Service network recommendation method, device and equipment, medium and program product

Abstract

The invention relates to the technical field of financial science and technology, and discloses a service network recommendation method, device and equipment, a medium and a program product. The method comprises the following steps: acquiring a door-to-door service demand of a user, and acquiring a plurality of candidate service websites according to the door-to-door service demand by adopting a hybrid genetic ant colony algorithm; and obtaining a service queue and a path queue corresponding to each candidate service network point, and solving a preset overall utility optimization problem by adopting a dynamic programming algorithm according to the service queue and the path queue corresponding to each candidate service network point to obtain a recommended service network point corresponding to the user. According to the scheme of the embodiment, the service network is preliminarily screened based on the hybrid genetic ant colony algorithm, then the dynamic programming algorithm is adopted to solve the preset overall utility optimization problem, and the service network is screened again, so that the optimal door-to-door service network can be recommended to the user, the customer demand that the service cannot be handled at the network can be met, and the user experience is improved. And long-time queuing and waiting of customers can be effectively avoided.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a method, device, equipment, medium and program product for recommending a service outlet. Background Art

[0002] In recent years, with the rapid development of information technology, the functions of mobile banking have become more and more user-friendly, effectively solving the problem that a large number of customers cannot go to branches to handle business due to lack of time, long distance, etc., and customers' expectations for the quality of business experience are also getting higher and higher.

[0003] At present, when customers need door-to-door service, they usually call customer service or go to a bank branch to explain their request for door-to-door service. However, this method is time-consuming and inefficient, especially for businesses with high timeliness requirements. It can no longer meet the personalized needs of customers with limited mobility who need to handle business at the counter, which greatly reduces customer satisfaction. Summary of the invention

[0004] The present invention provides a service outlet recommendation method, device, equipment, medium and program product, which can recommend the best door-to-door service outlet for users, meet the needs of customers who cannot go to the outlet to handle business, and effectively avoid customers waiting in line for a long time, thereby improving user satisfaction.

[0005] According to one aspect of the present invention, a method for recommending a service point is provided, comprising:

[0006] Obtaining the user's door-to-door service needs, and using a hybrid genetic ant colony algorithm to obtain multiple candidate service outlets according to the door-to-door service needs;

[0007] The service queue and path queue corresponding to each of the candidate service outlets are obtained, and a dynamic programming algorithm is used to solve a preset overall utility optimization problem according to the service queue and path queue corresponding to each of the candidate service outlets to obtain a recommended service outlet corresponding to the user.

[0008] According to another aspect of the present invention, there is provided a device for recommending a service point, comprising:

[0009] A candidate service outlet acquisition module is used to acquire the user's door-to-door service needs and adopt a hybrid genetic ant colony algorithm to acquire multiple candidate service outlets according to the door-to-door service needs;

[0010] The optimization problem solving module is used to obtain the business queue and path queue corresponding to each of the candidate service outlets, and adopt a dynamic programming algorithm to solve the preset overall utility optimization problem according to the business queue and path queue corresponding to each of the candidate service outlets to obtain the recommended service outlets corresponding to the user.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the service point recommendation method described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program is used to enable a processor to implement the service point recommendation method described in any embodiment of the present invention when executed.

[0016] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method for recommending a service point according to any embodiment of the present invention is implemented.

[0017] The technical solution of the embodiment of the present invention obtains the door-to-door service demand of the user, and adopts a hybrid genetic ant colony algorithm to obtain multiple candidate service outlets according to the door-to-door service demand; obtains the business queue and path queue corresponding to each candidate service outlet, and adopts a dynamic programming algorithm to solve the preset overall utility optimization problem according to the business queue and path queue corresponding to each candidate service outlet, and obtains the recommended service outlet corresponding to the user; by first performing a preliminary screening of the service outlets based on the hybrid genetic ant colony algorithm, and then adopting a dynamic programming algorithm to solve the preset overall utility optimization problem, and then screening the service outlets again, the optimal door-to-door service outlet can be recommended to the user, which can meet the needs of customers who cannot go to the outlets to handle business, and effectively avoid customers waiting in line for a long time, which can improve user satisfaction.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a flow chart of a method for recommending service outlets provided according to Embodiment 1 of the present invention;

[0021] Figure 2 is a flow chart of another method for recommending service outlets provided according to the first embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of changes in information age values ​​provided according to the first embodiment of the present invention;

[0023] Figure 4 is a flow chart of door-to-door service processing provided according to the first embodiment of the present invention;

[0024] Figure 5 is a flow chart for solving a preset overall utility optimization problem provided according to the first embodiment of the present invention;

[0025] Figure 6 is a schematic diagram of the structure of a service point recommendation device provided according to Embodiment 2 of the present invention;

[0026] Figure 7 It is a structural schematic diagram of an electronic device for implementing the service outlet recommendation method of an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 A flowchart of a method for recommending a service outlet is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the optimal door-to-door service outlet is recommended when a user has a door-to-door service request. The method can be executed by a recommendation device of a service outlet. The recommendation device of the service outlet can be implemented in the form of hardware and / or software. Typically, the recommendation device of the service outlet can be configured in an electronic device, such as a computer device or a server. Figure 1 As shown, the method includes:

[0031] S110, obtaining the user's door-to-door service demand, and using a hybrid genetic ant colony algorithm to obtain a plurality of candidate service outlets according to the door-to-door service demand.

[0032] In this embodiment, the user can log in to the mobile banking client to enter the door-to-door service demand page, and fill in the name, contact information, brief description of the business to be handled and the address, etc., to generate the door-to-door service demand. After obtaining the door-to-door service demand, the strong global search capability of the genetic algorithm and the positive feedback characteristics of the ant colony algorithm can be used to process the door-to-door service demand, and the corresponding data can be quickly and accurately searched. Each piece of data will have a corresponding pheromone concentration. As the number of iterations increases, the pheromone concentration of the optimal data will be greater. The optimal path is selected according to the descending order of the corresponding concentration of the data, and the initial service outlet corresponding to the selected optimal path is used as a candidate service outlet that is closer to the user.

[0033] Specifically, first, the address information filled in by the user is initialized with a genetic algorithm with strong global search capabilities, and it is used as the initial pheromone construction solution space of the ant colony algorithm, and the service outlet information is updated regularly; secondly, according to the positive feedback characteristics of the ant colony algorithm, the pheromone concentration on the optimal path is increased to quickly find the service outlet with the lowest user cost; finally, through multiple iterations, the distribution diversity of the outlet path is increased, and genetic operations are introduced to avoid the path selection problem from falling into the local optimum. Finally, based on the minimum total cost, a better outlet path can be recommended to the user, and the initial service outlet corresponding to the better outlet path can be used as a candidate service outlet.

[0034] It should be noted that the information collected in this embodiment is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0035] S120, obtaining the service queue and path queue corresponding to each of the candidate service outlets, and using a dynamic programming algorithm to solve a preset overall utility optimization problem according to the service queue and path queue corresponding to each of the candidate service outlets, to obtain a recommended service outlet corresponding to the user.

[0036] Specifically, when determining the candidate service outlet, the optimal path between it and the user address is determined at the same time. The number of optimal paths can be one or more, thereby obtaining the path queue corresponding to each candidate service outlet. Secondly, in this embodiment, in order to shorten the response time of the user's time-sensitive services, the customer service can be converted into a virtual task queue Q by optimizing the data information life cycle of the service. i (t), where t∈{1,2,…,T} represents time and i∈{1,2,…,N} represents the user set.

[0037] For example, the door-to-door service requirements filled in by customers can be converted into data tasks in the virtual queue and stored in the form of a single data packet queue. Old data from the same user will be discarded from the service queue. The data packet at time t is the freshest data in each service queue, that is, the user service with the shortest data information life cycle. i (t)∈{0,1} represents the indicator function of the user's service handling progress, X i (t) = 1 means that the service outlet can handle the business and store the corresponding business. The outlet customer service manager goes to the customer's location to handle the business through the optimal path. Otherwise, X i (t) = 0. The number and location of service outlets are fixed and known, and m∈{1,2,…,M} represents the number of outlets and j∈{1,2,…,J} represents the location of the outlets.

[0038] It is understandable that for a service that is sensitive to the life cycle of data information, it is often necessary to pay attention to the "freshness" of the data in the service queue. This embodiment assumes that the service outlet maintains a single data packet service queue and always keeps the data in the queue up to date. If the life cycle of the data information in the queue is too long, it may cause time-sensitive tasks to make wrong decisions, which may cause certain losses to users. Therefore, it is very necessary to introduce the problem of minimizing the long-term average information age in the outlet selection to optimize the data information life cycle of the task in the queue model to measure the length of time the user handles the business at the corresponding outlet.

[0039] In a specific example, the preset overall utility optimization problem can be an average information age minimization optimization problem. For users who have urgent business needs, the concept of minimizing the information age is proposed, and the business handled by each candidate service outlet within a period of time is converted into a virtual business queue. In each business queue, the tasks are sorted according to priority (according to the demand classification filled in by the user) according to the multi-level feedback queue scheduling algorithm, and the life cycle of each task is calculated, and the service outlet with the smallest value is arranged first. In this embodiment, the path queue can be used as a constraint condition, and a dynamic programming algorithm can be used to solve the average information age minimization optimization problem according to the business queue corresponding to each candidate service outlet, so as to obtain the candidate service outlet with the smallest corresponding average information age as the recommended service outlet corresponding to the user.

[0040] Assume that users upload door-to-door service needs through mobile banking clients at times t1 and t2, and are received by the best outlets at times t1' and t2'. At any time during the working day, there will be users going to service outlets to handle business or users who have been called but have not handled business and leave the outlets, making the number of services handled by service outlets unstable. Let D i (t) indicates the calling data of the user handling the business, d i (t) indicates that the user cancels the calling data, γ i (t) = D i (t) / A i (t) represents the success rate of business handling, A i (t) represents the total amount of services in this period. When the user service queue is too long or no services are being processed, the services at the end of the queue will be discarded and the newly generated services will be stored at the end of the queue. Then the next time slot Q i The queue backlog at (t+1) is Q i (t+1)=max{Q i (t)-D i (t)-d i (t)+A i (t)+t k ,0}.

[0041] Information age is a user-centric parameter that measures the freshness of information on business processing progress. i (t) represents the queue backlog Q of the user traffic at the network point i The information age value of (t+1), without loss of generality, assumes that a i (0) = 1, the mathematical formula is a i (t) is defined as tU i (t),U i (t) indicates the timestamp of the latest data update received by the outlet from the customer, a iThe smaller (t) is, the fresher the data is.

[0042] In a specific implementation of this embodiment, the process of the service point recommendation method can be as follows: Figure 2 As shown. Among them, the user logs in to the door-to-door service demand page by logging into the mobile banking client and fills in the door-to-door service demand data. The server optimizes the distance and the number of services handled by the branch according to the information age minimization optimization method, and recommends the service branch with the least number of services currently handled as the recommended service branch on the basis of meeting the distance minimization. By adopting the service branch recommendation method based on information age minimization based on the comprehensive judgment of the distance to the store and the current number of services handled by the branch, it can greatly facilitate the personalized needs of customers, thereby improving user satisfaction and increasing customer stickiness to a certain extent.

[0043] Optionally, after determining the recommended service point, the recommended service point can be pushed to the client page for user confirmation. If a user confirmation instruction is detected, the door-to-door service demand can be sent to the recommended service point so that the point can dispatch staff to provide door-to-door service.

[0044] The technical solution of the embodiment of the present invention obtains the door-to-door service demand of the user, and adopts a hybrid genetic ant colony algorithm to obtain multiple candidate service outlets according to the door-to-door service demand; obtains the business queue and path queue corresponding to each candidate service outlet, and adopts a dynamic programming algorithm to solve the preset overall utility optimization problem according to the business queue and path queue corresponding to each candidate service outlet, and obtains the recommended service outlet corresponding to the user; by first performing a preliminary screening of the service outlets based on the hybrid genetic ant colony algorithm, and then adopting a dynamic programming algorithm to solve the preset overall utility optimization problem, and then screening the service outlets again, the optimal door-to-door service outlet can be recommended to the user, which can meet the needs of customers who cannot go to the outlets to handle business, and effectively avoid customers waiting in line for a long time, which can improve user satisfaction.

[0045] In an optional implementation of this embodiment, a hybrid genetic ant colony algorithm is used to obtain multiple candidate service outlets according to the door-to-door service demand, which may include:

[0046] According to the door-to-door service demand, the user address is obtained, and the user address is encoded to obtain the chromosome code corresponding to the user;

[0047] Using a genetic algorithm, according to the chromosome code corresponding to the user, a plurality of initial network point paths between the user address and each initial service network point are obtained;

[0048] Based on a preset pheromone update function and a preset fitness function, multiple target network point paths are screened from multiple initial network point paths, and multiple candidate service network points are obtained according to the multiple target network point paths.

[0049] In this embodiment, in order to index users and service outlets, each user address and outlet location can be uniquely encoded to obtain the chromosome code corresponding to the user. The user address (user demand queue) is counted as the chromosome length, the user address corresponds to the element, and the number assigned to the corresponding service outlet corresponds to the element value. For example, the function G can be used i ={g1,g2,…,g N} represents the chromosome number, g i represents the result of allocating user demand to the corresponding service outlets, and g i ∈[1,M],i∈[1,N].

[0050] Secondly, a genetic algorithm can be used to perform a global search based on the chromosome code corresponding to each user, and the optimal path from the user address to the network point can be modeled to obtain multiple initial network point paths between the user address and each initial service network point. Then, an ant colony algorithm can be used to update the pheromone concentration of each initial network point path based on the preset pheromone update function, and a genetic algorithm can be used to iteratively calculate the fitness function value of each initial network point path based on the preset fitness function, and the target network point path can be screened based on the fitness function value. Finally, the service network point connected to the target network point path can be determined as a candidate service network point.

[0051] In this embodiment, by combining the genetic algorithm and the ant colony algorithm, it is possible to quickly and accurately search for the service outlet with the shortest distance, and the search efficiency of the candidate service outlets can be improved.

[0052] Optionally, based on a preset pheromone update function and a preset fitness function, screening multiple target network point paths from multiple initial network point paths may include:

[0053] Based on the preset pheromone update function, the pheromone concentration of each initial network point path is updated to obtain the target pheromone concentration corresponding to each initial network point path; based on the preset fitness function, according to the target pheromone concentration corresponding to each initial network point path, the fitness function value corresponding to each initial network point path is calculated; according to the fitness function value corresponding to each initial network point path, multiple target network point paths are screened from multiple initial network point paths.

[0054] The preset pheromone update function may be based on an ant-cycle model. For example, the formula of the preset pheromone update function may be:

[0055]

[0056] Among them, the increment of the pheromone concentration of the customer on the path kj is marked as The pheromone concentration increased by the path successfully is q i (t), is a constant with a value of [10, 10000], L i The total length of the network path selected for the customer. In order to speed up the convergence and minimize the user cost, the pheromone concentration should be larger.

[0057] Secondly, through the fitness function value, consider whether the user's needs are to handle the business through the optimal path from his address to the outlet. When iteratively updating the fitness function value, the decision value of the path selection problem is converted into a normalized parameter value. The larger the value, the lower the user's cost. Finally, the fitness function value is used to select the approximate optimal outlet path and recommend it to the user. The definition of the preset fitness function can be:

[0058]

[0059] Among them, F(X) represents the optimization target of the function, Maxlter represents the maximum iteration value, and lter represents the current iteration value. The optimization objective function is nonlinear to update the fitness of each user in real time. Typically, considering the cost of each user, the value of Maxlter can be set to 200.

[0060] Specifically, the pheromone concentration of each initial point path can be iteratively updated based on a preset pheromone update function to obtain the final pheromone concentration corresponding to each initial point path. Then, the pheromone concentration can be used as the initial fitness function value, and based on the preset fitness function, the fitness function value of each initial point path can be iteratively updated according to the initial fitness function value to obtain the final fitness function value corresponding to each initial point path. Finally, the corresponding initial point paths can be screened in descending order of fitness function values ​​to be used as target point paths.

[0061] In this embodiment, the accuracy of obtaining the optimal network point path can be improved by combining the pheromone concentration and the fitness function value to screen the optimal network point path.

[0062] Optionally, when determining the target outlet path, the selection, crossover and mutation operations of the genetic algorithm can also be used. Among them, the selection algorithm evaluates the fitness function value of each user, takes the inverse of the length of the path selected by the user, and performs roulette selection; the crossover operation, in order to prevent problems such as slow processing progress caused by a large number of outlet-to-store users, the algorithm constrains the user to visit 3 service outlets each time in the process of selecting the optimal path through partial matching crossover functions; the mutation operation, when the optimized outlet path falls into a local optimum, the algorithm is used to ensure the diversity of the path distribution while preventing the optimal path from converging prematurely.

[0063] In another optional implementation of this embodiment, before using a dynamic programming algorithm to solve a preset overall utility optimization problem according to the service queues and path queues corresponding to each of the candidate service outlets to obtain a recommended service outlet corresponding to the user, the following may also be included:

[0064] Obtaining an initial average information age function, and updating the initial average information age function using a state update zero-wait strategy to obtain a target average information age function;

[0065] By comprehensively considering the business processing time and the time spent on door-to-door visits, a preset overall utility optimization problem is generated according to the target average information age function.

[0066] In this embodiment, in order to improve user experience and ensure that user services can be handled in the shortest distance and fastest time, the door-to-door service processing flow can be as follows: Figure 4 As shown. The user fills in the door-to-door service demand in the mobile banking client, which is transmitted to the bank system wirelessly and pushed to the corresponding branch through path optimization. The branch staff will give feedback after receiving the information. The traditional time cost is only the time required to process the business, but some users' businesses are subject to time limits. If the business is not completed before the deadline, it will cause losses to the user. This embodiment introduces the concept of minimizing the age of information to measure the freshness of the available status information of the branch, and introduces a dynamic programming function and a zero-wait strategy for status updates, which can achieve efficient recommendation of the optimal service branch and timely processing of time-sensitive businesses.

[0067] Among them, the change of the information age value of the branch user's business handling can be as follows Figure 3 As shown, in the interval [0, T), when T→∞, let the service queue status update of the network point generate a steady-state rate, and the resulting status update interval delay is expressed as Y k =t k -t k-1 , the mathematical expression of information age is And the average information age of the service queue (initial average information age function) of the number of users at the duration [0, T] is expressed as:

[0068]

[0069] Among them, T k =t k '-t k , E[·] represents the expected operator. To ensure that each outlet completes the user business processing within the working deadline, γ t =1 / E[Y],ρ s ∈(0,1), R i (t) represents the channel transmission rate, P i tra (t) represents the service transmission rate, which is related to the length of the network path. If it is not met, it will lead to the accumulation of services, the age of information will increase, and the data information life cycle of user services will increase.

[0070] If the service queue of a branch is too long, it will affect the efficiency of door-to-door service for customers. At this time, other branches need to be selected for processing. Therefore, for a fixed P i tra (t), a zero-wait strategy for state updates is proposed to determine the sequence of state updates and optimize ρ s Minimize the average information age of the queue data. k The order of the customer who needs door-to-door service is the shortest distance from the outlet. The information age of the data in the business queue increases linearly with time. The data life cycle optimization problem of the customer's business processing time at any time is modeled as the information age minimization problem. The function is expressed as:

[0071]

[0072] In order to obtain the latest status update information of the number of branch services, this embodiment uses the average information age as the objective function for optimization and solution. The solved information age value is used to represent the freshness of the branch service data information. The smaller the value, the "newer" the data. For the zero-wait strategy for status update, assuming that the time for information status update is negligible and the status update can always be successfully transmitted, the customer's service queue is t k Update the queue status at all times. If E i upd (t k )≥1, then execute the task, otherwise wait for the next update time, which recursively defines the state update time t k It can be expressed as:

[0073]

[0074] in, is a positive number, b i (t-1) represents the business quantity threshold within a certain period of time. If E i upd (t k )≥1, the data in the service queue is k Execute and update the status.

[0075] Under any feasible state update zero-wait strategy, the initial average information age function can be optimized to the target average information age function, that is:

[0076]

[0077] It should be noted that customer cost is an important indicator to measure the quality of customer service in branch-based business. Therefore, a branch selection model of a data state update device with path constraints is modeled. By optimizing each customer branch selection decision X, an overall utility optimization problem P1 that minimizes the function θ(X) is constructed, which can be described as:

[0078]

[0079] Among them, T total It includes the time staff spend on the road when providing door-to-door services, as well as the time spent on business handling. The time spent on business handling includes the time waiting for other business handling and the time spent on this business handling. The average information age can represent the time spent on business handling. The older the average information age, the longer the business handling time. The overall utility optimization problem can be understood as the optimization goal of minimizing the queue backlog of each service outlet and minimizing the total time spent on all business handling.

[0080] The advantage of the above setting is that it can further improve the accuracy of recommending the best door-to-door service outlets, effectively avoid business backlogs, and improve user experience.

[0081] Optionally, by comprehensively considering the business handling time and the door-to-door time, generating a preset overall utility optimization problem according to the target average information age function may include:

[0082] By comprehensively considering the business handling time and the door-to-door time, an initial overall utility optimization problem is generated according to the target average information age function;

[0083] A preset overall utility optimization problem is generated according to the initial overall utility optimization problem and the preset penalty value.

[0084] In this embodiment, a preset penalty value can be added to the initial overall utility optimization problem to generate the final preset overall utility optimization problem. For example, θ(X) = θ(X) + σ, where σ represents the preset penalty value, typically σ = 10 9 .

[0085] The advantage of the above settings is that it can improve the stability of the model and prevent the performance of branch selection from being affected by the long life cycle of customer data information.

[0086] Optionally, a dynamic programming algorithm is used to solve a preset overall utility optimization problem according to the service queues and path queues corresponding to the candidate service outlets to obtain the recommended service outlets corresponding to the user, which may include:

[0087] A dynamic programming algorithm is used to solve a preset overall utility optimization problem according to the service queues and path queues corresponding to each of the candidate service outlets to obtain target transmission parameters;

[0088] The service transmission rate is calculated according to the target transmission parameter and the preset channel transmission rate, and the recommended service network point corresponding to the user is obtained according to the service transmission rate.

[0089] In this embodiment, in order to recommend the service outlets with the shortest distance and the smallest number of customers to customers and improve customer demand efficiency, a two-dimensional outlet decision can be constructed using a dynamic programming function, and the tuple<S,Y,A> Definition, represents the network path, business quantity and average information age respectively. Among them, S represents the path queue, that is, S = {s1, s2, ..., s N}, Y represents the customer service status update set, that is, A represents the average information age of branch business handling, that is Solving the preset overall utility optimization problem based on the dynamic programming function can be expressed as:

[0090]

[0091] In this embodiment, a dynamic programming algorithm can be used to solve the preset overall utility optimization problem according to the service queues and path queues corresponding to each candidate service point to obtain the target transmission parameter ρ S , and can be based on the formula According to the target transmission parameter ρ S and the preset channel transmission rate R i (t), calculate the service transmission rate P i tra (t); Then, a target network point path matching the current service transmission rate can be found, and the candidate service network point corresponding to the target network point path can be determined as a recommended service network point.

[0092] The advantage of the above setting is that it can improve the efficiency of solving the overall utility optimization problem and improve the efficiency of recommending the optimal service outlets.

[0093] In a specific implementation of this embodiment, the solution process of the preset overall utility optimization problem can be as follows: Figure 5 As shown in the figure, the input is the path queue and the service queue, and the output is the optimal network point decision set. Based on the optimal network point decision set, the recommended service network point corresponding to each user address can be determined, that is, the optimal door-to-door service network point.

[0094] Embodiment 2

[0095] Figure 6 This is a schematic diagram of the structure of a service point recommendation device provided by Embodiment 2 of the present invention. Figure 6 As shown, the device includes: a candidate service point acquisition module 210 and an optimization problem solving module 220; wherein,

[0096] The candidate service outlet acquisition module 210 is used to acquire the user's door-to-door service demand and adopt a hybrid genetic ant colony algorithm to acquire multiple candidate service outlets according to the door-to-door service demand;

[0097] The optimization problem solving module 220 is used to obtain the business queue and path queue corresponding to each of the candidate service outlets, and adopt a dynamic programming algorithm to solve the preset overall utility optimization problem according to the business queue and path queue corresponding to each of the candidate service outlets to obtain the recommended service outlet corresponding to the user.

[0098] The technical solution of the embodiment of the present invention obtains the door-to-door service demand of the user, and adopts a hybrid genetic ant colony algorithm to obtain multiple candidate service outlets according to the door-to-door service demand; obtains the business queue and path queue corresponding to each candidate service outlet, and adopts a dynamic programming algorithm to solve the preset overall utility optimization problem according to the business queue and path queue corresponding to each candidate service outlet, and obtains the recommended service outlet corresponding to the user; by first performing a preliminary screening of the service outlets based on the hybrid genetic ant colony algorithm, and then adopting a dynamic programming algorithm to solve the preset overall utility optimization problem, and then screening the service outlets again, the optimal door-to-door service outlet can be recommended to the user, which can meet the needs of customers who cannot go to the outlets to handle business, and effectively avoid customers waiting in line for a long time, which can improve user satisfaction.

[0099] Optionally, the candidate service outlet acquisition module 210 is specifically used to acquire the user address according to the door-to-door service demand, and encode the user address to acquire the chromosome code corresponding to the user;

[0100] Using a genetic algorithm, according to the chromosome code corresponding to the user, a plurality of initial network point paths between the user address and each initial service network point are obtained;

[0101] Based on a preset pheromone update function and a preset fitness function, multiple target network point paths are screened from multiple initial network point paths, and multiple candidate service network points are obtained according to the multiple target network point paths.

[0102] Optionally, the candidate service point acquisition module 210 is specifically configured to update the pheromone concentration of each initial point path based on a preset pheromone update function, and obtain the target pheromone concentration corresponding to each initial point path;

[0103] Based on a preset fitness function, and according to the target pheromone concentration corresponding to each of the initial network point paths, the fitness function value corresponding to each of the initial network point paths is calculated;

[0104] According to the fitness function value corresponding to each of the initial network point paths, a plurality of target network point paths are screened out from the plurality of initial network point paths.

[0105] Optionally, the recommended device for the service outlet also includes:

[0106] A function acquisition module is used to acquire an initial average information age function, and to update the initial average information age function using a state update zero-wait strategy to acquire a target average information age function;

[0107] The problem generating module is used to generate a preset overall utility optimization problem according to the target average information age function by comprehensively considering the business handling time and the door-to-door time.

[0108] Optionally, a problem generation module is specifically used to generate an initial overall utility optimization problem according to the target average information age function by comprehensively considering the business processing time and the door-to-door time;

[0109] A preset overall utility optimization problem is generated according to the initial overall utility optimization problem and the preset penalty value.

[0110] Optionally, the optimization problem solving module 220 is specifically configured to use a dynamic programming algorithm to solve a preset overall utility optimization problem according to the service queues and path queues corresponding to each of the candidate service outlets to obtain target transmission parameters;

[0111] The service transmission rate is calculated according to the target transmission parameter and the preset channel transmission rate, and the recommended service network point corresponding to the user is obtained according to the service transmission rate.

[0112] The service outlet recommendation device provided in the embodiment of the present invention can execute the service outlet recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0113] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0114] Embodiment 3

[0115] Figure 7 A schematic diagram of the structure of an electronic device 30 that can be used to implement an embodiment of the present invention is shown. The electronic device 30 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 30 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0116] like Figure 7 As shown, the electronic device 30 includes at least one processor 31, and a memory connected to the at least one processor 31, such as a read-only memory (ROM) 32, a random access memory (RAM) 33, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 31 can perform various appropriate actions and processes according to the computer program stored in the read-only memory 32 or the computer program loaded from the storage unit 38 to the random access memory 33. In the RAM 33, various programs and data required for the operation of the electronic device 30 can also be stored. The processor 31, the ROM 32 and the RAM 33 are connected to each other through a bus 34. The input / output (I / O) interface 35 is also connected to the bus 34.

[0117] A number of components in the electronic device 30 are connected to the I / O interface 35, including: an input unit 36, such as a keyboard, a mouse, etc.; an output unit 37, such as various types of displays, speakers, etc.; a storage unit 38, such as a disk, an optical disk, etc.; and a communication unit 39, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 31 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 31 include, but are not limited to, a central processing unit, a graphics processing unit, various special artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any appropriate processors, controllers, microcontrollers, etc. The processor 31 executes the various methods and processes described above, such as the recommendation method of the service outlet.

[0119] In some embodiments, the recommendation method of the service outlet can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 38. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 30 via the ROM 32 and / or the communication unit 39. When the computer program is loaded into the RAM 33 and executed by the processor 31, one or more steps of the recommendation method of the service outlet described above can be performed. Alternatively, in other embodiments, the processor 31 can be configured to execute the recommendation method of the service outlet in any other appropriate manner (for example, by means of firmware).

[0120] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays, application specific integrated circuits, application specific standard products, systems on a chip, load programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0122] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 30 having: a display device (e.g., a cathode ray tube or a liquid crystal display) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device 30. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area networks, wide area networks, blockchain networks, and the Internet.

[0125] A computing system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server.

[0126] This embodiment may also include a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for recommending service outlets provided by any embodiment of the present invention is implemented.

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution 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 recommending a service outlet, characterized in that: include: Obtaining the user's door-to-door service needs, and using a hybrid genetic ant colony algorithm to obtain multiple candidate service outlets according to the door-to-door service needs; The service queue and path queue corresponding to each of the candidate service outlets are obtained, and a dynamic programming algorithm is used to solve a preset overall utility optimization problem according to the service queue and path queue corresponding to each of the candidate service outlets to obtain a recommended service outlet corresponding to the user.

2. The method according to claim 1, characterized in that: A hybrid genetic ant colony algorithm is used to obtain multiple candidate service outlets according to the door-to-door service demand, including: According to the door-to-door service demand, the user address is obtained, and the user address is encoded to obtain the chromosome code corresponding to the user; Using a genetic algorithm, according to the chromosome code corresponding to the user, a plurality of initial network point paths between the user address and each initial service network point are obtained; Based on a preset pheromone update function and a preset fitness function, multiple target network point paths are screened from multiple initial network point paths, and multiple candidate service network points are obtained according to the multiple target network point paths.

3. The method according to claim 2, characterized in that Based on the preset pheromone update function and the preset fitness function, multiple target network point paths are screened from multiple initial network point paths, including: Based on a preset pheromone update function, the pheromone concentration of each initial network point path is updated to obtain the target pheromone concentration corresponding to each initial network point path; Based on a preset fitness function, and according to the target pheromone concentration corresponding to each of the initial network point paths, the fitness function value corresponding to each of the initial network point paths is calculated; According to the fitness function value corresponding to each of the initial network point paths, a plurality of target network point paths are screened out from the plurality of initial network point paths.

4. The method according to claim 1, characterized in that: Before using a dynamic programming algorithm to solve a preset overall utility optimization problem according to the service queues and path queues corresponding to the candidate service outlets to obtain the recommended service outlets corresponding to the user, the method further includes: Obtaining an initial average information age function, and updating the initial average information age function using a state update zero-wait strategy to obtain a target average information age function; By comprehensively considering the business processing time and the time spent on door-to-door visits, a preset overall utility optimization problem is generated according to the target average information age function.

5. The method according to claim 4, characterized in that By comprehensively considering the business handling time and the time spent on door-to-door visits, a preset overall utility optimization problem is generated according to the target average information age function, including: By comprehensively considering the business handling time and the door-to-door time, an initial overall utility optimization problem is generated according to the target average information age function; A preset overall utility optimization problem is generated according to the initial overall utility optimization problem and the preset penalty value.

6. The method according to claim 1, characterized in that A dynamic programming algorithm is used to solve the preset overall utility optimization problem according to the business queues and path queues corresponding to each of the candidate service outlets, and the recommended service outlets corresponding to the user are obtained, including: A dynamic programming algorithm is used to solve a preset overall utility optimization problem according to the service queues and path queues corresponding to each of the candidate service outlets to obtain target transmission parameters; The service transmission rate is calculated according to the target transmission parameter and the preset channel transmission rate, and the recommended service network point corresponding to the user is obtained according to the service transmission rate.

7. A service point recommendation device, characterized in that: include: A candidate service outlet acquisition module is used to acquire the user's door-to-door service needs and adopt a hybrid genetic ant colony algorithm to acquire multiple candidate service outlets according to the door-to-door service needs; The optimization problem solving module is used to obtain the business queue and path queue corresponding to each of the candidate service outlets, and adopt a dynamic programming algorithm to solve the preset overall utility optimization problem according to the business queue and path queue corresponding to each of the candidate service outlets to obtain the recommended service outlets corresponding to the user.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor, and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the service outlet recommendation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the service outlet recommendation method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the service outlet recommendation method according to any one of claims 1 to 6.

Images