Brand resource scheduling method and device, computer equipment and storage medium

Abstract

The invention relates to a brand resource scheduling method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining the introduction demand information of a brand of an abnormal bunk in a plurality of business states in a target region range, the demand information is used for indicating the brand introduction task of the abnormal berth in the first period and the second period and the successful completion degree of the berth after brand introduction; an objective function and constraint conditions are constructed according to the demand information, and the constraint conditions are used for performing condition limitation on variables in the objective function; generating a target model according to the target function and the constraint condition; and processing the target model by using a target solution algorithm to obtain a target brand resource to be scheduled, the target brand resource being a brand resource which needs to be scheduled at present for each abnormal bunk corresponding to each business state in the target area range. According to the method and the device, the purpose of dynamically adjusting the abnormal bunk in each business state in the target area and finally obtaining the target brand resource with relatively high recommendation matching degree is achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, apparatus, computer equipment and storage medium for brand resource scheduling. Background Art

[0002] Each brand currently located in the shopping center has been pre-screened by the brand introduction staff to meet the segment planning, match the shopping center level, and meet the rental standards. After telephone contact, communication and negotiation, and repeated confirmation with the brand, the contract is finally signed. Normally, a standard shopping center of 100,000 cubic meters is calculated based on the number of 200 main shops. If each shop needs to reserve 2 brands, at least 400 brands must be reserved. This places very high demands on the brand reserve and sensitivity of the brand introduction staff. In such a complex environment, brand iterations are changing with each passing day. How to keenly perceive brands with labels such as hot, emerging, and popular, and reduce the proportion of abnormal shops in the shopping center, is the key to the good ecological operation of the shopping center.

[0003] At present, when reducing the proportion of abnormal shops in shopping malls, brand merchants are usually introduced to each shop in the shopping mall artificially based on the brand introduction staff's own brand knowledge reserves, brand sensitivity and grasp of brand trends. However, this method relies too much on the ability of the brand introduction staff themselves. Different personal abilities lead to uneven brand levels, and there are too many unstable factors, resulting in a low success rate of brand introduction and a high time cost of brand introduction.

[0004] Therefore, there is an urgent need for a unified brand planning mechanism to solve the problems of low brand introduction success rate and high brand introduction time cost caused by artificial selection of store locations in related technologies. Summary of the invention

[0005] In view of this, the present disclosure provides a method, apparatus, computer device and storage medium for brand resource scheduling to solve the problem of low brand introduction success rate and high brand introduction time cost caused by manual selection of store locations.

[0006] In a first aspect, the present disclosure provides a method for brand resource scheduling, the method comprising:

[0007] Obtain demand information for brand introduction to abnormal shops in multiple business formats within the target area, wherein the abnormal shops are shops that have not been successfully located, and the demand information is used to indicate the brand introduction tasks of the abnormal shops in the first period and the second period and the degree of successful completion of the location after the brand introduction;

[0008] Construct an objective function and constraints based on the demand information, where the constraints are used to conditionally limit the variables in the objective function;

[0009] Generate a target model based on the objective function and constraints;

[0010] The target model is processed using the target solution algorithm to obtain the target brand resources to be scheduled, where the target brand resources are the brand resources that need to be scheduled for each abnormal shop corresponding to each business format within the target area.

[0011] In the disclosed embodiment, the brand introduction demand information of abnormal shops under multiple business formats within the target area is obtained to construct the objective function and constraints, and then the target model generated based on the objective function and constraints is solved. In this way, the brand introduction demand information taking the abnormal shops into consideration can be obtained, and then the abnormal shops under various business formats in the target area can be dynamically adjusted according to the attributes of the abnormal shops and the brand attributes, so as to finally obtain the purpose of recommending target brand resources with a higher matching degree, avoid the problems of incomplete brand resource reserves and brand mismatch of brand introduction personnel, improve the success rate of brand introduction, and shorten the time cost of brand introduction.

[0012] In an optional implementation, constructing an objective function and constraint conditions according to demand information includes:

[0013] Obtain target scheduling strategy for scheduling brand resources based on demand information;

[0014] According to the evaluation index of the target scheduling strategy, the nonlinear programming problem is abstracted to generate the objective function and constraint conditions, where the evaluation index is used to characterize the ultimate purpose of the objective function.

[0015] In the disclosed embodiment, the objective function and constraints are generated through the target scheduling strategy, and the brand introduction status of each square is judged and corresponding brand recommendations are made at a fixed period. This can not only ensure that the task completion status of the square is grasped in a timely manner, but also recommend a new round of brands to solve the problem of rapid brand updates and iterations.

[0016] In an optional implementation, generating an objective function and constraints includes:

[0017] Obtain the number of brand dispatches obtained from multiple brand subordinate libraries in each business format, the dispatch priority corresponding to each business format, the expected gap corresponding to each business format, the first penalty weight coefficient, the second penalty weight coefficient, the number of brands that have not been placed in each business format, the number of brand dispatch targets in each business format, the number of abnormal stores in each business format, the completion rate of placement after the introduction of brands, the resource utilization rate of target brand resources, the upper limit of the number of brand dispatches in each business format, and the total dispatch upper limit of each business format within the target area;

[0018] According to the brand dispatch quantity, dispatch priority, expected gap, first penalty weight coefficient and second penalty weight coefficient, the objective function is obtained;

[0019] Constraints are obtained based on the brand scheduling quantity, expected gap, brand quantity, brand scheduling target quantity, abnormal store quantity, location completion rate, resource utilization rate, upper limit of brand scheduling quantity and total scheduling upper limit of each business format within the target area.

[0020] In the disclosed embodiment, based on the target model, the number of brand dispatches obtained from multiple brand subordinate libraries under each business format, the dispatch priority corresponding to each business format and other indicators are taken into consideration, and the target brand resources available in the square are periodically and dynamically adjusted. From the perspective of global optimization, the target brand resources recommended for abnormal shops have a higher matching degree.

[0021] In an optional implementation, generating a target model according to the target function and the constraint conditions includes:

[0022] The target model is obtained according to the following formula:

[0023]

[0024] xT i,j >0,

[0025] S j >0,

[0026] ∑ i ∑ j X i,j ≤L,

[0027] Tar j =λ*β*M j *P j ,

[0028]

[0029] Among them: The objective function is The constraints are: X i,j >0,S j>0,∑ i ∑ j X i,j ≤L,Tar j =λ*β*M j *P j ,Inv j +∑ i X ij +S j ≥Tar j Among them, penalty order is the first penalty weight coefficient; X i,j is the number of brand dispatches; i is the brand subordinate library, i∈[1,n]; j is the business format, j∈[1,m]; wh j is the scheduling priority; S j is the expected gap; penalty slack is the second penalty weight coefficient; L is the total dispatch limit of each business format within the target area; λ is the completion rate of placement; β is the resource utilization rate; M j is the number of abnormal berths; P j The upper limit of the number of brand scheduling; j is the number of brands; j Schedule target quantities for brands.

[0030] In an optional implementation, obtaining the brand dispatch quantity obtained from multiple brand subordinate libraries in each business format includes:

[0031] Get the level of each brand's subordinate library;

[0032] The number of brand dispatches that match the corresponding level is determined based on the level.

[0033] In an optional implementation, the target model is processed using a target solution algorithm to obtain target brand resources to be scheduled, including:

[0034] Obtain a preset number of path finding objects, the number of all brand resources that can be called for each abnormal store, and the similarity distance between each brand resource;

[0035] According to the path finding object, the number of all brand resources that can be called for each abnormal shop, and the similarity distance, the probability of each path finding object matching each brand resource for each abnormal shop is determined;

[0036] Generate multiple brand resource candidate paths corresponding to each abnormal store based on probability;

[0037] According to the pheromone concentration released by the path search object on the abnormal store and each brand resource candidate path corresponding to the abnormal store and the maximum number of iterations, the brand resource target path is selected from the brand resource candidate paths;

[0038] According to the target model and the brand resource target path, the target brand resources to be scheduled are obtained.

[0039] In the disclosed embodiment, a target solution algorithm is used to process the target model to obtain target brand resources to be scheduled. Based on the target solution algorithm, more and more feedback information can be obtained, making the recommended brand resources more and more accurate.

[0040] In an optional implementation, after the target model is processed by the target solution algorithm to obtain the target brand resources to be scheduled, the method further includes:

[0041] Send target brand resources to the terminal as recommended resources;

[0042] Obtain the terminal's conversion rate for the target brand resources and obtain the recommendation index of the target brand resources.

[0043] In the disclosed embodiment, by acquiring the conversion rate of each target brand resource, the recommendation index of the target brand resource is obtained, which is conducive to directly recommending resources according to the recommendation index in the later stage, ensuring timely grasp of the task completion status of the square, reducing the vacant shop rate of the square, and shortening the time for introducing brands of vacant shops.

[0044] In a second aspect, the present disclosure provides a device for brand resource scheduling, the device comprising:

[0045] An acquisition module is used to acquire demand information for brand introduction of abnormal shops under multiple business formats within a target area, wherein the abnormal shops are shops that have not been successfully located, and the demand information is used to indicate the brand introduction tasks of the abnormal shops in the first period and the second period and the degree of successful completion of the location after the brand introduction;

[0046] A construction module is used to construct an objective function and constraint conditions according to the demand information, wherein the constraint conditions are used to conditionally limit the variables in the objective function;

[0047] A generation module is used to generate a target model according to the target function and constraint conditions;

[0048] The first obtaining module is used to process the target model using the target solution algorithm to obtain the target brand resources to be scheduled, wherein the target brand resources are the brand resources that need to be scheduled for each abnormal shop corresponding to each business format within the target area.

[0049] In a third aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the brand resource scheduling method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0050] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the brand resource scheduling method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 is a flowchart of a method for brand resource scheduling according to some embodiments of the present disclosure;

[0053] Figure 2 is a structural block diagram of an apparatus for brand resource scheduling according to some embodiments of the present disclosure;

[0054] Figure 3 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0056] At present, each brand that is placed in a shopping mall is pre-screened by brand introduction personnel to meet the segment planning, match the shopping mall level, and meet the rental standards. After telephone contact, communication and negotiation, and repeated confirmation with the brand party, the final contract is signed and placed. This places very high demands on the brand reserve and sensitivity of the brand introduction personnel. At present, when placing each brand, it is usually based on the brand introduction staff's own brand knowledge reserves, brand sensitivity, and grasp of brand trends. In terms of artificial introduction of brand merchants to each store in the shopping mall. However, this method relies too much on the ability of the brand introduction staff themselves. Different personal abilities have uneven levels of brand planning for stores, and there are too many unstable factors, resulting in a low success rate of brand introduction and a high time cost for brand introduction.

[0057] In order to solve the problems of related technologies, according to an embodiment of the present disclosure, a method embodiment of brand resource scheduling is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] In this embodiment, a method for brand resource scheduling is provided. Figure 1 is a flowchart of a method for brand resource scheduling according to an embodiment of the present disclosure. Figure 1 As shown, the method can be applied to the server side, and the process includes the following steps:

[0059] Step S101, obtaining demand information for brand introduction of abnormal shops under multiple business formats within the target area, wherein the abnormal shops are shops that have not been successfully located, and the demand information is used to indicate the brand introduction tasks of the abnormal shops in the first period and the second period and the degree of successful completion of the location after the brand introduction.

[0060] Optionally, in the disclosed embodiment, a target area, such as a certain square, is used as the object for brand resource scheduling, and brand introduction demand information of abnormal shops in multiple business formats (such as clothing, catering, beauty, etc.) in the square is obtained. In addition, the disclosed embodiment can also obtain multiple abnormal shops in multiple business formats according to a certain period, such as once every 3 days, and then determine the corresponding brand introduction demand information.

[0061] It should be noted that abnormal shops are some empty shops in an idle state, or some shops whose contracts are about to expire but have not been renewed, or some shops with abnormal business status and warning signs. At the same time, the abnormal shops usually contain corresponding shop attributes, such as the number of square meters occupied, geographical location, floor location, etc.; the introduced brands also include brand attributes, such as high-end categories, women's clothing categories, etc.

[0062] In addition, the demand information for brand introduction in abnormal stores under the above-mentioned formats refers to the corresponding brand introduction tasks for stores that are vacant in the first period (such as the preparation period) and the second period (such as the operation period), as well as the degree of successful completion of the brand introduction after the introduction.

[0063] Step S102, constructing an objective function and constraint conditions according to the demand information, wherein the constraint conditions are used to conditionally limit the variables in the objective function.

[0064] Optionally, a quantitative analysis of the actual problem is performed based on the demand information, appropriate target variables and decision variables are selected, and a functional relationship between the target variables and the decision variables is established, which is called the objective function. Then various restrictions are abstracted to obtain some equations or inequalities that the decision variables should satisfy, which are called constraints. Among them, the constraints are used to conditionally limit the variables in the objective function.

[0065] Step S103, generating a target model according to the target function and the constraint conditions.

[0066] Optionally, after determining the objective function and the constraints, a target model is generated from these two parts. It can be understood that the target model is actually a mathematical model, which is mainly used for the subsequent acquisition of target brand resources.

[0067] Step S104, using the target solution algorithm to process the target model to obtain the target brand resources to be scheduled, wherein the target brand resources are the brand resources that need to be scheduled for each abnormal shop corresponding to each business format within the target area.

[0068] Optionally, the disclosed embodiment may select a target solution algorithm, such as an ant colony algorithm, to process the target model and solve the overall optimal solution, which is the target brand resource to be dispatched at the corresponding abnormal store in each business format. For example, for an abnormal store in the clothing business format, the target brand resource recommended to be dispatched at the moment is XX.

[0069] In the disclosed embodiment, the brand introduction demand information of abnormal shops under multiple business formats within the target area is obtained to construct the objective function and constraints, and then the target model generated based on the objective function and constraints is solved. In this way, the brand introduction demand information taking the abnormal shops into consideration can be obtained, and then the abnormal shops under various business formats in the target area can be dynamically adjusted according to the attributes of the abnormal shops and the brand attributes, so as to finally obtain the purpose of recommending target brand resources with a higher matching degree, avoid the problems of incomplete brand resource reserves and brand mismatch of brand introduction personnel, improve the success rate of brand introduction, and shorten the time cost of brand introduction.

[0070] In some optional implementations, constructing an objective function and constraints based on demand information includes:

[0071] Obtain target scheduling strategy for scheduling brand resources based on demand information;

[0072] According to the evaluation index of the target scheduling strategy, the nonlinear programming problem is abstracted to generate the objective function and constraint conditions, where the evaluation index is used to characterize the ultimate purpose of the objective function.

[0073] Optionally, in the disclosed embodiment, demand information introduced by the brand of each abnormal shop under each business format can be used, and then a target scheduling strategy for scheduling brand resources can be obtained based on the demand information. The target scheduling strategy actually abstracts the problem into a nonlinear programming problem based on the acquired demand information to construct an objective function and constraints. In the target scheduling strategy, it is necessary to define evaluation indicators that meet the expected prerequisites. For example, the evaluation indicator is the minimum actual brand resource replenishment quantity. At this time, when constructing the objective function, it is necessary to construct the objective function based on the evaluation indicator.

[0074] It is understandable that nonlinear programming is a method for solving optimization problems with one or more nonlinear functions in the objective function or constraints. The disclosed embodiment abstracts the nonlinear programming problem based on the evaluation index of the target scheduling strategy, and then generates the objective function and constraints in each fixed period, thereby obtaining the brand resources that need to be scheduled at the moment.

[0075] In the disclosed embodiment, the objective function and constraints are generated through the target scheduling strategy, and the brand introduction status of each square is judged and corresponding brand recommendations are made at a fixed period. This can not only ensure that the task completion status of the square is grasped in a timely manner, but also recommend a new round of brands to solve the problem of rapid brand updates and iterations.

[0076] In some optional implementations, generating an objective function and constraints includes:

[0077] Obtain the number of brand dispatches obtained from multiple brand subordinate libraries in each business format, the dispatch priority corresponding to each business format, the expected gap corresponding to each business format, the first penalty weight coefficient, the second penalty weight coefficient, the number of brands that have not been placed in each business format, the number of brand dispatch targets in each business format, the number of abnormal stores in each business format, the completion rate of placement after the introduction of brands, the resource utilization rate of target brand resources, the upper limit of the number of brand dispatches in each business format, and the total dispatch upper limit of each business format within the target area;

[0078] According to the brand dispatch quantity, dispatch priority, expected gap, first penalty weight coefficient and second penalty weight coefficient, the objective function is obtained;

[0079] Constraints are obtained based on the brand scheduling quantity, expected gap, brand quantity, brand scheduling target quantity, abnormal store quantity, location completion rate, resource utilization rate, upper limit of brand scheduling quantity and total scheduling upper limit of each business format within the target area.

[0080] Optionally, the disclosed embodiment will obtain some data based on the demand information, such as the number of brand dispatches obtained from multiple brand subordinate libraries under each business format, the dispatch priority corresponding to each business format, the expected gap corresponding to each business format, the first penalty weight coefficient, the second penalty weight coefficient, the number of brands that have not been placed under each business format, the target number of brand dispatches under each business format, the number of abnormal shops under each business format, the completion rate of brand placement after introduction, the resource utilization rate of target brand resources, the upper limit of the number of brand dispatches under each business format, and the total dispatch upper limit number of each business format within the target area.

[0081] It should be noted that the brand subordinate library under each business format here is actually the region where the brand belongs. The brand subordinate library can be divided into n levels. The embodiment of this disclosure takes 3 levels as an example: national library / regional library / city company library. The number of brands that can be dispatched from different levels is different. For example, a women's clothing brand in the clothing industry, if it is spread all over the country, then the amount of brand resources dispatched from the national library, this brand subordinate library, should be higher than that of the city library or a large regional library. For example, a Sichuan dish in the catering industry, because its brand originates from Sichuan, the level of the city company library is set higher at this time, then the amount of brand resources dispatched from the brand subordinate library in Sichuan should be higher than that of the national library or a large regional library.

[0082] Get the dispatch priority corresponding to each business format. This priority can be set according to the actual situation of the square and business experience. For example, set the clothing format> catering format> beauty format. As much as possible, the business format with a high priority should be allocated first. When the business format with the highest priority is met, other business formats will be allocated.

[0083] Obtain the expected gap corresponding to each business format. This expected gap is actually the predicted overall brand shortage of abnormal stores under a certain business format, which can be determined based on demand information.

[0084] Get the first penalty weight coefficient and the second penalty weight coefficient. The first penalty weight coefficient and the second penalty weight coefficient are used to balance the replenishment brand resources to meet the formula requirements corresponding to the objective function.

[0085] Obtain the number of brands that have not been settled in each business format. The number of brands that have not been settled here actually refers to the brands that have never successfully settled in, and then count the total number of brands that have never successfully settled in each business format.

[0086] Get the number of brand scheduling targets under each business format. The number of brand scheduling targets here is the number of brand scheduling targets that need to be achieved under each business format.

[0087] Get the placement completion rate after the introduction of the brand. The placement completion rate here is the proportion of abnormal shop placements within a certain period. It is the number of vacant shops counted at the start of a certain period. After brand resource scheduling, the number of vacant shops that have signed placement contracts is counted. The placement completion rate after the introduction of the brand is the number of vacant shops that have signed placement contracts after brand resource scheduling divided by the number of vacant shops counted at the start of the period.

[0088] Obtain the resource utilization rate of the target brand resources. The resource utilization rate here is the proportion of brands that have been communicated among the recommended brands. That is, after obtaining the optimal solution: the target brand resources, they need to be invested in subsequent brand recommendations. If the brand introduction personnel use the target brand resources and conduct brand introduction communication, it is considered that the target brand resources have been utilized, and then the resource utilization rate of the target brand resources can be determined.

[0089] Get the upper limit of the number of brand dispatches under each business format. The upper limit of the number of brand dispatches under each business format here refers to the maximum number of brand dispatches allowed under each business format. In the initial state, the upper limit of the number of brand dispatches under each business format can be customized. For example, the upper limit of resource dispatches of different brand subordinate libraries in the catering and food business format can be 6, 5, and 3; after going online, count the sources of store brands that have successfully landed each quarter and reset the upper limit.

[0090] The total upper limit of dispatch quantity for each business format within the target area. The total upper limit of dispatch quantity for each business format within the target area here refers to the maximum total number of brand dispatches allowed for all business formats included in the entire square.

[0091] After obtaining all the above information, the objective function is obtained according to the brand dispatch quantity, dispatch priority, expected gap, first penalty weight coefficient and second penalty weight coefficient. The specific formula is as follows:

[0092]

[0093] Among them, penalty order is the first penalty weight coefficient; X i,j Scheduling quantity for brands; j is the scheduling priority; S jFor the expected gap; Penalty slack is the second penalty weight coefficient; i is the brand affiliation library, i∈[1,n]; j is the business format, j∈[1,m].

[0094] The objective function consists of two parts. The first part indicates that the brand replenishment volume should be as small as possible, and the second part indicates that the brand dispatch volume should be as small as possible. The overall optimization principle is: to minimize the brand dispatch volume while ensuring that all business formats are not out of stock. Use the penalty coefficient to achieve the goal: In theory, there will be a penalty for each resource replenished. order Penalty score, for each resource not met, there will be a penalty slack Obviously, penalty order Much lower than penalty slack , so that X can be achieved while meeting the store's target inventory level. i,j The smaller the better. For example, order Set to 1, penalty slack Set to 1000.

[0095] After obtaining all the above information, the constraints are obtained based on the brand scheduling quantity, expected gap, brand quantity, brand scheduling target quantity, abnormal store quantity, location completion rate, resource utilization rate, upper limit of brand scheduling quantity and total scheduling upper limit of each business format within the target area. The constraint formula is as follows:

[0096] xT i,j >0,

[0097] S j >0,

[0098] ∑ i ∑ j X i,j ≤L,

[0099] Tar j =λ*β*M j *P j ,

[0100]

[0101] Among them, L is the total dispatch limit of each business format within the target area; λ is the completion rate of placement; β is the resource utilization rate; M j is the number of abnormal berths; P j The upper limit of the number of brand dispatches; j is the number of brands; j Schedule target quantities for brands.

[0102] It should be noted that L is the total dispatch limit of each business format within the target area, which is negatively correlated with the number of dispatches:

[0103]

[0104] Considerations for setting the above constraints: The brand dispatch quantity (i.e. replenishment quantity) and the preset gap (i.e. out-of-stock quantity) cannot be negative in theory: X i,j >0,S j >0;

[0105] The replenishment quantity of subordinate warehouses of different brands for all formats shall not exceed the maximum replenishment quantity limit:∑ i ∑ j X i,j ≤L;

[0106] The sum of the number of unplaced brands in format j, the replenishment quantity of format j by different brand subordinate libraries, and the expected replenishment quantity of format j should be greater than or equal to the target replenishment quantity of format j, that is, the replenishment quantity should be greater than or equal to the target replenishment quantity: Inv j +∑ i X ij +S j ≥Tar j .

[0107] Therefore, the target model is generated by the objective function and constraints, and the formula is as follows:

[0108]

[0109] xT i,j >0,

[0110] S j >0,

[0111] ∑ i ∑ j X i,j ≤L,

[0112] Tar j =λ*β*M j *P j ,

[0113]

[0114] In the above target model, min() is the target function, and the following st is the constraint condition.

[0115] In the disclosed embodiment, based on the target model, the number of brand dispatches obtained from multiple brand subordinate libraries under each business format, the dispatch priority corresponding to each business format and other indicators are taken into consideration, and the target brand resources available in the square are periodically and dynamically adjusted. From the perspective of global optimization, the target brand resources recommended for abnormal shops have a higher matching degree.

[0116] In some optional implementations, the target model is processed using a target solution algorithm to obtain target brand resources to be scheduled, including:

[0117] Obtain a preset number of path finding objects, the number of all brand resources that can be called for each abnormal store, and the similarity distance between each brand resource;

[0118] According to the path finding object, the number of all brand resources that can be called for each abnormal shop, and the similarity distance, the probability of each path finding object matching each brand resource for each abnormal shop is determined;

[0119] Generate multiple brand resource candidate paths corresponding to each abnormal store based on probability;

[0120] According to the pheromone concentration released by the path search object on the abnormal store and each brand resource candidate path corresponding to the abnormal store and the maximum number of iterations, the brand resource target path is selected from the brand resource candidate paths;

[0121] According to the target model and the brand resource target path, the target brand resources to be scheduled are obtained.

[0122] Optionally, in the embodiment of the present disclosure, an ant colony algorithm is used as a target solution algorithm to process the target model to obtain the target brand resources to be scheduled, specifically:

[0123] The ant colony algorithm is a bionic algorithm inspired by the foraging behavior of ants in nature. Ant colonies can always find an optimal path from the ant nest and the food source, which can be well used for task-resource allocation problems. Based on the scheduling algorithm, different brand resources are allocated according to different brand introduction tasks. The essence of brand introduction task allocation is to match brand introduction tasks with several brand resources according to a certain principle. The brand introduction task here refers to recommending and scheduling brand resources for each abnormal shop under each business format. If there are 3 abnormal shops in the clothing business format that need to recommend and schedule brand resources, the number of brand introduction tasks in the clothing business format is 3, and then the number of abnormal shops in other business formats under the square is obtained. The sum of abnormal shops is the total number of brand introduction tasks in the entire square.

[0124] Specifically, (1) Initialize some ant colony algorithm parameters, such as ant colony size (number of ants), pheromone concentration, etc. The ants here are path finding objects. The number of ants in the entire ant colony can be set as antNum, which has a preset number (such as 50), the total number of brand introduction tasks is taskNum, the number of all brand resources that can be called for each abnormal store is brandNum, and the distance between brands (the vector is constructed based on the business format to which the brand belongs, the brand level, the brand customer unit price and other factors, and the cosine similarity is used as the distance between brands) is dij (i, j = 1, 2, 3, ..., brandNum). The pheromone concentration of brand introduction task ti and brand resource rj at time t is τ ij (t), at the initial moment, all brand introduction tasks have the same concentration as the matching path of each brand, so the pheromone concentration is initialized to τ ij =1, i<=taskNum, j<=brandNum.

[0125] (2) Constructing the solution space: Based on the number of all brand resources that can be called by each ant and each abnormal shop and the similarity distance between brands, calculate the probability that any ant k (k = 1, 2, ..., antNum) matches the brand resource rj for the brand introduction task ti at the current time t.

[0126]

[0127] Among them, τ ij (t) represents the pheromone concentration of brand introduction task ti matched to brand resource rj at time t, η ij (t) represents the heuristic function that matches the brand introduction task ti to the brand resource rj at time t, (To ensure that the denominator is not zero, add a very small positive number, such as 10 -4 ).

[0128] allowed k (k=1,2,...,antNum) is the set of brand resources to be matched by ant k, s is a brand resource, if s does not belong to the set of brand resources to be matched by ant k, the probability is 0. As time goes by, allowed kThe elements in decrease continuously until it is empty, which means that all brand resources have been matched; α is the pheromone importance factor. The larger its value, the greater the role of pheromone concentration in transfer, which is generally set to 1; β is the heuristic function importance factor. The larger its value, the greater the role of heuristic function in transfer, that is, the ant will transfer to a more matching brand with a greater probability, which is generally set to 5. After a certain period of time, the ant can match all brands and complete a cycle, that is, construct a set of paths, that is, construct a set of matching brands for the current brand introduction task ti. In this way, multiple brand resource candidate paths corresponding to each abnormal shop are generated according to the above probability.

[0129] In addition, as ants release pheromones, the pheromones on the brand introduction task and brand matching path gradually disappear. At this time, the pheromone concentration needs to be continuously updated. Generally, the Ant Cycle System model is used to calculate the concentration of released pheromones. That is, the shorter the path the ants pass, the higher the concentration of released pheromones. In this way, the target path with the shortest path and the highest concentration of released pheromones is selected from multiple candidate paths of brand resources. The specific method is as follows: (3) Update pheromone concentration: Set the parameter ρ (0<ρ<1, empirical value 0.1) to represent the volatility of pheromones. Therefore, when all ants complete a cycle, the pheromone concentrations on each brand introduction task and all brand matching paths need to be updated in real time:

[0130]

[0131] in: represents the pheromone concentration released by the kth ant on the matching path between the brand introduction task ti and the brand resource rj

[0132] Δτ ij It represents the sum of pheromone concentrations released by all ants on the matching path between brand introduction task i and brand resource j.

[0133] (4) If the maximum number of iterations (e.g. 200) is reached, the calculation is terminated and the optimal solution (i.e. the brand resource target path) is output. Otherwise, the record table of all ant paths is cleared and the process returns to step (2) to continue the iteration.

[0134] Since the target path of brand resources that will be obtained in the end actually contains many brand resources, at this time, each brand resource on the target path of brand resources is combined with the target model to obtain the target brand resource that satisfies the target function of the target model, and the target brand resource is used as the brand resource to be scheduled. It can be understood that since the embodiment of the present disclosure starts from the entire square, a unique target brand resource will be obtained under each business dimension, so from the perspective of the square, there will be several target brand resources to be scheduled.

[0135] In the disclosed embodiment, a target solution algorithm is used to process the target model to obtain target brand resources to be scheduled. Based on the target solution algorithm, more and more feedback information can be obtained, making the recommended brand resources more and more accurate.

[0136] In some optional implementations, after the target model is processed using the target solution algorithm to obtain the target brand resources to be scheduled, the method further includes:

[0137] Send target brand resources to the terminal as recommended resources;

[0138] Obtain the terminal's conversion rate for the target brand resources and obtain the recommendation index of the target brand resources.

[0139] Optionally, in the disclosed embodiment, the server sends the obtained target brand resources as recommended resources to the terminal. After receiving the target brand resources, if the brand introduction staff makes a telephone contact or signs a contract based on the target brand resources, it means that the brand introduction staff has successfully converted the recommended target brand resources. Then, based on the conversion rate of each target brand resource, a recommendation index can be generated for the recommended target brand resource, and a recommendation histogram or line chart of the target brand resource can also be generated based on the obtained recommendation index.

[0140] In the disclosed embodiment, by acquiring the conversion rate of each target brand resource, the recommendation index of the target brand resource is obtained, which is conducive to directly recommending resources according to the recommendation index in the later stage, ensuring timely grasp of the task completion status of the square, reducing the vacant shop rate of the square, and shortening the time for introducing brands of vacant shops.

[0141] In this embodiment, a device for brand resource scheduling is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0142] This embodiment provides a device for brand resource scheduling, such as Figure 2 As shown, including:

[0143] The acquisition module 201 is used to acquire demand information for brand introduction of abnormal shops under multiple business formats within the target area, wherein the abnormal shops are shops that have not been successfully located, and the demand information is used to indicate the brand introduction tasks of the abnormal shops in the first period and the second period and the degree of successful completion of the location after the brand introduction;

[0144] A construction module 202 is used to construct an objective function and constraint conditions according to the demand information, wherein the constraint conditions are used to conditionally limit the variables in the objective function;

[0145] A generation module 203 is used to generate a target model according to the target function and the constraint conditions;

[0146] The first obtaining module 204 is used to process the target model using the target solution algorithm to obtain the target brand resources to be scheduled, wherein the target brand resources are the brand resources that need to be scheduled for each abnormal shop corresponding to each business format within the target area.

[0147] In some optional implementations, the construction module 202 includes:

[0148] An acquisition unit, used for acquiring a target scheduling strategy for scheduling brand resources according to demand information;

[0149] The generation unit is used to abstract the nonlinear programming problem according to the evaluation index of the target scheduling strategy and generate the objective function and constraint conditions, wherein the evaluation index is used to characterize the purpose that the objective function ultimately needs to achieve.

[0150] In some optional implementations, the generating unit includes:

[0151] The first acquisition submodule is used to obtain the number of brand dispatches obtained from multiple brand subordinate libraries in each business format, the dispatch priority corresponding to each business format, the expected gap corresponding to each business format, the first penalty weight coefficient, the second penalty weight coefficient, the number of brands that have not been placed in each business format, the number of brand dispatch targets in each business format, the number of abnormal stores in each business format, the completion rate of brand placement after introduction, the resource utilization rate of target brand resources, the upper limit of the number of brand dispatches in each business format, and the total dispatch upper limit of each business format within the target area;

[0152] A first obtaining submodule is used to obtain an objective function according to the brand dispatch quantity, the dispatch priority, the expected gap, the first penalty weight coefficient and the second penalty weight coefficient;

[0153] The second sub-module is used to obtain constraints based on the brand scheduling quantity, expected gap, brand quantity, brand scheduling target quantity, abnormal store quantity, location completion rate, resource utilization rate, upper limit of brand scheduling quantity and total scheduling upper limit of each business format within the target area.

[0154] In some optional implementations, the generating module 203 includes:

[0155] The target model is obtained according to the following formula:

[0156]

[0157] xT i,j >0,

[0158] S j >0,

[0159] ∑ i ∑ j X i,j ≤L,

[0160] Tar j =λ*β*M j *P j ,

[0161]

[0162] Among them: The objective function is The constraints are: X i,j >0,S j >0,∑ i ∑ j X i,j ≤L,Tar j =λ*β*M j *P j ,Inv j +∑ i X ij +S j ≥Tar j Among them, penalty order is the first penalty weight coefficient; X i,j is the number of brand dispatches; i is the brand subordinate library, i∈[1,n]; j is the business format, j∈[1,m]; wh j is the scheduling priority; S j is the expected gap; penalty slack is the second penalty weight coefficient; L is the total dispatch limit of each business format within the target area; λ is the completion rate of placement; β is the resource utilization rate; M j is the number of abnormal berths; P j The upper limit of the number of brand scheduling; j is the number of brands; j Schedule target quantities for brands.

[0163] In some optional implementations, the first acquisition submodule includes:

[0164] Get subunits for obtaining the level of each brand's subordinate library;

[0165] A determination subunit is used to determine the brand dispatch quantity matching the corresponding level according to the level.

[0166] In some optional implementations, the first obtaining module 204 includes:

[0167] The second acquisition submodule is used to obtain a preset number of path finding objects, the number of all brand resources that can be called for each abnormal store, and the similarity distance between each brand resource;

[0168] The first determination submodule is used to determine the probability of each path finding object matching each brand resource for each abnormal shop according to the path finding object, the number of all brand resources that can be called for each abnormal shop, and the similarity distance;

[0169] A generation submodule is used to generate multiple brand resource candidate paths corresponding to each abnormal store according to probability;

[0170] A selection submodule is used to select a brand resource target path from the brand resource candidate paths according to the pheromone concentration released by the path search object on the abnormal store and each brand resource candidate path corresponding to the abnormal store and the maximum number of iterations;

[0171] The third submodule is used to obtain the target brand resources to be scheduled according to the target model and the brand resource target path.

[0172] In some optional embodiments, the device further comprises:

[0173] A sending module is used to process the target model using the target solution algorithm to obtain the target brand resources to be scheduled, and then send the target brand resources as recommended resources to the terminal;

[0174] The second obtaining module is used to obtain the conversion rate of the terminal to the target brand resource and obtain the recommendation index of the target brand resource.

[0175] The brand resource scheduling device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0176] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0177] The present disclosure also provides a computer device having the above Figure 2 The brand resource scheduling device is shown.

[0178] See also Figure 3 , Figure 3 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0179] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0180] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0181] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0182] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0183] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0184] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0185] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for brand resource scheduling, characterized in that: The method comprises: Obtaining demand information for brand introduction of abnormal shops under multiple business formats within the target area, wherein the abnormal shops are shops that have not been successfully located, and the demand information is used to indicate the brand introduction tasks of the abnormal shops in the first period and the second period and the degree of successful completion of the location after the brand introduction; Constructing an objective function and constraint conditions according to the demand information, wherein the constraint conditions are used to conditionally limit variables in the objective function; Generate a target model according to the target function and the constraint conditions; The target model is processed using a target solution algorithm to obtain target brand resources to be scheduled, wherein the target brand resources are brand resources that need to be scheduled at the moment for each abnormal shop corresponding to each business format within the target area.

2. The method according to claim 1, characterized in that The constructing of the objective function and the constraint conditions according to the demand information includes: Acquire a target scheduling strategy for scheduling brand resources according to the demand information; A nonlinear programming problem is abstracted according to the evaluation index of the target scheduling strategy to generate the objective function and the constraint conditions, wherein the evaluation index is used to characterize the purpose that the objective function ultimately needs to achieve.

3. The method according to claim 2, characterized in that The generating the objective function and the constraint condition comprises: Obtain the number of brand dispatches obtained from multiple brand subordinate libraries in each business format, the dispatch priority corresponding to each business format, the expected gap corresponding to each business format, the first penalty weight coefficient, the second penalty weight coefficient, the number of brands that have not been placed in each business format, the number of brand dispatch targets in each business format, the number of abnormal stores in each business format, the completion rate of placement after the introduction of brands, the resource utilization rate of the target brand resources, the upper limit of the number of brand dispatches in each business format, and the total dispatch upper limit of each business format within the target area; Obtaining the objective function according to the brand dispatch quantity, the dispatch priority, the expected gap, the first penalty weight coefficient, and the second penalty weight coefficient; The constraint conditions are obtained according to the brand scheduling quantity, the expected gap, the brand quantity, the brand scheduling target quantity, the abnormal store quantity, the placement completion rate, the resource utilization rate, the upper limit of the brand scheduling quantity and the total scheduling upper limit quantity of each business format within the target area.

4. The method according to claim 3, characterized in that The generating of the target model according to the target function and the constraint condition comprises: The target model is obtained according to the following formula: Among them: The objective function is The constraints are: X i,j >0,S j >0,∑ i ∑ j X i,j ≤L,Tar j =λ*β*M j *P j ,Inv j +∑ i X ij +S j ≥Tar j Among them, penalty order is the first penalty weight coefficient; i,j is the dispatch quantity of the brand; i is the brand subordinate library, i∈[1,n]; j is the business format, j∈[1,m]; wh j is the scheduling priority; S j is the expected shortfall; penalty slack is the second penalty weight coefficient; L is the total scheduling upper limit of each business format within the target area; λ is the placement completion rate; β is the resource utilization rate; M j is the number of abnormal berths; P j The upper limit of the number of dispatches for the brand; j is the number of brands mentioned; Tar j Dispatch target quantity for said brand.

5. The method according to claim 3, characterized in that: The obtaining of the brand dispatch quantity obtained from the multiple brand subordinate libraries in each business format includes: Obtaining the level of each of the brand's subordinate libraries; The brand dispatch quantity matching the corresponding level is determined according to the level.

6. The method according to claim 1, characterized in that The target model is processed by the target solution algorithm to obtain the target brand resources to be scheduled, including: Obtain a preset number of path finding objects, the number of all brand resources that can be called for each abnormal store, and the similarity distance between each brand resource; Determine the probability of each path finding object matching each brand resource for each abnormal shop according to the path finding object, the number of all brand resources that can be called for each abnormal shop, and the similarity distance; Generate multiple brand resource candidate paths corresponding to each of the abnormal shops according to the probability; Selecting a brand resource target path from the brand resource candidate paths according to the pheromone concentration released by the path search object on the abnormal shop and each brand resource candidate path corresponding to the abnormal shop and the maximum number of iterations; The target brand resource to be scheduled is obtained according to the target model and the brand resource target path.

7. The method according to any one of claims 1 or 6, characterized in that: After the target model is processed by the target solution algorithm to obtain the target brand resources to be scheduled, the method further includes: Sending the target brand resource as a recommended resource to the terminal; The conversion rate of the terminal to the target brand resource is obtained to obtain a recommendation index of the target brand resource.

8. A device for brand resource scheduling, characterized in that: The device comprises: An acquisition module is used to acquire demand information for brand introduction of abnormal shops under multiple business formats within a target area, wherein the abnormal shops are shops that have not been successfully located, and the demand information is used to indicate the brand introduction tasks of the abnormal shops in the first period and the second period and the degree of successful completion of the location after the brand introduction; A construction module, used to construct an objective function and constraint conditions according to the demand information, wherein the constraint conditions are used to conditionally limit variables in the objective function; A generating module, used for generating a target model according to the target function and the constraint conditions; The first obtaining module is used to process the target model using a target solution algorithm to obtain target brand resources to be scheduled, wherein the target brand resources are brand resources that need to be scheduled at present for each abnormal shop corresponding to each business format within the target area.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for brand resource scheduling according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for brand resource scheduling according to any one of claims 1 to 7.

Images