CN109784654A - Task creating method, device, computer equipment and storage medium - Google Patents
Task creating method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109784654A CN109784654A CN201811544276.0A CN201811544276A CN109784654A CN 109784654 A CN109784654 A CN 109784654A CN 201811544276 A CN201811544276 A CN 201811544276A CN 109784654 A CN109784654 A CN 109784654A
- Authority
- CN
- China
- Prior art keywords
- task
- user
- released
- target
- questionnaire
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims description 48
- 238000013210 evaluation model Methods 0.000 claims description 32
- 230000000977 initiatory effect Effects 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 17
- 239000012141 concentrate Substances 0.000 claims description 7
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000015572 biosynthetic process Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves field of artificial intelligence, a kind of task creating method, device, computer equipment and storage medium are provided.The described method includes: obtaining the corresponding task type of task to be released and customer ID;Corresponding target topic is chosen from the preset public exam pool according to the task type;Corresponding customer information is searched according to the customer ID, the customer information includes the corresponding contract number of client;The corresponding contract information of the task to be released is searched according to the contract number;Based on the task type, the customer information and the contract information, the questionnaire Matching Model that use has been trained obtains the corresponding target questionnaire of task to be released;Preset public topic is obtained, and task to be released is generated according to the preset public topic, the target topic and the target questionnaire.The formation efficiency of task can be improved using the present processes.
Description
Technical field
This application involves field of artificial intelligence, more particularly to a kind of task creating method, device, computer equipment
And storage medium.
Background technique
With the rapid development of internet, there is crowdsourcing platform Internet-based, by crowdsourcing platform, lease is public
The enterprises such as department, finance company can be dispensed the tasks such as the work such as collection, investigation after leasing, providing a loan using internet.
In traditional technology, task publisher can be expressed in the form of topic and be appointed in release tasks on crowdsourcing platform
Be engaged in content, but in traditional technology, task publisher is usually required for each task come manual setting topic, it is bothersome arduously,
Lead to inefficiency.
Summary of the invention
Based on this, it is necessary to which topic in view of the above technology provides a kind of task generation that can be improved task formation efficiency
Method, apparatus, computer equipment and storage medium.
A kind of task creating method, which comprises
Obtain the corresponding task type of task to be released and customer ID;
Corresponding target topic is chosen from the preset public exam pool according to the task type;
Corresponding customer information is searched according to the customer ID, the customer information includes that the corresponding contract of client is compiled
Number;
The corresponding contract information of the task to be released is searched according to the contract number;
Based on the task type, the customer information and the contract information, the questionnaire that use has been trained matches mould
Type obtains the corresponding target questionnaire of task to be released;
Preset public topic is obtained, and is asked according to the preset public topic, the target topic and the target
Volume generates task to be released.
In one of the embodiments, described according to the preset public topic, the target topic and the mesh
Mark questionnaire generates after task to be released, which comprises
Obtain the corresponding pushing condition of the task to be released;
The pushing condition is matched with each user in active user's set, the user of successful match is determined
User is pushed for target;
The task to be released is pushed to the corresponding terminal of target push user.
It is described in one of the embodiments, to obtain the corresponding pushing condition of the task to be released, comprising:
Obtain the corresponding task grade of the task to be released;
It is described to match the pushing condition with each user in active user's set, by the user of successful match
It is determined as target push user, comprising:
Obtain the corresponding current user's level of each user in active user's set;
When the current user's level of any one user task grade corresponding not less than the task to be released, by institute
It states user and is determined as target push user.
In one of the embodiments, before obtaining the corresponding task grade of the task to be released, comprising:
The first training sample set is obtained, it includes historic task pair that first training sample, which concentrates each first training sample,
Task type, contract information and the first markup information answered;
Determine the model structure information of initiating task grade evaluation model, and the initialization initiating task grade assessment
The model parameter of model;
Based in first training sample task type and contract information using the initiating task grade assess mould
Type obtains the corresponding task grade of first training sample;
Based on the difference between obtained task grade and first markup information, the initiating task grade is adjusted
The model parameter of assessment models;
The initiating task grade evaluation model is determined as goal task grade evaluation model;
It is described to obtain the corresponding task grade of the task to be released, comprising:
Based on the corresponding task type of the task to be released and contract information, mould is assessed using the goal task grade
Type obtains the corresponding task grade of the task to be released.
The corresponding current user's level of each user in acquisition active user set in one of the embodiments,
Include:
Obtain the initial user grade of each user in active user's set;
Task is completed in the history for obtaining each user in active user's set;
The corresponding task identification of task is completed according to the history and searches corresponding task scoring;
The initial user grade that each user is adjusted according to task scoring, obtains the active user of each user
Grade.
The generation step of the questionnaire Matching Model includes: in one of the embodiments,
The second training sample set is obtained, it includes historic task pair that second training sample, which concentrates each second training sample,
Task type, customer information, contract information and the second markup information answered;
Determine the model structure information of initial questionnaire Matching Model, and the mould of the initialization initial questionnaire Matching Model
Shape parameter;
The initial questionnaire is used based on task type, customer information and the contract information in second training sample
The corresponding target questionnaire of second training sample is obtained with model;
Based on the difference between obtained target questionnaire and second markup information, the questionnaire Matching Model is adjusted
Model parameter, obtain target questionnaire Matching Model;
The target questionnaire Matching Model is determined as to the questionnaire Matching Model trained.
A kind of task generating device, described device include:
Data acquisition module, for obtaining the corresponding task type of task to be released and customer ID;
Target topic obtains module, corresponding for being chosen from the preset public exam pool according to the task type
Target topic;
Customer information searching module, for searching corresponding customer information, the customer information according to the customer ID
Including the corresponding contract number of client;
Contract information searching module is believed for searching the corresponding contract of the task to be released according to the contract number
Breath;
Target questionnaire matching module is adopted for being based on the task type, the customer information and the contract information
The corresponding target questionnaire of task to be released is obtained with the questionnaire Matching Model trained;
Task generation module to be released, for obtaining preset public topic, and according to the preset public topic, institute
It states target topic and the target questionnaire generates task to be released.
Described device in one of the embodiments, further include: task pushing module, for obtaining the task to be released
Corresponding pushing condition;The pushing condition is matched with each user in active user's set, by successful match
User is determined as target push user;The task to be released is pushed to the corresponding terminal of target push user.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the step of task creating method described in above-mentioned any embodiment when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of task creating method described in above-mentioned any embodiment is realized when row.
Above-mentioned task creating method, device, computer equipment and storage medium are being obtained by the way that a public exam pool is arranged
After getting the corresponding task type of task to be released and customer ID, preset public topic can be obtained respectively from public exam pool
Mesh, target topic, and task based access control type and the customer information got according to customer ID, contract information, using having instructed
Experienced questionnaire Matching Model obtains target questionnaire, is obtained according to preset public topic, target topic and target questionnaire to be released
Task realizes automatically generating for task to be released, saves task setup time, improves the generation effect of task to be released
Rate.
Detailed description of the invention
Fig. 1 is the application scenario diagram of task creating method in one embodiment;
Fig. 2 is the flow diagram of task creating method in one embodiment;
Fig. 3 is the flow diagram of the generation step of initiating task grade evaluation model in one embodiment;
Fig. 4 is the structural block diagram of task generating device in one embodiment;
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Task creating method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, terminal 102
It is communicated by network with server 104.Wherein, terminal 102 can show task type list and customer name list, appoint
Business publisher can select in task type list and customer name list, after the completion of task publisher selection, terminal
The task type that task publisher selects and the corresponding customer ID of customer name are sent to service 104, server 104 by 102
After having got these data, first according to task type from preset public exam pool selection target topic, target topic
Refer to the essential topic of the corresponding all tasks of the task type, then server 104 is searched according to customer ID and corresponded to
Customer information, customer information here includes but is not limited to industry belonging to client, the corresponding contract number of client etc., into one
Step, based on contract server 104 is numbered can search corresponding contract information, including the amount of money etc. that subject matter of a contract object, contract are related to,
Then, server 104 can be come with the questionnaire Matching Model that task based access control type, customer information and contract information, use have been trained
It obtains task to be released and corresponds to target questionnaire, wherein target questionnaire refers to the topic set of multiple topic compositions, finally, clothes
Business device 104 can obtain preset public topic from preset public exam pool, and according to preset public topic, target topic
And target questionnaire generates task to be released, and the task to be released of generation is back to terminal 102.
Wherein, terminal 102 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer
With portable wearable device, server 104 can use the server set of the either multiple server compositions of independent server
Group realizes.
In one embodiment, as shown in Fig. 2, providing a kind of task creating method, it is applied in Fig. 1 in this way
It is illustrated for server, comprising the following steps:
Step S202 obtains the corresponding task type of task to be released and customer ID.
Wherein, task type refers to classification belonging to task to be released.Task type can carry out thing according to the actual situation
It first sets, as that can be classified according to the industry field belonging to task, can also be divided according to the event type belonging to task
Class, for example, can be divided into assets prospecting task, logistics survey tasks, factoring reconnoitres task after renting, wherein assets reconnoitre task
Refer to the regular on-the-spot make an inspection tour task of assets after renting for enterprise, logistics survey tasks are referred to for business rental object arrival
Live veritification task, prospecting task refers to that the acquisition prospecting of live business circumstance after renting for factoring enterprise is appointed after factoring is rented
Business.The identity of the corresponding client of customer ID user's unique identification task, such as in assets prospecting type tasks, customer ID
For the identity of unique identification capital lease side, customer ID can be made of at least one of number, letter, symbol.
The relevant APP of crowdsourcing business can be installed in the present embodiment, in terminal, terminal can be shown by the APP appoints
Service type list is selected for task publisher, meanwhile, terminal can also show customer name search box, task by APP
Publisher can be searched for customer name and be selected by task search frame, after task publisher has selected customer name, eventually
Hold the corresponding customer ID of the available customer name, further, terminal can to server send task posting request, and
Task type and customer ID are carried in task posting request, server after the task posting request for receiving terminal transmission,
The task posting request is parsed, task type and customer ID can be got.
Step S204 chooses corresponding target topic according to task type from preset public exam pool.
Specifically, in the application, task definition is presented in the form of topic, and topic may include multiple-choice question, fill a vacancy
Topic, statement topic etc.;Preset public exam pool refers to exam pool composed by the alternative topic being previously set, task type
Corresponding target topic refers to topic common to the task of a certain type, for example, choosing for the task of assets prospecting class
Target topic may include shooting by the relevant topic of the photo of prospecting assets.In the present embodiment, each task type is right with it
Corresponding relationship has been previously set between the target topic answered, server after getting the corresponding task type of task to be released,
Target topic corresponding with the task type can be searched from preset public exam pool according to task type.
Step S206 searches corresponding customer information according to customer ID, and customer information includes that the corresponding contract of client is compiled
Number.
Wherein, customer information includes but is not limited to industry belonging to client, the corresponding contract number of client, wherein client
Affiliated industry for example can be preschool education, Civilian Hospital, engineering construction, from trade area etc., the corresponding contract number of client
Refer to the number of business contract corresponding with client, for example, when business corresponding with the client is charter business, contract
Number is the number for the contract of lease of property that the client signs.
In the present embodiment, due to the corresponding storage in the database of customer information and customer ID, server is obtaining
To after customer ID, corresponding customer information can be searched from database according to customer ID.
Step S208, based on contract number searches the corresponding contract information of task to be released.
Wherein, contract information refers to the relevant information of business contract corresponding with client, for example, when the client is corresponding
Business be charter business when, business contract is the contract of lease of property, and contract information includes subject matter of a contract assets, the case-involving amount of money of contract
Deng subject matter of a contract assets refer to object pointed by the rights or obligation in the corresponding contract documents of task, such as automobile leasing
In contract, subject matter of a contract assets are automobile;The case-involving amount of money of contract for example can be cash pledge, guarantee fund, rent etc..
In the present embodiment, corresponding storage, server in data are getting customer information to contract number with contract information
Afterwards, corresponding contract information is searched from database according to the contract number in customer information.
Step S210, task based access control type, customer information and contract information, the questionnaire Matching Model that use has been trained obtain
To the corresponding target questionnaire of task to be released.
Wherein, target questionnaire refers to the topic set as composed by multiple topics in preset public exam pool, questionnaire
Matching Model is used to characterize the corresponding relationship between task type, customer information and contract information and questionnaire.Implement at one
In example, questionnaire Matching Model can be technical staff based on to a large amount of task type, customer information, contract information and questionnaire
Pair for the corresponding relationship for counting and pre-establishing, be stored between multiple tasks type, customer information, contract information and questionnaire
Answer relation table;In another embodiment, questionnaire Matching Model be also possible to technical staff based on the statistics to mass data and
It presets and stores in the server, to one or more numerical value in task type, customer information and contract information
Numerical value is carried out to calculate with the calculation formula of the obtained calculated result for characterizing questionnaire matching result.
In the present embodiment, server can be used and train after getting task type, customer information and contract information
Task Matching Model, the corresponding target questionnaire of task to be released is matched from pre-set multiple questionnaires.
Step S212 obtains preset public topic, and raw according to preset public topic, target topic and target questionnaire
At task to be released.
Wherein, preset public topic refers to topic common to all types of tasks, for example, can will be with client
Personal information related topic, including customer name, address etc. be set as preset public topic.It is preset in the present embodiment
The corresponding target topic of public topic, task type and target questionnaire collectively constitute the corresponding topic set of task to be released, clothes
Being engaged in device can be according to topic set generation task to be released, and task to be released is returned to terminal.
In one embodiment, terminal is after the task to be released for receiving server return, the corresponding task hair of terminal
Cloth person can further be configured task, for example, the amount of money award of setting task, pushing condition that task is arranged etc..
In above-mentioned task creating method, by the way that a public exam pool is arranged, server is getting task correspondence to be released
Task type and customer ID after, preset public topic, the corresponding mesh of task type can be obtained respectively from public exam pool
Title mesh, and task based access control type and the customer information got according to customer ID, contract information, what use had been trained asks
Volume Matching Model obtains target questionnaire, is finally asked according to preset public topic, the corresponding target topic of task type and target
Volume obtains task to be released, realizes automatically generating for task to be released, saves task setup time, improves to be released
The formation efficiency of business.
In one embodiment, task to be released is being generated according to preset public topic, target topic and target questionnaire
Later, the above method further include: obtain the corresponding pushing condition of task to be released;It will be in pushing condition and active user's set
Each user matches, and the user of successful match is determined as target push user;To the corresponding terminal of target push user
Push task to be released.
Wherein, it includes the corresponding area of task to be released, task to be released that pushing condition, which includes but is not limited to pushing condition,
Corresponding task grade, the corresponding user identity of task to be released.In the present embodiment, server is getting task pair to be released
After the pushing condition answered, pushing condition is matched with each user in active user's set, by the user of successful match
Be determined as target push user, wherein successful match includes at least one of following situations: the corresponding registered address of user with
The corresponding area of task to be released is identical;The corresponding current user's level of user is not less than the corresponding task dispatching of task to be released
Grade;Corresponding with the task to be released task identity of the corresponding user identity of user requires to match, wherein user identity include but
It is not limited to students, professional person, social people etc.;Active user's set refers to it is all registered receivable tasks
Set composed by the user of push.It is appreciated that the user in the present embodiment is the executor of task, with client above
Not identical, by taking crowdsourcing platform as an example, user refers to that crowdsourcing platform executes task to obtain the crowd of reward, and what client referred to
It is the client in the corresponding business of the task, for example, client refers to carrying out goods and materials rent from leasing company in logistics survey tasks
The crowd to rent.
In above-described embodiment, by obtaining pushing condition, server no longer needs to push all users this to be released
Business, so as to save Internet resources.
In one embodiment, the corresponding pushing condition of task to be released is obtained, comprising: it is corresponding to obtain task to be released
Task grade;Pushing condition is matched with each user in active user's set, the user of successful match is determined as
Target pushes user, comprising: obtains the corresponding current user's level of each user in active user's set;As any one user
Current user's level not less than task to be released corresponding task grade when, user is determined as target push user.
Wherein, the confidence level of user gradation user characterization user, the higher user of user gradation, confidence level are higher.?
People in one embodiment, since user needs to carry out recognition of face when registering, when can be according to user's registration
Face identifies score to determine the corresponding user gradation of some user.The setting of specific user gradation can be by technical staff according to industry
Business demand is previously set, such as may be set to high, medium and low, also can be set as level-one, second level, three-level ... ..., and n grades.
Task grade characterization task corresponds to the height that the identity confidence level of performer requires, and task higher grade task is right
It is required in the identity confidence level of executor higher.The delimitation of task grade and the delimitation of user gradation are identical, such as user gradation
Delimit be it is high, medium and low, then task grade equally delimit be it is high, medium and low, for another example, user gradation and task grade can also be all
Delimit is level-one, second level, three-level, level Four etc..
In one embodiment, meet the target user of its pushing condition to ensure that task can be accurately pushed to, clothes
Business device obtains task grade first, then obtains the user gradation of each user in active user's set, judges each user's
Whether user gradation is not less than the corresponding task grade of task to be released, and user gradation is corresponding not less than task to be released
The user of task grade is determined as target push user.
In above-described embodiment, determine that target pushes user by matching task grade with user gradation, it can be with
Task to be released is enabled accurately to be pushed to the user for meeting its push request, to save to the use for being unsatisfactory for requiring
Internet resources when family is pushed.
In one embodiment, as shown in figure 3, before obtaining the corresponding task grade of task to be released, the above method
Further include the generation step of task grade evaluation model, specifically include:
Step S302 obtains the first training sample set, and it includes history that the first training sample, which concentrates each first training sample,
The corresponding task type of task, contract information and the first markup information.
Wherein, the first markup information is for characterizing the corresponding task grade of historic task.In one embodiment, the first mark
Note information can be the vector comprising task class letter, for example, using vector when task grade includes high, medium and low three-level
(1,0,0) advanced tasks are characterized, intermediate task is characterized with vector (0,1,0), characterizes low-level tasks with vector (0,0,1);Another
In one embodiment, the first markup information can be the vector including the first probability, the second probability and third probability, wherein
First probability is for characterizing a possibility that historic task is advanced tasks, and the second probability is for characterizing historic task as intermediate task
A possibility that, third probability is for characterizing a possibility that historic task is low-level tasks.
Step S304, determines the model structure information of initiating task grade evaluation model, and initializes the initiating task
The model parameter of grade evaluation model.
Specifically, initiating task grade evaluation model can be the various machine learning models that classification feature may be implemented,
For different types of model, the model structure information of required determination is not also identical.For example, task grade evaluation model can be with
For decision tree, logistic regression, naive Bayesian, neural network etc..
Further, it is possible to by each model parameter of initiating task grade evaluation model with some different small random numbers into
Row initialization." small random number " is used to guarantee that model will not enter saturation state because weight is excessive, so as to cause failure to train,
" difference " is used to guarantee that model can normally learn.
Step S306, based in the first training sample task type and contract information using initiating task grade assess mould
Type obtains the corresponding task grade of the first training sample.
Specifically, the corresponding task type of historic task and contract information can be mapped as input vector, will input to
In amount input initiating task grade evaluation model, so as to obtain the task grade of historic task in the first training sample.
Step S308 adjusts initiating task etc. based on the difference between obtained task grade and the first markup information
The model parameter of grade assessment models.
Initiating task grade evaluation model is determined as goal task grade evaluation model by step S310.
Specifically, it can use preset loss function (for example, L1 norm or L2 norm etc.) and calculate obtained go through
The difference between the first markup information in the task grade and training sample of history task, and based on the resulting difference tune of calculating
The model parameter of whole above-mentioned initiating task grade evaluation model, and when meeting default training termination condition, terminate training, by this
When initiating task grade evaluation model be determined as goal task grade evaluation model.Wherein preset training termination condition include but
Be not limited to: the training time is more than preset threshold;Frequency of training is more than preset times;It calculates obtained difference and is less than default difference
Threshold value.In the present embodiment, it can be based on the resulting above-mentioned initiating task grade of discrepancy adjustment of calculating using various implementations and comment
Estimate the model parameter of model.For example, BP (Back Propagation, backpropagation) algorithm or SGD (Stochastic
Gradient Descent, stochastic gradient descent) algorithm.
Further, in the present embodiment, the corresponding task grade of task to be released is obtained, comprising: be based on task pair to be released
The task type and contract information answered obtain the corresponding task grade of task to be released using goal task grade evaluation model.
Specifically, task type and contract information can be mapped as input vector, and is input to obtained target class assessment mould
In type, the corresponding task grade of task to be released is obtained.
In above-described embodiment, it is determined by the grade that training mission grade evaluation model treats release tasks, it can be with
So that the determination of task grade is more accurate, while the determination efficiency of task grade can be improved.
In one embodiment, the corresponding current user's level of each user in active user's set is obtained, comprising: obtain
The initial user grade of each user in active user's set;The history for obtaining each user in active user's set, which is completed, appoints
Business;The corresponding task identification of task is completed according to history and searches corresponding task scoring;Each use is adjusted according to task scoring
The initial user grade at family, obtains the current user's level of each user.
In the present embodiment, the user etc. that recognition of face score when initial user grade is according to user's registration determines
Grade.Task is completed in the history for obtaining target user in server, and the corresponding task identification of task is completed according to history and searches
The scoring of corresponding task is scored the initial user grade of adjustable target user according to task.Wherein, task scoring is used for table
Satisfaction of the sign task publisher to task performance.
In one embodiment, when the task quantity that user completes is more than first threshold and the corresponding task scoring of task
When mean value is more than second threshold, the grade of active user can be promoted;When the task quantity that target user completes is more than
When the mean value that first threshold and the corresponding task of task score is less than third threshold value, the corresponding grade of user is reduced.
In above-described embodiment, the grade of target user is adjusted by task scoring, user can be excited to complete to appoint
The enthusiasm of business.
In one embodiment, the generation step of questionnaire Matching Model includes: to obtain the second training sample set, the second training
Each second training sample includes the corresponding task type of historic task, customer information, contract information and second in sample set
Markup information;Determine the model structure information of initial questionnaire Matching Model, and the model of the initial questionnaire Matching Model of initialization
Parameter;It is obtained based on task type, customer information and the contract information in the second training sample using initial questionnaire Matching Model
The corresponding target questionnaire of second training sample;Based on the difference between obtained target questionnaire and the second markup information, adjustment
The model parameter of questionnaire Matching Model obtains target questionnaire Matching Model;Target questionnaire Matching Model is determined as having trained
Questionnaire Matching Model.
Wherein, the second markup information is for characterizing the corresponding target questionnaire of historic task.In one embodiment, the second mark
Note information can be the vector comprising questionnaire mark, for example, vector (1,0,0,0) is used respectively when preset questionnaire has 4,
(0,1,0,0), (0,0,1,0), (0,0,0,1) indicate this 4 questionnaires;In another embodiment, the second markup information can be
Vector including multiple probability values, for example, the second markup information may include 4 probability values when preset questionnaire has 4,
This four probability values characterize a possibility that each questionnaire is historic task corresponding target questionnaire respectively.
It is referred in the application in other embodiments it is appreciated that closing other explanations in this present embodiment and limiting
Description, this will not be repeated here by the application.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of task generating device 400, comprising:
Data acquisition module 402, for obtaining the corresponding task type of task to be released and customer ID;
Target topic obtains module 404, and corresponding target topic is chosen from preset public exam pool according to task type;
Customer information searching module 406, for searching corresponding customer information according to customer ID, customer information includes visitor
The corresponding contract number in family;
Contract information searching module 408 searches the corresponding contract information of task to be released for based on contract number;
Target questionnaire matching module 410, is used for task based access control type, customer information and contract information, and use has been trained
Questionnaire Matching Model obtain the corresponding target questionnaire of task to be released;
Task generation module 412 to be released, for obtaining preset public topic, and according to preset public topic, mesh
Title mesh and target questionnaire generate task to be released.
In one embodiment, above-mentioned apparatus further include: task pushing module, task to be released is corresponding to be pushed away for obtaining
Send condition;Pushing condition is matched with each user in active user's set, the user of successful match is determined as mesh
Mark push user;Task to be released is pushed to the corresponding terminal of target push user.
In one embodiment, above-mentioned task pushing module is also used to obtain the corresponding task grade of task to be released;It obtains
Take active user gather in the corresponding current user's level of each user;When the current user's level of any one user is not less than
When the corresponding task grade of task to be released, user is determined as target push user.
In one embodiment, before obtaining the corresponding task grade of task to be released, above-mentioned apparatus further includes task
Grade evaluation model generation module, for obtaining the first training sample set, the first training sample concentrates each first training sample
Including the corresponding task type of historic task, contract information and the first markup information;Determine initiating task grade evaluation model
Model structure information, and the model parameter of initialization initiating task grade evaluation model;Based on appointing in the first training sample
Service type and contract information use initiating task grade evaluation model to obtain the corresponding task grade of the first training sample;Based on institute
Difference between obtained task grade and the first markup information adjusts the model parameter of initiating task grade evaluation model;It will
Initiating task grade evaluation model is determined as goal task grade evaluation model;Above-mentioned task pushing module is also used to based on pending
The corresponding task type of cloth task and contract information obtain task to be released corresponding using goal task grade evaluation model
Business grade.
In one embodiment, above-mentioned task pushing module be also used to obtain active user set in each user it is initial
User gradation;Task is completed in the history for obtaining each user in active user's set;It is corresponding that task is completed according to history
Task identification searches corresponding task scoring;The initial user grade that each user is adjusted according to task scoring, obtains each use
The current user's level at family.
In one embodiment, above-mentioned apparatus further includes questionnaire Matching Model generation module, for obtaining the second training sample
This collection, it includes the corresponding task type of historic task, customer information, contract that the second training sample, which concentrates each second training sample,
Information and the second markup information;Determine the model structure information of initial questionnaire Matching Model, and the initial questionnaire of initialization
Model parameter with model;Initial questionnaire is used based on task type, customer information and the contract information in the second training sample
Matching Model obtains the corresponding target questionnaire of the second training sample;Based between obtained target questionnaire and the second markup information
Difference, adjust questionnaire Matching Model model parameter, obtain target questionnaire Matching Model;Target questionnaire Matching Model is determined
For the questionnaire Matching Model trained.
Specific about task generating device limits the restriction that may refer to above for task creating method, herein not
It repeats again.Modules in above-mentioned task generating device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as contract information, customer information.The network interface of the computer equipment be used for it is outer
The terminal in portion passes through network connection communication.To realize a kind of task creating method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor realize the task generation side provided in any one embodiment of the application when executing computer program
The step of method.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of task creating method provided in any one embodiment of the application when being executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of task creating method, which comprises
Obtain the corresponding task type of task to be released and customer ID;
Corresponding target topic is chosen from preset public exam pool according to the task type, is searched according to the customer ID
Corresponding customer information, the customer information include the corresponding contract number of client;
The corresponding contract information of the task to be released is searched according to the contract number;
Based on the task type, the customer information and the contract information, the questionnaire Matching Model that use has been trained is obtained
To the corresponding target questionnaire of task to be released;
Preset public topic is obtained, and raw according to the preset public topic, the target topic and the target questionnaire
At task to be released.
2. the method according to claim 1, wherein described according to the preset public topic, the mesh
Title mesh and the target questionnaire generate after task to be released, comprising:
Obtain the corresponding pushing condition of the task to be released;
The pushing condition is matched with each user in active user's set, the user of successful match is determined as mesh
Mark push user;
The task to be released is pushed to the corresponding terminal of target push user.
3. according to the method described in claim 2, it is characterized in that, described obtain the corresponding push item of the task to be released
Part, comprising:
Obtain the corresponding task grade of the task to be released;
It is described to match the pushing condition with each user in active user's set, the user of successful match is determined
User is pushed for target, comprising:
Obtain the corresponding current user's level of each user in active user's set;
When the current user's level of any one user task grade corresponding not less than the task to be released, by the use
Family is determined as target push user.
4. according to the method described in claim 3, it is characterized in that, obtain the corresponding task grade of the task to be released it
Before, comprising:
The first training sample set is obtained, it includes that historic task is corresponding that first training sample, which concentrates each first training sample,
Task type, contract information and the first markup information;
Determine the model structure information of initiating task grade evaluation model, and the initialization initiating task grade evaluation model
Model parameter;
Based in first training sample task type and contract information obtained using the initiating task grade evaluation model
To the corresponding task grade of first training sample;
Based on the difference between obtained task grade and first markup information, the initiating task grade assessment is adjusted
The model parameter of model;
The initiating task grade evaluation model is determined as goal task grade evaluation model;
It is described to obtain the corresponding task grade of the task to be released, comprising:
Based on the corresponding task type of the task to be released and contract information, obtained using the goal task grade evaluation model
To the corresponding task grade of the task to be released.
5. according to the method described in claim 3, it is characterized in that, each user is corresponding in acquisition active user set
Current user's level, comprising:
Obtain the initial user grade of each user in active user's set;
Task is completed in the history for obtaining each user in active user's set;
The corresponding task identification of task is completed according to the history and searches corresponding task scoring;
The initial user grade that each user is adjusted according to task scoring, obtains the active user etc. of each user
Grade.
6. according to claim 1 to method described in 5 any one, which is characterized in that the generation of the questionnaire Matching Model walks
Suddenly include:
The second training sample set is obtained, it includes that historic task is corresponding that second training sample, which concentrates each second training sample,
Task type, customer information, contract information and the second markup information;
Determine the model structure information of initial questionnaire Matching Model, and the model ginseng of the initialization initial questionnaire Matching Model
Number;
Mould is matched using the initial questionnaire based on task type, customer information and the contract information in second training sample
Type obtains the corresponding target questionnaire of second training sample;
Based on the difference between obtained target questionnaire and second markup information, the mould of the questionnaire Matching Model is adjusted
Shape parameter obtains target questionnaire Matching Model;
The target questionnaire Matching Model is determined as to the questionnaire Matching Model trained.
7. a kind of task generating device, which is characterized in that described device includes:
Data acquisition module, for obtaining the corresponding task type of task to be released and customer ID;
Target topic obtains module, for choosing corresponding target from the preset public exam pool according to the task type
Topic;
Customer information searching module, for searching corresponding customer information according to the customer ID, the customer information includes
The corresponding contract number of client;
Contract information searching module, for searching the corresponding contract information of the task to be released according to the contract number;
Target questionnaire matching module, for being based on the task type, the customer information and the contract information, using
Trained questionnaire Matching Model obtains the corresponding target questionnaire of task to be released;
Task generation module to be released, for obtaining preset public topic, and according to the preset public topic, the mesh
Title mesh and the target questionnaire generate task to be released.
8. device according to claim 7, which is characterized in that described device further include: task pushing module, for obtaining
The corresponding pushing condition of the task to be released;By each user progress in the pushing condition and active user's set
Match, the user of successful match is determined as target push user;To target push user corresponding terminal push it is described to
Release tasks.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811544276.0A CN109784654B (en) | 2018-12-17 | 2018-12-17 | Task generation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811544276.0A CN109784654B (en) | 2018-12-17 | 2018-12-17 | Task generation method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109784654A true CN109784654A (en) | 2019-05-21 |
CN109784654B CN109784654B (en) | 2024-05-17 |
Family
ID=66498035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811544276.0A Active CN109784654B (en) | 2018-12-17 | 2018-12-17 | Task generation method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109784654B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110263235A (en) * | 2019-06-05 | 2019-09-20 | 深圳市腾讯计算机***有限公司 | Information pushes object updating method, device and computer equipment |
CN110288193A (en) * | 2019-05-23 | 2019-09-27 | 中国平安人寿保险股份有限公司 | Mission Monitor processing method, device, computer equipment and storage medium |
CN110310085A (en) * | 2019-06-05 | 2019-10-08 | 上海易点时空网络有限公司 | A kind of answer activity management configuration method, server and computer readable storage medium |
CN110750614A (en) * | 2019-07-25 | 2020-02-04 | 卫宁健康科技集团股份有限公司 | Hospital intelligent service evaluation method, system, equipment and storage medium |
CN111222923A (en) * | 2020-01-13 | 2020-06-02 | 秒针信息技术有限公司 | Method and device for judging potential customer, electronic equipment and storage medium |
CN111429104A (en) * | 2020-04-03 | 2020-07-17 | 青岛大学 | Crowdsourcing item execution device, method, equipment and readable storage medium |
CN112364219A (en) * | 2020-10-26 | 2021-02-12 | 北京五八信息技术有限公司 | Content distribution method and device, electronic equipment and storage medium |
CN112507141A (en) * | 2020-12-01 | 2021-03-16 | 平安医疗健康管理股份有限公司 | Investigation task generation method and device, computer equipment and storage medium |
WO2022048515A1 (en) * | 2020-09-01 | 2022-03-10 | ***通信有限公司研究院 | Method and apparatus for implementing evaluation, and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108197305A (en) * | 2018-01-30 | 2018-06-22 | 深圳壹账通智能科技有限公司 | Questionnaire test and appraisal processing method, device, computer equipment and storage medium |
CN108428152A (en) * | 2018-03-12 | 2018-08-21 | 平安科技(深圳)有限公司 | questionnaire generation method, server and computer readable storage medium |
-
2018
- 2018-12-17 CN CN201811544276.0A patent/CN109784654B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108197305A (en) * | 2018-01-30 | 2018-06-22 | 深圳壹账通智能科技有限公司 | Questionnaire test and appraisal processing method, device, computer equipment and storage medium |
CN108428152A (en) * | 2018-03-12 | 2018-08-21 | 平安科技(深圳)有限公司 | questionnaire generation method, server and computer readable storage medium |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110288193A (en) * | 2019-05-23 | 2019-09-27 | 中国平安人寿保险股份有限公司 | Mission Monitor processing method, device, computer equipment and storage medium |
CN110288193B (en) * | 2019-05-23 | 2024-04-09 | 中国平安人寿保险股份有限公司 | Task monitoring processing method and device, computer equipment and storage medium |
CN110263235A (en) * | 2019-06-05 | 2019-09-20 | 深圳市腾讯计算机***有限公司 | Information pushes object updating method, device and computer equipment |
CN110310085A (en) * | 2019-06-05 | 2019-10-08 | 上海易点时空网络有限公司 | A kind of answer activity management configuration method, server and computer readable storage medium |
CN110750614A (en) * | 2019-07-25 | 2020-02-04 | 卫宁健康科技集团股份有限公司 | Hospital intelligent service evaluation method, system, equipment and storage medium |
CN110750614B (en) * | 2019-07-25 | 2020-12-22 | 卫宁健康科技集团股份有限公司 | Hospital intelligent service evaluation method, system, equipment and storage medium |
CN111222923A (en) * | 2020-01-13 | 2020-06-02 | 秒针信息技术有限公司 | Method and device for judging potential customer, electronic equipment and storage medium |
CN111222923B (en) * | 2020-01-13 | 2023-12-15 | 秒针信息技术有限公司 | Method and device for judging potential clients, electronic equipment and storage medium |
CN111429104A (en) * | 2020-04-03 | 2020-07-17 | 青岛大学 | Crowdsourcing item execution device, method, equipment and readable storage medium |
WO2022048515A1 (en) * | 2020-09-01 | 2022-03-10 | ***通信有限公司研究院 | Method and apparatus for implementing evaluation, and storage medium |
CN112364219A (en) * | 2020-10-26 | 2021-02-12 | 北京五八信息技术有限公司 | Content distribution method and device, electronic equipment and storage medium |
CN112507141A (en) * | 2020-12-01 | 2021-03-16 | 平安医疗健康管理股份有限公司 | Investigation task generation method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109784654B (en) | 2024-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109784654A (en) | Task creating method, device, computer equipment and storage medium | |
US10528916B1 (en) | Competency-based question selection for digital evaluation platforms | |
CN110321291A (en) | Test cases intelligent extraction system and method | |
CN109816200A (en) | Task method for pushing, device, computer equipment and storage medium | |
JP6819355B2 (en) | Recommendation generation | |
US20220292999A1 (en) | Real time training | |
Kokkodis | Dynamic, multidimensional, and skillset-specific reputation systems for online work | |
Wong | Sequence based course recommender for personalized curriculum planning | |
CN110750523A (en) | Data annotation method, system, computer equipment and storage medium | |
KR20210082108A (en) | Method for the operation of the real estate expected actual transaction price calculation device based on the real estate actual transaction price prediction | |
KR102281161B1 (en) | Server and Method for Generating Interview Questions based on Letter of Self-Introduction | |
Gong | Estimating participants for knowledge-intensive tasks in a network of crowdsourcing marketplaces | |
Daraei et al. | An analysis on the relation between strategic knowledge management and talent management strategy in profitability of the Southern Khorasan Electric Distribution Company (SKEDC) | |
Vannuccini et al. | Artificial Intelligence’s new clothes? A system technology perspective | |
Rogers | The digital transformation roadmap: rebuild your organization for continuous change | |
Rodriguez et al. | Before and after modelling: Risk knowledge management is required | |
Stenholm et al. | Knowledge management life cycle: an individual’s perspective | |
EP3834079A1 (en) | Multi-question multi-answer configuration | |
US11615364B2 (en) | Managing sales opportunities within an organization | |
CN110414690A (en) | The method and device of prediction is executed using machine learning model | |
WO2021071428A1 (en) | System and method for innovation, creativity, and learning as a service | |
CN112365302A (en) | Product recommendation network training method, device, equipment and medium | |
Khatwani et al. | Real-time prediction of information search channel using data mining techniques | |
Bi et al. | Software Architecture for Machine Learning in Personal Financial Planning | |
Mureithi | Predictive Analytics Model for Small and Medium Enterprises in Kenya, Forecasting on Supply and Demand |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |