Method, device and computer equipment for automatic task allocation based on data statistics

Abstract

The present invention belongs to the field of artificial intelligence technology, and is applied to task allocation scenarios of various business data in smart city construction. A method and device for automatic task allocation based on data statistics are disclosed. The method obtains historical data of completed tasks and performs cluster analysis on them; calculates the execution status of each executor on different types of completed tasks through the historical data to determine the rating of the executor in different task types; determines the task type and geographical location to which the task to be allocated belongs; searches for candidate executors within a preset range according to the geographical location of the task to be allocated; compares the ratings of the candidate executors in the task type of the task to be allocated to determine the recommended executor with the highest rating; and automatically allocates the task to be allocated to the recommended executor, thereby realizing an objective and operable quantitative evaluation of the executors and facilitating effective management of overall task allocation.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology in artificial intelligence, and is applied to task allocation scenarios of various business data in smart city construction, and in particular to a method, device, computer equipment and storage medium for automatic task allocation based on data statistics. Background Art

[0002] At present, with the continuous development of electronic information technology, data analysis and intelligent systems based on data analysis statistical results, such as recommendation systems, have begun to be widely used in many different fields, greatly improving processing efficiency.

[0003] The management and allocation of tasks is also an important application area of ​​data statistics and analysis. There are some digital systems and platforms related to task management and allocation, which can provide certain conveniences for users to select and execute tasks that suit them.

[0004] However, these digital systems and platforms have a low level of intelligence, and often face problems such as one task being claimed by multiple people while some tasks are left unclaimed. They are also unable to match tasks with executors in a targeted manner, especially when the task data is more complex and has a high degree of specificity, making it difficult to provide accurate and objective allocation and management. Summary of the invention

[0005] The embodiments of the present invention provide a method, apparatus, computer equipment and storage medium for automatic task allocation based on data statistics, aiming to solve the problem in the prior art that digital systems are difficult to provide accurate and objective allocation and management, and are unable to effectively quantify data when task data is relatively complex and has a high degree of specificity.

[0006] In a first aspect, an embodiment of the present invention provides a method for automatically allocating tasks based on data statistics, which includes:

[0007] Acquire historical data of completed tasks; cluster the completed tasks according to the historical data through a clustering algorithm to determine the task type to which each completed task belongs; determine the executor corresponding to each completed task; calculate the execution status of each executor on different types of completed tasks through the historical data, and the execution status is represented by a number of evaluation indicators, including: the number of completed tasks, the success rate and the time to complete the task; determine the rating of the executor in different task types according to the execution status; determine the task type and geographical location to which the task to be assigned belongs; search for candidate executors within a preset range according to the geographical location of the task to be assigned; compare the ratings of the candidate executors in the task type of the task to be assigned to determine the recommended executor with the highest rating; and automatically assign the task to be assigned to the recommended executor.

[0008] In a second aspect, an embodiment of the present invention provides a device for automatically allocating tasks based on data statistics, which includes:

[0009] A historical data acquisition unit is used to acquire historical data of completed tasks; a task type labeling unit is used to cluster the completed tasks according to the historical data through a clustering algorithm, and determine the task type to which each completed task belongs; an executor search unit is used to determine the executor corresponding to each completed task; an execution status calculation unit is used to calculate the execution status of each executor on different types of completed tasks through the historical data, and the execution status is represented by a number of evaluation indicators, and the evaluation indicators include: the number of completed tasks, the success rate and the time to complete the task; an executor rating unit is used to determine the rating of the executor in different task types according to the execution status; a task acquisition unit to be assigned is used to determine the task type and geographical location to which the task to be assigned belongs; a candidate executor search unit is used to search for candidate executors within a preset range according to the geographical location of the task to be assigned; a rating analysis unit is used to compare the ratings of the candidate executors in the task type of the task to be assigned to determine the recommended executor with the highest rating; a task assignment unit is used to automatically assign the task to be assigned to the recommended executor.

[0010] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for automatic task allocation based on data statistics described in the first aspect is implemented.

[0011] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the method for automatic task allocation based on data statistics described in the first aspect above.

[0012] The automatic task allocation method provided in the embodiment of the present invention can better mine the data patterns in the historical data of completed tasks by analyzing the task types, and realize objective and operational quantitative evaluation of the executors, thereby making the results of automatic task allocation more reasonable and facilitating the effective management of the overall task allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0014] Figure 1 A flowchart of a method for automatically allocating tasks based on data statistics provided by an embodiment of the present invention;

[0015] Figure 2 A schematic diagram of a flow chart of a method for automatic task allocation based on data statistics provided by another embodiment of the present invention;

[0016] Figure 3 A flowchart of step 102 provided in an embodiment of the present invention;

[0017] Figure 4 A flowchart of step 1021 provided in an embodiment of the present invention;

[0018] Figure 5 A schematic block diagram of a device for automatically allocating tasks based on data statistics provided by an embodiment of the present invention;

[0019] Figure 6 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0022] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0023] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] See also Figure 1 , Figure 1 The present invention provides a flowchart of a method for automatically allocating tasks based on data statistics, which can be applied to electronic computing platforms such as servers to implement the automatic task allocation function. The method is executed by application software installed in the electronic computing platform.

[0025] like Figure 1 As shown, the method includes steps S101 to S110.

[0026] S101. Obtain historical data of completed tasks.

[0027] In this embodiment, in order to more clearly understand the technical solution, the terminal involved in the electronic computing platform is described in detail below. This application describes the technical solution from the perspective of the server.

[0028] The user end, that is, the intelligent terminal used by the user (such as a smartphone, tablet computer, etc.), is used to obtain tasks and display relevant information of the tasks to the executors. It can also obtain relevant information of the user end, such as location information, and upload it to the server to realize automatic task allocation.

[0029] Generally, a user terminal establishes a connection with a server by first downloading an APP application provided by the server and then entering a user name and password, so that the APP application serves as a medium for data exchange between the user terminal and the server.

[0030] The server is used to perform data statistics, analysis and other related logical processing steps, and provide corresponding data information to the user end. Historical data refers to tasks that have been processed previously. Usually, depending on the actual situation, a variety of corresponding task attributes will be used to represent it. Among them, the historical data of completed tasks stored in the server includes task name, task processing time period, task handler, task real-life picture, task audio and other data. For example, taking the company's field staff task platform as an example, the completed historical data corresponding to each field staff generally includes the field task name, field task processing time period, field task handler, field task real-life picture, field task audio, etc.

[0031] S102: Clustering the completed tasks according to the historical data using a clustering algorithm to determine the task type to which each completed task belongs.

[0032] In this embodiment, the completed tasks are divided into a plurality of different task types by a clustering algorithm. The specific number of task types can be set according to the needs of the actual situation. The clustering algorithm can be selected and used according to the needs of the actual situation, such as the commonly used K-means algorithm.

[0033] In one embodiment, if Figure 3 As shown, step 102 may specifically include:

[0034] S1021. Convert the historical data of the completed tasks into a plurality of task attributes and attribute values ​​corresponding to the task attributes.

[0035] In this embodiment, the task attribute is used to describe one aspect of the completed task. Each completed task can be described by multiple task attributes. The attribute value is the value under a specific task attribute, which represents the specific situation of the completed task under the task attribute. Depending on the different task attributes, the attribute value may also be in different data forms.

[0036] In general, the historical data of completed tasks are mixed with various data forms, including numbers, text, audio or images, etc. In order to effectively realize the conversion of historical data and facilitate processing by electronic computing platforms such as servers, such as Figure 4 As shown, step 1021 may specifically include:

[0037] S1021a, converting the historical data into text data in text form.

[0038] In this embodiment, in order to unify and facilitate subsequent processing, all historical data can be converted into text data, which accounts for the majority, thereby reducing the amount of pre-processed data.

[0039] S1021b. Determine the task attributes constituting the text data through a preset expert dictionary.

[0040] In this embodiment, the expert dictionary is a dictionary pre-set by technicians based on expert knowledge, which records the task attributes corresponding to different text data, thereby arranging the messy historical data into structured data that can be used by computers.

[0041] S1021c: Using a keyword dictionary corresponding to the task attribute, extract a key character string in each task attribute as the attribute value.

[0042] In this embodiment, the keyword dictionary is similar to the expert dictionary and is also a set of pre-set keyword screening rules. The keyword dictionary can further screen out unimportant or redundant text data in the historical data to facilitate subsequent similarity calculations.

[0043] The key string is data information that can be recognized by a computer and can representatively describe the status of the completed task under specific task attributes.

[0044] Through the above-mentioned conversion and data preprocessing process, the messy historical data can be effectively organized into structured data information of computer-recognizable character strings, thereby making automatic task classification of completed tasks possible.

[0045] S1022. Calculate the similarity between each task attribute of different completed tasks based on the attribute value.

[0046] In this embodiment, the similarity is a percentage obtained by comparing the attribute values ​​of different completed tasks under a certain task attribute, indicating the degree of similarity between the two in a certain aspect. Specifically, according to the data form of the attribute value, a suitable measurement or representation method can be used to calculate the similarity between the two. For example, for a numeric attribute value, the ratio of the difference between the two to the total value can be used to represent it.

[0047] In another embodiment, cosine similarity can be used to calculate the similarity between attribute values ​​of different completed tasks in the same task attribute. Cosine similarity is a good way to measure vector attribute values ​​such as text vectors.

[0048] S1023. According to a preset task attribute weight coefficient, weighted sum is performed on the similarities between all task attributes of the completed tasks to obtain the distance between the completed tasks.

[0049] In this embodiment, the task attribute weight coefficient is a coefficient used to measure the importance of different task attributes. By adjusting the weight coefficient, the importance of different task attributes in the classification process can be reflected. The technician can set a suitable task attribute weight coefficient according to the actual needs.

[0050] S1024. Perform clustering using a K-means clustering algorithm based on the distances between the completed tasks to determine the task types to which the completed tasks belong.

[0051] In this embodiment, the distance between different completed tasks is the result of weighted summation of all task attribute similarities, which reflects or expresses the overall similarity or proximity of the completed tasks. Using this as the basic data for clustering can obtain accurate task classification results.

[0052] Through appropriate similarity measurement methods, the correlation between completed tasks can be explored, which can serve as the basis for K-means clustering and realize automatic classification of completed tasks. After automatic classification, the execution status of completed tasks can be better and more comprehensively analyzed and counted.

[0053] S103: Determine the executor corresponding to each of the completed tasks.

[0054] In this embodiment, the executor is the user who completed the completed task. Depending on the tasks in different fields, there will be corresponding types of executors. It can mark or record the executor of each completed task in any suitable way such as device ID or account password.

[0055] S104, calculating the execution status of each executor on different types of completed tasks through the historical data. The execution status is represented by a number of evaluation indicators, including: the number of completed tasks, the success rate, and the time required to complete the task.

[0056] In this embodiment, the evaluation index refers to the relevant standard for measuring or evaluating the completion of the task. According to different actual application situations, corresponding evaluation indicators can be selected to be expressed. The evaluation index can be one or more to better reflect the completion of the task, including the number of completed tasks, the success rate, and the time to complete the task.

[0057] In one embodiment, if Figure 2 As shown, after step 104, the following steps may also be included:

[0058] S105. Display the execution status of the executor in the form of a chart according to the received display instruction.

[0059] The charts include line charts and pie charts, and one evaluation indicator is displayed by at least one chart. Of course, appropriate charts can also be selected for display according to the specific data type of the evaluation indicator.

[0060] This chart display can effectively provide feedback on the execution status of each executor and provide an objective and comprehensive evaluation, which is helpful for managers or executors to understand their own situation and further improve the efficiency of subsequent task processing.

[0061] S106: Determine the rating of the executor in different task types according to the execution status.

[0062] In this embodiment, the rating refers to a specific evaluation given to each executor for their performance. The rating can be expressed in any form, for example, a corresponding number of ratings can be set by setting thresholds for multiple evaluation indicators. The better the evaluation indicator data, the higher the corresponding rating.

[0063] S107: Determine the task type and geographical location of the task to be assigned.

[0064] In this embodiment, the task to be assigned is a newly generated task that needs to be assigned by the system to the corresponding processing personnel or executors for processing. The geographical location of the task refers to the location where the executor needs to go to complete the task. For complex tasks, their geographical location is the data information that needs to be focused on during the assignment process.

[0065] S108: Search for candidate executors within a preset range according to the geographical location of the task to be assigned.

[0066] In this embodiment, the location information corresponding to the executor can be provided by the device information of the user end. In actual application, the preset range can be an empirical value, which is set by the technician according to the actual needs. For example, the geographical location of the recommended repair task can be used as the center of the circle, and the business personnel within the set radius can be selected as candidate executors.

[0067] S109: Compare the ratings of the candidate executors in the task types of the tasks to be assigned to determine a recommended executor with the highest rating.

[0068] In this embodiment, the geographical location is used as the primary screening condition. After screening out the possible candidate executors, the recommended executors are selected according to the executor's rating in the task category. There may be multiple executors with the same rating, so there may also be multiple recommended executors.

[0069] S110: Automatically assign the to-be-assigned task to the recommended executor.

[0070] In this embodiment, automatic allocation refers to a method of providing the to-be-allocated tasks to suitable executors for completion without relying on the results of manual data analysis. It can be completed in any suitable form. For example, active allocation can be adopted to directly bind the to-be-allocated tasks to the corresponding recommended executors, or the form of "grabbing orders" can be adopted, and the recommended executors can complete the automatic allocation of the to-be-allocated tasks in a two-way selection manner according to their own wishes.

[0071] In one embodiment, if Figure 2 As shown, after step S110, the following steps are also included:

[0072] S111 . Searching for a route between the task to be assigned and the recommended executor through a map mobile application.

[0073] In this embodiment, the map mobile application refers to any type of mobile application program that can realize path search between two points or related navigation functions. In actual application, the path search function can be realized by calling the relevant functional interface.

[0074] S112: Display the route to the recommended executor who has accepted the task to be assigned.

[0075] In this embodiment, the route can be displayed on the user terminal device of the recommendation executor. If the user terminal device supports it, navigation and other functions can also be provided so that the recommendation executor can better perform the task.

[0076] The automatic task allocation method provided in the embodiment of the present invention can better mine the data patterns in the historical data of completed tasks by analyzing the task types, and realize objective and operational quantitative evaluation of the executors, thereby making the results of automatic task allocation more reasonable and facilitating the effective management of the overall task allocation.

[0077] In order to fully illustrate the automatic task allocation method provided by the embodiment of the present invention, the following is a detailed description of the method using the application scenario of vehicle repair as an example.

[0078] "Vehicle repair recommendation" refers to the act of the insurance company's dedicated personnel recommending a vehicle repair unit to the owner of the accident vehicle and guiding the owner to the recommended vehicle repair unit for repair in order to ensure the effectiveness of vehicle repairs and maintain the cooperative relationship between the insurance company and the vehicle repair unit after a vehicle accident occurs and the insurance is reported.

[0079] Since each vehicle repair task is unique, it is difficult to manually quantify a large number of vehicle repair tasks according to a unified standard. Therefore, the automated data processing method provided by the embodiment of the present invention can be applied to achieve an objective and operable quantitative evaluation of vehicle repair tasks and business personnel, which is convenient for the allocation and management of vehicle repair tasks.

[0080] In general, in this embodiment, several aspects may be included, such as data statistics, business personnel evaluation, and automatic allocation of vehicle repair tasks.

[0081] 1) About data statistics:

[0082] First, obtain the historical data of completed recommended repair tasks. For a complete recommended repair task, it can usually be represented by multiple different items. For example, the cause of the accident, the brand and model of the repaired vehicle, the repair items, the recommended repair unit, the repair cost, and the feedback and evaluation of the owner. These items are the task attributes used to describe each vehicle recommended repair task.

[0083] Then, the completed maintenance tasks are clustered and the types of each maintenance task are marked. It can be understood that the project content is usually expressed in text form. Therefore, the text data can be extracted and converted to a character string that can be recognized by the computer.

[0084] For example, the content of the task attribute of the maintenance item "the fender is damaged and needs to be replaced as a whole" can be matched through the corresponding dictionary, and the meaningless words can be deleted, while retaining the keywords such as "fender" and "replacement" as its attribute values.

[0085] Finally, the set clustering algorithm is used to cluster all the recommended repair tasks, and multiple categories are automatically generated for quantitative processing. That is, each category generated by clustering is set with corresponding annotation information, representing a type.

[0086] In this embodiment, clustering and task type labeling are completed using a K-means clustering algorithm.

[0087] Specifically, when clustering, for different recommended tasks, first use cosine similarity to calculate the text similarity between each item. Then, according to the preset weight coefficient, the cosine similarity of all items in the recommended task is weighted and superimposed to obtain the distance between two recommended tasks. Finally, according to the K-means clustering algorithm, the number of clusters K and N is set, and the clustering of the recommended tasks is completed after the iteration converges.

[0088] 2) Regarding the evaluation of business personnel:

[0089] First, obtain the recommended repair tasks that the business personnel have completed. Each completed recommended repair task has a corresponding business personnel. The business personnel are also the executors in the above embodiment. Specifically, all recommended repair tasks handled by a specific business personnel can be searched and determined from the data platform or the corresponding database.

[0090] Then, the execution of different types of recommended repair tasks by the business personnel is calculated respectively. For vehicle recommended repair tasks, the evaluation indicators used to measure the execution status may include but are not limited to: the communication time, the number of tasks undertaken, and the percentage of successful visits to the store for a certain type of recommended repair tasks.

[0091] Finally, the ratings of the business personnel in different task types are determined according to the execution status.

[0092] The rating can be divided and evaluated based on the statistical data used for the execution. For example, business personnel can be divided into four levels from A to D according to the acceptance rate of recommended repairs, customer contact rate, average communication time, etc., and their rating will be set to null if the number of cases handled is lower than the set threshold.

[0093] The specific rating method or the number of levels can be adjusted according to the actual situation. After completing the rating steps, each business person will have a three-dimensional and objective evaluation standard, which can highlight the business person's areas of expertise. For example, the type with a higher rating is the area in which the business person is good at.

[0094] In addition, it is also possible to combine the relevant data provided by the external data system, conduct corresponding statistics and output specific statistical results in an intuitive and appropriate manner, so that other user roles such as managers can objectively evaluate business personnel.

[0095] For example, based on the completed historical data analysis and conversion results, you can use line charts and pie charts to display the following information according to different task types:

[0096] 1) The ratio between the maintenance output value and the auto insurance premium generated by the sales personnel and their outlets within a set time period (such as monthly or annually).

[0097] 2) The proportion of sales personnel and the outlets they represent who agree, are not sure, or refuse to come to the store after the repair task is completed.

[0098] 3) The acceptance rate, customer contact rate and average communication time of the salesperson in this type of salesperson tasks, as well as the average value of the outlets. Provides the ability to receive user instructions and display the execution status of the salesperson and the outlets to which he belongs in a set manner.

[0099] Among them, outlets refer to the convenience of management, and a large administrative area is divided into multiple different sub-areas. Each outlet is responsible for the corresponding area's auto insurance, repair and other related businesses. Business personnel belong to different outlets, and each outlet can include multiple business personnel.

[0100] 3) Automatic allocation of vehicle repair tasks:

[0101] First, the relevant information of the newly generated vehicle recommended repair task is obtained. After the new recommended repair task is generated, the information of the new recommended repair task can be collected and obtained as relevant information (at least including the geographical location) according to the recorded task attributes.

[0102] Then, the type of the newly generated recommended repair task is determined based on the relevant information. Based on the classification results of the recommended repair tasks determined by clustering, the similarity between the newly generated vehicle recommended repair task and different types of vehicle recommended repair tasks can be calculated in the same manner as the similarity calculation in the above step, thereby determining the type of the newly generated vehicle recommended repair task.

[0103] Finally, according to the geographic location and type of the recommended maintenance task, it is automatically pushed to the corresponding business personnel. After determining the type and geographic location, the new recommended maintenance task can be automatically pushed to the business personnel who are closer to follow up, so as to achieve resource optimization and improve the effect of recommended maintenance.

[0104] Specifically, first, the geographical location of the vehicle repair task is used as the center of the circle, and the salespersons within the set radius are selected as candidates. Then, among the candidates, the salespersons with a rating of A or B in the type of repair business are preferentially selected. If there is no salesperson with a rating of A or B, the salesperson with a rating of null is assigned.

[0105] In addition, in the process of selecting the business personnel within the set radius as candidates with the geographical location of the recommended repair task as the center, whether the location of the business personnel is within the set radius can be determined in the following manner:

[0106] First, the location of the business personnel's smart mobile terminal is obtained. Then, only when the location of the business personnel is within the set radius and the recommended repair task belongs to the network point to which the business personnel belongs, is selected as a candidate. Finally, if there are no candidates, the recommended repair task is sent to the responsible network point, and the network point assigns it by itself.

[0107] 4) Implementation of other functions:

[0108] Firstly, in order to facilitate the use of business personnel and quickly guide the victim to the vehicle maintenance unit, after the pushed vehicle repair task is accepted by the business personnel, the best route from the repair task to the vehicle maintenance unit can be shown to the business personnel.

[0109] Specifically, the route between the geographical location of the recommended repair task and the vehicle maintenance unit can be searched by calling the interface of the map mobile application, and the route can be displayed on the business personnel's smart mobile terminal accordingly.

[0110] Secondly, it can also provide real-time feedback on the processing progress of the vehicle maintenance unit. That is, it can synchronize with the networked vehicle maintenance unit to obtain the subsequent case processing progress corresponding to the recommended repair task in a timely manner, such as whether the vehicle has arrived at the store, the vehicle's maintenance progress, etc.

[0111] In actual operation, the corresponding relationship between the vehicle license plate number involved in the repair task and the subsequent case can be established, so that the processing progress of the subsequent case can be displayed to the corresponding business personnel in real time.

[0112] It should be noted that the above historical data can be data stored in a node of a blockchain. The technical solution of the present application can also be applied to other data stored on the blockchain and the automatic allocation of tasks. The blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0113] An embodiment of the present invention further provides an automatic task allocation device based on data statistics, and the automatic task allocation device based on data statistics is used to execute any embodiment of the aforementioned automatic task allocation method based on data statistics. Figure 5 1 is a schematic block diagram of an automatic task allocation device based on data statistics provided by an embodiment of the present invention. The automatic task allocation device based on data statistics 500 can be configured in a server.

[0114] Specifically, see Figure 5 The automatic task allocation device 500 may include: a historical data acquisition unit 501, a task type labeling unit 502, an executor search unit 503, an execution status calculation unit 504, an executor rating unit 505, a to-be-assigned task acquisition unit 506, a candidate executor search unit 507, a rating analysis unit 508 and a task allocation unit 509.

[0115] Among them, the historical data acquisition unit 501 is used to acquire the historical data of completed tasks; the task type labeling unit 502 is used to cluster the completed tasks according to the historical data through a clustering algorithm, and determine the task type to which each completed task belongs; the executor search unit 503 is used to determine the executor corresponding to each completed task; the execution status calculation unit 504 is used to calculate the execution status of each executor on different types of completed tasks through the historical data, and the execution status is represented by several evaluation indicators, and the evaluation indicators include: the number of completed tasks, the success rate and the time to complete the task; the executor rating unit 505 is used to determine the rating of the executor in different task types according to the execution status; the task acquisition unit 506 is used to determine the task type and geographical location to which the task to be assigned belongs; the candidate executor search unit 507 is used to search for candidate executors within a preset range according to the geographical location of the task to be assigned; the rating analysis unit 508 is used to compare the ratings of the candidate executors in the task type of the task to be assigned to determine the recommended executor with the highest rating; the task assignment unit 509 is used to automatically assign the task to be assigned to the recommended executor.

[0116] The automatic task allocation device provided in the embodiment of the present invention can better mine the data patterns in the historical data of completed tasks by analyzing the task types, and realize objective and operational quantitative evaluation of the executors, thereby making the results of automatic task allocation more reasonable and facilitating the effective management of the overall task allocation.

[0117] In one embodiment, the automatic task allocation device 500 may further include: a route search unit 510 and a route display unit 511 .

[0118] The route search unit 510 is used to search for a route between the task to be assigned and the recommended executor through a map mobile application. The route display unit 511 is used to display the route to the recommended executor who has accepted the task to be assigned.

[0119] Through route search and display, executors can complete tasks better and faster, which helps to improve the efficiency of task execution.

[0120] The above-mentioned automatic task allocation device based on data statistics can be implemented in the form of a computer program. The computer program can be used in Figure 6 Runs on the computer device shown.

[0121] See also Figure 6 , Figure 6600 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 600 is a server, which can be an independent server or a server cluster composed of multiple servers.

[0122] See also Figure 6 The computer device 600 includes a processor 602 , a memory and a network interface 605 connected via a system bus 601 , wherein the memory may include a non-volatile storage medium 603 and an internal memory 604 .

[0123] The non-volatile storage medium 603 can store an operating system 6031 and a computer program 6032. When the computer program 6032 is executed, the processor 602 can execute the automatic task allocation method based on data statistics.

[0124] The processor 602 is used to provide computing and control capabilities to support the operation of the entire computer device 600 .

[0125] The internal memory 604 provides an environment for the operation of the computer program 6032 in the non-volatile storage medium 603. When the computer program 6032 is executed by the processor 602, the processor 602 can execute the automatic task allocation method based on data statistics.

[0126] The network interface 605 is used for network communication, such as providing data information transmission, etc. 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 invention, and does not constitute a limitation on the computer device 600 to which the solution of the present invention is applied. The specific computer device 600 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] The processor 602 is used to run a computer program 6032 stored in the memory to implement the vehicle type identification method based on image recognition disclosed in an embodiment of the present invention.

[0128] Those skilled in the art will understand that Figure 6 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 6 The embodiments shown are consistent and will not be described again here.

[0129] It should be understood that in the embodiment of the present invention, the processor 602 may be a central processing unit (CPU), and the processor 602 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0130] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the vehicle type recognition method based on image recognition disclosed in the embodiment of the present invention is implemented.

[0131] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment, devices and units can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0132] In the several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. Units with the same function may also be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0134] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), disk or optical disk and other media that can store program codes.

[0136] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for automatic task allocation based on data statistics, characterized in that: include: Get historical data of completed tasks; Clustering the completed tasks according to the historical data using a clustering algorithm to determine the task type to which each completed task belongs; Determine the executor corresponding to each of the completed tasks; The execution status of each executor on different types of completed tasks is calculated through the historical data, and the execution status is represented by a number of evaluation indicators, including: the number of completed tasks, the success rate, and the time to complete the task; Determining the rating of the executor in different task types according to the execution situation; Determine the task type and geographical location of the task to be assigned; Searching for candidate executors within a preset range according to the geographical location of the task to be assigned; comparing the ratings of the candidate performers in the task type of the task to be assigned to determine a recommended performer with the highest rating; Automatically assigning the to-be-assigned task to the recommended executor; After the task to be assigned is automatically assigned to the recommended executor, the method further includes: Searching for a route between the task to be assigned and the recommended executor through a map mobile application; Displaying the route to the recommended executor who has accepted the task to be assigned; After obtaining the execution status of each executor on different types of completed tasks through the historical data, the method further includes: According to the received display instruction, the execution status of the executor is displayed in the form of a chart; the chart includes a line chart and a pie chart, and an evaluation indicator is displayed by at least one chart; The clustering of the completed tasks according to the historical data by a clustering algorithm to determine the task type to which each completed task belongs includes: Converting the historical data of the completed tasks into a plurality of task attributes and attribute values ​​corresponding to the task attributes; Calculate the similarity between each task attribute of different completed tasks according to the attribute value; According to a preset task attribute weight coefficient, weighted sum is performed on the similarities between all task attributes of the completed tasks to obtain the distance between the completed tasks; According to the distances between the completed tasks, clustering is performed using a K-means clustering algorithm to determine the task type to which the completed tasks belong; The converting the historical data of the completed tasks into a plurality of task attributes and attribute values ​​corresponding to the task attributes includes: Converting the historical data into text data in text form; Determining the task attributes constituting the text data through a preset expert dictionary; Using a keyword dictionary corresponding to the task attributes, a key character string in each task attribute is extracted as the attribute value.

2. The method for automatic task allocation based on data statistics according to claim 1 is characterized in that: Calculating the similarity between each task attribute between different completed tasks according to the attribute value includes: Use cosine similarity to calculate the similarity between attribute values ​​of different completed tasks in the same task attribute.

3. A task automatic allocation device based on data statistics, characterized in that: include: A historical data acquisition unit, used to acquire historical data of completed tasks; A task type labeling unit, configured to cluster the completed tasks according to the historical data by using a clustering algorithm, and determine the task type to which each completed task belongs; An executor search unit, used to determine the executor corresponding to each of the completed tasks; An execution status calculation unit, used to calculate the execution status of each executor on different types of completed tasks through the historical data, wherein the execution status is represented by a number of evaluation indicators, including: the number of completed tasks, the success rate, and the time required to complete the task; An executor rating unit, used to determine the rating of the executor in different task types according to the execution situation; A task acquisition unit to be assigned, used to determine the task type and geographical location of the task to be assigned; A candidate executor searching unit, configured to search for candidate executors within a preset range according to the geographical location of the task to be assigned; a rating analysis unit, for comparing the ratings of the candidate performers in the task types of the task to be assigned to determine a recommended performer with the highest rating; A task allocation unit, used for automatically allocating the to-be-allocated task to the recommended executor; The automatic task allocation device based on data statistics may also include: a route search unit and a route display unit; After the task allocating unit automatically allocates the to-be-allocated task to the recommended executor, the method further includes: The route search unit is used to search for a route between the task to be assigned and the recommended executor through a map mobile application; The route display unit is used to display the route to the recommended executor who has accepted the task to be assigned; After the execution status calculation unit calculates the execution status of each executor on different types of completed tasks through the historical data, the method further includes: According to the received display instruction, the execution status of the executor is displayed in the form of a chart; the chart includes a line chart and a pie chart, and an evaluation indicator is displayed by at least one chart; The task type labeling unit clusters the completed tasks according to the historical data by using a clustering algorithm to determine the task type to which each completed task belongs, including: Converting the historical data of the completed tasks into a plurality of task attributes and attribute values ​​corresponding to the task attributes; Calculate the similarity between each task attribute of different completed tasks according to the attribute value; According to a preset task attribute weight coefficient, weighted sum is performed on the similarities between all task attributes of the completed tasks to obtain the distance between the completed tasks; According to the distances between the completed tasks, clustering is performed using a K-means clustering algorithm to determine the task type to which the completed tasks belong; The task type labeling unit converts the historical data of the completed task into a plurality of task attributes and attribute values ​​corresponding to the task attributes, including: Converting the historical data into text data in text form; Determining the task attributes constituting the text data through a preset expert dictionary; Using a keyword dictionary corresponding to the task attributes, a key character string in each task attribute is extracted as the attribute value.

4. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for automatic task allocation based on data statistics as described in any one of claims 1 to 2 is implemented.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to perform the method for automatic task allocation based on data statistics as described in any one of claims 1 to 2.

Images