Personnel allocation method and device, computer equipment, storage medium and computer program product

Abstract

The embodiment of the invention provides a personnel allocation method and device, computer equipment, a storage medium and a computer program product, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining object basic information of a to-be-distributed object, and obtaining an object semantic vector of the to-be-distributed object according to the object basic information; determining matching object data of a plurality of matching objects matched with the to-be-distributed object in an object semantic vector library according to the object semantic vector; determining a plurality of candidate matching personnel corresponding to the to-be-distributed object according to the plurality of matching objects and the matching object data of each matching object; acquiring a personnel evaluation result of each candidate matching personnel according to the at least one evaluation index of each candidate matching personnel and the evaluation basis data of each evaluation index by using a personnel evaluation model; and determining a target matching person of the to-be-allocated object according to the person evaluation result. According to the method, the accuracy and efficiency of personnel allocation are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a personnel allocation method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] In some business scenarios, it is necessary to match suitable service personnel to the objects to be assigned, such as customers. Generally, artificial intelligence technology can be introduced to improve the accuracy of service personnel matching.

[0003] In the current related technologies, candidate service personnel can be screened based on their service results, and ultimately the target service personnel for the object to be assigned, that is, the most suitable service personnel, can be determined. However, insufficient consideration of the service personnel's characteristic information may lead to low service personnel matching accuracy. Therefore, the current related technologies have the problem of low matching precision. Summary of the invention

[0004] Based on this, it is necessary to provide a personnel allocation method, apparatus, computer equipment, storage medium and computer program product to address the above technical issues.

[0005] In a first aspect, the present application provides a personnel allocation method. The method comprises:

[0006] Obtaining object basic information of the object to be assigned, and obtaining an object semantic vector of the object to be assigned according to the object basic information;

[0007] According to the object semantic vector, determining matching object data of a plurality of matching objects matching the object to be assigned in a pre-built object semantic vector library;

[0008] Determine a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects;

[0009] Using the personnel evaluation model, according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator, obtaining a personnel evaluation result of each candidate matching person;

[0010] According to the personnel evaluation result, a target matching person for the object to be assigned is determined from among the plurality of candidate matching persons, and the target matching person is assigned to the object to be assigned.

[0011] In one embodiment, the method of obtaining the object semantic vector of the object to be assigned based on the object basic information includes: obtaining the object semantic vector corresponding to the object to be assigned based on the object basic information of the object to be assigned; the object basic information includes multiple feature key-value pairs; each feature key-value pair includes a feature name and a feature value; there is a corresponding relationship between the feature name and the feature value; the object basic information is input into a pre-trained semantic representation model to obtain the object semantic vector of the object to be assigned; wherein the semantic representation model uses a pre-trained multi-layer perceptron network to determine and output the object semantic vector of the object to be assigned based on the feature value vectors of the multiple feature key-value pairs contained in the object basic information.

[0012] In one of the embodiments, the object semantic vector library includes historical semantic vectors of multiple historical objects; determining the matching object data of multiple matching objects that match the object to be assigned in a pre-built object semantic vector library based on the object semantic vector includes: obtaining the similarity between the object semantic vector and the historical semantic vector of each of the multiple historical objects; determining the historical object corresponding to the similarity greater than a preset similarity threshold as the matching object of the object to be assigned, and determining the historical object data of the historical object as the matching object data of the object to be assigned.

[0013] In one of the embodiments, determining multiple candidate matching persons corresponding to the objects to be assigned based on the multiple matching objects and the matching object data of each matching object includes: determining the assigned persons corresponding to each matching object based on the multiple matching objects and the matching object data of each matching object; determining the assigned persons as the candidate matching persons corresponding to the objects to be assigned, to obtain multiple candidate matching persons.

[0014] In one of the embodiments, the use of the personnel evaluation model, before obtaining the personnel evaluation results of each candidate matching person based on at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator, also includes: determining at least one evaluation indicator of each candidate matching person; obtaining basic personnel information of each candidate matching person; and determining the evaluation basis data of each evaluation indicator based on the basic personnel information and at least one evaluation indicator.

[0015] In one of the embodiments, the personnel evaluation model is used to obtain the personnel evaluation results of each candidate matching person according to at least one evaluation indicator of each candidate matching person and the evaluation basis data of each evaluation indicator, including: using the personnel evaluation model to obtain the single indicator evaluation results of each candidate matching person under each evaluation indicator according to at least one evaluation indicator of each candidate matching person and the evaluation basis data of each evaluation indicator; obtaining the personnel evaluation results of each candidate matching person according to the single indicator evaluation results corresponding to each evaluation indicator in at least one evaluation indicator.

[0016] In a second aspect, the present application provides a personnel allocation device. The device comprises:

[0017] An acquisition module, used to acquire object basic information of an object to be allocated, and acquire an object semantic vector of the object to be allocated according to the object basic information;

[0018] A matching module, configured to determine, in a pre-built object semantic vector library, matching object data of a plurality of matching objects that match the object to be assigned according to the object semantic vector;

[0019] A screening module, used for determining a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects;

[0020] An evaluation module, used to obtain a personnel evaluation result of each candidate matching person according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator by using a personnel evaluation model;

[0021] An allocation module is used to determine a target matching person for the object to be allocated from among a plurality of candidate matching persons according to the personnel evaluation result, and allocate the target matching person to the object to be allocated.

[0022] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0023] Obtaining object basic information of the object to be assigned, and obtaining an object semantic vector of the object to be assigned according to the object basic information;

[0024] According to the object semantic vector, determining matching object data of a plurality of matching objects matching the object to be assigned in a pre-built object semantic vector library;

[0025] Determine a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects;

[0026] Using the personnel evaluation model, according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator, obtaining a personnel evaluation result of each candidate matching person;

[0027] According to the personnel evaluation result, a target matching person for the object to be assigned is determined from among the plurality of candidate matching persons, and the target matching person is assigned to the object to be assigned.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0029] Obtaining object basic information of the object to be assigned, and obtaining an object semantic vector of the object to be assigned according to the object basic information;

[0030] According to the object semantic vector, determining matching object data of a plurality of matching objects matching the object to be assigned in a pre-built object semantic vector library;

[0031] Determine a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects;

[0032] Using the personnel evaluation model, according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator, obtaining a personnel evaluation result of each candidate matching person;

[0033] According to the personnel evaluation result, a target matching person for the object to be assigned is determined from among the plurality of candidate matching persons, and the target matching person is assigned to the object to be assigned.

[0034] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Obtaining object basic information of the object to be assigned, and obtaining an object semantic vector of the object to be assigned according to the object basic information;

[0036] According to the object semantic vector, determining matching object data of a plurality of matching objects matching the object to be assigned in a pre-built object semantic vector library;

[0037] Determine a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects;

[0038] Using the personnel evaluation model, according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator, obtaining a personnel evaluation result of each candidate matching person;

[0039] According to the personnel evaluation result, a target matching person for the object to be assigned is determined from among the plurality of candidate matching persons, and the target matching person is assigned to the object to be assigned.

[0040] In the above-mentioned personnel allocation method, device, computer equipment, storage medium and computer program product, the object basic information of the object to be allocated is obtained, and the object semantic vector of the object to be allocated is obtained according to the object basic information; according to the object semantic vector, the matching object data of multiple matching objects matching the object to be allocated is determined in the pre-constructed object semantic vector library; according to the multiple matching objects and the matching object data of each matching object, multiple candidate matching personnel corresponding to the object to be allocated are determined; using the personnel evaluation model, according to at least one evaluation index of each candidate matching personnel and the evaluation basis data of each evaluation index, the personnel evaluation result of each candidate matching personnel is obtained; according to the personnel evaluation result, the target matching personnel of the object to be allocated is determined among the multiple candidate matching personnel, and the target matching personnel is assigned to the object to be allocated. In the method provided by the embodiment of the present application, a large model can be introduced, that is, a personnel evaluation model to realize the personnel allocation of the object to be allocated, and multiple evaluation indicators for the candidate matching personnel can be determined as the prompt words of the large model, and then, the large model is used to perform multi-dimensional evaluation on the candidate matching personnel, and according to the evaluation results, the target matching personnel of the object to be allocated is determined, which can improve the accuracy of personnel evaluation, and then, the accuracy and efficiency of personnel allocation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] FIG1 is a flow chart of a personnel allocation method provided in an embodiment of the present application;

[0043] FIG2 is a flow chart of another personnel allocation method provided in an embodiment of the present application;

[0044] FIG3 is a schematic diagram of a process for screening matching objects for an object to be assigned provided in an embodiment of the present application;

[0045] FIG4 is a schematic diagram of a process for obtaining multiple candidate matching persons provided in an embodiment of the present application;

[0046] FIG5 is a schematic diagram of a process for determining evaluation basis data for each evaluation indicator provided in an embodiment of the present application;

[0047] FIG6 is a structural block diagram of a personnel allocation device provided in an embodiment of the present application;

[0048] FIG. 7 is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0051] In an exemplary embodiment, as shown in FIG1 , a personnel allocation method is provided. This embodiment is illustrated by applying the method to a server. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0052] Step 102: Obtain object basic information of the object to be assigned, and obtain an object semantic vector of the object to be assigned according to the object basic information.

[0053] Among them, the object to be assigned can be a customer to be assigned in a specific business scenario, and the customer to be assigned can be any customer who needs to be assigned a service personnel (for example, a salesperson), for example, a new customer and a secondary customer who needs to reallocate a service personnel. The corresponding financial business system can obtain the customer basic information of the customer to be assigned and perform relevant processing on the customer basic information of the customer to be assigned with the authorization of the customer to be assigned. The scope of authorization may include but is not limited to the following aspects: collecting and obtaining the customer basic information of the customer to be assigned; converting the customer basic information into a customer semantic vector; performing vector retrieval in the customer semantic vector library based on the customer semantic vector to determine the matching object data of multiple matching objects that match the object to be assigned; obtaining the similarity between the customer basic information and multiple historical semantic vectors in the object semantic vector library. The authorization method includes but is not limited to verbal confirmation and written confirmation. The object basic information includes basic data information of multiple dimensions of the object to be allocated, such as customer identification information (e.g., customer identification (ID)), customer basic portrait (gender, age, education, occupation, place of birth and address, etc.), customer behavior data (whether to have been insured in the past, whether to have made claims and whether to have registered for life insurance applications, etc.), customer relationship network (family relationship, social relationship and policy relationship, etc.) and customer source channels, etc. In a possible implementation, a customer feature library can be constructed, which can include multiple customers and customer feature data of each of the multiple customers, that is, object basic information, and each group of customer feature data can be marked with the customer ID of the corresponding customer. In this case, in the process of obtaining the object basic information of the object to be allocated, the customer feature data corresponding to the object to be allocated can be obtained in the customer feature library according to the object identification of the object to be allocated, that is, the customer ID, and the object basic information of the object to be allocated can be determined according to the customer feature data corresponding to the object to be allocated. The object basic information of the object to be allocated includes multiple feature key-value pairs, each feature key-value pair includes a feature name and a feature value; there is a corresponding relationship between the feature name and the feature value; the customer feature information of the object to be allocated is pre-stored in the customer feature library.

[0054] Furthermore, a semantic representation model for obtaining a customer's customer semantic vector may be pre-trained, and the semantic representation model may be used to convert the object basic information of the object to be assigned into the object semantic vector of the object to be assigned. Specifically, the object basic information of the object to be assigned may be input into a pre-trained semantic representation model, and the semantic identification model may perform feature extraction on the object basic information to obtain the object semantic vector of the object to be assigned. The semantic representation model may be a neural network model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), and a long short-term memory network (LSTM).

[0055] Step 104 : determining, in a pre-built object semantic vector library according to the object semantic vector, matching object data of a plurality of matching objects that match the object to be assigned.

[0056] The pre-built object semantic vector library may be a pre-built customer semantic vector library. The customer semantic vector library may be built based on the historical customer data of multiple historical customers. The historical customer data are all acquired and processed with full authorization of the corresponding historical customers. The authorization scope may include but is not limited to the following aspects: the corresponding financial business system may acquire the historical customer data of the historical customer with the authorization of each historical customer; build a customer semantic vector library based on the historical customer data; and determine the candidate matching personnel for the customer to be assigned according to the historical customer data. The authorization method includes but is not limited to verbal confirmation and written confirmation. The historical customer data of each historical customer among the multiple historical customers may include the customer semantic vector of the corresponding historical customer, the service personnel (e.g., sales personnel) corresponding to the historical customer, and the corresponding order label. The customer semantic vector of the corresponding historical customer may be the customer feature vector of the historical customer; the historical customer is a customer to whom a service personnel has been assigned; and the order label is used to indicate whether the service personnel and the historical customer have reached a transaction and completed the order. The historical customer data may include the customer feature information corresponding to the historical customer, and the historical customer data may be obtained from the insurance policy database or user database of each business system. In this step, the object semantic vector library includes the historical semantic vectors of multiple historical customers, and the similarity between the customer semantic vector of the customer to be assigned and the historical semantic vector of each of the multiple historical customers can be obtained. Then, multiple matching objects that match the object to be assigned can be determined based on the similarity, and the historical customer data of each of the multiple matching objects can be used as the matching object data of the customer to be assigned. In a possible implementation, the historical customers whose similarity is greater than the preset similarity threshold can be used as matching customers of the customer to be assigned, that is, matching objects. Among them, the similarity between the customer semantic vector and the historical semantic vector of each of the multiple historical customers can be measured by the distance between the customer semantic vector and the historical semantic vector of each of the multiple historical customers. The distance between the customer semantic vector and the historical semantic vector of each of the multiple historical customers can be obtained by using a variety of distance calculation methods, such as Euclidean distance, cosine distance, Hamming distance, and Manhattan distance. As shown in Figure 2, the process of this step can be called similar customer retrieval, and the pre-built object semantic vector library can be called a service customer vector library.

[0057] Step 106: Determine a plurality of candidate matching persons corresponding to the objects to be assigned based on the plurality of matching objects and the matching object data of each matching object.

[0058] Among them, the matching object data includes the customer feature information of the corresponding matching object, the corresponding service personnel, and the corresponding order label, and the multiple service personnel corresponding to the multiple matching objects can be determined as the multiple candidate matching personnel corresponding to the object to be assigned. In a possible implementation, the score of each service personnel can also be obtained according to the order label corresponding to the service personnel, and then, according to the score, the service personnel whose scores are greater than the preset score threshold among the multiple service personnel corresponding to the multiple matching objects can be determined as the multiple candidate matching personnel corresponding to the object to be assigned. As shown in Figure 2, the process of this step can be described as candidate sales extraction.

[0059] Step 108: using the personnel evaluation model, obtaining personnel evaluation results according to at least one evaluation indicator of each candidate matching personnel and evaluation basis data of each evaluation indicator.

[0060] Among them, in this step, the large model can be used to obtain the personnel evaluation model, and the personnel evaluation model can perform multi-dimensional evaluation on each of the multiple candidate matching personnel. The basic personnel information and evaluation basis data of each candidate matching personnel involved in the evaluation process are obtained and processed under the condition that the corresponding candidate matching personnel are fully authorized. The authorization scope may include but is not limited to the following aspects: collecting and obtaining the basic personnel information and evaluation basis data of each candidate matching personnel; multi-dimensionally dividing the basic personnel information of each candidate matching personnel to obtain at least one evaluation indicator and the evaluation basis data of each evaluation indicator; obtaining the single indicator evaluation results of each candidate matching personnel under each evaluation indicator according to the evaluation basis data; obtaining the personnel evaluation results of each candidate matching personnel according to at least one single indicator evaluation result of each candidate matching personnel. The authorization method includes but is not limited to verbal confirmation and written confirmation. The implementation of the multi-dimensional evaluation may include: determining multiple evaluation indicators assigned to the service personnel of the object to be assigned, for example, the basic characteristics, professional ability, communication ability and work attitude of the service personnel; obtaining the prompt words of the personnel evaluation model according to the multiple evaluation indicators; and then, the personnel evaluation model can be used to perform multi-dimensional evaluation on each of the multiple candidate matching personnel. Among them, the basic characteristics include: sales personnel's education, age, years of work in the insurance industry, years of work in the company, graduation school level, whether to obtain relevant certificates, gender, etc.; professional ability includes: control of various insurance products, completion of training courses, job level, performance in the past two years, understanding of market dynamics, understanding of competitors, etc.; communication ability includes: language level, communication and expression ability rating, negotiation skills ability rating, customer understanding ability rating, customer persuasion ability rating, etc.; work attitude includes: self-driving force rating, continuous learning ability rating, career planning ability rating, work enthusiasm rating, etc. Specifically, the object basic information of the object to be assigned, at least one evaluation indicator of each candidate matching person in the multiple candidate matching persons, and the evaluation basis data of each evaluation indicator can be input into the personnel evaluation model, and the personnel evaluation model can obtain the single indicator evaluation results of each candidate matching person under each evaluation indicator, and then, according to the single indicator evaluation results of each candidate matching person under each evaluation indicator, the personnel evaluation results of each candidate matching person can be obtained.In one possible implementation, the single indicator evaluation result and the personnel evaluation result may be in the form of evaluation scores, the single indicator evaluation result may be a first evaluation score, and the personnel evaluation result may be a second evaluation score. The indicator weight of each evaluation indicator may be determined based on the importance of each evaluation indicator for the evaluation of candidate matching personnel. Furthermore, based on the indicator weight, the first evaluation score corresponding to at least one evaluation indicator, i.e., the single indicator evaluation result, may be weightedly summed to obtain the second evaluation score of each candidate matching personnel, i.e., the personnel evaluation result.

[0061] Step 110, according to the personnel evaluation result, determine the target matching personnel of the object to be assigned from multiple candidate matching personnel, and assign the target matching personnel to the object to be assigned.

[0062] The target matching person for the object to be assigned can be determined from the multiple candidate matching persons according to the personnel evaluation results of the multiple candidate matching persons. If the personnel evaluation result is the second evaluation score, the candidate matching person with the highest second evaluation score can be determined as the target matching person for the object to be assigned.

[0063] In the method of this embodiment, the object basic information of the object to be assigned is obtained, and the object semantic vector of the object to be assigned is obtained according to the object basic information; according to the object semantic vector, the matching object data of multiple matching objects matching the object to be assigned is determined in the pre-constructed object semantic vector library; according to the multiple matching objects and the matching object data of each matching object, multiple candidate matching personnel corresponding to the object to be assigned are determined; using the personnel evaluation model, according to at least one evaluation index of each candidate matching personnel and the evaluation basis data of each evaluation index, the personnel evaluation result of each candidate matching personnel is obtained; according to the personnel evaluation result, the target matching personnel of the object to be assigned is determined among the multiple candidate matching personnel, and the target matching personnel is assigned to the object to be assigned. In the method provided by the embodiment of the present application, a large model can be introduced, that is, a personnel evaluation model to realize the personnel allocation of the object to be assigned, and multiple evaluation indicators for the candidate matching personnel can be determined as the prompt words of the large model, and then, the large model is used to perform multi-dimensional evaluation on the candidate matching personnel, and according to the evaluation results, the target matching personnel of the object to be assigned is determined, which can improve the accuracy of personnel evaluation, and then, can improve the accuracy and efficiency of personnel allocation.

[0064] In an exemplary embodiment, obtaining the object semantic vector of the object to be assigned according to the object basic information in step 102 may include:

[0065] According to the object basic information of the object to be assigned, the object semantic vector corresponding to the object to be assigned is obtained; the object basic information includes multiple feature key-value pairs; each feature key-value pair includes a feature name and a feature value; there is a corresponding relationship between the feature name and the feature value; the object basic information is input into a pre-trained semantic representation model to obtain the object semantic vector of the object to be assigned; wherein the semantic representation model uses a pre-trained multi-layer perceptron network to determine and output the object semantic vector of the object to be assigned according to the feature value vectors of multiple feature key-value pairs contained in the object basic information.

[0066] Among them, a semantic representation model for obtaining a customer's customer semantic vector can be pre-trained, and the semantic representation model can be used to convert the object basic information of the object to be allocated into the object semantic vector of the object to be allocated. Specifically, the object basic information of the object to be allocated can be input into the pre-trained semantic representation model, and the semantic identification model can perform feature extraction on the object basic information to obtain the object semantic vector of the object to be allocated. The semantic representation model can be a neural network model, for example, a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM) and other models.

[0067] In the method of this embodiment, the semantic representation model can be used to convert the basic object information of the object to be assigned into the object semantic vector of the object to be assigned, thereby improving the accuracy of feature extraction and semantic conversion.

[0068] In an exemplary embodiment, as shown in FIG3 , step 104 may include steps 302 to 304. Among them:

[0069] Step 302: Obtain the similarity between the object semantic vector and the historical semantic vector of each historical object in the plurality of historical objects.

[0070] Step 304 : determine the historical objects corresponding to the similarities greater than the preset similarity threshold as matching objects of the object to be assigned, and determine the historical object data of the historical objects as matching object data of the object to be assigned.

[0071] Among them, the pre-built object semantic vector library can be a pre-built customer semantic vector library. The customer semantic vector library can be built based on the historical customer data of multiple historical customers. The historical customer data of each historical customer in the multiple historical customers can include the customer semantic vector of the corresponding historical customer, the service personnel (for example, sales personnel) corresponding to the historical customer, and the corresponding order label. The customer semantic vector corresponding to the historical customer can be the customer feature vector of the historical customer; the historical customer is a customer who has been assigned a service personnel; the order label is used to indicate whether the service personnel and the historical customer have reached a transaction and completed the order. The historical customer data can include customer feature information corresponding to the historical customer, and the historical customer data can be obtained from the insurance policy database or user database of each business system. In this step, the object semantic vector library includes the historical semantic vectors of multiple historical customers, and the similarity between the customer semantic vector of the customer to be assigned and the historical semantic vector of each historical customer in the multiple historical customers can be obtained. Then, according to the similarity, multiple matching objects that match the object to be assigned can be determined, and the historical customer data of each matching object in the multiple matching objects is used as the matching object data of the customer to be assigned. In a possible implementation, the historical customer whose similarity is greater than a preset similarity threshold can be used as a matching customer of the customer to be assigned, i.e., a matching object. The similarity between the customer semantic vector and the historical semantic vector of each of the multiple historical customers can be measured by the distance between the customer semantic vector and the historical semantic vector of each of the multiple historical customers. The distance between the customer semantic vector and the historical semantic vector of each of the multiple historical customers can be obtained by using a variety of distance calculation methods, such as Euclidean distance, cosine distance, Hamming distance, and Manhattan distance.

[0072] In the method of this embodiment, the similarity between the customer semantic vector and the historical semantic vector of each of the multiple historical customers can be measured by the distance between the customer semantic vector and the historical semantic vector of each of the multiple historical customers. Then, based on the similarity, multiple matching objects that match the object to be assigned can be determined, thereby improving the accuracy of matching object screening.

[0073] In an exemplary embodiment, as shown in FIG4 , step 106 may include steps 402 to 404. Among them:

[0074] Step 402: Determine the assigned personnel corresponding to each matching object according to the plurality of matching objects and the matching object data of each matching object.

[0075] Step 404: determine the assigned personnel as candidate matching personnel corresponding to the object to be assigned, and obtain multiple candidate matching personnel.

[0076] The matching object data includes the customer feature information of the corresponding matching object, the corresponding service personnel, and the corresponding order labels, and the multiple service personnel corresponding to the multiple matching objects, that is, the assigned personnel, can be determined as the multiple candidate matching personnel corresponding to the object to be assigned. In a possible implementation, the score of each service personnel can also be obtained according to the order label corresponding to the service personnel, and then, according to the score, the service personnel whose scores are greater than the preset score threshold among the multiple service personnel corresponding to the multiple matching objects can be determined as the multiple candidate matching personnel corresponding to the object to be assigned.

[0077] In the method of this embodiment, the allocation personnel of similar customers of the customer to be allocated can be used as multiple candidate matching personnel corresponding to the object to be allocated, which can improve the accuracy of subsequent target matching personnel screening.

[0078] In an exemplary embodiment, as shown in FIG5 , before step 108, steps 502 to 506 may also be included. Among them:

[0079] Step 502: Determine at least one evaluation index for each candidate matching person.

[0080] Step 504, obtaining basic information of each candidate matching person.

[0081] Step 506: Determine evaluation basis data for each evaluation indicator based on the basic personnel information and at least one evaluation indicator.

[0082] Among them, at least one evaluation index can be pre-set for the candidate matching personnel, and the at least one evaluation index can include evaluation indexes of multiple dimensions, such as basic characteristics, professional ability, communication ability and work attitude of the service personnel. The basic personnel information can include characteristic information of multiple dimensions of the corresponding candidate matching personnel, wherein the basic personnel information of each candidate matching personnel can include parameter information of multiple personnel parameters, for example, the parameters can be education, age, graduation school and years of work, etc.; according to the correlation between each personnel parameter and each evaluation indicator in the at least one evaluation index, the parameter information of the multiple personnel parameters can be divided, and then, the parameter information of the personnel parameters whose correlation with each evaluation indicator is greater than the correlation threshold can be determined as the evaluation basis data of the corresponding evaluation indicator. The correlation is used to characterize the degree of association between the personnel parameters and the evaluation indicators. For example, the evaluation basis data of the basic characteristics of the evaluation indicator can be the basic characteristic information of the service personnel, the evaluation basis data of the professional ability of the evaluation indicator can be the professional ability characteristic information, the evaluation basis data of the communication ability of the evaluation indicator can be the communication ability characteristic information, and the evaluation basis data of the work attitude of the evaluation indicator can be the work attitude characteristic information, etc. Among them, the parameters of basic characteristics include: sales personnel's education level, age, years of work in the insurance industry, years of work in the company, grade of graduation school, whether relevant professional certificates are obtained, gender, etc.; the parameters of professional ability include: control of various insurance products, completion of training courses, job level, performance in the past two years, understanding of market dynamics, understanding of competitors, etc.; the parameters of communication ability include: language proficiency level, communication and expression ability rating, negotiation skills ability rating, customer understanding ability rating, customer persuasion ability rating, etc.; the parameters of work attitude include: self-motivation rating, continuous learning ability rating, career planning ability rating, work enthusiasm rating, etc.

[0083] In an exemplary embodiment, step 108 may include:

[0084] Utilizing the personnel evaluation model, based on at least one of the evaluation indicators of each candidate matching person and the evaluation basis data of each evaluation indicator, obtain the single indicator evaluation result of each candidate matching person under each evaluation indicator; based on the single indicator evaluation result corresponding to each evaluation indicator in at least one of the evaluation indicators, obtain the personnel evaluation result of each candidate matching person.

[0085] Specifically, the object basic information of the object to be assigned, at least one evaluation index of each candidate matching person among the multiple candidate matching persons, and the evaluation basis data of each evaluation index can be input into the personnel evaluation model, and the personnel evaluation model can obtain the single index evaluation results of each candidate matching person under each evaluation index, and then, the personnel evaluation results of each candidate matching person can be obtained according to the single index evaluation results of each candidate matching person under each evaluation index. In a possible implementation, the single index evaluation result and the personnel evaluation result can be in the form of evaluation scores, the single index evaluation result can be a first evaluation score, and the personnel evaluation result can be a second evaluation score. The indicator weight of each evaluation indicator can be determined according to the importance of each evaluation indicator to the candidate matching person evaluation, and then, the first evaluation score corresponding to the at least one evaluation indicator, that is, the single index evaluation result, can be weighted and summed according to the indicator weight to obtain the second evaluation score of each candidate matching person, that is, the personnel evaluation result.

[0086] In the method of this embodiment, a large model, namely a personnel evaluation model, can be introduced to realize the personnel allocation of the objects to be assigned, and multiple evaluation indicators for the candidate matching personnel can be determined as prompt words of the large model. Then, the candidate matching personnel can be evaluated in multiple dimensions using the large model, and the target matching personnel of the objects to be assigned can be determined based on the evaluation results, which can improve the accuracy of personnel evaluation, and further, can improve the accuracy and efficiency of personnel allocation.

[0087] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0088] Based on the same inventive concept, the embodiment of the present application also provides a personnel allocation device for implementing the personnel allocation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the personnel allocation device provided below can refer to the limitations of the personnel allocation method above, and will not be repeated here.

[0089] In one embodiment, as shown in FIG6 , a personnel allocation device is provided, including: an acquisition module 602, a matching module 604, a screening module 606, an evaluation module 608 and an allocation module 610, wherein:

[0090] An acquisition module 602 is used to acquire basic object information of an object to be allocated, and acquire an object semantic vector of the object to be allocated according to the basic object information;

[0091] A matching module 604 is used to determine, according to the object semantic vector, matching object data of a plurality of matching objects that match the object to be assigned in a pre-built object semantic vector library;

[0092] A screening module 606, configured to determine a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects;

[0093] An evaluation module 608 is used to obtain a personnel evaluation result of each candidate matching person according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator by using a personnel evaluation model;

[0094] The allocation module 610 is used to determine a target matching person for the object to be allocated from among the plurality of candidate matching persons according to the personnel evaluation result, and allocate the target matching person to the object to be allocated.

[0095] In one embodiment, the acquisition module 602 is also used to: acquire the object semantic vector corresponding to the object to be assigned according to the object basic information of the object to be assigned; the object basic information includes multiple feature key-value pairs; each feature key-value pair includes a feature name and a feature value; there is a corresponding relationship between the feature name and the feature value; input the object basic information into a pre-trained semantic representation model to obtain the object semantic vector of the object to be assigned; wherein the semantic representation model uses a pre-trained multi-layer perceptron network to determine and output the object semantic vector of the object to be assigned according to the feature value vectors of the multiple feature key-value pairs contained in the object basic information.

[0096] In one embodiment, the object semantic vector library includes historical semantic vectors of a plurality of historical objects;

[0097] The matching module 604 is also used to: obtain the similarity between the object semantic vector and the historical semantic vector of each of the multiple historical objects; determine the historical object corresponding to the similarity greater than a preset similarity threshold as the matching object of the object to be assigned, and determine the historical object data of the historical object as the matching object data of the object to be assigned.

[0098] In one embodiment, the screening module 606 is further used to: determine the assigned personnel corresponding to each of the matching objects based on the multiple matching objects and the matching object data of each of the matching objects; determine the assigned personnel as the candidate matching personnel corresponding to the object to be assigned, and obtain multiple candidate matching personnel.

[0099] In one embodiment, the evaluation module 608 is further used to: determine at least one evaluation indicator for each candidate matching person; obtain basic personnel information of each candidate matching person; and determine the evaluation basis data for each evaluation indicator based on the basic personnel information and at least one evaluation indicator.

[0100] In one embodiment, the evaluation module 608 is also used to: utilize the personnel evaluation model to obtain the single indicator evaluation result of each candidate matching person under each evaluation indicator according to at least one evaluation indicator of each candidate matching person and the evaluation basis data of each evaluation indicator; and obtain the personnel evaluation result of each candidate matching person according to the single indicator evaluation result corresponding to each evaluation indicator in at least one evaluation indicator.

[0101] Each module in the above-mentioned personnel allocation device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0102] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7 . The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store personnel allocation related data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a personnel allocation method is implemented.

[0103] Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0104] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0106] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0109] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0110] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A personnel allocation method, characterized in that: The method comprises: Obtaining object basic information of the object to be assigned, and obtaining an object semantic vector of the object to be assigned according to the object basic information; According to the object semantic vector, determining matching object data of a plurality of matching objects matching the object to be assigned in a pre-built object semantic vector library; Determine a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects; Using the personnel evaluation model, according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator, obtaining a personnel evaluation result of each candidate matching person; According to the personnel evaluation result, a target matching person for the object to be assigned is determined from among the plurality of candidate matching persons, and the target matching person is assigned to the object to be assigned.

2. The method according to claim 1, characterized in that The acquiring the object semantic vector of the object to be allocated according to the object basic information includes: According to the object basic information of the object to be assigned, an object semantic vector corresponding to the object to be assigned is obtained; the object basic information includes a plurality of feature key-value pairs; each of the feature key-value pairs includes a feature name and a feature value; and there is a corresponding relationship between the feature name and the feature value; Inputting the object basic information into a pre-trained semantic representation model to obtain the object semantic vector of the object to be assigned; The semantic representation model uses a pre-trained multi-layer perceptron network to determine and output the object semantic vector of the object to be assigned according to the feature value vectors of the plurality of feature key-value pairs contained in the object basic information.

3. The method according to claim 1, characterized in that The object semantic vector library includes historical semantic vectors of multiple historical objects; The step of determining, in a pre-built object semantic vector library according to the object semantic vector, matching object data of a plurality of matching objects that match the object to be assigned comprises: Obtaining a similarity between the object semantic vector and the historical semantic vector of each of the historical objects; The historical object corresponding to the similarity greater than a preset similarity threshold is determined as the matching object of the object to be assigned, and the historical object data of the historical object is determined as the matching object data of the object to be assigned.

4. The method according to claim 1, characterized in that: The step of determining a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each matching object includes: Determine, according to the plurality of matching objects and the matching object data of each matching object, an assigned person corresponding to each matching object; The assigned personnel are determined as candidate matching personnel corresponding to the object to be assigned, and a plurality of candidate matching personnel are obtained.

5. The method according to claim 1, characterized in that Before obtaining the personnel evaluation result of each candidate matching person according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator by using the personnel evaluation model, the method further includes: Determining at least one evaluation indicator for each candidate matching person; Obtaining basic information of each candidate matching person; The evaluation basis data of each evaluation indicator is determined according to the basic personnel information and at least one evaluation indicator.

6. The method according to claim 5, characterized in that The utilizing of the personnel evaluation model to obtain the personnel evaluation result of each of the candidate matching personnel according to at least one evaluation indicator of each of the candidate matching personnel and evaluation basis data of each of the evaluation indicators comprises: Utilizing the personnel evaluation model, according to at least one evaluation indicator of each candidate matching person and the evaluation basis data of each evaluation indicator, obtaining a single indicator evaluation result of each candidate matching person under each evaluation indicator; The personnel evaluation result of each of the candidate matching personnel is obtained according to the single indicator evaluation result corresponding to each of the evaluation indicators in at least one of the evaluation indicators.

7. A personnel allocation device, characterized in that: The device comprises: An acquisition module, used to acquire object basic information of an object to be allocated, and acquire an object semantic vector of the object to be allocated according to the object basic information; A matching module, configured to determine, in a pre-built object semantic vector library, matching object data of a plurality of matching objects that match the object to be assigned according to the object semantic vector; A screening module, used for determining a plurality of candidate matching persons corresponding to the object to be assigned according to the plurality of matching objects and the matching object data of each of the matching objects; An evaluation module, used to obtain a personnel evaluation result of each candidate matching person according to at least one evaluation indicator of each candidate matching person and evaluation basis data of each evaluation indicator by using a personnel evaluation model; An allocation module is used to determine a target matching person for the object to be allocated from among a plurality of candidate matching persons according to the personnel evaluation result, and allocate the target matching person to the object to be allocated.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images