Address determination method, device and equipment for commercial facilities based on big data

Abstract

The invention provides a commercial facility address determination method, device and equipment based on big data, and can be applied to the technical field of big data. The method comprises: determining a plurality of facility points of a plurality of types from a candidate area, the facility points including commercial facility points, residential facility points, and traffic facility points; determining attribute parameters of each facility point according to the online evaluation data of each facility point; based on a particle swarm algorithm, according to the attribute parameter, the position data and the living data of each facility point, target position data is determined from the candidate area, the target position data is used as the address of the target commercial facility, and a constraint function of the particle swarm algorithm comprises an attribute constraint item and a service quality constraint item; the attribute constraint item is determined according to the attribute parameter and a search area searched by the particle swarm algorithm each time, and the service quality constraint item is determined according to the living data and the search area.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to a method, device and equipment for determining the address of a commercial facility based on big data. Background Art

[0002] With the development of online technology, customers' shopping consumption is no longer limited to traditional physical spaces, but has expanded to new forms and channels of consumption on the Internet platform. Compared with the traditional in-person consumption model, this new form and new channel has higher service efficiency and radiation range, and reduces people's dependence on physical spaces. Therefore, the customers being served also have new choices and preferences. In this regard, merchants need to constantly adjust their site selection strategies to meet the rapidly changing needs of customers and ensure their own profits.

[0003] The site selection of commercial facilities needs to consider a variety of conditions, on the one hand to increase the profits of merchants, and on the other hand to bring service convenience to nearby residents. The site selection of experiential commercial facilities under online technology must not only consider the traditional built environment and population factors, but also the impact of the development of Internet technology on consumer consumption habits and commercial site selection.

[0004] In recent years, the impact of online technology has brought new development opportunities to urban commerce. Comprehensive online evaluation platforms or websites have replaced some of the service functions of physical businesses, expanding the actual service coverage of commercial facilities and reducing the time cost of customer consumption. This impact is also reflected in physical space. The location selection of some businesses in disadvantaged locations has been enhanced under the influence of Internet technology.

[0005] Therefore, the accuracy of the commercial facility address determination method based only on the actual geographical location is low. Summary of the invention

[0006] In view of this, the present invention provides a method, device and equipment for determining the address of commercial facilities based on big data.

[0007] One aspect of the present invention provides a method for determining the address of commercial facilities based on big data, comprising: determining multiple types of multiple facility points from a candidate area, wherein the facility points include commercial facility points, residential facility points and transportation facility points; determining the attribute parameters of each facility point based on the online evaluation data of each facility point; based on a particle swarm algorithm, determining target location data from the candidate area based on the attribute parameters, location data and residential data of each facility point, and using the target location data as the address of the target commercial facility, wherein the constraint function of the particle swarm algorithm includes attribute constraint items and service quality constraint items, the attribute constraint items are determined based on the attribute parameters and the search area of ​​each search of the particle swarm algorithm, and the service quality constraint items are determined based on the residential data and the search area.

[0008] According to an embodiment of the present invention, the constraint function includes a first constraint target, a second constraint target and a third constraint target. The priority of the first constraint target is higher than that of the second constraint target and the third constraint target. The first constraint target is used to maximize the difference between the attribute constraint value of the attribute constraint item and the service quality constraint value of the service quality constraint item. The second constraint target is used to maximize the attribute constraint value and the third constraint target is used to minimize the service quality constraint value.

[0009] According to an embodiment of the present invention, the attribute constraint value is determined according to the following method: in the process of iterating using the particle swarm algorithm, a search area is determined according to a preset search radius and a search center of the current iteration number, wherein the candidate area includes the search area; multiple target facility points within the search area are determined from multiple facility points; and the attribute parameters of each target facility point are summed to obtain the attribute constraint value.

[0010] According to an embodiment of the present invention, the service quality constraint value is determined according to the following method: determining at least one residential facility point from multiple target facility points; for each residential facility point, determining the number of commercial facility points within a search radius centered on the residential facility point, and determining the ratio of the number to the residential data of the residential facility point; determining the variance for the search area based on the respective ratios of at least one residential facility point, and using the variance as the service quality constraint value.

[0011] According to an embodiment of the present invention, the attribute parameters of each facility point are determined based on the online evaluation data of each facility point, including: determining at least one keyword related to each facility point based on the name of the facility point; for each keyword, determining the number of times the keyword is mentioned by integrating the online evaluation data of each facility point; determining a residential basic value, a traffic basic value, and a commercial basic value based on the number of times the keyword is mentioned; determining an additional evaluation value of each commercial facility point based on the online evaluation data of each commercial facility point; and determining the attribute parameters based on the residential basic value, the traffic basic value, the commercial basic value, and the additional evaluation value.

[0012] According to an embodiment of the present invention, determining the residential basic value, the traffic basic value, and the commercial basic value based on the number of mentions includes: determining an initial residential basic value based on the number of mentions of each keyword related to each residential facility point; normalizing the initial residential basic value to obtain a residential basic value; determining an initial traffic basic value based on the number of mentions of each keyword related to each traffic facility point; normalizing the initial traffic basic value to obtain a traffic basic value; and determining an initial commercial basic value based on the number of mentions of each keyword related to each commercial facility point; normalizing the initial commercial basic value to obtain a commercial basic value.

[0013] According to an embodiment of the present invention, determining the additional evaluation value of each of the commercial facility points based on the online evaluation data of each of the commercial facility points includes: determining the parameter value of the commercial facility point in at least one service dimension based on the online evaluation data, wherein the service dimension includes at least one of the following: number of evaluations, service ratings, number of shopping packages, and search order in the same category; within the service dimension, normalizing the parameter value of at least one commercial facility point to obtain a normalized parameter value; using the service dimension as a keyword, determining the number of times each service dimension is mentioned in the online evaluation data, and using the number of times the service dimension is mentioned as the respective weight of each service dimension; determining the additional evaluation value of each commercial facility point based on the normalized parameter value and weight of at least one service dimension.

[0014] According to an embodiment of the present invention, the target location data includes location data of the facility point located in the candidate area, or location data of a non-facility point.

[0015] Another aspect of the present invention provides an address determination device for commercial facilities based on big data, comprising: a first determination module, used to determine multiple facility points of multiple types from a candidate area, wherein the facility points include commercial facility points, residential facility points and transportation facility points; a second determination module, used to determine the attribute parameters of each facility point based on the online evaluation data of each facility point; a third determination module, used to determine the target location data from the candidate area based on the attribute parameters, location data and residential data of each facility point based on a particle swarm algorithm, and use the target location data as the address of the target commercial facility, wherein the constraint function of the particle swarm algorithm includes attribute constraint items and service quality constraint items, the attribute constraint items are determined based on the attribute parameters and the search area of ​​each search of the particle swarm algorithm, and the service quality constraint items are determined based on the residential data and the search area.

[0016] Another aspect of the present invention provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0017] Another aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0018] Another aspect of the present invention provides a computer program product, the computer program product comprising computer executable instructions, and the instructions are used to implement the above method when being executed.

[0019] The embodiments of the present invention enrich the facilities that affect the site selection of commercial facilities by introducing commercial, residential and transportation facilities, and the newly added online evaluation data for each facility helps to improve the accuracy of address determination of commercial facilities. In addition, by introducing attribute constraints and service quality constraints in the particle swarm algorithm, when using the particle swarm algorithm for commercial site selection, it is not only possible to comprehensively consider multiple factors to determine a better commercial facility address, but also possible to determine the commercial facility address in a more fine-grained manner. Compared with the solution based on rasterized map site selection, the present invention can further improve the accuracy of address determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings.

[0021] Figure 1 An exemplary system architecture of the method and apparatus for determining addresses of commercial facilities based on big data to which the present invention can be applied is shown.

[0022] Figure 2 A flow chart of a method for determining an address of a commercial facility based on big data according to an embodiment of the present invention is shown.

[0023] Figure 3 A diagram showing an application scenario for determining target location data according to a specific embodiment of the present invention is shown.

[0024] Figure 4 A flow chart for determining target location data according to a specific embodiment of the present invention is shown.

[0025] Figure 5 A block diagram of a device for determining an address of a commercial facility based on big data according to an embodiment of the present invention is shown.

[0026] Figure 6 A block diagram of an electronic device 600 suitable for implementing address determination of commercial facilities based on big data according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0029] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0030] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0031] In the embodiments of the present invention, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage and other aspects of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain user personal information security, network security and national security. In the embodiments of the present invention, the user's authorization or consent is obtained before obtaining or collecting user personal information.

[0032] In the address determination scenario, that is, the site selection scenario, the evaluation method and evaluation factors are the core points. In recent years, existing solutions have used model algorithms to establish factor evaluation models to screen the most optimal site selection points, such as particle swarm algorithms, ant colony algorithms, K-means clustering, etc. The evaluation factors are the distance from residential areas and facilities to the site selection points, the number distribution of urban population, structural distribution, supply data, population data, and life power supply data.

[0033] However, the existing schemes have at least the following problems: (1) The evaluation factors are not comprehensive enough. The current evaluation factors are mainly concentrated on traditional population and distance factors, such as population distribution and facility distance, without considering the impact of online technology on the address determination of commercial facilities in the context of the times, which affects the accuracy of address determination. (2) The accuracy needs to be improved. The current address determination scheme is usually based on the optimal unit given by surveys or studies (that is, the smallest unit of the search grid is the optimal unit), or the grid divided according to population distribution is the basic unit. However, for commercial facilities, there is still a possibility that there are multiple better addresses at a finer granularity within the optimal unit / basic unit selected by the model evaluation, resulting in the optimization of address determination. There is still room for accuracy improvement. (3) The results need to be further studied. In the current address determination scheme, the final result only includes the location of the optimal address or the optimal unit, and it is impossible to intuitively obtain the test conditions of other locations, which is not conducive to the user's evaluation of the rationality and practicability of the results, and the interpretability is poor.

[0034] In order to solve at least one of the above technical problems, the present invention provides a method for determining the address of commercial facilities based on big data, including: determining multiple types of multiple facility points from a candidate area, wherein the facility points include commercial facility points, residential facility points and transportation facility points; determining the attribute parameters of each facility point based on the online evaluation data of each facility point; based on the particle swarm algorithm, determining the target location data from the candidate area according to the attribute parameters, location data and residential data of each facility point, and using the target location data as the address of the target commercial facility, wherein the constraint function of the particle swarm algorithm includes attribute constraint items and service quality constraint items, the attribute constraint items are determined according to the attribute parameters and the search area of ​​each search of the particle swarm algorithm, and the service quality constraint items are determined according to the residential data and the search area. Through the above embodiments, the embodiments of the present invention incorporate online evaluation data into the evaluation factors of site selection, which at least improves the final address determination accuracy.

[0035] Figure 1 An exemplary system architecture of the method and apparatus for determining addresses of commercial facilities based on big data to which the present invention can be applied is shown.

[0036] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0037] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only for example).

[0038] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0039] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0040] It should be noted that the address determination method of commercial facilities based on big data provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the address determination device of commercial facilities based on big data provided in the embodiment of the present invention can generally be set in the server 105. The address determination method of commercial facilities based on big data provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Correspondingly, the address determination device of commercial facilities based on big data provided in the embodiment of the present invention can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Alternatively, the address determination method of commercial facilities based on big data provided in the embodiment of the present invention can also be executed by the first terminal device 101, the second terminal device 102, and the third terminal device 103, or can also be executed by other terminal devices different from the first terminal device 101, the second terminal device 102, and the third terminal device 103. Accordingly, the address determination device for commercial facilities based on big data provided in the embodiment of the present invention can also be set in the first terminal device 101, the second terminal device 102, the third terminal device 103, or in other terminal devices different from the first terminal device 101, the second terminal device 102, the third terminal device 103.

[0041] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0042] Figure 2 A flow chart of a method for determining an address of a commercial facility based on big data according to an embodiment of the present invention is shown.

[0043] like Figure 2 As shown, the method 200 includes operations S210 to S230.

[0044] In operation S210, a plurality of facility points of a plurality of types are determined from the candidate area, wherein the facility points include commercial facility points, residential facility points, and transportation facility points.

[0045] In operation S220, attribute parameters of each facility point are determined according to the online evaluation data of each facility point.

[0046] In operation S230, based on the particle swarm algorithm, target location data is determined from the candidate areas according to the attribute parameters, location data and residence data of each facility point, and the target location data is used as the address of the target commercial facility.

[0047] According to an embodiment of the present invention, the candidate area may be a relatively large area specified according to the requirements, such as the area between Street 1 and Street 2. Alternatively, the candidate area may be an area screened using multiple screening conditions. For example, the area of ​​the candidate area is greater than a certain threshold, the surrounding environment of the candidate area meets the environmental requirements, etc.

[0048] According to an embodiment of the present invention, the candidate region may be a region consisting of a regular or irregular shape.

[0049] For operation S210, the current building situation of the candidate area can be obtained to determine the current multiple types of multiple facility points in the candidate area. Among them, commercial facility points include various specific stores, such as fresh food supermarkets, chess and card rooms, etc.; residential facility points include residential areas, such as communities, apartments, etc.; transportation facility points can be understood as facility points with transportation functions, such as subway stations, bus stops, airports, etc.

[0050] For facilities with comprehensive functions, each type is set and calculated separately. For example, a commercial building has the function of a residential facility and may also contain commercial facilities. The type of the facility can be set as a residential facility, while the small shops contained in it can be set as commercial facilities.

[0051] For operation S220, for each facility point, the attribute parameters of each facility point can be determined according to the online evaluation data of each facility point. The online evaluation data is divided into two types, one is the online evaluation data of the evaluation type, such as comments; the other is the data displayed online after integrating multiple evaluations, such as rating data, search ranking, etc.

[0052] For example, the data involved in the online evaluation data can be normalized and added together to obtain the attribute parameters of each facility point.

[0053] For operation S230, the location data of the facility point may be coordinates formed by longitude and latitude. For example, commercial facilities, residential facilities, and transportation facilities all have their own longitude and latitude coordinates. The residential data of the facility point may include the population size and population density of the facility point. The online evaluation data is data obtained through public online evaluation platforms, such as ordering platforms, social platforms, and comprehensive platforms.

[0054] In one embodiment, the location data of each facility point can be determined through public map software or geographic platforms; residential data can be determined through public real estate trading platforms or questionnaires; and data can be directly called through the interface of online evaluation platforms. In one embodiment, missing value processing, cleaning, and deduplication can be performed on the data, and the processed data can be organized into a file in a tabular form.

[0055] The particle swarm algorithm is an optimization algorithm based on swarm intelligence. It simulates the foraging behavior of biological groups such as bird flocks and fish schools, and uses information sharing and collaboration between individuals to find the optimal solution to the problem. In the embodiment of the present invention, each "particle" in the particle swarm algorithm includes attributes such as position data and attribute parameters. The process of determining the target location data from the candidate area based on the particle swarm algorithm is essentially to obtain a target solution, and use the target location data corresponding to the target solution as the address of the target commercial facility.

[0056] The constraint function of the particle swarm algorithm includes attribute constraints and service quality constraints. The attribute constraints are determined based on the attribute parameters and the search area of ​​each search of the particle swarm algorithm, and the service quality constraints are determined based on the residential data and the search area.

[0057] The attribute constraint can be understood as a constraint on the attribute parameters within a certain search area. Therefore, it can be determined based on the attribute parameters and the search area of ​​each search by the particle swarm algorithm. The service quality constraint can be understood as a constraint on the quality of service provided by the target solution (target commercial facility) to the users of residential facilities in the search area. Therefore, it can be determined based on residential data and the search area. The particle swarm algorithm usually obtains the final target solution through multiple iterations, and each iteration searches in a certain search area. The scope of the search area can be predetermined, and the search center changes in each iteration.

[0058] The embodiments of the present invention enrich the facilities that affect the site selection of commercial facilities by introducing commercial, residential and transportation facilities, and add online evaluation data for each facility point, which helps to improve the accuracy of address determination of commercial facilities. In addition, by introducing attribute constraints and service quality constraints in the particle swarm algorithm, when using the particle swarm algorithm for commercial site selection, it is not only possible to comprehensively consider multiple factors to determine a better commercial facility address, but also possible to determine the commercial facility address in a more fine-grained manner. Compared with the solution based on rasterized map site selection, the present invention can further improve the accuracy of address determination.

[0059] According to an embodiment of the present invention, the constraint function includes a first constraint target, a second constraint target and a third constraint target. The priority of the first constraint target is higher than that of the second constraint target and the third constraint target. The first constraint target is used to maximize the difference between the attribute constraint value of the attribute constraint item and the service quality constraint value of the service quality constraint item. The second constraint target is used to maximize the attribute constraint value and the third constraint target is used to minimize the service quality constraint value.

[0060] The particle swarm algorithm adopted in the embodiment of the present invention is a multi-objective optimization particle swarm algorithm, that is, it includes a first constraint target, a second constraint target and a third constraint target, each constraint target is a constraint on at least one of the attribute constraint value of the attribute constraint item and the service quality constraint value of the service quality constraint item.

[0061] According to an embodiment of the present invention, since the priority of the first constraint target is higher than the second constraint target and the third constraint target, during the optimization process, it is necessary to prioritize ensuring that the difference between the attribute constraint value and the service quality constraint value is maximized. In this case, if there are multiple solutions, either the attribute constraint value can be maximized or the service quality constraint value can be minimized.

[0062] According to another embodiment of the present invention, there may also be a priority difference between the second constraint target and the third constraint target. For example, the priority of the second constraint target is higher than that of the third constraint target, so that when there are multiple targets that maximize the difference between the attribute constraint value and the service quality constraint value, the solution with the largest attribute constraint value is determined as the target solution. Alternatively, the priority of the third constraint target is higher than that of the second constraint target, so that when there are multiple targets that maximize the difference between the attribute constraint value and the service quality constraint value, the solution with the smallest service quality constraint value is determined as the target solution.

[0063] According to an embodiment of the present invention, the attribute constraint value is determined according to the following method: in the process of iterating using the particle swarm algorithm, a search area is determined according to a preset search radius and a search center of the current iteration number, wherein the candidate area includes the search area; a plurality of target facility points within the search area are determined from a plurality of the facility points; and the attribute parameters of each of the target facility points are weightedly summed to obtain the attribute constraint value.

[0064] According to an embodiment of the present invention, multiple searches need to be performed with multiple search centers in each iteration process. In each iteration process, each point in the candidate area is calculated as a search center, thereby obtaining a selectable target solution. Through multiple iterations, a final target solution can be determined from multiple target solutions. Among them, the candidate area includes facility points and non-facility points, and both facility points and non-facility points need to be calculated as search centers.

[0065] According to an embodiment of the present invention, the search center and / or the change rule of the search center in each iteration process may be set according to a preset rule.

[0066] The following will take a search center under the current iteration number as an example to illustrate the method of calculating attribute constraint values ​​and service quality constraint values.

[0067] It should be noted that the search area is within the candidate area. For example, for a search center located around the boundary of a candidate area, its search area only covers the candidate area, and the area outside the candidate area is not considered as the search area. For example, if the search center is a corner point of a rectangular candidate area, and the shape of the search area is set to a circle, the actual search area of ​​the search center is only 1 / 4 of the circle located within the candidate area.

[0068] According to an embodiment of the present invention, the search radius may be a preset value, such as d 0 =1000m.

[0069] After searching the area, multiple target facility points located in the search area may be determined. At this time, the target facility points may include at least one of the following: commercial facility points, residential facility points, and transportation facility points. For example, the current search area includes only 5 residential facility points, or includes 2 commercial facility points, 2 residential facility points, and 2 transportation facility points.

[0070] According to an embodiment of the present invention, after determining the search area and multiple target facility points within the search area, the attribute parameters of each facility point calculated in operation S220 may be obtained, and the attribute constraint values ​​after searching with the current search center may be calculated by summing.

[0071] The embodiment of the present invention calculates the attribute parameter values ​​of the constraint function by using the attribute parameters of the search area and each target facility point, selects the optimal solution from the location perspective, and not only utilizes location data and residential data, but also utilizes online evaluation data for address determination, which can improve the accuracy of the target location data calculated by the particle swarm algorithm.

[0072] For example, the attribute constraint item is as follows: Formula (1), and the attribute constraint value can be obtained by substituting the specific value into Formula (1):

[0073] (1)

[0074] in, is the attribute parameter of the i-th target facility point. The search area includes a total of N target facilities points.

[0075] The second constraint objective is as follows:

[0076] (2)

[0077] Among them, Max represents the maximum value function.

[0078] According to an embodiment of the present invention, the service quality constraint value is determined according to the following method: determining at least one residential facility point from multiple target facility points; for each residential facility point, determining the number of commercial facility points within a search radius centered on the residential facility point, and determining the ratio of the number to the residential data of the residential facility point; determining the variance for the search area based on the respective ratios of at least one residential facility point, and using the variance as the service quality constraint value.

[0079] According to an embodiment of the present invention, after determining a search area and determining a plurality of target facility points from the search area, it is necessary to determine at least one residential facility point from the plurality of target facility points based on the type of the target facility point.

[0080] For each residential facility point, determine the number of commercial facilities within the search radius centered on the residential facility point. It should be noted that the area divided by the search radius centered on the residential facility point may completely overlap with the current search area, such as the residential facility point is the current search center; or there may be differences, such as the residential facility point is not the current search center.

[0081] For each residential facility point, after determining the number of commercial facility points within the search radius with the residential facility point as the center, this number can reflect the overall service quality of the commercial facility points to the residential facility point, and after calculating the ratio of this number to the residential data of the residential facility point, this ratio can reflect the service quality of the commercial facility points to each user in the residential facility point. After determining the variance of multiple ratios based on the ratios of at least one residential facility point, that is, the variance for the search area, this variance can reflect the service quality of the commercial facility points to each user in each residential facility point in the search area, so the variance can be used as a service quality constraint value.

[0082] For the resident data of each facility point, in one embodiment, the resident data of the commercial facility point is a first default value of 1, and the resident data of the transportation facility point is a second default value of 0. The first default value and the second default value are different. In another embodiment, the resident data of the commercial facility point is a first default value of 0, and the resident data of the transportation facility point is a second default value of 0. The first default value and the second default value are the same. The resident data of the residential facility point can be the population.

[0083] The service quality constraint term is as follows: Formula (3), and the service quality constraint value can be obtained by substituting specific values ​​into Formula (3):

[0084] (3)

[0085] in, represents the number of commercial facilities within the search radius centered on the i-th residential facility point. is the residential data of i residential facility points, and the search area includes a total of M residential facility points.

[0086] The third constraint objective is as follows:

[0087] (4)

[0088] Among them, Min represents the minimum function.

[0089] The embodiments of the present invention calculate the service quality constraint value of the constraint function by utilizing the search area and residential data, and calculate the optimization goal of minimizing the per capita service gap from the perspective of the service quality of commercial facilities to each user in each residential facility point within the search area, thereby improving the accuracy of the target location data calculated by the particle swarm algorithm.

[0090] Based on the above description, the first constraint objective is as follows:

[0091] (5)

[0092] The attribute constraint value A is obtained by using formula (1), and the service quality constraint value B is obtained by using the above formula (3).

[0093] According to an embodiment of the present invention, the target location data includes location data of facility points located in the candidate area, or location data of non-facility points.

[0094] In this embodiment, since the particle algorithm is for each search center, but the search center is a traversal of all points (facility points and non-facility points) in the candidate area, the target location data finally solved is the location data of a certain search center, and the location data of the search center can be the location data of the facility point or the location data of the non-facility point.

[0095] In summary, the present invention introduces new attribute constraints and service quality constraints into the particle swarm algorithm, so that when using the particle swarm algorithm for commercial site selection, it can comprehensively consider multiple factors to determine a better commercial facility address and improve the address determination accuracy. In addition, the embodiment of the present invention can also determine the commercial facility address in a more fine-grained manner with each point as the search center. Compared with the solution based on rasterized map site selection, the present invention can further improve the address determination accuracy.

[0096] In a specific embodiment, if the multiple target facilities in the search area do not include a residential facility, the service quality constraint value is zero.

[0097] According to an embodiment of the present invention, the attribute parameters of each facility point are determined based on the online evaluation data of each facility point, including: determining at least one keyword related to each facility point based on the name of the facility point; for each keyword, determining the number of times the keyword is mentioned by integrating the online evaluation data of each facility point; determining the residential basic value, the transportation basic value, and the commercial basic value based on the number of mentions; determining the additional evaluation value of each commercial facility point based on the online evaluation data of each commercial facility point; and determining the attribute parameters based on the residential basic value, the transportation basic value, the commercial basic value, and the additional evaluation value.

[0098] According to an embodiment of the present invention, each type of facility point includes a residential basic value, a transportation basic value, and a commercial basic value, but only commercial facility points include additional evaluation values, that is, the additional evaluation values ​​of residential facility points and transportation facility points are 0.

[0099] Considering that the contribution of residential, transportation, and commercial dimensions to the location of commercial facilities in the candidate area may be different. However, the more times a user mentions a target facility point in online reviews, the higher the exposure of the target facility point, and the higher the exposure that can be obtained by setting up a target commercial facility at the target facility point. Therefore, the residential basic value, transportation basic value, and commercial basic value can be determined based on the number of times the same type of facility point is mentioned in the online evaluation data.

[0100] Based on the name of the facility, the full name, abbreviation, or abbreviation of the facility can be used as a keyword. Keywords can be matched from online evaluation data on online evaluation platforms, such as user comments. The number of matched keywords with a similarity higher than a certain threshold is used as the number of times the keyword is mentioned in the online evaluation data.

[0101] Since commercial facilities usually have commercial dimension evaluation, the additional evaluation value unique to the commercial facilities can be determined based on the online evaluation data of the commercial facilities. For commercial facilities with online evaluation, the additional evaluation value can be calculated based on the online evaluation data, and for commercial facilities without online evaluation, the additional evaluation value is zero.

[0102] According to an embodiment of the present invention, the basic residential value, the basic traffic value, the basic commercial value and the additional evaluation value may be summed to obtain the attribute parameter. Alternatively, the basic residential value, the basic traffic value, the basic commercial value and the additional evaluation value may be weighted and summed to obtain the attribute parameter.

[0103] In one embodiment, the business basic value and the additional evaluation value are regarded as data of the business dimension, and the business comprehensive value, the residential basic value, and the traffic basic value composed of the business basic value and the additional evaluation value are taken as three data, and the attribute parameter value is obtained by weighted summation. For example, the weights of the above three data can be determined according to experience.

[0104] In another embodiment, there is also an adjustment weight between the business base value and the additional evaluation value. Considering that the business base value is determined by comprehensively considering multiple commercial facilities in the entire candidate area, the business base value is low for commercial facilities with large traffic and high exposure; the business base value is high for commercial facilities with small traffic and low exposure. However, the additional evaluation value is for each commercial facility point and can reflect more real data. Therefore, the product of the additional evaluation value and the adjustment weight and the business base value are summed to obtain the comprehensive business value, wherein the adjustment weight is used to increase the proportion of the additional evaluation value in the comprehensive business value.

[0105] According to an embodiment of the present invention, determining the residential basic value, the traffic basic value, and the commercial basic value based on the number of mentions includes: determining an initial residential basic value based on the number of mentions of each keyword related to each residential facility point; normalizing the initial residential basic value to obtain a residential basic value; determining an initial traffic basic value based on the number of mentions of each keyword related to each traffic facility point; normalizing the initial traffic basic value to obtain a traffic basic value; and determining an initial commercial basic value based on the number of mentions of each keyword related to each commercial facility point; normalizing the initial commercial basic value to obtain a commercial basic value.

[0106] According to an embodiment of the present invention, the number of times each keyword related to each residential facility point is mentioned can be summed and averaged to obtain an initial residential basic value; the number of times each keyword related to each transportation facility point is mentioned can be summed and averaged to obtain an initial transportation basic value; the number of times each keyword related to each commercial facility point is mentioned can be summed and averaged to determine an initial commercial basic value. Afterwards, the initial residential basic value of each residential facility point is summed, and the initial residential basic value is normalized with the help of the summed data to obtain the residential basic value. The initial transportation basic value of each transportation facility point is summed, and the initial transportation basic value is normalized with the help of the summed data to obtain the transportation basic value. The initial commercial basic value of each commercial facility point is summed, and the initial commercial basic value is normalized with the help of the summed data to obtain the commercial basic value.

[0107] According to an embodiment of the present invention, an additional evaluation value of each commercial facility point is determined based on the online evaluation data of each commercial facility point, including: determining a parameter value of the commercial facility point in at least one service dimension based on the online evaluation data, wherein the service dimension includes at least one of the following: number of evaluations, service ratings, number of shopping packages, and search order in the same category; within the service dimension, normalizing the parameter value of at least one commercial facility point to obtain a normalized parameter value; using the service dimension as a keyword, determining the number of times each service dimension is mentioned in the online evaluation data, and using the number of times the service dimension is mentioned as the respective weight of each service dimension; determining the additional evaluation value of each commercial facility point based on the normalized parameter value and weight of at least one service dimension.

[0108] According to the parameter values ​​of multiple commercial facilities in the candidate area in each service dimension, the parameter values ​​of the current service dimension are normalized to obtain the normalized parameter values. For example, for the number of evaluations, the number of evaluations of each commercial facility point can be divided by the sum of the number of evaluations of multiple commercial facilities in the candidate area to obtain the normalized number of evaluations of each commercial facility point; similarly, the normalized service score value, the normalized shopping package quantity value, and the normalized same category search rank value of each commercial facility point can be obtained. The same category search rank is the current commercial facility point in the search results; the number of evaluations can also be the number of evaluations in the form of pictures + text.

[0109] According to an embodiment of the present invention, similar to calculating the above weight, after keyword matching, the number of keywords evaluating the current service dimension is screened out from the number of matched keywords, and the number of keywords evaluating the current service dimension is used as the weight. Afterwards, the additional evaluation value of each commercial facility point can be determined based on the normalized parameter value and weight of at least one service dimension.

[0110] For example, for a commercial facility point XX, the additional evaluation value of commercial facility point XX is obtained by the normalized parameter value of service dimension 1 * the weight of service dimension 1 + the normalized parameter value of service dimension 2 * the weight of service dimension 2 + the normalized parameter value of service dimension 3 * the weight of service dimension 3 + the normalized parameter value of service dimension 4 * the weight of service dimension 4.

[0111] The embodiments of the present invention calculate the online evaluation data of commercial facility points by integrating multiple service dimensions, and can obtain more accurate online evaluation data that better reflects the characteristics of online users from multiple perspectives, which helps to improve the accuracy of subsequent address determination.

[0112] The online evaluation data of the residential facility points and the transportation facility points may be a third default value, such as 1. The third default value may be the same as the first default value and the second default value, or may be different.

[0113] Figure 3 A diagram showing an application scenario for determining target location data according to a specific embodiment of the present invention is shown.

[0114] like Figure 3 As shown, the embodiment 300 includes operation S301 , operation S304 - operation S308 , built environment data 302 and online evaluation data 303 .

[0115] In operation S301 , data of each facility point in the candidate area is obtained and preprocessed. For example, the obtained data includes built environment data 302 and online evaluation data 303 .

[0116] The built environment data 302 includes the coordinates of residential facility points, the population of the residential facility points, the coordinates of transportation facility points, and the coordinates of commercial facility points.

[0117] The online evaluation data 303 includes the search ranking of the same category of the commercial facility points, the number of evaluations of the commercial facility points, the service ratings of the commercial facility points, and the number of shopping packages of the commercial facility points.

[0118] The preprocessing operation may be to process the above data into a table file.

[0119] In operation S304, the address of the commercial facility is determined using a multi-objective based particle swarm algorithm.

[0120] In operation S305, the number of points is set.

[0121] According to an embodiment of the present invention, when the target position data is calculated using the particle swarm algorithm, the number of points can be set so that at least one target position data is finally output. If the number of points is set to D, D target position data are finally output.

[0122] In operation S306, operation parameter setting is performed.

[0123] According to an embodiment of the present invention, the operating parameters required by the particle swarm algorithm include the inertia factor , the number of iterations maxgen, the first acceleration constant C1, the second acceleration constant C2, the population size (num particles), the boundary of the candidate region, that is, the running boundary. For example, the number of iterations maxgen can be 1000, the population size can be 500, and the inertia factor See the following formula (6), the first acceleration constant C1 and the second acceleration constant C2 see the following formula (7):

[0124] (6)

[0125] Among them, k is the current iteration number, rand is a random number between [0,1], and are the global optimal fitness values ​​of the kth and k+1th iteration processes respectively, The initial value of is 0.

[0126] (7)

[0127] The meanings of the parameters in formula (7) are as above and will not be repeated here.

[0128] According to an embodiment of the present invention, when solving using the particle swarm algorithm, in order to prevent premature convergence or falling into a local optimum, the global optimal position of the particle is disturbed with a certain probability every period according to the following formula (8):

[0129] (8)

[0130] in, is a disturbance factor randomly generated between (0,1) with a mean of 0 and a variance of 1. is the d-th dimension variable of the ith particle.

[0131] In operation S307 , the constraint function sets: a first constraint target, a second constraint target, and a third constraint target.

[0132] In operation S308, target position data is output.

[0133] According to an embodiment of the present invention, when using the particle swarm algorithm for calculation, not only the final at least one target position data is obtained, but also a first file pso_result is generated and resulted, including the optimal target solution in each iteration process and each searched position data within the population; a second file fitness_result is also exported, including the function value of the constraint function in each iteration process.

[0134] Figure 4 FIG. 2 shows a flow chart of determining target location data according to a specific embodiment of the present invention. Figure 4 As shown, embodiment 400 includes operations S401-S412.

[0135] S401, start.

[0136] S402, read data.

[0137] S403, inputting site selection conditions. A site selection area is obtained through preliminary screening, and a candidate area is selected from the site selection area through operation S404.

[0138] S404: Select a candidate region.

[0139] S405, initializing the speed and position data of the particles.

[0140] S406, calculating the fitness of the particle.

[0141] S407, obtaining the target solution of each particle iteration process.

[0142] S408, obtaining the global target solution of the particle.

[0143] S409, whether the convergence condition is met. The convergence condition is whether the target constraint value finally calculated by the particle swarm algorithm converges. If the convergence condition is met, perform operation S410; otherwise, perform operation S407.

[0144] S410, whether the maximum number of iterations is satisfied. If the maximum number of iterations is satisfied, perform operation S411; otherwise, perform operation S407.

[0145] S411, output target position data.

[0146] S412, end.

[0147] According to an embodiment of the present invention, the method further includes a visualization operation, such as steps 1 to 6 below:

[0148] Step 1: Create a new file 1 and import the visualization code into the file.

[0149] Step 2: Select the colors at both ends of the visualization and fill in the colors in English.

[0150] Step 3: Create a grid to count the frequency of points. Fill the number of columns into the "Number (num)" of "x_edges" and the number of rows into the "Number (num)" of "y_edges".

[0151] Step 4: Establish an association between the file to be visualized and the new file 1. For example, fill the file name of the file to be visualized into the new file 1.

[0152] Step 5: Click to generate a visualization result.

[0153] Step 6: Store the visualization results locally.

[0154] In summary, the embodiments of the present invention can improve the accuracy of commercial facility address determination: the present invention incorporates built environment data such as population, transportation, distance and online evaluation data such as customer experience, product evaluation, and merchant pricing of online platforms into the evaluation factors of address determination, and combines traditional and online address determination influences to optimize the address determination method. In addition, the embodiments of the present invention can also improve the accuracy of commercial facility address determination. Compared with the rasterization calculation of preset points or pre-selected plots in the existing scheme, the present invention combines the multi-objective particle swarm algorithm for address determination, and directly obtains the target location data in the candidate area, which can be accurate to the specific coordinate longitude and latitude. In this way, subsequent manpower calculations are saved, and the efficiency and accuracy of address determination are improved. In addition, the present invention also provides a more comprehensive reference result, and uses visualization operations to visualize the search process in the form of a heat map, so that users can intuitively see the advantages and disadvantages of all facility points and non-facility points in the area.

[0155] Figure 5 A block diagram of a device for determining an address of a commercial facility based on big data according to an embodiment of the present invention is shown.

[0156] like Figure 5 As shown, the device 500 for determining the address of a commercial facility based on big data includes a first determining module 510 , a second determining module 520 and a third determining module 530 .

[0157] The first determination module 510 is used to determine a plurality of facility points of a plurality of types from the candidate area, wherein the facility points include commercial facility points, residential facility points and transportation facility points.

[0158] The second determination module 520 is used to determine the attribute parameters of each facility point according to the online evaluation data of each facility point.

[0159] The third determination module 530 is used to determine the target location data from the candidate area based on the particle swarm algorithm according to the attribute parameters, location data and residential data of each facility point, and use the target location data as the address of the target commercial facility, wherein the constraint function of the particle swarm algorithm includes attribute constraint items and service quality constraint items, the attribute constraint items are determined based on the attribute parameters and the search area of ​​each search of the particle swarm algorithm, and the service quality constraint items are determined based on the residential data and the search area.

[0160] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a proper combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be executed.

[0161] It should be noted that the device part in the embodiment of the present invention corresponds to the method part in the embodiment of the present invention. The description of the device part specifically refers to the method part, which will not be repeated here.

[0162] Figure 6A block diagram of an electronic device 600 suitable for implementing address determination of commercial facilities based on big data according to an embodiment of the present invention is shown.

[0163] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0164] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present invention by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present invention by executing the program stored in the one or more memories.

[0165] According to an embodiment of the present invention, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0166] According to an embodiment of the present invention, the method flow according to an embodiment of the present invention can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present invention are executed. According to an embodiment of the present invention, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0167] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0168] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device.

[0169] For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0170] The embodiment of the present invention also includes a computer program product, which includes a computer program, the computer program includes a program code for executing the method provided by the embodiment of the present invention, and when the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the method provided by the embodiment of the present invention. When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present invention are executed. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0171] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0172] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0173] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present invention can be combined and / or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features recorded in the various embodiments of the present invention can be combined and / or combined in various ways. All these combinations and / or combinations fall within the scope of the present invention.

[0174] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for determining the address of a commercial facility based on big data, characterized in that: The method comprises: Determine a plurality of facility points of a plurality of types from the candidate area, wherein the facility points include commercial facility points, residential facility points, and transportation facility points; Determining attribute parameters of each of the facility points based on the online evaluation data of each of the facility points; Based on the particle swarm algorithm, according to the attribute parameters, location data and residential data of each of the facility points, the target location data is determined from the candidate area, and the target location data is used as the address of the target commercial facility, wherein the constraint function of the particle swarm algorithm includes attribute constraint items and service quality constraint items, the attribute constraint items are determined according to the attribute parameters and the search area of ​​each search of the particle swarm algorithm, and the service quality constraint items are determined according to the residential data and the search area.

2. The method according to claim 1, characterized in that: The constraint function includes a first constraint target, a second constraint target and a third constraint target. The priority of the first constraint target is higher than that of the second constraint target and the third constraint target. The first constraint target is used to maximize the difference between the attribute constraint value of the attribute constraint item and the service quality constraint value of the service quality constraint item. The second constraint target is used to maximize the attribute constraint value and the third constraint target is used to minimize the service quality constraint value.

3. The method according to claim 2, characterized in that The attribute constraint value is determined according to the following method: in the process of iterating using the particle swarm algorithm, Determine the search area according to a preset search radius and a search center of a current iteration number, wherein the candidate area includes the search area; Determine a plurality of target facility points within the search area from the plurality of facility points; The attribute parameters of each of the target facility points are summed to obtain the attribute constraint value.

4. The method according to claim 3, characterized in that The service quality constraint value is determined according to the following method: Determine at least one residential facility point from a plurality of target facility points; For each residential facility point, determine the number of commercial facility points within the search radius centered on the residential facility point, and determine the ratio of the number to the residential data of the residential facility point; According to the ratio of at least one of the residential facility points, a variance for the search area is determined, and the variance is used as the service quality constraint value.

5. The method according to claim 1, characterized in that Determining the attribute parameters of each facility point according to the online evaluation data of each facility point includes: Determining at least one keyword related to each of the facility points according to the name of the facility point; For each of the keywords, the online evaluation data of each of the facilities is integrated to determine the number of times the keyword is mentioned; According to the number of times mentioned, determine the residential basic value, the transportation basic value, and the commercial basic value; Determining an additional evaluation value of each of the commercial facility points according to the online evaluation data of each of the commercial facility points; and The attribute parameter is determined according to the residential basic value, the traffic basic value, the commercial basic value and the additional evaluation value.

6. The method according to claim 5, characterized in that Determining the residential basic value, the transportation basic value, and the commercial basic value according to the number of times mentioned includes: Determine an initial residential basic value according to the number of times each of the keywords related to each of the residential facility points is mentioned; normalize the initial residential basic value to obtain the residential basic value; Determine an initial traffic basic value according to the number of times each of the keywords related to each of the traffic facilities is mentioned; normalize the initial traffic basic value to obtain the traffic basic value; and An initial commercial base value is determined according to the number of times each of the keywords related to each of the commercial facility points is mentioned; and the initial commercial base value is normalized to obtain the commercial base value.

7. The method according to claim 6, characterized in that Determining the additional evaluation value of each commercial facility point according to the online evaluation data of each commercial facility point includes: Determine, based on the online evaluation data, a parameter value of the commercial facility point in at least one service dimension, wherein the service dimension includes at least one of the following: the number of evaluations, the service rating, the number of shopping packages, and the search ranking of the same category; Normalizing a parameter value of at least one of the commercial facility points within the service dimension to obtain a normalized parameter value; Taking the service dimension as a keyword, determining the number of times each of the service dimensions is mentioned in the online evaluation data, and using the number of times the service dimension is mentioned as the weight of each of the service dimensions; The additional evaluation value of each of the commercial facility points is determined according to the normalized parameter value and the weight of at least one of the service dimensions.

8. The method according to claim 1, characterized in that: The target location data includes location data of the facility point located in the candidate area, or location data of a non-facility point.

9. A device for determining the address of a commercial facility based on big data, characterized in that: The device comprises: A first determination module is used to determine a plurality of facility points of a plurality of types from the candidate area, wherein the facility points include commercial facility points, residential facility points and transportation facility points; A second determination module is used to determine the attribute parameters of each of the facility points according to the online evaluation data of each of the facility points; The third determination module is used to determine the target location data from the candidate area based on the particle swarm algorithm according to the attribute parameters, location data and residence data of each of the facility points, and use the target location data as the address of the target commercial facility, wherein the constraint function of the particle swarm algorithm includes attribute constraint items and service quality constraint items, the attribute constraint items are determined based on the attribute parameters and the search area searched by the particle swarm algorithm each time, and the service quality constraint items are determined based on the residence data and the search area.

10. An electronic device comprising: one or more processors; a memory for storing one or more programs, It is characterized in that when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

Images