An AI site selection method and system for offline franchising

Abstract

The present invention relates to the field of AI site selection technology, and specifically discloses an AI site selection method and system for offline franchising. The present invention receives the site selection condition requirements of offline franchising, screens and recommends franchising cases; performs relevant matching in the target site selection area, and determines multiple relevant site selection stores; performs AI trial operation planning, generates trial operation planning data; performs AI trial operation records, obtains multiple store trial operation data; performs data identification and evaluation comparison, selects and marks the target site selection store. It can screen and recommend franchising cases according to the site selection condition requirements, perform relevant matching in the target site selection area, determine multiple relevant site selection stores, perform AI trial operation planning and AI trial operation records, obtain multiple store trial operation data and perform evaluation comparison, and finally select the target site selection store, which can realize accurate store site selection recommendations within the region, and can collect and actual survey data, with the advantages of strong timeliness, small site selection range, and high site selection quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of AI site selection, and in particular, relates to an AI site selection method and system for offline franchising. Background Art

[0002] Offline franchising is a standardized process of joining a mature brand through agency, franchising, etc., and leveraging its culture, technology, management and rapid store operation.

[0003] In the digital age, the market environment is changing rapidly, and the cost of trial and error in site selection for offline franchising is becoming increasingly high.

[0004] In the existing technology, AI site selection for offline franchises can only make regional site recommendations based on non-time-sensitive population, financial, and transportation data. Due to the lack of actual research data, it is impossible to make real comparisons and recommendations for multiple stores in a region. It has the defects of poor timeliness, large site selection range, and low site selection quality. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an AI site selection method and system for offline franchising, aiming to solve the problems raised in the background technology.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] An AI site selection method for offline franchising, the method specifically comprising the following steps:

[0008] Receive offline franchise site selection requirements, conduct business matching and comparison based on the site selection requirements, and screen and recommend franchise cases;

[0009] Obtain a target location area for offline franchising, perform relevant matching in the target location area based on the recommended franchising cases, and determine multiple relevant location stores;

[0010] Conduct AI trial operation planning for multiple relevant selected stores to generate trial operation planning data;

[0011] According to the trial operation planning data, AI trial operation records are performed in multiple relevant selected stores to obtain trial operation data of multiple stores;

[0012] Data identification and evaluation comparison are performed on the trial operation data of the plurality of stores, and a target site selection store is selected and marked from the plurality of related site selection stores.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the receiving of the site selection condition requirements of offline franchises, performing business matching and comparison according to the site selection condition requirements, and screening recommended franchise cases specifically include the following steps:

[0014] Receive offline franchise site selection requirements;

[0015] Update historical franchise data of offline franchise;

[0016] According to the site selection requirements, business matching is performed in the historical franchise data to determine multiple matching franchise cases;

[0017] According to the historical franchise data, a plurality of matching franchise cases are compared for operation, and franchise cases are screened for recommendation.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the step of obtaining the target location area for offline franchising, performing relevant matching in the target location area according to the recommended franchising cases, and determining a plurality of relevant location stores specifically comprises the following steps:

[0019] Performing feature analysis on the recommended franchise cases to obtain multiple recommendation features;

[0020] Obtain the target location area for offline franchising;

[0021] Determine a plurality of stores to be rented according to the target site selection area;

[0022] According to the plurality of recommended features, relevant matching is performed on the plurality of stores to be rented, and a plurality of relevant selected stores are determined.

[0023] As a further limitation of the technical solution of the embodiment of the present invention, the AI ​​trial operation planning for the multiple related site selection stores and the generation of trial operation planning data specifically include the following steps:

[0024] Obtaining a regional planning map of the target site selection area;

[0025] In the regional planning map, marking a plurality of the relevant selected stores to generate a regional marking map;

[0026] According to the preset impact distance, AI trial operation planning is carried out in the area marking map to generate trial operation planning data.

[0027] As a further limitation of the technical solution of the embodiment of the present invention, the AI ​​trial operation record is performed in multiple related site selection stores according to the trial operation planning data, and the acquisition of trial operation data of multiple stores specifically includes the following steps:

[0028] Generate sequential trial operation instructions according to the trial operation planning data;

[0029] According to the sequential trial operation instruction, AI trial operation control is performed in a plurality of the relevant selected location stores;

[0030] During the AI ​​trial operation process of the multiple related site selection stores, AI trial operation records are made to obtain trial operation data of the multiple stores.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the data identification and evaluation comparison of the trial operation data of the plurality of stores, and the selection and marking of the target site selection store from the plurality of related site selection stores specifically include the following steps:

[0032] Extracting evaluation features from the trial operation data of multiple stores, including foot traffic, visit volume, audience volume, and environment score;

[0033] Calculate trial operation evaluation scores of the trial operation data of the plurality of stores;

[0034] Comparing the multiple trial operation evaluation scores to obtain a score comparison result;

[0035] According to the score comparison result, a target store is selected and marked from the multiple related store locations.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the trial operation evaluation score is:

[0037] P i =k1R i +k2D i +k3S i +k4H i ;

[0038] k1+k2+k3+k4=1;

[0039] Among them, k1, k2, k3 and k4 are the influence coefficients of traffic, visit volume, audience volume and environmental score respectively, R i is the flow of people in the trial operation data of the i-th store, D i is the number of visits in the trial operation data of the i-th store, S i is the audience size in the trial operation data of the i-th store, H i is the environmental score in the trial operation data of the i-th store.

[0040] An AI site selection system for offline franchising, the system comprising a recommended case screening module, a region-related matching module, an AI trial operation planning module, an AI trial operation recording module and a trial operation evaluation comparison module, wherein:

[0041] The recommended case screening module is used to receive the site selection condition requirements of offline franchisees, perform business matching and comparison according to the site selection condition requirements, and screen recommended franchise cases;

[0042] A regional correlation matching module is used to obtain a target location selection area for offline franchises, and to perform correlation matching in the target location selection area according to the recommended franchise cases to determine a plurality of related location selection stores;

[0043] An AI trial operation planning module is used to perform AI trial operation planning on a plurality of the related selected stores and generate trial operation planning data;

[0044] An AI trial operation record module is used to perform AI trial operation records in multiple relevant selected stores according to the trial operation planning data, and obtain trial operation data of multiple stores;

[0045] The trial operation evaluation comparison module is used to perform data identification and evaluation comparison on the trial operation data of the plurality of stores, and select and mark the target site selection store from the plurality of related site selection stores.

[0046] As a further limitation of the technical solution of the embodiment of the present invention, the recommended case screening module specifically includes:

[0047] A conditional receiving unit, used to receive the site selection condition requirements of offline franchisees;

[0048] A history update unit, used to update the historical franchise data of offline franchises;

[0049] An operation matching unit, configured to perform operation matching in the historical franchise data according to the site selection condition requirements, and determine a plurality of matching franchise cases;

[0050] The business comparison unit is used to compare the business of multiple matching franchise cases according to the historical franchise data, and screen and recommend franchise cases.

[0051] As a further limitation of the technical solution of the embodiment of the present invention, the AI ​​trial operation planning module specifically includes:

[0052] A map acquisition unit, used to acquire a regional planning map of the target site selection area;

[0053] A store marking unit, used for marking a plurality of the related selected stores in the regional planning map to generate a regional marking map;

[0054] The trial operation planning unit is used to perform AI trial operation planning in the area marking map according to a preset influence distance and generate trial operation planning data.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] (1) The present invention can perform relevant matching in the target site selection area, determine multiple related site selection stores, perform AI trial operation planning and AI trial operation records, obtain multiple store trial operation data and perform evaluation and comparison, and finally select the target site selection store. It can realize accurate store site selection recommendation within the region, and can collect and use actual survey data. It has the advantages of strong timeliness, small site selection range, and high site selection quality.

[0057] (2) The present invention can perform business matching and business comparison according to the site selection requirements and historical franchise data of offline franchises, screen recommended franchise cases, perform feature analysis on the recommended franchise cases, obtain multiple recommendation features, and determine multiple related site selection stores within the target site selection area based on the multiple recommendation features, thereby narrowing the scope for subsequent AI trial operation planning and AI trial operation records, and effectively improving the efficiency of AI site selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0059] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0060] Figure 2 A flow chart of screening recommended franchise cases in the method provided by an embodiment of the present invention is shown.

[0061] Figure 3 A flow chart of target site selection area correlation matching in the method provided by an embodiment of the present invention is shown.

[0062] Figure 4 A flow chart of AI trial operation planning of a store in the method provided by an embodiment of the present invention is shown.

[0063] Figure 5 A flow chart of AI trial operation records of stores in the method provided in an embodiment of the present invention is shown.

[0064] Figure 6 A flow chart of trial operation data evaluation and comparison in the method provided in an embodiment of the present invention is shown.

[0065] Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0066] Figure 8 The structure block diagram of the recommended case screening module in the system provided by the embodiment of the present invention is shown.

[0067] Fig. 9A structural block diagram of an AI trial operation planning module in a system provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] It is understandable that in the digital age, the market environment is changing rapidly, and the trial and error cost of offline franchise site selection is getting higher and higher. In the existing technology, AI site selection for offline franchises can only make regional site selection recommendations based on non-timely population, financial and transportation data. Due to the lack of actual research data, it is impossible to make real comparisons and recommendations for multiple stores in a region, which has the defects of poor timeliness, large site selection range, and low site selection quality.

[0070] To solve the above problems, the embodiment of the present invention receives the site selection condition requirements of offline franchises, performs business matching and comparison according to the site selection condition requirements, and screens recommended franchise cases; obtains the target site selection area of ​​offline franchises, performs relevant matching in the target site selection area according to the recommended franchise cases, and determines multiple relevant site selection stores; performs AI trial operation planning for multiple relevant site selection stores, and generates trial operation planning data; performs AI trial operation records in multiple relevant site selection stores according to the trial operation planning data, and obtains multiple store trial operation data; performs data identification and evaluation comparison on multiple store trial operation data, and selects and marks the target site selection store from multiple relevant site selection stores. It can screen recommended franchise cases according to the site selection condition requirements, perform relevant matching in the target site selection area, determine multiple relevant site selection stores, perform AI trial operation planning and AI trial operation records, obtain multiple store trial operation data and perform evaluation comparison, and finally select the target site selection store, which can realize accurate store site selection recommendation within the region, and can collect and actual survey data, with the advantages of strong timeliness, small site selection range, and high site selection quality.

[0071] Figure 1 A schematic flow chart of a method provided by an embodiment of the present invention is shown.

[0072] Specifically, in a preferred embodiment of the present invention, an AI site selection method for offline franchising includes the following steps:

[0073] Step S101, receiving the site selection condition requirements for offline franchising, performing business matching and comparison according to the site selection condition requirements, and screening and recommending franchising cases.

[0074] In an embodiment of the present invention, when a user has a site selection requirement for an offline franchise, the user can input conditional information such as operating hours, operating scenarios (operating scenarios include: supermarket supporting scenarios, school surrounding scenarios, hospital surrounding scenarios, factory surrounding scenarios, etc.), operating rent, etc., generate and upload site selection condition requirements, receive the site selection condition requirements uploaded by the user, and update the historical franchise data of the offline franchise according to the receiving time, perform business matching in the historical franchise data according to the site selection condition requirements, determine multiple matching franchise cases with the same operating hours, consistent business scenarios, and consistent upper limits on business rents as the site selection condition requirements, and then extract business status data of multiple matching franchise cases in the historical franchise data, and then compare the multiple business status data, select the matching franchise case with the best business status, and mark it as a recommended franchise case.

[0075] It can be understood that historical franchise data is the operating record data of the brand to be joined before the user joins offline; all completed offline franchises will continuously record the operating conditions and continuously update the historical franchise data, so as to not only conduct effective business monitoring of completed offline franchises, but also provide effective franchise references for subsequent franchises.

[0076] Specifically, Figure 2 A flow chart of screening recommended franchise cases in the method provided by an embodiment of the present invention is shown.

[0077] Among them, in the preferred implementation mode provided by the present invention, the receiving of the site selection condition requirements of offline franchisees, performing business matching and comparison according to the site selection condition requirements, and screening the recommended franchise cases specifically include the following steps:

[0078] Step S1011, receiving the site selection requirements for offline franchising.

[0079] Step S1012, updating the historical franchise data of offline franchise.

[0080] Step S1013, performing business matching in the historical franchise data according to the site selection condition requirements, and determining a plurality of matching franchise cases.

[0081] Step S1014, performing business comparison on a plurality of matching franchise cases according to the historical franchise data, and screening recommended franchise cases.

[0082] Furthermore, the AI ​​site selection method for offline franchising also includes the following steps:

[0083] Step S102, obtaining the target site selection area for offline franchising, performing relevant matching in the target site selection area according to the recommended franchising cases, and determining a plurality of relevant site selection stores.

[0084] In an embodiment of the present invention, feature analysis is performed on recommended franchise cases to obtain multiple recommended features of the recommended franchise cases, and then a target site selection area for offline franchises is obtained. Based on big data technology, multiple stores to be rented within the target site selection area are determined, and basic store information of the multiple stores to be rented is obtained. According to the multiple recommended features, relevant matching analysis is performed on the multiple store basic information, and multiple relevant site selection stores are selected, and the multiple relevant site selection stores all meet the multiple recommended features.

[0085] It can be understood that there are multiple recommendation features, including store size and scene location, among which the scene location is the location feature of the recommended franchise case relative to the hot center. The hot center is the place where the flow of people can gather around the recommended franchise case, such as large supermarkets, schools, hospitals, factories, etc.; the store for rent is a store that is located in the target site selection area and is for rent and meets the user's operating rental conditions.

[0086] It is understandable that multiple relevant location stores can meet the user's location needs and meet the store size and scene location of the recommended franchise cases. However, it is still necessary to further determine the best location target among multiple relevant location stores.

[0087] Specifically, Figure 3 A flow chart of target site selection area correlation matching in the method provided by an embodiment of the present invention is shown.

[0088] Among them, in the preferred implementation mode provided by the present invention, the step of obtaining the target site selection area for offline franchise, performing relevant matching in the target site selection area according to the recommended franchise case, and determining a plurality of relevant site selection stores specifically comprises the following steps:

[0089] Step S1021, performing feature analysis on the recommended franchise cases to obtain multiple recommendation features.

[0090] Step S1022, obtaining the target location area for offline franchising.

[0091] Step S1023, determining a plurality of stores to be rented according to the target site selection area.

[0092] Step S1024: performing relevant matching on the multiple stores to be rented according to the multiple recommended features, and determining multiple relevant selected stores.

[0093] Furthermore, the AI ​​site selection method for offline franchising also includes the following steps:

[0094] Step S103, conducting AI trial operation planning for the plurality of related selected stores and generating trial operation planning data.

[0095] In an embodiment of the present invention, a regional planning map of the target site selection area is obtained. The specific location and range of each store can be displayed in the regional planning map. Multiple related site selection stores are marked in the regional planning map to generate a regional marking map. Then, according to the preset influence distance, AI trial operation planning is performed for multiple related site selection stores in the regional marking map, the AI ​​trial operation order and corresponding AI trial operation period of each related site selection store are determined, and trial operation planning data is generated.

[0096] It is understandable that according to the trial operation planning data, the distance between two adjacent related site selection stores in the AI ​​trial operation order is greater than the impact distance, thereby avoiding a large impact between the two AI trial operations, and the AI ​​trial operation period of each related site selection store includes both weekdays and weekends.

[0097] Specifically, Figure 4 A flow chart of AI trial operation planning of a store in the method provided by an embodiment of the present invention is shown.

[0098] Among them, in the preferred implementation manner provided by the present invention, the AI ​​trial operation planning is performed on the plurality of related selected stores, and the generation of trial operation planning data specifically comprises the following steps:

[0099] Step S1031, obtaining a regional planning map of the target site selection area.

[0100] Step S1032: Mark the plurality of related selected stores in the regional planning map to generate a regional marking map.

[0101] Step S1033, according to the preset influence distance, perform AI trial operation planning in the area marking map to generate trial operation planning data.

[0102] Furthermore, the AI ​​site selection method for offline franchising also includes the following steps:

[0103] Step S104: Perform AI trial operation records in multiple related selected stores according to the trial operation planning data to obtain trial operation data of multiple stores.

[0104] In an embodiment of the present invention, according to the trial operation planning data, when the relevant AI trial operation time period is met, sequential trial operation instructions are generated, and then according to the sequential trial operation instructions, AI trial operation control is performed in the relevant site selection stores, and during the AI ​​trial operation process of multiple relevant site selection stores, AI trial operation records are performed. After multiple relevant site selection stores have completed the store AI trial operation and recording, multiple store trial operation data are obtained.

[0105] It can be understood that AI trial operation control is the process of controlling AI robots to conduct trial sales of related products. It can perform simple product production, product promotion and sales interactions. For example, when offline franchising is a milk tea shop, AI trial operation control includes the production of several simple milk teas, promotion of milk tea sales, interaction with buyers, etc.

[0106] It can be understood that the AI ​​trial operation records are the monitoring and filming of the interior and exterior of the relevant selected stores during the AI ​​trial operation control process; the store trial operation data are the video data captured by the monitoring.

[0107] Specifically, Figure 5 A flow chart of AI trial operation records of stores in the method provided in an embodiment of the present invention is shown.

[0108] Among them, in the preferred implementation manner provided by the present invention, the AI ​​trial operation record is performed in multiple relevant site selection stores according to the trial operation planning data, and the acquisition of trial operation data of multiple stores specifically includes the following steps:

[0109] Step S1041, generating sequential trial operation instructions according to the trial operation planning data.

[0110] Step S1042: Perform AI trial operation control in the plurality of related selected stores according to the sequential trial operation instruction.

[0111] Step S1043: During the AI ​​trial operation of the plurality of related selected stores, AI trial operation records are made to obtain trial operation data of the plurality of stores.

[0112] Furthermore, the AI ​​site selection method for offline franchising also includes the following steps:

[0113] Step S105, performing data identification and evaluation comparison on the trial operation data of the plurality of stores, and selecting and marking a target site selection store from the plurality of related site selection stores.

[0114] In the embodiment of the present invention, multiple store trial operation data are identified, and multiple evaluation features corresponding to each store trial operation data are extracted, including traffic, visit volume, audience volume and environment score, and then P is used to evaluate the evaluation features. i =k1R i +k2D i +k3S i +k4H i The trial operation evaluation scores corresponding to the trial operation data of multiple stores are calculated by summing k1+k2+k3+k4=1, where k1, k2, k3 and k4 are the influence coefficients of traffic, visit volume, audience volume and environmental score respectively, and R i is the flow of people in the trial operation data of the i-th store, D iis the number of visits in the trial operation data of the i-th store, S i is the audience size in the trial operation data of the i-th store, H i is the environmental score in the trial operation data of the i-th store. By comparing multiple trial operation evaluation scores, the score comparison result is obtained, and the relevant location store corresponding to the trial operation data of the store with the highest trial operation evaluation score is selected, and the relevant location store is marked as the target location store. The target location store is the most suitable store for offline franchising determined by AI site selection, and then the target location store is recommended to the user.

[0115] It is understandable that the number of people passing by the relevant selected stores can be calculated through character feature recognition of the store trial operation data to obtain the flow of people. The larger the flow of people, the higher the trial operation evaluation score. Therefore, k1 is a positive number. The number of people entering the relevant selected stores can be calculated to obtain the number of visits. The larger the number of visits, the higher the trial operation evaluation score. Therefore, k2 is a positive number. The number of people passing by the relevant selected stores and meeting the age and / or gender of the audience selling the goods can be identified and calculated to obtain the audience volume. The larger the audience volume, the higher the trial operation evaluation score. Therefore, k3 is a positive number. According to the area marking map, the number of competing stores near the relevant selected stores can be analyzed to obtain the environment score. The higher the environment score, the lower the trial operation evaluation score. Therefore, k4 is a negative number.

[0116] Specifically, Figure 6 A flow chart of trial operation data evaluation and comparison in the method provided in an embodiment of the present invention is shown.

[0117] Among them, in the preferred embodiment provided by the present invention, the data identification and evaluation comparison of the trial operation data of the plurality of stores, and the selection and marking of the target site selection store from the plurality of related site selection stores specifically include the following steps:

[0118] Step S1051, extracting evaluation features from the trial operation data of multiple stores, including traffic volume, visit volume, audience volume and environment score.

[0119] Step S1052, calculating the trial operation evaluation scores of the trial operation data of the plurality of stores.

[0120] Step S1053, comparing the multiple trial operation evaluation scores to obtain a score comparison result.

[0121] Step S1054: According to the score comparison result, a target store is selected and marked from the plurality of related store locations.

[0122] Furthermore, Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0123] Among them, in another preferred embodiment provided by the present invention, an AI site selection system for offline franchising includes:

[0124] The recommended case screening module 101 is used to receive the site selection condition requirements of offline franchises, perform business matching and comparison according to the site selection condition requirements, and screen recommended franchise cases.

[0125] In an embodiment of the present invention, when a user has a site selection requirement for an offline franchise, the user can input conditional information such as operating time, operating scenario (operating scenarios include: supermarket supporting scenarios, school surrounding scenarios, hospital surrounding scenarios, factory surrounding scenarios, etc.), operating rent, etc., to generate and upload site selection condition requirements. The recommended case screening module 101 receives the site selection condition requirements uploaded by the user, and updates the historical franchise data of the offline franchise according to the receiving time. According to the site selection condition requirements, the operation matching is performed in the historical franchise data, and multiple matching franchise cases with the same operating time, consistent operating scenario, and consistent operating rent upper limit as the site selection condition requirements are determined. Then, the operating status data of multiple matching franchise cases are extracted from the historical franchise data, and then the multiple operating status data are compared to select the matching franchise case with the best operating status, and mark it as a recommended franchise case.

[0126] Specifically, Figure 8 It shows a structural block diagram of the recommended case screening module 101 in the system provided by an embodiment of the present invention.

[0127] Among them, in the preferred implementation mode provided by the present invention, the recommended case screening module 101 specifically includes:

[0128] The condition receiving unit 1011 is used to receive the site selection condition requirements for offline franchising.

[0129] The history updating unit 1012 is used to update the historical franchise data of offline franchises.

[0130] The business matching unit 1013 is used to perform business matching in the historical franchise data according to the site selection condition requirements, and determine multiple matching franchise cases.

[0131] The business comparison unit 1014 is used to perform business comparison on the multiple matching franchise cases according to the historical franchise data, and screen and recommend franchise cases.

[0132] Furthermore, the AI ​​site selection system for offline franchising also includes:

[0133] The regional correlation matching module 102 is used to obtain the target site selection area for offline franchise, perform correlation matching in the target site selection area according to the recommended franchise case, and determine a plurality of relevant site selection stores.

[0134] In an embodiment of the present invention, the regional correlation matching module 102 performs feature analysis on the recommended franchise cases, obtains multiple recommended features of the recommended franchise cases, and then obtains the target site selection area for offline franchises. Based on big data technology, multiple stores to be rented within the target site selection area are determined, and basic store information of multiple stores to be rented is obtained. According to multiple recommended features, correlation matching analysis is performed on the basic information of multiple stores, and multiple related site selection stores are selected, and the multiple related site selection stores all meet multiple recommended features.

[0135] The AI ​​trial operation planning module 103 is used to perform AI trial operation planning on the plurality of related site selection stores and generate trial operation planning data.

[0136] In an embodiment of the present invention, the AI ​​trial operation planning module 103 obtains a regional planning map of the target site selection area. The specific location and range of each store can be displayed in the regional planning map, and multiple related site selection stores are marked in the regional planning map to generate a regional marking map. Then, according to the preset influence distance, AI trial operation planning is performed on multiple related site selection stores in the regional marking map, and the AI ​​trial operation order and corresponding AI trial operation period of each related site selection store are determined to generate trial operation planning data.

[0137] Specifically, Fig. 9 The structure block diagram of the AI ​​trial operation planning module 103 in the system provided by an embodiment of the present invention is shown.

[0138] Among them, in the preferred embodiment provided by the present invention, the AI ​​trial operation planning module 103 specifically includes:

[0139] The map acquisition unit 1031 is used to acquire a regional planning map of the target site selection area.

[0140] The store marking unit 1032 is used to mark the multiple related site selection stores in the regional planning map to generate a regional marking map.

[0141] The trial operation planning unit 1033 is used to perform AI trial operation planning in the area marking map according to a preset influence distance and generate trial operation planning data.

[0142] Furthermore, the AI ​​site selection system for offline franchising also includes:

[0143] The AI ​​trial operation record module 104 is used to perform AI trial operation records in multiple related site selection stores according to the trial operation planning data, and obtain trial operation data of multiple stores.

[0144] In an embodiment of the present invention, the AI ​​trial operation recording module 104 generates sequential trial operation instructions according to the trial operation planning data when the relevant AI trial operation time period is met, and then performs AI trial operation control in the relevant site selection stores according to the sequential trial operation instructions, and performs AI trial operation records during the AI ​​trial operation process of multiple relevant site selection stores. After multiple relevant site selection stores have completed the store AI trial operation and recording, multiple store trial operation data are obtained.

[0145] The trial operation evaluation comparison module 105 is used to perform data identification and evaluation comparison on the trial operation data of the plurality of stores, and select and mark a target site selection store from the plurality of related site selection stores.

[0146] In the embodiment of the present invention, the trial operation evaluation comparison module 105 identifies multiple store trial operation data, extracts multiple evaluation features corresponding to each store trial operation data, including traffic, visit volume, audience volume and environment score, and then compares the P i =k1R i +k2D i +k3S i +k4H i The trial operation evaluation scores corresponding to the trial operation data of multiple stores are calculated by summing k1+k2+k3+k4=1, where k1, k2, k3 and k4 are the influence coefficients of traffic, visit volume, audience volume and environmental score respectively, and R i is the flow of people in the trial operation data of the i-th store, D i is the number of visits in the trial operation data of the i-th store, S i is the audience size in the trial operation data of the i-th store, H i is the environmental score in the trial operation data of the i-th store. By comparing multiple trial operation evaluation scores, the score comparison result is obtained, and the relevant location store corresponding to the trial operation data of the store with the highest trial operation evaluation score is selected, and the relevant location store is marked as the target location store. The target location store is the most suitable store for offline franchising determined by AI site selection, and then the target location store is recommended to the user.

[0147] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0148] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0149] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. An AI site selection method for offline franchising, characterized in that: The method specifically comprises the following steps: Receive offline franchise site selection requirements, conduct business matching and comparison based on the site selection requirements, and screen and recommend franchise cases; When a user has a site selection requirement for offline franchising, the user inputs condition information including operating time, operating scenario, and operating rent, generates and uploads the site selection condition requirement, receives the site selection condition requirement uploaded by the user, and updates the historical franchising data of offline franchising according to the receiving time, performs business matching in the historical franchising data according to the site selection condition requirement, determines multiple matching franchising cases with the same operating time, matching business scenario, and consistent upper limit of operating rent as the site selection condition requirement, and then extracts the business status data of multiple matching franchising cases from the historical franchising data, compares the multiple business status data, selects the matching franchising case with the best business status, and marks it as a recommended franchising case; Obtain a target location area for offline franchising, perform relevant matching in the target location area based on the recommended franchising cases, and determine multiple relevant location stores; Perform feature analysis on recommended franchise cases, obtain multiple recommended features of recommended franchise cases, and then obtain the target location area for offline franchises. Based on big data technology, determine multiple stores to be rented in the target location area, and obtain the basic store information of multiple stores to be rented. According to multiple recommended features, perform relevant matching analysis on the basic information of multiple stores, select multiple relevant location stores, and multiple relevant location stores all meet multiple recommended features; Conduct AI trial operation planning for multiple relevant selected stores to generate trial operation planning data; Obtain a regional planning map of the target site selection area, which can display the specific location and range of each store. Mark multiple relevant site selection stores in the regional planning map to generate a regional marking map. Then, according to the preset influence distance, perform AI trial operation planning for multiple relevant site selection stores in the regional marking map, determine the AI ​​trial operation order and corresponding AI trial operation period of each relevant site selection store, and generate trial operation planning data. According to the trial operation planning data, the distance between two relevant site selection stores that are adjacent in the AI ​​trial operation order is greater than the influence distance, and the AI ​​trial operation period of each relevant site selection store includes both working days and rest days. According to the trial operation planning data, AI trial operation records are performed in multiple relevant selected stores to obtain trial operation data of multiple stores; According to the trial operation planning data, when the relevant AI trial operation period is met, a sequential trial operation instruction is generated, and then according to the sequential trial operation instruction, AI trial operation control is carried out in the relevant selected stores, and AI trial operation records are carried out during the AI ​​trial operation of multiple relevant selected stores. After the AI ​​trial operation and records of multiple relevant selected stores are completed, multiple store trial operation data are obtained; AI trial operation control is the process of controlling the AI ​​robot to conduct trial sales of relevant products; AI trial operation records are the monitoring and shooting of the interior and exterior of the relevant selected stores during the AI ​​trial operation control process; store trial operation data is the video data shot by monitoring; Performing data identification and evaluation comparison on the trial operation data of the plurality of stores, and selecting and marking a target location store from the plurality of relevant location stores; By identifying multiple store trial operation data, we extract multiple evaluation features corresponding to each store trial operation data, including traffic, visit volume, audience volume and environment score, and then use P i =k1R i +k2D i +k3S i +k4H i The trial operation evaluation scores corresponding to the trial operation data of multiple stores are calculated by summing k1+k2+k3+k4=1, where k1, k2, k3 and k4 are the influence coefficients of traffic, visit volume, audience volume and environmental score respectively, and R i is the flow of people in the trial operation data of the i-th store, D i is the number of visits in the trial operation data of the i-th store, S i is the audience size in the trial operation data of the i-th store, H i is the environment score in the trial operation data of the ith store. By comparing multiple trial operation evaluation scores, the score comparison result is obtained, and the relevant location store corresponding to the trial operation data of the store with the highest trial operation evaluation score is selected, and the relevant location store is marked as the target location store, and then the target location store is recommended to the user. According to the regional marking map, the number of competing stores near the relevant location store is analyzed to obtain the environment score.

2. An AI site selection system for offline franchising, characterized in that: The system includes a recommended case screening module, a regional related matching module, an AI trial operation planning module, an AI trial operation recording module and a trial operation evaluation comparison module, wherein: The recommended case screening module is used to receive the site selection condition requirements of offline franchisees, perform business matching and comparison according to the site selection condition requirements, and screen recommended franchise cases; When a user has a site selection requirement for offline franchise, he / she inputs condition information including operation time, operation scene, and operation rent, generates and uploads the site selection condition requirement. The recommended case screening module receives the site selection condition requirement uploaded by the user, and updates the historical franchise data of offline franchise according to the receiving time. According to the site selection condition requirement, the module performs operation matching in the historical franchise data, determines multiple matching franchise cases with the same operation time, operation scene, and upper limit of operation rent as the site selection condition requirement, and then extracts the operation status data of multiple matching franchise cases from the historical franchise data, compares the multiple operation status data, selects the matching franchise case with the best operation status, and marks it as the recommended franchise case. A regional correlation matching module is used to obtain a target location selection area for offline franchises, and to perform correlation matching in the target location selection area according to the recommended franchise cases to determine a plurality of related location selection stores; The regional related matching module performs feature analysis on the recommended franchise cases, obtains multiple recommended features of the recommended franchise cases, and then obtains the target location area for offline franchises. Based on big data technology, it determines multiple stores to be rented in the target location area, and obtains the basic store information of multiple stores to be rented. According to multiple recommended features, it performs related matching analysis on the basic information of multiple stores, and selects multiple related location stores, and the multiple related location stores all meet multiple recommended features. An AI trial operation planning module is used to perform AI trial operation planning on a plurality of the related selected stores and generate trial operation planning data; The AI ​​trial operation planning module obtains the regional planning map of the target site selection area. The regional planning map can display the specific location and range of each store, mark multiple related site selection stores in the regional planning map, generate a regional marking map, and then perform AI trial operation planning for multiple related site selection stores in the regional marking map according to the preset influence distance, determine the AI ​​trial operation order and corresponding AI trial operation period of each related site selection store, and generate trial operation planning data; according to the trial operation planning data, the distance between two related site selection stores adjacent in the AI ​​trial operation order is greater than the influence distance, and the AI ​​trial operation period of each related site selection store includes both working days and rest days; An AI trial operation record module is used to perform AI trial operation records in multiple relevant selected stores according to the trial operation planning data, and obtain trial operation data of multiple stores; The AI ​​trial operation record module generates a sequential trial operation instruction according to the trial operation planning data when the relevant AI trial operation period is met, and then performs AI trial operation control in the relevant selected stores according to the sequential trial operation instruction, and performs AI trial operation records during the AI ​​trial operation process of multiple relevant selected stores. After multiple relevant selected stores have completed the store AI trial operation and record, multiple store trial operation data are obtained; AI trial operation control is the process of controlling the AI ​​robot to conduct trial sales of relevant products; AI trial operation record is the process of monitoring and shooting the interior and exterior of the relevant selected stores during the AI ​​trial operation control process; store trial operation data is the video data shot by monitoring; A trial operation evaluation comparison module is used to perform data identification and evaluation comparison on the trial operation data of the plurality of stores, and select and mark a target location store from the plurality of related location stores; The trial operation evaluation comparison module identifies the trial operation data of multiple stores, extracts multiple evaluation features corresponding to each store trial operation data, including traffic, visit volume, audience volume and environment score, and then compares the P i =k1R i +k2D i +k3S i +k4H i The trial operation evaluation scores corresponding to the trial operation data of multiple stores are calculated by summing k1+k2+k3+k4=1, where k1, k2, k3 and k4 are the influence coefficients of traffic, visit volume, audience volume and environmental score respectively, and R i is the flow of people in the trial operation data of the i-th store, D i is the number of visits in the trial operation data of the i-th store, S i is the audience size in the trial operation data of the i-th store, H i is the environment score in the trial operation data of the ith store. By comparing multiple trial operation evaluation scores, the score comparison result is obtained, and the relevant location store corresponding to the trial operation data of the store with the highest trial operation evaluation score is selected, and the relevant location store is marked as the target location store, and then the target location store is recommended to the user. According to the regional marking map, the number of competing stores near the relevant location store is analyzed to obtain the environment score.

3. The AI ​​site selection system for offline franchising according to claim 2 is characterized in that: The recommended case screening module specifically includes: A conditional receiving unit, used to receive the site selection condition requirements of offline franchisees; A history update unit, used to update the historical franchise data of offline franchises; An operation matching unit, configured to perform operation matching in the historical franchise data according to the site selection condition requirements, and determine a plurality of matching franchise cases; The business comparison unit is used to compare the business of multiple matching franchise cases according to the historical franchise data, and screen and recommend franchise cases.

4. The AI ​​site selection system for offline franchising according to claim 2 is characterized in that: The AI ​​trial operation planning module specifically includes: A map acquisition unit, used to acquire a regional planning map of the target site selection area; A store marking unit, used for marking a plurality of the related selected stores in the regional planning map to generate a regional marking map; The trial operation planning unit is used to perform AI trial operation planning in the area marking map according to a preset influence distance and generate trial operation planning data.

Images