Task matching method and device, computer equipment and readable storage medium

Abstract

The invention discloses a task matching method and device, computer equipment and a readable storage medium, and the method comprises the steps: firstly obtaining a fixed attribute of a packet sender and fixed attributes corresponding to a plurality of packet receivers, and determining a target packet receiver based on the matching result of the fixed attributes; and then distributing the outsourcing task corresponding to the packet sender to the determined target packet receiver. According to the method, the matching between the task and the packet receiver can be accurately realized, so that the task completion efficiency and quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of task scheduling, and in particular, to a task matching method, device, computer device, and readable storage medium. Background Art

[0002] In the traditional task allocation process, it usually relies on manual selection or simple rules for matching, such as following the first-come, first-served principle, or selecting according to the historical evaluation of the packet receiving party, etc. However, these methods cannot take into account the specific requirements of the task and the specific capabilities of the packet receiving party, which may lead to the inability to guarantee the efficiency and quality of task allocation. Therefore, it has become an urgent need to develop a method that can accurately match tasks with packet receiving parties. Summary of the Invention

[0003] The purpose of the present invention is to provide a task matching method, device, computer device, and readable storage medium.

[0004] In a first aspect, an embodiment of the present invention provides a task matching method, including:

[0005] Obtain the first fixed attribute of the task issuer, and the second fixed attributes corresponding to multiple packet receiving parties respectively;

[0006] Based on the matching result of the first fixed attribute and multiple second fixed attributes, determine the target packet receiving party corresponding to the target fixed attribute;

[0007] Allocate the outsourcing task corresponding to the task issuer to the target packet receiving party.

[0008] In a possible implementation manner, the obtaining the first fixed attribute of the task issuer, and the second fixed attributes corresponding to multiple packet receiving parties respectively, includes:

[0009] Determine the first fixed attribute according to the outsourcing task attribute provided by the task issuer;

[0010] Determine the second fixed attribute of each packet receiving party according to the personal portrait attribute configured for each packet receiving party.

[0011] In a possible implementation manner, the first fixed attribute includes a first professional field, a first category, and a first task scope, and the second fixed attribute includes a second professional field, a second category, and a second task scope; the determining the target packet receiving party corresponding to the target fixed attribute based on the matching result of the first fixed attribute and multiple second fixed attributes, includes:

[0012] Match the first professional field with multiple second professional fields. If the match is successful, assign the first matching value to the packet receiving party corresponding to the successfully matched second professional field;

[0013] Match the first category with multiple second categories. If the match is successful, assign a second matching value corresponding to the successful second category to the packet receiving party.

[0014] Match the first task scope with multiple second task scopes. If the match is successful, assign a third matching value corresponding to the successful second task scope to the packet receiving party. The first matching value is greater than the second matching value, and the second matching value is greater than the third matching value.

[0015] Calculate the sum of the first matching value, the second matching value, and the third matching value corresponding to each packet receiving party, and use the packet receiving party with the highest sum as the target packet receiving party.

[0016] In a possible implementation manner, the method further includes:

[0017] Obtain multiple historical first fixed attributes of the contract awarding party, and multiple task scoring attributes for each historical first fixed attribute.

[0018] Based on the first relevance between the multiple historical first fixed attributes and the multiple task scoring attributes, assign corresponding weights to each task scoring attribute.

[0019] Obtain multiple task processing characteristics of the packet receiving party, and determine the second relevance between the multiple task processing characteristics and the multiple task scoring attributes.

[0020] According to the second relevance and the weights assigned to each task scoring attribute, perform weighted calculation on the multiple task processing characteristics to obtain a fourth matching value.

[0021] Use the packet receiving party with the largest fourth matching value as the target packet receiving party.

[0022] In a possible implementation manner, the multiple historical first fixed attributes include professional category, gender, age, and customer classification, the multiple task scoring attributes include timeliness, professionalism, and practicality, and the task processing characteristics include processing time, the amount of professional vocabulary used, and text richness. Based on the first relevance between the multiple historical first fixed attributes and the multiple task scoring attributes, assigning corresponding weights to each task scoring attribute includes:

[0023] Based on the first relevance between the professional category, gender, age, customer classification and the timeliness, professionalism, and practicality, assign corresponding weights to the timeliness, professionalism, and practicality.

[0024] Obtaining multiple task processing characteristics of the packet receiving party, and determining a second relevance between the multiple task processing characteristics and the multiple task scoring attributes, includes:

[0025] Obtaining the processing time, the usage amount of professional vocabulary, and the text richness, and determining a second relevance between the processing time, the usage amount of professional vocabulary, and the text richness and the timeliness, professionalism, and practicality.

[0026] In a possible implementation manner, the method further includes:

[0027] Using the determined associated data of the target packet receiving party as reference data for determining the first relevance and the second relevance.

[0028] In a possible implementation manner, the method further includes:

[0029] Performing overfitting detection on the target packet receiving party at a preset period.

[0030] In a second aspect, an embodiment of the present invention provides a task matching device, including:

[0031] An obtaining module, which obtains a first fixed attribute of the task sending party and respective second fixed attributes of multiple task receiving parties;

[0032] A matching module, configured to determine a target task receiving party corresponding to a target fixed attribute based on a matching result of the first fixed attribute and the multiple second fixed attributes; and allocate the outsourcing task corresponding to the task sending party to the target task receiving party.

[0033] In a third aspect, an embodiment of the present invention provides a computer device, where the computer device includes a processor and a non-volatile memory storing computer instructions, and when the computer instructions are executed by the processor, the computer device executes the task matching method described in the first aspect.

[0034] In a fourth aspect, an embodiment of the invention provides a readable storage medium, where the readable storage medium includes a computer program, and when the computer program runs, it controls a computer device where the readable storage medium is located to execute the task matching method described in the first aspect.

[0035] Compared with the prior art, the beneficial effects provided by the present invention include: By adopting a task matching method, device, computer device, and readable storage medium disclosed in the present invention, by obtaining the fixed attributes of the task sending party and the respective fixed attributes of multiple task receiving parties, and determining the target task receiving party based on the matching result of these fixed attributes. Then, the outsourcing task corresponding to the task sending party is allocated to the determined target task receiving party. This method can accurately implement the matching between tasks and task receiving parties, thereby improving the efficiency and quality of task completion. Brief Description of the Drawings

[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 It is a schematic structural diagram of the steps of the task matching method provided by the embodiment of the present invention;

[0038] Figure 2 It is a schematic block diagram of the structure of the task matching device provided by the embodiment of the present invention;

[0039] Figure 3 It is a schematic block diagram of the structure of the computer device provided by the embodiment of the present invention. Detailed Embodiments

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0041] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0042] It should be noted that: similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0043] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "upper", "lower", "inner", "outer", "left", "right", etc. are based on the orientation or positional relationships shown in the drawings, or the orientation or positional relationships in which the product of this application is usually placed during use, or the orientation or positional relationships commonly understood by those skilled in the art. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention.

[0044] In addition, terms such as "first", "second", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0045] In the description of the present invention, it should also be noted that unless otherwise clearly specified and defined, terms such as "set" and "connect" should be understood in a broad sense. For example, "connect" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0046] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings.

[0047] In order to solve the technical problems in the foregoing background art, Figure 1 The following is a schematic flowchart of the task matching method provided by the embodiments of the present disclosure, and the task matching method will be introduced in detail below.

[0048] Step S201: Obtain the first fixed attribute of the contract awarding party and the second fixed attributes corresponding to multiple contract receiving parties respectively;

[0049] Step S202: Determine the target contract receiving party corresponding to the target fixed attribute based on the matching result of the first fixed attribute and the multiple second fixed attributes;

[0050] Step S203: Allocate the outsourcing task corresponding to the contract awarding party to the target contract receiving party.

[0051] In an embodiment of the present invention, exemplarily, Xiaoming, as the contract awarding party, registered and posted a software development task on an online platform. This task requires experienced developers and involves a technology stack including Java, Python, and database management. The platform obtains Xiaoming's first fixed attribute, that is, his description and requirements for the required task. For example, "I need a developer with many years of programming experience to complete this software development task, proficient in Java, Python, and database management." The platform obtains the second fixed attributes of multiple registered contract receiving parties, that is, their respective corresponding skills and experiences. For example, contract receiving party A noted in their profile "I am a programmer with 5 years of Java development experience", contract receiving party B wrote in their profile "I am good at Python development and have 2 years of relevant project experience", while contract receiving party C described as "I am a database management expert, familiar with mainstream database systems, and have 3 years of actual work experience". By analyzing the first fixed attribute of the contract awarding party and the second fixed attributes of multiple contract receiving parties, the platform can determine the target contract receiving party most suitable for completing the task based on a matching algorithm. In this example, the platform may, according to Xiaoming's requirements, assign the task to contract receiving party A because he has Java development experience and his skills are relatively well-matched with the task requirements. After task matching, the platform automatically assigns Xiaoming's software development task to contract receiving party A. Contract receiving party A will receive a notice or see the task on the platform and start negotiating detailed requirements with Xiaoming and carry out the development work. Designed in this way, through this task matching method, the platform can more accurately assign the tasks of the contract awarding party to the appropriate contract receiving party, improve the efficiency and quality of task completion, and at the same time provide a convenient communication and collaboration platform for the contract awarding party and the contract receiving party to cooperate better.

[0052] In a possible implementation manner, the foregoing step S201 may be executed and implemented in the following manner.

[0053] (1) Determine the first fixed attribute according to the outsourcing task attributes provided by the contract awarding party;

[0054] (2) Determine the second fixed attribute of each contract receiving party according to the personal portrait attributes configured by each contract receiving party.

[0055] In an embodiment of the present invention, assume that Xiaohong is the client who posts a graphic design task on an online platform. She needs to find a designer who is proficient in Photoshop and Illustrator software and has creative thinking to complete this task. The online platform determines Xiaohong's first fixed attributes based on the task attributes provided by Xiaohong, such as requirement descriptions, skill requirements, etc. In this example, the first fixed attribute can be "I need a designer who is proficient in Photoshop and Illustrator software and has unique insights into creative design." When registering, the platform requires the contractor to fill in personal information and skill tags, and the contractors will configure their personal portrait attributes. For example, Contractor X writes in the personal information "I am an experienced graphic designer, proficient in Photoshop and Illustrator software, and have participated in multiple creative projects", while Contractor Y describes as "I am a UI designer, good at using various design tools for creative design, and have in-depth research on user experience". Designed in this way, based on the previous task matching method and combined with this technical solution, the platform will match according to Xiaohong's first fixed attributes and the second fixed attributes of the contractors to determine the target contractor most suitable for completing the task. In this example, the task may be assigned to Contractor X because he has the required skills and experience and is more in line with Xiaohong's task requirements. Through this method, the platform can more precisely match suitable contractors to complete the task according to the task attributes provided by the client and the personal portrait attributes configured by the contractors. This can meet the needs of the client, improve the accuracy and efficiency of task assignment, and at the same time enable the contractors to receive outsourcing tasks more in line with their skills and interests.

[0056] In a possible implementation manner, the first fixed attribute includes a first professional field, a first category, and a first task scope, and the second fixed attribute includes a second professional field, a second category, and a second task scope; the foregoing step S202 may be executed in the following manner.

[0057] (1) Match the first professional field with multiple second professional fields. If the match is successful, assign the first matching value to the contractor corresponding to the successfully matched second professional field;

[0058] (2) Match the first category with multiple second categories. If the match is successful, assign the second matching value to the contractor corresponding to the successfully matched second category;

[0059] (3) Match the first task scope with multiple second task scopes. If the match is successful, assign the third matching value to the contractor corresponding to the successfully matched second task scope, where the first matching value is greater than the second matching value, and the second matching value is greater than the third matching value;

[0060] (4) Calculate the sum of the first matching value, the second matching value, and the third matching value corresponding to each of the said packet receiving parties, and use the packet receiving party with the highest sum as the said target packet receiving party.

[0061] In an embodiment of the present invention, by way of example, it is assumed that the contract awarding party issues a software development task with the following first fixed attributes: First professional field: mobile application development; First category: iOS development; First task scope: develop a social media application program. There are three packet receiving parties A, B, and C on this platform, and their second fixed attributes are as follows: Packet receiving party A: Second professional field: mobile application development; Second category: Android development; Second task scope: develop an e-commerce application program; Packet receiving party B: Second professional field: iOS development; Second category: game development; Second task scope: develop a casual game application program; Packet receiving party C: Second professional field: mobile application development; Second category: iOS development; Second task scope: develop an educational application program. Match the first professional field with multiple second professional fields: The first professional field of the contract awarding party is mobile application development, and the second professional fields of packet receiving parties A and C are also mobile application development. Therefore, give the first matching value to packet receiving parties A and C. Match the first category with multiple second categories: The first category of the contract awarding party is iOS development, and the second categories of packet receiving parties B and C are also iOS development. Therefore, give the second matching value to packet receiving parties B and C. Match the first task scope with multiple second task scopes: The first task scope of the contract awarding party is to develop a social media application program, and the second task scopes of packet receiving parties B and C are game development and educational application program respectively, which do not match the first task scope of the contract awarding party. Designed in this way, combined with the set corresponding matching values, a relatively matching target packet receiving party can be determined.

[0062] In a possible implementation manner, the embodiment of the present invention also provides the following method.

[0063] (1) Obtain multiple historical first fixed attributes of the said contract awarding party, and multiple task scoring attributes for each of the said historical first fixed attributes;

[0064] (2) Based on the first correlation between the multiple historical first fixed attributes and the multiple task scoring attributes, assign corresponding weights to each of the said task scoring attributes;

[0065] (3) Obtain multiple task processing characteristics of the said packet receiving party, and determine the second correlation between the multiple task processing characteristics and the multiple task scoring attributes;

[0066] (4) Assign corresponding weights according to the second relevance and each of the task scoring attributes, and perform weighted calculation on the multiple task processing characteristics to obtain a fourth matching value;

[0067] (5) Use the recipient with the largest fourth matching value as the target recipient.

[0068] In an embodiment of the present invention, assume that the sender publishes a software development task on an online platform, with the following historical first fixed attributes and task scoring attributes:

[0069] Historical first fixed attribute 1: First professional field: Artificial intelligence; First category: Machine learning algorithm; First task scope: Image recognition.

[0070] Task scoring attribute 1: Task difficulty score: 8 / 10; Delivery quality score: 9 / 10; Communication ability score: 7 / 10.

[0071] Historical first fixed attribute 2: First professional field: Mobile application development; First category: Android development; First task scope: Develop a social media application.

[0072] Task scoring attribute 2: Task difficulty score: 6 / 10; Delivery quality score: 8 / 10; Communication ability score: 9 / 10.

[0073] Now there are three recipients A, B, and C on the platform, and their task processing characteristics are as follows:

[0074] Recipient A: Task processing speed: Fast; Problem-solving ability: High; Teamwork ability: Average.

[0075] Recipient B: Task processing speed: Average; Problem-solving ability: Medium; Teamwork ability: High.

[0076] Recipient C: Task processing speed: Fast; Problem-solving ability: High; Teamwork ability: High.

[0077] Perform matching and calculation of matching values according to the following steps:

[0078] Obtain the historical first fixed attribute and task scoring attribute of the contract awarding party, and assign corresponding weights to each task scoring attribute: For the historical first fixed attribute 1, assign weights according to the relevance of multiple task scoring attributes 1. For the historical first fixed attribute 2, assign weights according to the relevance of multiple task scoring attributes 2. Obtain the task processing characteristics of the contract receiving party, and determine the relevance between the task processing characteristics and the task scoring attributes. According to the second relevance and the weights of each task scoring attribute, perform a weighted calculation on the task processing characteristics to obtain the fourth matching value. Take the contract receiving party with the largest fourth matching value as the target contract receiving party. In this example, the specific weights and relevance need to be determined according to the specific situation. We can assume the following example weights and relevance:

[0079] Weights of task scoring attributes for the historical first fixed attribute 1: Weight of task difficulty score: 0.4; Weight of delivery quality score: 0.3; Weight of communication ability score: 0.3.

[0080] Weights of task scoring attributes for the historical first fixed attribute 2: Weight of task difficulty score: 0.2; Weight of delivery quality score: 0.4; Weight of communication ability score: 0.4.

[0081] Relevance between task processing characteristics and task scoring attributes: Relevance between task processing speed and task difficulty score: 0.6; Relevance between problem-solving ability and delivery quality score: 0.8; Relevance between teamwork ability and communication ability score: 0.7.

[0082] According to the above weights and relevance, the fourth matching value of each contract receiving party can be calculated:

[0083] Contract receiving party A:

[0084] Fourth matching value = (task processing speed * 0.6 + problem-solving ability * 0.8 + teamwork ability * 0.7) = (fast * 0.6 + high * 0.8 + average * 0.7).

[0085] Contract receiving party B:

[0086] Fourth matching value = (task processing speed * 0.6 + problem-solving ability * 0.8 + teamwork ability * 0.7) = (average * 0.6 + medium * 0.8 + high * 0.7).

[0087] Contract receiving party C:

[0088] Fourth matching value = (task processing speed * 0.6 + problem-solving ability * 0.8 + teamwork ability * 0.7) = (fast * 0.6 + high * 0.8 + high * 0.7).

[0089] According to the calculated fourth matching value, determine the contract receiving party with the maximum value as the target contract receiving party.

[0090] Please note that this is just an example. In actual situations, the weights need to be determined and matching calculations need to be performed based on specific requirements and relevance. At the same time, the accuracy and feasibility of the method also need to be ensured to meet the needs of the contract awarding party.

[0091] In the embodiments of the present invention, the multiple historical first fixed attributes include professional categories, gender, age, and customer classification. The multiple task scoring attributes include timeliness, professionalism, and practicality. The task processing characteristics include processing time, the amount of professional vocabulary used, and text richness. The step of assigning corresponding weights to each of the task scoring attributes based on the first relevance between the multiple historical first fixed attributes and the multiple task scoring attributes can be implemented through the following examples.

[0092] (1) Based on the first relevance between the professional categories, gender, age, customer classification and the timeliness, professionalism, and practicality, assign corresponding weights to the timeliness, professionalism, and practicality;

[0093] The step of obtaining the multiple task processing characteristics of the contract receiving party and determining the second relevance between the multiple task processing characteristics and the multiple task scoring attributes can be implemented through the following examples.

[0094] Obtain the processing time, the amount of professional vocabulary used, and text richness, and determine the second relevance between the processing time, the amount of professional vocabulary used, and text richness and the timeliness, professionalism, and practicality.

[0095] In the embodiments of the present invention, by way of example, assume that the contract awarding party publishes a translation task on an online platform, with the following historical first fixed attributes and task scoring attributes:

[0096] Historical first fixed attribute 1: Professional category: Linguistics; Gender: Female; Age: 30 years old; Customer classification: Enterprise customer.

[0097] Task scoring attribute 1: Timeliness score: 9 / 10; Professionalism score: 8 / 10; Practicality score: 7 / 10.

[0098] Historical first fixed attribute 2: Professional category: Literature; Gender: Male; Age: 35 years old; Customer classification: Individual customer.

[0099] Task scoring attribute 2: Timeliness score: 7 / 10; Professionalism score: 9 / 10; Practicality score: 8 / 10.

[0100] Now there are three contract receiving parties A, B, and C on the platform, and their task processing characteristics are as follows:

[0101] Packet receiving party A: Processing time: fast; Quantity of specialized vocabulary used: high; Text richness: average.

[0102] Packet receiving party B: Processing time: medium; Quantity of specialized vocabulary used: medium; Text richness: high.

[0103] Packet receiving party C: Processing time: slow; Quantity of specialized vocabulary used: low; Text richness: high.

[0104] According to the method requirements, perform matching and calculate the matching value according to the following steps:

[0105] Obtain multiple historical first fixed attributes and task scoring attributes of the contract awarding party, and assign corresponding weights to each task scoring attribute:

[0106] For historical first fixed attribute 1, assign weights according to the relevance of multiple task scoring attributes 1.

[0107] For historical first fixed attribute 2, assign weights according to the relevance of multiple task scoring attributes 2.

[0108] Obtain multiple task processing characteristics of the packet receiving party, and determine the relevance between the task processing characteristics and the task scoring attributes.

[0109] Based on the relevance of professional categories, gender, age, customer classification, timeliness, professionalism, and practicality, assign corresponding weights to timeliness, professionalism, and practicality.

[0110] Based on the relevance of processing time, quantity of specialized vocabulary used, and text richness to timeliness, professionalism, and practicality, assign corresponding weights to processing time, quantity of specialized vocabulary used, and text richness.

[0111] Calculate the fourth matching value of each packet receiving party:

[0112] Packet receiving party A: Fourth matching value = (processing time * weight + quantity of specialized vocabulary used * weight + text richness * weight).

[0113] Packet receiving party B: Fourth matching value = (processing time * weight + quantity of specialized vocabulary used * weight + text richness * weight).

[0114] Packet receiving party C: Fourth matching value = (processing time * weight + quantity of specialized vocabulary used * weight + text richness * weight).

[0115] According to the calculated fourth matching value, determine the packet receiving party with the maximum value as the target packet receiving party.

[0116] Please note that this is just an example. In actual situations, the weights need to be determined and matching calculations need to be performed based on specific requirements and relevance. At the same time, it is also necessary to ensure the accuracy and feasibility of the method to meet the needs of the contract awarding party.

[0117] In an embodiment of the present invention, the following solutions are also provided.

[0118] Use the associated data for determining the target packet receiving party as the reference data for determining the first relevance and the second relevance.

[0119] In an embodiment of the present invention, by way of example, assume that there are multiple similar software testing tasks completed on the platform and these tasks have been scored and recorded. We can use this historical data to determine the degree of association between different historical first fixed attributes (such as professional categories, genders, ages, customer classifications) and task scoring attributes (such as timeliness, professionalism, practicality). By analyzing the distribution and scoring of different attributes in the historical data, we can calculate correlation coefficients or other statistical indicators to measure the relevance between the two.

[0120] In addition, user feedback and evaluations can also be considered, such as evaluations of the work quality and communication ability of the packet receiving party. These feedbacks can be direct user comments, scores, or other forms of feedback data. By analyzing user feedback and evaluations, we can understand the performance of the packet receiving party under different task scoring attributes and user satisfaction, thereby further determining the weights of the relevance.

[0121] It should be noted that the embodiment of the present invention also provides the following implementation manners for the noise data in the scoring process.

[0122] Suppose there is an online platform connecting task awarding parties and packet receiving parties. The awarding parties can release task requirements, and the packet receiving parties can select suitable tasks to receive according to their own capabilities and interests. The platform assigns tasks to the most suitable packet receiving parties through a matching algorithm.

[0123] During the matching process, we need to consider the historical first fixed attributes of the awarding parties and task scoring attributes, as well as the task processing characteristics of the packet receiving parties. However, the historical scoring data (i.e., the data related to scoring) may be noisy, that is, the scoring results may be inaccurate or have large subjective biases.

[0124] To eliminate this noisy data, we can use a regression function for data cleaning. The following are two possible effective methods:

[0125] 1. Mean deviation method: The mean deviation method is a commonly used data cleaning method. It corrects the noisy data by calculating the mean deviation between the historical scoring data and the true score. The specific steps are as follows:

[0126] Collect the tasks released by the contract awarding party and record the true scores of each task (e.g., objective evaluations obtained through other means).

[0127] For the historical first fixed attribute and task score attribute of each contract awarding party, calculate their corresponding average deviation of task scores.

[0128] Use a regression function to clean the historical score data and correct the noise data by subtracting the average deviation of task scores.

[0129] 2. Standard deviation test: The standard deviation test can help us identify outliers in the historical score data. The specific steps are as follows:

[0130] For the historical first fixed attribute and task score attribute of each contract awarding party, calculate their corresponding standard deviation of task scores.

[0131] Identify the historical score data with a standard deviation greater than a certain threshold (e.g., 3 times the standard deviation), and these data may be noise data.

[0132] Use a regression function to clean the identified abnormal score data and purify the score data by deleting or replacing these data.

[0133] Through the above two methods, we can clean the noise in the historical score data, thereby improving the robustness of the matching model. The accurate and objective scores after cleaning will better reflect the capabilities and performances of the contract receiving parties, thus helping the platform to allocate tasks more precisely. In the embodiments of the present invention, the following solutions are also provided.

[0134] Perform overfitting detection on the target contract receiving party at a preset cycle.

[0135] In the embodiments of the present invention, exemplarily, after determining the target contract receiving party, performing overfitting detection on it at a preset cycle is to ensure that the selected contract receiving parties can maintain good performances during long-term operations and avoid overfitting to certain specific tasks. Overfitting refers to the situation where the model performs well on the training data but poorly on new data. To avoid overfitting, we can set a cycle for monitoring and evaluation, such as checking the performances of the target contract receiving parties at regular intervals. By comparing with the expected results, we can determine whether the target contract receiving parties have overfitted to certain tasks or have other abnormal situations, and take corresponding measures in a timely manner, such as adjusting the matching weights, re-evaluating the relevance, etc. Such overfitting detection can help the platform maintain the diversity and stability of the contract receiving parties, ensure the fairness and efficiency of task allocation. At the same time, it also helps to ensure that the needs of the contract awarding parties are met and improve the overall user experience.

[0136] The following provides an overall implementation manner of an embodiment of the present invention. Among them, the contract receiver can be an individual, a legal person, or a collective, and can provide professional services in a certain field, such as law, medicine, forensic medicine, finance, etc. The contract receiver works on a single outsourcing task, starting from receiving the task and ending at completion. The professional and specialized contract issuer (customer) can be an individual, a legal person, or a collective. During the production process, it needs professional and specialized personnel for temporary professional guidance, but cannot invest too much cost in hiring such personnel. The specific process is as follows:

[0137] (1) Initial matching

[0138] According to the roles, it is divided into the contract issuer and the contract receiver. By assigning fixed attribute codes and variable attribute scores to each role, the fixed attribute code of the contract issuer is composed of the outsourcing task attributes submitted by the contract issuer, and the fixed attribute of the contract receiver is composed of the personal portrait attributes of the contract receiver to ensure rapid preliminary matching.

[0139] Taking the professional field of appraisal and consultation as an example, the initial fixed attribute code of the task package issued by the contract issuer is the professional field M, the professional category N, the specific task scope X1, X2... Xn; the personal attributes of the contract receiver are the corresponding professional field m, the professional category n, and the specific task scope x1, x2... xn.

[0140] The professional attribute M retrieves the professional field m of the contract receiver, completes the first screening, and outputs the list menu1 that meets the conditions. All personnel in the table are assigned 1000

[0141] The professional category N continues to retrieve the professional category n of the contract receiver in menu1 and outputs the menu2 that meets the conditions. All personnel in the table are assigned 100

[0142] There are multiple specific requirement tags for professional and specialized work packages. List all requirement tags, the specific task scope X1, X2... Xn. There are multiple specific requirement tags for professional and specialized contract receivers, and the specific task scope is x1, x2... xn.

[0143] Perform Boolean operations. X1 and x1 can complete the corresponding output of 1, and the non-corresponding output is 0.

[0144] Add up all the assignments in the three steps, take the highest score, and complete the matching.

[0145] (2) Optimized matching

[0146] The automatic retrieval and matching method in step 1 is simple and direct. If more refined matching is desired, other variable attribute matching needs to be added.

[0147] The variable attributes are dynamically collected. Through statistical attribution, the variable attributes that the contract awarding party pays the most attention to are determined, and a matching linkage is formed with the variable attributes of the contract receiving party. The variable attributes are iterated periodically based on the collection of data such as the behavior and feedback of the contract awarding party to ensure the accuracy of the best match.

[0148] It is assumed that the contract awarding party sends out N packages, and each package contains the professional category N of attribute information, gender G, age X, customer classification C, timeliness T of the score at the end of the task, professionalism Q, practicality E, and customization U.

[0149] Calculate the correlation between each fixed attribute code and each score to determine whether there is a correlation, so as to obtain the ranking of the customer's concerns (timeliness T, professionalism Q, practicality E, customization U) for a certain type of professional and specialized outsourcing task. Assign values to the factors from large to small according to the ranking from high to low, such as the first assignment is 110% and the lowest assignment is 0.9%.

[0150] It is assumed that the processing time t of the contract receiving party, the usage amount q of professional vocabulary, the text richness e, and the customization u are related to the timeliness T of the score at the end of the customer task, professionalism Q, practicality E, and customization U.

[0151] Calculate the actual correlation between the objective situation of the contract receiving party and the customer's perceived score. And assign a value of 5 to each variable.

[0152] According to the assignment factors of the timeliness T of the score at the end of the task, professionalism Q, practicality E, and customization U, multiply the original constant assignment of 5 for the processing time t, the usage amount q of professional vocabulary, the text richness e, and the customization u of the contract receiving party by the assignment factor, add the results, and assign the task to the contract receiving party with the optimal score.

[0153] (3) Dynamic matching

[0154] Subsequently, continuously collect data on the customer evaluation score, dynamically adjust the attribute - concern score, and the concern score - contract receiving party portrait to obtain a dynamic best match.

[0155] (4) Maintenance

[0156] In the matching learning, if overfitting occurs, clear it regularly.

[0157] Please refer to Figure 2 , Figure 2 A task matching device 110 provided by an embodiment of the present invention includes:

[0158] An acquisition module 1101, which acquires the first fixed attribute of the contract awarding party and the second fixed attributes corresponding to multiple contract receiving parties respectively;

[0159] A matching module 1102 is configured to determine a target packet receiving party corresponding to a target fixed attribute based on a matching result between the first fixed attribute and a plurality of the second fixed attributes; and allocate the outsourcing task corresponding to the sending party to the target packet receiving party.

[0160] It should be noted that the implementation principle of the foregoing task matching device 110 may refer to the implementation principle of the foregoing task matching method, which will not be elaborated herein. It should be understood that the division of each module of the above device is only a logical function division. In actual implementation, it may be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the task matching device 110 can be a separately established processing element, or can be integrated in a certain chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device to perform the functions of the above task matching device 110. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or can be independently implemented. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the processor element in hardware or the instruction in software form.

[0161] For example, the above modules can be one or more integrated circuits configured to implement the above method, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), etc. Again, when a certain module above is implemented in the form of a processing element scheduling program code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. Again, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0162] An embodiment of the present invention provides a computer device 100. The computer device 100 includes a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device 100 executes the foregoing task matching device 110. As Figure 3As shown, Figure 3 The computer device 100 provided in the embodiment of the present invention is a structural block diagram. The computer device 100 includes a task matching device 110, a memory 111, a processor 112 and a communication unit 113.

[0163] To achieve data transmission or interaction, the memory 111, the processor 112 and the communication unit 113 are electrically connected to each other directly or indirectly. For example, the electrical connection between these elements can be achieved through one or more communication buses or signal lines. The task matching device 110 includes at least one software function module that can be stored in the memory 111 in the form of software or firmware or solidified in the operating system (OS) of the computer device 100. The processor 112 is used to execute the task matching device 110 stored in the memory 111, such as the software function modules and computer programs included in the task matching device 110.

[0164] An embodiment of the present invention provides a readable storage medium, which includes a computer program. When the computer program is executed, the computer device where the readable storage medium is located is controlled to execute the aforementioned task matching method.

[0165] For the purpose of illustration, the foregoing description is made with reference to specific embodiments. However, the above illustrative discussion is not intended to be exhaustive or to limit the present disclosure to the precise form disclosed. In accordance with the above teachings, numerous modifications and variations are possible. These embodiments are selected and described in order to best illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can best utilize the present disclosure and utilize various embodiments with different modifications to suit the intended specific application. For the purpose of illustration, the foregoing description is made with reference to specific embodiments. However, the above illustrative discussion is not intended to be exhaustive or to limit the present disclosure to the precise form disclosed. In accordance with the above teachings, numerous modifications and variations are possible. These embodiments are selected and described in order to best illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can best utilize the present disclosure and utilize various embodiments with different modifications to suit the intended specific application.

Claims

1. A task matching method, characterized in that, Including: Obtaining a first fixed attribute of the contract awarding party and second fixed attributes respectively corresponding to multiple contract receiving parties; Determining a target contract receiving party corresponding to a target fixed attribute based on a matching result of the first fixed attribute and the multiple second fixed attributes; Assigning an outsourcing task corresponding to the contract awarding party to the target contract receiving party.

2. The method according to claim 1, wherein The obtaining a first fixed attribute of the contract awarding party and second fixed attributes respectively corresponding to multiple contract receiving parties includes: Determining the first fixed attribute according to an outsourcing task attribute provided by the contract awarding party; Determining the second fixed attribute of each contract receiving party according to a personal portrait attribute configured for each contract receiving party.

3. The method according to claim 2, characterized in that The first fixed attribute includes a first professional field, a first category, and a first task scope, and the second fixed attribute includes a second professional field, a second category, and a second task scope; the determining a target contract receiving party corresponding to a target fixed attribute based on a matching result of the first fixed attribute and the multiple second fixed attributes includes: Matching the first professional field with the multiple second professional fields, and if the match is successful, assigning a first matching value to the contract receiving party corresponding to the successfully matched second professional field; Matching the first category with the multiple second categories, and if the match is successful, assigning a second matching value to the contract receiving party corresponding to the successfully matched second category; Matching the first task scope with the multiple second task scopes, and if the match is successful, assigning a third matching value to the contract receiving party corresponding to the successfully matched second task scope, where the first matching value is greater than the second matching value, and the second matching value is greater than the third matching value; Calculating the sum of the first matching value, the second matching value, and the third matching value corresponding to each contract receiving party, and taking the contract receiving party with the highest sum as the target contract receiving party.

4. The method according to claim 1, characterized in that, The method further includes: Obtaining multiple historical first fixed attributes of the contract awarding party and multiple task scoring attributes for each of the historical first fixed attributes; Assigning corresponding weights to each of the task scoring attributes based on a first correlation between the multiple historical first fixed attributes and the multiple task scoring attributes; Obtaining multiple task processing characteristics of the contract receiving party and determining a second correlation between the multiple task processing characteristics and the multiple task scoring attributes; Performing a weighted calculation on the multiple task processing characteristics according to the second correlation and the weights assigned to each of the task scoring attributes to obtain a fourth matching value; Taking the contract receiving party with the largest fourth matching value as the target contract receiving party.

5. The method according to claim 4, wherein The multiple historical first fixed attributes include professional categories, gender, age, and customer classification, the multiple task scoring attributes include timeliness, professionalism, and practicality, and the task processing characteristics include processing time, the amount of professional vocabulary used, and text richness. The assigning corresponding weights to each of the task scoring attributes based on a first correlation between the multiple historical first fixed attributes and the multiple task scoring attributes includes: Based on the first relevance of the professional category, gender, age, customer classification, and the timeliness, professionalism, and practicality, allocate corresponding weights to the timeliness, professionalism, and practicality; The obtaining of multiple task processing characteristics of the packet receiving party and determining the second relevance between the multiple task processing characteristics and the multiple task scoring attributes includes: Obtain the processing time, the usage amount of professional vocabulary, and the text richness, and determine the second relevance between the processing time, the usage amount of professional vocabulary, and the text richness and the timeliness, professionalism, and practicality.

6. The method according to claim 4, wherein The method further includes: Use the determined associated data of the target packet receiving party as the reference data for determining the first relevance and the second relevance.

7. The method according to claim 4, characterized in that The method further includes: Perform overfitting detection on the target packet receiving party at a preset cycle.

8. A task matching device, characterized in that, Includes: An obtaining module that obtains the first fixed attribute of the contract awarding party and the respective corresponding second fixed attributes of multiple packet receiving parties; A matching module for determining the target packet receiving party corresponding to the target fixed attribute based on the matching result of the first fixed attribute and the multiple second fixed attributes; Allocate the outsourcing tasks corresponding to the contract awarding party to the target packet receiving party.

9. A computer device, characterized in that, The computer device includes a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device executes the task matching method according to any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium includes a computer program. When the computer program runs, it controls the computer device where the readable storage medium is located to execute the task matching method according to any one of claims 1-7.

Images