CN113762695A

CN113762695A - Task list distribution method and device

Info

Publication number: CN113762695A
Application number: CN202110062986.5A
Authority: CN
Inventors: 姜盛乾; 杨熠; 潘洪臣
Original assignee: Beijing Jingdong Qianshi Technology Co Ltd
Current assignee: Beijing Jingdong Qianshi Technology Co Ltd
Priority date: 2021-01-18
Filing date: 2021-01-18
Publication date: 2021-12-07
Anticipated expiration: 2041-01-18
Also published as: CN113762695B

Abstract

The invention discloses a task list distribution method and device, and relates to the technical field of computers. One embodiment of the method comprises: clustering a plurality of task objects according to task types to determine a set corresponding to each task object; acquiring user information corresponding to each task object in the same set, and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object; and distributing the task list to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task list, wherein the task label indicates the task field and the task level corresponding to the task list. The implementation method improves the distribution efficiency and the distribution accuracy rate of the task list and improves the user experience.

Description

Task list distribution method and device

Technical Field

The invention relates to the technical field of computers, in particular to a task list distribution method and device.

Background

With the development of Network content, the internet trend that starts to rise from live broadcast and tape goods changes the structure of an industrial chain from a supply end to an MCN (Multi-Channel Network, a product form of a Multi-Channel Network) platform to a KOL (Key Opinion Leader) to a user, and influences the development and decision of the MCN platform. How to accurately and efficiently distribute the task list provided by the supply end to the corresponding KOL object for task processing by the MCN platform to maintain the operation of the whole industrial chain and improve the benefits of each party is a problem that needs to be solved urgently.

The prior art has at least the following problems:

the existing task list distribution method has the technical problems of low distribution efficiency, low distribution accuracy, poor user experience, unfavorable benign development of task objects and the like.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for task list allocation, which can improve the efficiency and accuracy of task list allocation, promote the benign development of task objects, and improve user experience.

To achieve the above object, according to a first aspect of an embodiment of the present invention, there is provided a method for allocating a task list, including:

clustering a plurality of task objects according to task types to determine a set corresponding to each task object;

acquiring user information corresponding to each task object in the same set, and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object;

and distributing the task list to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task list, wherein the task label indicates the task field and the task level corresponding to the task list.

Further, the step of determining the task tag comprises:

acquiring task list information corresponding to a plurality of task lists, and classifying the plurality of task lists according to the task list information;

and determining the task grade corresponding to each task list according to the classification processing result, and generating a task label according to the task grade and the task field.

Further, the classifying processing of the plurality of task lists according to the task list information further includes:

respectively extracting task attributes corresponding to the task lists from the task list information corresponding to the plurality of task lists;

calculating a task value corresponding to each task list according to the task attribute;

and classifying the plurality of task lists according to the task values and the classification algorithm.

Further, calculating a task value corresponding to each task list according to the task attribute, further comprising:

respectively configuring the weight coefficients of a plurality of task attributes corresponding to each task list; the sum of the weight coefficients of a plurality of task coefficients corresponding to each task list is 1;

and weighting the product of the attribute values corresponding to the plurality of task attributes and the weight coefficient to obtain the task value corresponding to each task list.

Further, the user information includes user preference information and user behavior information; according to the user information, hierarchy division is carried out on the task objects in the same set to determine the corresponding hierarchy of each task object, and the method further comprises the following steps:

historical task information corresponding to the task object is obtained, and an object value corresponding to the task object is calculated according to the historical task information;

calculating a first characteristic value corresponding to the user according to the user preference information, and calculating a second characteristic value corresponding to the user according to the user behavior information;

and performing hierarchical division on the task objects in the same set according to the object values corresponding to the task objects and the first characteristic values and the second characteristic values of the users corresponding to the task objects so as to determine the hierarchy corresponding to each task object.

Further, according to the object value corresponding to the task object and the first and second feature values of the user corresponding to the task object, performing hierarchy division on the task objects in the same set to determine the hierarchy corresponding to each task object, the method further includes:

calculating a hierarchy value according to the object value corresponding to the task object and the first characteristic value and the second characteristic value of the user corresponding to the task object;

and sequencing the hierarchy values, and determining the hierarchy corresponding to each task object according to the layering conditions and the sequencing result.

Further, still include:

and acquiring a characteristic value corresponding to the task object, and updating the hierarchy corresponding to the task object according to the characteristic value.

Further, distributing the task list to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task list, further comprising:

determining a target task list set according to the task field corresponding to the task object;

determining a target task list according to the hierarchy corresponding to the task object and the task level of each task list in the target task list set;

and distributing the target task list to the task object.

Further, still include:

and acquiring the task processing state of the task object to the distributed task list, and updating the distribution state according to the task processing state.

Further, the acquiring a task processing state of the task object to the assigned task list, and updating the assignment status according to the task processing state, further includes:

acquiring task processing states of the task object to the distributed task list, and calculating the probability corresponding to each task processing state according to an exponential distribution model;

calculating task completion values according to the probabilities corresponding to the task processing states and the task object information;

and updating the distribution condition according to the task completion value and the safety threshold value.

According to a second aspect of the embodiments of the present invention, there is provided a task list distribution apparatus including:

the set determining module is used for clustering a plurality of task objects according to task types to determine a set corresponding to each task object;

the hierarchy determining module is used for acquiring user information corresponding to each task object in the same set and performing hierarchy division on the task objects in the same set according to the user information to determine a hierarchy corresponding to each task object;

and the task list distribution module is used for distributing the task list to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task list, wherein the task label indicates the task field and the task level corresponding to the task list.

According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus, including:

one or more processors;

a storage device for storing one or more programs,

when executed by one or more processors, cause the one or more processors to implement any of the above-described methods of taskbill assignment.

According to a fourth aspect of embodiments of the present invention, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements any one of the above-described methods of tasking.

One embodiment of the above invention has the following advantages or benefits: clustering a plurality of task objects according to task types to determine a set corresponding to each task object; acquiring user information corresponding to each task object in the same set, and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object; according to the hierarchy corresponding to the task object and the task label corresponding to the task list, the task list is distributed to the corresponding task object, wherein the task label indicates the task field corresponding to the task list and the technical means of the task level, so that the technical problems that the task list distribution efficiency is low, the distribution accuracy rate is low, the benign development of the task object is not facilitated, and the user experience is poor in the existing task list distribution method are solved, and the technical effects of improving the task list distribution efficiency and the distribution accuracy rate, promoting the benign development of the task object, and improving the user experience are achieved.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic view of a main flow of a task sheet assignment method provided according to a first embodiment of the present invention;

FIG. 2a is a schematic diagram of a main flow of a task list distribution method according to a second embodiment of the present invention;

FIG. 2b is a diagram illustrating a task processing state when a task object performs task processing on an assigned task sheet in the method of FIG. 2 a;

FIG. 3 is a schematic diagram of the main modules of a task sheet distribution device provided according to an embodiment of the present invention;

FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 5 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic view of a main flow of a task sheet assignment method provided according to a first embodiment of the present invention; as shown in fig. 1, the task list allocation method provided by the embodiment of the present invention mainly includes:

step S101, clustering processing is carried out on a plurality of task objects according to task types so as to determine a set corresponding to each task object.

Specifically, the task type indicates a task field served by the task object, and a plurality of task objects belonging to the same task field can be clustered into a set by clustering a plurality of task objects. According to a specific implementation manner of the embodiment of the invention, multiple clustering processes can be performed on multiple task objects, so that multiple subsets are obtained, the task objects can be subjected to finer-grained hierarchical division, and the precision rate of allocation of subsequent task lists is improved.

Step S102, obtaining user information corresponding to each task object in the same set, and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object.

Through the arrangement, the hierarchy division is carried out according to the task objects serving the same task field (namely, the task objects are in the same set), so that the corresponding task list can be distributed according to the hierarchy of the task objects, the distribution efficiency and the distribution accuracy of the task list are further improved, and the user experience is improved.

Specifically, according to the embodiment of the present invention, the user information includes user preference information and user behavior information; the above-mentioned hierarchical division of task objects under the same set according to the user information to determine the hierarchy corresponding to each task object further includes:

Further, according to an embodiment of the present invention, the hierarchically dividing the task objects in the same set according to the object value corresponding to the task object and the first feature value and the second feature value of the user corresponding to the task object to determine the hierarchy corresponding to each task object further includes:

calculating a hierarchical value according to the object value corresponding to the task object and the first characteristic value and the second characteristic value of the user corresponding to the task object;

According to the embodiment of the invention, the historical task information of the task object comprises information such as the type and the number of products corresponding to the task object in a past period of time, and according to the historical task information, a task benefit currently generated by the task object can be calculated by using a prediction model (such as an index model and a winter prediction model), so that an object value corresponding to the task object can be obtained. The user preference value (i.e. the first characteristic value) and the user quality value (i.e. the second characteristic value) can be respectively calculated through the user information (including the user preference information, the user behavior information, and the like) corresponding to the task object. With the above arrangement, the task object is hierarchically divided using the predicted value of the task object itself (i.e., the object value) and the feature value of the user corresponding to the task object (i.e., the first feature value and the second feature value) as parameters, which contributes to accurately dividing the hierarchy of the task object.

Further, according to an embodiment of the present invention, the task list allocation method further includes:

Specifically, the feature values corresponding to the task objects include: according to a specific implementation manner of the embodiment of the present invention, a feature vector may be constructed according to the feature values, the feature vector may be classified by using a classification algorithm, and a hierarchy corresponding to the task object may be updated according to a classification result, so as to further improve accuracy of the divided task object hierarchy.

And S103, distributing the task list to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task list, wherein the task label indicates the task field and the task level corresponding to the task list.

Through the arrangement, the task list is distributed by combining the levels divided by the task objects and the task labels (mainly comprising the task field and the task level) corresponding to the task list, so that the task list distribution is reasonable and efficient, the user experience is improved, and the benign development of the task objects is promoted.

Specifically, according to an embodiment of the present invention, the step of determining the task tag includes:

Specifically, according to the embodiment of the present invention, after receiving a task list processing request initiated by a supply end, a task object management platform may classify a plurality of task lists through task list information (such as task list processing time, a publishing platform, a processing form, a task field, and the like), determine a task level corresponding to the task list according to a classification result, and further generate a task label according to the task level and the task field.

Further, according to an embodiment of the present invention, the classifying the plurality of task lists according to the task list information further includes:

Through the setting, the task attributes (such as quotation, expected income, influence and the like) are extracted from the task list information, corresponding weight coefficients can be set for the task attributes according to actual requirements, and then the task values corresponding to the task list are obtained through calculation; and classifying the task list according to the task value and a classification algorithm to determine the task grade of the task list.

Illustratively, according to an embodiment of the present invention, the hierarchically dividing the task objects in the same set according to the object value corresponding to the task object and the first feature value and the second feature value of the user corresponding to the task object to determine the hierarchy corresponding to each task object further includes:

Preferably, according to an embodiment of the present invention, the allocating the task sheet to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task sheet further includes:

and distributing the target task list to the task object.

Specifically, according to the embodiment of the invention, a plurality of task sheets can be determined as a target task sheet set in the same task field; and further determining the target task list according to the hierarchy of the task object and the task level of each task list in the target task list set. Through the arrangement, the distribution efficiency and the distribution accuracy of the task list are improved.

Further, the task list distribution method further includes:

Specifically, according to the embodiment of the present invention, the obtaining a task processing state of the task object to the assigned task list, and updating the assignment status according to the task processing state further includes:

Through the setting, the task processing state of the task list can be acquired in a specified period (such as the processing period of the task list), the task processing risk value of the task list can be monitored through constructing a mathematical model, and is compared with the risk threshold value, so that the distribution condition of the task list is updated. According to a specific implementation manner of the embodiment of the present invention, the updating measure may be a task training for the task object, a task object is added, or the task object is reassigned to the task sheet. Through the arrangement, the processing efficiency of the distributed task list is improved, and the processing effect of the distributed task list is guaranteed.

According to the technical scheme of the embodiment of the invention, the task objects are clustered according to the task types to determine the corresponding set of each task object; acquiring user information corresponding to each task object in the same set, and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object; according to the hierarchy corresponding to the task object and the task label corresponding to the task list, the task list is distributed to the corresponding task object, wherein the task label indicates the task field corresponding to the task list and the technical means of the task level, so that the technical problems that the task list distribution efficiency is low, the distribution accuracy rate is low, the benign development of the task object is not facilitated, and the user experience is poor in the existing task list distribution method are solved, and the technical effects of improving the task list distribution efficiency and the distribution accuracy rate, promoting the benign development of the task object, and improving the user experience are achieved.

FIG. 2a is a schematic diagram of a main flow of a task list distribution method according to a second embodiment of the present invention; an application scenario of the embodiment of the present invention is that an MSN platform allocates a task sheet received from a supply end to a KOL, as shown in fig. 2a, a task sheet allocation method provided by the embodiment of the present invention mainly includes:

step S201, acquiring task sheet information corresponding to a plurality of task sheets, and extracting task attributes corresponding to each task sheet from the task sheet information.

Specifically, after receiving a task order provided by a supplier (upstream merchant), task attributes are extracted from task order information (such as task order processing time, issuing platform, processing form, task field, and the like).

Step S202, calculating task values corresponding to the task lists according to the task attributes, and classifying the task lists according to the task values and a classification algorithm.

According to a specific implementation manner of the embodiment of the invention, the extracted task attributes comprise quotation, expected income and influence, and the weight coefficients corresponding to the attributes are set as

And the sum of the weight coefficients corresponding to the attributes is 1, i.e.

Recording the quote as X₁(ii) a Predicted yield is X₂Wherein

a is risk coefficient (0 < a < 1), D_jA budget cost interval; recording the influence (meaning the influence of the commodity/brand) as X₃，

Wherein N is the commodity/brand industry rank, M is the total quantity of commodities/brands in the industry, c is the predicted sales volume or the minimum sales volume of the merchants in the MCN channel, and p is the MCN end single piece profit. In summary, the task value is denoted as P_j(j ═ 1,2, …, n), then

Recording a task value set corresponding to a plurality of task lists as B ═ P₁,P₂,…,P_j}。

Then arranging all elements in the task value set corresponding to the plurality of task sheets according to the sequence from big to small to obtain

And classifying the data by adopting an ABC inventory method. According to a specific implementation of the embodiments of the present invention, when

When, i.e. front k₁The item task list is an A-type task; when in use

And then, the task list in the interval set is a B-type task, and the rest task lists in the set are marked as C-type tasks. It should be noted that the above classification method is only an example, and other classification methods in the prior art may also be adopted.

Step S203, determining the task label corresponding to each task list according to the classification processing result.

And determining the task rating corresponding to each task list according to the classification processing result, and generating a task label according to the task field and the task rating corresponding to the task list.

According to a specific implementation manner of the embodiment of the invention, taking a task field corresponding to food as an example, an enterprise issues an advertising task sheet for marketing a food commodity, and requests to sell 10000 food commodities through an X platform channel, so as to generate task sheet information [ food, X platform, sales with goods ].

According to the information of the task order, the merchant gives the price of the task order of 10 ten thousand yuan, then X₁100000; the sales amount is 10000, i.e., c is 10000, the profit of a single piece is 15 yuan, and p is 15. MCN estimates the cost of this task to be at [4,6 ]](unit: ten thousand yuan), the risk coefficient is a is 0.1, then maxD_j＝60000，minD_jCalculated as 40000

Assuming that the food field comprises 50 brands, the brand is 10 in the comprehensive sales line of the food industry, and N is 10, and M is 50

In conclusion, the task value corresponding to the task list can be calculated.

Further, suppose that 100 task sheets exist in the task sheet set corresponding to the current task field, the task is ranked as 7 in the task set through ranking, and the task value of the first 10 task sheets reaches 70% of the total value of the task sheet set, so that the task level of the task sheet is a.

And generating a task label according to the task grade and the task field to obtain a task label [ food, X platform, sales delivery, grade A ], and storing the task label into a database for subsequent screening.

And step S204, clustering the plurality of task objects according to the task types to determine a set corresponding to each task object.

According to a specific implementation manner of the embodiment of the present invention, a task object set in the same field can be determined by clustering according to a main task label (corresponding task type, such as travel, life, movie, and the like) of a KOL (task object).

Step S205, historical task information corresponding to the task object is obtained, and an object value corresponding to the task object is calculated according to the historical task information.

Specifically, the more recent historical task information is from the current time, the calculated object valueThe more accurate. According to the embodiment of the invention, the task object values under different mathematical models are calculated by adopting the weight changing along with the time. Taking exponential as an example-let the weight of the closest point be η_i(0 < eta < 1), the attenuation is increased along with the time interval, namely eta_k，k＞2，

The parameter k is the number of time intervals, and the weight corresponding to the historical task information with a large time interval (i.e., a time far from the current time interval) is close to 0. The historical task information corresponding to the task object can be calculated by using a prediction model (such as an index model, a winter prediction model and the like), and the object value χ corresponding to the task object can be obtained_i。

Step S206, user information corresponding to each task object in the same set is obtained, and a first characteristic value and a second characteristic value corresponding to the user are calculated according to the user information.

Specifically, the user information includes user preference information and user behavior information.

According to the embodiment of the invention, all static and dynamic information of a user in a content publishing platform by a KOL under an MCN platform is obtained from a database, wherein the static information comprises information such as attention duration, consumption accumulated amount, consumption average period, user gender, age, region and the like; the dynamic information comprises browsing, attention, consumption, inquiry, comment, praise and other information in the user platform.

The user preference information (indicating the user's preferred content area) can be inductively matched based on the user history (the user static information and the user dynamic information described above) in the database. The user preference information includes user content preferences and corresponding user exertion energy indices. According to a specific implementation manner of the embodiment of the present invention, for all users in a certain domain KOL, a preference degree of a certain personalized content tag (i.e. a certain task domain) is a user amount of a subsystem (the task object set mentioned above) occupied by a preferred userThe ratio of (a) x the effort-wasting index is higher than the average ratio of the preferred users; taking a content field as an example, for example, the food category tags include desserts, cooked foods, Chinese food, daily food, seafood, etc., a certain tag is related to 100 users such as desserts, the MCN food category covers 2000 users in total, the preferred user accounts for 5%, the food category users consume 60 yuan averagely, 50 platform consumption of the 100 related tags is higher than 60, the consumption is higher than the average user rate is 50%, 9 personalized content tags with the highest user preference degree are taken, and thus a user preference content tag list records [ pl ] is constructed_q]＝[pl₁,pl₂,…,pl₉]Introducing a boolean variable, wherein when a certain personalized tag of the KOL is the same as the existing tags in the list, the value of the boolean variable is 1, and otherwise, the value of the boolean variable is 0. When the pool is 1, giving the position weight according to the position sequence of the corresponding personalized tag in the list

(a plurality of same ones are the first ones), a Boolean weighted preference eigenvalue (i.e. the first eigenvalue corresponding to the user) is obtained

According to another specific implementation manner of the embodiment of the present invention, the user behavior information includes whether there is a purchase history (L) in the KOL channel_n) Frequency of interaction (T)_n) Duration of interest (M)_n) And so on. Taking the above three items of information as an example, the user h_nFor the quality of the KOL (task object)

Wherein,

psi is the consumption average mass coefficient, M_zFor the registration period, the user value (i.e. the second characteristic value) of the corresponding user of the KOL is

Step S207, performing hierarchy division on the task objects in the same set according to the object values corresponding to the task objects and the first and second feature values of the users corresponding to the task objects, so as to determine the hierarchy corresponding to each task object.

Specifically, according to the embodiment of the present invention, the following may be obtained by performing calculation according to the object value corresponding to the task object and the first feature value and the second feature value of the user corresponding to the task object:

wherein v is a hot content addition value, and after sorting is performed according to the calculation result, layering is performed according to the proportion of 10%, 20% and 70% (namely layering conditions). It should be noted that the above layering manner and the corresponding layering values are merely examples, and the layering values or the layering method may be adjusted according to actual situations.

Through the arrangement, sufficient training data can be obtained by calibrating a sufficient amount of user information And content information data, so that a task object hierarchical model can be constructed, And a Classification method listed above is selected (including but not limited to K-Nearest neighbor (KNN), Classification Regression Tree (CART), naive Bayes (Bayesian), a kernel-based Support Vector Machine (SVM), a Neural Network (Neural Network) And trained to obtain an effective feature classifier, which can be used for solving KOL (hierarchical object model) layering.

According to a specific implementation manner of the embodiment of the invention, the historical task data (the historical task information) of a certain KOL in the past 3 months is {50,70,60}, and the task value of the KOL in the current month is calculated to reach 63 according to the exponential smoothing method, so that chi is obtained_i＝63。

Taking a user corresponding to the KOL as an example, the user history data is a purchase record, the interaction frequency is 0.5 times/day, the attention duration is 200 days, the account registration duration is 300 days, and the average quality coefficient of consumption is

Under the model (2), the quantitative index P of the user quality of the user_nIs 0.7. Similarly, the sum of the quantization indexes P of the user quality of all the users covered by the KOL can be calculated_z,i。

Assuming that the KOL is 10 in rank, the task domain has a total of 50-bit KOLs, and the KOL is at the second level. In addition, assuming that the personalization index (task attribute) is 5 items, that is, the number l of feature values corresponding to the task object is 5, calibrating a training data set, where the training data is, for example, <1|0.1,0.4,3.2,20245,1>, normalizing the training data, and then using a Support Vector Classification (SVC) method to select a gaussian Kernel (RBF Kernel) to construct a model, and performing model training to obtain an SVM Classification model C with a parameter C of 1.27 and a parameter g of 3.55. And (3) predicting the characteristic data by using the model, wherein the characteristic data is <0.5,0.7,3.1,9011 and 0.1>, inputting the characteristic data into the trained model C to obtain a prediction result as a second level, and updating/correcting the level of the task object.

And S208, determining a target task list set according to the task field corresponding to the task object, determining a target task list according to the hierarchy corresponding to the task object and the task level of each task list in the target task list set, and distributing the target task list to the task object.

According to a specific implementation manner of the embodiment of the present invention, the task label set of the task list may be traversed according to the KOL hierarchy sorting in the above steps, after the high-quality task list in the task field is screened, the task list consistent with the main label is screened again, if the label successfully corresponds to the high-quality task list, the composite score of the current KOL is reduced (the hierarchy of the current KOL is reduced) according to the decay function, and meanwhile, a relevant rule is set (for example, the number of class a task objects of the KOL is limited), so that the task object (the KOL) is not allocated with too many class a tasks in the subsequent round of selection; and if the correspondence is not successful, removing the label and screening again, wherein the KOL comprehensive score needs to be multiplied by a deviation coefficient beta to dispatch the optimal task list in the score range. Meanwhile, marking the selected task as a null element, ensuring that the virtual total amount in the task list set is unchanged and the corresponding grade of each task list is unchanged. And similarly, performing task dispatching to the next KOL according to the ranking rotation until the task dispatching is completed, namely all task singlets in the task list set are empty.

Step S209 is to acquire the task processing state of the task object to the assigned task list, and update the assignment state according to the task processing state.

The steps actually construct a task list distribution system, and the distribution system is used for distributing the task list. In practical application, a reliability state model can be introduced according to a composition structure (including a supply end, an MCN, a KOL and a user) in the task list distribution system, the reliability of the distribution system under the influence of time factors is calculated, and a reliability threshold value is set according to the existing development strategy, so that risk prediction is carried out, and an adjustment decision is made in advance aiming at risks. The detailed process is as follows:

establishing a reliability structure of a subsystem (a task object set obtained by the clustering process and comprising a plurality of KOLs), recording the normal working state of an individual KOL as 0 in a specified period (usually taking contract duration), recording the state of the KOL which cannot normally work due to factors such as emergency as 1, taking an exponential distribution model as an example, setting parameters lambda and mu to obey exponential distribution, wherein the parameters are determined by a standard mathematical model, and the state transition condition of the KOL in the period is shown in FIG. 2b and comprises P₀₀、P₀₁、P₁₀And P₁₁Four task processing states, P₀₀The KOL state is unchanged after Δ t time; p₀₁The state is 0 at the moment t, and becomes 1 after the time of delta t; p, P₁₀And P₁₁The same meaning is applied. The probability of occurrence of the four task processing states is calculated by the following formula:

P₀₀{Δt}＝P{X(t+Δt)＝0|X(t)＝0}＝1-λΔt+o(Δt)

P₀₁{Δt}＝P{X(t+Δt)＝1|X(t)＝0}＝λΔt+o(Δt)

P₁₀{Δt}＝P{X(t+Δt)＝0|X(t)＝1}＝μΔt+o(Δt)

P₁₁{Δt}＝P{X(t+Δt)＝1|X(t)＝1}＝1-μΔt+o(Δt)

the overall reliability values of the series system, the parallel system and the voting system can be deduced according to the subsystem reliability calculation formula and are marked as P_cIn a normal state, the subsystems and the overall system formed by the subsystems are respectively a voting system structure and a parallel system structure.

Further, a system safety threshold value is set, a safety threshold value tau is set according to the risk resistance of the current MCN end, and when the reliability of the whole system is lower than the threshold value, namely P_cWhen the value is less than or equal to tau, the method can take measures in advance and quickly locate the problem to the KOL under a certain subsystem, thereby improving the running speed of the supply flow. In addition, according to market demand change and enterprise development change, corresponding indexes are flexibly adjusted along with the market demand change and the enterprise development change, and prediction is more accurate.

Taking the food subsystem as an example, assume that the subsystem includes 5 bitskol, if the flow demand can be completed only when five kol work at the same time, the system is a tandem system, and the reliability of kol (i.e., the task completion value indicating the completion status of the assigned task list in the current assignment state) at the current time is calculated according to the task object information (e.g., the time of entry, the historical task processing status, etc.), and the system reliability is P_c＝P₁(t₁)*P₂(t₂)*P₃(t₃)*P₄(t₄)*P₅(t₅) Then comparing it with safety threshold tau to judge P_cAnd the magnitude of τ, if P_cAnd (4) the distribution condition is updated when the value is less than or equal to tau, and the updating measure can be a mode of performing task training on the task object, adding the task object or redistributing the task object to the task list and the like. Through the arrangement, the processing efficiency of the distributed task list is improved, and the processing effect of the distributed task list is guaranteed.

FIG. 3 is a schematic diagram of the main modules of a task sheet distribution device provided according to an embodiment of the present invention; as shown in fig. 3, the task list distribution apparatus 300 according to the embodiment of the present invention mainly includes:

the set determining module 301 is configured to perform clustering processing on the plurality of task objects according to the task types to determine a set corresponding to each task object.

The hierarchy determining module 302 is configured to obtain user information corresponding to each task object in the same set, and perform hierarchy division on the task objects in the same set according to the user information to determine a hierarchy corresponding to each task object.

Specifically, according to an embodiment of the present invention, the hierarchy determining module 302 is further configured to:

Further, according to an embodiment of the present invention, the hierarchy determining module 302 is further configured to:

Further, according to an embodiment of the present invention, the above task list distribution apparatus 300 further includes a hierarchy updating module, configured to:

Specifically, the feature values corresponding to the task objects include: according to a specific implementation manner of the embodiment of the invention, the personalized characteristic values such as the average UV flow, the ROI qualification rate, the user overall value and the like can be used for constructing a characteristic vector according to the characteristic values, classifying the characteristic vector by using a classification algorithm, and updating the level corresponding to the task object according to the classification processing result so as to further improve the accuracy of the divided task object level.

And the task sheet distributing module 303 is configured to distribute the task sheet to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task sheet, where the task label indicates the task field and the task level corresponding to the task sheet.

Specifically, according to the embodiment of the present invention, the task sheet distributing device 300 further includes a task label generating module, configured to:

Further, according to an embodiment of the present invention, the task tag generating module is further configured to:

Illustratively, according to an embodiment of the present invention, the task tag generating module is further configured to:

Preferably, according to an embodiment of the present invention, the task list allocating module 303 is further configured to:

and distributing the target task list to the task object.

Further, the task list distributing apparatus 300 further includes a distribution status updating module, configured to:

Fig. 4 shows an exemplary system architecture 400 to which the method or apparatus for tasking orders of embodiments of the present invention may be applied.

As shown in fig. 4, the system architecture 400 may include

terminal devices

401, 402, 403, a network 404, and a server 405 (this architecture is merely an example, and the components included in a particular architecture may be adapted according to application specific circumstances). The network 404 serves as a medium for providing communication links between the

terminal devices

401, 402, 403 and the server 405. Network 404 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

A user may use

terminal devices

401, 402, 403 to interact with a server 405 over a network 404 to receive or send messages or the like. Various communication client applications, such as a task sheet assignment type application, a data processing type application, etc. (for example only), may be installed on the

terminal devices

401, 402, 403.

The

terminal devices

401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 405 may be a server that provides various services, such as a server (for example only) that is (performs assignment of a job ticket/performs data processing) for a user using the

terminal devices

401, 402, 403. The server may analyze and perform other processing on the received data such as the task type and the user information, and feed back a processing result (for example, a set corresponding to the task object and a hierarchy corresponding to the task object — only an example) to the terminal device.

It should be noted that the task list allocation method provided by the embodiment of the present invention is generally executed by the server 405, and accordingly, the task list allocation apparatus is generally disposed in the server 405.

It should be understood that the number of terminal devices, networks, and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 5, a block diagram of a computer system 500 suitable for use with a terminal device or server implementing an embodiment of the invention is shown. The terminal device or the server shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a set determination module, a hierarchy determination module, and a task order assignment module. The names of the modules do not limit the modules themselves in some cases, for example, the set determining module may also be described as a "module for clustering a plurality of task objects according to task types to determine a set corresponding to each task object".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: clustering a plurality of task objects according to task types to determine a set corresponding to each task object; acquiring user information corresponding to each task object in the same set, and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object; and distributing the task list to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task list, wherein the task label indicates the task field and the task level corresponding to the task list.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for assigning a task order, comprising:

2. The method of claim 1, wherein the step of determining the task label comprises:

acquiring task list information corresponding to a plurality of task lists, and classifying the task lists according to the task list information;

and determining a task grade corresponding to each task list according to the classification processing result, and generating a task label according to the task grade and the task field.

3. The method according to claim 2, wherein the classifying the plurality of the job tickets according to the job ticket information further comprises:

and classifying the plurality of task lists according to the task values and a classification algorithm.

4. The method according to claim 3, wherein the calculating a task value corresponding to each task sheet according to the task attribute further comprises:

and performing weighting processing on the product of the attribute values corresponding to the plurality of task attributes and the weight coefficient to obtain the task value corresponding to each task list.

5. The method of claim 1, wherein the user information includes user preference information and user behavior information; the hierarchy division is performed on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object, and the method further comprises the following steps:

and performing hierarchical division on the task objects under the same set according to the object values corresponding to the task objects and the first characteristic values and the second characteristic values of the users corresponding to the task objects so as to determine the hierarchy corresponding to each task object.

6. The method for allocating the task list according to claim 5, wherein the task objects in the same set are hierarchically divided according to the object value corresponding to the task object and the first feature value and the second feature value of the user corresponding to the task object to determine the hierarchy corresponding to each task object, further comprising:

7. The method of claim 5, further comprising:

and acquiring a characteristic value corresponding to the task object, and updating a hierarchy corresponding to the task object according to the characteristic value.

8. The method according to claim 1, wherein the step of assigning the task sheet to the corresponding task object according to the hierarchy corresponding to the task object and the task label corresponding to the task sheet further comprises:

determining a target task list according to the corresponding hierarchy of the task object and the task level of each task list in the target task list set;

and distributing the target task list to the task object.

9. The method of claim 1, further comprising:

10. The method according to claim 9, wherein the acquiring of the task processing state of the task object to the assigned task list updates the assignment status according to the task processing state, and further comprises:

11. A task order distribution apparatus, comprising:

the hierarchy determining module is used for acquiring user information corresponding to each task object in the same set and performing hierarchy division on the task objects in the same set according to the user information to determine the hierarchy corresponding to each task object;

12. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-10.

13. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-10.