Object selection method, device and computer equipment

Abstract

The application relates to an object selection method and device and a computer device, and belongs to the technical field of artificial intelligence. The method comprises the following steps: obtaining project requirement information of a target project and object attribute information of each candidate object. According to the project requirement information and the object attribute information of each candidate object, the matching degree between the corresponding candidate object and the target project is determined, and then the object selection result of the target project is determined. In the application, the project requirement information of the target project and the object attribute information of each candidate object can be automatically obtained under the condition of having a project requirement, and the matching degree between each candidate object and the target project is determined according to the project requirement information and the object attribute information. Then, the object selection result of the target project is automatically determined based on the matching degree between each candidate object and the target project. Not only the human input is reduced, but also the project requirement information and the object attribute information are considered, the consideration is more comprehensive, and the accuracy of the object selection result is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to an object selection method, apparatus, and computer device. Background Technology

[0002] When a company has project requirements, it needs to select the target objects for the project from candidates (such as employees or other resources).

[0003] Currently, when selecting target candidates, most companies rely on manual methods, spending a significant amount of time reviewing candidate profiles and then manually filtering them. This results in low efficiency, and the filtering process often relies solely on the technical tags of the candidates (e.g., if the candidate is an employee, the technical tag is their major). This approach is too simplistic and leads to poor accuracy in the selection. Summary of the Invention

[0004] Therefore, it is necessary to provide an object selection method, apparatus, and computer device that can effectively improve the efficiency and accuracy of object selection, addressing the aforementioned technical problems.

[0005] Firstly, this application provides an object selection method. The method includes:

[0006] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0007] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0008] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0009] In one embodiment, determining the matching degree between the corresponding candidate object and the target project based on project requirement information and object attribute information of each candidate object includes:

[0010] Based on the project requirements information, determine the project requirement characteristics and project constraints;

[0011] For each candidate object, based on the object attribute information of the candidate object, determine the corresponding object skill feature representation, object experience feature representation, object historical project success rate and object constraint information;

[0012] Based on the object's skill characteristics, experience characteristics, historical project success rate, constraint information, project requirement characteristics, and project constraints, the matching degree between candidate objects and target projects is determined.

[0013] In one embodiment, the matching degree between candidate objects and target projects is determined based on object skill feature representation, object experience feature representation, object historical project success rate, object constraint information, project requirement feature representation, and project constraints, including:

[0014] Determine the first similarity between the project requirement feature representation and the object skill feature representation;

[0015] Determine the second similarity between the project requirement feature representation and the object experience feature representation;

[0016] Determine the constraint matching degree based on the object constraint information and project constraints;

[0017] The matching degree between the candidate object and the target object is determined based on the first similarity, the second similarity, the constraint matching degree, and the success rate of the object's historical projects.

[0018] In one embodiment, the matching degree between the candidate object and the target item is determined based on a first similarity, a second similarity, a constraint matching degree, and the object's historical item success rate, including:

[0019] Based on the first weight, second weight, third weight, and fourth weight, the first similarity, second similarity, the success rate of the object's historical projects, and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

[0020] In one embodiment, determining the object skill feature representation of the candidate object based on object attribute information includes:

[0021] Determine the initial skill feature representation based on the object attribute information;

[0022] Based on the initial skill feature representation and skill weights, determine the object skill feature representation of the candidate object.

[0023] In one embodiment, determining the object experience feature representation of the candidate object based on object attribute information includes:

[0024] Determine the initial empirical feature representation based on the object attribute information;

[0025] Based on the initial empirical feature representation and empirical weights, determine the object empirical feature representation of the candidate object.

[0026] In one embodiment, the object selection result of the target item is determined based on the matching degree between each candidate object and the target item, including:

[0027] Based on the matching degree between each candidate and the target project, select the target object from each candidate;

[0028] Based on the target object and the matching degree of the target object, the object selection result of the target project is determined.

[0029] Secondly, this application also provides an object selection device. The device includes:

[0030] The acquisition module is used to acquire project requirements information of the target project and object attribute information of each candidate object;

[0031] The first determination module is used to determine the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object;

[0032] The second determination module is used to determine the object selection result of the target project based on the matching degree between each candidate object and the target project.

[0033] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0034] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0035] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0036] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0038] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0039] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0040] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0041] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0042] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0043] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0044] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0045] The aforementioned object selection method, apparatus, and computer equipment acquire project requirement information of the target project and object attribute information of each candidate object. Based on the project requirement information and the object attribute information of each candidate object, the matching degree between the corresponding candidate object and the target project is determined. Based on the matching degree between each candidate object and the target project, the object selection result for the target project is determined. In this application, when there are project requirements, the project requirement information of the target project and the object attribute information of the candidate objects can be automatically acquired. Based on the project requirement information and object attribute information, the matching degree between each candidate object and the target project is determined, and then based on the matching degree between each candidate object and the target project, the object selection result for the target project is automatically determined. This not only eliminates the need for manual intervention, reducing manpower input, but also considers both project requirement information and object attribute information, providing a more comprehensive consideration and improving the accuracy of the object selection result. Attached Figure Description

[0046] Figure 1 This is a diagram illustrating the application environment of the object selection method provided in this embodiment.

[0047] Figure 2 This is a flowchart illustrating the first object selection method provided in this embodiment;

[0048] Figure 3 This is a flowchart illustrating the matching degree between the first type of selected object and the target project provided in this embodiment;

[0049] Figure 4 This is a flowchart illustrating the matching degree between the second type of selected object and the target project provided in this embodiment;

[0050] Figure 5 This is a flowchart illustrating the second object selection method provided in this embodiment;

[0051] Figure 6 This is a structural block diagram of an object selection device provided in this embodiment;

[0052] Figure 7 This is an internal structural diagram of the computer device provided in this embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] When a company has project requirements, it needs to select the target objects for the project from candidates (such as employees or other resources).

[0055] Currently, when selecting target candidates, most companies rely on manual methods, spending a significant amount of time reviewing candidate profiles and then manually filtering them. This results in low efficiency, and the filtering process often relies solely on the technical tags of the candidates (e.g., if the candidate is an employee, the technical tag is their major). This approach is too simplistic and leads to poor accuracy in the selection.

[0056] To address the aforementioned technical problems, the object selection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, when an enterprise has project requirements, such as needing to select the talent required for a target project, the terminal sends a selection request to the server. Upon receiving the selection request, the server obtains the project requirements information of the target project and the object attribute information of each candidate object; and determines the matching degree between the corresponding candidate object and the target project based on the project requirements information and the object attribute information of each candidate object. Finally, based on the matching degree between each candidate object and the target project, the server determines the object selection result for the target project.

[0057] In this context, the server refers to the equipment that can select the skilled personnel needed for a target project based on the terminal's requirements. The server can be a standalone server or a server cluster. The terminal refers to the user-side terminal device, such as a mobile phone or computer.

[0058] In one embodiment, such as Figure 2 As shown, an object selection method is provided, which is applied to... Figure 1 Taking the server-side as an example, the explanation includes the following steps:

[0059] S201, Obtain the project requirements information of the target project and the object attribute information of each candidate object.

[0060] The target project refers to the project for which a target object needs to be selected, such as a "railway intelligent detection project," a "railway communication construction project," and a "railway network intelligent power distribution project." Project requirements information refers to information such as project research and development, implementation requirements, and professional requirements. Candidate objects refer to alternative targets; these can be skilled personnel or hardware resources and equipment that can provide technical support for the project. Object attribute information can include basic object information, skill information, experience information, and service history information.

[0061] As an optional implementation of this application, when the terminal has an object selection requirement, it sends an object selection request to the server. The object selection request carries project requirement information for the target project. The server can obtain object attribute information of the selected object from a storage device or a specific database. The specific database can be an OA system, a project lifecycle management system, a scientific research results database, an employee information system, etc.

[0062] Another optional implementation of this application embodiment is that the server receives the project requirement information of the target project sent by the terminal. The server publishes object selection requirement information to the associated terminal devices and receives the object attribute information of the candidate objects fed back by the terminal devices. The object selection requirement information includes the project requirement information of the target project. It should be noted that the server can send object selection requirement information to all terminal devices associated with the objects and use the objects that have provided object attribute information as candidate objects.

[0063] S202, based on the project requirements information and the object attribute information of each candidate object, determine the matching degree between the corresponding candidate object and the target project.

[0064] The matching degree refers to the degree of matching between the candidate and the target project. The higher the matching degree, the more suitable the candidate is for the target project. Conversely, the lower the matching degree, the less suitable the candidate is for the target project.

[0065] As an optional implementation of this application, the project requirement information and the object attribute information of each candidate object are input into the correlation analysis model, and the correlation analysis model outputs the matching degree between each candidate object and the target project.

[0066] Another optional implementation of this application involves obtaining a project requirement feature vector based on project requirement information. Then, based on the object attribute information of each candidate object, determining the object skill feature vector for each candidate object. Finally, determining the cosine distance between the object skill feature vector and the project requirement feature vector for each candidate object, and using this cosine distance as the matching degree between each candidate object and the target project.

[0067] S203, determine the object selection result of the target project based on the matching degree between each candidate object and the target project.

[0068] Among them, the object selection result refers to the information related to the object selection of the target project.

[0069] As an optional implementation of this application, a target object is selected based on the matching degree between each candidate object and the target project; and the selected target object is used as the object selection result of the target project.

[0070] Another optional implementation of this application embodiment is to select a target object from each candidate object based on the matching degree between each candidate object and the target project. The object selection result of the target project is determined based on the target object and its corresponding matching degree. In this embodiment, one optional implementation of selecting a target object from each candidate object based on the matching degree is to use candidate objects with a matching degree greater than a preset threshold as target objects. Another optional implementation is to sort each candidate object in descending order based on the matching degree, and select the top preset number of candidate objects as target objects. In this embodiment, an optional implementation of determining the object selection result of the target project based on the target object and its corresponding matching degree is to determine the project responsibilities of each target object based on the matching degree of the target object. The object selection result is determined based on the matching degree of each target object and its project responsibilities. In this embodiment, an optional implementation of determining the object selection result based on the matching degree of each target object and its project responsibilities is to use the matching degree of the target object as the total matching degree, and determine the project responsibilities based on the total matching degree. The technical matching degree and management matching degree are determined based on the object attribute information and project requirement information of the target object, and a comprehensive recommendation index is determined based on the technical matching degree and management matching degree. The selection results are determined based on the overall match rate, project responsibilities, technical skills, management skills, and comprehensive recommendation index of each target candidate. For example, the candidate selection result could be: Zhang: Overall match rate 90%, technical skills match rate 95%, management skills match rate 70%, comprehensive recommendation index ★★★★☆, selected as project leader.

[0071] In this embodiment, project requirement information of the target project and object attribute information of candidate objects are obtained. Based on the project requirement information and object attribute information, the matching degree between each candidate object and the target project is determined. Based on the matching degree between each candidate object and the target project, the object selection result for the target project is determined. In this application, when there are project requirements, the project requirement information of the target project and object attribute information of candidate objects can be automatically obtained. Based on the project requirement information and object attribute information, the matching degree between each candidate object and the target project is determined, and then based on the matching degree between each candidate object and the target project, the object selection result for the target project is automatically determined. This not only eliminates the need for manual intervention, reducing manpower input, but also considers project requirement information and object attribute information, providing a more comprehensive consideration and improving the accuracy of the object selection result.

[0072] In one embodiment, to more accurately determine the matching degree between candidate objects and target items, such as Figure 3 As shown, the optional implementation methods for determining the matching degree between the corresponding candidate object and the target project based on project requirement information and object attribute information of each candidate object include:

[0073] S301, Based on the project requirement information, determine the project requirement characteristics and project constraints.

[0074] The project constraints include time constraints, professional skills and qualifications, and personnel quantity constraints.

[0075] As an optional implementation of this application, the text content corresponding to the project requirement information is input into a pre-trained BERT model. The model's multi-layer Transformer encoder performs semantic encoding on the text content, extracts context-related word embedding vectors, and then performs pooling (average / max pooling) on ​​all word vectors in the text content to generate a fixed-dimensional project requirement feature representation and project constraints. Both the project requirement feature representation and the project constraints can be represented using vectors.

[0076] Another optional implementation method in this application is to pre-construct an ontology library (such as the technical system and experience dimension hierarchy in the fields of rail transit and artificial intelligence, for example, "machine vision" includes sub-technologies such as "object detection and image segmentation"); then map the text corresponding to the project requirement information to nodes in the ontology library, and extract structured domain features (such as technical level, experience type, and domain affiliation); finally, quantify the structured features into project requirement feature representations and project constraints. Both the project requirement feature representations and project constraints can be represented using vectors.

[0077] S302, for each candidate object, determine the candidate object's object skill characteristic representation, object experience characteristic representation, object historical project success rate, and object constraint information based on the candidate object's object attribute information.

[0078] As an optional implementation of this application, semantic analysis is performed on the object attribute information, and based on the semantic analysis results, the object skill feature representation, object experience feature representation, object historical project success rate, and object constraint information of the candidate object are obtained.

[0079] Another optional implementation of this application is to determine the initial experience feature representation based on the object attribute information; specifically, the object attribute information is processed by experience feature extraction to obtain the initial experience feature representation, i.e., the initial experience feature vector representation. Based on the initial experience feature representation and experience weights, the object experience feature representation of the candidate object is determined. An optional implementation of determining experience weights in this embodiment is to first determine four dimensions: experience, expertise, achievements, and potential. Using the four dimensions as rows and columns, a 4th-order judgment matrix P is constructed (rows and columns are all "experience, expertise, achievements, and potential"). Each element p in the matrix... ij Let represent the importance value of the i-th indicator relative to the j-th indicator, and satisfy p ji =1 / p ij (Reverse comparison), p ii=1 (self-comparison). Based on the constructed judgment matrix P, the weight values ​​w1, w2, w3, and w4 of the four-dimensional indicators are solved using classic AHP calculation methods such as the eigenvalue method, sum-product method, and square root method. The core constraint is: w1 + w2 + w3 + w4 = 1. Since the judgment matrix is ​​constructed manually through pairwise comparisons, logical contradictions are prone to exist (such as "experience is more important than expertise, expertise is more important than achievements, and achievements are more important than experience"). Therefore, the validity of the weights needs to be verified through consistency checks. Only when the check passes can the weight vector be used. The core calculation and judgment criteria are as follows: Consistency ratio CR = RI / CI, where the definitions and calculations of the two core indicators are: CI is used to reflect the degree to which the judgment matrix deviates from "complete consistency". The larger the CI value, the more serious the logical contradiction; CI = 0 indicates that the matrix is ​​completely consistent and there is no logical contradiction. Calculation formula: CI = (λmax - n) / (n - 1) where λmax is the largest eigenvalue of the judgment matrix P, and n is the matrix order, here n = 4. RI is a fixed constant, representing the "random interference baseline value" corresponding to the matrix order. It is given by the classical AHP theory and does not require manual calculation. The RI value for a fourth-order matrix is ​​0.90 (an industry-standard value). CR < 0.1 is the gold standard for judging whether the matrix passes the consistency test: if CR < 0.1, the consistency test passes, the weight vector W is logically sound, and it can be directly used for subsequent calculations; if CR ≥ 0.1, the consistency test fails, indicating a significant logical contradiction in the judgment matrix. The importance comparison values ​​between indicators need to be readjusted, i.e., the weight values ​​of the four dimensions need to be adjusted until the test passes. Optionally, in this embodiment, the product of the initial empirical feature representation and the empirical weights can be used as the object's empirical feature representation.

[0080] Another optional implementation of this application embodiment is to determine an initial skill feature representation based on object attribute information. Then, based on the initial skill feature representation and skill weights, determine the object skill feature representation of the candidate object. Optionally, the professional weight in the above embodiments is the same as the skill weight in this embodiment. Another optional implementation is that the skill weight in this embodiment is a weighted sum of the professional weight, achievement weight, and potential weight in the above embodiments. In this embodiment, the product of the initial skill feature representation and the skill weight is used as the object skill feature representation of the candidate object.

[0081] S303. Based on the object's skill characteristics, experience characteristics, historical project success rate, constraint information, project requirement characteristics, and project constraints, determine the matching degree between the candidate object and the target project.

[0082] As an optional implementation of this application, the object skill feature representation, object experience feature representation, object historical project success rate, object constraint information, project requirement feature representation, and project constraint conditions are input into the matching degree analysis model, and the matching degree analysis model outputs the matching degree between the candidate object and the target project.

[0083] Another optional implementation method of this application is to perform feature splicing and fusion on the object-side features and the project-side features respectively to generate a comprehensive feature vector of the object and a comprehensive requirement vector of the project. Then, the cosine similarity of the two fused vectors is calculated, and a weighted correction is made in combination with the historical success rate and constraint matching degree to obtain the matching degree between the candidate object and the target project.

[0084] In this embodiment, project requirement characteristics and project constraints are determined based on project requirement information. For each candidate object, based on object attribute information, the candidate object's skill characteristics, experience characteristics, historical project success rate, and constraint information are determined. Based on these characteristics, the matching degree between the candidate object and the target project is determined. This embodiment effectively improves the accuracy of the matching degree.

[0085] Based on the above embodiments, in order to further improve the accuracy of the determined matching degree, such as Figure 4 As shown, one optional implementation method for determining the matching degree between candidate objects and target projects based on object skill feature representation, object experience feature representation, object historical project success rate, object constraint information, project requirement feature representation, and project constraint conditions includes:

[0086] S401, determine the first similarity between the project requirement feature representation and the object skill feature representation.

[0087] One possible implementation is to determine the cosine distance between the project requirement feature representation and the object skill feature representation, and use the ratio of the cosine distance to a preset threshold as the first similarity.

[0088] Another alternative implementation is to substitute the project requirement feature representation and the object skill feature representation into the cosine similarity function to obtain the first similarity.

[0089] Another alternative implementation involves transforming the project requirement feature representation and the object skill feature representation into a standardized label set (e.g., project requirement {deep learning, computer vision}, talent skill {deep learning, Python}), and calculating the ratio of the intersection to the union of the two sets. This ratio is the first similarity.

[0090] S402, determine the second similarity between the project requirement feature representation and the object experience feature representation.

[0091] It should be noted that the method for determining the second similarity can refer to the various implementation methods for determining the first similarity in the above embodiments, and will not be repeated here.

[0092] S403, determine the constraint matching degree based on object constraint information and project constraints.

[0093] One possible implementation is to verify information such as object availability, project time conflict, and professional qualification matching based on object constraint information and project constraints, and then determine the degree of constraint matching.

[0094] Another alternative implementation is to set a quantitative scoring standard of 0-1 for each constraint (assigning values ​​according to the degree of satisfaction, such as 1 point for complete satisfaction, 0.5 points for partial satisfaction, and 0 points for non-satisfaction), and then assign business weights to each constraint (core constraints have higher weights); constraint matching degree = ∑(score of each constraint × corresponding weight).

[0095] Another alternative implementation is to standardize all constraint terms to numerical values ​​of the same dimension, calculate the Euclidean / Manhattan distance between the object constraint feature vector and the project constraint requirement vector, and then map the distance value inversely to a constraint condition matching degree of 0-1.

[0096] S404. Determine the matching degree between the candidate object and the target object based on the first similarity, the second similarity, the constraint matching degree, and the object's historical project success rate.

[0097] Optionally, in this embodiment, the first similarity, second similarity, historical project success rate of the object, and constraint matching degree are weighted and summed according to the first weight, second weight, third weight, and fourth weight to obtain the matching degree between the candidate object and the target project. Specifically, the matching degree between the candidate object and the target project can be determined by the following formula:

[0098] MatchScore(P,T) = α·Sim(P_req, T_skill) + β·Sim(P_exp, T_exp) +γ·SuccessRate(T) + δ·ConstraintFit(P,T)

[0099] Where P_req represents the project requirement feature representation, T_skill represents the object skill feature representation, Sim() represents the cosine similarity function, T_exp represents the object experience feature representation, SuccessRate(T) represents the object's historical project success rate, ConstraintFit(P,T) represents the constraint matching degree, and α, β, γ, δ represent the first weight, second weight, third weight, and fourth weight, respectively. Each weight can be automatically adjusted according to the project type.

[0100] In this embodiment, the technology calculates the feature similarity and constraint matching degree of projects and objects in a precise manner across multiple dimensions, and integrates the object's historical project success rate to comprehensively determine the matching degree. Its beneficial effects are reflected in the following aspects: it realizes the refinement, quantification, and scientification of object-project matching; splitting the first and second similarity degrees makes the assessment of skill and experience matching more targeted, avoiding the one-sidedness of single-dimensional matching; combining constraint matching degree to achieve precise verification of hard admission requirements; and incorporating historical project success rate to further consider the object's project execution ability and performance. The indicators of each dimension complement each other and support each other, which not only improves the accuracy and rationality of object-project matching, but also makes the matching calculation logic clearer and more interpretable. It provides an objective and hierarchical quantitative basis for subsequent two-way intelligent recommendation and ranking review, effectively avoiding the bias of human subjective judgment, and adapting to the matching needs of different types of projects, helping to efficiently screen target objects with suitable skills, relevant experience, meeting constraints, and excellent performance.

[0101] In one embodiment, such as Figure 5 As shown, one optional implementation of an object selection method includes:

[0102] S501, obtain the project requirements information of the target project and the object attribute information of each candidate object.

[0103] S502, Based on the project requirement information, determine the project requirement characteristics and project constraints.

[0104] S503, for each candidate object, determine the initial skill feature representation based on the object attribute information of the candidate object.

[0105] S504, Based on the initial skill feature representation and skill weight, determine the object skill feature representation of the candidate object.

[0106] S505, Determine the initial empirical feature representation based on the object attribute information.

[0107] S506, Based on the initial empirical feature representation and empirical weights, determine the object empirical feature representation of the selected object.

[0108] S507, Based on the object attribute information of the candidate object, determine the historical project success rate and object constraint information of the candidate object.

[0109] S508, determine the first similarity between the project requirement feature representation and the object skill feature representation.

[0110] S509, determine the second similarity between the project requirement feature representation and the object experience feature representation.

[0111] S510, determine the constraint matching degree based on object constraint information and project constraints.

[0112] S511, based on the first weight, second weight, third weight and fourth weight, the first similarity, second similarity, the success rate of the object's historical projects and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

[0113] S512, Select the target object from each candidate object based on the matching degree between each candidate object and the target project.

[0114] S513, determine the object selection result of the target project based on the target object and the matching degree corresponding to the target object.

[0115] This application obtains the project requirements information of the target project and the object attribute information of each candidate object. Based on the project requirements information and the object attribute information of each candidate object, it determines the matching degree between the corresponding candidate object and the target project. Based on the matching degree between each candidate object and the target project, it determines the object selection result of the target project. In the case of project requirements, this application can automatically obtain the project requirements information of the target project and the object attribute information of the candidate objects, and determine the matching degree between each candidate object and the target project based on the project requirements information and object attribute information. Then, based on the matching degree between each candidate object and the target project, it automatically determines the object selection result of the target project. This not only eliminates the need for manual intervention, reducing manpower input, but also considers project requirements information and object attribute information, making it more comprehensive and improving the accuracy of the object selection result.

[0116] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0117] Based on the same inventive concept, this application also provides an object selection apparatus for implementing the object selection method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more object selection apparatus embodiments provided below can be found in the limitations of the object selection method described above, and will not be repeated here.

[0118] In one embodiment, such as Figure 6 As shown, an object selection device 1 is provided, including: an acquisition module 10, a first determination module 20, and a second determination module 30, wherein:

[0119] Module 10 retrieves the project requirements information of the target project and the object attribute information of each candidate object;

[0120] The first determining module 20 is used to determine the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object;

[0121] The second determining module 30 is used to determine the object selection result of the target project based on the matching degree between each candidate object and the target project.

[0122] In one embodiment, the first determining module is further specifically used for:

[0123] Based on the project requirements information, determine the project requirement characteristics and project constraints;

[0124] For each candidate object, based on the object attribute information of that candidate object, determine the object skill feature representation, object experience feature representation, object historical project success rate, and object constraint information of the candidate object;

[0125] Based on the object's skill characteristics, experience characteristics, historical project success rate, constraint information, project requirement characteristics, and project constraints, the matching degree between candidate objects and target projects is determined.

[0126] In one embodiment, the first determining module is further specifically used for:

[0127] Determine the first similarity between the project requirement feature representation and the object skill feature representation;

[0128] Determine the second similarity between the project requirement feature representation and the object experience feature representation;

[0129] Determine the constraint matching degree based on the object constraint information and project constraints;

[0130] The matching degree between the candidate object and the target object is determined based on the first similarity, the second similarity, the constraint matching degree, and the success rate of the object's historical projects.

[0131] In one embodiment, the first determining module is further specifically used for:

[0132] Based on the first weight, second weight, third weight, and fourth weight, the first similarity, second similarity, the success rate of the object's historical projects, and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

[0133] In one embodiment, the first determining module is further specifically used for:

[0134] Determine the initial skill feature representation based on the object attribute information;

[0135] Based on the initial skill feature representation and skill weights, determine the object skill feature representation of the candidate object.

[0136] In one embodiment, the first determining module is further specifically used for:

[0137] Determine the initial empirical feature representation based on the object attribute information;

[0138] Based on the initial empirical feature representation and empirical weights, determine the object empirical feature representation of the candidate object.

[0139] In one embodiment, the second determining module is further specifically used for:

[0140] Based on the matching degree between each candidate and the target project, select the target object from each candidate;

[0141] Based on the target object and the matching degree of the target object, the object selection result of the target project is determined.

[0142] Each module in the aforementioned object selection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the operations corresponding to each module.

[0143] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores object selection-related data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements an object selection method.

[0144] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0145] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0146] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0147] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0148] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0149] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object, including:

[0150] Based on the project requirements information, determine the project requirement characteristics and project constraints;

[0151] For each candidate object, based on the object attribute information of that candidate object, determine the object skill feature representation, object experience feature representation, object historical project success rate, and object constraint information of the candidate object;

[0152] Based on the object's skill characteristics, experience characteristics, historical project success rate, constraint information, project requirement characteristics, and project constraints, the matching degree between candidate objects and target projects is determined.

[0153] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the matching degree between candidate objects and target projects based on object skill feature representation, object experience feature representation, object historical project success rate, object constraint information, project requirement feature representation, and project constraints, including:

[0154] Determine the first similarity between the project requirement feature representation and the object skill feature representation;

[0155] Determine the second similarity between the project requirement feature representation and the object experience feature representation;

[0156] Determine the constraint matching degree based on the object constraint information and project constraints;

[0157] The matching degree between the candidate object and the target object is determined based on the first similarity, the second similarity, the constraint matching degree, and the success rate of the object's historical projects.

[0158] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the matching degree between the candidate object and the target item based on a first similarity, a second similarity, a constraint matching degree, and the object's historical item success rate, including:

[0159] Based on the first weight, second weight, third weight, and fourth weight, the first similarity, second similarity, the success rate of the object's historical projects, and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

[0160] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the object skill feature representation of the candidate object based on object attribute information, including:

[0161] Determine the initial skill feature representation based on the object attribute information;

[0162] Based on the initial skill feature representation and skill weights, determine the object skill feature representation of the candidate object.

[0163] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the object empirical feature representation of the candidate object based on object attribute information, including:

[0164] Determine the initial empirical feature representation based on the object attribute information;

[0165] Based on the initial empirical feature representation and empirical weights, determine the object empirical feature representation of the candidate object.

[0166] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the object selection result of the target item based on the matching degree between each candidate object and the target item, including:

[0167] Based on the matching degree between each candidate and the target project, select the target object from each candidate;

[0168] Based on the target object and the matching degree of the target object, the object selection result of the target project is determined.

[0169] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0170] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0171] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0172] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0173] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object, including:

[0174] Based on the project requirements information, determine the project requirement characteristics and project constraints;

[0175] For each candidate object, based on the object attribute information of that candidate object, determine the object skill feature representation, object experience feature representation, object historical project success rate, and object constraint information of the candidate object;

[0176] Based on the object's skill characteristics, experience characteristics, historical project success rate, constraint information, project requirement characteristics, and project constraints, the matching degree between candidate objects and target projects is determined.

[0177] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the matching degree between candidate objects and target projects based on object skill feature representation, object experience feature representation, object historical project success rate, object constraint information, project requirement feature representation, and project constraints, including:

[0178] Determine the first similarity between the project requirement feature representation and the object skill feature representation;

[0179] Determine the second similarity between the project requirement feature representation and the object experience feature representation;

[0180] Determine the constraint matching degree based on the object constraint information and project constraints;

[0181] The matching degree between the candidate object and the target object is determined based on the first similarity, the second similarity, the constraint matching degree, and the success rate of the object's historical projects.

[0182] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the matching degree between the candidate object and the target item based on a first similarity, a second similarity, a constraint matching degree, and the object's historical item success rate, including:

[0183] Based on the first weight, second weight, third weight, and fourth weight, the first similarity, second similarity, the success rate of the object's historical projects, and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

[0184] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the object skill feature representation of the candidate object based on object attribute information, including:

[0185] Determine the initial skill feature representation based on the object attribute information;

[0186] Based on the initial skill feature representation and skill weights, determine the object skill feature representation of the candidate object.

[0187] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the object empirical feature representation of the candidate object based on object attribute information, including:

[0188] Determine the initial empirical feature representation based on the object attribute information;

[0189] Based on the initial empirical feature representation and empirical weights, determine the object empirical feature representation of the candidate object.

[0190] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the object selection result of the target item based on the matching degree between each candidate object and the target item, including:

[0191] Based on the matching degree between each candidate and the target project, select the target object from each candidate;

[0192] Based on the target object and the matching degree of the target object, the object selection result of the target project is determined.

[0193] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0194] Obtain the project requirements information of the target project and the object attribute information of each candidate object;

[0195] Based on the project requirements and the object attribute information of each candidate, determine the matching degree between the corresponding candidate and the target project;

[0196] The selection result of the target project is determined based on the matching degree between each candidate and the target project.

[0197] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object, including:

[0198] Based on the project requirements information, determine the project requirement characteristics and project constraints;

[0199] For each candidate object, based on the object attribute information of that candidate object, determine the object skill feature representation, object experience feature representation, object historical project success rate, and object constraint information of the candidate object;

[0200] Based on the object's skill characteristics, experience characteristics, historical project success rate, constraint information, project requirement characteristics, and project constraints, the matching degree between candidate objects and target projects is determined.

[0201] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the matching degree between candidate objects and target projects based on object skill feature representation, object experience feature representation, object historical project success rate, object constraint information, project requirement feature representation, and project constraints, including:

[0202] Determine the first similarity between the project requirement feature representation and the object skill feature representation;

[0203] Determine the second similarity between the project requirement feature representation and the object experience feature representation;

[0204] Determine the constraint matching degree based on the object constraint information and project constraints;

[0205] The matching degree between the candidate object and the target object is determined based on the first similarity, the second similarity, the constraint matching degree, and the success rate of the object's historical projects.

[0206] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the matching degree between the candidate object and the target item based on a first similarity, a second similarity, a constraint matching degree, and the object's historical item success rate, including:

[0207] Based on the first weight, second weight, third weight, and fourth weight, the first similarity, second similarity, the success rate of the object's historical projects, and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

[0208] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the object skill feature representation of the candidate object based on object attribute information, including:

[0209] Determine the initial skill feature representation based on the object attribute information;

[0210] Based on the initial skill feature representation and skill weights, determine the object skill feature representation of the candidate object.

[0211] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the object empirical feature representation of the candidate object based on object attribute information, including:

[0212] Determine the initial empirical feature representation based on the object attribute information;

[0213] Based on the initial empirical feature representation and empirical weights, determine the object empirical feature representation of the candidate object.

[0214] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the object selection result of the target item based on the matching degree between each candidate object and the target item, including:

[0215] Based on the matching degree between each candidate and the target project, select the target object from each candidate;

[0216] Based on the target object and the matching degree of the target object, the object selection result of the target project is determined.

[0217] It should be noted that the data involved in this application (including but not limited to messages and information during the object selection process) are all data that have been fully authorized by all parties, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0218] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0219] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0220] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An object selection method, characterized in that, The method includes: Obtain the project requirements information of the target project and the object attribute information of each candidate object; Based on the project requirement information and the object attribute information of each candidate object, the matching degree between the corresponding candidate object and the target project is determined; The object selection result of the target project is determined based on the matching degree between each candidate object and the target project.

2. The method according to claim 1, characterized in that, The step of determining the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object includes: Based on the project requirement information, determine the project requirement characteristics and project constraints; For each candidate object, based on the object attribute information of the candidate object, determine the object skill feature representation, object experience feature representation, object historical project success rate, and object constraint information of the candidate object; The matching degree between the candidate object and the target project is determined based on the object's skill feature representation, object's experience feature representation, object's historical project success rate, object's constraint information, project requirement feature representation, and project constraint conditions.

3. The method according to claim 2, characterized in that, The step of determining the matching degree between the candidate object and the target project based on the object's skill feature representation, object's experience feature representation, object's historical project success rate, object constraint information, project requirement feature representation, and project constraint conditions includes: Determine the first similarity between the project requirement feature representation and the object skill feature representation; Determine a second similarity between the project requirement feature representation and the object experience feature representation; Determine the constraint matching degree based on the object constraint information and the project constraints; The matching degree between the candidate object and the target object is determined based on the first similarity, the second similarity, the constraint matching degree, and the object's historical project success rate.

4. The method according to claim 3, characterized in that, Determining the matching degree between the candidate object and the target item based on the first similarity, the second similarity, the constraint matching degree, and the object's historical item success rate includes: Based on the first weight, second weight, third weight, and fourth weight, the first similarity, the second similarity, the historical project success rate of the object, and the constraint matching degree are weighted and summed to obtain the matching degree between the candidate object and the target project.

5. The method according to claim 2, characterized in that, The step of determining the object skill feature representation of the candidate object based on the object attribute information includes: Based on the object attribute information, determine the initial skill feature representation; Based on the initial skill feature representation and skill weights, the object skill feature representation of the candidate object is determined.

6. The method according to claim 2, characterized in that, The step of determining the object empirical feature representation of the candidate object based on the object attribute information includes: Based on the object attribute information, determine the initial empirical feature representation; Based on the initial empirical feature representation and empirical weights, the object empirical feature representation of the candidate object is determined.

7. The method according to claim 1, characterized in that, The step of determining the object selection result of the target project based on the matching degree between each candidate object and the target project includes: Based on the matching degree between each candidate object and the target project, a target object is selected from each candidate object; Based on the target object and the matching degree corresponding to the target object, the object selection result of the target project is determined.

8. An object selection device, characterized in that, include: The acquisition module is used to acquire project requirements information of the target project and object attribute information of each candidate object; The first determining module is used to determine the matching degree between the corresponding candidate object and the target project based on the project requirement information and the object attribute information of each candidate object; The second determining module is used to determine the object selection result of the target project based on the matching degree between each candidate object and the target project.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the object selection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the object selection method according to any one of claims 1 to 7.

Images