Development path recommendation method and system based on hospital talent portraits and medium

Abstract

The invention discloses a development path recommendation method and system based on hospital talent portraits and a medium. The method comprises the steps of obtaining hospital strategic target data and processing the data to obtain priority weights and capability demand vectors corresponding to talent development paths, collecting multi-dimensional data of hospital talents, generating talent portrait vectors according to the multi-dimensional data, extracting talent capability feature vectors, obtaining industry trend data, and calculating the industry trend data according to the industry trend data. And performing processing to obtain a gain coefficient corresponding to each talent development path, performing similarity calculation on the ability demand vector and the talent ability feature vector, and selecting a recommended development path according to the similarity, the priority weight and the gain coefficient. Therefore, the purpose of intelligently and accurately recommending the development paths of hospital talents is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of talent development path recommendation, and specifically, to a development path recommendation method, system, and medium based on hospital talent portraits. Background Art

[0002] The traditional hospital talent development model has the following flaws: (1) Talent planning is disconnected from the organization's strategic goals and lacks a systematic connection mechanism; (2) Career development paths are single and fail to fully consider individual differences; (3) Response to industry changes is delayed and lacks the ability to dynamically adjust; (4) Resource allocation is poorly matched with talent characteristics. Existing patented technologies involve career path planning, but they do not address the strategic coordination and dynamic adaptation issues unique to the medical industry. Summary of the Invention

[0003] The purpose of this application is to provide a development path recommendation method, system and medium based on hospital talent portraits. Based on hospital talent portraits, hospital strategic goals and industry development trends, a path matching algorithm is designed. This algorithm recommends the most suitable development path for each hospital talent by calculating the similarity and adaptability between hospital talent portraits and different development paths.

[0004] This application also recommends a development path based on hospital talent portraits, including the following steps:

[0005] Obtain hospital strategic goal data and process it to obtain the priority weights and capability requirement vectors corresponding to each talent development path;

[0006] Collect multi-dimensional data of hospital talents, generate talent portrait vectors based on the multi-dimensional data, and extract talent ability feature vectors;

[0007] Obtain industry trend data and process it to obtain the gain coefficient corresponding to each talent development path;

[0008] Calculating similarity between the capability requirement vector and the talent capability feature vector;

[0009] The recommended development path is determined based on the similarity, priority weight, and gain coefficient.

[0010] Optionally, in the development path recommendation method based on hospital talent profile described in the present application, the step of obtaining hospital strategic goal data and processing to obtain priority weights and capability requirement vectors corresponding to each talent development path includes:

[0011] Obtain hospital strategic goal data and determine the talent development paths and corresponding capability demand indicators based on the hospital strategic goal data;

[0012] Use the Delphi method to quantify the hospital's strategic goal data and obtain the priority weights corresponding to each talent development path;

[0013] The preset AHP algorithm is used to assign indicator weights to the ability requirement indicators corresponding to each talent development path, and the ability requirement vector corresponding to each talent development path is obtained.

[0014] Optionally, in the development path recommendation method based on hospital talent portrait described in the present application, the steps of collecting multi-dimensional data of hospital talents, generating talent portrait vectors based on the multi-dimensional data, and extracting talent capability feature vectors include:

[0015] Collect multi-dimensional data of hospital talents, including basic information data, ability and quality data, and career development data;

[0016] Quantifying the basic information data, ability and quality data, and career development data, and constructing a talent profile vector based on the quantification results;

[0017] The vector component values ​​corresponding to the ability demand indicators are extracted from the talent portrait vector to generate the talent ability feature vector.

[0018] Optionally, in the development path recommendation method based on hospital talent profile described in the present application, the step of obtaining industry trend data and processing to obtain a gain coefficient corresponding to each talent development path includes:

[0019] Obtain industry trend data and input it into the preset LSTM model to obtain the demand forecast value of various industry trend data for various talent development paths;

[0020] Use preset quantitative conversion rules to convert demand forecast values ​​into gain coefficients for each talent development path.

[0021] Optionally, in the development path recommendation method based on hospital talent profile described in the present application, the similarity calculation of the capability requirement vector and the talent capability feature vector includes:

[0022] The preset cosine similarity algorithm is used to calculate the similarity between the capability requirement vector and the talent capability feature vector to obtain the similarity corresponding to each talent development path.

[0023] Optionally, in the development path recommendation method based on hospital talent profile described in the present application, determining the recommended development path based on the similarity and the priority weight and gain coefficient includes:

[0024] The matching degree of each talent development path is obtained according to the similarity, gain coefficient and priority weight corresponding to each talent development path;

[0025] Sort the matching degrees corresponding to each talent development path according to their numerical values, and select the talent development path corresponding to the largest matching degree as the recommended development path.

[0026] In a second aspect, the present application provides a development path recommendation system based on hospital talent portraits, the system comprising: a memory and a processor, wherein the memory stores a program for a development path recommendation method based on hospital talent portraits, and when the program for the development path recommendation method based on hospital talent portraits is executed by the processor, the following steps are implemented:

[0027] Obtain hospital strategic goal data and process it to obtain the priority weights and capability requirement vectors corresponding to each talent development path;

[0028] Collect multi-dimensional data of hospital talents, generate talent portrait vectors based on the multi-dimensional data, and extract talent ability feature vectors;

[0029] Obtain industry trend data and process it to obtain the gain coefficient corresponding to each talent development path;

[0030] Calculating similarity between the capability requirement vector and the talent capability feature vector;

[0031] The recommended development path is determined based on the similarity, priority weight, and gain coefficient.

[0032] Optionally, in the development path recommendation system based on hospital talent profile described in the present application, the step of obtaining hospital strategic goal data and processing to obtain priority weights and capability requirement vectors corresponding to each talent development path includes:

[0033] Obtain hospital strategic goal data and determine the talent development paths and corresponding capability demand indicators based on the hospital strategic goal data;

[0034] Use the Delphi method to quantify the hospital's strategic goal data and obtain the priority weights corresponding to each talent development path;

[0035] The preset AHP algorithm is used to assign indicator weights to the ability requirement indicators corresponding to each talent development path, and the ability requirement vector corresponding to each talent development path is obtained.

[0036] Optionally, in the development path recommendation system based on hospital talent portraits described in the present application, the steps of collecting multi-dimensional data of hospital talents, generating talent portrait vectors based on the multi-dimensional data, and extracting talent capability feature vectors include:

[0037] Collect multi-dimensional data of hospital talents, including basic information data, ability and quality data, and career development data;

[0038] Quantifying the basic information data, ability and quality data, and career development data, and constructing a talent profile vector based on the quantification results;

[0039] The vector component values ​​corresponding to the ability demand indicators are extracted from the talent portrait vector to generate the talent ability feature vector.

[0040] In a third aspect, the present application also provides a computer-readable storage medium, which stores a development path recommendation method program based on hospital talent portraits. When the development path recommendation method program based on hospital talent portraits is executed by a processor, the steps of the development path recommendation method based on hospital talent portraits as described in any one of the above items are implemented.

[0041] From the above, it can be seen that the development path recommendation method, system and medium based on hospital talent portrait provided in this application are designed based on hospital talent portrait, hospital strategic goals and industry development trends. A path matching algorithm is designed. The algorithm recommends the most suitable development path for each hospital talent by calculating the similarity and adaptability between the hospital talent portrait and different development paths.

[0042] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A flowchart of a method for recommending development paths based on hospital talent profiles provided in an embodiment of the present application;

[0045] Figure 2 A flowchart of the method for recommending development paths based on hospital talent profiles provided in an embodiment of the present application, which provides a method for obtaining priority weights and capability requirement vectors corresponding to each talent development path;

[0046] Figure 3 A flowchart of obtaining talent capability feature vectors for a development path recommendation method based on hospital talent portraits provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0048] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0049] Please refer to Figure 1 , Figure 1 This is a flowchart of a method for recommending career paths based on hospital talent profiles in some embodiments of the present application. The method for recommending career paths based on hospital talent profiles is used in a terminal device, such as a computer or mobile phone terminal. The method for recommending career paths based on hospital talent profiles includes the following steps:

[0050] S11. Obtain hospital strategic goal data and process it to obtain the priority weights and capability requirement vectors corresponding to each talent development path;

[0051] S12. Collect multi-dimensional data of hospital talents, generate talent portrait vectors based on the multi-dimensional data, and extract talent capability feature vectors;

[0052] S13. Obtain industry trend data and process it to obtain the gain coefficient corresponding to each talent development path;

[0053] S14, calculating the similarity between the capability requirement vector and the talent capability feature vector;

[0054] S15. Determine a recommended development path based on the similarity, the priority weight, and the gain coefficient.

[0055] It should be noted that the hospital's strategic goal data is obtained and processed to obtain the priority weights of each talent development path (such as clinical expert type, scientific research innovation type, clinical management type) and the capability demand vectors corresponding to each talent development path (such as clinical diagnosis and treatment ability, scientific research ability, management ability, teamwork ability, doctor-patient communication ability, etc.). Multi-dimensional data of hospital talents is collected, and a talent portrait vector containing all features is generated based on the multi-dimensional data. The talent capability feature vector is extracted from the talent portrait vector. Then, based on the industry trend data, the demand forecast value of each talent development path for various industry trend data is obtained, and then converted into the gain coefficient corresponding to each talent development path. Finally, the similarity between the capability demand vector and the talent capability feature vector is calculated, and the recommended development path is selected based on the similarity, priority weight, and gain coefficient. This achieves the purpose of making intelligent and accurate recommendations for the development paths of hospital talents.

[0056] Please refer to Figure 2 , Figure 2 This is a flow chart of obtaining the priority weights and capability requirement vectors corresponding to each talent development path in a development path recommendation method based on hospital talent profiles in some embodiments of the present application. According to an embodiment of the present invention, obtaining hospital strategic goal data and processing to obtain the priority weights and capability requirement vectors corresponding to each talent development path includes:

[0057] S21. Obtain the hospital's strategic goal data and determine the talent development paths and corresponding capability demand indicators based on the hospital's strategic goal data;

[0058] S22. Use the Delphi method to quantify the hospital's strategic goal data and obtain the priority weights corresponding to each talent development path;

[0059] S23. Use the preset AHP algorithm to assign indicator weights to the capability requirement indicators corresponding to each talent development path, and obtain the capability requirement vector corresponding to each talent development path.

[0060] It should be noted that the talent development paths and the corresponding capability requirement indicators for each path are determined according to the hospital's strategic goals, and then the weight values ​​corresponding to different talent development paths are determined according to the Delphi method (such as 0.5 for clinical expert type, 0.3 for scientific research and innovation type, and 0.2 for clinical management type). Then, an independent AHP hierarchical model is constructed for each development path, and the judgment matrix is ​​generated and the global weight is calculated through the pairwise comparison method. The normalized weights are used to generate the standardized capability requirement vector corresponding to each talent development path.

[0061] Please refer to Figure 3 , Figure 3This is a flow chart of obtaining a talent capability feature vector for a development path recommendation method based on hospital talent profiles in some embodiments of the present application. According to embodiments of the present invention, the steps of collecting multi-dimensional data of hospital talents, generating a talent profile vector based on the multi-dimensional data, and extracting the talent capability feature vector include:

[0062] S31. Collect multi-dimensional data on hospital personnel, including basic information data, ability and quality data, and career development data;

[0063] S32. Quantify the basic information data, ability and quality data, and career development data, and construct a talent profile vector based on the quantification results;

[0064] S33. Extract the vector component values ​​corresponding to the capability requirement indicators from the talent portrait vector to generate a talent capability feature vector.

[0065] It should be noted that multi-dimensional data includes basic information data (personal basic data, professional qualification data), ability and quality data (clinical diagnosis and treatment data, scientific research and teaching data, performance output data, 360-degree evaluation results data) and career development data (career experience data, career tendency test data). Among them, personal basic data include name, age, length of service, professional title, professional qualification, educational background and job information data; professional qualification data include professional and technical titles and promotion time data; academic position data include position in medical associations / associations and journal reviewer position data; clinical diagnosis and treatment data include surgical classification and number, diagnostic accuracy, success rate of critical and severe rescue, and number of difficult cases handled; scientific research and teaching data include the number and impact factor of papers published, the level and number of projects, the number of patents / books published, the number of students taught and teaching scores, teaching hours, and the number of teaching achievement awards; performance output data include patient satisfaction scores, outpatient volume, number of operating tables, surgical success rate, and number of consultations; 360-degree assessment result data include teamwork ability scores, cross-departmental collaboration evaluation scores, management ability scores, communication ability scores, and emergency response ability scores; career experience data include the years required for job promotion and the number of major projects participated in; career orientation test data can be obtained through the Holland Scale.

[0066] In this embodiment, the basic information data, ability and quality data, and career development data are first standardized respectively. Among them, categorical data (such as professional titles and job information data) can be processed using one-hot encoding or embedded vectors, and numerical data (such as the number of papers, surgical grade and number, etc.) can be normalized using Z-score. The weight coefficient of each sub-data is then determined according to the Delphi method. Based on the standardized data and weight processing, a talent portrait vector containing all features is obtained. The vector component values ​​corresponding to the ability demand indicators are extracted from the full talent portrait vector to generate a talent ability feature vector (such as a feature vector that can be composed of clinical diagnosis and treatment capabilities, scientific research capabilities, management capabilities, teamwork capabilities, and doctor-patient communication capabilities).

[0067] According to an embodiment of the present invention, the step of obtaining industry trend data and processing to obtain a gain coefficient corresponding to each talent development path includes:

[0068] Obtain industry trend data and input it into the preset LSTM model to obtain the demand forecast value of various industry trend data for various talent development paths;

[0069] Use preset quantitative conversion rules to convert demand forecast values ​​into gain coefficients for each talent development path.

[0070] It should be noted that the predicted value output by the LSTM model is a quantitative representation of the changing trend of factors related to future talent demand. If the predicted value is greater than 0.8, it means that industry trend data has a significant positive impact on the talent development path; a predicted value between 0.2-0.8 indicates a moderate positive impact; a predicted value between 0.2-0.1 indicates a small positive impact; a predicted value between -0.1 and 0.1 indicates no impact; a predicted value less than -0.8 indicates a significant negative impact; a predicted value between -0.8 and -0.2 indicates a moderate negative impact; and a predicted value between -0.2 and -0.1 indicates a small negative impact. In this way, continuous predicted values ​​are mapped to different influence degree intervals, and quantitative conversion rules are further formulated, that is, according to the above influence degree intervals, specific gain coefficient assignment rules are set: when the influence degree is "significant positive influence", the gain coefficient is set to +0.6, when the influence degree is "moderate positive influence", the gain coefficient is set to +0.3, when the influence degree is "small positive influence", the gain coefficient is set to +0.1, when the influence degree is "no influence", the gain coefficient is set to 0, when the influence degree is "significant negative influence", the gain coefficient is set to -0.6, when the influence degree is "moderate negative influence", the gain coefficient is set to -0.3, and when the influence degree is "small positive influence", the gain coefficient is set to -0.1.

[0071] According to an embodiment of the present invention, the similarity calculation between the capability requirement vector and the talent capability feature vector includes:

[0072] The preset cosine similarity algorithm is used to calculate the similarity between the capability requirement vector and the talent capability feature vector to obtain the similarity corresponding to each talent development path.

[0073] It should be noted that the preset cosine similarity algorithm is used to calculate the similarity between the capability requirement vector and the talent capability feature vector corresponding to each talent development path, so as to obtain the similarity corresponding to each talent development path.

[0074] According to an embodiment of the present invention, determining the recommended development path based on the similarity, the priority weight, and the gain coefficient includes:

[0075] The matching degree of each talent development path is obtained according to the similarity, gain coefficient and priority weight corresponding to each talent development path;

[0076] Sort the matching degrees corresponding to each talent development path according to their numerical values, and select the talent development path corresponding to the largest matching degree as the recommended development path.

[0077] It should be noted that the product of the similarity and the gain coefficient + 1 is multiplied by the priority weight as the matching value, and the matching degrees of each talent development path are sorted according to the numerical value, and the talent development path corresponding to the largest matching degree is selected as the recommended development path.

[0078] The present invention also discloses a development path recommendation system based on hospital talent portraits, comprising a memory and a processor. The memory stores a development path recommendation method program based on hospital talent portraits. When the development path recommendation method program based on hospital talent portraits is executed by the processor, the following steps are implemented:

[0079] Obtain hospital strategic goal data and process it to obtain the priority weights and capability requirement vectors corresponding to each talent development path;

[0080] Collect multi-dimensional data of hospital talents, generate talent portrait vectors based on the multi-dimensional data, and extract talent ability feature vectors;

[0081] Obtain industry trend data and process it to obtain the gain coefficient corresponding to each talent development path;

[0082] Calculating similarity between the capability requirement vector and the talent capability feature vector;

[0083] The recommended development path is determined based on the similarity, priority weight, and gain coefficient.

[0084] It should be noted that the hospital's strategic goal data is obtained and processed to obtain the priority weights of each talent development path (such as clinical expert type, scientific research innovation type, clinical management type) and the capability demand vectors corresponding to each talent development path (such as clinical diagnosis and treatment ability, scientific research ability, management ability, teamwork ability, doctor-patient communication ability, etc.). Multi-dimensional data of hospital talents is collected, and a talent portrait vector containing all features is generated based on the multi-dimensional data. The talent capability feature vector is extracted from the talent portrait vector. Then, based on the industry trend data, the demand forecast value of each talent development path for various industry trend data is obtained, and then converted into the gain coefficient corresponding to each talent development path. Finally, the similarity between the capability demand vector and the talent capability feature vector is calculated, and the recommended development path is selected based on the similarity, priority weight, and gain coefficient. This achieves the purpose of making intelligent and accurate recommendations for the development paths of hospital talents.

[0085] According to an embodiment of the present invention, the step of obtaining hospital strategic goal data and processing to obtain priority weights and capability requirement vectors corresponding to each talent development path includes:

[0086] Obtain hospital strategic goal data and determine the talent development paths and corresponding capability demand indicators based on the hospital strategic goal data;

[0087] Use the Delphi method to quantify the hospital's strategic goal data and obtain the priority weights corresponding to each talent development path;

[0088] The preset AHP algorithm is used to assign indicator weights to the ability requirement indicators corresponding to each talent development path, and the ability requirement vector corresponding to each talent development path is obtained.

[0089] It should be noted that the talent development paths and the corresponding capability requirement indicators for each path are determined according to the hospital's strategic goals, and then the weight values ​​corresponding to different talent development paths are determined according to the Delphi method (such as 0.5 for clinical expert type, 0.3 for scientific research and innovation type, and 0.2 for clinical management type). Then, an independent AHP hierarchical model is constructed for each development path, and the judgment matrix is ​​generated and the global weight is calculated through the pairwise comparison method. The normalized weights are used to generate the standardized capability requirement vector corresponding to each talent development path.

[0090] According to an embodiment of the present invention, the steps of collecting multi-dimensional data of hospital talents, generating talent portrait vectors based on the multi-dimensional data, and extracting talent capability feature vectors include:

[0091] Collect multi-dimensional data of hospital talents, including basic information data, ability and quality data, and career development data;

[0092] Quantifying the basic information data, ability and quality data, and career development data, and constructing a talent profile vector based on the quantification results;

[0093] The vector component values ​​corresponding to the ability demand indicators are extracted from the talent portrait vector to generate the talent ability feature vector.

[0094] It should be noted that multi-dimensional data includes basic information data (personal basic data, professional qualification data), ability and quality data (clinical diagnosis and treatment data, scientific research and teaching data, performance output data, 360-degree evaluation results data) and career development data (career experience data, career tendency test data). Among them, personal basic data include name, age, length of service, professional title, professional qualification, educational background and job information data; professional qualification data include professional and technical titles and promotion time data; academic position data include position in medical associations / associations and journal reviewer position data; clinical diagnosis and treatment data include surgical classification and number, diagnostic accuracy, success rate of critical and severe rescue, and number of difficult cases handled; scientific research and teaching data include the number and impact factor of papers published, the level and number of projects, the number of patents / books published, the number of students taught and teaching scores, teaching hours, and the number of teaching achievement awards; performance output data include patient satisfaction scores, outpatient volume, number of operating tables, surgical success rate, and number of consultations; 360-degree assessment result data include teamwork ability scores, cross-departmental collaboration evaluation scores, management ability scores, communication ability scores, and emergency response ability scores; career experience data include the years required for job promotion and the number of major projects participated in; career orientation test data can be obtained through the Holland Scale.

[0095] In this embodiment, the basic information data, ability and quality data, and career development data are first standardized respectively. Among them, categorical data (such as professional titles and job information data) can be processed using one-hot encoding or embedded vectors, and numerical data (such as the number of papers, surgical grade and number, etc.) can be normalized using Z-score. The weight coefficient of each sub-data is then determined according to the Delphi method. Based on the standardized data and weight processing, a talent portrait vector containing all features is obtained. The vector component values ​​corresponding to the ability demand indicators are extracted from the full talent portrait vector to generate a talent ability feature vector (such as a feature vector that can be composed of clinical diagnosis and treatment capabilities, scientific research capabilities, management capabilities, teamwork capabilities, and doctor-patient communication capabilities).

[0096] According to an embodiment of the present invention, the step of obtaining industry trend data and processing to obtain a gain coefficient corresponding to each talent development path includes:

[0097] Obtain industry trend data and input it into the preset LSTM model to obtain the demand forecast value of various industry trend data for various talent development paths;

[0098] Use preset quantitative conversion rules to convert demand forecast values ​​into gain coefficients for each talent development path.

[0099] It should be noted that the predicted value output by the LSTM model is a quantitative representation of the changing trend of factors related to future talent demand. If the predicted value is greater than 0.8, it means that industry trend data has a significant positive impact on the talent development path; a predicted value between 0.2-0.8 indicates a moderate positive impact; a predicted value between 0.2-0.1 indicates a small positive impact; a predicted value between -0.1 and 0.1 indicates no impact; a predicted value less than -0.8 indicates a significant negative impact; a predicted value between -0.8 and -0.2 indicates a moderate negative impact; and a predicted value between -0.2 and -0.1 indicates a small negative impact. In this way, continuous predicted values ​​are mapped to different influence degree intervals, and quantitative conversion rules are further formulated, that is, according to the above influence degree intervals, specific gain coefficient assignment rules are set: when the influence degree is "significant positive influence", the gain coefficient is set to +0.6, when the influence degree is "moderate positive influence", the gain coefficient is set to +0.3, when the influence degree is "small positive influence", the gain coefficient is set to +0.1, when the influence degree is "no influence", the gain coefficient is set to 0, when the influence degree is "significant negative influence", the gain coefficient is set to -0.6, when the influence degree is "moderate negative influence", the gain coefficient is set to -0.3, and when the influence degree is "small positive influence", the gain coefficient is set to -0.1.

[0100] According to an embodiment of the present invention, the similarity calculation between the capability requirement vector and the talent capability feature vector includes:

[0101] The preset cosine similarity algorithm is used to calculate the similarity between the capability requirement vector and the talent capability feature vector to obtain the similarity corresponding to each talent development path.

[0102] It should be noted that the preset cosine similarity algorithm is used to calculate the similarity between the capability requirement vector and the talent capability feature vector corresponding to each talent development path, so as to obtain the similarity corresponding to each talent development path.

[0103] According to an embodiment of the present invention, determining the recommended development path based on the similarity, the priority weight, and the gain coefficient includes:

[0104] The matching degree of each talent development path is obtained according to the similarity, gain coefficient and priority weight corresponding to each talent development path;

[0105] Sort the matching degrees corresponding to each talent development path according to their numerical values, and select the talent development path corresponding to the largest matching degree as the recommended development path.

[0106] It should be noted that the product of the similarity and the gain coefficient + 1 is multiplied by the priority weight as the matching value, and the matching degrees of each talent development path are sorted according to the numerical value, and the talent development path corresponding to the largest matching degree is selected as the recommended development path.

[0107] A third aspect of the present invention provides a readable storage medium, which stores a development path recommendation method program based on hospital talent portraits. When the development path recommendation method program based on hospital talent portraits is executed by a processor, the steps of the development path recommendation method based on hospital talent portraits as described in any one of the above items are implemented.

[0108] The present invention discloses a development path recommendation method, system and medium based on hospital talent portraits. Based on hospital talent portraits, hospital strategic goals and industry development trends, a path matching algorithm is designed. The algorithm recommends the most suitable development path for each hospital talent by calculating the similarity and adaptability between hospital talent portraits and different development paths.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0110] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0111] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0112] Those skilled in the art will understand that all or part of the steps of the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc. Various media that can store program codes.

[0113] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A development path recommendation method based on hospital talent portraits, characterized by: The following steps are involved: Obtain hospital strategic goal data and process it to obtain the priority weights and capability requirement vectors corresponding to each talent development path; Collect multi-dimensional data of hospital talents, generate talent portrait vectors based on the multi-dimensional data, and extract talent ability feature vectors; Obtain industry trend data and process it to obtain the gain coefficient corresponding to each talent development path; Calculating similarity between the capability requirement vector and the talent capability feature vector; The recommended development path is determined based on the similarity, priority weight, and gain coefficient.

2. The method for recommending development paths based on hospital talent portraits according to claim 1 is characterized in that: The step of obtaining hospital strategic goal data and processing the data to obtain the priority weights and capability requirement vectors corresponding to each talent development path includes: Obtain hospital strategic goal data and determine the talent development paths and corresponding capability demand indicators based on the hospital strategic goal data; Use the Delphi method to quantify the hospital's strategic goal data and obtain the priority weights corresponding to each talent development path; The preset AHP algorithm is used to assign indicator weights to the ability requirement indicators corresponding to each talent development path, and the ability requirement vector corresponding to each talent development path is obtained.

3. The method for recommending development paths based on hospital talent portraits according to claim 2 is characterized in that: The method of collecting multi-dimensional data of hospital talents, generating talent portrait vectors based on the multi-dimensional data, and extracting talent capability feature vectors includes: Collect multi-dimensional data of hospital talents, including basic information data, ability and quality data, and career development data; Quantifying the basic information data, ability and quality data, and career development data, and constructing a talent profile vector based on the quantification results; The vector component values ​​corresponding to the ability demand indicators are extracted from the talent portrait vector to generate the talent ability feature vector.

4. The method for recommending development paths based on hospital talent portraits according to claim 3 is characterized in that: The acquisition of industry trend data and processing to obtain the gain coefficient corresponding to each talent development path includes: Obtain industry trend data and input it into the preset LSTM model to obtain the demand forecast value of various industry trend data for various talent development paths; Use preset quantitative conversion rules to convert demand forecast values ​​into gain coefficients for each talent development path.

5. The method for recommending development paths based on hospital talent portraits according to claim 4 is characterized in that: The similarity calculation between the capability requirement vector and the talent capability feature vector includes: The preset cosine similarity algorithm is used to calculate the similarity between the capability requirement vector and the talent capability feature vector to obtain the similarity corresponding to each talent development path.

6. The method for recommending development paths based on hospital talent portraits according to claim 5 is characterized in that: The determining of the recommended development path according to the similarity, the priority weight, and the gain coefficient includes: The matching degree of each talent development path is obtained according to the similarity, gain coefficient and priority weight corresponding to each talent development path; Sort the matching degrees corresponding to each talent development path according to their numerical values, and select the talent development path corresponding to the largest matching degree as the recommended development path.

7. The development path recommendation system based on hospital talent portrait is characterized by: The system includes a memory and a processor, wherein the memory stores a program for a method for recommending a development path based on a hospital talent profile, and when the program for recommending a development path based on a hospital talent profile is executed by the processor, the following steps are implemented: Obtain hospital strategic goal data and process it to obtain the priority weights and capability requirement vectors corresponding to each talent development path; Collect multi-dimensional data of hospital talents, generate talent portrait vectors based on the multi-dimensional data, and extract talent ability feature vectors; Obtain industry trend data and process it to obtain the gain coefficient corresponding to each talent development path; Calculating similarity between the capability requirement vector and the talent capability feature vector; The recommended development path is determined based on the similarity, priority weight, and gain coefficient.

8. The development path recommendation system based on hospital talent portrait according to claim 7 is characterized in that: The step of obtaining hospital strategic goal data and processing the data to obtain the priority weights and capability requirement vectors corresponding to each talent development path includes: Obtain hospital strategic goal data and determine the talent development paths and corresponding capability demand indicators based on the hospital strategic goal data; Use the Delphi method to quantify the hospital's strategic goal data and obtain the priority weights corresponding to each talent development path; The preset AHP algorithm is used to assign indicator weights to the ability requirement indicators corresponding to each talent development path, and the ability requirement vector corresponding to each talent development path is obtained.

9. The development path recommendation system based on hospital talent portrait according to claim 8 is characterized in that: The method of collecting multi-dimensional data of hospital talents, generating talent portrait vectors based on the multi-dimensional data, and extracting talent capability feature vectors includes: Collect multi-dimensional data of hospital talents, including basic information data, ability and quality data, and career development data; Quantifying the basic information data, ability and quality data, and career development data, and constructing a talent profile vector based on the quantification results; The vector component values ​​corresponding to the ability demand indicators are extracted from the talent portrait vector to generate the talent ability feature vector.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a development path recommendation program based on hospital talent portraits. When the development path recommendation program based on hospital talent portraits is executed by a processor, the steps of the development path recommendation method based on hospital talent portraits as described in any one of claims 1 to 6 are implemented.

Images