Layout optimization method and device for shops in function interleaving area of commercial complex

Abstract

The invention relates to the technical field of building space planning, and particularly provides a method and a device for optimizing the layout of shops in a function interleaving area of a commercial complex. The method comprises the following steps: acquiring a pre-constructed macro optimization model based on shop attributes and a pre-constructed micro optimization model based on pedestrian attributes; respectively determining a macroscopic optimization target and a constraint condition of the macroscopic optimization model and a microscopic optimization target of the microscopic optimization model; determining a plurality of candidate shop layouts by utilizing the macroscopic optimization model, the macroscopic optimization target and the constraint condition; and determining a target shop layout from the plurality of candidate shop layouts by using the microscopic optimization model and the microscopic optimization target, so as to perform shop layout on the commercial complex function interleaving area by using the target shop layout. According to the method, the number of pedestrians entering the shop can be increased, the pedestrians can be induced to flow, internal traffic congestion is avoided, cross interference is reduced, and the operation efficiency of a commercial complex is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of building space planning, and in particular, to a method and device for optimizing the layout of shops in the functional intersection area of a commercial complex. Background Art

[0002] A commercial complex aims to integrate various functions in a city, such as commercial activities, office space, catering services, shopping, entertainment, and transportation. In the Functional Interchange Area (FIA) of a commercial complex, there are pedestrians with different travel purposes such as commuting, shopping, and business, supplemented by multi-attribute shops that meet various needs. However, this also poses challenges to commercial complexes, such as crowded crowds, complex facility layouts, and chaotic space perception.

[0003] In the related art, the utilization rate of shops in the functional intersection area of a commercial complex is low, and there are problems such as cross-crowded pedestrian flow lines, high regional density, and low operating efficiency of the commercial complex. Summary of the Invention

[0004] In view of the above problems, the present disclosure is proposed. The present disclosure provides a method and device for optimizing the layout of shops in the functional intersection area of a commercial complex.

[0005] According to one aspect of the present disclosure, there is provided a method for optimizing the layout of shops in the functional intersection area of a commercial complex, including: Obtaining a pre-constructed macro-optimization model based on shop attributes and a micro-optimization model based on pedestrian attributes; wherein, the macro-optimization model is used to optimize the total attraction of shops and the penalty for unbalanced passenger flow in the functional intersection area of a commercial complex, and the micro-optimization model is used to optimize the passenger flow density of channels in the functional intersection area of the commercial complex; Respectively determining the macro-optimization objective and constraint conditions of the macro-optimization model, and the micro-optimization objective of the micro-optimization model; Using the macro-optimization model, the macro-optimization objective, and the constraint conditions to determine multiple candidate shop layouts; Using the micro-optimization model and the micro-optimization objective to determine a target shop layout from the multiple candidate shop layouts, so as to use the target shop layout to perform shop layout in the functional intersection area of the commercial complex.

[0006] According to another aspect of the present disclosure, there is provided a device for optimizing the layout of shops in the functional intersection area of a commercial complex, including: An acquisition module for acquiring a pre-constructed macro-optimization model based on store attributes and a micro-optimization model based on pedestrian attributes; wherein the macro-optimization model is used to optimize the total attraction of stores and the unbalanced passenger flow penalty in the functional intersection area of a commercial complex, and the micro-optimization model is used to optimize the passenger flow density of channels in the functional intersection area of the commercial complex. A processing module for respectively determining the macro-optimization objective and constraints of the macro-optimization model, and the micro-optimization objective of the micro-optimization model. The processing module is further configured to use the macro-optimization model, the macro-optimization objective, and the constraints to determine multiple candidate store layouts. The processing module is further configured to use the micro-optimization model and the micro-optimization objective to determine a target store layout from the multiple candidate store layouts, so as to use the target store layout to perform store layout for the functional intersection area of the commercial complex.

[0007] Another aspect of the exemplary embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the method of the exemplary embodiment of the present disclosure.

[0008] Another aspect of the exemplary embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method of the exemplary embodiment of the present disclosure.

[0009] Another aspect of the exemplary embodiment of the present disclosure provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method of the exemplary embodiment of the present disclosure.

[0010] As will be described in detail below, a method for optimizing the layout of shops in the functional intersection area of a commercial complex according to an embodiment of the present disclosure includes obtaining a pre-constructed macro-optimization model based on shop attributes and a micro-optimization model based on pedestrian attributes. The macro-optimization model is used to optimize the total attraction of shops and the unbalanced passenger flow penalty in the functional intersection area of the commercial complex, and the micro-optimization model is used to optimize the passenger flow density of channels in the functional intersection area of the commercial complex. The macro-optimization objective and constraints of the macro-optimization model and the micro-optimization objective of the micro-optimization model are determined respectively. Using the macro-optimization model, the macro-optimization objective and the constraints, multiple candidate shop layouts are determined. Using the micro-optimization model and the micro-optimization objective, the target shop layout is determined from multiple candidate shop layouts, so as to use the target shop layout to layout the shops in the functional intersection area of the commercial complex, which can ensure the rationality of regional division in terms of internal functional space, attract more non-shopping pedestrians into the shops, and increase the overall number of pedestrians entering the shops. In terms of traffic planning, it can induce the pedestrian flow line, avoid internal traffic congestion, reduce cross-interference, and improve the operation efficiency of the commercial complex. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] By describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure, and constitute a part of the specification, and are used to explain the present disclosure together with the embodiments of the present disclosure, and do not constitute a limitation to the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 FIG. shows a schematic flowchart of a method for optimizing the layout of shops in the functional intersection area of a commercial complex provided by an exemplary embodiment of the present disclosure; Figure 2 FIG. shows a change diagram of the overall density of channels under three layout schemes provided by an embodiment of the present disclosure; Figure 3 FIG. shows a comparison diagram of the total in-store traffic of various types of shops under three layout schemes provided by an embodiment of the present disclosure; Figure 4 FIG. shows a schematic structural diagram of a device for optimizing the layout of shops in the functional intersection area of a commercial complex provided by an exemplary embodiment of the present disclosure; Figure 5 FIG. shows a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure; Figure 6 FIG. shows a schematic structural diagram of a computer system provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] To make the objectives, technical solutions, and advantages of the present disclosure more apparent, exemplary embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. Apparently, the described embodiments are only a part rather than all of the embodiments of the present disclosure. It should be understood that the present disclosure is not limited by the exemplary embodiments described herein.

[0014] It should be understood that the steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0015] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order of the functions executed by these devices, modules, or units or their interdependent relationships.

[0016] It should be noted that the modifications of "one" and "a plurality" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0017] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0018] Space syntax theory and optimization models are respectively the two most commonly used methods for two macroscopic layout strategies. However, using these methods to optimize the layout of shops in the functional intersection area is too macroscopic, weakening the behavioral diversity and randomness of heterogeneous pedestrians with different travel attributes. In addition, these methods also ignore the differential attraction effect of multi-attribute shops on heterogeneous pedestrians and the passenger flow exchange effect between shops. Therefore, the layout optimization strategies planned by these methods may reduce the utilization rate of shops.

[0019] Meanwhile, whether it is pedestrian behavior analysis, preference analysis, or trajectory analysis, they are actually discussing the attraction effect of stores on pedestrians. That is, pedestrians in traditional shopping centers only have two attributes: purposeful shopping, looking for interesting stores, and switching between the two. However, in the functional intersection area, there are pedestrians with different travel purposes such as commuting, shopping, and business, and each type of pedestrian has different shopping needs. However, most of the existing methods ignore the internal connection between multi-attribute stores and heterogeneous pedestrians, making it difficult to describe the attraction of stores to different types of pedestrians and unable to truly simulate the travel behavior and flow of pedestrians in the commercial complex. Therefore, the layout optimization strategies simulated by these models will cause problems such as crossed and crowded pedestrian flow lines, high regional density, and low operation efficiency of the commercial complex.

[0020] In summary, the layout of the functional intersection area currently faces two main problems: in terms of the internal functional space, how to design the layout according to commercial needs to ensure the rationality of regional division, attract more non-shopping pedestrians into the stores, and increase the overall number of pedestrians entering the stores. In terms of traffic planning, how to optimize the layout of the commercial complex, induce the pedestrian flow line, avoid internal traffic congestion, reduce cross-interference, and improve the operation efficiency of the commercial complex.

[0021] To solve these two problems, the embodiments of the present disclosure propose a macro-to-micro layout optimization framework for the functional intersection area based on the internal connection between multi-attribute stores and heterogeneous pedestrians. Macroscopically, with the maximization of the total attraction of stores as the optimization goal and considering the complementarity between different types of stores, a preliminary layout plan is obtained; microscopically, an Attraction-Potential Social Force Model (AP-SFM) is proposed to simulate the attraction effect of different stores on heterogeneous pedestrians and truly simulate the movement process and behavior of heterogeneous pedestrians in the functional intersection area. On the basis of the preliminary plan, the optimization goal at the micro level is to minimize the pedestrian density in the channels of the functional intersection area, and according to the simulation results of AP-SFM, the final layout plan of the functional intersection area is obtained.

[0022] The embodiments of the present disclosure combine the research and analysis of the actual situation of typical functional intersection area sites (such as the basement floor of Guomao in a certain city) to study the macro-to-micro layout optimization method of the functional intersection area of the commercial complex. To better illustrate the purpose of the embodiments of the present disclosure, the following assumptions are made first: I. Hypothesis Conditions The embodiments of the present disclosure aim to incorporate the complementarity between multi-attribute stores into the layout plan of the functional intersection area of the commercial complex and consider the influence of the different attractions of multi-attribute stores on heterogeneous pedestrians. Layout optimization is a complex problem involving multiple factors such as construction, operation, management, economy, vision, and traffic. Therefore, the embodiments of the present disclosure make the following assumptions: Hypothesis 1: During the process of optimizing the layout of shops in the functional intersection area of a commercial complex, operators only need to allocate shops within the already divided space, without re-dividing the internal space of the mall. In other words, the purpose of the embodiments of the present disclosure is to optimize the layout of shops in the existing space, without considering re-dividing the space of the functional intersection area.

[0023] Hypothesis 2: In the macroscopic layout optimization model, the complementarity between shops is considered, so the externality between anchor shops and non-anchor shops is no longer considered separately. At the same time, the quantification of anchor stores is reflected by factors such as the area, type, and brand of the shops, and the anchor stores are no longer fixed.

[0024] Hypothesis 3: Pedestrians in a group are calculated based on individual attraction. When one person in the group is attracted, all people enter the shop at the same time. When the group is a family, the influence of the shop on children is ignored, and only the influence on adults is considered.

[0025] Hypothesis 4: When shopping pedestrians complete their initial goals, the entrance farthest from their current position is determined as the new goal, and they will move within the functional intersection area as potential consumers.

[0026] Hypothesis 5: The influence of factors related to the fields of architecture and visual communication, such as building appearance, lighting design, etc., is not considered.

[0027] II. Construction of a macroscopic optimization model based on shop attributes 1. Optimization objectives of the macroscopic optimization model Most existing studies take maximizing rent as the objective function of layout optimization, but this ignores the needs and characteristics of shops. In the embodiments of the present disclosure, due to the diversity of functions of the commercial complex, heterogeneous pedestrians with various travel purposes will flow randomly inside. At the same time, according to Hypothesis 4, pedestrians originally with shopping purposes will also transform into potential consumers with random shopping behavior after completing their shopping purposes. Therefore, the objective of the embodiments of the present disclosure is to attract more potential customers to transform into in-store customers through layout optimization, while avoiding the phenomenon of uneven passenger flow between different shops. In short, the optimization objective is to maximize the overall attraction of the shops while reducing the phenomenon of uneven passenger flow.

[0028] Exemplarily, the optimization objectives of the macroscopic optimization model may include the objective function of the macroscopic optimization model and the constraint conditions of the macroscopic optimization model; among them, the macroscopic optimization model can be represented by the following formula (1), the objective function of the macroscopic optimization model can be expressed as maxZ, and the constraint conditions of the macroscopic optimization model can be represented by the following formula (2) to formula (6). Among them, formula (1) to formula (6) are as follows:

[0029]

[0030]

[0031]

[0032]

[0033]

[0034] Among them, I = {1, 2..., n} represents the set of stores, J = {1, 2..., m} represents the set of store locations, and x ij ∈ {0, 1} indicates whether store i is assigned to location j, represents the attractiveness of store i at location j, represents the penalty weight for unbalanced passenger flow, represents the passenger flow ratio limit, represents the initial predicted attractiveness of store i at location j, represents the area of location j, represents the maximum passenger flow capacity of store i, represents the type of store i, represents the total attractiveness of stores in the functional intersection area.

[0035] Here, s.t. means subject to.

[0036] In the above formula (1), the first term is the attractiveness term, representing the total attractiveness of stores under the optimized layout, and the second term is the penalty term, representing the penalty for unbalanced passenger flow. The purpose of the constraint conditions in the above formula (2) is to ensure that each store has a location. According to assumption 2 in the previous text, the main stores are no longer fixed, and each store can be set at any empty location. The constraint conditions in the above formula (3) can ensure the full utilization of the leasable area in the functional intersection area. The constraint conditions in the above formula (4) can be used to represent that the passenger flow of each store cannot exceed its maximum passenger flow capacity. The constraint conditions in the above formula (5) are proposed according to assumption 1 and assumption 5 in the previous text, indicating that the embodiments of the present disclosure do not consider the influence of factors related to the construction field, and catering stores involve factors such as flue ducts and fire protection. Therefore, during the optimization process, only adjustments can be made at the original locations of catering stores. The constraint conditions in the above formula (6) can be used to ensure that the total passenger flow in the functional intersection area is fixed.

[0037] 2. Attractiveness of Stores In the macroscopic layout optimization model, the embodiments of the present disclosure ignore the influence of pedestrian attributes on the attractiveness of shops, that is, the embodiments of the present disclosure neither consider the matching relationship between heterogeneous pedestrians and diverse shops, nor consider the positions of pedestrians, and only establish an attractiveness function based on the inherent attributes of the shops. According to previous research and many empirical studies, the proposed attractiveness function depends on the scale, type, location, brand level, and complementarity of the shops:

[0038] Among them, represents the attractiveness of the shop, represents the scale of the shop, represents the type of the shop, represents the brand level of the shop, represents the location of the shop, represents the complementarity of the shop.

[0039] Here, regarding the scale of the shop: it can be the area of the shop. When shop i is located at position j, the area of shop i is equal to the area of position j.

[0040] Regarding the type of the shop: According to the commercial industry standard "Shopping Center Tenant Mix Strategy Guide", the types of shops in a shopping center can be divided into 8 categories: fashion, family and children, accessories, catering, desserts and beverages, lifestyle, beauty and cosmetics, and services. Among them, the type of restaurant refers to a formal restaurant, which needs to be placed in a fixed and permitted area. While the shops of the dessert and beverage type can be freely adjusted without area restrictions.

[0041] Regarding the brand level of the shop: It is determined by the scale and type of the shop. The embodiments of the present disclosure divide the brands of shops into 5 levels, and the identification of the brand level is based on the type and scale of the shop.

[0042] Regarding the location of the shop: It can be the spatial distribution of the shop. In addition to the type and brand level of the shop, the relative positions of the shop with the entrances and elevators will also result in differences in the attractiveness of the shop. The location attractiveness parameter is introduced as the location attractiveness of shop i at position j, which can use the Euclidean distance to measure the distance between the center point of each position and the center point of the entrance or elevator of the mall, as shown in the following formula (8):

[0043] Among them, represents the location attractiveness of shop i at position j, represents the set of entrances e of the functional interweaving area, represents the set of elevators l,( , ) represents the coordinates of position j, ( , ) represents the coordinates of entrance e, ( , ) represents the coordinates of elevator l.

[0044] Complementarity of stores: The degree to which store i is affected by surrounding stores. During the shopping process, whether for comparing product quality or price, customers will unconsciously shift their attention to other stores in the same area, which can easily convert potential customers into in-store customers.

[0045] Based on this psychology of pedestrians, attempts are made to improve the complementarity of stores through layout optimization, thereby effectively increasing the overall attractiveness of stores. That is, first, it is necessary to determine the spatial range within which complementary effects occur between stores. Only stores within a certain range are considered to exhibit complementarity. In addition, complementarity between stores also shows a saturation effect. Assume that a pedestrian's interest in a specific type of store changes as the number of similar stores in the area increases, and this process is divided into two stages. However, once the number of similar stores exceeds a certain critical value, the system enters the saturation stage, at which point the pedestrian's interest begins to decline.

[0046] In addition, according to on-site investigations, it is found that pedestrians' desire to purchase the same type of products weakens after a shopping experience. Therefore, there is not only positive complementarity between similar stores, but also a reverse mutual exclusion effect, that is, the attractiveness of stores selling the same type of products decreases after shopping. For example, in the case of restaurants or dessert and beverage stores, after consuming at one store, the attractiveness of nearby similar stores drops to zero, resulting in no interest in visiting other nearby similar stores at all.

[0047] In summary, in order to eliminate the dimensional inconsistency and numerical incomparability between different parameters, the above parameters are normalized, and the attractiveness of store i at position j is defined as follows:

[0048] where, represents the scale of store i, which is equal to the area of position j , represents the type of store i, represents the brand level of store i, represents a distance boolean variable used to characterize the complementary effect between store i at position j and store n. If > , = 0, represents the distance between the central coordinates of position j and store n, represents the influence radius of store i, represents the complementary weight between store i and store n represents the initial predicted attractiveness of store n at location m , represents the saturation effect function of store i represents the number of stores of the same type within the influence radius of store i at location j, and α>0 represents the saturation rate parameter represents the purchase desire adjustment parameter ∈[0,1].

[0049] III. Construction of a Microscopic Optimization Model Based on Pedestrian Heterogeneity 1. Optimization Objectives of the Microscopic Optimization Model After optimizing with the macroscopic optimization model based on store attributes, there are two reasons for using the microscopic optimization model based on pedestrian heterogeneity for the second-step optimization: On the one hand, due to its inherent structure, the objective function of the first-step macroscopic optimization model is non-convex. The attraction term introduces non-linearity through the complementary effect and saturation effect functions, and these factors create dependencies between store allocations, resulting in the objective function of the macroscopic optimization model presenting a complex non-convex state. In addition, the penalty term is an isolated quadratic convex term. However, when the penalty term is combined with the non-linear attraction term, the entire objective function of the macroscopic optimization model becomes non-convex. A non-convex objective function has multiple local optimal points, so it is difficult to ensure that the obtained solution is globally optimal. And the above constraints such as formula (2) to formula (6) further exacerbate this challenge because these constraints bring additional complexity to the feasible region of the functional intersection area. In this case, standard optimization techniques such as gradient or heuristic methods are easily converged to local optima. Therefore, the generated solutions are usually multiple sub-optimal solutions, representing local optima rather than global optima.

[0050] On the other hand, macroscopic optimization from the perspective of stores ignores the influence of pedestrian heterogeneity. As mentioned above, the behavior of pedestrians in stores is largely affected by the attributes of pedestrians, and the ultimate goal of the embodiments of the present disclosure is to increase the number of pedestrians in stores by optimizing the store layout. Therefore, it is necessary to introduce a simulation method and incorporate the influence of pedestrian heterogeneity in the second step of the optimization model to determine the final store layout.

[0051] In summary, considering that the first-step optimization may produce multiple sub-optimal solutions and the heterogeneity of pedestrians needs to be incorporated into the optimization model, a second-step optimization based on simulation is introduced.

[0052] Embodiments of the present disclosure propose an Attraction Potential-based Social Force Model (AP-SFM) for simulating the attraction effects of different shops on heterogeneous pedestrians under multiple sub-optimal shop layouts (i.e., multiple candidate shop layouts) generated in the first step. The ultimate goal of the embodiments of the present disclosure is to maximize the number of pedestrians in the shops. However, due to the inherent differences in the number of customers and the residence time among shops of different types and brand levels, it is challenging to comprehensively evaluate the overall rationality of the shop layout in the functional intersection area. Therefore, to solve this problem, the optimization objective of the micro-optimization model is defined as minimizing the average pedestrian density in the passageway. The micro-optimization model based on pedestrian attributes can be represented by the following formulas (10) - (12):

[0053]

[0054]

[0055] Among them, represents the passenger flow density of the passageway in the functional intersection area, C represents the range of the passageway in the functional intersection area, represents the vertex coordinates of the passageway, T represents the total time steps, P represents the total number of pedestrians in the functional intersection area, represents the area of the passageway, represents the pedestrian number indicator function of the passageway, represents the position of pedestrian p at time t, represents the position of pedestrian p at time step t + 1, represents the actual speed of pedestrian p at time t, represents the pedestrian position update function.

[0056] Here, in the constraint conditions of the above formula (12), the movement of pedestrians is based on the proposed AP-SFM to determine the pedestrian trajectory in the next time step, The pedestrian position update function represented can be the Attraction Potential-based Social Force Model (AP-SFM).

[0057] The shape of the passageway in the above functional intersection area can be a polygon, which is specifically determined according to the actual application scenario. The embodiments of the present disclosure do not make specific limitations on the shape of this passageway.

[0058] 2. Social Force Model in Related Technologies According to the original Social Force Model (SFM), the movement of pedestrian p in a complex environment is represented by the driving force of pedestrian p, the interaction force between pedestrian p and other pedestrian q, and the repulsive force between pedestrian p and wall w. The social force model can be represented by the following formulas (13) - (18):

[0059]

[0060]

[0061]

[0062]

[0063]

[0064] Among them, represents the mass of pedestrian p, represents the driving force of pedestrian p, represents the interaction force between pedestrian p and other pedestrian q, represents the repulsive force between pedestrian p and the inner wall w of the passage, represents the actual speed of pedestrian p, represents the actual speed of other pedestrian q, represents the desired speed of pedestrian p at time t, represents the unit vector pointing to the desired target at time t, and τ represents a certain characteristic time, represents the strength of the social interaction force, represents the range of the social interaction force, and are both constants, represents the sum of the radii of pedestrian p and other pedestrian q, represents the radius of pedestrian p, represents the distance between the centroid of pedestrian p and other pedestrian q, represents the distance between the centroid of pedestrian p and the wall w, represents the normalized vector of other pedestrian q pointing to pedestrian p, represents the normalized vector of the wall w pointing to pedestrian p, represents the body compression coefficient, represents the sliding friction coefficient, represents the tangential direction between pedestrian p and other pedestrian q, represents the tangential direction between pedestrian p and the wall w, Q represents the total number of pedestrians, and W represents the total number of walls, represents whether pedestrians are non - contacting or contacting the wall, represents the position of pedestrian p at time t, represents the position of pedestrian p at the initial time.

[0065] Here, is a step function (when When > 0, take " ", otherwise "0"), indicating that it is only when in contact ( < or < ), a physical force is generated, that is, take "0" for non-contact, and take " " for contact (the same for pedestrians and walls).

[0066] Obviously, the SFM in the related art cannot truly and effectively simulate the attraction effect of different shops on heterogeneous pedestrians. Therefore, the embodiments of the present disclosure introduce attraction to improve the original social force model and propose a social force model based on attraction potential energy (AP-SFM).

[0067] 3. Attraction of pedestrians Similar to the attraction of shops, the attraction of shops to pedestrians is also affected by factors such as the scale and type of shops. After adding the relevant factors of pedestrians, it is also necessary to additionally consider the distance between the shop and the pedestrian, the guiding property of the shop, and the visual distance of the pedestrian.

[0068] Based on this, the embodiments of the present disclosure introduce the gravitational potential in the law of universal gravitation, that is, attraction potential energy (which can also be called attraction potential energy). The attraction potential energy between a shop and a pedestrian can be expressed by the following formulas (19) - (20):

[0069]

[0070] Among them, represents the attraction potential energy between the shop and the pedestrian , represents the attraction between the shop and the pedestrian , represents the normalized vector of the pedestrian pointing to the shop , represents the weight parameter to ensure the consistency of the unit magnitude, and the value is , which can be determined according to the intensity of the social interaction force of the original SFM, represents the scale of the shop , represents the guiding coefficient of the shop , represents the distance between the shop and the pedestrian , represents the distance between the shop and the pedestrian The matching degree between represents a range constraint and is used to determine whether a store is within the pedestrian's attention range. represents the store and the pedestrian The angle between represents the angle of the pedestrian's attention range. represents the depth of the pedestrian's attention range.

[0071] Here, regarding the scale of the store: In the gravitational model, the scale of the store should be the mass of the object, that is, the product of density and volume. Since all stores are on the same horizontal plane, it is considered that the environmental density and height of the stores are the same. Therefore, the mass of the store can be converted into the area of the store, which is consistent with the definition of the size factor of the attraction function of the store in the previous text. In addition, for normalization, should be in the range of [0, 1], and it can be calculated by the area of store i divided by the total area of all stores, that is:

[0072] where represents the area of store i.

[0073] Regarding the matching degree matrix between the store and the pedestrian: The matching degree between the type of the store and the attributes of the pedestrian is one of the important factors affecting the attraction. A matching degree matrix is established, where each element represents the matching degree between different types of stores and different types of pedestrians. All elements of the matching degree matrix are subjected to minimum normalization within the range of [0, 1].

[0074] Regarding the guiding coefficient of the store: In the functional intersection area, there are various stores arranged to attract pedestrians, but the perception ability of pedestrians is limited. Relying solely on visual stimuli to attract pedestrians into the store is often challenging. Therefore, various guiding measures are usually taken, but some measures may have the opposite effect (for example, playing overly loud music through a speaker may irritate pedestrians). These guiding measures are divided into three categories: publicity, events, and hawking. Among them, The normalized value of is in the range of [-1, 1], which ensures that ( ) the normalized value is in the range of [0, 2].

[0075] Regarding the pedestrian's attention range: When pedestrians move, the range they can perceive is farther than the moving range. This perceived range is defined as the pedestrian's attention range, which is composed of the angle ( ) and the depth ( The determined sector range. Among them, the attraction only takes effect when the store is within the pedestrian's attention range. In the embodiments of the present disclosure, it is set that = 120°, = 10m.

[0076] Regarding the range constraint: For simplicity, the entrance of store i is defined as a solid line. Therefore, can be calculated as the distance between the centroid of pedestrian p and the proximal end of the solid line. At the same time, whether store i is within the pedestrian's perception range can be judged by the angle formed by the line connecting the centroid of pedestrian p and the proximal end of store i and the direction of pedestrian p. Only when store i is within the attention range of pedestrian p will an attraction effect be generated. Therefore, the range constraint condition can be calculated as:

[0077] Among them, represents the indicator function. If the input predicate is true, it returns 1, otherwise it returns 0.

[0078] 4. Social force model based on attraction potential energy In the embodiments of the present disclosure, the comprehensive force criterion is used, rather than simple force addition or subtraction, to integrate the attraction into the original social force model. In addition, the process of pedestrians being affected by the perceived attraction is conceptualized as a cumulative process of attraction potential energy, which is divided into two stages: (a) Perceiving attraction, pedestrians evaluate various attractions and select the attraction that can most stimulate or attract them. (b) Successful attraction, when the attraction exceeds the original driving force of the pedestrians, the temporary goals and trajectories of the pedestrians will change accordingly.

[0079] To simulate this situation, a comprehensive force criterion that combines attraction with the original SFM is proposed. That is, at each time step, the attraction and driving force of pedestrians are compared. If the attraction is less than the driving force, it is not considered. On the contrary, if the attraction is greater than the driving force, the latter will be temporarily overwritten. In addition, once a store is visited, its attraction is set to zero to prevent further influence. Therefore, the social force model based on attraction potential energy can be used to characterize in the above formula (12), which can be expressed by the following formula (23) to formula (30):

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087] Among them, represents the effective force value.

[0088] Here, is the binary matching parameter, and its calculation formula is:

[0089] On this basis, the embodiments of the present disclosure provide a method for optimizing the layout of shops in the functional intersection area of a commercial complex, which can be executed by a terminal or by a chip applied to the terminal.

[0090] Exemplarily, the above-mentioned terminal may include one or more of a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), and a wearable device based on augmented reality (AR) and / or virtual reality (VR) technology. The exemplary embodiments of the present disclosure do not make specific limitations thereto.

[0091] Figure 1 shows a schematic flowchart of the method for optimizing the layout of shops in the functional intersection area of a commercial complex provided by the exemplary embodiments of the present disclosure. As Figure 1 shown, the method for optimizing the layout of shops in the functional intersection area of a commercial complex includes: S101, obtaining a pre-constructed macro optimization model based on shop attributes and a micro optimization model based on pedestrian attributes; among them, the macro optimization model is used to optimize the total attraction of shops and the unbalanced passenger flow penalty in the functional intersection area of a commercial complex, and the micro optimization model is used to optimize the passenger flow density of channels in the functional intersection area of a commercial complex; S102, respectively determining the macro optimization objective and constraint conditions of the macro optimization model, and the micro optimization objective of the micro optimization model; S103, using the macro optimization model, the macro optimization objective and the constraint conditions to determine multiple candidate shop layouts; S104. Using the micro-optimization model and the micro-optimization objective, determine the target store layout from multiple candidate store layouts, so as to use the target store layout to layout the stores in the functional intersection area of the commercial complex.

[0092] Specifically, as can be seen from the foregoing, according to the diversity of the functions of the commercial complex in the embodiments of the present disclosure, heterogeneous pedestrians with various travel purposes will flow randomly inside. By optimizing the layout, more potential customers can be attracted to become in-store customers, while avoiding the phenomenon of uneven passenger flow between different stores. Based on this, the embodiments of the present disclosure construct a macro-optimization model based on store attributes, and under the constraints of the macro-optimization objective and constraints, use the macro-optimization model to preliminarily optimize the store layout to obtain multiple candidate store layouts.

[0093] The embodiments of the present disclosure construct a micro-optimization model based on pedestrian attributes to simulate the attraction effect of different stores on heterogeneous pedestrians, and truly simulate the movement process and behavior of heterogeneous pedestrians in the functional intersection area. Based on this, under the guidance of the micro-optimization objective, use the micro-optimization model to further optimize the store layout, and determine the target store layout from multiple candidate store layouts, so as to use the target store layout to layout the stores in the functional intersection area of the commercial complex.

[0094] According to the technical solution of the exemplary embodiment of the present disclosure, by obtaining the pre-constructed macro-optimization model based on store attributes and the micro-optimization model based on pedestrian attributes; wherein, the macro-optimization model is used to optimize the total attraction of stores and the penalty for uneven passenger flow in the functional intersection area of the commercial complex, and the micro-optimization model is used to optimize the passenger flow density of the channels in the functional intersection area of the commercial complex; respectively determine the macro-optimization objective and constraints of the macro-optimization model, and the micro-optimization objective of the micro-optimization model; use the macro-optimization model, the macro-optimization objective and constraints to determine multiple candidate store layouts; use the micro-optimization model and the micro-optimization objective to determine the target store layout from multiple candidate store layouts, so as to use the target store layout to layout the stores in the functional intersection area of the commercial complex, which can ensure the rationality of the regional division in terms of the internal functional space, attract more non-shopping pedestrians into the stores, and increase the overall number of pedestrians entering the stores; in terms of traffic planning, induce the pedestrian flow line, avoid internal traffic congestion, reduce cross-interference, and improve the operation efficiency of the commercial complex.

[0095] In some embodiments, the method may further include: Based on store attributes, determine the total attraction of stores in the functional intersection area of the commercial complex; Obtain the penalty weight for unbalanced passenger flow, the passenger flow ratio limit, and the initial predicted attractiveness of the store, and determine the penalty for unbalanced passenger flow of the store in the functional intersection area of the commercial complex based on the total attractiveness of the store in the functional intersection area of the commercial complex, the penalty weight for unbalanced passenger flow, the passenger flow ratio limit, and the initial predicted attractiveness of the store. Construct a macro-optimization model based on the total attractiveness of the store in the functional intersection area of the commercial complex and the penalty for unbalanced passenger flow. Specifically, the macro-optimization model is constructed based on store attributes, which can specifically include two parts, namely the total attractiveness of the store and the penalty for unbalanced passenger flow of the store.

[0096] Exemplarily, the macro-optimization model is represented by the following formula:

[0097] where \(I = \{1, 2,\cdots, n\}\) represents the set of stores, \(J=\{1, 2,\cdots, m\}\) represents the set of store locations, \(x_{ij}\) ij \(\in \{0, 1\}\) indicates whether store \(i\) is assigned to location \(j\), represents the attractiveness of store \(i\) at location \(j\), represents the penalty weight for unbalanced passenger flow, represents the passenger flow ratio limit, represents the initial predicted attractiveness of store \(i\) at location \(j\).

[0098] In the above formula (1), the first term is the attractiveness term, which is used to characterize the total attractiveness of the stores in the functional intersection area of the commercial complex under the optimized layout; the second term is the penalty term, which is used to characterize the penalty for unbalanced passenger flow of the stores in the functional intersection area of the commercial complex under the optimized layout.

[0099] Exemplarily, the above store attributes may include the scale, type, location, brand level, and complementarity of the store; the attractiveness of store \(i\) at location \(j\) can be calculated by the following formula:

[0100] where represents the scale of store \(i\), which is equal to the area of location \(j\) , represents the type of store \(i\), represents the brand level of store \(i\), represents the location attractiveness of store \(i\) at location \(j\), represents the distance Boolean variable, which is used to characterize the complementary effect between store \(i\) at location \(j\) and store \(n\). If \(>\) , \( = 0\), Denote the distance between the central coordinate of position j and store n, Denote the influence radius of store i, Denote the complementary weight between store i and store n, Denote the initial predicted attractiveness of store n at position m, , Denote the saturation effect function of store i, Denote the number of stores of the same type within the influence radius of store i at position j, and α>0 denotes the saturation rate parameter, Denote the purchase desire adjustment parameter, ∈[0,1]; The location attractiveness of store i at position j is expressed by the following formula:

[0101] where, Denote the set of entrances e of the functional intertwining area, Denote the set of elevators l,( , ) denote the coordinates of position j,( , ) denote the coordinates of entrance e,( , ) denote the coordinates of elevator l.

[0102] In some embodiments, the macroscopic optimization goal is to maximize the total attractiveness of stores in the functional intertwining area of the commercial complex; it can be denoted by maxZ.

[0103] The above constraints can be expressed by the following formula:

[0104]

[0105]

[0106]

[0107]

[0108] where, Denote the area of position j, Denote the maximum passenger flow carrying capacity of store i, Denote the type of store i, Denote the total attractiveness of stores in the functional intertwining area.

[0109] Here, for the relevant content of the above formulas (2) to (6), please refer to the previous text specifically, and it will not be elaborated here.

[0110] In some embodiments, the microscopic optimization objective is to minimize the passenger flow density of the passageways in the functional intersection area of the commercial complex; The method may further include: Obtain the range of the passageway, the area of the passageway, the pedestrian number indication function, and the pedestrian position update function in the functional intersection area of the commercial complex; Based on the range of the passageway, the area of the passageway, the pedestrian number indication function, and the pedestrian position update function in the functional intersection area of the commercial complex, construct a microscopic optimization model; Specifically, the microscopic optimization model is constructed based on pedestrian attributes, and the pedestrian attributes here may be the pedestrian heterogeneity in the foregoing text.

[0111] Exemplarily, the microscopic optimization model can be represented by the following formula:

[0112]

[0113]

[0114] Among them, represents the passenger flow density of the passageway in the functional intersection area, C represents the range of the passageway in the functional intersection area, represents the vertex coordinates of the passageway, T represents the total time step, P represents the total number of pedestrians in the functional intersection area, represents the area of the passageway, represents the indication function of the number of pedestrians in the passageway, represents the position of pedestrian p at time t, represents the position of pedestrian p at time step t + 1, represents the pedestrian position update function, represents the actual speed of pedestrian p at time t.

[0115] In some embodiments, the pedestrian position update function may be a social force model based on attractive potential energy; The method may further include: Obtain the driving force of the pedestrians in the functional intersection area of the commercial complex, the interaction force between the pedestrians and other pedestrians, the repulsive force between the pedestrians and the inner walls of the passageway, and the attractive potential energy between the shops and the pedestrians; Based on the driving force of the pedestrians in the functional intersection area of the commercial complex, the interaction force between the pedestrians and other pedestrians, the repulsive force between the pedestrians and the inner walls of the passageway, and the attractive potential energy between the shops and the pedestrians, construct a social force model based on attractive potential energy.

[0116] Specifically, in the functional intersection area of a commercial complex, the movement of pedestrians is affected by multiple forces, which can specifically include: the driving force of pedestrians, the interaction force between pedestrians and other pedestrians, the repulsive force between pedestrians and the inner wall of the passage, and the attractive potential energy between shops and pedestrians.

[0117] After obtaining the driving force of pedestrians, the interaction force between pedestrians and other pedestrians, the repulsive force between pedestrians and the inner wall of the passage, and the attractive potential energy between shops and pedestrians, a social force model based on attractive potential energy can be constructed based on the driving force of pedestrians, the interaction force between pedestrians and other pedestrians, the repulsive force between pedestrians and the inner wall of the passage, and the attractive potential energy between shops and pedestrians in the functional intersection area of the commercial complex.

[0118] Exemplarily, the social force model based on attractive potential energy is represented by the following formula:

[0119]

[0120]

[0121]

[0122]

[0123]

[0124]

[0125]

[0126] Among them, represents the mass of pedestrian p, represents the driving force of pedestrian p, represents the interaction force between pedestrian p and other pedestrian q, represents the repulsive force between pedestrian p and the inner wall w of the passage, represents the shop and pedestrian between the attractive potential energy, represents the actual speed of pedestrian p, represents the actual speed of other pedestrian q, represents the desired speed of pedestrian p at time t, represents the unit vector pointing to the desired target at time t, τ represents a certain characteristic time, represents the strength of the social interaction force, represents the range of the social interaction force, and are all constants represents the sum of the radii of pedestrian p and other pedestrian q represents the radius of pedestrian p represents the distance between the centroid of pedestrian p and other pedestrian q represents the distance between the centroid of pedestrian p and wall w represents the normalized vector from other pedestrian q to pedestrian p represents the normalized vector from wall w to pedestrian p represents the body compression coefficient represents the sliding friction coefficient represents the tangential direction of pedestrian p and other pedestrian q represents the tangential direction of pedestrian p and wall w, Q represents the total number of pedestrians, and W represents the total number of walls represents whether pedestrians are not in contact with each other or in contact with the wall represents the position of pedestrian p at time t represents the position of pedestrian p at the initial time represents the effective force value represents the store on the pedestrian attraction represents the pedestrian pointing to the store normalized vector represents the weight parameter to ensure the consistency of the unit magnitude, with a value of , represents the store scale represents the store guidance coefficient represents the store and the pedestrian distance between represents the store and the pedestrian matching degree between represents the range constraint for determining whether the store is within the pedestrian's attention range represents the store and the pedestrian angle between represents the angle of the pedestrian's attention range represents the depth of the pedestrian's attention range

[0127] Based on this, the exemplary embodiments of the present disclosure provide a specific application embodiment to specifically illustrate the method of the embodiments of the present disclosure.

[0128] The multi-objective optimization problem of store layout is essentially a two-stage optimization process. According to the attributes of the stores, various feasible store layouts are proposed. Then, the pedestrian simulation results are used to evaluate these strategies to determine the final layout plan. And the optimization process involves many parameters that need to be calibrated. Therefore, the implementation methods include data collection, calibrating the parameters of the optimization model with the collected data, and the optimization algorithm. The specific implementation steps are as follows: Step 1: Data collection To analyze the travel behavior of heterogeneous pedestrians in the FIA and quantify the parameters of the optimization model, the B1 floor of a certain international trade center was selected as the research object, and data collection was carried out through video recording, pedestrian tracking, and questionnaire surveys.

[0129] The Guomao Mall is located in the central business district of a certain city, covering an area of 230,000 square meters, including a shopping center and office buildings. In short, a certain international trade center is a very typical commercial complex, containing pedestrians with various travel purposes such as commuting, shopping, and business. At the same time, the Guomao Station of Subway Line 1 and Line 10 in a certain city is located below this international trade center, and its entrances and exits are connected to the B1 floor of the shopping center. The selected area represents a typical FIA, which not only includes 122 stores of the above 8 types but also has multiple entrances and exits connecting the shopping center, office space, hotel area, subway line, and external environment.

[0130] The activities of pedestrians have great randomness and variability. The same pedestrian will show different behaviors depending on whether it is a weekday or weekend, peak hour or off-peak hour. Therefore, in order to minimize the influence of external factors and explore the attractiveness of stores to pedestrians, 8 volunteers were recruited for data collection. From December 2, 2024 (Monday) to December 8, 2024 (Sunday), the volunteers used their mobile phones to record the pedestrian travel behavior in the research area at eight designated corners during two specific time periods every day: 3:00 - 4:00 pm and 6:00 - 7:00 pm.

[0131] Since it is not allowed to install cameras in a certain international trade center, this study mainly relies on the observation method to analyze the pedestrian behavior between different stores. Therefore, the requirement for the video resolution is relatively low, and mobile phone recording is sufficient. In addition, due to limited personnel, the video cannot cover the entire research area. If a pedestrian leaves all video frames, it is defaulted that they leave from the mall entrance. At the same time, their behavior before that is also regarded as valid data.

[0132] In addition to video recording, the volunteers were also required to conduct questionnaire surveys from 4:00 - 6:00 pm every day, including basic information, movement preferences between stores (which can be the complementary weights between stores, )), and the desire to purchase after shopping ( ), the matching degree between shops and pedestrians ( ), the effectiveness of shop guidance measures (the guidance coefficient of the shop, ) and other major issues. To facilitate data collection, an electronic questionnaire was selected. Pedestrians could enter the survey through a quick response code and complete the questionnaire at their convenience. Finally, a total of 429 questionnaires were collected.

[0133] Step 2: Parameter calibration According to the proposed optimization model, four parameters need to be calibrated, namely the complementary weight between shop i and n , the purchase desire adjustment parameter , the matching degree between pedestrians and shops and the guidance coefficient of the shop .

[0134] (1) Complementary relationship between different shops Based on the analysis of pedestrians' in-store behaviors in each video segment, a quantitative framework for the complementary relationship between different shops was initially established, which can be divided into the following four types: Highly complementary shops: Exchange 15% of customers (marked as ); Moderately complementary shops: Exchange 10% of customers (marked as ); Lowly complementary shops: Exchange 5% of customers (marked as ); Non-complementary shops: Exchange 0 customers (marked as ).

[0135] In the questionnaire survey, the Likert scale was used to quantify pedestrians' choices. After pedestrians visited type shops (without shopping), the desire strength to enter different types of surrounding shops was defined as no desire, slight desire, some desire, moderate desire, strong desire, and very strong desire, and was assigned values from 0 to 5 points. After normalization, the complementary relationships between different types of shops are summarized in Table 1, which can be used to calculate the complementary weight matrix and between shops in practical applications. .

[0136] Table 1 Complementary relationships between different types of shops

[0137] (2) Purchase desire adjustment parameter This embodiment of the present disclosure investigated pedestrians in specific types of shops The desire to enter similar stores around after shopping is also divided into six levels, from no desire to very strong, with scores ranging from 0 to 5. Based on the normalized questionnaire results, the purchase desire adjustment parameters (1-δn) for different types of stores are obtained as follows:

[0138] (3) Matching degree between shops and pedestrians Similarly, the disclosed embodiment also investigates the pedestrians entering the The desire of the type of shop is defined, and the same six desire levels are defined. Among them, the embodiment of the disclosure ignores the differences between shops, and the final result only corresponds to the type of shop; in addition, the embodiment of the disclosure believes that gender has a greater impact on the matching degree, so gender is distinguished in the statistical analysis, and the matching degree matrix is ​​shown on the left side of Table 2.

[0139] Table 2 Matching degree and bootstrap coefficient matrix

[0140] Another interesting finding is that men have lower overall desire than women, meaning that men are less likely to be attracted. Therefore, to increase the number of customers in your store, it would be more effective to attract female customers.

[0141] (4) The guiding role of shops In addition, the disclosed embodiment also investigated the impact of three types of guidance on pedestrians, which were defined as six levels: very disgusting, disgusting, no impact, interested, and very interested, and recorded as -2 to 2 points respectively. There are many interesting points, such as pedestrians have different feelings about different guidance, and most pedestrians still think that guidance plays a positive role or has no effect. Compared with visual guidance (propaganda and events), pedestrians are more disgusted with voice guidance (hawking), and women are more easily attracted by guidance than men.

[0142] Step 3: Algorithm Description Generally speaking, the model solution process can be divided into two steps. In the first step, a macro optimization model is used to search for the layout of the local optimization solution. That is, all shops are randomly placed in different locations, and the total shop attractiveness of the current layout is calculated. Then, by adjusting the shop positions, the total attractiveness of the new layout and the old layout is compared, and the layout with higher attractiveness is retained. If the attractiveness of the two layouts is the same, both layouts are retained, and then the next round of adjustments is carried out. This is repeated until the layout with the highest attractiveness is found.

[0143] Step 2: Based on the multiple layout solutions obtained in Step 1, further verification is carried out using the simulation model. Simulate the pedestrian behavior under different layouts, and calculate the pedestrian density of the passage under each layout according to the simulation results. Finally, by comparing the passage densities of different layouts, select the layout with the smallest density as the final layout solution.

[0144] In the embodiment of the present disclosure, the greedy-based brute-force search algorithm is used to solve in the first step, and the social force model based on attractive potential energy is used to simulate the pedestrian density in the second step, as shown in Algorithm 1.

[0145] For example, Algorithm 1: Macro to Micro Shop Location Optimization Algorithm and Simulation: Input: I: Shops; J: Locations; Entr, Elev: Entrance, Elevator; Attributes: 、 、 ; Parameters: ; Initial attraction ; Total number of pedestrians N.

[0146] Output: Final shop location allocation index ; Total attraction of shops and passenger flow density of the passage .

[0147] Step1. Step 1: Shop location optimization; Step2. Generate initial random feasible solutions that satisfy ; Step3. Randomly initialize for all shops; Step4. When not converged, execute Step5~Step8; Step5. Do for : Step6. Calculate :

[0148] Step7. End; Step8. Optimization:

[0149] According to dynamically update ; Step9. End; Step10. Store all candidate solutions with the maximum value; Step11. Step 2: Passage density optimization; Step12. Operate on the candidate with the maximum value; Step13. Use the social force model based on attractive potential energy to simulate the behavior and trajectory of pedestrians:

[0150]

[0151]

[0152] Calculate the number of pedestrians in the passageway:

[0153] Calculate the average passenger flow density:

[0154] Step14. End; Step15. Select the solution with the minimum average passenger flow density ; Step16. Output: The final , and .

[0155] Step Four: Numerical and Simulation Experiments Verify the effectiveness of the proposed optimization model through numerical and simulation experiments. The numerical and simulation experiments are respectively implemented in MATLAB2016b and Anylogic Professional 8.8.5 with JAVA 2.0, and run on an Intel (R) Core (TM) i5-10210U 1.60 GHZ PC with 16 GB of memory. The optimization model is tested based on the data of the B1 floor of this international business center mall.

[0156] In the numerical experiment, by repeatedly evaluating the random adjustment coefficient of the shop locations during the iterative process, a standard deviation of 0.05 is selected as the random offset. According to Hypothesis 1 and the constraints, without changing the locations of public infrastructure, optimize the layout of 122 shops. Each iteration is set to run 50,000 times and repeated three times to observe the stability of the algorithm and obtain multiple feasible solutions. To improve the operation efficiency, in the numerical experiment, the intermediate values and the total shop attraction are rounded to two decimal places.

[0157] ​In the simulation experiment, pedestrians arriving at the connection entrance of the mall and subway line are set to follow a normal distribution N[20, 1] (p / min), and pedestrians arriving at the elevator are set to follow a normal distribution N[15, 1] (p / min). In addition, 200 pedestrians are initially set to move within the research area, with a male-female ratio of 1:1. According to the results of the numerical experiment, each layout plan is simulated for 60 minutes and repeated 3 times to obtain the pedestrian density of the passageway, and the optimal layout plan is obtained through comparison.

[0158] (1) Numerical experiment For the original layout of the research area, the total attraction of the shops is 60.34. At the same time, after the program runs three times (2, 3, and 2 layouts are iterated each time), 7 optimized layouts are obtained, and the total attractions of the shops are 67.62, 67.54, and 67.71 respectively. The maximum fluctuation result of the shop attraction is 0.3%, which proves the stability of the algorithm. Therefore, the two optimized layouts with the largest total shop attraction (Optimization Plan A and Optimization Plan B) are selected for subsequent analysis and simulation experiments, and these two optimized layout plans follow different design principles.

[0159] By comparing the two layout plans, it can be found that Optimization Plan A pays more attention to the complementarity between shops of the same type, while Optimization Plan B pays more attention to the complementarity between shops of different types. For example, both plans relocate the "Family and Children" shops with low traffic. The former concentrates them in one area for easy comparison shopping, increasing the number of in-store consumers. However, this approach also reduces the possibility of consumers visiting shops in other areas. The latter distributes them in different areas according to their complementarity with dessert and beverage shops and lifestyle shops, providing more potential consumers for other types of shops.

[0160] In addition, although some areas in both plans accommodate the same type of shops, the specific shops assigned to each location are different. Therefore, it is challenging to determine the most suitable layout for the research area only through numerical simulation. Therefore, the second step of the algorithm needs to be introduced to conduct microscopic pedestrian simulation experiments under different layouts.

[0161] (2) Simulation experiment Table 3 shows the simulation parameters for setting AP-SFM in the embodiments of the present disclosure.

[0162] Table 3 Parameter settings of AP-SFM

[0163] Based on the results of three simulations for each layout plan, the optimization effects can be compared from both qualitative and quantitative perspectives. On the one hand, according to the comparison of static local density, it can be qualitatively seen that the two optimized layout plans not only avoid unreasonable congestion but also reduce the pedestrian density in the aisles. In other words, without changing objective conditions such as pedestrian arrival rate, pedestrian heterogeneity, or store types, simply adjusting the mall layout can effectively encourage more pedestrians to enter the stores.

[0164] On the other hand, Figure 2 The figure shows the change diagram of the overall density of the aisles under three layout plans provided by the embodiments of the present disclosure. As Figure 2 shown, in the original layout, due to the ineffective consideration of the complementarity between stores, pedestrians need to spend a lot of time walking in the aisles to find new stores of interest after completing their shopping. Therefore, as more and more pedestrians come to the research area, the overall density of the aisles shows an upward trend.

[0165] In contrast, Optimization Plan A emphasizes the complementarity between stores of the same type, enabling pedestrians to quickly enter stores of the same type for comparison shopping. However, when their shopping needs in this area are met, they often wander aimlessly in the aisles or look for exits to leave the mall. This behavior causes the aisle density of Optimization Plan A to increase sharply when the simulation time reaches 1500s. In addition, Optimization Plan B pays more attention to the complementarity between different types of stores, which prompts pedestrians to be attracted by various types of stores and repeatedly perform in-store behaviors. Among them, the scattered layout of stores of the same type increases the walking time of pedestrians in the aisles and also delays the time point when pedestrians fully meet their shopping needs. Therefore, the gradual growth time of the aisle density in the simulated Optimization Plan B is longer than that of Optimization Plan A, which also results in a later occurrence of the density surge than Optimization Plan A.

[0166] Both optimization plans have increased the in-store frequency of pedestrians, Figure 3 which is intuitively shown. Figure 3 The figure shows the comparison diagram of the total in-store traffic of various types of stores under three layout plans provided by the embodiments of the present disclosure. As Figure 3 shown, calculate the total in-store traffic of each store in the simulation and summarize the results by store type. Obviously, with the total pedestrian traffic remaining unchanged, both optimized layouts effectively increase the total in-store traffic of various types of stores.

[0167] In addition, the embodiments of the present disclosure also calculated the average aisle density of the original plan, Optimization Plan A, and Optimization Plan B, which are 0.161 p / m 2 , 0.141 p / m 2 and 0.137 p / m 2 . Therefore, in this case, Optimization Plan B is more suitable for implementation.

[0168] The above mainly introduces the solutions provided by the embodiments of the present disclosure. It can be understood that, in order to implement the above functions, an electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0169] The embodiments of the present disclosure can divide the functional units of the electronic device according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of modules in the embodiments of the present disclosure is illustrative, only a logical functional division, and there can be other division methods in actual implementation.

[0170] In the case of dividing each functional module corresponding to each function, an exemplary embodiment of the present disclosure provides a layout optimization device for shops in the functional intersection area of a commercial complex. The layout optimization device for shops in the functional intersection area of a commercial complex can be a terminal or a chip applied to a terminal. Figure 4 FIG. shows a schematic structural diagram of a layout optimization device for shops in the functional intersection area of a commercial complex provided by an exemplary embodiment of the present disclosure. As Figure 4 shown, the device 400 includes: An acquisition module 401, configured to acquire a pre-constructed macroscopic optimization model based on shop attributes and a microscopic optimization model based on pedestrian attributes; wherein, the macroscopic optimization model is used to optimize the total attraction of shops and the unbalanced passenger flow penalty in the functional intersection area of the commercial complex, and the microscopic optimization model is used to optimize the passenger flow density of the channels in the functional intersection area of the commercial complex; A processing module 402, configured to respectively determine the macroscopic optimization objective and constraints of the macroscopic optimization model, and the microscopic optimization objective of the microscopic optimization model; The processing module 402 is further configured to use the macroscopic optimization model, the macroscopic optimization objective, and the constraints to determine a plurality of candidate shop layouts; The processing module 402 is further configured to determine a target store layout from the multiple candidate store layouts by using the micro-optimization model and the micro-optimization objective, so as to perform store layout on the functional intersection area of the commercial complex by using the target store layout.

[0171] In some embodiments, the processing module 402 is further configured to determine the total attraction of the stores in the functional intersection area of the commercial complex based on the store attributes; The obtaining module 401 is further configured to obtain the penalty weight of unbalanced passenger flow, the passenger flow ratio limit, and the initial predicted attraction of the stores; The processing module 402 is further configured to determine the penalty for unbalanced passenger flow of the stores in the functional intersection area of the commercial complex based on the total attraction of the stores in the functional intersection area of the commercial complex, the penalty weight of unbalanced passenger flow, the passenger flow ratio limit, and the initial predicted attraction of the stores; The processing module 402 is further configured to construct the macro-optimization model based on the total attraction of the stores in the functional intersection area of the commercial complex and the penalty for unbalanced passenger flow; The macro-optimization model is represented by the following formula:

[0172] where I = {1, 2..., n} represents the set of stores, J = {1, 2..., m} represents the set of store locations, and x ij ∈ {0, 1} indicates whether store i is assigned to location j, represents the attraction of store i at location j, represents the penalty weight of unbalanced passenger flow, represents the passenger flow ratio limit, represents the initial predicted attraction of store i at location j; The store attributes include the scale, type, location, brand level, and complementarity of the store; the attraction of store i at location j is calculated by the following formula:

[0173] where represents the scale of store i, which is equal to the area of location j , represents the type of store i, represents the brand level of store i, represents the location attraction of store i at location j, represents a distance boolean variable used to characterize the complementary effect between store i at location j and store n. If > , = 0, represents the distance between the central coordinate of position j and store n, represents the influence radius of store i, represents the complementary weight between store i and store n, represents the initial predicted attractiveness of store n at position m, , represents the saturation effect function of store i, represents the number of stores of the same type within the influence radius of store i at position j, and α > 0 represents the saturation rate parameter, represents the purchase desire adjustment parameter, ∈[0, 1]; The location attractiveness of store i at position j is represented by the following formula:

[0174] where, represents the set of entrances e of the functional intersection area, represents the set of elevators l, ( , ) represents the coordinates of position j, ( , ) represents the coordinates of entrance e, ( , ) represents the coordinates of elevator l.

[0175] In some embodiments, the macro optimization objective is to maximize the total attractiveness of the stores in the functional intersection area of the commercial complex; The constraint conditions are represented by the following formula:

[0176]

[0177]

[0178]

[0179]

[0180] where, represents the area of position j, represents the maximum passenger flow carrying capacity of store i, represents the type of store i, represents the total attractiveness of the stores in the functional intersection area.

[0181] In some embodiments, the micro optimization objective is to minimize the passenger flow density of the channels in the functional intersection area of the commercial complex; The obtaining module 401 is further configured to obtain the range of the passageway, the area of the passageway, the pedestrian quantity indication function, and the pedestrian position update function in the functional intersection area of the commercial complex; The processing module 402 is further configured to construct the microscopic optimization model based on the range of the passageway, the area of the passageway, the pedestrian quantity indication function, and the pedestrian position update function in the functional intersection area of the commercial complex; The microscopic optimization model is represented by the following formula:

[0182]

[0183]

[0184] Wherein, represents the passenger flow density of the passageway in the functional intersection area, C represents the range of the passageway in the functional intersection area, represents the vertex coordinates of the passageway, T represents the total time step, P represents the total number of pedestrians in the functional intersection area, represents the area of the passageway, represents the pedestrian quantity indication function of the passageway, represents the position of pedestrian p at time t, represents the position of pedestrian p at time step t + 1, represents the pedestrian position update function, represents the actual speed of pedestrian p at time t.

[0185] In some embodiments, the pedestrian position update function is a social force model based on attractive potential energy; The obtaining module 401 is further configured to obtain the driving force of the pedestrians in the functional intersection area of the commercial complex, the interaction force between the pedestrians and other pedestrians, the repulsive force between the pedestrians and the inner wall of the passageway, and the attractive potential energy between the shops and the pedestrians; The processing module 402 is further configured to construct the social force model based on attractive potential energy based on the driving force of the pedestrians in the functional intersection area of the commercial complex, the interaction force between the pedestrians and other pedestrians, the repulsive force between the pedestrians and the inner wall of the passageway, and the attractive potential energy between the shops and the pedestrians.

[0186] In some embodiments, the social force model based on attractive potential energy is represented by the following formula:

[0187]

[0188]

[0189]

[0190]

[0191]

[0192]

[0193]

[0194] Among them, represents the mass of pedestrian p, represents the driving force of pedestrian p, represents the interaction force between pedestrian p and other pedestrian q, represents the repulsive force between pedestrian p and the inner wall w of the passage, represents the store and pedestrian the attractive potential energy between them, represents the actual speed of pedestrian p, represents the actual speed of other pedestrian q, represents the expected speed of pedestrian p at time t, represents the unit vector pointing to the expected target at time t, τ represents a certain characteristic time, represents the strength of the social interaction force, represents the range of the social interaction force, and are both constants, represents the sum of the radii of pedestrian p and other pedestrian q, represents the radius of pedestrian p, represents the distance between the centroid of pedestrian p and other pedestrian q, represents the distance between the centroid of pedestrian p and the wall w, represents the normalized vector pointing from other pedestrian q to pedestrian p, represents the normalized vector pointing from the wall w to pedestrian p, represents the body compression coefficient, represents the sliding friction coefficient, represents the tangential direction between pedestrian p and other pedestrian q, represents the tangential direction between pedestrian p and the wall w, Q represents the total number of pedestrians, W represents the total number of walls, represents whether pedestrians are non - contacting or contacting the wall, represents the position of pedestrian p at time t, represents the position of pedestrian p at the initial time, Represents the effective force value; Represents a store For pedestrians Attraction; Represents pedestrians Normalized vector pointing to the store ; Represents a weight parameter to ensure unit magnitude consistency, with a value of , Represents the scale of the store , Represents the guiding coefficient of the store , Represents the store And pedestrians Distance between; Represents the store And pedestrians Degree of matching between; Represents a range constraint for determining whether the store is within the pedestrian's attention range, Represents the store And pedestrians Angle between; Represents the angle of the pedestrian's attention range, Represents the depth of the pedestrian's attention range.

[0195] The embodiments of the present disclosure also provide an electronic device, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the above method disclosed in the embodiments of the present disclosure.

[0196] Figure 5 Shows a schematic structural diagram of the electronic device provided by the exemplary embodiments of the present disclosure. As Figure 5 Shown, the electronic device 500 includes at least one processor 501 and a memory 502 coupled to the processor 501. The processor 501 can execute the corresponding steps in the above method disclosed in the embodiments of the present disclosure.

[0197] The above-mentioned processor 501 can also be referred to as a Central Processing Unit (CPU). It can be an integrated circuit chip with the ability to process signals. Each step in the above methods disclosed in the embodiments of the present disclosure can be completed by the integrated logic circuit in hardware or instructions in software form in the processor 501. The above-mentioned processor 501 can be a general-purpose processor, a Digital Signal Processor (DSP), an ASIC, a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present disclosure can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module can be located in the memory 502, such as a random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, and other mature storage media in the art. The processor 501 reads the information in the memory 502 and combines its hardware to complete the steps of the above method.

[0198] In addition, when various operations / processes according to the present disclosure are implemented through software and / or firmware, a program constituting the software can be installed from a storage medium or a network into a computer system having a dedicated hardware structure, such as Figure 6 the computer system 600 shown. When various programs are installed in the computer system, it can execute various functions, including functions such as those described above. Figure 6 The structural schematic diagram of a computer system provided by an exemplary embodiment of the present disclosure is shown.

[0199] The computer system 600 is intended to represent various forms of digital electronic computer devices, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, 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 disclosure described and / or claimed herein.

[0200] As Figure 6As shown, computer system 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0201] Multiple components in the computer system 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 can be any type of device capable of inputting information into the computer system 600. The input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function controls of the electronic device. The output unit 607 can be any type of device capable of presenting information and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 can include, but is not limited to, magnetic disks and optical disks. The communication unit 609 allows the computer system 600 to exchange information / data with other devices through a network such as the Internet and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset. For example, a BluetoothTM device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0202] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 executes the various methods and processes described above. For example, in some embodiments, the above-described methods disclosed in the embodiments of the present disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device via the ROM 602 and / or the communication unit 609. In some embodiments, the computing unit 601 can be configured to execute the above-described methods disclosed in the embodiments of the present disclosure by any other appropriate means (such as by means of firmware).

[0203] Embodiments of the present disclosure also provide a computer-readable storage medium. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the above methods disclosed in the embodiments of the present disclosure.

[0204] The computer-readable storage medium in the embodiments of the present disclosure may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The above computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specifically, the above computer-readable storage medium may include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0205] The above computer-readable medium may be included in the above electronic device; or may exist separately without being assembled into the electronic device.

[0206] Embodiments of the present disclosure also provide a computer program product, including a computer program, wherein when the computer program is executed by a processor, the above methods disclosed in the embodiments of the present disclosure are implemented.

[0207] In the embodiments of the present disclosure, computer program code for performing the operations of the present disclosure can be written in one or more programming languages or combinations thereof. The above programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network (including a local area network (LAN) or a wide area network (WAN)), or can be connected to an external computer.

[0208] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0209] The modules, components, or units described in the embodiments of the present disclosure can be implemented in software or in hardware. Among them, the names of the modules, components, or units do not, in some cases, constitute a limitation on the modules, components, or units themselves.

[0210] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0211] The above description is only some embodiments of the present disclosure and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present disclosure.

[0212] Although some specific embodiments of the present disclosure have been described in detail by way of example, those skilled in the art should understand that the above examples are only for the purpose of illustration and not for the purpose of limiting the scope of the present disclosure. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for optimizing the layout of shops in the functional interweaving area of ​​a commercial complex, characterized in that: include: Obtain a pre-built macro optimization model based on store attributes and a micro optimization model based on pedestrian attributes; wherein the macro optimization model is used to optimize the total attractiveness of stores and the penalty for unbalanced passenger flow in the functional interweaving area of ​​the commercial complex, and the micro optimization model is used to optimize the passenger flow density of the passage in the functional interweaving area of ​​the commercial complex; Respectively determining the macro optimization objectives and constraints of the macro optimization model and the micro optimization objectives of the micro optimization model; Determine multiple candidate store layouts using the macro optimization model, the macro optimization goal and the constraint conditions; The micro-optimization model and the micro-optimization target are used to determine a target shop layout from the multiple candidate shop layouts, so as to use the target shop layout to carry out shop layout in the functional interweaving area of ​​the commercial complex.

2. The method according to claim 1, characterized in that The method further comprises: Based on the attributes of the shops, determining the total attractiveness of the shops in the functional interweaving area of ​​the commercial complex; Obtaining the penalty weight of unbalanced passenger flow, the passenger flow ratio limit and the initial predicted attractiveness of the shops, and determining the unbalanced passenger flow penalty for the shops in the functional interweaving area of ​​the commercial complex based on the total attractiveness of the shops in the functional interweaving area of ​​the commercial complex, the penalty weight of unbalanced passenger flow, the passenger flow ratio limit and the initial predicted attractiveness of the shops; Constructing the macro optimization model based on the total attractiveness of the shops in the functional interweaving area of ​​the commercial complex and the unbalanced passenger flow penalty; The macro optimization model is expressed by the following formula: Where I = {1, 2..., n} represents the set of shops, J = {1, 2..., m} represents the location set of shops, and x ij ∈{0,1} indicates whether shop i is assigned to location j, represents the attractiveness of store i at location j, represents the penalty weight of unbalanced passenger flow, Indicates passenger flow ratio limit, represents the initial predicted attractiveness of store i at location j; The store attributes include the store's size, type, location, brand level and complementarity; the attractiveness of the store i at location j is calculated by the following formula: in, Represents the size of store i, which is equal to the area of ​​location j , Indicates the type of shop i, represents the brand level of store i, represents the location attractiveness of store i at location j, Represents a distance Boolean variable, which is used to characterize the complementary effect between store i and store n at location j. If > , =0, represents the distance between the center coordinates of location j and shop n, represents the influence radius of shop i, represents the complementary weight between shop i and shop n, represents the initial predicted attractiveness of store n at location m, , represents the saturation effect function of shop i, represents the number of shops of the same type within the influence radius of shop i at location j, α>0 represents the saturation rate parameter, indicates the purchase desire adjustment parameter, ∈[0,1]; The location attractiveness of the store i at location j is expressed by the following formula: in, represents the set of entries e of the functional interweaving area, represents the set of elevators l, ( , ) represents the coordinates of position j, ( , ) represents the coordinates of the entrance e, ( , ) represents the coordinates of elevator l.

3. The method according to claim 2, characterized in that The macro optimization goal is to maximize the total attractiveness of the shops in the functional interweaving area of ​​the commercial complex; The constraint condition is expressed by the following formula: in, represents the area of ​​position j, represents the maximum passenger flow carrying capacity of shop i, Indicates the type of shop i, Represents the overall attractiveness of shops in the interwoven functional area.

4. The method according to claim 1, characterized in that The micro-optimization goal is to minimize the passenger flow density of the passage in the functional interweaving area of ​​the commercial complex; The method further comprises: Obtaining the range of the passage in the functional interweaving area of ​​the commercial complex, the area of ​​the passage, a pedestrian quantity indication function, and a pedestrian position update function; Constructing the micro-optimization model based on the range of the passage in the functional interweaving area of ​​the commercial complex, the area of ​​the passage, the pedestrian quantity indication function and the pedestrian position update function; The micro-optimization model is expressed by the following formula: in, represents the passenger flow density of the channel in the functional interweaving area, C represents the range of the channel in the functional interweaving area, represents the vertex coordinates of the channel, T represents the total time step, P represents the total number of pedestrians in the functional interweaving area, represents the area of ​​the channel, The indicator function representing the number of pedestrians in the channel, represents the position of pedestrian p at time t, represents the position of pedestrian p at time step t+1, represents the pedestrian position update function, represents the actual speed of pedestrian p at time t.

5. The method according to claim 4, characterized in that The pedestrian position update function is a social force model based on attractive potential energy; the method further includes: Obtaining the driving force of pedestrians in the functional interweaving area of ​​the commercial complex, the interaction force between the pedestrians and other pedestrians, the repulsive force between the pedestrians and the walls in the passage, and the attractive potential energy between the shops and pedestrians; Based on the driving force of pedestrians in the functional intersection area of ​​the commercial complex, the interaction force between the pedestrians and other pedestrians, the repulsive force between the pedestrians and the walls in the passage, and the attractive potential energy between the shops and pedestrians, the social force model based on attractive potential energy is constructed.

6. The method according to claim 5, characterized in that The social force model based on attractive potential is expressed by the following formula: in, represents the mass of pedestrian p, represents the driving force of pedestrian p, represents the interaction force between pedestrian p and other pedestrians q, represents the repulsive force between pedestrian p and the wall w in the channel, Indicates shop and pedestrians The attractive potential energy between represents the actual speed of pedestrian p, represents the actual speed of other pedestrians q, represents the expected speed of pedestrian p at time t, represents the unit vector pointing to the desired target at time t, τ represents a certain characteristic time, represents the strength of social interaction, represents the range of social interaction forces, and are constants, represents the sum of the radii of pedestrian p and other pedestrians q, represents the radius of pedestrian p, represents the distance between the centroid of pedestrian p and other pedestrians q, represents the distance between the center of mass of pedestrian p and wall w, represents the normalized vector from other pedestrian q to pedestrian p, represents the normalized vector from the wall w to the pedestrian p, represents the body compression coefficient, is the sliding friction coefficient, represents the tangent direction of pedestrian p and other pedestrians q, represents the tangent direction of pedestrian p and wall w, Q represents the total number of pedestrians, W represents the total number of walls, Indicates whether pedestrians are not touching each other or touching the wall. represents the position of pedestrian p at time t, represents the position of pedestrian p at the initial time, Indicates the effective force value; Indicates shop For pedestrians attractiveness; Indicates pedestrian Point to shop The normalized vector of ; Represents the weight parameter to ensure the consistency of unit magnitude, and its value is , Indicates shop The scale of Indicates shop The guidance coefficient, Indicates shop With pedestrians The distance between Indicates shop With pedestrians The matching degree between Represents a range constraint, which is used to determine whether a store is within the pedestrian's attention range. Indicates shop and pedestrians The angle between The angle representing the pedestrian's attention range, Indicates the depth of the pedestrian's attention range.

7. A layout optimization device for shops in the functional interweaving area of ​​a commercial complex, characterized in that: include: An acquisition module, used to acquire a pre-built macro optimization model based on store attributes and a micro optimization model based on pedestrian attributes; wherein the macro optimization model is used to optimize the total attractiveness of stores and the penalty for unbalanced passenger flow in the functional interweaving area of ​​the commercial complex, and the micro optimization model is used to optimize the passenger flow density of the passage in the functional interweaving area of ​​the commercial complex; A processing module, used to respectively determine the macro optimization target and constraint conditions of the macro optimization model and the micro optimization target of the micro optimization model; The processing module is also used to determine multiple candidate store layouts using the macro optimization model, the macro optimization target and the constraint conditions; The processing module is also used to use the micro-optimization model and the micro-optimization target to determine a target shop layout from the multiple candidate shop layouts, so as to use the target shop layout to arrange shops in the functional interweaving area of ​​the commercial complex.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images