Object auditing task allocation method and device, equipment, storage medium and program product

Abstract

The invention relates to an object auditing task allocation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining statistical information of a to-be-audited object to determine a priority of the to-be-audited object; according to the priority, sequentially caching auditing tasks corresponding to the to-be-audited object to a to-be-allocated task sequence; obtaining auditor information to determine a working coefficient corresponding to each auditor; based on the historical auditing quantity corresponding to each auditing person, determining a corresponding auditing quantity change coefficient; determining a corresponding auditing task number based on the working coefficient corresponding to each auditing person, the auditing amount change coefficient and the total number of the to-be-audited objects; and based on the preference weights for different object categories, allocating the auditing tasks in the to-be-allocated task sequence to each auditing person until the number of the auditing tasks is reached. According to the method, the object auditing task allocation accuracy and efficiency and the object auditing task processing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for allocating object audit tasks. Background Art

[0002] Currently, the allocation of object review tasks is usually done manually, that is, selecting objects one by one and manually assigning reviewers. When the number of object submissions on the platform increases, the corresponding manpower and time costs will increase, and the accuracy of the allocation varies from person to person. Based on this, how to improve the efficiency and accuracy of the current object review task allocation is a problem that needs to be solved. Summary of the invention

[0003] Based on this, it is necessary to provide an object audit task allocation method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0004] In a first aspect, the present application provides a method for allocating object audit tasks, comprising:

[0005] Based on the periodic analysis of the content uploaded by users in the review system, obtain the statistical information of the objects to be reviewed, and determine the priority of the objects to be reviewed based on the statistical information; the statistical information includes the waiting time for review, the object category and the review rejection information;

[0006] According to the priority, the audit tasks corresponding to the audited objects are cached in sequence to the task sequence to be assigned;

[0007] Based on the audit record information corresponding to the audited object in the audit system, the auditor information is obtained, and based on the auditor information, the work coefficient corresponding to each auditor is determined; the auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor;

[0008] Based on the historical audit quantity corresponding to each auditor in multiple historical preset periods, determine the audit quantity change coefficient corresponding to each auditor;

[0009] Determine the number of audit tasks corresponding to each auditor based on the corresponding work coefficient of each auditor, the audit volume change coefficient and the total number of objects to be audited;

[0010] Based on the preference weights for different object categories, the audit tasks in the task sequence to be assigned are assigned to each auditor in turn until the number of audit tasks is reached.

[0011] In one embodiment, determining the priority of the object to be reviewed based on the statistical information includes:

[0012] Based on the waiting time for review, the corresponding time weight is determined from the preset time weight table; wherein the waiting time for review is positively correlated with the time weight;

[0013] Based on the object category, determine the corresponding category weight from a preset category weight table;

[0014] Based on the review rejection information, determine the corresponding reexamination weight from the preset reexamination weight table;

[0015] Determine the priority of the objects to be reviewed based on the time weight, review weight and category weight.

[0016] In one embodiment, based on the review rejection information, the corresponding reconsideration weight is determined from a preset reconsideration weight table, including:

[0017] Determine the corresponding number of rejections based on the review rejection information;

[0018] According to the number of rejections, the corresponding retrial weight is determined from the preset retrial weight table; among them,

[0019] When the number of rejections is less than or equal to the preset first number of rejections, the number of rejections is positively correlated with the reexamination weight;

[0020] When the number of rejections is greater than the first number of rejections, the number of rejections is negatively correlated with the reexamination weight.

[0021] In one embodiment, the number of audit tasks corresponding to each auditor is determined based on the work coefficient corresponding to each auditor, the audit volume variation coefficient, and the total number of objects to be audited, including:

[0022] Based on the work coefficient corresponding to each auditor, the audit volume change coefficient and the total number of objects to be audited, the initial number of audit tasks corresponding to each auditor is determined; the number of historical audits corresponding to at least one historical preset period adjacent to the current preset period is determined as the reference audit number; based on the reference audit number, the initial number of audit tasks is adjusted to obtain the number of audit tasks corresponding to each auditor.

[0023] In one embodiment, based on the auditor information, determining the work coefficient corresponding to each auditor includes:

[0024] Determine the basic work coefficient corresponding to each auditor based on the audit accuracy and audit efficiency;

[0025] Based on the product of the basic work coefficient and the preference weight, the category work coefficient of each auditor corresponding to each object category is determined.

[0026] In one embodiment, determining the audit quantity variation coefficient corresponding to each auditor includes: determining the category audit quantity variation coefficient corresponding to each auditor compared to each object category;

[0027] Based on the work coefficient of each auditor, the audit volume change coefficient and the total number of objects to be audited, determine the number of audit tasks corresponding to each auditor, including:

[0028] According to the total number of objects to be audited, determine the total number of each category corresponding to the objects to be audited;

[0029] Based on the category work coefficient, category audit volume change coefficient and the total number of each category, determine the number of category audit tasks corresponding to each auditor compared to each object category;

[0030] Determine the number of audit tasks for each auditor based on the number of audit tasks by category.

[0031] In a second aspect, the present application also provides an object audit task allocation device, comprising:

[0032] The first determination module is used to obtain statistical information of the objects to be reviewed based on the periodic analysis of the content uploaded by users in the review system, and determine the priority of the objects to be reviewed according to the statistical information; the statistical information includes the waiting review time, the object category and the review rejection information; according to the priority, the review tasks corresponding to the objects to be reviewed are sequentially cached in the task sequence to be assigned;

[0033] The second determination module is used to obtain the auditor information based on the audit record information corresponding to the audited objects in the audit system, and determine the work coefficient corresponding to each auditor based on the auditor information; the auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor; based on the historical audit quantity corresponding to each auditor in multiple historical preset periods, determine the audit quantity change coefficient corresponding to each auditor; based on the work coefficient corresponding to each auditor, the audit quantity change coefficient and the total number of objects to be audited, determine the number of audit tasks corresponding to each auditor;

[0034] The allocation module is used to allocate the audit tasks in the task sequence to be allocated to each auditor in turn based on the preference weights of different object categories until the number of audit tasks is reached.

[0035] 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 the processor implements the steps of the object review task allocation method in the first aspect when executing the computer program.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the object review task assignment method in the first aspect.

[0037] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the object review task allocation method in the first aspect.

[0038] The object audit task allocation method, device, computer equipment, computer readable storage medium and computer program product obtain statistical information of the object to be audited by periodically analyzing the content uploaded by users in the audit system, and determine the priority of the object to be audited according to the statistical information; according to the priority, the audit tasks corresponding to the object to be audited are cached in sequence to the task sequence to be assigned. This sorts and plans the audit tasks to be assigned, thereby facilitating the orderly development of the object audit task allocation, and at the same time, it also helps the audit tasks to be assigned in a timely and accurate manner, thereby facilitating timely audit processing. The number of audit tasks corresponding to each auditor is determined by the work coefficient corresponding to each auditor, the audit volume change coefficient and the total number of objects to be audited, which helps to more accurately determine the number of audit tasks that each auditor can handle, and avoid too many or too few audit tasks. At the same time, according to the preference weights for different object categories, the audit tasks in the task sequence to be assigned are sequentially assigned to each auditor until the number of audit tasks is reached. This can assign the object audit task to the auditor who matches it more highly, that is, improve the accuracy and efficiency of the object audit task allocation, thereby helping to improve the processing efficiency of the object audit task. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A first flow chart of a method for assigning object audit tasks in one embodiment;

[0041] Figure 2 A second flow chart of a method for assigning object audit tasks in one embodiment;

[0042] Figure 3 A third flow chart of a method for assigning object audit tasks in one embodiment;

[0043] Figure 4A fourth flow chart of a method for assigning object audit tasks in one embodiment;

[0044] Figure 5 It is a structural block diagram of an object audit task allocation device in one embodiment;

[0045] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Unless otherwise specified, the "multiple" referred to herein can be understood as two or more than two, and the same applies to the understanding of "multiple times".

[0047] In one embodiment, Figure 1 As shown, a method for assigning object audit tasks is provided. This embodiment uses the method applied to a server as an example. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes steps S101 to S106, which are as follows:

[0048] Step S101: Based on the periodic analysis of the content uploaded by users in the review system, obtain the statistical information of the objects to be reviewed, and determine the priority of the objects to be reviewed based on the statistical information; the statistical information includes the waiting time for review, the object category and the review rejection information.

[0049] The periodic analysis can be performed on a periodic basis of minutes, hours, days, weeks, months, etc. For example, the analysis can be performed every 10 minutes. Due to the uncertainty of the content uploaded by users in the audit system, if real-time analysis is adopted, analysis may be performed even when the user has not uploaded any content, wasting resources. At the same time, periodic analysis can also help obtain more accurate statistical information and avoid obtaining statistical information too frequently, especially when the statistical information does not change much.

[0050] The waiting time for review indicates the time that the object to be reviewed waits for review, which can be understood in a broad sense and can include the time that it takes to wait for re-review after the review is rejected. For example, the waiting time for review can be triggered when the system receives the content uploaded by the user, or when the review is returned to the system after being rejected.

[0051] The object to be reviewed may be one that has not been reviewed yet, or one that has been reviewed once or multiple times but rejected. Accordingly, the review rejection information may represent the review rejection situation of the object to be reviewed. For example, the review rejection information may include the corresponding number and frequency of rejections.

[0052] For example, the priority of the object to be reviewed can be determined through statistical information, that is, the priority order between different objects to be reviewed can be obtained. For example, when the review rejection information indicates that the number of rejections is greater than 10 times, the corresponding priority can be lowered. For another example, when the waiting time for review is greater than the preset waiting time for review, for example, greater than 10 days, the corresponding priority can be increased.

[0053] In some possible embodiments, the priority can be determined according to different object categories. For example, for the same object category, the corresponding priority can be determined as a sub-priority; for different object categories, the corresponding priority can also be determined as a main priority.

[0054] Step S102: according to the priority, the audit tasks corresponding to the objects to be audited are sequentially cached into the task sequence to be assigned.

[0055] The task sequence to be assigned may be cached in a volatile memory such as a memory and / or a non-volatile memory; it may be stored locally or in the cloud, which is not limited here.

[0056] After determining the priority, the corresponding audit tasks can be cached in a sequence according to the priority.

[0057] In some possible embodiments, similar to the aforementioned main or sub-priority, the task sequence to be assigned may also include a main task sequence to be assigned and a sub-task sequence to be assigned, the former corresponding to the priority between different object categories, and the latter corresponding to the priority between the same object category.

[0058] In some possible embodiments, the priority and the sequence of tasks to be assigned may be dynamic. For example, the priority may support manual active adjustment, and when the priority changes, the sequence of tasks to be assigned may be adjusted accordingly to ensure the accuracy of the sequence of tasks to be assigned.

[0059] Step S103: Based on the audit record information corresponding to the audited object in the audit system, obtain the auditor information, and based on the auditor information, determine the work coefficient corresponding to each auditor; the auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor.

[0060] In some possible embodiments, the audit accuracy rate may be determined by the ratio of the number of audit tasks completed accurately by auditors within a certain period to the total number of audit tasks.

[0061] Similarly, the audit efficiency can also be determined by the ratio of the number of audit tasks completed by auditors within a certain period to the target number of audit tasks within that period.

[0062] In some possible embodiments, the number of completed audit tasks, audit accuracy, and audit efficiency of the same auditor compared to each object category can be counted to determine the auditor's preference weight for different object categories. For example, for the same auditor, if the audit accuracy and audit efficiency of object category A are greater than the audit accuracy and audit efficiency of object category B, then the preference weight of object category A is greater than the preference weight of object category B.

[0063] Step S104: Determine the audit quantity variation coefficient corresponding to each auditor based on the historical audit quantity corresponding to each auditor in multiple historical preset periods.

[0064] The historical preset period may be for the past time starting from the current time, for example, the historical preset period may be every month, every half month, etc. in the past time.

[0065] The historical audit quantity may represent the number of audits completed by the auditor in a historical preset period. For example, the number of audits completed last month was 100.

[0066] For example, the audit completion volume of the same category of goods in each month can be counted to determine the number of audits completed by auditors. For example, from January to June, the audit completion volume is 100, 120, 110, 130, 120, and 140, respectively. Then, the fluctuation of the audit completion volume from January to June can be calculated, such as variance, standard deviation, etc., and then different audit volume variation coefficients can be determined for different fluctuations. For example, a relevant table can be pre-built and then determined by looking up the table.

[0067] Step S105: Determine the number of audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit volume variation coefficient, and the total number of objects to be audited.

[0068] After determining the work coefficient and audit volume variation coefficient, the total number of audit objects can be allocated and the number of audit tasks that each auditor needs to complete can be determined.

[0069] In some possible embodiments, the number of audit tasks of different object categories that each auditor needs to complete may be determined based on the classification of the object categories.

[0070] Step S106: Based on the preference weights for different object categories, the audit tasks in the task sequence to be assigned are sequentially assigned to each auditor until the number of audit tasks is reached.

[0071] After determining the number of audit tasks for each auditor, the cached task sequence to be assigned can be extracted and assigned in sequence according to the preference weights of each auditor for different commodity categories. When the number of tasks assigned to an auditor reaches the number of audit tasks determined in the above step, the corresponding auditor will no longer participate in the assignment.

[0072] In some possible embodiments, audit tasks not assigned by the system are not considered assigned audit tasks, that is, they are not counted in the number of audit tasks determined in the above steps. For example, if the auditor actively claims the audit task from the queue.

[0073] In this embodiment, by periodically analyzing the content uploaded by users in the audit system, the statistical information of the object to be audited is obtained, and the priority of the object to be audited is determined according to the statistical information; according to the priority, the audit tasks corresponding to the object to be audited are cached in sequence to the task sequence to be assigned. This sorts and plans the audit tasks to be assigned, thereby facilitating the orderly development of the object audit task assignment, and at the same time, it also helps the audit tasks to be assigned in a timely and accurate manner, thereby facilitating timely audit processing. The number of audit tasks corresponding to each auditor is determined by the work coefficient corresponding to each auditor, the audit volume change coefficient and the total number of objects to be audited, which helps to more accurately determine the number of audit tasks that each auditor can handle, and avoid too many or too few audit tasks. At the same time, according to the preference weights for different object categories, the audit tasks in the task sequence to be assigned are assigned to each auditor in sequence until the number of audit tasks is reached. This can assign the object audit task to the auditor who matches it more highly, that is, improve the accuracy and efficiency of the object audit task assignment, thereby helping to improve the processing efficiency of the object audit task.

[0074] In one embodiment, if Figure 2 As shown, the "determining the priority of the object to be reviewed according to the statistical information" in the above embodiment may include steps S201 to S204:

[0075] Step S201: Based on the waiting time for review, determine the corresponding time weight from a preset time weight table; wherein the waiting time for review is positively correlated with the time weight.

[0076] Exemplarily, a time weight table may be pre-constructed, which may include the waiting time for review and the corresponding time weight. When the waiting time for review is known, the corresponding time weight may be determined by looking up the table.

[0077] Exemplarily, the corresponding waiting time for review can be determined in parallel for multiple objects to be reviewed, thereby determining the corresponding time weights, so that the deadlines for the waiting time for review corresponding to multiple objects to be reviewed can be unified. In fact, the deadlines for the waiting time for review corresponding to different objects to be reviewed can be unified, so that the relative order of the waiting time for review corresponding to different objects to be reviewed can be consistent with the corresponding determination time of different objects to be reviewed. For example, the determination time can be determined based on the upload system time, and the determination time corresponding to the object to be reviewed A is 10 o'clock, and the determination time corresponding to the object to be reviewed B is 11 o'clock. Then, no matter when the deadline is, as long as the deadlines of the objects to be reviewed A and B are the same, such as 12 o'clock, 15 o'clock, etc., then the waiting time for review corresponding to the object to be reviewed B is shorter than the waiting time for review corresponding to the object to be reviewed A.

[0078] In some possible embodiments, the corresponding time weight can be determined according to the relationship between the waiting review times corresponding to different waiting review objects. For example, the longest waiting review time has the largest corresponding time weight, and conversely, the shortest waiting review time has the smallest corresponding time weight.

[0079] Step S202: Based on the object category, determine the corresponding category weight from a preset category weight table.

[0080] Exemplarily, similar to the aforementioned method for determining the time weight, a category weight table may be pre-constructed and the corresponding category weight may be determined by looking up the table based on the object category.

[0081] Step S203: Based on the review rejection information, determine the corresponding reexamination weight from a preset reexamination weight table.

[0082] The object to be reviewed may be one that has not been reviewed yet, or it may be one that has been reviewed once or multiple times but failed the review and was rejected and then resubmitted for review, which can generate corresponding review rejection information.

[0083] For example, a retrial weight table may be pre-constructed according to different rejection times, that is, different rejection times may correspond to different retrial weights.

[0084] For example, similar to the aforementioned method for determining the time weight, a retrial weight table may be constructed in advance, and the corresponding retrial weight may be determined by looking up the table based on the review rejection information.

[0085] Step S204: Determine the priority of the object to be reviewed based on the time weight, review weight and category weight.

[0086] For example, the total weight of the object to be reviewed can be calculated based on the time weight, the review weight, and the category weight, and then the corresponding priority can be determined according to the size of the total weight.

[0087] It should be noted that the order between step S201 and step S204 can be adjusted, and this embodiment is only used for enumeration and explanation, rather than limiting the order. For example, step S201 can be performed before or after step S203, or even both at the same time.

[0088] In this embodiment, the time weight is determined by the waiting time for review, the category weight is determined by the object category, and the reexamination weight is determined by the review rejection information. Then, the priority of the object to be reviewed is determined based on the time weight, reexamination weight and category weight. That is, the priority of the object to be reviewed is comprehensively determined from the three aspects of the waiting time for review, the object category and the review rejection situation, which can make the determined priority more reasonable and accurate, thereby facilitating the accurate allocation and timely and rapid processing of the corresponding review tasks.

[0089] In one embodiment, if Figure 3 As shown, the “determining the corresponding retrial weight from a preset retrial weight table based on the review rejection information” in the aforementioned embodiment may include steps S301 to S302:

[0090] Step S301: Determine the corresponding number of rejections based on the review rejection information.

[0091] Step S302: Determine the corresponding retrial weight from a preset retrial weight table according to the number of rejections; wherein, when the number of rejections is less than or equal to the preset first number of rejections, the number of rejections is positively correlated with the retrial weight; and when the number of rejections is greater than the first number of rejections, the number of rejections is negatively correlated with the retrial weight.

[0092] For example, as mentioned above, the object to be reviewed may not have been reviewed yet, or it may have been reviewed once or more times but failed the review and was rejected and then resubmitted. If the number of rejections reaches a certain number, such as 50 or 100 times, it means that the object may be abnormal. If the corresponding review task is assigned again, there is a high probability that it will still be rejected. Therefore, its corresponding reexamination weight can be reduced, not given priority, or even added to the blacklist. For those whose number of rejections has not reached a certain number, the corresponding review task can be assigned, and as the number of rejections increases, the corresponding reexamination weight can increase.

[0093] In this embodiment, the corresponding reconsideration weight is determined according to the number of rejections. When the number of rejections does not exceed the threshold, that is, the preset first number of rejections, the more rejections there are, the greater the reconsideration weight is. This helps to promptly assign the audit tasks that have been rejected, thereby facilitating the timely processing of the audit tasks; when the number of rejections exceeds the threshold, that is, the preset first number of rejections, the more rejections there are, the smaller the reconsideration weight is. This can deal with the audit tasks corresponding to the same audit object being rejected and re-examined too frequently. This can identify "low-quality" audit tasks with a low probability of passing the audit and a high probability of being rejected. By reducing the corresponding reconsideration weight, "low-quality" audit tasks are not given priority, thereby facilitating the reasonable allocation and rapid processing of the overall audit tasks.

[0094] In one embodiment, if Figure 4 As shown, the "determining the number of audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit volume variation coefficient and the total number of objects to be audited" in the above embodiment may include steps S401 to S403:

[0095] Step S401: Determine the number of initial audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit volume variation coefficient, and the total number of objects to be audited.

[0096] Step S402: Determine the number of historical audits corresponding to at least one historical preset period adjacent to the current preset period as a reference audit number.

[0097] Step S403: Based on the reference audit number, the initial audit task number is adjusted to obtain the audit task number corresponding to each auditor.

[0098] In this embodiment, the initial number of audit tasks corresponding to each auditor can be determined based on the work coefficient, the audit volume variation coefficient and the total number of objects to be audited, and the initial number of audit tasks can be adjusted and corrected based on the number of historical audits corresponding to at least one historical preset period adjacent to the current preset period as a reference audit number, thereby reducing the difference between the determined number of audit tasks and the reference audit number, avoiding excessive differences in the number of audit tasks between adjacent periods, and thus avoiding unreasonable task allocation.

[0099] In one of the embodiments, the "determining the work coefficient corresponding to each auditor based on the auditor information" in the aforementioned embodiment may include: determining the basic work coefficient corresponding to each auditor based on the audit accuracy and audit efficiency; determining the category work coefficient corresponding to each auditor compared to each object category based on the product of the basic work coefficient and the preference weight.

[0100] For example, as described above, there may be a main priority for different object categories, and a sub-priority for the same object category. Similarly, for different object categories, the corresponding category work coefficient of the auditor may be determined.

[0101] In this embodiment, for different object categories, the basic work coefficient corresponding to each auditor is determined by the audit accuracy and audit efficiency, and the corresponding category work coefficient is determined based on the product of the basic work coefficient and the preference weight. This helps to determine the category work coefficient corresponding to the auditor according to the different object categories, thereby helping to more accurately determine the audit task allocation for each auditor.

[0102] In one of the embodiments, determining the audit quantity variation coefficient corresponding to each auditor includes: determining the category audit quantity variation coefficient corresponding to each auditor compared to each object category; determining the number of audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit quantity variation coefficient and the total number of objects to be audited, including: determining the total number of categories corresponding to the objects to be audited based on the total number of objects to be audited; determining the number of category audit tasks corresponding to each auditor compared to each object category based on the category work coefficient, the category audit quantity variation coefficient and the total number of categories; determining the number of audit tasks for each auditor based on the number of category audit tasks.

[0103] In this embodiment, based on the object category, the number of category audit tasks of each auditor is determined compared with the corresponding number of each object category, and then the number of audit tasks of each auditor is determined. This can determine a more accurate number of audit tasks.

[0104] In an exemplary embodiment, a method for assigning object review tasks is provided, which can be applied to an e-commerce system, wherein the object review can include a product review, specifically, a functional scenario in an e-commerce system - the system automatically assigns product reviews, which can be a technical module developed by the e-commerce system to improve the efficiency of product review assignment. The system automatically assigns products to form a technical solution of allocation rule maintenance-audit data collection-allocation sequence calculation-allocation rule execution. The method configures the product allocation task, supports operators to maintain work coefficients and allocation rules, so that the allocation strategy is adjustable and extensible. Operators can set different weights according to the review focus and difficulty of the category, and regularly collect the total number of reviews of the reviewers. After maintaining the allocation strategy, the system automatically dynamically assigns product review tasks according to factors such as the work efficiency of the reviewers, ensuring that the workload of each reviewer is relatively balanced, thereby speeding up the allocation of product review tasks and meeting the platform's requirements for review efficiency. Specifically, the method includes several parts:

[0105] The first part involves the priority and queuing strategy of the products to be reviewed. This part corresponds to "obtaining statistical information of the objects to be reviewed based on the periodic analysis of the content uploaded by users in the review system, and determining the priority of the objects to be reviewed based on the statistical information; the statistical information includes the waiting time for review, the object category, and the review rejection information; based on the priority, the review tasks corresponding to the objects to be reviewed are cached in sequence to the task sequence to be assigned" and other related content. The specific content is as follows:

[0106] To improve the efficiency of the audit, the products to be audited can be pre-processed in the following aspects:

[0107] 1. Classification. Classification can be achieved using a similarity algorithm or a large artificial intelligence model. Based on the existing classification model, you can use the pre-classified data to train it, and then feed a small part of the relevant data of the goods to be classified into the model to obtain the corresponding classification results, and then evaluate the classification results. Here, you can use the loss algorithm to get the corresponding evaluation, and guide, correct, and optimize the model based on the evaluation to improve the accuracy of classification.

[0108] 2. Count the waiting time for review of the products. The products to be reviewed may be the latest uploaded products, or they may have been uploaded some time ago but have not been reviewed yet. Counting the waiting time for review helps to avoid the situation where the waiting time for review of one or more products is too long, that is, to allocate the corresponding review tasks in time and complete the review in time.

[0109] 3. Obtain review rejection information. The products to be reviewed may not have been reviewed yet, or may have been reviewed once or more times but failed the review and were resubmitted after being rejected. If the number of rejections reaches a certain number, such as 10 times, then the corresponding review priority can be reduced, not given priority, or even added to the blacklist, etc. For those that have not been rejected a certain number of times, the corresponding review tasks can be assigned.

[0110] Through the above three aspects, the priority of the goods to be reviewed can be determined, and thus the corresponding sequential queue can be formed, that is, the sequence of tasks to be assigned. There can be multiple queues, for example, a main sequential queue and a sub-sequential queue. The main sequential queue includes the sequential relationship between different product categories, that is, across categories, and the sub-sequential queue includes the sequential relationship within the same product category. The corresponding sequential queue is cached. Here, a database can be built to cache the above queues. A possible calculation method for determining the priority is given below:

[0111] ,

[0112] in:

[0113] P is the priority of the product to be reviewed.

[0114] T is the waiting time for the product to be reviewed.

[0115] W1 is the weight of the category to which the product to be reviewed belongs, that is, the category weight.

[0116] B rejected It is the re-examination weight corresponding to the pending product, which can be determined based on the number or frequency of rejections corresponding to the pending product, for example:

[0117] When the number of rejections is 0, the weight is 1.0; when the number of rejections is 1, the weight is 1.3;

[0118] When the number of rejections is 2, the weight is 1.6; when the number of rejections is 3, the weight is 1.3;

[0119] When the number of rejections is 4, the weight is 1.0; when the number of rejections is 5, the weight is 0.8;

[0120] When the number of rejections is 6, the weight is 0.6, and so on.

[0121] This can ensure that when the application is rejected for the first time or several times, it will be handled first, which helps to handle the review in a timely manner. When there are too many rejections, it means that there may be more serious problems that affect the review, and the processing can be postponed to avoid excessive use of review resources, etc.

[0122] The above about B rejected The weights of can be determined by pre-stating various situations to form a table, and when needed later, it can be determined by looking up the table. The weight values ​​corresponding to T and W1 are similar to this and will not be repeated.

[0123] The weights in the above formula may also be other values ​​and may be adjusted according to actual needs, and there is no restriction here.

[0124] The second part involves determining the number of audit tasks corresponding to each auditor. This part corresponds to "obtaining auditor information based on the audit record information corresponding to the audited objects in the audit system, and determining the work coefficient corresponding to each auditor based on the auditor information; auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor; determining the audit volume change coefficient corresponding to each auditor based on the number of historical audits corresponding to each auditor in multiple historical preset cycles; determining the number of audit tasks corresponding to each auditor based on the work coefficient, audit volume change coefficient and the total number of objects to be audited" and other related content.

[0125] ,

[0126] in:

[0127] j represents different categories of products to be reviewed.

[0128] T is the number of audit tasks assigned to each auditor.

[0129] M1 is the actual number of audit tasks completed each month; M2 is the target number of audit tasks each month. The ratio of the two is the audit efficiency.

[0130] A1 is the number of audit tasks actually completed accurately each month; A2 is the number of audit tasks actually completed each month, including those with accurate audits and those with errors. The ratio of the two is the audit accuracy rate.

[0131] W j It is the reviewer's preference weight for different product categories. The preference weight can also be determined by table lookup, which is the same as the aforementioned table lookup method and will not be repeated here.

[0132] N j It is the number of products to be reviewed corresponding to different categories, that is, the total number of each category.

[0133] n is the total number of auditors.

[0134] Δ lastMonth is the audit task number deviation adjustment value, which can be obtained based on the reference audit number, that is, the number of historical audits corresponding to at least one of the historical preset periods adjacent to the current preset period. For example, if the number of audit tasks last month is 100 and the number of audit tasks the month before is 110, the reference audit numbers can be obtained to include 100 and 110. lastMonth The number of audit tasks for this month calculated by the external audit department is 150, and the corresponding audit task number deviation adjustment value can be 10, that is, 150-10=140. The purpose of the audit task number deviation adjustment value is to reduce the difference between the determined audit task number and the reference audit number, correct the determined audit task number, avoid excessive differences in the number of audit tasks between adjacent periods, and thus avoid unreasonable task allocation.

[0135] V jIt is the coefficient of variation of the auditor's audit volume for different commodity categories, that is, the category audit volume variation coefficient, which can be determined by counting the audit completion volume of the same category of commodities in each month since the auditor took office. For example, from January to June, the audit completion volume is 100, 120, 110, 130, 120, and 140 respectively. Then, the corresponding fluctuation of the audit completion volume from January to June can be calculated, such as variance, standard deviation, etc., and then different audit volume variation coefficients can be determined for different fluctuations. Similar to the aforementioned determination of re-examination weights, time weights, etc., a table related to "fluctuation situation-audit volume variation coefficient" can be constructed, and then determined by looking up the table.

[0136] In some possible embodiments, a profile of each auditor in comparison with the audit tasks of each category of goods can be pre-built, and the corresponding number of audit tasks can be determined and / or adjusted based on the profile. Through big data analysis, a user profile of the auditor's professional field is constructed, and the classification field in which he is good is matched. The historical audit records are counted, and the priority scores of personnel and classification are calculated for the compliance rate and audit timeliness. The relevant calculation formula is as follows:

[0137]

[0138] in:

[0139] S user is the reviewer's rating.

[0140] H history It is the historical performance factor.

[0141] A accuracy It is the audit accuracy rate.

[0142] T efficiency It is the audit efficiency.

[0143] F favoriteCategory is the weighted value of the reviewer's preference category.

[0144] Through this formula, the professionalism and efficiency of each auditor in different categories can be evaluated to better match the tasks.

[0145] The third part involves how to allocate audit tasks. This part corresponds to "based on the preference weights of different object categories, the audit tasks in the task sequence to be allocated are allocated to each auditor in turn until the number of audit tasks is reached" and other related content. The specific content is as follows:

[0146] After determining the number of audit tasks for each auditor, the aforementioned cached queue is extracted for allocation. The logic of allocation has three lines: first, the queue is extracted and allocated in sequence according to the cache order of the queue; second, the extracted commodities to be audited are allocated according to the preference weights of each auditor for different commodity categories, that is, for the category to which the extracted commodities to be audited belong, the corresponding audit task is allocated to the auditor with the largest preference weight corresponding to the category; third, when the number of tasks assigned to the auditor reaches the number of audit tasks determined in the aforementioned steps, the corresponding auditor will no longer participate in the allocation. Of course, an exception mechanism can be established, such as when the auditor actively claims the task from the queue, this limitation does not apply.

[0147] In some possible embodiments, auditors can proactively claim tasks from the queue, and corresponding audit task data will be adjusted accordingly.

[0148] In some possible embodiments, considering the situation that auditors leave and take leave, and the explosive growth of commodity audit data, emergency strategies can be set in advance to reasonably arrange auditors' work tasks to maximize efficiency. If auditors are not on duty, the goods will flow to other auditors, and the efficiency of auditing unfamiliar classification fields will be reduced. Therefore, the system needs to automatically set up a reward mechanism for historical classification audit records, add points for unfamiliar classification fields, and assign auditors in groups to make dynamic adjustments to deal with emergencies.

[0149] In this embodiment, by configuring and automating the allocation of commodity audit tasks, the efficiency of audit task allocation is improved, and the problem of audit progress delays caused by untimely manual allocation of audit tasks is avoided, thereby helping to improve audit efficiency.

[0150] In this embodiment, by determining the priority of the object to be audited, the audit tasks corresponding to the object to be audited are cached in sequence to the sequence of tasks to be assigned. This arranges and plans the audit tasks to be assigned, thereby facilitating the orderly development of the object audit task assignment. At the same time, it also helps the audit tasks to be assigned in a timely and accurate manner, thereby facilitating timely audit processing. The number of audit tasks corresponding to each auditor is determined by the work coefficient corresponding to each auditor, the audit volume variation coefficient, and the total number of objects to be audited. This helps to more accurately determine the number of audit tasks that each auditor can handle, and avoid too many or too few audit tasks. At the same time, according to the preference weights for different object categories, the audit tasks in the sequence of tasks to be assigned are assigned to each auditor in sequence until the number of audit tasks is reached. This can assign the object audit task to the auditor who matches it more highly, that is, improve the accuracy and efficiency of the object audit task assignment, thereby helping to improve the processing efficiency of the object audit task. By determining the corresponding re-examination weight according to the number of rejections, it is helpful to timely assign the audit tasks that have been rejected, and to deal with the audit tasks corresponding to the same audit object being rejected and re-examined too frequently, identify those "low-quality" audit tasks with a low probability of passing the audit and a high probability of being rejected, and by reducing the corresponding re-examination weight, do not give priority to "low-quality" audit tasks, which is helpful for the reasonable allocation and rapid processing of the overall audit tasks. According to the work coefficient, the audit volume change coefficient and the total number of audit objects, the initial audit task number corresponding to each auditor is determined, and the initial audit task number is adjusted according to the reference audit number to reduce the difference between the determined audit task number and the reference audit number, so as to avoid the audit task number between adjacent cycles. Too large a difference can be avoided, thereby avoiding unreasonable task allocation. For different object categories, the corresponding basic work coefficient is determined, and the corresponding category work coefficient, category audit task number, and audit task number are determined according to the product of the basic work coefficient and the preference weight, which helps to more accurately determine the audit task allocation for each auditor.

[0151] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0152] Based on the same inventive concept, the embodiment of the present application also provides an object audit task allocation device for implementing the object audit task allocation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more object audit task allocation device embodiments provided below can refer to the limitations of the object audit task allocation method above, and will not be repeated here.

[0153] In an exemplary embodiment, Figure 5 As shown, a device 500 for allocating object audit tasks is provided, comprising:

[0154] The first determination module 501 is used to obtain statistical information of the objects to be reviewed based on the periodic analysis of the content uploaded by users in the review system, and determine the priority of the objects to be reviewed according to the statistical information; the statistical information includes the waiting review time, the object category and the review rejection information; according to the priority, the review tasks corresponding to the objects to be reviewed are sequentially cached in the task sequence to be assigned;

[0155] The second determination module 502 is used to obtain the information of the auditors based on the audit record information corresponding to the audited objects in the audit system, and determine the work coefficient corresponding to each auditor based on the auditor information; the auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor; based on the historical audit quantity corresponding to each auditor in multiple historical preset periods, determine the audit quantity change coefficient corresponding to each auditor; based on the work coefficient corresponding to each auditor, the audit quantity change coefficient and the total number of objects to be audited, determine the number of audit tasks corresponding to each auditor;

[0156] The allocation module 503 is used to allocate the audit tasks in the to-be-allocated task sequence to each auditor in sequence based on the preference weights of different object categories until the number of audit tasks is reached.

[0157] In one embodiment, the first determination module 501 is also used to determine the priority of the object to be reviewed based on statistical information, including: based on the waiting time for review, determining the corresponding time weight from a preset time weight table; wherein the waiting time for review is positively correlated with the time weight; based on the object category, determining the corresponding category weight from a preset category weight table; based on the review rejection information, determining the corresponding reexamination weight from a preset reexamination weight table; and determining the priority of the object to be reviewed based on the time weight, reexamination weight and category weight.

[0158] In one embodiment, the first determination module 501 is further used to determine the corresponding retrial weight from a preset retrial weight table based on the review rejection information, including: determining the corresponding number of rejections based on the review rejection information; determining the corresponding retrial weight from a preset retrial weight table according to the number of rejections; wherein, when the number of rejections is less than or equal to the preset first number of rejections, the number of rejections is positively correlated with the retrial weight; when the number of rejections is greater than the first number of rejections, the number of rejections is negatively correlated with the retrial weight.

[0159] In one embodiment, the second determination module 502 is also used to determine the number of audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit volume change coefficient and the total number of objects to be audited, including: determining the initial number of audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit volume change coefficient and the total number of objects to be audited; determining the number of historical audits corresponding to at least one historical preset period adjacent to the current preset period as a reference audit number; adjusting the initial audit task number based on the reference audit number to obtain the number of audit tasks corresponding to each auditor.

[0160] In one embodiment, the second determination module 502 is also used to determine the work coefficient corresponding to each auditor based on the auditor information, including: determining the basic work coefficient corresponding to each auditor based on the audit accuracy and audit efficiency; determining the category work coefficient corresponding to each auditor compared to each object category based on the product of the basic work coefficient and the preference weight.

[0161] In one embodiment, the second determination module 502 is also used to determine the audit quantity variation coefficient corresponding to each auditor, including: determining the category audit quantity variation coefficient corresponding to each auditor compared to each object category; determining the number of audit tasks corresponding to each auditor based on the work coefficient corresponding to each auditor, the audit quantity variation coefficient and the total number of objects to be audited, including: determining the total number of categories corresponding to the objects to be audited based on the total number of objects to be audited; determining the number of category audit tasks corresponding to each auditor compared to each object category based on the category work coefficient, the category audit quantity variation coefficient and the total number of categories; determining the number of audit tasks for each auditor based on the number of category audit tasks.

[0162] Each module in the above-mentioned object audit task allocation device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0163] 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 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store data required for executing the object audit task allocation method, such as the aforementioned auditor information. 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, an object audit task allocation method is implemented.

[0164] Those skilled in the art will understand that Figure 6 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0165] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0166] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0167] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0168] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0169] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0170] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for assigning object audit tasks, characterized in that: The method comprises: Based on the periodic analysis of the content uploaded by users in the review system, obtain the statistical information of the objects to be reviewed, and determine the priority of the objects to be reviewed according to the statistical information; the statistical information includes the waiting time for review, the object category and the review rejection information; According to the priority, the audit tasks corresponding to the to-be-audited objects are sequentially cached into a sequence of tasks to be assigned; Based on the audit record information corresponding to the audited object in the audit system, the auditor information is obtained, and based on the auditor information, the work coefficient corresponding to each auditor is determined; the auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor; Determine the audit quantity change coefficient corresponding to each of the auditors based on the historical audit quantity corresponding to each of the auditors in multiple historical preset periods; Determine the number of audit tasks corresponding to each of the auditors based on the work coefficient corresponding to each of the auditors, the audit volume variation coefficient, and the total number of objects to be audited; Based on the preference weights for different object categories, the audit tasks in the to-be-assigned task sequence are sequentially assigned to each of the auditors until the number of audit tasks is reached.

2. The method according to claim 1, characterized in that Determining the priority of the object to be reviewed according to the statistical information includes: Based on the waiting time for review, a corresponding time weight is determined from a preset time weight table; wherein the waiting time for review is positively correlated with the time weight; Based on the object category, determining a corresponding category weight from a preset category weight table; Based on the review rejection information, determine the corresponding reexamination weight from a preset reexamination weight table; The priority of the object to be reviewed is determined according to the time weight, the review weight and the category weight.

3. The method according to claim 2, characterized in that The determining, based on the review rejection information, a corresponding reexamination weight from a preset reexamination weight table includes: Based on the review rejection information, determine the corresponding number of rejections; According to the number of rejections, a corresponding retrial weight is determined from a preset retrial weight table; wherein, When the number of rejections is less than or equal to the preset first number of rejections, the number of rejections is positively correlated with the reexamination weight; When the number of rejections is greater than the first number of rejections, the number of rejections is negatively correlated with the reexamination weight.

4. The method according to claim 1, characterized in that: The determining the number of audit tasks corresponding to each of the auditors based on the work coefficient corresponding to each of the auditors, the audit volume variation coefficient, and the total number of objects to be audited includes: Determine the number of initial audit tasks corresponding to each of the auditors based on the work coefficient corresponding to each of the auditors, the audit volume variation coefficient, and the total number of objects to be audited; Determine the number of historical audits corresponding to at least one of the historical preset periods adjacent to the current preset period as a reference audit number; Based on the reference audit number, the initial audit task number is adjusted to obtain the audit task number corresponding to each auditor.

5. The method according to claim 1, characterized in that The determining of the work coefficient corresponding to each auditor based on the auditor information includes: Based on the audit accuracy and the audit efficiency, determining the basic work coefficient corresponding to each of the auditors; Based on the product of the basic work coefficient and the preference weight, the category work coefficient of each auditor corresponding to each object category is determined.

6. The method according to claim 5, characterized in that The determining of the audit quantity variation coefficient corresponding to each of the auditors includes: determining the category audit quantity variation coefficient corresponding to each of the auditors compared to each category of the object; The determining the number of audit tasks corresponding to each of the auditors based on the work coefficient corresponding to each of the auditors, the audit volume variation coefficient, and the total number of objects to be audited includes: According to the total number of objects to be reviewed, determine the total number of each category corresponding to the objects to be reviewed; Based on the category work coefficient, the category audit volume variation coefficient and the total number of each category, determine the number of category audit tasks corresponding to each audit personnel compared to each object category; The number of audit tasks for each auditor is determined based on the number of audit tasks of the category.

7. A device for allocating object audit tasks, characterized in that: The device comprises: The first determination module is used to obtain statistical information of the objects to be reviewed based on the periodic analysis of the content uploaded by users in the review system, and determine the priority of the objects to be reviewed according to the statistical information; the statistical information includes the waiting review time, the object category and the review rejection information; according to the priority, the review tasks corresponding to the objects to be reviewed are sequentially cached in the task sequence to be assigned; The second determination module is used to obtain the information of the auditors based on the audit record information corresponding to the audited objects in the audit system, and determine the work coefficient corresponding to each auditor based on the auditor information; the auditor information includes the audit accuracy, audit efficiency and preference weights for different object categories of each auditor; based on the number of historical audits corresponding to each auditor in multiple historical preset periods, determine the audit quantity change coefficient corresponding to each auditor; based on the work coefficient corresponding to each auditor, the audit quantity change coefficient and the total number of objects to be audited, determine the number of audit tasks corresponding to each auditor; The allocation module is used to allocate the audit tasks in the to-be-allocated task sequence to each of the audit personnel in sequence based on the preference weights of the different object categories until the number of audit tasks is reached.

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

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

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

Images