A method, device, computer equipment and storage medium for dynamic work dispatching

Through multi-dimensional analysis of dispatched workers and tasks, historical data and target indicators are used to screen, and the best dispatched workers are determined, solving the problems of low efficiency and strong subjectivity in the existing dispatch methods, and achieving efficient and customized The task distribution improves user experience and satisfaction.

CN113344431BActive Publication Date: 2024-11-26CHINA PING AN PROPERTY INSURANCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110723297.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-28
Publication Date
2024-11-26
Estimated Expiration
2041-06-28

AI Technical Summary

Technical Problem

The existing task distribution method is susceptible to human subjective factors, resulting in unreasonable task allocation, which in turn reduces the efficiency of task execution.

Method used

By using the historical dispatched task data of the workers to be dispatched to generate the first feature data set, and using the target indicator data of the current dispatched task to generate the second feature data set, performing multi-level screening and matching to determine the most suitable dispatched workers To improve task distribution efficiency.

Benefits of technology

It realizes the accuracy and intelligence of task distribution, improves the quality and speed of task completion, meets the task requirements of different users, reduces enterprise costs, and improves user satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113344431B_ABST
    Figure CN113344431B_ABST
Patent Text Reader

Abstract

The present invention discloses a method, device, computer equipment and storage medium for dynamic dispatching, wherein the method comprises the following steps: using the historical dispatching task data of the personnel to be dispatched to classify the personnel to be dispatched to generate multiple first feature data sets; extracting task target indicator data from the current dispatching task data, and using the task target indicator data to generate a second feature data set; screening and processing multiple first feature data sets according to the second feature data set, and using at least one first feature data set as a target feature data set; matching the current dispatching task with the personnel to be dispatched in the target feature data set to determine the designated dispatching personnel; and allocating the current dispatching task to the designated dispatching personnel. The present invention uses a big data processing method to perform precise and intelligent dispatching according to the actual situation of the personnel to be dispatched and the dispatching task situation, so as to ensure the high quality and rapid completion of the dispatching task, greatly improving user satisfaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of big data processing technology. More specifically, the present invention can provide a method, device, computer equipment and storage medium for dynamic dispatching. Background Art

[0002] At present, task dispatching often relies on subjective dispatching by the person in charge. This conventional method is not only easily affected by human subjective consciousness and emotions, but also often results in the assigned tasks being unsuitable for the assigned person. For example, the current person has no time to handle the currently assigned task due to other tasks or conditions, which results in low efficiency in task dispatching and affects the timeliness of task processing by the person in charge. Therefore, how to objectively dispatch tasks and improve task execution efficiency has become a technical problem that needs to be solved and a research focus for those skilled in the art. Summary of the invention

[0003] In order to solve the technical problems of low task execution efficiency and excessive subjectivity in conventional task dispatching methods, the present invention can specifically provide a method, device, computer equipment and storage medium for dynamic task dispatching, so as to achieve the technical goals of improving the execution efficiency of dispatched tasks and objectively dispatching tasks.

[0004] To achieve the above technical objectives, the present invention can provide a method for dynamic work dispatching, which may include but is not limited to one or more of the following steps.

[0005] Using historical work task data of the workers to be dispatched, the workers to be dispatched are classified to generate a plurality of first feature data sets;

[0006] Extracting task target indicator data from the acquired current work assignment task data, and generating a second feature data set using the task target indicator data;

[0007] Screening the plurality of first feature data sets according to the second feature data set to select at least one of the first feature data sets as a target feature data set;

[0008] Matching the current work assignment task with the workers to be assigned in the target feature data set to determine the worker to be assigned who has the highest matching degree with the current work assignment task as the designated worker to be assigned;

[0009] The current work dispatching task is assigned to the designated work dispatching personnel so that the current work dispatching task is processed by the designated work dispatching personnel.

[0010] Furthermore, the historical work task data of the workers to be dispatched are used to classify the workers to be dispatched to generate a plurality of first feature data sets, including:

[0011] Forming a plurality of labels based on the historical work assignment data and the data of personnel to be assigned;

[0012] Using the label as a classification basis, all the personnel to be dispatched are divided;

[0013] The first feature data set is formed using the data of personnel to be dispatched belonging to the same category.

[0014] Furthermore, the classification of all the personnel to be dispatched currently using the labels as a classification basis includes:

[0015] Sort all tags according to their impact on the current task;

[0016] Set weight values ​​for each label in the sorting results in turn;

[0017] All the personnel to be dispatched are divided based on the labels and their weight values.

[0018] Furthermore, the dividing of all the personnel to be dispatched based on the labels and their weight values ​​includes:

[0019] Read the indicator values ​​corresponding to each tag;

[0020] Normalizing the indicator values ​​so that different indicator values ​​are mapped to the same numerical range;

[0021] Calculate the final classification value based on the label weight value and the normalized index value;

[0022] Determine the workers to be dispatched who have final classification values ​​within the same set range to be classified in the same category.

[0023] Furthermore, extracting task target indicator data from the acquired current work assignment task data includes:

[0024] Extracting work dispatch note information from the current work dispatch task data;

[0025] Performing content recognition processing on the work dispatch note information based on natural language processing to determine the work dispatch requirement information;

[0026] The current work assignment task data is subjected to data extraction processing according to the work assignment requirement information to obtain task target indicator data.

[0027] Further, the screening process of the plurality of first feature data sets according to the second feature data set includes:

[0028] Calculating a target score value corresponding to the task target indicator data in the second feature data set, wherein the target score value is used to indicate the degree of task requirement;

[0029] The plurality of first feature data sets are screened according to the target score value.

[0030] Furthermore, the allocating the current work assignment to the designated work assignment personnel includes:

[0031] Sending information about the current work assignment to the terminal of the designated work assignee;

[0032] According to the task reception confirmation information fed back by the terminal, task countdown reminder information is sent to the terminal at a preset frequency.

[0033] To achieve the above technical objectives, the present invention can also provide a dynamic work dispatching device, which includes but is not limited to a personnel classification processing module, a task target acquisition module, a data screening processing module, a task personnel matching module and a work dispatching task sending module.

[0034] The personnel classification processing module is used to classify the personnel to be dispatched using their historical work task data to generate a plurality of first feature data sets.

[0035] The task target acquisition module is used to extract task target indicator data from the acquired current work assignment task data, and to generate a second feature data set using the task target indicator data.

[0036] The data screening and processing module is used to screen the plurality of first feature data sets according to the second feature data set, so as to use at least one of the first feature data sets as a target feature data set.

[0037] The task-personnel matching module is used to match the current work assignment task with the personnel to be assigned in the target feature data set to determine the personnel to be assigned who has the highest matching degree with the current work assignment task as the designated person to be assigned.

[0038] The work dispatching task sending module is used to distribute the current work dispatching task to the designated work dispatching personnel so that the current work dispatching task can be processed by the designated work dispatching personnel.

[0039] To achieve the above-mentioned technical objectives, the present invention may provide a computer device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the dynamic dispatching method described in any embodiment of the present invention.

[0040] To achieve the above-mentioned technical objectives, the present invention may also provide a storage medium storing computer-readable instructions, which, when executed by one or more processors, enables the one or more processors to execute the steps of the dynamic dispatching method described in any embodiment of the present invention.

[0041] The beneficial effects of the present invention are:

[0042] The present invention screens the first feature data set formed by the data of the personnel to be dispatched through the second feature data set formed by the task target indicator data, that is, the accurate and intelligent dispatch is performed according to the actual situation of the personnel to be dispatched and the dispatch task situation through the big data processing method. Through the layer-by-layer screening of all the personnel to be dispatched, the present invention can determine the best personnel to be dispatched from the part of the personnel to be dispatched who are most likely to meet the current dispatch task, that is, determine the designated dispatch personnel, so as to ensure the high quality and rapid completion of the dispatch task. Moreover, the present invention analyzes and considers the dispatch tasks and dispatch personnel from a multi-dimensional perspective, fully meets the different task requirements of different users, and realizes the customized allocation of the most suitable personnel to be dispatched for processing for each dispatch task, so as to fundamentally ensure the timeliness and targeted response of the dispatch task, and greatly improve the user satisfaction and user experience. Especially for the underwriting scenario in the insurance industry, the present invention can realize the dispatch scheduling of underwriters in a multi-dimensional manner, which effectively reduces the cost of enterprise dispatch while meeting the needs of users, and takes into account the satisfaction of users and underwriters. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic flow chart of a method for dynamic dispatching in one or more embodiments of the present invention is shown.

[0044] Figure 2 A schematic diagram of a process for generating a plurality of first feature data sets in one or more embodiments of the present invention is shown.

[0045] Figure 3 A schematic diagram of a process for dividing all current personnel to be dispatched in one or more embodiments of the present invention is shown.

[0046] Figure 4 A schematic diagram of a process for extracting task target indicator data from acquired current work assignment task data in one or more embodiments of the present invention is shown.

[0047] Figure 5 A schematic diagram showing the composition of an apparatus for dynamic work dispatching in one or more embodiments of the present invention is shown.

[0048] Figure 6 A schematic diagram of the internal structure of a computer device in one or more embodiments of the present invention is shown. DETAILED DESCRIPTION

[0049] The following is a detailed explanation and description of a dynamic work dispatching method, device, computer equipment and storage medium provided by the present invention in conjunction with the drawings in the specification.

[0050] In order to solve the technical problems existing in conventional dispatching methods, such as low task processing efficiency, unreasonable task allocation and great influence of human subjective factors, the present invention can provide a dynamic dispatching method, device, computer equipment and storage medium to overcome one or more problems existing in the prior art.

[0051] like Figure 1 As shown, one or more embodiments of the present invention can specifically provide a method for dynamic work dispatching, which may include but is not limited to one or more of the following steps.

[0052] Step 100 , the present invention classifies the personnel to be dispatched using their historical dispatch task data to generate a plurality of first feature data sets.

[0053] Among them, the elements in the first feature data set of this embodiment are the data of personnel to be assigned, and the historical assigned task data are data that are constantly and dynamically changing as each assigned task is carried out.

[0054] like Figure 2 As shown, in one or more embodiments of the present invention, historical work assignment data of workers to be assigned are used to classify workers to generate multiple first feature data sets, including but not limited to steps 110 to 130, which are specifically described as follows.

[0055] Step 110: multiple labels are formed based on the acquired historical dispatch task data and data of personnel to be dispatched. In this embodiment, the labels include but are not limited to task type, task importance, task quantity, task completion time, task response time, personnel age, personnel position level and personnel gender, etc. For example, the personnel to be dispatched are underwriters in the underwriting scenario of the insurance industry, and the labels may include but are not limited to the verification time, verification type and verification timeliness, etc.

[0056] Step 120 , classify all the current workers to be dispatched using the labels as the classification basis, so as to distinguish different workers to be dispatched based on the historical task conditions and the conditions of the workers to be dispatched.

[0057] like Figure 3 As shown, in one or more embodiments of the present invention, using labels as a classification basis to classify all current personnel to be dispatched includes steps 121 to 123.

[0058] Step 121, sorting all tags according to the degree of influence on the current assigned task; this embodiment can obtain a sorting result from high to low influence or from low to high influence.

[0059] Step 122, weight values ​​are set for each tag in the sorting result in turn. In this embodiment, a larger weight value is set for tags with a high degree of impact on the dispatched task, and a smaller weight value is set for tags with a low degree of impact on the dispatched task; the process of setting weight values ​​for sorted tags is more efficient.

[0060] Step 123, divide all the current personnel to be dispatched based on the labels and their weight values. The present invention intelligently distinguishes the personnel to be dispatched through labels, and closely links the labels with the dispatch tasks through weight values. The present invention realizes effective division of dispatched personnel based on the dispatch tasks.

[0061] Specifically, in an embodiment of the present invention, all current personnel to be dispatched are divided based on labels and their weight values, including: reading the indicator values ​​corresponding to each label, wherein the indicator values ​​may include, for example, a length of service of 5 years, a response task time of 10 hours, a position level of C, a gender of male, a number of tasks of 12, etc.; normalizing the indicator values ​​so that different indicator values ​​are mapped to the same numerical interval, and in this embodiment, the same numerical interval is [0, 1], for example, a length of service of 5 years is normalized to 0.5, a response task time of 10 hours is normalized to 0.1, a position level of C (for example, level A>level B>level C) is normalized to 0.3, a gender of male corresponds to 0.35 after normalization, and a number of tasks of 12 is normalized to 0.12; the specific normalization calculation method is set according to the actual situation, and this embodiment will not be repeated; the final classification value is calculated according to the weight value of the label and the normalized indicator value, and the personnel to be dispatched with the final classification value in the same set range are determined to be divided into the same category; the final classification value in this embodiment where q i represents the index value after normalization of the ith value, w i Indicates that i The corresponding i-th weight value, n represents the number of indicator values.

[0062] It can be seen from this that the present invention can realize the quantitative calculation or measurement of the situations of different personnel to be dispatched, so as to achieve the purpose of finely distinguishing different personnel to be dispatched, and provide reliable data support for the present invention to realize the precise dispatching plan.

[0063] Optionally, in order to improve the speed of personnel classification and reduce the amount of calculation, in other embodiments of the present invention, all current personnel to be dispatched are divided based on labels as classification basis, including: different personnel to be dispatched with a preset number of the same labels are classified into the same category, and the preset number is greater than or equal to 3.

[0064] Step 130, using the data of the personnel to be dispatched belonging to the same category to form a first feature data set. It can be seen that the present invention can use the big data formed by the actual task situation and personnel-related data as an objective basis, so as to reasonably distinguish the personnel to be dispatched in multiple dimensions through labels.

[0065] Step 200: extracting task target indicator data from the currently acquired task data, and generating a second feature data set using the task target indicator data.

[0066] Among them, the elements in the second feature data set of this embodiment are task target indicator data, which are used to describe the requirements of the current dispatch task. Task target indicator data, for example, includes but is not limited to the maximum allowable processing time data of the current dispatch task, the latest allowable processing time data of the current dispatch task, the minimum position level data of the dispatch personnel required by the current dispatch task, and other related data, of course, but is not limited to this.

[0067] like Figure 4 As shown, one or more embodiments of the present invention extract task target indicator data from the acquired current work assignment task data, including steps 210 to 230.

[0068] Step 210, extracting the work assignment note information from the current work assignment task data; the work assignment note information includes, but is not limited to, "requirement that the task processing must be completed on time", "VIP customer designated personnel level", etc.

[0069] Step 220: Perform content recognition processing on the current work dispatch note information based on natural language processing (NPL) to determine the work dispatch requirement information. The specific natural language processing algorithm used can be selected as needed, and this embodiment will not be repeated.

[0070] Step 230, extract data from the current dispatch task data according to the dispatch requirement information to obtain task target indicator data; for example, extract task completion deadline related data, to-be-dispatched personnel level related data, etc. It can be seen that the embodiment of the present invention can annotate the dispatch requirement related information as needed according to the actual situation, and this method can bring great flexibility and freedom to the dispatch technical solution, and then dynamically dispatch according to the dynamically changing tasks and requirements. It can be seen that the present invention has outstanding advantages such as strong adaptability, high intelligence and wide application range.

[0071] Optionally, in some other embodiments of the present invention, extracting task target indicator data from the acquired current work dispatch task data includes: reading form data formed together with the task target instruction data, the form data recording the work dispatch requirement information of the current task, and the form data being structured data; then obtaining one or more work dispatch requirement information from the form data, generally obtaining all work dispatch requirement information; finally, performing data extraction processing on the work dispatch task data according to the work dispatch requirement information, so as to obtain the task target indicator data by means of data extraction. Based on the structured form data formed together with the work dispatch task data, the present invention can more conveniently and accurately determine the requirements of the current work dispatch task, and can reduce the difficulty of data processing and improve the data processing speed. It can be seen that the present invention also has outstanding advantages such as strong reliability, high stability and high execution efficiency.

[0072] Step 300, the second feature data set generated by the present invention is used to screen multiple first feature data sets to select at least one first feature data set as a target feature data set. It can be seen that the present invention narrows the data range by selecting the first feature data set, that is, narrows the range of personnel to be assigned.

[0073] Optionally, in one or more embodiments of the present invention, filtering and processing multiple first feature data sets according to the second feature data set may include: calculating the target score value corresponding to the task target indicator data in the second feature data set, the target score value of the present invention is used to indicate the degree of task requirement; filtering and processing multiple first feature data sets according to the target score value, this embodiment compares the target score value with the classification value range of each first feature data set, and determines the filtering result based on the comparison result, for example, determining at least one first feature data set whose final classification value range is greater than the target score value as the filtering result; wherein the classification value range of the first feature data set refers to the value range of the final classification value of the personnel to be dispatched in the first feature data set.

[0074] Optionally, the target score value corresponding to the task target indicator data in the second feature data set calculated in one or more embodiments of the present invention includes: obtaining the currently determined work dispatch requirement information, which is obtained based on the work dispatch note information or form data; normalizing the obtained work dispatch requirement information so that the data corresponding to each work dispatch requirement information is mapped to the same numerical range. This process can be the same as the normalization process of the indicator value, and the same numerical range can also be [0, 1]. For example, the information "Please process within 24 hours" is 0.24 after normalization, and the information "VIP customers please assign a senior manager at least" is 0.9 after normalization, but of course it is not limited to this. Finally, this embodiment can obtain the target score value by accumulating the score values ​​corresponding to the work dispatch requirement information or other methods.

[0075] Optionally, one or more embodiments of the present invention compare the target score value with the classification value range of each first feature data set, including: selecting the first feature data sets one by one according to the range of the final classification value from large to small, that is, in this embodiment, the first feature data sets with a large classification value range are given priority, and the first feature data sets with a small classification value range are selected later; comparing the upper limit values ​​of the classification value range of the first feature data sets with the target score value one by one in the selection order; comparing the next upper limit value with the target score value based on the current upper limit value being greater than or equal to the target score value, or ending the comparison step based on the current upper limit value being less than the target score value.

[0076] Step 400 , matching the current work assignment task with the personnel to be assigned in the target feature data set, so as to determine a personnel to be assigned who has the highest matching degree with the current work assignment task as the designated person to be assigned.

[0077] Optionally, in one or more embodiments of the present invention, the process of matching the current dispatched task with the personnel to be dispatched may include: reading the task target indicator data of the current dispatched task, matching the personnel data to be dispatched in the target feature data set (after the above-mentioned screening process, the number of personnel that can be selected at this time is relatively small) with the task target indicator data one by one, taking the underwriting business as an example, comparing the required order verification time with the personnel's historical order verification time, the required order verification type with the personnel's historical order verification type, the required order verification timeliness with the personnel's historical order verification timeliness, etc., to obtain a comprehensive matching result, and can determine the personnel to be dispatched with the highest degree of matching based on the comprehensive matching result. Among them, the embodiment of the present invention can regard the obtained target feature data set as a population based on the trained genetic algorithm model, and the individuals in the population are the personnel to be dispatched, and select, cross and mutate the task target indicator data and the personnel data to be dispatched based on the genetic algorithm model, so as to more quickly determine the best individual from the population, that is, the comprehensive matching result of this embodiment.

[0078] Step 500, assigning the current work assignment to a designated work assignment personnel so that the current work assignment is processed by the designated work assignment personnel.

[0079] Optionally, allocating the current work assignment to the designated work assignment personnel includes: sending information about the current work assignment task to the terminal of the designated work assignment personnel; and based on the task reception confirmation information received from the terminal, sending task countdown reminder information to the terminal at a preset frequency to remind the personnel to process it on time.

[0080] like Figure 5 As shown, based on the same inventive technical concept as the method for dynamic dispatching, one or more embodiments of the present invention can also provide a device for dynamic dispatching.

[0081] The device may include but is not limited to a personnel classification processing module, a task target acquisition module, a data screening processing module, a task personnel matching module and a work assignment task sending module, as described in detail below.

[0082] The personnel classification processing module can be used to classify the personnel to be dispatched using the historical work task data of the personnel to be dispatched, so as to generate multiple first feature data sets. The personnel classification processing module can be used to form multiple labels based on the historical work task data and the personnel to be dispatched data, and to divide all the current personnel to be dispatched using the labels as the classification basis, and to form the first feature data set using the personnel to be dispatched data belonging to the same category.

[0083] Optionally, the personnel classification processing module can be used to sort all labels according to their impact on the current work assignment, and to set weight values ​​for each label in the sorting results in turn, and to divide all current personnel to be assigned based on the labels and their weight values.

[0084] Optionally, the personnel classification processing module can be used to read the indicator values ​​and normalized indicator values ​​corresponding to each label so that different indicator values ​​are mapped to the same numerical range; the personnel classification processing module is also used to calculate the final classification value based on the weight value of the label and the normalized indicator value, and can be used to determine the personnel to be dispatched with the final classification value in the same set range so that they can be classified into the same category.

[0085] The task target acquisition module is used to extract task target indicator data from the acquired current work assignment task data, and to generate a second feature data set using the task target indicator data.

[0086] Optionally, the task target acquisition module can be used to extract work dispatch note information from the current work dispatch task data, and can be used to perform content recognition processing on the work dispatch note information based on natural language processing to determine the work dispatch requirement information; the task target acquisition module is also used to perform data extraction processing on the current work dispatch task data specifically according to the work dispatch requirement information, so as to obtain task target indicator data for generating a second feature data set.

[0087] The data screening processing module is used to screen multiple first feature data sets according to the second feature data set, so as to use at least one first feature data set as a target feature data set. The data screening processing module is specifically used to calculate the target score value corresponding to the task target indicator data in the second feature data set, and can be used to screen multiple first feature data sets according to the target score value, and the target score value is used to indicate the degree of task requirements.

[0088] The task-personnel matching module is used to match the current work assignment task with the personnel to be assigned in the target feature data set to determine the personnel to be assigned who has the highest degree of matching with the current work assignment task as the designated person to be assigned.

[0089] The work dispatching task sending module is used to assign the current work dispatching task to the designated work dispatching personnel so that the current work dispatching task can be processed by the designated work dispatching personnel.

[0090] Optionally, the work assignment task sending module is used to send information about the current work assignment task to the terminal of the designated work assignment personnel, and can be used to send task countdown reminder information to the terminal at a preset frequency based on task reception confirmation information fed back by the terminal.

[0091] like Figure 6 As shown, based on the same inventive technical concept as the method for dynamic dispatching, one or more embodiments of the present invention may provide a computer device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for dynamic dispatching in any embodiment of the present invention. The method for dynamic dispatching includes but is not limited to the following one or more steps: Step 100, the present invention uses the historical dispatching task data of the personnel to be dispatched to classify the personnel to be dispatched, so as to generate multiple first feature data sets. Figure 2 As shown, the historical work task data of the personnel to be dispatched are used to classify the personnel to be dispatched to generate multiple first feature data sets, including steps 110 to 130. Step 110, forming multiple labels based on the historical work task data and the personnel to be dispatched data. Step 120, using the labels as the classification basis to classify all the current personnel to be dispatched. Figure 3 As shown, using labels as the classification basis to divide all current personnel to be dispatched includes steps 121 to 123. Step 121, sorting all labels according to the degree of influence on the current dispatch task; step 122, setting weight values ​​for each label in the sorting result in turn; step 123, dividing all current personnel to be dispatched based on labels and their weight values. Specifically, this embodiment divides all current personnel to be dispatched based on labels and their weight values, including: reading the indicator values ​​corresponding to each label, normalizing the indicator values ​​so that different indicator values ​​are mapped to the same numerical range; calculating the final classification value according to the weight value of the label and the normalized indicator value, determining the personnel to be dispatched with the final classification value in the same set range, and dividing them into the same category. Step 130, using the data of personnel to be dispatched belonging to the same category to form a first feature data set. Step 200, extracting task target indicator data from the currently acquired current dispatch task data, and generating a second feature data set using the task target indicator data. As Figure 4As shown, extracting task target indicator data from the acquired current dispatch task data includes steps 210 to 230. Step 210, extracting dispatch note information from the current dispatch task data; step 220, performing content recognition processing on the dispatch note information based on natural language processing to determine dispatch requirement information; step 230, performing data extraction processing on the current dispatch task data according to the dispatch requirement information to obtain task target indicator data. Step 300, screening multiple first feature data sets according to the second feature data set generated by the present invention, so as to use at least one first feature data set as a target feature data set. Optionally, in one or more embodiments of the present invention, screening multiple first feature data sets according to the second feature data set includes: calculating the target score value corresponding to the task target indicator data in the second feature data set, the target score value is used to indicate the degree of task requirement; screening multiple first feature data sets according to the target score value. Step 400, matching the current dispatch task with the personnel to be dispatched in the target feature data set, so as to determine a personnel to be dispatched with the highest degree of matching with the current dispatch task as the designated dispatch personnel. Step 500, assigning the current work assignment task to a designated work assignment personnel so that the designated work assignment personnel can process the current work assignment task. Optionally, assigning the current work assignment task to the designated work assignment personnel includes: sending information about the current work assignment task to the terminal of the designated work assignment personnel; and sending task countdown reminder information to the terminal at a preset frequency according to task reception confirmation information received from the terminal.

[0092] Based on the same technical concept as the method for dynamic dispatching, one or more embodiments of the present invention can also provide a storage medium storing computer-readable instructions, which, when executed by one or more processors, enables one or more processors to execute the steps of the method for dynamic dispatching in any embodiment of the present invention. The method for dynamic dispatching includes but is not limited to one or more of the following steps: Step 100, the present invention uses the historical dispatching task data of the personnel to be dispatched to classify the personnel to be dispatched, so as to generate multiple first feature data sets. Figure 2 As shown, the historical work task data of the personnel to be dispatched are used to classify the personnel to be dispatched to generate multiple first feature data sets, including steps 110 to 130. Step 110, forming multiple labels based on the historical work task data and the personnel to be dispatched data. Step 120, using the labels as the classification basis to classify all the current personnel to be dispatched. Figure 3As shown, using labels as the classification basis to divide all current personnel to be dispatched includes steps 121 to 123. Step 121, sorting all labels according to the degree of influence on the current dispatch task; step 122, setting weight values ​​for each label in the sorting result in turn; step 123, dividing all current personnel to be dispatched based on labels and their weight values. Specifically, this embodiment divides all current personnel to be dispatched based on labels and their weight values, including: reading the indicator values ​​corresponding to each label, normalizing the indicator values ​​so that different indicator values ​​are mapped to the same numerical range; calculating the final classification value according to the weight value of the label and the normalized indicator value, determining the personnel to be dispatched with the final classification value in the same set range, and dividing them into the same category. Step 130, using the data of personnel to be dispatched belonging to the same category to form a first feature data set. Step 200, extracting task target indicator data from the currently acquired current dispatch task data, and generating a second feature data set using the task target indicator data. As Figure 4 As shown, extracting task target indicator data from the acquired current dispatch task data includes steps 210 to 230. Step 210, extracting dispatch note information from the current dispatch task data; step 220, performing content recognition processing on the dispatch note information based on natural language processing to determine dispatch requirement information; step 230, performing data extraction processing on the current dispatch task data according to the dispatch requirement information to obtain task target indicator data. Step 300, screening multiple first feature data sets according to the second feature data set generated by the present invention, so as to use at least one first feature data set as a target feature data set. Optionally, in one or more embodiments of the present invention, screening multiple first feature data sets according to the second feature data set includes: calculating the target score value corresponding to the task target indicator data in the second feature data set, the target score value is used to indicate the degree of task requirement; screening multiple first feature data sets according to the target score value. Step 400, matching the current dispatch task with the personnel to be dispatched in the target feature data set, so as to determine a personnel to be dispatched with the highest degree of matching with the current dispatch task as the designated dispatch personnel. Step 500, assigning the current work assignment task to a designated work assignment personnel so that the designated work assignment personnel can process the current work assignment task. Optionally, assigning the current work assignment task to the designated work assignment personnel includes: sending information about the current work assignment task to the terminal of the designated work assignment personnel; receiving confirmation information of the task based on the feedback of the terminal, and sending task countdown reminder information to the terminal at a preset frequency.

[0093] In summary, the technical solution provided by the present invention can screen the first feature data set formed by the data of the personnel to be dispatched through the second feature data set formed by the task target indicator data, that is, to perform accurate and intelligent dispatch according to the actual situation of the personnel to be dispatched and the dispatch task situation through big data processing. Through the layer-by-layer screening of all the personnel to be dispatched, the present invention can determine the best personnel to be dispatched from the part of the personnel to be dispatched who are most likely to meet the current dispatch task, that is, determine the designated dispatch personnel, thereby ensuring the high quality and rapid completion of the dispatch task. Moreover, the present invention analyzes and considers the dispatch tasks and dispatch personnel from a multi-dimensional perspective, fully meets the different task requirements of different users, and can realize customized allocation of the most suitable personnel to be dispatched for processing for each dispatch task, so as to fundamentally ensure the timeliness and targeted response of the dispatch task, greatly improving user satisfaction and user experience. Especially for the underwriting scenarios involved in the insurance industry, the present invention can realize multi-dimensional dispatch scheduling of underwriters, meet user needs, and effectively reduce the cost of enterprise dispatch, taking into account user satisfaction and underwriter satisfaction.

[0094] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, apparatus, or device and execute instructions), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable storage medium" may be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device. More specific examples of computer-readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic devices), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory, or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM, Compact Disc Read-Only Memory). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0095] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA, Programmable Gate Array), a field programmable gate array (FPGA, Field Programmable Gate Array), etc.

[0096] In the description of this specification, the description with reference to the terms "this embodiment", "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0097] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and simple improvements made to the essential contents of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for dynamic work dispatching, characterized in that: include: Using historical work task data of the workers to be dispatched, the workers to be dispatched are classified to generate a plurality of first feature data sets; Extracting task target indicator data from the acquired current work assignment task data, and generating a second feature data set using the task target indicator data; Calculating a target score value corresponding to the task target indicator data in the second feature data set, wherein the target score value is used to indicate the degree of task requirement; Screening the plurality of first feature data sets according to the target score value to select at least one of the first feature data sets as a target feature data set; Matching the current work assignment task with the workers to be assigned in the target feature data set to determine the worker to be assigned who has the highest matching degree with the current work assignment task as the designated worker to be assigned; Allocate the current work assignment to the designated work dispatcher so that the current work assignment is processed by the designated work dispatcher; The method of using the historical work task data of the workers to be dispatched to classify the workers to be dispatched to generate multiple first feature data sets includes: forming multiple labels based on the historical work task data and the data of the workers to be dispatched; sorting all the labels according to the degree of influence on the current work task, and setting weight values ​​for each label in the sorting result in turn; dividing all the current workers to be dispatched based on the labels and their weight values; and forming the first feature data set using the data of the workers to be dispatched belonging to the same category; The classification of all the current personnel to be dispatched based on the labels and their weight values ​​includes: reading the indicator values ​​corresponding to each label; normalizing the indicator values ​​so that different indicator values ​​are mapped to the same numerical range; calculating the final classification value based on the weight value of the label and the normalized indicator value; determining the personnel to be dispatched with the final classification value in the same set range to classify them in the same category.

2. The method for dynamic dispatching according to claim 1, characterized in that: The step of extracting task target indicator data from the acquired current work task data includes: Extracting work dispatch note information from the current work dispatch task data; Performing content recognition processing on the work dispatch note information based on natural language processing to determine the work dispatch requirement information; The current work assignment task data is subjected to data extraction processing according to the work assignment requirement information to obtain task target indicator data.

3. The method for dynamic dispatching of work according to claim 1, characterized in that: The allocating the current work assignment to the designated work assignment personnel comprises: Sending information about the current work assignment to the terminal of the designated work assignee; According to the task reception confirmation information fed back by the terminal, task countdown reminder information is sent to the terminal at a preset frequency.

4. A device for dynamic dispatching, characterized in that: include: A personnel classification processing module is used to classify the personnel to be dispatched using the historical work task data of the personnel to be dispatched to generate multiple first feature data sets, including: forming multiple labels based on the historical work task data and the data of the personnel to be dispatched; sorting all the labels according to the degree of influence on the current work task, and setting weight values ​​for each label in the sorting results in turn; reading the index values ​​corresponding to each label; normalizing the index values ​​so that different index values ​​are mapped to the same numerical range; calculating the final classification value according to the weight value of the label and the normalized index value; determining the personnel to be dispatched with the final classification value in the same set range to be classified into the same category; forming the first feature data set using the data of the personnel to be dispatched belonging to the same category; A task target acquisition module, used to extract task target indicator data from the acquired current work assignment task data, and to generate a second feature data set using the task target indicator data; A data screening and processing module is used to calculate a target score value corresponding to the task target indicator data in the second feature data set, wherein the target score value is used to indicate the degree of task requirement; and to screen the plurality of first feature data sets according to the target score value to select at least one of the first feature data sets as a target feature data set; A task-personnel matching module is used to match the current work assignment task with the personnel to be assigned in the target feature data set, so as to determine the personnel to be assigned who has the highest matching degree with the current work assignment task as the designated personnel to be assigned; The work dispatching task sending module is used to distribute the current work dispatching task to the designated work dispatching personnel so that the current work dispatching task can be processed by the designated work dispatching personnel.

5. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the method for dynamic dispatching as claimed in any one of claims 1 to 3.

6. A storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the method for dynamic dispatching as claimed in any one of claims 1 to 3.