WO2019200780A1 - 任务派发方法、电子设备及存储介质 - Google Patents

任务派发方法、电子设备及存储介质 Download PDF

Info

Publication number
WO2019200780A1
WO2019200780A1 PCT/CN2018/100018 CN2018100018W WO2019200780A1 WO 2019200780 A1 WO2019200780 A1 WO 2019200780A1 CN 2018100018 W CN2018100018 W CN 2018100018W WO 2019200780 A1 WO2019200780 A1 WO 2019200780A1
Authority
WO
WIPO (PCT)
Prior art keywords
task
type
target task
target
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/100018
Other languages
English (en)
French (fr)
Inventor
李佳琳
刘鹏
赵�怡
王健宗
肖京
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2019200780A1 publication Critical patent/WO2019200780A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/101—Collaborative creation, e.g. joint development of products or services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products

Definitions

  • the present application relates to the field of data processing, and in particular, to a task dispatching method, an electronic device, and a storage medium.
  • Crowdsourcing refers to the practice of a company or organization outsourcing the tasks performed by employees in the past to the non-specific public network in a free and voluntary manner.
  • the task of crowdsourcing is usually undertaken by individuals.
  • the distribution and effective recycling of crowdsourcing tasks is an urgent problem to be solved.
  • a task dispatching method comprising:
  • the target task is sent to at least two current users of the crowdsourcing platform.
  • the crowdsourcing platform is in communication with the identification device, and the identification device is configured to process the ticket image, obtain a key segment in the ticket image, obtain a key segment in the ticket image, and obtain the ticket
  • the key fields in the picture are sent to the crowdsourcing platform.
  • An electronic device comprising a memory and a processor, the memory for storing computer readable instructions, the processor for executing the computer readable instructions to implement the task of any of any of the embodiments Distribution method.
  • a non-volatile readable storage medium storing at least one instruction, the at least one instruction being executed by a processor, implementing the task dispatching method of any of any of the embodiments .
  • the present application classifies all tasks in the crowdsourcing platform into various task types, each of which has multiple pending tasks, and distributes each to-be-processed task to the crowdsourcing platform.
  • Multiple users perform a check to determine the accuracy of the task.
  • an interface for switching the task type is provided to the user so that the user selects a favorite task type, and the task to be processed is also assigned based on the task priority.
  • the work of the user's inspection task is evaluated. Ensure that the crowdsourcing task achieves the unity of randomness and order, and can effectively prevent users from randomly brushing the questions during the task distribution process.
  • 1 is a flow chart of a first preferred embodiment of the task assignment method of the present application.
  • FIG. 2 is a flow chart of a second preferred embodiment of the task assignment method of the present application.
  • FIG. 3 is a block diagram of a program of a first preferred embodiment of the task dispatching apparatus of the present application.
  • FIG. 4 is a block diagram showing the program of a second preferred embodiment of the task dispatching apparatus of the present application.
  • FIG. 5 is a schematic structural diagram of a preferred embodiment of an electronic device in at least one example of the present application.
  • FIG. 1 it is a flowchart of a first preferred embodiment of the task assignment method of the present application.
  • the order of the steps in the flowchart may be changed according to different requirements, and some steps may be omitted.
  • the electronic device acquires a target task type.
  • the electronic device comprises: a processing device of a crowdsourcing platform.
  • the electronic device is configured to process data of a crowdsourcing platform, and there are multiple task types in the crowdsourcing platform, and each task type has multiple pending tasks.
  • the crowdsourcing platform is in communication with the identification device, the identification device is configured to: acquire a picture to be recognized; extract a picture of the ticket from the picture to be identified; perform text detection on the picture of the ticket, determine a text position; and identify a text position Key segment at the location, determine the machine recognition result of the key segment and the confidence of the machine recognition result; based on the confidence of the machine segment recognition result of the keyword segment and the machine recognition result, obtain the keyword segment that meets the condition (such as the machine recognition result)
  • the keyword segment with a confidence lower than or equal to the confidence threshold is sent to the crowdsourcing platform.
  • the crowdsourcing platform processing device sends the same key segment to multiple users of the crowdsourcing platform.
  • a category in which the same type of key fields in the various types of tickets are located is configured with one task type.
  • the ticket number field type corresponds to the ticket number task type
  • the hospital name field category corresponds to the hospital name task type
  • the uppercase amount field category corresponds to the capital amount task type.
  • each type of key field in each type of ticket is located is configured as a task type.
  • the ticket number of the hospital ticket is configured as a task type
  • the ticket number of the catering ticket is configured as a task type.
  • the method before acquiring the target task type, the method further includes: determining whether a trigger signal for acquiring the target task type is acquired.
  • the target task type is acquired.
  • the current user includes, but is not limited to, one or a combination of the following: a user who is currently successfully logged in, an online user.
  • the crowdsourcing platform receives login instructions including user data including, but not limited to, an account, an account password.
  • the user data is matched with the stored user information.
  • the verification succeeds, and the target task type is triggered to be acquired.
  • the crowdsourcing platform provides switching controls and switching options for switching task types on the user interface.
  • the display style of the switching control includes, but is not limited to, an icon, a button member, and the like.
  • the switching options include, but are not limited to, options of various task types.
  • the target task type is acquired.
  • the crowdsourcing platform randomly selects the task type of the capital amount to the A user, the A user finds that he is not very good at the task type of the capital amount, and the A user thinks that he is better at verifying the date task type, and can be on the user interface. Click the toggle control and select the date task type in the switch options and submit it to the crowdsourcing platform. This makes it easy for users to choose the type that suits them and improve the efficiency of completing tasks.
  • the method further includes: configuring a switching authority of the switching control.
  • the switching authority includes, but is not limited to, a combination of one or more of the following: the number of times of switching of the target time period (eg, one day, two hours), and the number of times each user switches within the target time period according to the user level. For example, the higher the level, the more the number of configuration switches. This can increase the enthusiasm of users in the crowdsourcing platform to complete tasks. At the same time, and limit the number of times the target time period is switched, the user can be prevented from brushing the questions at will.
  • the user level is configured according to the total number of tasks completed by the user.
  • the total number of tasks completed by the user is 5 to 100 for the first level, 100 to 200 for the second level, and so on.
  • the target task type is acquired.
  • the configured task type is the current task type processed by the current user.
  • the crowdsourcing platform allocates a task to the current user from the to-be-processed task in the current task type, until there is no pending task in the current task type, and acquires a new task type, which is to be processed from the new task type.
  • a task is assigned to the current user in the task.
  • obtaining the target task type includes, but is not limited to, one or more of the following combinations:
  • one task type is extracted from all task types as the target task type.
  • the crowdsourcing platform randomly distributes project x (1 ⁇ x ⁇ n) to the current user; when project x After the pending tasks are all completed, the crowdsourcing platform randomly distributes project y (1 ⁇ y ⁇ n and y ⁇ x) to the current user; when the pending tasks of project y are all completed, the crowdsourcing platform randomly distributes the project z To the current user (1 ⁇ z ⁇ n and z ⁇ x ⁇ y); and so on, until the task to be processed of all task types on the line is completed.
  • A2 Based on the extraction principle, extract multiple task types (for example, two task types) from all task types, and receive one task type selected by the user from the multiple task types, and select the selected one task type. As the target task type.
  • multiple task types for example, two task types
  • the extraction principle includes, but is not limited to, one or a combination of the following: a random extraction principle, a total amount of tasks to be processed in a task type, and the like. For example, according to the total number of tasks to be processed in the task type, the task type with a large amount of tasks to be processed is preferentially allocated to the current user.
  • the task type selected by the user included in the switching instruction is used as the target task type.
  • the electronic device acquires a task allocation instruction.
  • the task assignment instruction includes, but is not limited to, a random assignment instruction, a task priority based allocation instruction.
  • the electronic device acquires a target task from the to-be-processed task in the target task type according to the task allocation instruction.
  • At least one task is randomly extracted from the to-be-processed tasks in the target task type as the target task based on a random allocation instruction.
  • the task priority includes, but is not limited to, a combination of one or more of the following: a priority based on the current number of answers of the task, wherein the less the current number of answers to the task, the higher the priority; The chronological priority of the package platform, the earlier the time to enter the crowdsourcing platform, the higher the priority. In this way, tasks are distributed according to task priorities, which can effectively ensure the recovery efficiency of tasks.
  • each task to be processed of the crowdsourcing platform is allocated to multiple users to enable multiple users to verify the same pending task, so that the accuracy of the verification result can be ensured.
  • each user corresponding to each task to be processed each user is verified once, which is the number of times of answering. For example, if three users have been verified by one pending task, the current answer of the pending task is The number of times is three.
  • the answer of each task to be processed is completed.
  • an ordered queue is formed according to the current number of answers of the task to be processed from high to low, and the pending tasks of the same number of answers are entered into the crowdsourcing platform according to the task to be processed. Time sequenced.
  • the number of current answers for each task to be processed is n-1 times, n-2 times...0 times, which is the crowdsourcing platform.
  • the user enters the crowdsourcing platform and prioritizes the pending tasks of the crowdsourcing platform that have the first number of answers. After completing all the pending tasks with only one answering opportunity in chronological order, the crowdsourcing platform automatically switches to the pending task with only 2 times of answering times in order of entering the crowdsourcing platform, and so on, until completion. All pending tasks for each task type.
  • the electronic device sends the target task to a current user of the crowdsourcing platform, and each of the task types in the crowdsourcing platform is distributed to multiple users of the crowdsourcing platform for verification. .
  • the target task is displayed on the current user's user interface.
  • the current user inputs the verification result according to the picture of the target task and the user interface provided on the user interface. For example, if the target task is a hospital name task, the "people's hospital" is input according to the picture of the hospital name task, and submitted to the crowdsourcing platform.
  • all tasks in the crowdsourcing platform are classified into various task types, and each task type has multiple pending tasks, and each pending task is distributed to multiple users of the crowdsourcing platform.
  • a check is made to determine the accuracy of the task.
  • an interface for switching the task type is provided to the user so that the user selects a favorite task type, and the task to be processed is also assigned based on the task priority.
  • the application can ensure the unification of the randomness and the order of the crowdsourcing task, and can effectively prevent the user from randomly brushing in the task distribution process, and at the same time ensure the timeliness of the massive crowdsourcing task recovery.
  • FIG. 2 is a flow chart of a second preferred embodiment of the task assignment method of the present application.
  • the order of the steps in the flowchart may be changed according to different requirements, and some steps may be omitted.
  • S20 to S23 correspond to S10 to S13 in the first preferred embodiment of FIG. 1, respectively, and will not be described in detail herein.
  • the electronic device receives multiple verification results output by the current user of the target task, and determines a recognition result of the target task.
  • a check result exceeding a number of people thresholds among the plurality of test results is taken as a recognition result of each task to be processed. For example, if a date field task is sent to three users, if three users have three different answers to the verification result of the date field task, it is determined that there is no correct result, if two users have two users The answer is the same, the answer of the two users is used as the test result of the date field task.
  • a prompt that cannot be verified is sent to the device of the provider (reimbursement personnel) of the to-be-processed task to The provider of the to-be-processed task is re-uploaded with the task picture to ensure the accuracy of the task identification.
  • the electronic device evaluates a current user that verifies the target task based on the recognition result of the target task.
  • the current user score corresponding to the same test result as the recognition result of the target task is higher than the current user score corresponding to the test result different from the recognition result of the target task.
  • the user level is configured according to the user's rating. For example, the more the user's test results are correct, the higher the score, the higher the level, and the more times the user can get the type of the switch task, thus more effectively motivating the user to actively complete the task.
  • the tasks to be processed in the crowdsourcing platform are assigned according to user levels. For example, when the number of current users in the crowdsourcing platform is greater than the number of tasks to be processed, if the number of tasks in the crowdsourcing platform is insufficient, the user requirements with relatively high user levels are preferentially satisfied. This will more effectively motivate users to complete more tasks on the crowdsourcing platform.
  • the user level is configured according to the time data of the user, and the time data includes, but is not limited to, a time when the user completes each task, a duration of the user logging in to the crowdsourcing platform, and a task performed by the user on the crowdsourcing platform.
  • the duration for example, the user does the task on the crowdsourcing platform every day, so that you can configure the higher level
  • the continuity of the task performed by the user on the crowdsourcing platform can be further evaluated to further motivate the user to become a stable user of the crowdsourcing platform.
  • the present application classifies all tasks in the crowdsourcing platform into various task types, each of which has multiple tasks to be processed, and distributes each task to be distributed to the crowdsourcing platform. Multiple users perform a check to determine the accuracy of the task. At the same time, an interface for switching the task type is provided to the user so that the user selects a favorite task type, and the task to be processed is also assigned based on the task priority. After the user completes the task verification, and based on the correct answer of the task and the verification result of the user, the work of the user's inspection task is evaluated.
  • the application can ensure the unification of randomness and order in the crowdsourcing task, and can effectively prevent the user from randomly brushing the behavior during the task distribution process, and at the same time ensure the timeliness of the massive crowdsourcing task recovery.
  • the task dispatching device 3 includes, but is not limited to, one or more of the following modules: an obtaining module 30, a configuration module 31, a determining module 32, a triggering module 33, a distributing module 34, and a display module 35.
  • a unit referred to in this application refers to a series of computer readable instruction segments that can be executed by a processor of the task dispatching device 3 and capable of performing a fixed function, which is stored in a memory. The function of each module will be detailed in the subsequent embodiments.
  • the obtaining module 30 acquires a target task type.
  • the electronic device comprises: a processing device of a crowdsourcing platform.
  • the electronic device is configured to process data of a crowdsourcing platform, and there are multiple task types in the crowdsourcing platform, and each task type has multiple pending tasks.
  • the crowdsourcing platform is in communication with the identification device, the identification device is configured to: acquire a picture to be recognized; extract a picture of the ticket from the picture to be identified; perform text detection on the picture of the ticket, determine a text position; and identify a text position Key segment at the location, determine the machine recognition result of the key segment and the confidence of the machine recognition result; based on the confidence of the machine segment recognition result of the keyword segment and the machine recognition result, obtain the keyword segment that meets the condition (such as the machine recognition result)
  • the keyword segment with a confidence lower than or equal to the confidence threshold is sent to the crowdsourcing platform.
  • the crowdsourcing platform processing device sends the same key segment to multiple users of the crowdsourcing platform.
  • the configuration module 31 configures a category of the same type of key fields in the various types of tickets in a task type.
  • the ticket number field category corresponds to the ticket number task type
  • the hospital name field category corresponding to the hospital name task type
  • the uppercase amount field category corresponds to the uppercase amount task type.
  • the configuration module 31 configures a category in which each type of key field in each type of ticket is located as one task type. For example, the ticket number of the hospital ticket is configured as a task type, and the ticket number of the catering ticket is configured as a task type.
  • the determining module 32 determines whether a trigger signal for acquiring the target task type is acquired.
  • triggering module 33 to trigger the acquisition of the target task type, including, but not limited to, one or more of the following combinations:
  • the target task type is acquired.
  • the current user includes, but is not limited to, one or a combination of the following: a user who is currently successfully logged in, an online user.
  • the crowdsourcing platform receives login instructions including user data including, but not limited to, an account, an account password.
  • the user data is matched with the stored user information.
  • the verification succeeds, and the target task type is triggered to be acquired.
  • the crowdsourcing platform provides switching controls and switching options for switching task types on the user interface.
  • the display style of the switching control includes, but is not limited to, an icon, a button member, and the like.
  • the switching options include, but are not limited to, options of various task types.
  • the target task type is acquired.
  • the crowdsourcing platform randomly selects the task type of the capital amount to the A user, the A user finds that he is not very good at the task type of the capital amount, and the A user thinks that he is better at verifying the date task type, and can be on the user interface. Click the toggle control and select the date task type in the switch options and submit it to the crowdsourcing platform. This makes it easy for users to choose the type that suits them and improve the efficiency of completing tasks.
  • the configuration module is further configured to: configure a switching authority of the switching control.
  • the switching authority includes, but is not limited to, a combination of one or more of the following: the number of times of switching of the target time period (eg, one day, two hours), and the number of times each user switches within the target time period according to the user level. For example, the higher the level, the more the number of configuration switches. This can increase the enthusiasm of users in the crowdsourcing platform to complete tasks. At the same time, and limit the number of times the target time period is switched, the user can be prevented from brushing the questions at will.
  • the configuration module 31 configures a user level according to the total number of tasks completed by the user. For example, the total number of tasks completed by the user is 5 to 100 for the first level, 100 to 200 for the second level, and so on.
  • the target task type is acquired.
  • the configured task type is the current task type processed by the current user.
  • the crowdsourcing platform allocates a task to the current user from the to-be-processed task in the current task type, until there is no pending task in the current task type, and acquires a new task type, which is to be processed from the new task type.
  • a task is assigned to the current user in the task.
  • the acquiring the target task type by the obtaining module 30 includes, but is not limited to, one or more of the following combinations:
  • one task type is extracted from all task types as the target task type.
  • the crowdsourcing platform randomly distributes project x (1 ⁇ x ⁇ n) to the current user; when project x After the pending tasks are all completed, the crowdsourcing platform randomly distributes project y (1 ⁇ y ⁇ n and y ⁇ x) to the current user; when the pending tasks of project y are all completed, the crowdsourcing platform randomly distributes the project z To the current user (1 ⁇ z ⁇ n and z ⁇ x ⁇ y); and so on, until the task to be processed of all task types on the line is completed.
  • A2 Based on the extraction principle, extract multiple task types (for example, two task types) from all task types, and receive one task type selected by the user from the multiple task types, and select the selected one task type. As the target task type.
  • multiple task types for example, two task types
  • the extraction principle includes, but is not limited to, one or a combination of the following: a random extraction principle, a total amount of tasks to be processed in a task type, and the like. For example, according to the total number of tasks to be processed in the task type, the task type with a large amount of tasks to be processed is preferentially allocated to the current user.
  • the task type selected by the user included in the switching instruction is used as the target task type.
  • the acquisition module 30 acquires a task assignment instruction.
  • the task assignment instruction includes, but is not limited to, a random assignment instruction, a task priority based allocation instruction.
  • the obtaining module 30 acquires a target task from the to-be-processed tasks in the target task type according to the task allocation instruction.
  • the obtaining module 30 randomly extracts at least one task from the to-be-processed tasks in the target task type as the target task based on a random allocation instruction.
  • the task priority includes, but is not limited to, a combination of one or more of the following: a priority based on the current number of answers of the task, wherein the less the current number of answers to the task, the higher the priority; The chronological priority of the package platform, the earlier the time to enter the crowdsourcing platform, the higher the priority. In this way, tasks are distributed according to task priorities, which can effectively ensure the recovery efficiency of tasks.
  • each task to be processed of the crowdsourcing platform is assigned to multiple users to verify the same pending task by multiple users, so as to ensure the accuracy of the verification result.
  • each user For each user corresponding to each task to be processed, each user is verified once, which is the number of times of answering. For example, if three users have been verified by one pending task, the current answer of the pending task is The number of times is three.
  • the answer of each task to be processed is completed.
  • an ordered queue is formed according to the current number of answers of the task to be processed from high to low, and the pending tasks of the same number of answers are entered into the crowdsourcing platform according to the task to be processed. Time sequenced.
  • the number of current answers for each task to be processed is n-1 times, n-2 times...0 times, which is the crowdsourcing platform.
  • the user enters the crowdsourcing platform and prioritizes the pending tasks of the crowdsourcing platform that have the first number of answers. After completing all the pending tasks with only one answering opportunity in chronological order, the crowdsourcing platform automatically switches to the pending task with only 2 times of answering times in order of entering the crowdsourcing platform, and so on, until completion. All pending tasks for each task type.
  • the distribution module 34 sends the target task to the current user of the crowdsourcing platform, and each of the task types in the crowdsourcing platform is distributed to a plurality of users of the crowdsourcing platform for verification.
  • the target task is displayed on the current user's user interface.
  • the current user inputs the verification result according to the picture of the target task and the user interface provided on the user interface. For example, if the target task is a hospital name task, the "people's hospital" is input according to the picture of the hospital name task, and submitted to the crowdsourcing platform.
  • all tasks in the crowdsourcing platform are classified into various task types, and each task type has multiple pending tasks, and each pending task is distributed to multiple users of the crowdsourcing platform.
  • a check is made to determine the accuracy of the task.
  • an interface for switching the task type is provided to the user so that the user selects a favorite task type, and the task to be processed is also assigned based on the task priority.
  • the application can ensure the unification of randomness and order in the crowdsourcing task, and can effectively prevent the user from randomly brushing the behavior during the task distribution process, and at the same time ensure the timeliness of the massive crowdsourcing task recovery.
  • the task dispatching device 3 includes the one or more modules in the first preferred embodiment: the acquisition module 30, the configuration module 31, the determination module 32, the trigger module 33, the distribution module 34, and the display module 35, the task
  • the dispatching device 3 may also include one or more of the following modules: a receiving module 36, a determining module 37, a prompting module 38, and an evaluation module 39.
  • a unit referred to in this application refers to a series of computer readable instruction segments that can be executed by a processor of the task dispatching device 3 and capable of performing a fixed function, which is stored in a memory. The function of each module will be detailed in the subsequent embodiments.
  • the receiving module 36 receives a plurality of verification results output by the current user of the target task, and determines a recognition result of the target task.
  • the determining module 37 takes, as a recognition result of each to-be-processed task, a check result exceeding a number of people thresholds among the plurality of test results for each task to be processed. For example, if a date field task is sent to three users, if three users have three different answers to the verification result of the date field task, it is determined that there is no correct result, if two users have two users The answer is the same, the answer of the two users is used as the test result of the date field task.
  • the prompting module 38 sends, for each task to be processed, a verification result that exceeds the number of people thresholds in the plurality of inspection results, and sends a prompt that cannot be verified to the provider of the to-be-processed task (reimbursement personnel)
  • the provider of the task to be processed is re-uploaded with the task picture, thereby ensuring the accuracy of the task recognition.
  • the evaluation module 39 evaluates the current user who verifies the target task based on the recognition result of the target task.
  • the evaluation module 39 scores the current user corresponding to the test result identical to the recognition result of the target task, and the current user score corresponding to the test result that is different from the recognition result of the target task. In this way, the more the user's test results are correct, the higher the score, the more the user can avoid the problem of answering questions in order to improve the speed of answering questions.
  • the configuration module 31 configures the user level according to the user's rating. For example, the more the user's test result is correct, the higher the score, the higher the level, and the more times the user can obtain the type of the switch task, thus more effectively motivating the user to actively complete the task.
  • the distribution module 34 assigns pending tasks in the crowdsourcing platform according to user ratings. For example, when the number of current users in the crowdsourcing platform is greater than the number of tasks to be processed, if the number of tasks in the crowdsourcing platform is insufficient, the user requirements with relatively high user levels are preferentially satisfied. This will more effectively motivate users to complete more tasks on the crowdsourcing platform.
  • the configuration module 31 configures a user level according to time data of the user, where the time data includes, but is not limited to, a time when the user completes each task, a duration of the user logging in to the crowdsourcing platform, and the user is in the The duration of the task of the crowdsourcing platform (for example, the user does the task on the crowdsourcing platform every day, so that you can configure the higher level) and so on.
  • the continuity of the task performed by the user on the crowdsourcing platform can be further evaluated to further motivate the user to become a stable user of the crowdsourcing platform.
  • the present application classifies all tasks in the crowdsourcing platform into various task types, each of which has multiple tasks to be processed, and distributes each task to be distributed to the crowdsourcing platform. Multiple users perform a check to determine the accuracy of the task. At the same time, an interface for switching the task type is provided to the user so that the user selects a favorite task type, and the task to be processed is also assigned based on the task priority. After the user completes the task verification, and based on the correct answer of the task and the verification result of the user, the work of the user's inspection task is evaluated.
  • the application can ensure the unification of randomness and order in the crowdsourcing task, and can effectively prevent the user from randomly brushing the behavior during the task distribution process, and at the same time ensure the timeliness of the massive crowdsourcing task recovery.
  • the above-described integrated unit implemented in the form of a software program module can be stored in a non-volatile readable storage medium.
  • the software program module described above is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the method of each embodiment of the present application. Part of the steps.
  • the electronic device 5 comprises at least one transmitting device 51, at least one memory 52, at least one processor 53, at least one receiving device 54, and at least one communication bus.
  • the communication bus is used to implement connection communication between these components.
  • the electronic device 5 is a device capable of automatically performing numerical calculation and/or information processing according to an instruction set or stored in advance, and the hardware includes, but not limited to, a microprocessor, an application specific integrated circuit (ASIC). ), Field-Programmable Gate Array (FPGA), Digital Signal Processor (DSP), embedded devices, etc.
  • the electronic device 5 may also comprise a network device and/or a user device.
  • the network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud computing-based cloud composed of a large number of hosts or network servers, where the cloud computing is distributed computing.
  • a super virtual computer consisting of a group of loosely coupled computers.
  • the electronic device 5 can be, but is not limited to, any electronic product that can interact with a user through a keyboard, a touch pad, or a voice control device, such as a tablet, a smart phone, or a personal digital assistant (Personal Digital Assistant). , PDA), smart wearable devices, camera equipment, monitoring equipment and other terminals.
  • a keyboard e.g., a keyboard
  • a touch pad e.g., a touch pad
  • a voice control device such as a tablet, a smart phone, or a personal digital assistant (Personal Digital Assistant). , PDA), smart wearable devices, camera equipment, monitoring equipment and other terminals.
  • PDA Personal Digital Assistant
  • the network in which the electronic device 5 is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • the Internet includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • VPN virtual private network
  • the receiving device 54 and the sending device 51 may be wired transmission ports, or may be wireless devices, for example, including antenna devices, for performing data communication with other devices.
  • the memory 52 is used to store program code.
  • the memory 52 may be a circuit having a storage function, such as a RAM (Random-Access Memory), a FIFO (First In First Out), or the like, which is not in a physical form in the integrated circuit.
  • the memory 52 may also be a memory having a physical form, such as a memory stick, a TF card (Trans-flash Card), a smart media card, a secure digital card, a flash memory card.
  • Storage devices such as (flash card) and the like.
  • the processor 53 can include one or more microprocessors, digital processors.
  • the processor 53 can call program code stored in the memory 52 to perform related functions.
  • the various modules described in Figures 3 and 4 are program code stored in the memory 52 and executed by the processor 53 to implement a task dispatch method.
  • the processor 53 also known as a central processing unit (CPU), is a very large-scale integrated circuit, which is a computing core (Core) and a control unit (Control Unit).
  • the embodiment of the present application further provides a non-volatile readable storage medium having stored thereon computer instructions that, when executed by an electronic device including one or more processors, cause the electronic device to perform the method as described above
  • the task dispatch method described in the example is not limited to:
  • the memory 52 in the electronic device 5 stores a plurality of instructions to implement a task dispatching method, and the processor 53 can execute the plurality of instructions to implement:
  • the crowdsourcing platform is in communication with the identification device, and the identification device is configured to process the ticket image, obtain a key segment in the ticket image, and send the key segment in the ticket image to the identification. device.
  • the plurality of instructions executable by the processor 53 are further configured to: configure a category of a category of the same type of key segments in each type of ticket by one task type; or, each The category in which each type of key field in the type ticket is located is configured as a task type.
  • the plurality of instructions executable by the processor 53 are further configured to: before acquiring the target task type, the method further includes: determining whether acquiring the target task type is acquired Trigger signal
  • the manner of triggering the acquisition of the target task type includes one or more of the following combinations:
  • the target task type is acquired.
  • the acquiring the target task type comprises one or a combination of the following:
  • the task type selected by the user included in the switching instruction is used as the target task type.
  • the task assignment instruction includes a random assignment instruction, a task priority based allocation instruction;
  • the task priority includes: a priority based on a current number of answers of the task, and the number of current answers of the task is less, The higher the priority; based on the priority of the chronological order of the tasks entering the crowdsourcing platform, the earlier the time to enter the crowdsourcing platform, the higher the priority.
  • the plurality of instructions executable by the processor 53 are further used to implement:
  • the current user who verifies the target task is evaluated based on the recognition result of the target task.
  • the receiving the plurality of verification results output by the current user of the target task, and determining the recognition result of the target task includes:
  • a verification result exceeding a number of people thresholds among the corresponding plurality of test results of the target task is used as a recognition result of the target task.
  • the plurality of instructions corresponding to the task dispatch method are stored in the memory 52 in any of the embodiments and executed by the processor 53, and are not described in detail herein.
  • the above-described characteristic means of the present application can be implemented by an integrated circuit and control the functions of the task dispatching method described in any of the above embodiments. That is, the integrated circuit of the present application is installed in the electronic device, so that the electronic device performs the following functions: acquiring a target task type; acquiring a task assignment instruction; and executing a task to be processed from the target task type according to the task assignment instruction Obtaining a target task; sending the target task to at least two current users of the crowdsourcing platform.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application 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 integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a non-volatile readable storage medium.
  • a computer device which may be a personal computer, server or network device, etc.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提供一种任务派发方法，所述方法包括：获取目标任务类型；获取任务分配指令；根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；将所述目标任务发送至众包平台的至少两个以上的当前用户。本申请还提供一种电子设备及存储介质。本申请能保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷题行为。

Description

任务派发方法、电子设备及存储介质
本申请要求于2018年04月18日提交中国专利局，申请号为201810351125.7发明名称为“任务派发方法、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理领域，尤其涉及一种任务派发方法、电子设备及存储介质。
背景技术
众包是指一个公司或机构把过去由员工执行的工作任务，以自由自愿的形式外包给非特定的大众网络的做法，众包的任务通常由个人来承担。但众包任务的派发及有效回收是急需解决的问题。
发明内容
鉴于以上内容，有必要提供一种任务派发方法、电子设备及存储介质，能能保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷题行为。
一种任务派发方法，所述方法包括：
获取目标任务类型；
获取任务分配指令；
根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；
将所述目标任务发送至众包平台的至少两个以上的当前用户。
根据本申请优选实施例，所述众包平台与识别设备相通信，所述识别设备用于对票据图片进行处理，得到票据图片中的关键字段，得到票据图片中的关键字段，将票据图片中的关键字段发送给所述众包平台。
一种电子设备，所述电子设备包括存储器及处理器，所述存储器用于存储计算机可读指令，所述处理器用于执行所述计算机可读指令以实现任意实施例中任一项所述任务派发方法。
一种非易失性可读存储介质，所述非易失性可读存储介质存储有至少一个指令，所述至少一个指令被处理器执行时实现任意实施例中任一项所述任务派发方法。
由以上技术方案可知，本申请将众包平台中所有任务分类成各种不同的任务类型，每个任务类型中有多种待处理任务，将每个待处理任务分发至所述众包平台的多个用户进行校验以确定任务的准确度。同时提供切换任务类型的接口给用户以便用户选择喜欢的任务类型，还基于任务优先级分配待处理任务。在用户对任务检验完成后，并基于任务的正确答案及用户的校验结果，对用户的检验任务的工作进行评价。保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷题行为。
附图说明
图1是本申请任务派发方法的第一较佳实施例的流程图。
图2是本申请任务派发方法的第二较佳实施例的流程图。
图3是本申请任务派发装置的第一较佳实施例的程序模块图。
图4是本申请任务派发装置的第二较佳实施例的程序模块图。
图5是本申请至少一个实例中电子设备的较佳实施例的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
为使本申请的上述目的、特征和优点能够更加明显易懂，下面结合附图和具体实施方式对本申请作进一步详细的说明。
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”和“第三”等是用于区别不同对象，而非用于描述特定顺序。此外，术语“包括”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
如图1所示，是本申请任务派发方法的第一较佳实施例的流程图。根据不同的需求，该流程图中步骤的顺序可以改变，某些步骤可以省略。
S10、电子设备获取目标任务类型。
在可选实施例中，所述电子设备包括：众包平台的处理设备。所述电子设备用于处理众包平台的数据，在所述众包平台中有多种任务类型，每种任务类型有多个待处理任务。
优选地，所述众包平台与识别设备相通信，所述识别设备用于：获取待识别图片；从待识别图片中提取票据图片；并对票据图片进行文本检测，确定文本位置；识别文本位置处的关键字段，确定关键字段的机器识别结果及机器识别结果的置信度；基于关键字段的机器识别结果及机器识别结果的置信度，获取符合条件的关键字段(如机器识别结果的置信度低于或者等于置信阈值的关键字段)，将符合条件的关键字段发送至众包平台。所述众包平台处理设备将同一个关键字段发送至众包平台的多个用户。
进一步地，将各种类型票据中相同类型的关键字段所在的类别配置一个任务类型。例如，票据单号字段类别对应票据单号任务类型、医院名称字段类别对应医院名称任务类型、大写金额字段类别对应大写金额任务类型。在票据单号任务类型下有各种类型票据的票据单号的校验，例如，医院票据的票据单号、餐饮票据的票据单号等等。
进一步地，将每种类型票据中每种类型的关键字段所在的类别配置成一 个任务类型。例如，将医院票据的票据单号配置成一个任务类型，餐饮票据的票据单号配置成一个任务类型。
优选地，在获取所述目标任务类型之前，所述方法还包括：判断是否获取到获取所述目标任务类型的触发信号。
进一步地，触发获取所述目标任务类型的方式有很多种，包括，但不限于以下一种或者多种的组合：
(1)当获取到当前用户登录所述众包平台的登录指令时，则获取所述目标任务类型。所述当前用户包括，但不限于以下一种或者多种的组合：当前登录成功的用户、在线用户。例如，众包平台接收包含用户数据的登录指令，所述用户数据包括，但不限于：账户、账户密码。将所述用户数据与存储的用户信息进行匹配，当存储的用户信息中有与所述用户数据匹配的数据时，则验证成功，触发获取所述目标任务类型。
(2)当获取到当前用户的切换任务类型的切换指令时，则获取所述目标任务类型。
优选地，所述众包平台在用户界面上提供用于切换任务类型的切换控件及切换选项。所述切换控件的显示样式包括，但不限于：图标、按钮件等等。所述切换选项包括：但不限于各种任务类型的选项。当获取到用户触控所述切换控件而生成的切换指令时，则获取所述目标任务类型。例如，当众包平台随机选择了大写金额的任务类型给A用户，A用户发现自己不太擅长做大写金额的任务类型，A用户认为自己比较擅长日期任务类型的校验，则可以在用户界面上点击切换控件，并在切换选项中选择日期任务类型，并提交给众包平台。这样可以便于用户选择适合自己的类型，提高完成任务的效率。
进一步地，所述方法还包括：配置所述切换控件的切换权限。所述切换权限包括，但不限于以下一种或者多种的组合：目标时间段(如一天，两个小时)的切换次数、根据用户等级配置每个用户在目标时间段内的切换次数。例如，等级越高，配置的切换次数越多。这样可以提高众包平台中用户完成任务的积极性。同时并限制目标时间段的切换次数，可以防止用户随意刷题。
进一步地，根据用户完成的任务总量配置用户等级。例如用户完成的任务总量在5-100件为一级、100-200件为二级等等。
(3)当获取到当前用户的当前任务类型没有待处理任务时，则获取所述目标任务类型。在给当前用户配置一个任务类型后，所述配置的任务类型即为所述当前用户处理的当前任务类型。所述众包平台从当前任务类型中的待处理任务中分配任务给所述当前用户，直至所述当前任务类型中没有待处理任务，则获取新的任务类型，从新的任务类型中的待处理任务中分配任务给所述当前用户。
优选地，获取所述目标任务类型包括，但不限于以下一种或多种的组合：
A1、基于抽取原则，从所有任务类型中抽取一个任务类型作为所述目标任务类型。
进一步地，假设众包平台上有n(n≥1)个任务类型，第n个任务类型记为project n；众包平台随机派发project x(1≤x≤n)给当前用户；当project x 的待处理任务被全部完成后，众包平台随机派发project y(1≤y≤n且y≠x)给当前用户；当project y的待处理任务被全部完成后，众包平台随机派发project z给当前用户(1≤z≤n且z≠x≠y)；以此类推，直至线上所有任务类型的待处理任务被完成。
A2、基于抽取原则，从所有任务类型中抽取多个任务类型(例如，两个任务类型)，并接收用户从所述多个任务类型中选取的一个任务类型，将所述选取的一个任务类型作为所述目标任务类型。
进一步地，所述抽取原则包括，但不限于以下一种或者多种的组合：随机抽取原则，按照任务类型中待处理任务的总量等等。例如，按照任务类型中待处理任务的总量，优先分配待处理任务的总量多的任务类型给当前用户。
A3、当获取到当前用户的切换任务类型的切换指令时，将所述切换指令中包含的用户选中的任务类型作为所述目标任务类型。
S11、所述电子设备获取任务分配指令。
优选地，所述任务分配指令包括，但不限于：随机分配指令、基于任务优先级的分配指令。
S12、所述电子设备根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务。
优选地，基于随机分配指令，从所述目标任务类型中的待处理任务中随机抽取至少一个任务作为所述目标任务。
优选地，所述任务优先级包括，但不限于以下一种或者多种的组合：基于任务的当前答题次数的优先级，其中任务的当前答题次数越少，优先级越高；基于任务进入众包平台的时间顺序的优先级，其中进入众包平台的时间越早，优先级越高。这样按照任务优先级分发任务，可以有效地保证任务的回收效率。
进一步地，所述众包平台的每个待处理任务会分配给多个用户以使多个用户对同一个待处理任务进行校验，这样可以保证校验结果的准确度。对于每个待处理任务对应的多个用户，每个用户校验一次，即为一次答题次数，例如若一个待处理任务已经有3个用户进行了校验，则所述待处理任务的当前答题次数为3次。当每个待处理任务对应的多个用户都完成了校验，则每个待处理任务的答题完成。
在可选实施例中，具体地，对于每个任务类型，按待处理任务的当前答题次数从高到低形成有序队列，相同答题次数的待处理任务则按待处理任务进入众包平台的时间顺序排列。
在一个待处理任务需要派发给n个用户进行交叉验证时，按照每个待处理任务的当前答题次数从高到低依次为n-1次，n-2次……0次，即众包平台优先分发当前答题次数n-1次的待处理任务给当前用户，在分发当前答题次数是n-2次的待处理任务，以此类推，最后是当前答题次数为0的待处理任务。从用户角度看，用户进入众包平台，优先完成只剩1次答题次数的最先进入众包平台的待处理任务。当按时间顺序完成所有只剩1次答题机会的待处理任务后，众包平台自动切换到只剩2次答题次数按进入众包平台的时间 顺序排列的待处理任务，以此类推，直至完成每个任务类型的所有待处理任务。
S13、所述电子设备将所述目标任务发送至众包平台的当前用户，所述众包平台中每种任务类型中每个待处理任务分发至所述众包平台的多个用户进行校验。
将所述目标任务分发给所述当前用户后，在当前用户的用户界面上显示所述目标任务。当前用户根据所述目标任务的图片，并在用户界面上提供的用户接口输入校验结果。例如所述目标任务为医院名称任务，则根据医院名称任务的图片，输入“人民医院”，并提交至所述众包平台。
由以上实施例，将众包平台中所有任务分类成各种不同的任务类型，每个任务类型中有多种待处理任务，将每个待处理任务分发至所述众包平台的多个用户进行校验以确定任务的准确度。同时提供切换任务类型的接口给用户以便用户选择喜欢的任务类型，还基于任务优先级分配待处理任务。本申请能保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷分，同时保证海量众包任务回收的时效性。
如图2所示，是本申请任务派发方法的第二较佳实施例的流程图。根据不同的需求，该流程图中步骤的顺序可以改变，某些步骤可以省略。
S20至S23分别与图1中的第一较佳实施例中的S10至S13对应，在此不再详述。
S24、所述电子设备接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果。
优选地，对于每个待处理任务，将多个检验结果中超过人数阈值的校验结果作为每个待处理任务的识别结果。例如，将一个日期字段任务发送给三个用户，若三个用户对所述日期字段任务的校验结果有三个不同的答案，则确定没有正确结果，若三个用户中，有两个用户的答案相同，则将两个用户的答案作为日期字段任务的检验结果。
进一步地，根据每个待处理任务对应的多个用户的数量配置所述人数阈值。例如一个待处理任务需要由10个用户进行校验，则所述人数阈值为10*0.8＝8。
优选地，对于每个待处理任务，在多个检验结果中，不存在超过人数阈值的校验结果时，发送无法检验的提示至所述待处理任务的提供者(报销人员)的设备中以使所述待处理任务的提供者重新上传任务图片，从而保证任务识别的精度。
S25、所述电子设备基于所述目标任务的识别结果，评价校验所述目标任务的当前用户。
优选地，将对与所述目标任务的识别结果相同的检验结果对应的当前用户评分高于对与所述目标任务的识别结果不相同的检验结果对应的当前用户评分。这样用户对任务的检验结果正确的越多，评分越高，可以避免用户为了提高答题速度，随便乱答题。
优选地，根据用户的评分配置用户等级。例如，用户对任务的检验结果 正确的越多，评分越高，等级就越高，用户能获取的切换任务类型的次数就越多，从而更有效的激励用户积极地完成任务。
优选地，根据用户等级分配所述众包平台中的待处理任务。例如，当所述众包平台中当前用户数大于待处理任务的数量时，则所述众包平台中的任务数量不够，则优先满足用户等级比较高的用户需求。这样能更有效地激励用户在众包平台上更准确的完成更多的任务数量。
进一步地，根据用户的时间数据配置用户等级，所述时间数据包括，但不限于：用户完成每个任务的时间、用户登录所述众包平台的持续时间、用户在所述众包平台做任务的持续时间(例如用户每天都在众包平台上做任务，这样就可以配置较高等级)等等。这样根据用户的时间数据，可以进一步评估用户在所述众包平台上做任务的持续性，以进一步激励用户成为所述众包平台的稳定用户。
由以上实施例可知，本申请将众包平台中所有任务分类成各种不同的任务类型，每个任务类型中有多种待处理任务，将每个待处理任务分发至所述众包平台的多个用户进行校验以确定任务的准确度。同时提供切换任务类型的接口给用户以便用户选择喜欢的任务类型，还基于任务优先级分配待处理任务。在用户对任务检验完成后，并基于任务的正确答案及用户的校验结果，对用户的检验任务的工作进行评价。本申请能保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷分行为，同时保证海量众包任务回收的时效性。
如图3所示，本申请任务派发装置的第一较佳实施例的程序模块图。所述任务派发装置3包括，但不限于以下一个或者多个模块：获取模块30、配置模块31、判断模块32、触发模块33、分发模块34及显示模块35。本申请所称的单元是指一种能够被任务派发装置3的处理器所执行并且能够完成固定功能的一系列计算机可读指令段，其存储在存储器中。关于各模块的功能将在后续的实施例中详述。
所述获取模块30获取目标任务类型。
在可选实施例中，所述电子设备包括：众包平台的处理设备。所述电子设备用于处理众包平台的数据，在所述众包平台中有多种任务类型，每种任务类型有多个待处理任务。
优选地，所述众包平台与识别设备相通信，所述识别设备用于：获取待识别图片；从待识别图片中提取票据图片；并对票据图片进行文本检测，确定文本位置；识别文本位置处的关键字段，确定关键字段的机器识别结果及机器识别结果的置信度；基于关键字段的机器识别结果及机器识别结果的置信度，获取符合条件的关键字段(如机器识别结果的置信度低于或者等于置信阈值的关键字段)，将符合条件的关键字段发送至众包平台。所述众包平台处理设备将同一个关键字段发送至众包平台的多个用户。
进一步地，所述配置模块31将各种类型票据中相同类型的关键字段所在的类别配置一个任务类型。例如，票据单号字段类别对应票据单号任务类型、医院名称字段类别对应医院名称任务类型、大写金额字段类别对应大写 金额任务类型。在票据单号任务类型下有各种类型票据的票据单号的校验，例如，医院票据的票据单号、餐饮票据的票据单号等等。
进一步地，所述配置模块31将每种类型票据中每种类型的关键字段所在的类别配置成一个任务类型。例如，将医院票据的票据单号配置成一个任务类型，餐饮票据的票据单号配置成一个任务类型。
优选地，在获取所述目标任务类型之前，所述判断模块32判断是否获取到获取所述目标任务类型的触发信号。
进一步地，所述触发模块33触发获取所述目标任务类型的方式有很多种，包括，但不限于以下一种或者多种的组合：
(1)当获取到当前用户登录所述众包平台的登录指令时，则获取所述目标任务类型。所述当前用户包括，但不限于以下一种或者多种的组合：当前登录成功的用户、在线用户。例如，众包平台接收包含用户数据的登录指令，所述用户数据包括，但不限于：账户、账户密码。将所述用户数据与存储的用户信息进行匹配，当存储的用户信息中有与所述用户数据匹配的数据时，则验证成功，触发获取所述目标任务类型。
(2)当获取到当前用户的切换任务类型的切换指令时，则获取所述目标任务类型。
优选地，所述众包平台在用户界面上提供用于切换任务类型的切换控件及切换选项。所述切换控件的显示样式包括，但不限于：图标、按钮件等等。所述切换选项包括：但不限于各种任务类型的选项。当获取到用户触控所述切换控件而生成的切换指令时，则获取所述目标任务类型。例如，当众包平台随机选择了大写金额的任务类型给A用户，A用户发现自己不太擅长做大写金额的任务类型，A用户认为自己比较擅长日期任务类型的校验，则可以在用户界面上点击切换控件，并在切换选项中选择日期任务类型，并提交给众包平台。这样可以便于用户选择适合自己的类型，提高完成任务的效率。
进一步地，所述配置模块还用于：配置所述切换控件的切换权限。所述切换权限包括，但不限于以下一种或者多种的组合：目标时间段(如一天，两个小时)的切换次数、根据用户等级配置每个用户在目标时间段内的切换次数。例如，等级越高，配置的切换次数越多。这样可以提高众包平台中用户完成任务的积极性。同时并限制目标时间段的切换次数，可以防止用户随意刷题。
进一步地，所述配置模块31根据用户完成的任务总量配置用户等级。例如用户完成的任务总量在5-100件为一级、100-200件为二级等等。
(3)当获取到当前用户的当前任务类型没有待处理任务时，则获取所述目标任务类型。在给当前用户配置一个任务类型后，所述配置的任务类型即为所述当前用户处理的当前任务类型。所述众包平台从当前任务类型中的待处理任务中分配任务给所述当前用户，直至所述当前任务类型中没有待处理任务，则获取新的任务类型，从新的任务类型中的待处理任务中分配任务给所述当前用户。
优选地，所述获取模块30获取所述目标任务类型包括，但不限于以下一 种或者多种的组合：
A1、基于抽取原则，从所有任务类型中抽取一个任务类型作为所述目标任务类型。
进一步地，假设众包平台上有n(n≥1)个任务类型，第n个任务类型记为project n；众包平台随机派发project x(1≤x≤n)给当前用户；当project x的待处理任务被全部完成后，众包平台随机派发project y(1≤y≤n且y≠x)给当前用户；当project y的待处理任务被全部完成后，众包平台随机派发project z给当前用户(1≤z≤n且z≠x≠y)；以此类推，直至线上所有任务类型的待处理任务被完成。
A2、基于抽取原则，从所有任务类型中抽取多个任务类型(例如，两个任务类型)，并接收用户从所述多个任务类型中选取的一个任务类型，将所述选取的一个任务类型作为所述目标任务类型。
进一步地，所述抽取原则包括，但不限于以下一种或者多种的组合：随机抽取原则，按照任务类型中待处理任务的总量等等。例如，按照任务类型中待处理任务的总量，优先分配待处理任务的总量多的任务类型给当前用户。
A3、当获取到当前用户的切换任务类型的切换指令时，将所述切换指令中包含的用户选中的任务类型作为所述目标任务类型。
所述获取模块30获取任务分配指令。
优选地，所述任务分配指令包括，但不限于：随机分配指令、基于任务优先级的分配指令。
所述获取模块30根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务。
优选地，所述获取模块30基于随机分配指令，从所述目标任务类型中的待处理任务中随机抽取至少一个任务作为所述目标任务。
优选地，所述任务优先级包括，但不限于以下一种或者多种的组合：基于任务的当前答题次数的优先级，其中任务的当前答题次数越少，优先级越高；基于任务进入众包平台的时间顺序的优先级，其中进入众包平台的时间越早，优先级越高。这样按照任务优先级分发任务，可以有效地保证任务的回收效率。
进一步地，所述众包平台的每个待处理任务会分配给多个用户以多个用户对同一个待处理任务进行校验，这样可以保证校验结果的准确度。对于每个待处理任务对应的多个用户，每个用户校验一次，即为一次答题次数，例如若一个待处理任务已经有3个用户进行了校验，则所述待处理任务的当前答题次数为3次。当每个待处理任务对应的多个用户都完成了校验，则每个待处理任务的答题完成。
在可选实施例中，具体地，对于每个任务类型，按待处理任务的当前答题次数从高到低形成有序队列，相同答题次数的待处理任务则按待处理任务进入众包平台的时间顺序排列。
在一个待处理任务需要派发给n个用户进行交叉验证时，按照每个待处理任务的当前答题次数从高到低依次为n-1次，n-2次……0次，即众包平台 优先分发当前答题次数n-1次的待处理任务给当前用户，在分发当前答题次数是n-2次的待处理任务，以此类推，最后是当前答题次数为0的待处理任务。从用户角度看，用户进入众包平台，优先完成只剩1次答题次数的最先进入众包平台的待处理任务。当按时间顺序完成所有只剩1次答题机会的待处理任务后，众包平台自动切换到只剩2次答题次数按进入众包平台的时间顺序排列的待处理任务，以此类推，直至完成每个任务类型的所有待处理任务。
所述分发模块34将所述目标任务发送至众包平台的当前用户，所述众包平台中每种任务类型中每个待处理任务分发至所述众包平台的多个用户进行校验。
所述显示模块35将所述目标任务分发给所述当前用户后，在当前用户的用户界面上显示所述目标任务。当前用户根据所述目标任务的图片，并在用户界面上提供的用户接口输入校验结果。例如所述目标任务为医院名称任务，则根据医院名称任务的图片，输入“人民医院”，并提交至所述众包平台。
由以上实施例，将众包平台中所有任务分类成各种不同的任务类型，每个任务类型中有多种待处理任务，将每个待处理任务分发至所述众包平台的多个用户进行校验以确定任务的准确度。同时提供切换任务类型的接口给用户以便用户选择喜欢的任务类型，还基于任务优先级分配待处理任务。本申请能保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷分行为，同时保证海量众包任务回收的时效性。
如图4所示，本申请任务派发装置的第二较佳实施例的程序模块图。所述任务派发装置3除了包括第一较佳实施中的一个或者多个模块：获取模块30、配置模块31、判断模块32、触发模块33、分发模块34及显示模块35之外，所述任务派发装置3还可以包括以下一个或者多个模块：接收模块36、确定模块37、提示模块38及评价模块39。本申请所称的单元是指一种能够被任务派发装置3的处理器所执行并且能够完成固定功能的一系列计算机可读指令段，其存储在存储器中。关于各模块的功能将在后续的实施例中详述。
所述接收模块36接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果。
优选地，所述确定模块37对于每个待处理任务，将多个检验结果中超过人数阈值的校验结果作为每个待处理任务的识别结果。例如，将一个日期字段任务发送给三个用户，若三个用户对所述日期字段任务的校验结果有三个不同的答案，则确定没有正确结果，若三个用户中，有两个用户的答案相同，则将两个用户的答案作为日期字段任务的检验结果。
进一步地，所述配置模块31根据每个待处理任务对应的多个用户的数量配置所述人数阈值。例如一个待处理任务需要由10个用户进行校验，则所述人数阈值为10*0.8＝8。
优选地，所述提示模块38对于每个待处理任务，在多个检验结果中，不存在超过人数阈值的校验结果时，发送无法检验的提示至所述待处理任务的提供者(报销人员)的设备中以使所述待处理任务的提供者重新上传任务图 片，从而保证任务识别的精度。
所述评价模块39基于所述目标任务的识别结果，评价校验所述目标任务的当前用户。
优选地，所述评价模块39将对与所述目标任务的识别结果相同的检验结果对应的当前用户评分高于对与所述目标任务的识别结果不相同的检验结果对应的当前用户评分。这样用户对任务的检验结果正确的越多，评分越高，可以避免用户为了提高答题速度，随便乱答题。
优选地，所述配置模块31根据用户的评分配置用户等级。例如，用户对任务的检验结果正确的越多，评分越高，等级就越高，用户能获取的切换任务类型的次数就越多，从而更有效的激励用户积极地完成任务。
优选地，所述分发模块34根据用户等级分配所述众包平台中的待处理任务。例如，当所述众包平台中当前用户数大于待处理任务的数量时，则所述众包平台中的任务数量不够，则优先满足用户等级比较高的用户需求。这样能更有效地激励用户在众包平台上更准确的完成更多的任务数量。
进一步地，所述配置模块31根据用户的时间数据配置用户等级，所述时间数据包括，但不限于：用户完成每个任务的时间、用户登录所述众包平台的持续时间、用户在所述众包平台做任务的持续时间(例如用户每天都在众包平台上做任务，这样就可以配置较高等级)等等。这样根据用户的时间数据，可以进一步评估用户在所述众包平台上做任务的持续性，以进一步激励用户成为所述众包平台的稳定用户。
由以上实施例可知，本申请将众包平台中所有任务分类成各种不同的任务类型，每个任务类型中有多种待处理任务，将每个待处理任务分发至所述众包平台的多个用户进行校验以确定任务的准确度。同时提供切换任务类型的接口给用户以便用户选择喜欢的任务类型，还基于任务优先级分配待处理任务。在用户对任务检验完成后，并基于任务的正确答案及用户的校验结果，对用户的检验任务的工作进行评价。本申请能保证众包任务实现随机性与有序性的统一，可以在任务派发过程中有效防止用户随意刷分行为，同时保证海量众包任务回收的时效性。
上述以软件程序模块的形式实现的集成的单元，可以存储在一个非易失性可读取存储介质中。上述软件程序模块存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本申请每个实施例所述方法的部分步骤。
如图5所示，所述电子设备5包括至少一个发送装置51、至少一个存储器52、至少一个处理器53、至少一个接收装置54以及至少一个通信总线。其中，所述通信总线用于实现这些组件之间的连接通信。
所述电子设备5是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器(Digital Signal Processor，DSP)、嵌入式设备等。所述电子设备5还可包括网络设备和/或用户设备。其中，所 述网络设备包括但不限于单个网络服务器、多个网络服务器组成的服务器组或基于云计算(Cloud Computing)的由大量主机或网络服务器构成的云，其中，云计算是分布式计算的一种，由一群松散耦合的计算机集组成的一个超级虚拟计算机。
所述电子设备5可以是，但不限于任何一种可与用户通过键盘、触摸板或声控设备等方式进行人机交互的电子产品，例如，平板电脑、智能手机、个人数字助理(Personal Digital Assistant，PDA)、智能式穿戴式设备、摄像设备、监控设备等终端。
所述电子设备5所处的网络包括，但不限于互联网、广域网、城域网、局域网、虚拟专用网络(Virtual Private Network，VPN)等。
其中，所述接收装置54和所述发送装置51可以是有线发送端口，也可以为无线设备，例如包括天线装置，用于与其他设备进行数据通信。
所述存储器52用于存储程序代码。所述存储器52可以是集成电路中没有实物形式的具有存储功能的电路，如RAM(Random-Access Memory，随机存取存储器)、FIFO(First In First Out，)等。或者，所述存储器52也可以是具有实物形式的存储器，如内存条、TF卡(Trans-flash Card)、智能媒体卡(smart media card)、安全数字卡(secure digital card)、快闪存储器卡(flash card)等储存设备等等。
所述处理器53可以包括一个或者多个微处理器、数字处理器。所述处理器53可调用存储器52中存储的程序代码以执行相关的功能。例如，图3及图4中所述的各个模块是存储在所述存储器52中的程序代码，并由所述处理器53所执行，以实现一种任务派发方法。所述处理器53又称中央处理器(CPU，Central Processing Unit)，是一块超大规模的集成电路，是运算核心(Core)和控制核心(Control Unit)。
本申请实施例还提供一种非易失性可读存储介质，其上存储有计算机指令，所述指令当被包括一个或多个处理器的电子设备执行时，使电子设备执行如上文方法实施例所述的任务派发方法。
结合图1及图2所示，所述电子设备5中的所述存储器52存储多个指令以实现一种任务派发方法，所述处理器53可执行所述多个指令从而实现：
获取目标任务类型；获取任务分配指令；根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；将所述目标任务发送至众包平台的至少两个以上的当前用户。
根据本申请优选实施例，所述众包平台与识别设备相通信，所述识别设备用于对票据图片进行处理，得到票据图片中的关键字段，将票据图片中的关键字段发送给识别设备。
根据本申请优选实施例，所述处理器53可执行的所述多个指令还用于实现：将各种类型票据中相同类型的关键字段所在的类别配置一个任务类型；或，将每种类型票据中每种类型的关键字段所在的类别配置成一个任务类型。
根据本申请优选实施例，所述处理器53可执行的所述多个指令还用于实现：在获取所述目标任务类型之前，所述方法还包括：判断是否获取到获取所述 目标任务类型的触发信号；
触发获取所述目标任务类型的方式有包括以下一种或者多种的组合：
当获取到当前用户登录所述众包平台的登录指令时，则获取所述目标任务类型；
当获取到当前用户的切换任务类型的切换指令时，则获取所述目标任务类型；
当获取到当前用户的当前任务类型没有待处理任务时，则获取所述目标任务类型。
根据本申请优选实施例，所述获取所述目标任务类型包括以下一种或者多种的组合：
基于抽取原则，从所有任务类型中抽取一个任务类型作为所述目标任务类型；
基于抽取原则，从所有任务类型中抽取多个任务类型，并接收用户从所述多个任务类型中选取的一个任务类型，将所述选取的一个任务类型作为所述目标任务类型；
当获取到当前用户的切换任务类型的切换指令时，将所述切换指令中包含的用户选中的任务类型作为所述目标任务类型。
根据本申请优选实施例，所述任务分配指令包括随机分配指令、基于任务优先级的分配指令；所述任务优先级包括：基于任务的当前答题次数的优先级，任务的当前答题次数越少，优先级越高；基于任务进入众包平台的时间顺序的优先级，进入众包平台的时间越早，优先级越高。
根据本申请优选实施例，所述处理器53可执行的所述多个指令还用于实现：
接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果；
基于所述目标任务的识别结果，评价校验所述目标任务的当前用户。
根据本申请优选实施例，所述接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果包括：
将所述目标任务的对应的多个检验结果中超过人数阈值的校验结果作为所述目标任务的识别结果。
在任意实施例中所述任务派发方法对应的多个指令存储在所述存储器52，并通过所述处理器53来执行，在此不再详述。
以上说明的本申请的特征性的手段可以通过集成电路来实现，并控制实现上述任意实施例中所述任务派发方法的功能。即，本申请的集成电路安装于所述电子设备中，使所述电子设备发挥如下功能：获取目标任务类型；获取任务分配指令；根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；将所述目标任务发送至众包平台的至少两个以上的当前用户。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时 进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请的各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个非易失性可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (20)

  1. 一种任务派发方法，其特征在于，所述方法包括：
    获取目标任务类型；
    获取任务分配指令；
    根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；
    将所述目标任务发送至众包平台的至少两个以上的当前用户。
  2. 如权利要求1所述的任务派发方法，其特征在于，所述众包平台与识别设备相通信，所述识别设备用于对票据图片进行处理，得到票据图片中的关键字段，将票据图片中的关键字段发送给所述众包平台。
  3. 如权利要求2所述的任务派发方法，其特征在于，所述方法还包括：
    将各种类型票据中相同类型的关键字段所在的类别配置一个任务类型；或，将每种类型票据中每种类型的关键字段所在的类别配置成一个任务类型。
  4. 如权利要求1所述的任务派发方法，其特征在于，在获取所述目标任务类型之前，所述方法还包括：判断是否获取到获取所述目标任务类型的触发信号；
    触发获取所述目标任务类型的方式包括以下一种或者多种的组合：
    当获取到当前用户登录所述众包平台的登录指令时，则获取所述目标任务类型；
    当获取到当前用户的切换任务类型的切换指令时，则获取所述目标任务类型；
    当获取到当前用户的当前任务类型没有待处理任务时，则获取所述目标任务类型。
  5. 如权利要求1或4所述的任务派发方法，其特征在于，所述获取所述目标任务类型包括以下一种或者多种的组合：
    基于抽取原则，从所有任务类型中抽取一个任务类型作为所述目标任务类型；
    基于抽取原则，从所有任务类型中抽取多个任务类型，并接收用户从所述多个任务类型中选取的一个任务类型，将所述选取的一个任务类型作为所述目标任务类型；
    当获取到当前用户的切换任务类型的切换指令时，将所述切换指令中包含的用户选中的任务类型作为所述目标任务类型。
  6. 如权利要求1所述的任务派发方法，其特征在于，所述任务分配指令包括随机分配指令、基于任务优先级的分配指令；所述任务优先级包括：基于任务的当前答题次数的优先级，任务的当前答题次数越少，优先级越高；基于任务进入众包平台的时间顺序的优先级，进入众包平台的时间越早，优先级越高。
  7. 如权利要求1所述的任务派发方法，其特征在于，所述方法还包括：
    接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果；
    基于所述目标任务的识别结果，评价校验所述目标任务的当前用户。
  8. 如权利要求7所述的任务派发方法，其特征在于，所述接收所述目标任 务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果包括：
    将所述目标任务的对应的多个检验结果中超过人数阈值的校验结果作为所述目标任务的识别结果。
  9. 一种电子设备，其特征在于，所述电子设备包括存储器及处理器，所述存储器用于存储计算机可读指令，所述处理器用于执行所述计算机可读指令以实现以下步骤：
    获取目标任务类型；
    获取任务分配指令；
    根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；
    将所述目标任务发送至众包平台的至少两个以上的当前用户。
  10. 如权利要求9所述的电子设备，其特征在于，所述众包平台与识别设备相通信，所述识别设备用于对票据图片进行处理，得到票据图片中的关键字段，将票据图片中的关键字段发送给所述众包平台。
  11. 如权利要求10所述的电子设备，其特征在于，所述处理器还用于执行所述计算机可读指令以实现以下步骤：
    将各种类型票据中相同类型的关键字段所在的类别配置一个任务类型；或，将每种类型票据中每种类型的关键字段所在的类别配置成一个任务类型。
  12. 如权利要求9所述的电子设备，其特征在于，在获取所述目标任务类型之前，所述处理器用于执行所述计算机可读指令以实现以下步骤：
    判断是否获取到获取所述目标任务类型的触发信号；
    触发获取所述目标任务类型的方式包括以下一种或者多种的组合：
    当获取到当前用户登录所述众包平台的登录指令时，则获取所述目标任务类型；
    当获取到当前用户的切换任务类型的切换指令时，则获取所述目标任务类型；
    当获取到当前用户的当前任务类型没有待处理任务时，则获取所述目标任务类型。
  13. 如权利要求9所述的电子设备，其特征在于，所述处理器还用于执行所述计算机可读指令以实现以下步骤：
    接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果；
    基于所述目标任务的识别结果，评价校验所述目标任务的当前用户。
  14. 如权利要求13所述的电子设备，其特征在于，所述接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果包括：
    将所述目标任务的对应的多个检验结果中超过人数阈值的校验结果作为所述目标任务的识别结果。
  15. 一种非易失性可读存储介质，其特征在于，所述非易失性可读存储介质存储有至少一个指令，所述至少一个指令被处理器执行时实现以下步骤：
    获取目标任务类型；
    获取任务分配指令；
    根据任务分配指令，从所述目标任务类型中的待处理任务中获取目标任务；
    将所述目标任务发送至众包平台的至少两个以上的当前用户。
  16. 如权利要求15所述的存储介质，其特征在于，所述众包平台与识别设备相通信，所述识别设备用于对票据图片进行处理，得到票据图片中的关键字段，将票据图片中的关键字段发送给所述众包平台。
  17. 如权利要求16所述的存储介质，其特征在于，所述至少一个指令被处理器执行时还实现以下步骤：
    将各种类型票据中相同类型的关键字段所在的类别配置一个任务类型；或，将每种类型票据中每种类型的关键字段所在的类别配置成一个任务类型。
  18. 如权利要求15所述的存储介质，其特征在于，在获取所述目标任务类型之前，所述至少一个指令被处理器执行时还实现以下步骤：
    判断是否获取到获取所述目标任务类型的触发信号；
    触发获取所述目标任务类型的方式包括以下一种或者多种的组合：
    当获取到当前用户登录所述众包平台的登录指令时，则获取所述目标任务类型；
    当获取到当前用户的切换任务类型的切换指令时，则获取所述目标任务类型；
    当获取到当前用户的当前任务类型没有待处理任务时，则获取所述目标任务类型。
  19. 如权利要求15所述的存储介质，其特征在于，所述至少一个指令被处理器执行时还实现以下步骤：
    接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果；
    基于所述目标任务的识别结果，评价校验所述目标任务的当前用户。
  20. 如权利要求19所述的存储介质，其特征在于，所述接收所述目标任务的当前用户输出的多个校验结果，并确定所述目标任务的识别结果包括：
    将所述目标任务的对应的多个检验结果中超过人数阈值的校验结果作为所述目标任务的识别结果。
PCT/CN2018/100018 2018-04-18 2018-08-10 任务派发方法、电子设备及存储介质 Ceased WO2019200780A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810351125.7A CN108629560A (zh) 2018-04-18 2018-04-18 任务派发方法、电子设备及存储介质
CN201810351125.7 2018-04-18

Publications (1)

Publication Number Publication Date
WO2019200780A1 true WO2019200780A1 (zh) 2019-10-24

Family

ID=63705551

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/100018 Ceased WO2019200780A1 (zh) 2018-04-18 2018-08-10 任务派发方法、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN108629560A (zh)
WO (1) WO2019200780A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113157412A (zh) * 2021-04-09 2021-07-23 作业帮教育科技（北京）有限公司 一种防作弊的众包任务分配方法、装置及电子设备
RU2837803C2 (ru) * 2021-09-14 2025-04-04 Общество С Ограниченной Ответственностью «Яндекс» Способы и системы для формирования списка цифровых задач
US12353968B2 (en) 2021-05-24 2025-07-08 Y.E. Hub Armenia LLC Methods and systems for generating training data for computer-executable machine learning algorithm within a computer-implemented crowdsource environment

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109492135B (zh) * 2018-10-27 2024-03-19 平安科技（深圳）有限公司 一种基于数据处理的数据审核方法以及装置
CN109544015B (zh) * 2018-11-26 2023-07-25 平安科技（深圳）有限公司 一种基于数据处理的任务分配方法及相关设备
CN109582581B (zh) * 2018-11-30 2023-08-25 平安科技（深圳）有限公司 一种基于众包任务的结果确定方法及相关设备
CN111784523A (zh) * 2020-06-28 2020-10-16 平安医疗健康管理股份有限公司 基于保单案件的众包分配方法及装置
CN111832956B (zh) * 2020-07-20 2024-07-23 北京百度网讯科技有限公司 数据验证方法、装置、电子设备以及介质
CN113010323B (zh) * 2021-04-16 2026-03-13 中国建设银行股份有限公司 一种云生产资源分配方法、装置、系统、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160034840A1 (en) * 2014-07-31 2016-02-04 Microsoft Corporation Adaptive Task Assignment
CN107622336A (zh) * 2016-07-15 2018-01-23 阿里巴巴集团控股有限公司 任务的推送方法、装置及系统
CN107798299A (zh) * 2017-10-09 2018-03-13 平安科技（深圳）有限公司 票据信息识别方法、电子装置及可读存储介质
CN107832901A (zh) * 2017-07-28 2018-03-23 平安科技（深圳）有限公司 任务分配方法、装置、终端设备及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105005742A (zh) * 2015-07-30 2015-10-28 四川长虹电器股份有限公司 一种数据处理方法及数据处理系统
CN107194608B (zh) * 2017-06-13 2021-09-17 复旦大学 一种面向残疾人社区的众包标注任务分配方法
CN107392747A (zh) * 2017-08-01 2017-11-24 深圳易嘉恩科技有限公司 基于财务云平台的抢单功能设计方法
CN107590588A (zh) * 2017-08-24 2018-01-16 平安科技（深圳）有限公司 任务分配方法、装置及计算机可读存储介质
CN107885423B (zh) * 2017-10-30 2020-09-29 维沃移动通信有限公司 一种图片的处理方法及移动终端

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160034840A1 (en) * 2014-07-31 2016-02-04 Microsoft Corporation Adaptive Task Assignment
CN107622336A (zh) * 2016-07-15 2018-01-23 阿里巴巴集团控股有限公司 任务的推送方法、装置及系统
CN107832901A (zh) * 2017-07-28 2018-03-23 平安科技（深圳）有限公司 任务分配方法、装置、终端设备及存储介质
CN107798299A (zh) * 2017-10-09 2018-03-13 平安科技（深圳）有限公司 票据信息识别方法、电子装置及可读存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113157412A (zh) * 2021-04-09 2021-07-23 作业帮教育科技（北京）有限公司 一种防作弊的众包任务分配方法、装置及电子设备
US12353968B2 (en) 2021-05-24 2025-07-08 Y.E. Hub Armenia LLC Methods and systems for generating training data for computer-executable machine learning algorithm within a computer-implemented crowdsource environment
RU2837803C2 (ru) * 2021-09-14 2025-04-04 Общество С Ограниченной Ответственностью «Яндекс» Способы и системы для формирования списка цифровых задач

Also Published As

Publication number Publication date
CN108629560A (zh) 2018-10-09

Similar Documents

Publication Publication Date Title
WO2019200780A1 (zh) 任务派发方法、电子设备及存储介质
US10360367B1 (en) Multi-factor authentication devices
WO2019200781A1 (zh) 票据识别方法、装置及存储介质
CN109376873B (zh) 运维方法、装置、电子设备及计算机可读存储介质
JP2016081401A (ja) 情報検索提示装置、及び情報検索提示方法
US20180341685A1 (en) Integrating virtual and human agents in a multi-channel support system for complex software applications
CN107622336A (zh) 任务的推送方法、装置及系统
JP6923834B1 (ja) 情報処理装置、情報処理方法及びプログラム
CN110858423A (zh) 一种排队方案、队列推送方法和处理系统
JP7255680B2 (ja) 情報処理装置、情報処理方法及びプログラム
JP2015060432A (ja) プログラム、コンピュータおよび訓練データ作成支援方法
CN110351083A (zh) 随机源生成方法、电子设备、系统及介质
CN114036551B (zh) 隐私数据的数据处理方法、装置、计算机设备及介质
CN111368866A (zh) 图片分类方法、装置及系统
CN113626693B (zh) 产品推荐方法、装置、计算机设备和存储介质
CN115564301A (zh) 一种激活卡人数值预测方法、装置及计算机设备
CN113158944A (zh) 基于人脸识别的体检排队方法、系统、设备及存储介质
US10553062B2 (en) Method for generating winning numbers and apparatus
JP7226853B2 (ja) 顔認証装置、顔認証方法、およびプログラム
CN110232267A (zh) 名片显示方法、装置、电子设备及存储介质
US20190139149A1 (en) System and method for content reporting
CN117897738A (zh) 人工智能辅助的实况体育数据质量保证
CN110543754A (zh) 存储器、验证码实现方法、装置和设备
CN111008373B (zh) 智能问答的处理方法、装置、计算机可读介质及电子设备
CN111210544A (zh) 一种基于云计算的门控方法及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18915304

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19/01/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18915304

Country of ref document: EP

Kind code of ref document: A1