CN113033931A

CN113033931A - Closed-loop self-adaptive individual and region allocation method and device and computing equipment

Info

Publication number: CN113033931A
Application number: CN201911349557.5A
Authority: CN
Inventors: 杨雨青; 郑欢; 陈勇; 余侃; 高琴; 傅泉辉; 许林甲
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Zhejiang Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Zhejiang Co Ltd
Priority date: 2019-12-24
Filing date: 2019-12-24
Publication date: 2021-06-25
Anticipated expiration: 2039-12-24
Also published as: CN113033931B

Abstract

The embodiment of the invention relates to the technical field of instant messaging, and discloses a closed-loop self-adaptive individual and region allocation method, a closed-loop self-adaptive individual and region allocation device and computing equipment, wherein the method comprises the following steps: applying a hierarchical attribution model to perform hierarchical partition processing on the users according to the instant user distribution data; performing area division on core points according to a pre-stored area division strategy and a user partition attribution data application area automatic division model subjected to partition processing; performing closed-loop verification on the hierarchy attribution model and the automatic region division model according to service system data, and optimizing parameters; and outputting user partition attribution data and core point attribution data according to the optimized parameters. Through the mode, the embodiment of the invention supports multi-level scattered user summarization and diversified partition strategy control, is suitable for more complicated partition conditions, can realize partition result verification closed-loop control, and continuously optimizes region allocation.

Description

Closed-loop self-adaptive individual and region allocation method and device and computing equipment

Technical Field

The embodiment of the invention relates to the technical field of instant messaging, in particular to a closed-loop self-adaptive individual and area allocation method, a closed-loop self-adaptive individual and area allocation device and computing equipment.

Background

The reasonable division of management areas and the matching of service object attributions are the basis of intelligent management work. At present, an intelligent technical scheme is still lacking in the aspect of area division, and an area division mode is often determined based on administrative division and combination of subjective judgment. Although the only region division algorithm, such as the thieson polygon (Voronoi) algorithm, has universality, the algorithm depends on homogenized single data, and the application range is limited to the case that the region distribution is relatively uniform.

At present, the division of the area is mainly realized by two methods: the method is simple and extensive, but lacks data support, and cannot realize fine management. One is a standard Voronoi algorithm, and the only condition for dividing the region of the algorithm depends on the distance from a core point, so that the algorithm cannot support more complex division conditions. Meanwhile, the algorithm can work normally only under the condition that the core points are distributed relatively uniformly.

Disclosure of Invention

In view of the above, embodiments of the present invention provide a closed-loop adaptive individual and region allocation method, apparatus and computing device, which overcome or at least partially solve the above problems.

According to an aspect of the embodiments of the present invention, there is provided a closed-loop adaptive individual and region allocation method, the method comprising: applying a hierarchical attribution model to perform hierarchical partition processing on the users according to the instant user distribution data; performing area division on core points in a core point database according to a pre-stored area division strategy and a user partition attribution data application area automatic division model subjected to partition processing; performing closed-loop verification on the hierarchy attribution model and the area automatic division model according to service system data, and optimizing parameters of the hierarchy attribution model and the area automatic division model; and outputting user partition attribution data and core point attribution data according to the optimized hierarchical attribution model and the parameters of the automatic region division model.

In an optional manner, the applying a hierarchical attribution model to users according to the instant user distribution data includes: and attributing all users in the previous level partition to the current level partition according to the user permanent data application level attribution model in the instant user distribution data.

In an optional manner, applying a hierarchical attribution model to all users in a previous hierarchical partition according to the customer premises data in the instant user distribution data includes: calculating partition gravity centers according to the user permanent station data in the instant user distribution data and the current level partition list; calculating the Cartesian distance between the user grid and the partition gravity center according to the user permanent station data to form a user Cartesian distance vector; calculating a weighted Manhattan distance vector of the user grid and the partition gravity center according to the user permanent station data and the road network data; calculating a weighted double-distance vector of the user grid and the partition gravity center according to the user Cartesian distance vector and the weighted Manhattan distance vector; and extracting the weighted double-distance vectors of the user grid where the user resides and all the partition barycenters, and taking the partition corresponding to the partition barycenter with the shortest weighted double-distance as the attribution partition of the user.

In an optional manner, the performing area division on the core point in the core point database according to a pre-stored area division policy and a user partition attribution data application area automatic division model of partition processing includes: calculating a weighted double-distance vector between the core point and a hierarchical region by applying the hierarchical attribution model according to the core point; establishing a to-be-distributed set of all to-be-distributed hierarchy regions of a designated hierarchy of a strategy center; obtaining a minimum weighted population number of each core point in the set to be distributed according to the core point grade by applying a core point bottom-preserving distribution model; obtaining a attribution combination with the minimum weighted number of each core point in the remaining hierarchical regions to be distributed of the set to be distributed according to the core point grade by applying a core point attribution distribution model; and merging the bottom-preserving combination and the attribution combination of each core point to form a merged attribution combination of the core points.

In an optional manner, the obtaining, by the application of the core point warranty distribution model, a minimum weighted population of the core points in the set to be distributed according to the core point level includes: sequentially extracting the core points from the set to be distributed, and constructing all qualified base protection combinations of each core point, so that the sum of the attribution population of each qualified base protection combination is just greater than the requirement of the number of base protection people; calculating, for each of the core points, a weighted number of each of the qualified underwriting combinations of the core points; and arranging the core points from high to low according to grades, and sequentially taking the qualified guaranteed base combination with the smallest weighted number of people of each core point as the guaranteed base combination of each core point.

In an optional manner, the obtaining, by the application of the core point attribution allocation model, an attribution combination with a smallest weighted number of the core points in the remaining hierarchical regions to be allocated of the set to be allocated according to the core point level includes: sequentially extracting the core points from the rest hierarchical regions to be distributed of the sets to be distributed, and constructing all qualified attribution combinations of the core points, so that the sum of attribution crowds of each qualified attribution combination is just larger than the requirement of the number of attributions of the core points at the current level; calculating, for each of the core points, a weighted number of people for each of the qualified ascription combinations for the core point; and arranging the core points from high to low according to grades, and sequentially taking the qualified attribution combination with the smallest weighted number of people for each core point as the attribution combination of each core point.

In an optional manner, the performing closed-loop verification on the hierarchical attribution model and the regional automatic division model according to service system data, and optimizing parameters of the hierarchical attribution model and the regional automatic division model includes: respectively acquiring corresponding parameter sequences according to the parameters of the hierarchy attribution model and the automatic region division model; respectively calculating corresponding deviation functions according to the parameter sequences of the hierarchical attribution model and the automatic region division model; respectively introducing an optimization step length parameter according to the deviation functions to calculate corresponding deviation gradient functions; and calculating a new parameter sequence and a new deviation function according to the deviation gradient function and the optimized parameter step length until the new deviation function meets the convergence condition.

According to another aspect of the embodiments of the present invention, there is provided a closed-loop adaptive individual and regional allocation apparatus, the apparatus comprising: the hierarchical partition unit is used for applying a hierarchical attribution model to carry out hierarchical partition processing on the users according to the instant user distribution data; the area division unit is used for carrying out area division on the core points in the core point database according to a pre-stored area division strategy and a user partition attribution data application area automatic division model which is processed in a partition mode; the parameter verification unit is used for performing closed-loop verification on the hierarchy attribution model and the area automatic division model according to service system data and optimizing parameters of the hierarchy attribution model and the area automatic division model; and the data output unit is used for outputting user partition attribution data and core point attribution data according to the optimized hierarchical attribution model and the parameters of the automatic region division model.

According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is configured to store at least one executable instruction that causes the processor to perform the steps of the closed-loop adaptive individual and zone allocation method described above.

According to yet another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing the processor to perform the steps of the closed-loop adaptive individual and region allocation method described above.

The embodiment of the invention applies a hierarchical attribution model to carry out hierarchical partition processing on the users according to the instant user distribution data; performing area division on core points in a core point database according to a pre-stored area division strategy and a user partition attribution data application area automatic division model subjected to partition processing; performing closed-loop verification on the hierarchy attribution model and the area automatic division model according to service system data, and optimizing parameters of the hierarchy attribution model and the area automatic division model; user partition attribution data and core point attribution data are output according to the optimized hierarchical attribution model and the optimized parameters of the automatic region division model, multi-level scattered user summarization and diversified partition strategy control are supported, the method is suitable for complex division conditions, partition result verification closed-loop control can be achieved, and region allocation is continuously optimized.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart illustrating a closed-loop adaptive individual and regional distribution method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating a hierarchical zoning process for a user according to a closed-loop adaptive individual and regional distribution method provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram illustrating a method of hierarchical affiliation model for a closed-loop adaptive individual and regional allocation method provided by an embodiment of the invention;

fig. 4 is a schematic diagram illustrating the area division of core points by the closed-loop adaptive individual and area allocation method according to the embodiment of the present invention;

FIG. 5 is a schematic diagram illustrating a method for automatically partitioning a region into models by using a closed-loop adaptive individual and region allocation method according to an embodiment of the present invention;

fig. 6 is a schematic diagram illustrating a complete flow of region division for core points in the closed-loop adaptive individual and region allocation method according to an embodiment of the present invention;

FIG. 7 is a flowchart illustrating a parameter optimization method of a closed-loop adaptive individual and regional allocation method according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a closed-loop adaptive individual and regional distribution apparatus according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a computing device provided in an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

Fig. 1 is a flowchart illustrating a closed-loop adaptive individual and regional allocation method according to an embodiment of the present invention. As shown in fig. 1, the closed-loop adaptive individual and regional allocation method includes:

step S11: and applying a hierarchical attribution model to perform hierarchical partition processing on the users according to the instant user distribution data.

In an embodiment of the invention, a hierarchical attribution model is applied to attributing a population of users to meaningful cell partitions, such as residential cells. Small partitions will be further layered, i.e. the partitions are nested. In the case of a partition not fully paved, the hierarchical attribution model performs targeted processing according to conditions. The data relied on by the hierarchy attribution model is partition data (positions and boundaries) of each hierarchy and user permanent data. The user permanent station data distinguishes different types, and the longitude and latitude of the grid positioned by the user are used for the identification of the permanent station.

In the embodiment of the invention, all users in the previous level partition are attributed to the current level partition according to the user permanent data application level attribution model in the instant user distribution data. For example, as shown in fig. 2, performing level 1 partition definition according to the customer premises data application level attribution model in the instant user distribution data, attributing all users to a level 1 partition, generating a level 1 partition location library, performing level 2 partition definition according to the customer premises data application level attribution model, attributing all users in the level 1 partition to a level 2 partition, generating a level 2 partition location library, and so on, performing level n partition definition on all user application level attribution models in a previous n-1 partition of a level, attributing to a level n partition, generating a level n partition location library, and finally obtaining a user hierarchy partition location library.

The hierarchical attribution model of the embodiment of the invention adopts a binary weighted Distance with Cut-Off (DWDCO) model. The data processing flow is as follows: calculating partition gravity centers according to the user permanent station data in the instant user distribution data and the current level partition list; calculating the Cartesian distance between the user grid and the partition gravity center according to the user permanent station data to form a user Cartesian distance vector; calculating a weighted Manhattan distance vector of the user grid and the partition gravity center according to the user permanent station data and the road network data; calculating a weighted double-distance vector of the user grid and the partition gravity center according to the user Cartesian distance vector and the weighted Manhattan distance vector; and extracting the weighted double-distance vectors of the user grid where the user resides and all the partition barycenters, and taking the partition corresponding to the partition barycenter with the shortest weighted double-distance as the attribution partition of the user. When calculating a weighted Manhattan distance vector, establishing a shortest path between the partition gravity center and the user grid according to the road network data, and dividing the shortest path into different straight line sections; and calculating the weighted Manhattan distance vector of the user grid and the partition gravity center according to the weight of each straight line section provided in the road network data.

More specifically, when all users in the previous hierarchical region are attributed to the current hierarchical region according to the customer premises data application hierarchical attribution model, as shown in fig. 3, the method includes:

step S110: and acquiring the frequent user premises data in the instant user distribution data.

The customer premise data is the customer premise data of all the customers in the upper-level subarea.

Step S111: the partition center of gravity is calculated.

And calculating the partition gravity center according to the user permanent location data and the current level partition list. Center of gravity of partition j

The following relation is satisfied:

wherein p is_iIs the weight, x, of the user grid i_i、y_iThe latitude and longitude of the permanent station of the user grid i.

Step S112: the Cutoff distance vector is calculated.

Partitioning by hierarchy ensures that the user grid of the current hierarchy only computes distances to the partitions of the current hierarchyGenerating a Cutoff distance vector:

step S113: a user cartesian distance vector is calculated.

And aiming at each user grid i, calculating the Cartesian distance between the user grid and the partition gravity center according to the user permanent station data and the Cutoff distance vector to form a user Cartesian distance vector. Cartesian distance vector

The following relation is satisfied:

step S114: path segmentation is performed.

Aiming at the gravity center of each partition j, establishing the shortest path between the gravity center of the partition j and each user grid i by depending on road network data, and dividing the shortest path into different straight line sections

Wherein the content of the first and second substances,

representing the kth straight line segment on the shortest path from partition j to user grid i.

Step S115: a weighted manhattan distance vector is calculated.

Aiming at each user grid i, the path segmentation provided by the road network data is relied on, and the weight of each road section is considered

Calculating weighted Manhattan distance vectors of user grid i and all partitions j

The following relation is satisfied:

step S116: a weighted double distance vector is calculated.

Aiming at each user grid i, calculating weighted double-distance vectors of the user grid i and all partitions j according to the user Cartesian distance vector and the weighted Manhattan distance vector

The following relation is satisfied:

wherein the content of the first and second substances,

the partition is double weighted.

The weights of the user cartesian distance vectors,

is the weight of the weighted manhattan distance vector.

Step S117: and (5) polling the partitions.

And aiming at each user k, extracting the weighted double-distance vectors of the resident user grid of the user k and all the partitions j, and performing partition polling.

Step S118: and judging whether the distance is the shortest. If so, go to step S119; if not, step S117 is performed.

And judging whether the weighted double-distance vectors of the resident user grid i of the user k and all the partitions j are shortest or not.

Step S119: and forming user partition attribution.

The weighting double-distance vector of the resident user grid i of the user k and all the subareas j is shortest, the shortest weighting double distance is extracted, and the subareas j are taken as the usersk, forming user zone attribution. Finally, for each partition j, the number of its subscribers μ is summarized_j。

The embodiment of the invention takes objective data as a basis, generates division data based on a model algorithm, ensures the fairness of results, adopts a division scheme based on user permanent data, can adapt to more complex division conditions, has higher feasibility and universality of results and strong popularization, supports multi-level summarization, integrates Cartesian distance and Manhattan distance, and ensures the fairness and controllability of distribution.

Step S12: and performing area division on the core points in the core point database according to a pre-stored area division strategy and a user partition attribution data application area automatic division model subjected to partition processing.

The automatic region division model provided by the embodiment of the invention divides the region around the core point. The object of the operation when dividing the region is a small partition of a specified hierarchy. The user is indirectly assigned to the area by the area assignment of the partition as an object assigned to each partition. As shown in fig. 4, the input data of the automatic area division model mainly includes a user hierarchical partition home database and a core point database, and the core point area is allocated by the policy center according to the hierarchical area division policy by applying the automatic area division model control. The core point database comes from other systems and must include the location of the core point and its priority for controlling the assigned weights. The automatic region partitioning model is preferably a Guaranteed Priority Strategic Allocation (GPSA) model, and the partition to which each core point belongs is automatically allocated under the control of a policy center. The parameters controlled by the policy center include: the number of bottom-guaranteed attribution users and the minimum number of attribution users of each core point grade; default warranty weight coefficient η for each core point level_nAnd a default home weight coefficient ζ_n(ii) a And setting a hierarchy to be distributed.

In the embodiment of the present invention, as shown in fig. 5, the method includes:

step S121: and calculating the weighted double-distance vector of the core point and a hierarchical region by applying the hierarchical attribution model according to the core point.

In the embodiment of the invention, according to the configuration of the policy center, the hierarchical regions (for example, partitions) of the hierarchy to be distributed are selected, and the weighted double distance vector of each core point and each hierarchical region is calculated. The whole calculation process and method are consistent with the DWDCO model of the hierarchy attribution calculation, and are not described in detail herein.

Step S122: and establishing a to-be-allocated set of all to-be-allocated hierarchical regions of the designated hierarchy of the strategy center.

To be assigned collections

Where N is the number of all hierarchy regions that belong locally to the required hierarchy, AⁱIs the ith hierarchical region.

Step S123: and obtaining the minimum weighted bottom-preserving combination of each core point in the set to be distributed according to the core point grade by applying a core point bottom-preserving distribution model.

The core goal of the core point fidelity Allocation (KPBA) model is to better satisfy the requirements of the number of fidelity persons set by the policy center according to the core point level.

In the embodiment of the invention, the specific flow is as follows: and sequentially extracting the core points from the set to be distributed, and constructing all qualified base protection combinations of each core point, so that the sum of the attribution population of each qualified base protection combination is just greater than the requirement of the number of base protection people. The set of all qualified guaranteed combinations of the marked core points n is:

wherein M is_nThe number of qualified guaranteed-base combinations for core point n,

N_mnfor bottom protection combination

The number of hierarchical regions included in (a),

for bottom protection combination

The ith hierarchical region.

For each of the core points, calculating a weighted number of each of the qualified underwriting combinations of the core points:

is a weighted double distance vector, μ, of the core point n and the combined inner level region i_iThe number of the belongings of the inner-level region i is combined.

And arranging the core points from high to low according to grades, and sequentially taking the qualified guaranteed base combination with the smallest weighted number of people of each core point as the guaranteed base combination of each core point. The minimum weighted number of qualified guaranteed base combination of the core points n satisfies the relation:

inspection assembly

Whether all regions in the set to be allocated

And (available area condition) until satisfied. Mark the bottom-protected combination as

As a guaranteed combination of core points n.

Step S124: and obtaining the attribution combination with the minimum weighted number of the core points in the rest hierarchical regions to be distributed of the sets to be distributed according to the core point grades by applying a core point attribution distribution model.

The core goal of the Kernel Points Supplemental Allocation (KPSA) model is to allocate all the remaining regions to be allocated in the set D to be allocated to all the core Points according to the priority and the number of persons allocated to each level of the core Points, thereby completing the division of the regions to which the core Points belong.

In the embodiment of the invention, the specific flow is as follows: and sequentially extracting the core points from the rest hierarchical regions to be distributed of the sets to be distributed, and constructing all qualified attribution combinations of the core points, so that the sum of the attribution population of each qualified attribution combination is just larger than the requirement of the number of the attributions of the core points at the current level. The set of all qualified attributed combinations for the marked core point n is:

M_nthe number of eligible ascription combinations for core point n,

N_mnare combined as attribution

The number of hierarchical regions included in (a),

are combined as attribution

The ith hierarchical region.

For each of the core points, calculating a weighted number of people for each of the qualified combination of attributions of the core point:

And arranging the core points from high to low according to grades, and sequentially taking the qualified attribution combination with the smallest weighted number of people for each core point as the attribution combination of each core point. The qualified attribution combination with the smallest weighted number of the core points n meets the relation:

inspection of attribution combination

Whether all regions are in the hierarchical region set to be allocated

And (available area condition) until satisfied. Mark this attribution combination as

As a belonging combination for core point n.

Step S125: and merging the bottom-preserving combination and the attribution combination of each core point to form a merged attribution combination of the core points.

Merging attribution combination of core points n

In the embodiment of the present invention, a complete process of performing area division on a core point in a core point database by using an automatic area division model is shown in fig. 6, and includes:

step S200: the hierarchical region center of gravity is calculated.

Specifically, the gravity center of the hierarchical region is calculated according to the gravity centers of the partitions, the core point database and the hierarchical region obtained according to the region attribution crowd.

Step S201: the Cutoff distance vector is calculated.

And calculating the distance between the core point and the hierarchical region according to the division data to generate a Cutoff distance vector.

Step S202: a cartesian distance vector is calculated.

And calculating the Cartesian distance between the core point and the gravity center of the hierarchical region according to the gravity center of the hierarchical region, the core point database and the Cutoff distance vector to form a Cartesian distance vector.

Step S203: path segmentation is performed.

And (3) establishing a shortest path between the gravity center of the hierarchical region and each core point by depending on road network data, and dividing the shortest path into different straight line sections.

Step S204: a weighted manhattan distance vector is calculated.

And calculating weighted Manhattan distance vectors of the core points and all hierarchical regions by depending on path segmentation provided by road network data and considering road weight.

Step S205: a weighted double distance vector is calculated.

For each core point, a weighted double distance vector between the core point and all the hierarchical regions is calculated according to the Cartesian distance vector and the weighted Manhattan distance vector.

Step S206: and generating a bottom-preserving combination set.

Establishing a to-be-distributed set of all to-be-distributed hierarchy regions of a designated hierarchy of a strategy center, extracting core points from the to-be-distributed set according to a weighted double-distance vector sequence, constructing all qualified guaranteed-base combinations of each core point, and generating a guaranteed-base combination set.

Step S207: a weighted number of people is calculated.

The weighted number of each qualified underwriting combination of core points is calculated.

Step S208: a minimum weighted combination is generated.

And arranging the core points from high to low according to the grades, and sequentially taking the qualified guaranteed-base combination with the minimum weighted number of people of each core point to generate the minimum weighted combination.

Step S209: and (4) area attribution.

And when all the hierarchical regions in the minimum weighted combination are in the set to be distributed, taking the minimum weighted combination as a guaranteed combination of the core point, namely, attributing the core point to all the hierarchical regions in the minimum weighted combination.

Step S210: generating a home combination set.

And sequentially extracting core points from the rest hierarchical regions to be distributed of the set to be distributed, constructing all qualified attribution combinations of the core points, and generating an attribution combination set.

Step S211: a weighted number of people is calculated.

For each core point, a weighted number of people for each qualified ascription combination of core points is calculated.

Step S212: a minimum weighted combination is generated.

And arranging the core points from high to low according to the grades, and sequentially taking the qualified attribution combination with the minimum weighted number of people of each core point to generate the minimum weighted combination. And when all the hierarchical regions in the minimum weighted combination are in the hierarchical region set to be distributed, taking the minimum weighted combination as the attribution combination of each core point.

Step S213: and merging the bottom-preserving combination and the attribution combination.

And combining the bottom-preserving combination and the attribution combination of each core point to form a combined attribution combination of the core points, and finishing the regional attribution of the core points.

The embodiment of the invention supports multi-level summarization and diversified partition strategy control, supports a strategy center to control diversified core point hierarchical guaranteed-base attribution allocation strategies, ensures the fairness and controllability of allocation, has high automation degree, is compatible with manual strategy configuration, can be flexibly coupled with a service system, and has high application flexibility.

Step S13: and performing closed-loop verification on the hierarchy attribution model and the area automatic division model according to service system data, and optimizing parameters of the hierarchy attribution model and the area automatic division model.

In the embodiment of the invention, the verified core point attribution data of the user partition attribution and the hierarchy region are extracted from the butt-jointed service system so as to optimize the parameters in the DWDCO model and the GPSA model

The output data of the closed-loop adaptive individual and region allocation method of the embodiment of the invention comprises the subareas of the usersThe home, the home partition of the core point and the home subscriber group of the core point may be interfaced to the service system for use thereof. The service system can verify the data in the service operation and support process, and the verification conclusion is automatically fed back to carry out parameter optimization for further optimizing the hierarchy attribution model and the automatic region division model.

In the embodiment of the invention, because the parameter space to be optimized is huge and cannot be traversed, a Distance-based gradient Descent (DBGD) model is adopted to realize parameter optimization. As shown in fig. 7, the specific process is as follows:

step S131: and respectively acquiring corresponding parameter sequences according to the parameters of the hierarchy attribution model and the automatic region division model.

Specifically, parameter sequences in the two models are reformed to obtain the parameter sequence of the DWDCO model

And parameter sequences of the GPSA model

Step S132: and respectively calculating corresponding deviation functions according to the parameter sequences of the hierarchical attribution model and the automatic region division model.

The deviation function includes a user attribution deviation function corresponding to the hierarchical attribution model and a hierarchical region deviation function corresponding to the region automatic division model. Defining a user attribution bias function as:

wherein, theta is a system function representing DWDCO model,

and N is the distance between the gravity center of the current attribution partition of the ith user and the gravity center of the actual attribution partition, and the number of the total users.

Defining a hierarchical region deviation function as:

wherein xi is a system function representing the GPSA model,

for the jth hierarchical region, the distance between the current home core point and the actual home core point, M is the total number of hierarchical regions of the target hierarchy.

Step S133: and respectively introducing an optimization step length parameter according to the deviation functions to calculate the corresponding deviation gradient functions.

Introducing an optimization step length parameter lambda to a user attribution deviation function₁Introducing an optimization step size parameter lambda to a layer level region deviation function₂. Separately calculating the deviation function J_μ(theta) and G_v(xi) deviating gradient function:

step S134: and calculating a new parameter sequence and a new deviation function according to the deviation gradient function and the optimized parameter step length until the new deviation function meets the convergence condition.

New parameter sequences { mu '} and { ν' } are calculated, respectively. Wherein the content of the first and second substances,

the new parameter sequence calculates a new deviation function J_μ′(theta) and G_ν′(xi). Determining the new deviation function J_μ′(theta) and G_ν′(xi) whether convergence conditions are satisfied: | J_μ′(Θ)-J_μ(Θ)|<ε₁And | G_v′(Ξ)-G_v(Ξ)|<ε₂). If the convergence condition is not satisfied, the new parameter sequence and the new deviation function are repeatedly calculated. And if the convergence condition is met, stopping optimization, wherein the current parameter sequence is the optimized parameter sequence.

The embodiment of the invention realizes verification closed loop by butting the service system, simultaneously automatically optimizes a large number of parameters of the hierarchical attribution model and the automatic region division model, forms an optimized closed loop by verification data collected by the service system, supports self-verification and timely reflects the current situation, and can realize continuous improvement of the model without additional data collection and verification cost.

Step S14: and outputting user partition attribution data and core point attribution data according to the optimized hierarchical attribution model and the parameters of the automatic region division model.

In the embodiment of the present invention, user partition attribution data obtained by applying the optimized hierarchical attribution model to perform hierarchical partition processing on a user and core point attribution data obtained by applying the automatic area division model to perform area division on a core point are output, where the user partition attribution data, the core point attribution partition and the core point attribution data include a user partition attribution, a core point attribution partition and a core point attribution user group.

Fig. 8 is a schematic structural diagram of a closed-loop adaptive individual and regional distribution apparatus according to an embodiment of the present invention. As shown in fig. 8, the closed-loop adaptive individual and regional distribution apparatus includes: a hierarchical partitioning unit 801, an area dividing unit 802, a parameter verification unit 803, and a data output unit 804. Wherein:

the hierarchical partitioning unit 801 is configured to apply a hierarchical attribution model to perform hierarchical partitioning processing on a user according to the instant user distribution data; the region dividing unit 802 is configured to perform region division on the core points in the core point database according to a pre-stored region dividing policy and a user partition attribution data application region automatic dividing model for partition processing; the parameter verification unit 803 is configured to perform closed-loop verification on the hierarchical affiliation model and the area automatic division model according to service system data, and optimize parameters of the hierarchical affiliation model and the area automatic division model; the data output unit 804 is configured to output user partition attribution data and core point attribution data according to the optimized hierarchical attribution model and the parameters of the area automatic division model.

In an alternative approach, the hierarchical partition unit 801 is used to: and attributing all users in the previous level partition to the current level partition according to the user permanent data application level attribution model in the instant user distribution data.

In an alternative approach, the hierarchical partition unit 801 is used to: calculating partition gravity centers according to the user permanent station data in the instant user distribution data and the current level partition list; calculating the Cartesian distance between the user grid and the partition gravity center according to the user permanent station data to form a user Cartesian distance vector; calculating a weighted Manhattan distance vector of the user grid and the partition gravity center according to the user permanent station data and the road network data; calculating a weighted double-distance vector of the user grid and the partition gravity center according to the user Cartesian distance vector and the weighted Manhattan distance vector; and extracting the weighted double-distance vectors of the user grid where the user resides and all the partition barycenters, and taking the partition corresponding to the partition barycenter with the shortest weighted double-distance as the attribution partition of the user.

In an alternative manner, the area dividing unit 802 is configured to: calculating a weighted double-distance vector between the core point and a hierarchical region by applying the hierarchical attribution model according to the core point; establishing a to-be-distributed set of all to-be-distributed hierarchy regions of a designated hierarchy of a strategy center; obtaining a minimum weighted population number of each core point in the set to be distributed according to the core point grade by applying a core point bottom-preserving distribution model; obtaining a attribution combination with the minimum weighted number of each core point in the remaining hierarchical regions to be distributed of the set to be distributed according to the core point grade by applying a core point attribution distribution model; and merging the bottom-preserving combination and the attribution combination of each core point to form a merged attribution combination of the core points.

In an alternative manner, the area dividing unit 802 is configured to: sequentially extracting the core points from the set to be distributed, and constructing all qualified base protection combinations of each core point, so that the sum of the attribution population of each qualified base protection combination is just greater than the requirement of the number of base protection people; calculating, for each of the core points, a weighted number of each of the qualified underwriting combinations of the core points; and arranging the core points from high to low according to grades, and sequentially taking the qualified guaranteed base combination with the smallest weighted number of people of each core point as the guaranteed base combination of each core point.

In an alternative manner, the area dividing unit 802 is configured to: sequentially extracting the core points from the rest hierarchical regions to be distributed of the sets to be distributed, and constructing all qualified attribution combinations of the core points, so that the sum of attribution crowds of each qualified attribution combination is just larger than the requirement of the number of attributions of the core points at the current level; calculating, for each of the core points, a weighted number of people for each of the qualified ascription combinations for the core point; and arranging the core points from high to low according to grades, and sequentially taking the qualified attribution combination with the smallest weighted number of people for each core point as the attribution combination of each core point.

In an alternative manner, the parameter verification unit 803 is configured to: respectively acquiring corresponding parameter sequences according to the parameters of the hierarchy attribution model and the automatic region division model; respectively calculating corresponding deviation functions according to the parameter sequences of the hierarchical attribution model and the automatic region division model; respectively introducing an optimization step length parameter according to the deviation functions to calculate corresponding deviation gradient functions; and calculating a new parameter sequence and a new deviation function according to the deviation gradient function and the optimized parameter step length until the new deviation function meets the convergence condition.

Embodiments of the present invention provide a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction may execute the closed-loop adaptive individual and region allocation method in any of the above method embodiments.

The executable instructions may be specifically configured to cause the processor to:

applying a hierarchical attribution model to perform hierarchical partition processing on the users according to the instant user distribution data;

performing area division on core points in a core point database according to a pre-stored area division strategy and a user partition attribution data application area automatic division model subjected to partition processing;

performing closed-loop verification on the hierarchy attribution model and the area automatic division model according to service system data, and optimizing parameters of the hierarchy attribution model and the area automatic division model;

and outputting user partition attribution data and core point attribution data according to the optimized hierarchical attribution model and the parameters of the automatic region division model.

In an alternative, the executable instructions cause the processor to:

and attributing all users in the previous level partition to the current level partition according to the user permanent data application level attribution model in the instant user distribution data.

In an alternative, the executable instructions cause the processor to:

calculating partition gravity centers according to the user permanent station data in the instant user distribution data and the current level partition list;

calculating the Cartesian distance between the user grid and the partition gravity center according to the user permanent station data to form a user Cartesian distance vector;

calculating a weighted Manhattan distance vector of the user grid and the partition gravity center according to the user permanent station data and the road network data;

calculating a weighted double-distance vector of the user grid and the partition gravity center according to the user Cartesian distance vector and the weighted Manhattan distance vector;

and extracting the weighted double-distance vectors of the user grid where the user resides and all the partition barycenters, and taking the partition corresponding to the partition barycenter with the shortest weighted double-distance as the attribution partition of the user.

In an alternative, the executable instructions cause the processor to:

calculating a weighted double-distance vector between the core point and a hierarchical region by applying the hierarchical attribution model according to the core point;

establishing a to-be-distributed set of all to-be-distributed hierarchy regions of a designated hierarchy of a strategy center;

obtaining a minimum weighted population number of each core point in the set to be distributed according to the core point grade by applying a core point bottom-preserving distribution model;

obtaining a attribution combination with the minimum weighted number of each core point in the remaining hierarchical regions to be distributed of the set to be distributed according to the core point grade by applying a core point attribution distribution model;

and merging the bottom-preserving combination and the attribution combination of each core point to form a merged attribution combination of the core points.

In an alternative, the executable instructions cause the processor to:

sequentially extracting the core points from the set to be distributed, and constructing all qualified base protection combinations of each core point, so that the sum of the attribution population of each qualified base protection combination is just greater than the requirement of the number of base protection people;

calculating, for each of the core points, a weighted number of each of the qualified underwriting combinations of the core points;

and arranging the core points from high to low according to grades, and sequentially taking the qualified guaranteed base combination with the smallest weighted number of people of each core point as the guaranteed base combination of each core point.

In an alternative, the executable instructions cause the processor to:

sequentially extracting the core points from the rest hierarchical regions to be distributed of the sets to be distributed, and constructing all qualified attribution combinations of the core points, so that the sum of attribution crowds of each qualified attribution combination is just larger than the requirement of the number of attributions of the core points at the current level;

calculating, for each of the core points, a weighted number of people for each of the qualified ascription combinations for the core point;

and arranging the core points from high to low according to grades, and sequentially taking the qualified attribution combination with the smallest weighted number of people for each core point as the attribution combination of each core point.

In an alternative, the executable instructions cause the processor to:

respectively acquiring corresponding parameter sequences according to the parameters of the hierarchy attribution model and the automatic region division model;

respectively calculating corresponding deviation functions according to the parameter sequences of the hierarchical attribution model and the automatic region division model;

respectively introducing an optimization step length parameter according to the deviation functions to calculate corresponding deviation gradient functions;

and calculating a new parameter sequence and a new deviation function according to the deviation gradient function and the optimized parameter step length until the new deviation function meets the convergence condition.

Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the closed-loop adaptive individual and region allocation method of any of the above-described method embodiments.

In an alternative, the executable instructions cause the processor to:

Fig. 9 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the device.

As shown in fig. 9, the computing device may include: a processor (processor)902, a communication Interface 904, a memory 906, and a communication bus 908.

Wherein: the processor 902, communication interface 904, and memory 906 communicate with one another via a communication bus 908. A communication interface 904 for communicating with network elements of other devices, such as clients or other servers. The processor 902 is configured to execute a process 910, which may specifically perform the relevant steps in the above-described embodiments of the closed-loop adaptive individual and region allocation method.

In particular, the program 910 may include program code that includes computer operating instructions.

The processor 902 may be a central processing unit CPU or an application Specific Integrated circuit asic or an Integrated circuit or Integrated circuits configured to implement embodiments of the present invention. The one or each processor included in the device may be the same type of processor, such as one or each CPU; or may be different types of processors such as one or each CPU and one or each ASIC.

A memory 906 for storing a program 910. The memory 906 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 910 may specifically be configured to cause the processor 902 to perform the following operations:

In an alternative, the program 910 causes the processor to:

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims

1. A closed-loop adaptive individual and regional allocation method, the method comprising:

2. The method of claim 1, wherein applying a hierarchical attribution model to users according to the instant user profile data comprises:

3. The method of claim 2, wherein applying a hierarchical attribution model to the permanent premises data in the instant subscriber profile to attribution all subscribers in a previous hierarchical partition to a current hierarchical partition comprises:

4. The method according to claim 1, wherein said applying an area automatic segmentation model for segmentation of core points in a core point database according to pre-stored area segmentation policies and sectorized user partition home data comprises:

5. The method of claim 4, wherein said applying the core point warranty distribution model to obtain a minimum weighted population of warranty combinations of each of the core points in the set to be distributed according to the core point level comprises:

6. The method according to claim 5, wherein said applying the core point attribution allocation model to obtain a least weighted attribution combination for each core point in the remaining hierarchical regions to be allocated of the set to be allocated according to the core point level comprises:

7. The method of claim 1, wherein the closed-loop validation of the hierarchical attribution model and the regional automatic division model according to business system data, and the optimization of parameters of the hierarchical attribution model and the regional automatic division model comprises:

8. A closed-loop adaptive individual and regional distribution apparatus, the apparatus comprising:

the hierarchical partition unit is used for applying a hierarchical attribution model to carry out hierarchical partition processing on the users according to the instant user distribution data;

the area division unit is used for carrying out area division on the core points in the core point database according to a pre-stored area division strategy and a user partition attribution data application area automatic division model which is processed in a partition mode;

the parameter verification unit is used for performing closed-loop verification on the hierarchy attribution model and the area automatic division model according to service system data and optimizing parameters of the hierarchy attribution model and the area automatic division model;

and the data output unit is used for outputting user partition attribution data and core point attribution data according to the optimized hierarchical attribution model and the parameters of the automatic region division model.

9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is for storing at least one executable instruction that causes the processor to perform the steps of the closed-loop adaptive individual and zone allocation method of any of claims 1-7.

10. A computer storage medium having stored therein at least one executable instruction that causes a processor to perform the steps of the closed loop adaptive individual and zone allocation method according to any one of claims 1-7.