation list is created based on the ability fit. Users whose task completion rate is greater than or equal to the completion rate threshold and whose user rating is greater than or equal to the rating threshold are extracted as candidate users. These candidates are then sorted in descending order of ability fit, and the top Y candidate users are selected as the candidate list.

4. The intelligent matching and recommendation method for pharmaceutical products and services according to claim 3, characterized in that, The process of constructing task feature vectors is optimized based on interaction data, recommendation lists, and candidate lists to improve the task matching model. The number of users who accept recommendations in the interaction data corresponding to the same task content is extracted as the number of accepting users. The number of users who ignore recommendations in the interaction data corresponding to the same task content is extracted as the number of ignoring users. The number of users who accept recommendations in the interaction data of users in the candidate list corresponding to the same task content is extracted as the number of effective users. The recommendation matching parameters are analyzed based on the number of accepting users, the number of ignoring users, and the number of effective users. When the recommendation matching parameter is less than 1, the value of the preset matching parameter is updated to be equal to the recommendation matching parameter.

5. A pharmaceutical product service intelligent matching and recommendation platform, applied to the pharmaceutical product service intelligent matching and recommendation method as described in any one of claims 1-4, characterized in that, include: The data acquisition module collects user data and task release data; The parameter analysis module stores task release data and analyzes task difficulty coefficients. Based on the task difficulty coefficients and user data, it analyzes the user's task complexity adaptability. The vector construction module constructs user feature vectors based on user data and task complexity fitness, and constructs task feature vectors based on task release data and task difficulty coefficients. The model building module constructs a task matching model based on user feature vectors and task feature vectors to obtain the degree of demand matching and capability adaptation. The recommendation analysis module generates a recommendation list based on the degree of relevance to the user's needs and pushes it to the user's organization based on the degree of capability matching. The feedback optimization module collects user interaction data after receiving the recommendation list and optimizes the task matching model.

6. A storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the intelligent matching and recommendation method for pharmaceutical products and services as described in any one of claims 1-4.

Images