Task allocation method, device, computer equipment and storage medium

Abstract

The present application relates to a task assignment method, apparatus, computer equipment, storage medium, and computer program product, and relates to the field of artificial intelligence technology, and can be used in the field of financial technology or other related fields. The method includes: obtaining a business data sequence of each object to be analyzed, and based on each business data sequence, determining a first target business data sequence and a second target business data sequence; determining a first Euclidean distance and a first gray correlation between each business data sequence and the first target business data sequence, and a second Euclidean distance and a second gray correlation between each business data sequence and the second target business data sequence; determining a business task processing level for each object to be analyzed based on the first Euclidean distance, the second Euclidean distance, the first gray correlation, and the second gray correlation; and assigning business tasks corresponding to the business task processing level to each object to be analyzed. The use of this method can improve the efficiency of business task processing.

Description

Technical Field

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

[0002] As the business grows, the amount of business tasks increases. In order to avoid the accumulation of business tasks, more objects usually need to be arranged to complete them.

[0003] In traditional technology, a random assignment method is used when assigning business tasks to objects; however, this random assignment method easily leads to a long business task processing time, resulting in low business task processing efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a task allocation method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of business task processing in order to address the above technical problems.

[0005] In a first aspect, the present application provides a task allocation method, comprising:

[0006] Obtaining a business data sequence for each object to be analyzed, and determining a first target business data sequence and a second target business data sequence based on each of the business data sequences; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences;

[0007] respectively determining a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence;

[0008] For each of the business data sequences, determining a business task processing level of each of the objects to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree;

[0009] Acquire business tasks corresponding to the business task processing levels of the objects to be analyzed;

[0010] Business tasks corresponding to the business task processing levels of the objects to be analyzed are respectively allocated to the objects to be analyzed.

[0011] In one embodiment, determining, for each of the business data sequences, the business task processing level of each of the objects to be analyzed based on the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree includes:

[0012] For each of the business data sequences, converting the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree to obtain a converted first Euclidean distance, a converted second Euclidean distance, a converted first grey relational degree, and a converted second grey relational degree;

[0013] determining a first closeness between each of the business data sequences and the first target business data sequence based on the converted second Euclidean distance and the converted first grey relational degree, and determining a first distance between each of the business data sequences and the first target business data sequence based on the converted first Euclidean distance and the converted second grey relational degree;

[0014] determining a first relative closeness between each of the service data sequences and the first target service data sequence according to the first closeness and the first farthest;

[0015] The business task processing level of each of the objects to be analyzed is determined according to the first relative closeness.

[0016] In one embodiment, determining the first closeness between each of the business data sequences and the first target business data sequence based on the converted second Euclidean distance and the converted first grey relational degree, and determining the first distance between each of the business data sequences and the first target business data sequence based on the converted first Euclidean distance and the converted second grey relational degree, includes:

[0017] Obtain a first weight and a second weight; the sum of the first weight and the second weight is 1;

[0018] fusing the converted second Euclidean distance and the converted first grey relational degree according to the first weight and the second weight to obtain a first closeness between each of the business data sequences and the first target business data sequence;

[0019] According to the first weight and the second weight, the converted first Euclidean distance and the converted second grey relational degree are fused to obtain a first distance between each of the business data sequences and the first target business data sequence.

[0020] In one embodiment, before determining the business task processing level of each of the objects to be analyzed according to the first relative closeness, the method further includes:

[0021] Determine, based on the fourth Euclidean distance and the third grey relational degree, a second closeness between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence, and determine, based on the third Euclidean distance and the fourth grey relational degree, a second distance between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence;

[0022] determining, based on the second closeness and the second farthestness, a second relative closeness between a sub-business data sequence in each of the business data sequences and a corresponding third target business data sequence; the third Euclidean distance, the fourth Euclidean distance, the third grey relational degree, and the fourth grey relational degree are obtained based on the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence and fourth target business data sequence;

[0023] Determining the business task processing level of each object to be analyzed based on the first relative closeness includes:

[0024] The business task processing level of each of the objects to be analyzed is determined according to the first relative closeness and the second relative closeness.

[0025] In one embodiment, before determining the second closeness between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence based on the fourth Euclidean distance and the third gray correlation degree, and determining the second distance between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence based on the third Euclidean distance and the fourth gray correlation degree, the method further includes:

[0026] Splitting each of the business data sequences according to the business indicators to obtain sub-business data sequences in each of the business data sequences;

[0027] Determine, based on the sub-business data sequences in each of the business data sequences, a corresponding third target business data sequence and a fourth target business data sequence; the third target business data sequence is constructed based on the maximum sub-business data in the sub-business data sequences corresponding to the same business indicator, and the fourth target business data sequence is constructed based on the minimum sub-business data in the sub-business data sequences corresponding to the same business indicator;

[0028] Determine respectively the third Euclidean distance between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence, the fourth Euclidean distance between the sub-business data sequence in each of the business data sequences and the corresponding fourth target business data sequence, the third gray correlation between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence, and the fourth gray correlation between the sub-business data sequence in each of the business data sequences and the corresponding fourth target business data sequence.

[0029] In one embodiment, the first grey relational degree and the second grey relational degree are obtained by:

[0030] Obtaining a first grey correlation matrix between each of the business data sequences and the first target business data sequence, and a second grey correlation matrix between each of the business data sequences and the second target business data sequence;

[0031] According to the first grey correlation matrix, a first grey correlation degree between each of the business data sequences and the first target business data sequence is determined, and according to the second grey correlation matrix, a second grey correlation degree between each of the business data sequences and the second target business data sequence is determined.

[0032] In one embodiment, obtaining the business data sequence of each object to be analyzed includes:

[0033] Obtaining business data of each object to be analyzed under each business indicator;

[0034] Preprocessing the business data to obtain preprocessed business data;

[0035] Determining, according to the business indicator corresponding to the business data, a business weight corresponding to the business data as the business weight corresponding to the preprocessed business data;

[0036] The business data sequence of each object to be analyzed is determined according to the pre-processed business data and the business weight corresponding to the pre-processed business data.

[0037] In a second aspect, the present application further provides a task allocation device, comprising:

[0038] A sequence determination module is configured to obtain a business data sequence for each object to be analyzed and, based on each of the business data sequences, determine a first target business data sequence and a second target business data sequence; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences;

[0039] an information determination module, configured to respectively determine a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence;

[0040] a level determination module, configured to determine, for each of the business data sequences, a business task processing level of each of the objects to be analyzed based on the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree;

[0041] A task acquisition module, configured to acquire business tasks corresponding to the business task processing level of each object to be analyzed;

[0042] The task allocation module is used to allocate business tasks corresponding to the business task processing level of each object to be analyzed to each object to be analyzed.

[0043] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0044] Obtaining a business data sequence for each object to be analyzed, and determining a first target business data sequence and a second target business data sequence based on each of the business data sequences; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences;

[0045] respectively determining a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence;

[0046] For each of the business data sequences, determining a business task processing level of each of the objects to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree;

[0047] Acquire business tasks corresponding to the business task processing levels of the objects to be analyzed;

[0048] Business tasks corresponding to the business task processing levels of the objects to be analyzed are respectively allocated to the objects to be analyzed.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0050] Obtaining a business data sequence for each object to be analyzed, and determining a first target business data sequence and a second target business data sequence based on each of the business data sequences; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences;

[0051] respectively determining a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence;

[0052] For each of the business data sequences, determining a business task processing level of each of the objects to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree;

[0053] Acquire business tasks corresponding to the business task processing levels of the objects to be analyzed;

[0054] Business tasks corresponding to the business task processing levels of the objects to be analyzed are respectively allocated to the objects to be analyzed.

[0055] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0056] Obtaining a business data sequence for each object to be analyzed, and determining a first target business data sequence and a second target business data sequence based on each of the business data sequences; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences;

[0057] respectively determining a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence;

[0058] For each of the business data sequences, determining a business task processing level of each of the objects to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree;

[0059] Acquire business tasks corresponding to the business task processing levels of the objects to be analyzed;

[0060] Business tasks corresponding to the business task processing levels of the objects to be analyzed are respectively allocated to the objects to be analyzed.

[0061] The task assignment method, apparatus, computer device, storage medium, and computer program product first obtain a business data sequence for each object to be analyzed, and based on each business data sequence, determine a first target business data sequence constructed based on the maximum business data under the same business indicator in each business data sequence, and a second target business data sequence constructed based on the minimum business data under the same business indicator in each business data sequence. Then, a first Euclidean distance between each business data sequence and the first target business data sequence, a second Euclidean distance between each business data sequence and the second target business data sequence, a first grey correlation between each business data sequence and the first target business data sequence, and a second grey correlation between each business data sequence and the second target business data sequence are determined. Then, for each business data sequence, based on the first Euclidean distance, the second Euclidean distance, the first grey correlation, and the second grey correlation, a business task processing level for each object to be analyzed is determined. Next, a business task corresponding to the business task processing level of each object to be analyzed is obtained. Finally, the business task corresponding to the business task processing level of each object to be analyzed is assigned to each object to be analyzed. In this way, when performing task assignment, by calculating the Euclidean distance and grey correlation between each business data sequence and the first target business data sequence and the second target business data sequence, it is equivalent to conducting a comprehensive analysis of each business data sequence from multiple dimensions, which is beneficial to improving the accuracy of determining the business task processing level of each object to be analyzed; moreover, the business tasks corresponding to the business task processing level of each object to be analyzed are respectively assigned to each object to be analyzed, which is equivalent to assigning matching business tasks according to the business task processing level of each object to be analyzed, which is beneficial to more reasonable allocation of business tasks, avoiding the defect that the random allocation method easily leads to a long business task processing time, thereby causing low business task processing efficiency, thereby improving the business task processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 A flowchart of a task allocation method in one embodiment;

[0064] Figure 2 A flowchart illustrating steps for determining a business task processing level for each object to be analyzed in one embodiment;

[0065] Figure 31 is a flow chart of the steps of determining a first degree of closeness and a first degree of distance in one embodiment;

[0066] Figure 4 FIG1 is a flow chart of a step of determining a second relative closeness in one embodiment;

[0067] Figure 5 1 is a flow chart of steps for determining a third Euclidean distance, a fourth Euclidean distance, a third grey relational degree, and a fourth grey relational degree in one embodiment;

[0068] Figure 6 Schematic diagram of a flow chart of steps for determining a business data sequence of each object to be analyzed in one embodiment;

[0069] Figure 7 A flowchart of a task allocation method according to another embodiment;

[0070] Figure 8 A flowchart illustrating the steps of a method for classifying and evaluating bank customer service managers based on a superior-inferior solution distance method using Euclidean distance and grey relational degree in one embodiment;

[0071] Figure 9 is a structural block diagram of a task allocation device in one embodiment;

[0072] Figure 10 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0074] 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, and the collection, use and processing of relevant data must comply with relevant regulations.

[0075] In an exemplary embodiment, Figure 1As shown, a task allocation method is provided. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablet computers; the server can be implemented as an independent server or a server cluster consisting of multiple servers. In this embodiment, the method includes the following steps:

[0076] Step S101: Obtain the business data sequence of each object to be analyzed, and determine a first target business data sequence and a second target business data sequence based on each business data sequence; each business data sequence includes the business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each business data sequence, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each business data sequence.

[0077] The object to be analyzed refers to the object that needs to be analyzed, such as a customer manager.

[0078] The business data sequence refers to the data sequence corresponding to the business data of the object to be analyzed under various business indicators.

[0079] Business indicators are indicators that evaluate the business capabilities of the analyzed entity. In practical scenarios, these indicators focus on the business capabilities of account managers, evaluated based on four scoring criteria: service quality, marketing performance, learning and development, and risk control. There are 15 evaluation indicators in total: customer satisfaction, customer complaint rate, business processing efficiency, business volume, basic factoring referral success rate, deposits, precious metals, specialty cards, credit cards, and courier card bindings, individual account activations, participation in industry events, qualification certificates, completion rate of professional and skills training, risk awareness, risk control capabilities, and risk management events. Business indicators can be either positive or negative. With the exception of customer complaint rate and risk management events, which are negative indicators, all other business indicators (such as customer satisfaction, business processing efficiency, and business volume) are positive indicators. Business indicators are statistically analyzed using the corresponding business indicator table, as shown in Table 1.

[0080] Table 1 Business indicators

[0081]

[0082] Among them, business data refers to the data of the object to be analyzed under business indicators.

[0083] The first target business data sequence refers to a business data sequence constructed based on the maximum business data under the same business indicator in each business data sequence.

[0084] For example, the server may calculate the first target service data sequence using the following formula:

[0085]

[0086] in, Refers to the first target business data sequence, i refers to the object to be analyzed, n refers to the total number of objects to be analyzed, j refers to the business indicator, D refers to the indicator set corresponding to the business indicator, and m refers to the total number of business indicators. Refers to the business data of the object to be analyzed under the business indicators. It refers to the maximum value of the business data corresponding to the same business indicator in each business data series.

[0087] The second target business data sequence refers to a business data sequence constructed based on the minimum business data under the same business indicator in each business data sequence.

[0088] For example, the server may calculate the second target service data sequence using the following formula:

[0089]

[0090] in, refers to the second target business data sequence, It refers to the minimum value corresponding to the business data of each business data series under the same business indicator.

[0091] The maximum business data under the same business indicator in each business data sequence refers to the maximum value corresponding to the business data under the same business indicator in each business data sequence.

[0092] The minimum business data under the same business indicator in each business data sequence refers to the minimum value corresponding to the business data under the same business indicator in each business data sequence.

[0093] Exemplarily, in response to a task assignment instruction for an object to be analyzed, the server obtains the business data of each object to be analyzed under each business indicator from a financial database, and preprocesses the business data to obtain preprocessed business data; then, the server determines the business data sequence of each object to be analyzed based on the preprocessed business data; then, the server obtains the maximum business data under the same business indicator in each business data sequence, and constructs a first target business data sequence based on the maximum business data under the same business indicator in each business data sequence; then, the server obtains the minimum business data under the same business indicator in each business data sequence, and constructs a second target business data sequence based on the minimum business data under the same business indicator in each business data sequence.

[0094] Step S102, respectively determine the first Euclidean distance between each business data sequence and the first target business data sequence, the second Euclidean distance between each business data sequence and the second target business data sequence, the first grey correlation degree between each business data sequence and the first target business data sequence, and the second grey correlation degree between each business data sequence and the second target business data sequence.

[0095] The first Euclidean distance refers to the Euclidean distance between each service data sequence and the first target service data sequence.

[0096] For example, the server can calculate the first Euclidean distance using the following formula:

[0097]

[0098] in, is the first Euclidean distance.

[0099] The second Euclidean distance refers to the Euclidean distance between each service data sequence and the second target service data sequence.

[0100] For example, the server can calculate the second Euclidean distance using the following formula:

[0101]

[0102] in, is the first Euclidean distance.

[0103] The first grey correlation degree refers to the grey correlation degree between each business data sequence and the first target business data sequence.

[0104] For example, the server can calculate the first grey relational degree using the following formula:

[0105]

[0106] in, Refers to the first grey relational degree.

[0107] The second grey correlation degree refers to the grey correlation degree between each business data sequence and the second target business data sequence.

[0108] For example, the server can calculate the second grey relational degree using the following formula:

[0109]

[0110] in, Refers to the first grey relational degree.

[0111] Exemplarily, the server inputs each business data sequence and the first target business data sequence into the Euclidean distance determination model, and obtains the first Euclidean distance between each business data sequence and the first target business data sequence through the Euclidean distance determination model; then, the server inputs each business data sequence and the second target business data sequence into the Euclidean distance determination model, and obtains the second Euclidean distance between each business data sequence and the second target business data sequence through the Euclidean distance determination model; then, the server inputs each business data sequence and the first target business data sequence into the gray correlation determination model, and obtains the first gray correlation between each business data sequence and the first target business data sequence through the gray correlation determination model; then, the server inputs each business data sequence and the second target business data sequence into the gray correlation determination model, and obtains the second gray correlation between each business data sequence and the second target business data sequence through the gray correlation determination model.

[0112] Step S103 : for each business data sequence, determine the business task processing level of each object to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey correlation degree, and the second grey correlation degree.

[0113] The business task processing level refers to the capability level of the object to be analyzed in terms of business task processing.

[0114] Exemplarily, the server determines the relative closeness between each business data sequence and the first target business data sequence based on the first Euclidean distance, the second Euclidean distance, the first grey correlation degree and the second grey correlation degree; then, the server determines the business task processing level of each object to be analyzed based on the relative closeness between each business data sequence and the first target business data sequence.

[0115] Step S104: obtaining the business tasks corresponding to the business task processing level of each object to be analyzed.

[0116] Among them, business tasks refer to the work tasks of the analysis object.

[0117] Exemplarily, the server queries the correspondence between the business task processing level and the business task according to the business task processing level of each object to be analyzed, obtains the business task corresponding to the business task processing level as the business task corresponding to the business task processing level of each object to be analyzed.

[0118] Step S105 : assigning business tasks corresponding to the business task processing levels of the objects to be analyzed to the objects to be analyzed.

[0119] Exemplarily, the server allocates the business tasks corresponding to the business task processing level of each object to be analyzed to each object to be analyzed according to the correspondence between the business tasks and each object to be analyzed.

[0120] In the above-mentioned task assignment method, the business data sequence of each object to be analyzed is first obtained. Based on each business data sequence, a first target business data sequence constructed according to the maximum business data under the same business indicator in each business data sequence and a second target business data sequence constructed according to the minimum business data under the same business indicator in each business data sequence are determined. Then, a first Euclidean distance between each business data sequence and the first target business data sequence, a second Euclidean distance between each business data sequence and the second target business data sequence, a first grey correlation degree between each business data sequence and the first target business data sequence, and a second grey correlation degree between each business data sequence and the second target business data sequence are determined respectively. Then, for each business data sequence, the business task processing level of each object to be analyzed is determined based on the first Euclidean distance, the second Euclidean distance, the first grey correlation degree, and the second grey correlation degree. Then, a business task corresponding to the business task processing level of each object to be analyzed is obtained. Finally, the business task corresponding to the business task processing level of each object to be analyzed is respectively assigned to each object to be analyzed. In this way, when performing task assignment, by calculating the Euclidean distance and grey correlation between each business data sequence and the first target business data sequence and the second target business data sequence, it is equivalent to conducting a comprehensive analysis of each business data sequence from multiple dimensions, which is beneficial to improving the accuracy of determining the business task processing level of each object to be analyzed; moreover, the business tasks corresponding to the business task processing level of each object to be analyzed are respectively assigned to each object to be analyzed, which is equivalent to assigning matching business tasks according to the business task processing level of each object to be analyzed, which is beneficial to more reasonable allocation of business tasks, avoiding the defect that the random allocation method easily leads to a long business task processing time, thereby causing low business task processing efficiency, thereby improving the business task processing efficiency.

[0121] In an exemplary embodiment, Figure 2 As shown, the above step S103, for each business data sequence, determines the business task processing level of each object to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey correlation degree and the second grey correlation degree, specifically includes the following steps:

[0122] Step S201: For each business data sequence, the first Euclidean distance, the second Euclidean distance, the first grey correlation degree and the second grey correlation degree are converted to obtain the converted first Euclidean distance, the converted second Euclidean distance, the converted first grey correlation degree and the converted second grey correlation degree.

[0123] Step S202: Determine the first closeness between each business data sequence and the first target business data sequence based on the converted second Euclidean distance and the converted first gray correlation degree, and determine the first distance between each business data sequence and the first target business data sequence based on the converted first Euclidean distance and the converted second gray correlation degree.

[0124] Step S203 : determining a first relative closeness between each service data sequence and a first target service data sequence according to the first closeness and the first distance.

[0125] Step S204: determining the business task processing level of each object to be analyzed according to the first relative closeness.

[0126] Here, the conversion process refers to dimensionless processing.

[0127] For example, the server may perform dimensionless processing on the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree using the following formula to obtain the converted first Euclidean distance, the converted second Euclidean distance, the converted first grey relational degree, and the converted second grey relational degree:

[0128]

[0129] in, They are respectively the first Euclidean distance after conversion, the second Euclidean distance after conversion, the first grey relational degree after conversion and the second grey relational degree after conversion.

[0130] The converted first Euclidean distance refers to the first Euclidean distance after dimensionless processing.

[0131] The converted second Euclidean distance refers to the second Euclidean distance after dimensionless processing.

[0132] The converted first grey relational degree refers to the first grey relational degree after dimensionless processing.

[0133] The converted second grey relational degree refers to the second grey relational degree after dimensionless processing.

[0134] The first closeness represents the degree of proximity between each service data sequence and the first target service data sequence.

[0135] For example, the server can calculate the first closeness using the following formula:

[0136]

[0137] in, is the first degree of closeness, and is the weight coefficient corresponding to the converted second Euclidean distance and the converted first grey relational degree, satisfying .

[0138] The first distance represents the distance between each service data sequence and the first target service data sequence.

[0139] For example, the server can calculate the first distance using the following formula:

[0140]

[0141] in, is the first distance, and is the weight coefficient corresponding to the first Euclidean distance after transformation and the second grey relational degree after transformation, satisfying .

[0142] The first relative closeness represents the relative closeness between each business data sequence and the first target business data sequence.

[0143] For example, the server may calculate the first relative closeness using the following formula:

[0144]

[0145] in, Refers to the first relative closeness.

[0146] Exemplarily, the server converts the first Euclidean distance, the second Euclidean distance, the first gray correlation degree, and the second gray correlation degree for each business data sequence to obtain the converted first Euclidean distance, the converted second Euclidean distance, the converted first gray correlation degree, and the converted second gray correlation degree; for example, the server non-dimensionalizes the first Euclidean distance, the second Euclidean distance, the first gray correlation degree, and the second gray correlation degree for each business data sequence to obtain the non-dimensionalized first Euclidean distance, the non-dimensionalized second Euclidean distance, the non-dimensionalized first gray correlation degree, and the non-dimensionalized second gray correlation degree; then, the server inputs the converted second Euclidean distance and the converted first gray correlation degree into the proximity determination model, and obtains the first proximity corresponding to the converted second Euclidean distance and the converted first gray correlation degree through the proximity determination model as each business data The first closeness between the sequence and the first target business data sequence; then, the server inputs the converted first Euclidean distance and the converted second gray correlation into the distance determination model, and obtains the first distance corresponding to the converted first Euclidean distance and the converted second gray correlation through the distance determination model, as the first distance between each business data sequence and the first target business data sequence; then, the server inputs the first closeness and the first distance into the relative closeness determination model, and obtains the first relative closeness corresponding to the first closeness and the first distance through the relative closeness determination model, as the first relative closeness between each business data sequence and the first target business data sequence; finally, the server queries the correspondence between the first relative closeness and the business task processing level based on the first relative closeness, and obtains the business task processing level corresponding to the first relative closeness, as the business task processing level of each object to be analyzed.

[0147] In this embodiment, by determining the first relative closeness between each business data sequence and the first target business data sequence based on the first closeness and first farthest between each business data sequence and the first target business data sequence, it is beneficial to more accurately evaluate the relative proximity of each business data sequence to the first target business data sequence; moreover, determining the business task processing level of each object to be analyzed based on the first relative closeness is beneficial to accurately classify the objects to be analyzed with different capabilities according to the business task processing level, thereby improving the accuracy of determining the business task processing level of each object to be analyzed.

[0148] In an exemplary embodiment, Figure 3As shown, the above step S202, which determines the first closeness between each business data sequence and the first target business data sequence according to the converted second Euclidean distance and the converted first grey relational degree, and determines the first distance between each business data sequence and the first target business data sequence according to the converted first Euclidean distance and the converted second grey relational degree, specifically includes the following steps:

[0149] Step S301: Obtain a first weight and a second weight; the sum of the first weight and the second weight is 1.

[0150] Step S302 : performing a fusion process on the converted second Euclidean distance and the converted first grey relational degree according to the first weight and the second weight, to obtain a first closeness between each business data sequence and the first target business data sequence.

[0151] Step S303 , fusing the converted first Euclidean distance and the converted second grey relational degree according to the first weight and the second weight, to obtain a first distance between each business data sequence and the first target business data sequence.

[0152] The first weight refers to the weight corresponding to the Euclidean distance.

[0153] The second weight refers to the weight corresponding to the grey relational degree.

[0154] Here, fusion processing refers to weighted processing.

[0155] Exemplarily, the server obtains the first weight and the second weight from the financial data; then, the server inputs the converted second Euclidean distance, the converted first gray correlation, the first weight and the second weight into the proximity determination model, and obtains the first proximity corresponding to the converted second Euclidean distance, the converted first gray correlation, the first weight and the second weight through the proximity determination model, as the first proximity between each business data sequence and the first target business data sequence; then, the server inputs the converted first Euclidean distance, the converted second gray correlation, the first weight and the second weight into the distance determination model, and obtains the first distance corresponding to the converted first Euclidean distance, the converted second gray correlation, the first weight and the second weight through the distance determination model, as the first distance between each business data sequence and the first target business data sequence.

[0156] In this embodiment, by obtaining the first weight and the second weight, and performing weighted summation on the two indicators of Euclidean distance and gray correlation degree, a more comprehensive first closeness and first distance can be obtained, thereby more accurately reflecting the degree of closeness and distance between each business data sequence and the first target business data sequence.

[0157] In an exemplary embodiment, Figure 4 As shown, the above step S204, before determining the business task processing level of each object to be analyzed according to the first relative closeness, specifically includes the following steps:

[0158] Step S401, based on the fourth Euclidean distance and the third gray correlation degree, determine the second closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, and based on the third Euclidean distance and the fourth gray correlation degree, determine the second distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence.

[0159] Step S402, based on the second closeness and the second farthestness, determine the second relative closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence; the third Euclidean distance, the fourth Euclidean distance, the third gray correlation degree and the fourth gray correlation degree are obtained based on the sub-business data sequence in each business data sequence and the corresponding third target business data sequence and the fourth target business data sequence.

[0160] Then, determining the business task processing level of each object to be analyzed according to the first relative closeness includes: determining the business task processing level of each object to be analyzed according to the first relative closeness and the second relative closeness.

[0161] The fourth Euclidean distance refers to the Euclidean distance between the sub-service data sequence in each service data sequence and the corresponding fourth target service data sequence.

[0162] The sub-business data sequence refers to a business data sequence obtained by splitting the business data sequence according to each business indicator.

[0163] For example, referring to Table 1, the business data sequence is (a1, a2, a3, b1, b2, b3, b4, b5, b6, c1, c2, c3, d1, d2, d3), then the sub-business data sequence (such as the sub-business data sequence corresponding to learning and development) is (c1, c2, c3).

[0164] The fourth target business data sequence refers to a business data sequence constructed based on the minimum sub-business data in the sub-business data sequence corresponding to the same business indicator.

[0165] The minimum sub-business data in the sub-business data sequence corresponding to the same business indicator refers to the minimum value corresponding to the sub-business data in the sub-business data sequence corresponding to the same business indicator.

[0166] The sub-business data refers to the data in the sub-business data sequence.

[0167] The third grey correlation degree refers to the grey correlation degree between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence.

[0168] The third target business data sequence refers to a business data sequence constructed based on the maximum sub-business data in the sub-business data sequences corresponding to the same business indicator.

[0169] The maximum sub-business data in the sub-business data sequence corresponding to the same business indicator refers to the maximum value corresponding to the sub-business data in the sub-business data sequence corresponding to the same business indicator.

[0170] The second closeness represents the degree of proximity between each business data sequence and the second target business data sequence.

[0171] The third Euclidean distance refers to the Euclidean distance between the sub-service data sequence in each service data sequence and the corresponding third target service data sequence.

[0172] The fourth grey correlation degree refers to the grey correlation degree between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence.

[0173] The second distance represents the distance between each service data sequence and the second target service data sequence.

[0174] The second relative closeness represents the relative proximity between each service data sequence and the second target service data sequence.

[0175] Exemplarily, the server converts the third Euclidean distance, the fourth Euclidean distance, the third grey correlation degree and the fourth grey correlation degree for the sub-business data sequences in each business data sequence to obtain the converted third Euclidean distance, the converted fourth Euclidean distance, the converted third grey correlation degree and the converted fourth grey correlation degree; for example, the server non-dimensionalizes the third Euclidean distance, the fourth Euclidean distance, the third grey correlation degree and the fourth grey correlation degree for each business data sequence to obtain the non-dimensionalized third Euclidean distance, the non-dimensionalized fourth Euclidean distance, the non-dimensionalized third grey correlation degree and the non-dimensionalized fourth grey correlation degree; then, the server inputs the converted fourth Euclidean distance and the converted third grey correlation degree into the proximity determination model, and obtains the converted fourth Euclidean distance and the converted fourth grey correlation degree through the proximity determination model. The second closeness corresponding to the converted third gray correlation degree serves as the second closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence; then, the server inputs the converted third Euclidean distance and the converted fourth gray correlation degree into the distance determination model, and obtains the second distance corresponding to the converted third Euclidean distance and the converted fourth gray correlation degree through the distance determination model, as the second distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence; then, the server inputs the second closeness and the second distance into the relative closeness determination model, and obtains the second relative closeness corresponding to the second closeness and the second distance through the relative closeness determination model, as the second relative closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence.

[0176] In this embodiment, by determining the second relative closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence based on the second closeness and second farthest between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, it is beneficial to more accurately evaluate the relative closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, thereby improving the evaluation accuracy of the sub-business data sequence in each business data sequence.

[0177] In an exemplary embodiment, Figure 5 As shown, the above step S401, before determining the second closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence based on the fourth Euclidean distance and the third grey correlation degree, and determining the second distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence based on the third Euclidean distance and the fourth grey correlation degree, specifically includes the following steps:

[0178] Step S501 : split each business data sequence according to each business indicator to obtain a sub-business data sequence in each business data sequence.

[0179] Step S502: Determine the corresponding third target business data sequence and fourth target business data sequence based on the sub-business data sequence in each business data sequence; the third target business data sequence is constructed based on the maximum sub-business data in the sub-business data sequence corresponding to the same business indicator, and the fourth target business data sequence is constructed based on the minimum sub-business data in the sub-business data sequence corresponding to the same business indicator.

[0180] Step S503, respectively determine the third Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, the fourth Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence, the third gray correlation between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, and the fourth gray correlation between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence.

[0181] The splitting of each business data sequence refers to the process of dividing the data of each business data sequence according to each business indicator.

[0182] Exemplarily, the server splits each business data sequence according to each business indicator to obtain the split business data sequence as the sub-business data sequence in each business data sequence; then, the server obtains the maximum sub-business data in the sub-business data sequence corresponding to the same business indicator, and constructs a third target business data sequence based on the maximum sub-business data in the sub-business data sequence corresponding to the same business indicator; then, the server obtains the minimum sub-business data in the sub-business data sequence corresponding to the same business indicator, and constructs a fourth target business data sequence based on the minimum sub-business data in the sub-business data sequence corresponding to the same business indicator; then, the server inputs the sub-business data sequence in each business data sequence and the corresponding third target business data sequence into the Euclidean distance determination model, and obtains the first target distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence through the Euclidean distance determination model. Three Euclidean distances; then, the server inputs the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence into the Euclidean distance determination model, and obtains the fourth Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence through the Euclidean distance determination model; then, the server inputs the sub-business data sequence in each business data sequence and the corresponding third target business data sequence into the gray correlation determination model, and obtains the third gray correlation between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence through the gray correlation determination model; then, the server inputs the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence into the gray correlation determination model, and obtains the fourth gray correlation between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence through the gray correlation determination model.

[0183] In this embodiment, by analyzing the sub-business data sequences in each business data sequence, it is equivalent to performing data analysis from the dimensions of different business indicators, so that the performance of each object to be analyzed in different business indicators can be comprehensively analyzed, thereby improving the evaluation accuracy of each object to be analyzed.

[0184] In an exemplary embodiment, the first gray correlation degree and the second gray correlation degree are obtained in the following manner: obtaining a first gray correlation matrix between each business data sequence and the first target business data sequence, and a second gray correlation matrix between each business data sequence and the second target business data sequence; determining the first gray correlation degree between each business data sequence and the first target business data sequence based on the first gray correlation matrix, and determining the second gray correlation degree between each business data sequence and the second target business data sequence based on the second gray correlation matrix.

[0185] The first grey relational matrix refers to the grey relational matrix between each business data sequence and the first target business data sequence.

[0186] For example, the server can calculate the first grey correlation matrix using the following formula:

[0187]

[0188] in, refers to the first grey incidence matrix.

[0189] The second grey relational matrix refers to the grey relational matrix between each business data sequence and the second target business data sequence.

[0190] For example, the server can calculate the second grey correlation matrix using the following formula:

[0191]

[0192] in, refers to the second grey incidence matrix.

[0193] Exemplarily, the server inputs each business data sequence and the first target business data sequence into the gray correlation matrix determination model, and determines the first gray correlation matrix between each business data sequence and the first target business data sequence through the gray correlation matrix determination model; then, the server inputs each business data sequence and the second target business data sequence into the gray correlation matrix determination model, and determines the second gray correlation matrix between each business data sequence and the second target business data sequence through the gray correlation matrix determination model; then, the server inputs the first gray correlation matrix into the gray correlation degree determination model, and obtains the first gray correlation degree corresponding to the first gray correlation matrix through the gray correlation degree determination model, as the first gray correlation degree between each business data sequence and the first target business data sequence; then, the server inputs the second gray correlation matrix into the gray correlation degree determination model, and obtains the second gray correlation degree corresponding to the second gray correlation matrix through the gray correlation degree determination model, as the second gray correlation degree between each business data sequence and the second target business data sequence.

[0194] In this embodiment, determining the grey correlation degree through the grey correlation matrix is ​​beneficial to comprehensively analyzing the correlation between each business data sequence and the first target business data sequence and the second target business data sequence, thereby improving the accuracy of determining the grey correlation degree.

[0195] In an exemplary embodiment, Figure 6 As shown, the above step S101, obtaining the business data sequence of each object to be analyzed, specifically includes the following steps:

[0196] Step S601: Obtain business data of each object to be analyzed under each business indicator.

[0197] Step S602: pre-process the service data to obtain pre-processed service data.

[0198] Step S603 : determining the business weight corresponding to the business data according to the business indicator corresponding to the business data, as the business weight corresponding to the pre-processed business data.

[0199] Step S604 : determining the business data sequence of each object to be analyzed based on the pre-processed business data and the business weight corresponding to the pre-processed business data.

[0200] Among them, preprocessing includes missing value processing, outlier processing, data cleaning processing, data conversion processing, etc.

[0201] The pre-processed business data refers to the business data that has been pre-processed.

[0202] Among them, business weight refers to the weight corresponding to the business indicator, which is used to represent the importance of the business indicator.

[0203] Exemplarily, in response to a task assignment instruction for an object to be analyzed, the server obtains the business data of each object to be analyzed under each business indicator from a financial database; then, the server preprocesses the business data to obtain preprocessed business data; for example, the server performs missing value processing, outlier processing, data cleaning processing, and data conversion processing on the business data to obtain preprocessed business data; then, the server determines the business weight corresponding to the business indicator based on the business indicator corresponding to the business data, as the business weight corresponding to the business data, and uses the business weight corresponding to the business data as the business weight corresponding to the preprocessed business data; then, the server determines the business data sequence of each object to be analyzed based on the preprocessed business data and the business weight corresponding to the preprocessed business data; for example, the server constructs an initial business data sequence based on the preprocessed business data, and fuses the initial business data sequence with the business weight to obtain the business data sequence of each object to be analyzed.

[0204] In this embodiment, the business data is preprocessed to obtain preprocessed business data, which is beneficial to improving the data quality of the business data; moreover, the business data sequence of each object to be analyzed is determined based on the preprocessed business data and the business weight corresponding to the preprocessed business data. This is equivalent to more accurately determining the business data sequence of each object to be analyzed based on the importance of the business indicators, which is beneficial to improving the accuracy of determining the business data sequence of each object to be analyzed.

[0205] In an exemplary embodiment, Figure 7 As shown, another task allocation method is provided, which is described by taking the application of this method to a server as an example, and includes the following steps:

[0206] Step S701, obtain the business data of each object to be analyzed under each business indicator; preprocess the business data to obtain preprocessed business data; determine the business weight corresponding to the business data according to the business indicator corresponding to the business data, as the business weight corresponding to the preprocessed business data; determine the business data sequence of each object to be analyzed according to the preprocessed business data and the business weight corresponding to the preprocessed business data.

[0207] Step S702: Determine a first target business data sequence and a second target business data sequence based on each business data sequence; each business data sequence includes the business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each business data sequence, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each business data sequence.

[0208] Step S703 : determining a first Euclidean distance between each service data sequence and the first target service data sequence and a second Euclidean distance between each service data sequence and the second target service data sequence.

[0209] Step S704 : obtaining a first grey relational matrix between each business data sequence and the first target business data sequence, and a second grey relational matrix between each business data sequence and the second target business data sequence.

[0210] Step S705 , determining a first grey correlation degree between each business data sequence and the first target business data sequence according to the first grey correlation matrix, and determining a second grey correlation degree between each business data sequence and the second target business data sequence according to the second grey correlation matrix.

[0211] Step S706: For each business data sequence, the first Euclidean distance, the second Euclidean distance, the first grey correlation degree and the second grey correlation degree are converted to obtain the converted first Euclidean distance, the converted second Euclidean distance, the converted first grey correlation degree and the converted second grey correlation degree.

[0212] Step S707, obtain the first weight and the second weight; the sum of the first weight and the second weight is 1; according to the first weight and the second weight, the converted second Euclidean distance and the converted first gray correlation degree are fused to obtain the first closeness between each business data sequence and the first target business data sequence; according to the first weight and the second weight, the converted first Euclidean distance and the converted second gray correlation degree are fused to obtain the first distance between each business data sequence and the first target business data sequence.

[0213] Step S708 : determining a first relative closeness between each service data sequence and the first target service data sequence according to the first closeness and the first distance.

[0214] Step S709 : split each business data sequence according to each business indicator to obtain a sub-business data sequence in each business data sequence.

[0215] Step S710, based on the sub-business data sequence in each business data sequence, determine the corresponding third target business data sequence and fourth target business data sequence; the third target business data sequence is constructed according to the maximum sub-business data in the sub-business data sequence corresponding to the same business indicator, and the fourth target business data sequence is constructed according to the minimum sub-business data in the sub-business data sequence corresponding to the same business indicator.

[0216] Step S711, respectively determine the third Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, the fourth Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence, the third gray correlation between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, and the fourth gray correlation between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence.

[0217] Step S712, based on the fourth Euclidean distance and the third gray correlation degree, determine the second closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, and based on the third Euclidean distance and the fourth gray correlation degree, determine the second distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence.

[0218] Step S713 : determining a second relative closeness between the sub-service data sequence in each service data sequence and the corresponding third target service data sequence according to the second closeness and the second farthest.

[0219] Step S714 : determining the business task processing level of each object to be analyzed according to the first relative closeness and the second relative closeness.

[0220] Step S715 , obtaining business tasks corresponding to the business task processing level of each object to be analyzed; and assigning the business tasks corresponding to the business task processing level of each object to be analyzed to each object to be analyzed.

[0221] In the above-mentioned task assignment method, when performing task assignment, by calculating the Euclidean distance and grey correlation between each business data sequence and the first target business data sequence and the second target business data sequence, it is equivalent to comprehensively analyzing each business data sequence from multiple dimensions, which is beneficial to improving the accuracy of determining the business task processing level of each object to be analyzed; moreover, the business tasks corresponding to the business task processing level of each object to be analyzed are respectively assigned to each object to be analyzed, which is equivalent to assigning matching business tasks according to the business task processing level of each object to be analyzed, which is beneficial to more reasonably assigning business tasks, avoiding the defect that the random assignment method easily leads to a long business task processing time, thereby causing low business task processing efficiency, thereby improving the business task processing efficiency.

[0222] In an exemplary embodiment, in order to more clearly illustrate the task allocation method provided by the embodiment of the present application, the task allocation method is specifically described below using a specific embodiment. In one embodiment, Figure 8 As shown, the present application also provides a bank customer service manager classification and evaluation method based on the TOPSIS (superiority and inferiority solution distance) method of Euclid distance and grey correlation. When performing task assignment, the business data sequence of each object to be analyzed is first obtained, and based on each business data sequence, a first target business data sequence is determined based on the maximum business data under the same business indicator in each business data sequence, and a second target business data sequence is determined based on the minimum business data under the same business indicator in each business data sequence. Then, the first Euclidean distance between each business data sequence and the first target business data sequence, the first target distance between each business data sequence and the first target business data sequence, and the second target distance between each business data sequence and the first target business data sequence are determined respectively. The second Euclidean distance between the second target business data sequences, the first grey correlation between each business data sequence and the first target business data sequence, and the second grey correlation between each business data sequence and the second target business data sequence. Then, for each business data sequence, based on the first Euclidean distance, the second Euclidean distance, the first grey correlation, and the second grey correlation, the business task processing level of each object to be analyzed is determined. Then, the business tasks corresponding to the business task processing level of each object to be analyzed are obtained. Finally, the business tasks corresponding to the business task processing level of each object to be analyzed are respectively assigned to each object to be analyzed, thereby improving the business task processing efficiency. Specifically, it includes the following contents:

[0223] 1. Data collection and organization: Collect information data from branch customer service managers at various levels, such as customer evaluations, sales data, training records, etc., and organize them into an analyzable form.

[0224] By collecting information data from branch customer service managers at various levels of criteria, such as customer evaluations, sales data, training records, etc., the information data is captured once every quarter and an evaluation is conducted every quarter.

[0225] The formally determined customer service manager performance appraisal and evaluation index system has formed a systematic index system with clear hierarchy, condensed the actual situation of the outlets, and possessed a certain degree of objectivity and scientificity. It aims to distinguish it from the initial evaluation indicators at the theoretical level, and named the indicator symbols. The index system can be decomposed into several specific indicators according to the four aspects of service quality, marketing performance, learning and development, and risk control, and the assessment is listed separately according to basic indicators and auxiliary indicators.

[0226] (1) Service quality indicators

[0227] This category analyzes customers' evaluation of the quality of bank services. By evaluating customer satisfaction indicators, banks can understand customer needs, improve service quality, and provide a better customer experience. It includes the following three categories:

[0228] Customer satisfaction: This can be reflected in aspects such as service attitude, response speed, and problem solving. This indicator is mainly reflected in the system evaluation given by customers on the electronic operation screen after the business is completed.

[0229] Customer complaint rate: Banks can count the number of customer complaints. The complaint rate can be the ratio of the number of customer complaints to the total amount of bank business.

[0230] Business handling efficiency: The customer service manager's evaluation of the speed and efficiency of business handling, including processing time, processing procedures, etc.

[0231] (2) Marketing performance indicators

[0232] This type of indicator analyzes the performance of customer service managers in terms of business volume, deposit growth, etc., and measures their contribution to the bank's profits and business development, as this can help banks increase their market share and customer base, and promote business development and growth.

[0233] Specific indicators include the total business volume of the quarter, the success rate of fund, insurance and wealth management product recommendations (customer service managers can recommend customers who are interested in purchasing fund and factoring products to account managers, and the final result is based on the success of the recommendation), the total amount of deposits, the number of precious metals, specialty cards, credit cards and messengers processed, the number of bound cards, and the number of mobile banking accounts opened.

[0234] (3) Learning and development indicators

[0235] This type of indicator can help banks evaluate the learning and development capabilities of customer service managers, thereby improving their overall quality and work ability and promoting the bank's business development. It includes the following three categories:

[0236] Number of times attended industry activities: for example, the number of times a customer service manager has participated in special lectures, meetings, publicity activities, etc. within the industry.

[0237] Training Completion Rate: This evaluates the completion rate of customer service managers' training courses, including the ratio of the number of training courses attended to the total number of training courses. This can be assessed through training records and training completion status.

[0238] Qualification Certificate: Mainly depends on the number of qualification certificates obtained by the customer service manager.

[0239] (4) Risk control indicators

[0240] Assess customer service managers' risk control awareness and capabilities during business operations to ensure the security and compliance of banking services. This includes the following three categories:

[0241] Risk Awareness: Assess the customer service manager's awareness and understanding of risk, including their ability to identify and assess risks. This can be assessed through risk identification records and risk assessment reports.

[0242] Risk Control Capabilities: This evaluates the risk control measures implemented by the customer service manager during the business process, including the customer service manager's risk isolation and business modifications. This can be assessed through risk control measure records and risk control approvals.

[0243] Risk operation events: mainly the number of Class I, Class II, and Class III risk events triggered by customer service managers when operating business.

[0244] 2. Data preprocessing: Perform data preprocessing on the acquired raw data.

[0245] Data preprocessing is an important step in data analysis and machine learning tasks, which is used to clean, transform, and prepare raw data to ensure data quality and adaptability.

[0246] Data preprocessing requires missing value processing, outlier processing, data cleaning, and data conversion.

[0247] Missing Value Handling: Check for missing values ​​in the data and decide how to handle them. You can delete data points with missing values ​​or use interpolation to fill in the missing values.

[0248] Outlier handling: Detect and handle outliers. Statistical methods (such as standard deviation or boxplots) can be used to identify outliers and handle them appropriately, such as removing, replacing, or adjusting them.

[0249] Data cleaning: Checks and cleans data for errors, duplicates, or inconsistent entries. Data validation and correction can be performed to ensure consistency and accuracy.

[0250] Data conversion: After the data processing in the above steps, a decision matrix is ​​formed , let the set of participants in the evaluation (branch customer service managers) be , the indicator set is , the evaluated object For indicators The value of .

[0251] In order to eliminate the difference in dimensions, the indicators should be processed positively and normalized to form a standardized matrix: , only then can subsequent analysis be carried out to obtain the standardized values ​​of various performance evaluation indicators of customers.

[0252] In this invention, the customer complaint rate (a2) and risky operational events (d3) are negative indicators. Therefore, they need to be positively processed, that is, the two negative indicators are converted into positive indicators. The following formula is used for the conversion: , where is the maximum value of the jth indicator (for example, the customer complaint rate of a customer service manager is 70% (the higher the customer complaint rate, the worse the service quality), and the maximum customer complaint rate of the customer service manager is 90%), we can convert it into: =90% - 70% = 20%. In this way, we have converted the negative indicator customer complaint rate (a2) into a positive indicator. In addition, normalization is required. In the study of comprehensive evaluation problems, the units and dimensions of the indicators corresponding to the customer service manager performance appraisal will affect the final results. Therefore, we need to standardize the indicators and construct a standardized matrix: , thus obtaining the standardized values ​​of each performance evaluation indicator of the customer. Multiply the standardized value by 100 to obtain an indicator value between 0 and 100.

[0253] 3. Comprehensive calculation: Improve the traditional TOPSIS method and construct a performance appraisal method for customer service managers. Use the TOPSIS method based on Euclid distance and grey correlation to conduct comprehensive and classified evaluations of branch customer service managers, and compare the differences between the rankings at each criterion level and the comprehensive rankings.

[0254] This paper combines the TOPSIS method with the grey correlation method, replacing the traditional Euclidean distance with grey correlation and Euclidean distance. These methods, which reflect the proximity of alternatives to the ideal solution based on shape and positional similarity, respectively, are combined to construct a new relative closeness. The improved TOPSIS method comprehensively considers multiple evaluation metrics and does not require a linear relationship between them, making it more flexible and applicable. It determines the best option or optimal solution by calculating the proximity of each option to the best and worst solutions. This method not only handles nonlinear relationships but also copes with small or uneven data volumes.

[0255] Therefore, the TOPSIS method based on Euclid distance and grey correlation can objectively evaluate the comprehensive performance of branch customer service managers and the subsystem performance at the four scoring criteria levels by calculating the degree of proximity and the sum. It can also identify the strengths and weaknesses of customer service managers under different indicators, providing banks with more effective decision-making basis and improvement directions. The specific steps are as follows:

[0256] (1) Weight coefficient of confirmation.

[0257] The determination of weight coefficient plays a very important role in the objectivity and accuracy of the comprehensive evaluation results. In this paper, based on the situation of customer service managers at bank branches, the weight coefficient can be calculated by combining optimization of methods such as the Delphi method, the hierarchical analysis method, or the entropy method. In actual application, each branch may make necessary adjustments to the indicators and their weights based on the bank's own type, policies, and assessment priorities.

[0258] (2) Original decision matrix After data preprocessing, the standardized matrix is ​​obtained: , the indicator set is , there are m indicators, and the weight coefficients correspond to , then calculate the weighted normalization matrix .

[0259]

[0260] (3) Determine the optimal and worst reference sequences for customer service manager performance evaluation indicators , The best and worst reference sequences are selected based on the specific data. The best sequence is when each indicator obtains the best (largest) value of the evaluation indicator in the system, and the worst sequence is when each indicator obtains the worst (smallest) value of the evaluation indicator in the system. Because there are m indicators, each indicator column has a maximum and minimum value, for example It is the maximum value corresponding to the first column of data.

[0261]

[0262]

[0263] (4) Calculate the Euclid distance of each solution to the optimal reference sequence and the worst reference sequence.

[0264]

[0265] (5) Calculate the grey correlation coefficient matrix between each scheme and the optimal reference sequence and the worst reference sequence .

[0266]

[0267] (6) Calculate the grey correlation between each scheme and the optimal reference sequence and the worst reference sequence.

[0268]

[0269] (7) The Euclid distance and grey relational degree are dimensionless.

[0270]

[0271] (8) Combine the dimensionless distance and correlation determined above.

[0272] because and The larger the value, the closer the solution is to the optimal reference sequence, and and The larger the value, the further the solution is from the optimal reference sequence. Therefore, the merging formula can be determined as:

[0273]

[0274] in, and reflects the decision maker's preference for location and shape, and satisfies . Decision makers can determine their values ​​according to their preferences. It comprehensively reflects the closeness between the scheme sequence and the optimal reference sequence. The larger the value, the better the scheme. It reflects the degree of deviation between the solution and the ideal solution. The larger the value, the worse the solution.

[0275] (9) Calculate the relative closeness of the solutions.

[0276]

[0277] The new closeness is based on Euclidean distance and grey relational degree, and reflects the positional relationship between the solution sequence and the optimal reference sequence and the worst reference sequence, as well as the similarity difference of the data curves. Its physical meaning is clearer.

[0278] The plans (customer service managers) are sorted according to the relative closeness. The greater the closeness, the better the plan (customer service manager) performs. Conversely, the smaller the closeness, the weaker the plan (customer service manager) performs.

[0279] After comprehensively evaluating the four scoring criteria of bank branch customer service managers' service quality, marketing performance, learning and development, and risk control, the calculation process of the comprehensive evaluation is as described above, and an overall comprehensive ranking is obtained to understand one's overall level and ability in comprehensive work.

[0280] Branch customer service managers are then evaluated separately across the four scoring criteria, using the same categorical evaluation methodology as previously described. This yields performance evaluation scores and rankings for each customer service manager across the four different criteria. This allows us to explore the specific drivers of each customer service manager's overall performance ranking and identify areas of individual weakness. This helps individuals clearly identify their shortcomings and prioritize improvements and enhancements. Overall, this provides a comprehensive understanding of individual performance and capabilities across various dimensions, enabling the goal of continuously improving performance and work quality through personalized development opportunities and support. This helps banks achieve higher customer satisfaction and business results.

[0281] Here we can obtain the overall performance (with progress) of the branch customer service manager and the performance of the service quality subsystem, marketing performance subsystem, learning and development subsystem, and risk control subsystem.

[0282] 4. Data analysis and visualization: Using visualization tools to visualize the scoring results can help you understand the differences between various dimensions more intuitively.

[0283] After categorizing and evaluating branch customer service managers across four scoring criteria, a ranking was ultimately determined. Combining these rankings, a radar chart was used to visualize the branch customer service manager's performance rankings across four dimensions: service quality, marketing performance, learning and development, and risk control. This assessment assesses individual performance across these dimensions, with the radar chart highlighting each manager's ranking based on the categorized evaluation.

[0284] Through data analysis and visual radar charts, you can more intuitively understand the differences between various dimensions, find your personal weaknesses and areas that need improvement, and also identify your areas of strength, further develop your strengths, and find a suitable position for yourself.

[0285] If there are multiple customer service managers, all customer service managers can be ranked comprehensively first, and then grouped according to the ranking order, with every 5 customer service managers forming a group, until the last ranked person is assigned. After the groups are divided, the customer service managers in each group will be evaluated according to the four subsystem dimensions. Finally, by visually displaying the evaluation results, you can intuitively compare and view the ranking of each customer service manager in different subsystems, and you can also show your overall performance from the side through the performance in each dimension.

[0286] In the above embodiment, when performing task assignment, by calculating the Euclidean distance and gray correlation between each business data sequence and the first target business data sequence and the second target business data sequence, it is equivalent to performing a comprehensive analysis of each business data sequence from multiple dimensions, which is conducive to improving the accuracy of determining the business task processing level of each object to be analyzed; moreover, the business tasks corresponding to the business task processing level of each object to be analyzed are respectively assigned to each object to be analyzed, which is equivalent to assigning matching business tasks according to the business task processing level of each object to be analyzed, which is conducive to more reasonable allocation of business tasks, avoiding the defects of using a random assignment method that easily leads to long business task processing time and thus low business task processing efficiency, thereby improving business task processing efficiency. At the same time, this solution combines the actual situation of the branch and introduces the original data information of the branch customer service manager in four aspects: service quality, marketing performance, learning and development, and risk control, and conducts comprehensive and classified evaluation through performance appraisal evaluation methods. First, comprehensive evaluation can comprehensively assess the work performance of customer service managers from multiple dimensions, not just focusing on one criterion or indicator, thereby gaining a more comprehensive understanding of the quality and effectiveness of their work. It can also compare the performance of customer service managers with that of other colleagues, stimulate competition and enthusiasm, and promote the improvement of the overall performance of the team. Moreover, comprehensive evaluation can provide objective and fair evaluation results, reduce the influence of subjective factors, and ensure the fairness of the evaluation. Through comprehensive evaluation, banks can understand the performance levels of different customer service managers and identify areas with poor overall business performance, thereby providing targeted training, improvement and support to improve the overall business level, which will help banks achieve higher customer satisfaction and business results. Secondly, categorized evaluation, by evaluating and ranking each criterion, can more accurately assess customer service managers' performance and capabilities across different dimensions, providing a more detailed and comprehensive understanding—a more objective measurement method. By ranking and evaluating customer service managers across different criterion levels, they can gain a more comprehensive understanding of their performance across different dimensions. This helps identify individual strengths, further develop and leverage them, and share experiences and best practices, promoting both individual and team learning and growth. This helps improve overall team performance and synergy, while also identifying weaknesses and identifying areas for improvement. Banks can also better manage and monitor the performance of customer service managers, providing a basis for employee career development and personalized training, and enabling banks to more precisely identify and address performance issues. Furthermore, by visually displaying the evaluation results, bank management, decision makers, and other relevant personnel can clearly understand and compare the comprehensive evaluation and categorization levels of different customer service managers. This visual display can help decision makers make decisions and adjustments more quickly and accurately. Furthermore, traditional comprehensive evaluation methods, such as weighted average or pairwise comparison, typically assume a linear relationship between evaluation indicators and require the data to follow a specific distribution pattern.However, in reality, the relationships between evaluation indicators may be nonlinear, and data may not follow a specific distribution pattern. Therefore, this solution addresses the shortcomings of the traditional TOPSIS method and proposes replacing it with grey correlation and Euclidean distance. This approach, based on Euclid distance and grey correlation, offers greater flexibility and applicability. In summary, this method enables objective evaluation of the overall performance of branch customer service managers and the performance of subsystems across the four scoring criteria.

[0287] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed 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 portion of steps or stages in other steps.

[0288] Based on the same inventive concept, embodiments of the present application also provide a task allocation device for implementing the aforementioned task allocation method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations in one or more of the following embodiments of the task allocation device can be found in the above-mentioned limitations on the task allocation method and will not be further elaborated here.

[0289] In an exemplary embodiment, Figure 9 As shown, a task assignment device is provided, comprising: a sequence determination module 901, an information determination module 902, a level determination module 903, a task acquisition module 904 and a task assignment module 905, wherein:

[0290] The sequence determination module 901 is used to obtain the business data sequence of each object to be analyzed, and determine the first target business data sequence and the second target business data sequence based on each business data sequence; each business data sequence includes the business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each business data sequence, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each business data sequence.

[0291] The information determination module 902 is used to respectively determine the first Euclidean distance between each business data sequence and the first target business data sequence, the second Euclidean distance between each business data sequence and the second target business data sequence, the first grey correlation degree between each business data sequence and the first target business data sequence, and the second grey correlation degree between each business data sequence and the second target business data sequence.

[0292] The level determination module 903 is used to determine the business task processing level of each object to be analyzed based on the first Euclidean distance, the second Euclidean distance, the first grey correlation degree and the second grey correlation degree for each business data sequence.

[0293] The task acquisition module 904 is used to acquire the business tasks corresponding to the business task processing level of each object to be analyzed.

[0294] The task assignment module 905 is used to assign business tasks corresponding to the business task processing level of each object to be analyzed to each object to be analyzed.

[0295] In an exemplary embodiment, the level determination module 903 is also used to convert the first Euclidean distance, the second Euclidean distance, the first gray correlation degree and the second gray correlation degree for each business data sequence to obtain the converted first Euclidean distance, the converted second Euclidean distance, the converted first gray correlation degree and the converted second gray correlation degree; determine the first closeness between each business data sequence and the first target business data sequence based on the converted second Euclidean distance and the converted first gray correlation degree, and determine the first distance between each business data sequence and the first target business data sequence based on the converted first Euclidean distance and the converted second gray correlation degree; determine the first relative closeness between each business data sequence and the first target business data sequence based on the first closeness and the first distance; and determine the business task processing level of each object to be analyzed based on the first relative closeness.

[0296] In an exemplary embodiment, the level determination module 903 is also used to obtain a first weight and a second weight; the sum of the first weight and the second weight is 1; according to the first weight and the second weight, the converted second Euclidean distance and the converted first gray correlation degree are fused to obtain the first closeness between each business data sequence and the first target business data sequence; according to the first weight and the second weight, the converted first Euclidean distance and the converted second gray correlation degree are fused to obtain the first distance between each business data sequence and the first target business data sequence.

[0297] In an exemplary embodiment, the level determination module 903 is also used to determine the second closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence based on the fourth Euclidean distance and the third gray correlation degree, and to determine the second farthest between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence based on the third Euclidean distance and the fourth gray correlation degree; determine the second relative closeness between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence based on the second closeness and the second farthest; the third Euclidean distance, the fourth Euclidean distance, the third gray correlation degree and the fourth gray correlation degree are obtained based on the sub-business data sequence in each business data sequence and the corresponding third target business data sequence and the fourth target business data sequence.

[0298] In an exemplary embodiment, the level determination module 903 is further configured to determine the business task processing level of each object to be analyzed according to the first relative closeness and the second relative closeness.

[0299] In an exemplary embodiment, the level determination module 903 is also used to split each business data sequence according to each business indicator to obtain a sub-business data sequence in each business data sequence; determine the corresponding third target business data sequence and fourth target business data sequence based on the sub-business data sequence in each business data sequence; the third target business data sequence is constructed according to the maximum sub-business data in the sub-business data sequence corresponding to the same business indicator, and the fourth target business data sequence is constructed according to the minimum sub-business data in the sub-business data sequence corresponding to the same business indicator; respectively determine the third Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, the fourth Euclidean distance between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence, the third gray correlation between the sub-business data sequence in each business data sequence and the corresponding third target business data sequence, and the fourth gray correlation between the sub-business data sequence in each business data sequence and the corresponding fourth target business data sequence.

[0300] In an exemplary embodiment, the information determination module 902 is also used to obtain a first grey correlation matrix between each business data sequence and the first target business data sequence, and a second grey correlation matrix between each business data sequence and the second target business data sequence; determine the first grey correlation degree between each business data sequence and the first target business data sequence based on the first grey correlation matrix, and determine the second grey correlation degree between each business data sequence and the second target business data sequence based on the second grey correlation matrix.

[0301] In an exemplary embodiment, the sequence determination module 901 is also used to obtain business data of each object to be analyzed under each business indicator; preprocess the business data to obtain preprocessed business data; determine the business weight corresponding to the business data according to the business indicator corresponding to the business data, as the business weight corresponding to the preprocessed business data; determine the business data sequence of each object to be analyzed according to the preprocessed business data and the business weight corresponding to the preprocessed business data.

[0302] Each module in the task allocation device can be implemented in whole or in part through 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 the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0303] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 computer program in the non-volatile storage medium. The database of the computer device is used to store data such as business data sequences, Euclidean distance and gray correlation degree. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a task allocation method is implemented.

[0304] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the 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 component arrangement.

[0305] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0306] In an exemplary 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.

[0307] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0308] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. 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 above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0309] The technical features of the above embodiments can 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.

[0310] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A task allocation method, characterized in that: The method comprises: Obtaining a business data sequence for each object to be analyzed, and determining a first target business data sequence and a second target business data sequence based on each of the business data sequences; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences; respectively determining a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence; For each of the business data sequences, determining a business task processing level of each of the objects to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree; Acquire business tasks corresponding to the business task processing levels of the objects to be analyzed; Business tasks corresponding to the business task processing levels of the objects to be analyzed are respectively allocated to the objects to be analyzed.

2. The method according to claim 1, characterized in that The determining, for each of the business data sequences, the business task processing level of each of the objects to be analyzed according to the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree, includes: For each of the business data sequences, converting the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree to obtain a converted first Euclidean distance, a converted second Euclidean distance, a converted first grey relational degree, and a converted second grey relational degree; determining a first closeness between each of the business data sequences and the first target business data sequence based on the converted second Euclidean distance and the converted first grey relational degree, and determining a first distance between each of the business data sequences and the first target business data sequence based on the converted first Euclidean distance and the converted second grey relational degree; determining a first relative closeness between each of the service data sequences and the first target service data sequence according to the first closeness and the first farthest; The business task processing level of each of the objects to be analyzed is determined according to the first relative closeness.

3. The method according to claim 2, characterized in that The determining of a first closeness between each of the business data sequences and the first target business data sequence based on the converted second Euclidean distance and the converted first grey relational degree, and the determining of a first distance between each of the business data sequences and the first target business data sequence based on the converted first Euclidean distance and the converted second grey relational degree, includes: Obtain a first weight and a second weight; the sum of the first weight and the second weight is 1; fusing the converted second Euclidean distance and the converted first grey relational degree according to the first weight and the second weight to obtain a first closeness between each of the business data sequences and the first target business data sequence; According to the first weight and the second weight, the converted first Euclidean distance and the converted second grey relational degree are fused to obtain a first distance between each of the business data sequences and the first target business data sequence.

4. The method according to claim 2, characterized in that Before determining the business task processing level of each of the objects to be analyzed according to the first relative closeness, the method further includes: Determine, based on the fourth Euclidean distance and the third grey relational degree, a second closeness between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence, and determine, based on the third Euclidean distance and the fourth grey relational degree, a second distance between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence; determining, based on the second closeness and the second farthestness, a second relative closeness between a sub-business data sequence in each of the business data sequences and a corresponding third target business data sequence; the third Euclidean distance, the fourth Euclidean distance, the third grey relational degree, and the fourth grey relational degree are obtained based on the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence and fourth target business data sequence; Determining the business task processing level of each object to be analyzed based on the first relative closeness includes: The business task processing level of each of the objects to be analyzed is determined according to the first relative closeness and the second relative closeness.

5. The method according to claim 4, characterized in that Before determining the second closeness between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence based on the fourth Euclidean distance and the third grey relational degree, and determining the second distance between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence based on the third Euclidean distance and the fourth grey relational degree, the method further includes: Splitting each of the business data sequences according to the business indicators to obtain sub-business data sequences in each of the business data sequences; Determine, based on the sub-business data sequences in each of the business data sequences, a corresponding third target business data sequence and a fourth target business data sequence; the third target business data sequence is constructed based on the maximum sub-business data in the sub-business data sequences corresponding to the same business indicator, and the fourth target business data sequence is constructed based on the minimum sub-business data in the sub-business data sequences corresponding to the same business indicator; Determine respectively the third Euclidean distance between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence, the fourth Euclidean distance between the sub-business data sequence in each of the business data sequences and the corresponding fourth target business data sequence, the third gray correlation between the sub-business data sequence in each of the business data sequences and the corresponding third target business data sequence, and the fourth gray correlation between the sub-business data sequence in each of the business data sequences and the corresponding fourth target business data sequence.

6. The method according to claim 1, characterized in that The first grey relational degree and the second grey relational degree are obtained by: Obtaining a first grey correlation matrix between each of the business data sequences and the first target business data sequence, and a second grey correlation matrix between each of the business data sequences and the second target business data sequence; According to the first grey correlation matrix, a first grey correlation degree between each of the business data sequences and the first target business data sequence is determined, and according to the second grey correlation matrix, a second grey correlation degree between each of the business data sequences and the second target business data sequence is determined.

7. The method according to any one of claims 1 to 6, characterized in that The step of obtaining the business data sequence of each object to be analyzed includes: Obtaining business data of each object to be analyzed under each business indicator; Preprocessing the business data to obtain preprocessed business data; Determining, according to the business indicator corresponding to the business data, a business weight corresponding to the business data as the business weight corresponding to the preprocessed business data; The business data sequence of each object to be analyzed is determined according to the pre-processed business data and the business weight corresponding to the pre-processed business data.

8. A task allocation device, characterized in that: The device comprises: A sequence determination module is configured to obtain a business data sequence for each object to be analyzed and, based on each of the business data sequences, determine a first target business data sequence and a second target business data sequence; each business data sequence includes business data of the corresponding object to be analyzed under each business indicator; the first target business data sequence is constructed based on the maximum business data under the same business indicator in each of the business data sequences, and the second target business data sequence is constructed based on the minimum business data under the same business indicator in each of the business data sequences; an information determination module, configured to respectively determine a first Euclidean distance between each of the business data sequences and the first target business data sequence, a second Euclidean distance between each of the business data sequences and the second target business data sequence, a first grey correlation degree between each of the business data sequences and the first target business data sequence, and a second grey correlation degree between each of the business data sequences and the second target business data sequence; a level determination module, configured to determine, for each of the business data sequences, a business task processing level of each of the objects to be analyzed based on the first Euclidean distance, the second Euclidean distance, the first grey relational degree, and the second grey relational degree; A task acquisition module, configured to acquire business tasks corresponding to the business task processing level of each object to be analyzed; The task allocation module is used to allocate business tasks corresponding to the business task processing level of each object to be analyzed to each object to be analyzed.

9. 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 7 are implemented.

10. 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 7 are implemented.

11. 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 7 are implemented.

Images