Marketing suggestion generation method and device based on geographic point, equipment and medium

Abstract

The application provides a marketing suggestion generation method and device based on a geographic point, equipment and a medium. The method comprises the following steps: acquiring basic information of a target geographic point, wherein the basic information comprises geographic coordinate information of the target geographic point and basic user attribute information corresponding to the target geographic point; acquiring business data of other geographic points in a plurality of preset ranges according to the geographic coordinate information; generating a marketing recommendation score of the target geographic point by using a multidimensional evaluation module according to the business data of the other geographic points in the plurality of preset ranges; constructing a potential user portrait corresponding to the target geographic point according to the basic user attribute information; and generating a marketing suggestion of the target geographic point by using a preset artificial intelligence model according to the marketing recommendation score of the target geographic point and the potential user portrait. The marketing recommendation score is generated by using the multidimensional evaluation module, the potential user portrait is constructed in combination with the basic user attribute, and finally the marketing suggestion is output by using the artificial intelligence model.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method, apparatus, device, and medium for generating marketing suggestions based on geographic locations. Background Technology

[0002] In the process of credit marketing by financial institutions, account managers traditionally rely on geographical areas or their own industry experience to manually screen potential marketing locations and integrate information from scattered data systems to generate credit marketing assessment content related to the business entity. To assist this marketing process, existing technologies have developed several auxiliary solutions: a static display and manual screening solution based on point-of-interest (POI) information from map platforms, which imports POI data from map platforms into the internal system to display the merchant's location, industry category, and basic business information; and a point-of-interest assessment solution based on a single or limited number of dimensions, relying on preset tags and simple weighted scoring rules to screen potential customers.

[0003] Existing marketing support technologies suffer from numerous shortcomings, hindering marketing efficiency and accuracy: They lack unified modeling and automated site selection capabilities centered on Points of Interest (POIs), merely displaying POIs as static information and failing to systematically integrate multi-source information, resulting in reliance on manual selection and low automation. Site evaluation dimensions are limited, lacking a multi-dimensional scoring fusion mechanism, focusing only on a few indicators, and failing to achieve objective and quantifiable comprehensive comparisons, thus limiting the accuracy of credit recommendations. Marketing suggestions and product recommendations rely on manual analysis, lacking intelligent generation capabilities, increasing labor costs, and being susceptible to the influence of experience differences. These problems lead to low efficiency and high subjectivity in target audience selection, making it difficult to meet the needs of precision marketing and refined credit granting. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of the prior art by providing a method, apparatus, device, and medium for generating marketing suggestions based on geographic locations. This allows for the systematic acquisition of basic information and multi-preset range business data of target geographic locations, the generation of quantitative marketing recommendation scores through a multi-dimensional evaluation module, the construction of accurate potential user profiles by combining basic user attributes, and the output of personalized marketing suggestions through an artificial intelligence model.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a method for generating marketing suggestions based on geographic locations, including: Obtain basic information about the target geographic location, including: geographic coordinates of the target geographic location and basic user attribute information corresponding to the target geographic location; Based on the geographic coordinate information, obtain the operating data of other geographic locations within a preset range; Based on the operational data of other geographical locations within the preset range, a multi-dimensional evaluation module is used to generate a marketing recommendation score for the target geographical location. Based on the basic user attribute information, a potential user profile corresponding to the target geographical location is constructed. Based on the marketing recommendation score of the target geographical location and the potential user profile, a preset artificial intelligence model is used to generate marketing suggestions for the target geographical location.

[0006] In an optional implementation, the step of generating a marketing recommendation score for the target geographical location based on the operational data of other geographical locations within a plurality of preset ranges, using a multi-dimensional evaluation module, includes: Based on the operational data of other geographical locations within the first preset range, the multi-dimensional evaluation module is used to determine the job-related dimension score, geographical location dimension score, and consumption concentration dimension score. Based on the operational data of other geographical locations within the second preset range, the multi-dimensional assessment module is used to determine the loan popularity dimension score and the regional risk dimension score. Based on the operational data of other geographical locations within the third preset range, the multi-dimensional evaluation module is used to determine the event activity dimension score; Based on the job-related score, the geographical location score, the consumption concentration score, the loan popularity score, the regional risk score, and the event / activity score, a marketing recommendation score for the target geographical location is generated.

[0007] In an optional implementation, the operational data includes: occupational categories, transportation facility data, and consumption level data. The step of determining occupational dimension scores, geographical location dimension scores, and consumption concentration dimension scores using the multi-dimensional evaluation module based on operational data from other geographical locations within a first preset range includes: The job category score is determined based on the job category, number, and industry weight of each job category of other geographical locations within the first preset range. The geographical location dimension score is determined based on the density of transportation facilities within the first preset range and the distance between the target geographical location and each transportation facility. The consumption clustering dimension score is determined based on the consumption level data of other geographical locations within the first preset range.

[0008] In an optional implementation, the operational data further includes: financial data and overdue data. The step of determining loan popularity and regional risk scores using the multi-dimensional evaluation module based on operational data from other geographical locations within the second preset range includes: Based on the financial data of other geographical locations within the second preset range, determine the loan popularity dimension score; Based on the overdue data of the other geographical locations, determine the number of target overdue geographical locations within the second preset range, and determine the regional risk dimension score based on the number of target overdue geographical locations.

[0009] In an optional implementation, the operational data further includes: activity event data, wherein the determination of the event activity dimension score using the multi-dimensional evaluation module based on the operational data of other geographical locations within the third preset range includes: The event activity dimension score is determined based on the activity event data of other geographical locations within the third preset range and the weight of each activity event type.

[0010] In an optional implementation, the basic information further includes: marketing project configuration information, business product element information, and competitor product element information; the step of generating marketing suggestions for the target geographical location based on the marketing recommendation score of the target geographical location and the potential user profile, using a preset artificial intelligence model, includes: Based on the marketing recommendation score of the target geographic location, the potential user profile, the marketing project configuration information, the business product element information, the competitor product element information, and the compliance risk information, the preset artificial intelligence model is used to generate marketing suggestions and recommended product descriptions for the target geographic location.

[0011] In an optional implementation, the method further includes: During the marketing execution phase based on the marketing recommendations, customer interaction content corresponding to the target geographic location is obtained; The customer interaction content was analyzed to obtain loan intention analysis results; Based on the loan intention analysis results, the multi-dimensional evaluation module and / or the preset artificial intelligence model are adjusted to adjust the marketing recommendations.

[0012] Secondly, embodiments of this application also provide a marketing suggestion generation device based on geographic locations, the device comprising: The acquisition module is used to acquire basic information of the target geographic location, including: geographic coordinate information of the target geographic location and basic user attribute information corresponding to the target geographic location; The acquisition module is also used to acquire operational data of other geographical locations within a preset range based on the geographical coordinate information; The generation module is used to generate a marketing recommendation score for the target geographical location based on the operating data of other geographical locations within the preset range and using a multi-dimensional evaluation module. The construction module is used to construct a potential user profile corresponding to the target geographic location based on the basic user attribute information. The generation module is also used to generate marketing suggestions for the target geographical location based on the marketing recommendation score of the target geographical location and the potential user profile, using a preset artificial intelligence model.

[0013] Thirdly, embodiments of this application also provide a computer device, including: a processor, a storage medium, and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the marketing suggestion generation method based on geographic location as described in any of the first aspects.

[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the geographic location-based marketing suggestion generation method as described in any of the first aspects.

[0015] The beneficial effects of this application are: This application provides a method, apparatus, device, and medium for generating marketing suggestions based on geographic locations. The method includes: acquiring basic information of a target geographic location, including geographic coordinates and basic user attribute information corresponding to the target geographic location; acquiring operational data of other geographic locations within a preset range based on the geographic coordinates; generating a marketing recommendation score for the target geographic location using a multi-dimensional evaluation module based on the operational data of other geographic locations within the preset range; constructing a potential user profile corresponding to the target geographic location based on the basic user attribute information; and generating marketing suggestions for the target geographic location using a preset artificial intelligence model based on the marketing recommendation score and the potential user profile. The method in this application systematically acquires basic information of target geographical locations and operational data from multiple preset areas, generates quantitative marketing recommendation scores through a multi-dimensional evaluation module, constructs accurate potential user profiles by combining basic user attributes, and finally outputs personalized marketing suggestions through an artificial intelligence model. It effectively integrates multi-source data such as geography, operations, and users, realizes accurate evaluation of marketing location value and intelligent generation of marketing decisions, significantly reduces manual analysis costs, improves the accuracy and efficiency of marketing, and solves the pain points of subjective location selection and experience-dependent suggestion generation in traditional marketing. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 One of the flowcharts for a marketing suggestion generation method based on geographic location provided in this application embodiment; Figure 2 A second schematic flowchart illustrating a marketing suggestion generation method based on geographic location provided in this application embodiment; Figure 3 A third schematic flowchart illustrating a marketing suggestion generation method based on geographic location provided in this application embodiment; Figure 4 A fourth flowchart illustrating a marketing suggestion generation method based on geographic location provided in this application embodiment; Figure 5 Fifth flowchart illustrating a marketing suggestion generation method based on geographic location provided in this application embodiment; Figure 6 A schematic diagram of the functional modules of a marketing suggestion generation device based on geographic location provided in an embodiment of this application; Figure 7 This is a schematic diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0019] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] In the description of this application, it should be noted that if the terms "upper", "lower", etc. appear to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship that the product of this application is usually placed in, it is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0021] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0023] To address the shortcomings of existing technologies in credit marketing, such as the lack of a unified point selection model centered on geographic locations (POIs), the single dimension of point evaluation, and the reliance on manual marketing follow-up, this application uses POI entities provided by map platforms or third-party data sources as marketing targets. By integrating multi-source data, it performs multi-dimensional scoring modeling of the geographic environment, personnel distribution characteristics, historical credit and operational characteristics, and financial risks associated with POIs. Based on the scoring results, it automatically generates marketing suggestions and project product recommendations for POIs.

[0024] The marketing suggestion generation method based on geographic location provided in this application will be explained in detail below with reference to the accompanying drawings and specific examples. The marketing suggestion generation method based on geographic location provided in this application can also be implemented by a computer device by running an algorithm or software. The computer device can be, for example, a server or a terminal, and the terminal can be a user's computer. Figure 1 One of the flowcharts for a marketing suggestion generation method based on geographic location provided in this application embodiment; such as Figure 1 As shown, the method includes: S101. Obtain basic information about the target geographic location.

[0025] The basic information includes: the geographic coordinates of the target geographic location and the basic user attribute information corresponding to the target geographic location.

[0026] In this embodiment, POI data provided by a map platform, list data imported from within the bank, and existing POI data from the internal business system are acquired. The acquired POI data is standardized to generate POI entity records in a unified format. Each POI entity includes at least the following fields: unique POI identifier, administrative division code, address information, industry type, consumption level, geographic coordinates, business entity identifier, and management personnel identifier.

[0027] Taking the target geographic location as an example, the geographic coordinates of the target geographic location are first obtained through the POI interface of the map platform, in latitude and longitude format, to ensure spatial positioning accuracy. Basic user attribute information is obtained through the bank's internal business system, enterprise registration information, and the People's Bank of China's regional occupational credit report, including the industry type, occupational distribution, company type, business entity identifier, management personnel identifier, administrative division code, and address information of the business entity associated with the target geographic location. Specifically, a multi-source data fusion method is adopted, importing the business entity registration information from the bank's internal business system, synchronizing occupational credit data through the People's Bank of China's regional occupational credit report interface, and obtaining administrative division and address association information from the enterprise registration information data platform. After data cleaning and deduplication, the data is structured and stored in the database of the target geographic location POI.

[0028] S102. Based on geographic coordinate information, obtain operational data of other geographic locations within multiple preset ranges.

[0029] S103. Based on the operational data of other geographical locations within multiple preset ranges, a multi-dimensional evaluation module is used to generate a marketing recommendation score for the target geographical location.

[0030] Specifically, taking the geographical coordinates of the target geographical location as the center, the system obtains the operating data of other geographical locations within multiple preset ranges. Using a multi-dimensional evaluation module, the system generates a marketing recommendation score for the target geographical location based on the operating data of other geographical locations within multiple preset ranges.

[0031] S104. Based on basic user attribute information, construct potential user profiles corresponding to the target geographical locations.

[0032] Specifically, based on basic user attribute information, a pre-set artificial intelligence model is used to analyze and extract tagged features to form a structured potential user profile, including tags such as basic attributes, needs and preferences, fund usage tendencies, sensitivities, and communication preferences.

[0033] For example, taking target geographical location A as an example, basic attributes include: business location, industry type, company type, company age group, etc. Demand preferences include: loan amount, loan term, etc. Fund usage preferences include, for example, company renovation, holiday stocking, etc. Sensitive points include, for example, hidden fees, complex approval process, early repayment penalty, etc. Communication preferences include, for example, communication during working hours, etc.

[0034] S105. Based on the marketing recommendation score and potential user profile of the target geographical location, a preset artificial intelligence model is used to generate marketing suggestions for the target geographical location.

[0035] Specifically, the marketing recommendation score and potential user profile of the target geographic location are input into a preset artificial intelligence model, which then outputs marketing suggestions for the target geographic location, such as reasons for product recommendation, risk warnings, scenario-specific scripts, suggestions for next steps, and details of recommended products.

[0036] In summary, this application provides a method for generating marketing suggestions based on geographic locations. The method includes: acquiring basic information about a target geographic location, including geographic coordinates and basic user attribute information corresponding to the target geographic location; acquiring operational data of other geographic locations within a preset range based on the geographic coordinates; generating a marketing recommendation score for the target geographic location using a multi-dimensional evaluation module based on the operational data of the other geographic locations within the preset range; constructing a potential user profile corresponding to the target geographic location based on the basic user attribute information; and generating marketing suggestions for the target geographic location using a preset artificial intelligence model based on the marketing recommendation score and the potential user profile. The method in this application systematically acquires basic information of target geographical locations and operational data from multiple preset areas, generates quantitative marketing recommendation scores through a multi-dimensional evaluation module, constructs accurate potential user profiles by combining basic user attributes, and finally outputs personalized marketing suggestions through an artificial intelligence model. It effectively integrates multi-source data such as geography, operations, and users, realizes accurate evaluation of marketing location value and intelligent generation of marketing decisions, significantly reduces manual analysis costs, improves the accuracy and efficiency of marketing, and solves the pain points of subjective location selection and experience-dependent suggestion generation in traditional marketing.

[0037] This application also provides another possible implementation of a marketing suggestion generation method based on geographic location. Figure 2 A second schematic flowchart illustrating a marketing suggestion generation method based on geographic location, provided as an embodiment of this application; Figure 2 As shown, based on the operational data of other geographical locations within multiple preset ranges, a multi-dimensional evaluation module is used to generate a marketing recommendation score for the target geographical location, including: S201. Based on the operational data of other geographical locations within the first preset range, a multi-dimensional evaluation module is used to determine the job-related dimension score, geographical location dimension score, and consumption concentration dimension score.

[0038] In this embodiment, the first preset range is, for example, 3000 meters. Then, the operating data of other geographical locations within 3000 meters are obtained with the target geographical location as the center.

[0039] Specifically, for the job-related dimension score, firstly, the distribution and weight of occupations at other geographical locations within 3000 meters are statistically analyzed to calculate the value coefficient of existing occupations; then, the density of stable industries is statistically analyzed to calculate the industry stability coefficient; next, the proportion of supporting POIs is statistically analyzed to calculate supporting stimulus factors; finally, the proportion of high-risk occupations is statistically analyzed to calculate the risk inhibition factor. The average of the four factors is the final job-related dimension score, Scoring.

[0040] For the geographical location dimension score, firstly, the distribution of business types within 3000 meters is statistically analyzed, and the industry diversity index and synergy weight are calculated to obtain the business type synergy coefficient; then, the number and distance of transportation facilities are statistically analyzed, and the distance to transportation hubs and facility density are calculated to obtain the transportation accessibility score. The average of the two is the final geographical location dimension score Cgeo.

[0041] For the consumption clustering dimension score, first calculate the ratio of per capita consumption to the district / county average to obtain the consumption capacity index; then calculate the density of POIs in the same industry to obtain the clustering intensity score; finally calculate the proportion and weight of various POIs to obtain the industry vitality coefficient. The average of the three is the final consumption clustering dimension score, ConsumeClusterScore.

[0042] S202. Based on the operating data of other geographical locations within the second preset range, a multi-dimensional evaluation module is used to determine the loan popularity dimension score and the regional risk dimension score.

[0043] The second preset range can be 1000 meters, in which case the operational data of other geographical locations within 1000 meters are obtained, with the target geographical location as the center.

[0044] Specifically, for the loan popularity dimension scoring, firstly, financial data from the second preset range is extracted from the bank's existing financial system to calculate the loan demand popularity score; then, the proportion of credit failures, credit limit cancellations, and overdue users is statistically analyzed to calculate the risk adjustment factor; next, the ratio of district / county existing users to the city-level average is calculated to obtain the regional economic weight; the average of the three is the final loan popularity dimension score, LoanHotScore.

[0045] For the regional risk dimension scoring, firstly, the GPS trajectory points of overdue users are extracted from the risk management system and spatially correlated with the target POI coordinates to count the number of hits n within 1000 meters; then, the regional risk dimension score RiskSafe is calculated according to the linear deduction formula and cropped to 0-10 points; finally, risk labels (early warning, observation, low risk) are mapped according to the score.

[0046] S203. Based on the operational data of other geographical locations within the third preset range, a multi-dimensional evaluation module is used to determine the event activity dimension score.

[0047] The third preset range can be 5000 meters, which means that the operating data of other geographical locations within 5000 meters are obtained with the target geographical location as the center.

[0048] For the event activity dimension score, event information within a third preset range is extracted from the POI event interface and the news public data platform, and the event activity dimension score EventScore is determined based on the event information.

[0049] S204. Based on the scores from the industry / position dimension, geographical location dimension, consumption concentration dimension, loan popularity dimension, regional risk dimension, and event / activity dimension, generate marketing recommendation scores for the target geographical location.

[0050] Specifically, based on the weights corresponding to multiple dimensions, the scores for industry / position dimension, geographical location dimension, consumption concentration dimension, loan popularity dimension, regional risk dimension, and event / activity dimension are weighted and integrated to obtain the marketing recommendation score, which is expressed as: Marketing Recommendation Score = Industry / Position Dimension Score × 0.20 + Geographical Location Dimension Score × 0.25 + Loan Popularity Dimension Score × 0.15 + Consumption Concentration Dimension × 0.15 + Event / Activity Dimension Score × 0.10 + Regional Risk Dimension Score × 0.15.

[0051] Each dimension is scored on a scale of 0–10 or mapped to the same scale. The weight parameters can be versioned according to the organization's strategy, product elements and project configuration, and the weight version and calculation version are recorded for each output to facilitate reproduction.

[0052] The method provided in this application splits the data collection and scoring dimensions according to different preset ranges, accurately calculates the scores of the six core dimensions, and weights and merges them to construct a comprehensive and logically clear quantitative evaluation system. This not only ensures the relevance and accuracy of the scores of each dimension, but also achieves objective comparability between different points through unified weights. It overcomes the problems of single traditional evaluation dimensions and insufficient stability of results, and provides a scientific and traceable core basis for the generation of subsequent marketing suggestions.

[0053] This application also provides another possible implementation of a geographic location-based marketing suggestion generation method. The operational data includes: industry occupational categories, transportation facility data, and consumption level data. Figure 3 A flowchart illustrating a marketing suggestion generation method based on geographic location, as provided in this application embodiment, is shown in Figure 3. Figure 3 As shown, based on the operational data of other geographical locations within the first preset range, a multi-dimensional evaluation module is used to determine the job-related dimension score, geographical location dimension score, and consumption concentration dimension score, including: S301. Determine the job category score based on the job categories, quantities, and industry weights of other geographical locations within the first preset range.

[0054] In this embodiment, based on the occupational categories, quantities, and industry weights of other geographical locations within the first preset range, the stock occupational value coefficient, industry stability coefficient, supporting stimulus factors, and risk inhibition factors are calculated.

[0055] Among them, if the distance from the residential address to the geographical location is 500 meters, it is determined that they are in the same area. The total number of each occupation in each area is counted. The formula for calculating the stock occupation value coefficient is expressed as: Stock Occupation Value Coefficient = 5 × (Σ(Number of users of each occupation / Total number of users in the community × Occupation weight) / Number of occupations). Different occupations correspond to different occupations. For example, the occupation weight corresponding to the head of a public institution is 0.85, and the occupation weight corresponding to a general employee of a public institution is 0.65, etc.

[0056] The total number of industries in each region is counted, and the formula for calculating the industry stability coefficient is expressed as: Industry Stability Coefficient = 10 × (Regional Stability Density / City-level Stability Density) × Business Diversity Index. Stable industries include: social organizations / public institutions / non-profit organizations, medical institutions, scientific research / education, etc. The Business Diversity Index is expressed as: Business Diversity Index = Σ((Number of POIs of each type / Total number of POIs) × ln(Number of POIs of each type / Total number of POIs)).

[0057] The formula for calculating the supporting factors and incentive factors for each region is as follows: Supporting Incentive Factors = 10 × (Total number of convenience-related POIs / Total number of POIs * 0.1 + Number of high-end consumption POIs / Total number of POIs * 0.2).

[0058] The formula for calculating the risk mitigation factor in occupational risk statistics for each region is: Risk Mitigation Factor = 10 × (1 - (Max(Number of users in each occupation / Total number of users in each occupation)) * 0.5 + 0.25 * Number of high-risk occupations / Total number of occupations). High-risk occupations include others (self-employed individuals, private enterprises, freelancers), and retail trade, etc.

[0059] Finally, the average of the existing occupational value coefficient, industry stability coefficient, supporting stimulus factors, and risk inhibition factors is taken to obtain the occupational dimension score, which is specifically expressed as: Occupational dimension score = (existing occupational value coefficient + industry stability coefficient + supporting stimulus factors + risk inhibition factors) / 4.

[0060] S302. Determine the geographical location dimension score based on the density of transportation facilities within the first preset range and the distance between the target geographical location and each transportation facility.

[0061] Specifically, based on the transportation facility data of other geographical locations within the first preset range, the density of transportation facilities and the distance between the target geographical location and each transportation facility are statistically analyzed to calculate the transportation accessibility score. Specifically, the transportation facilities within the first preset range are statistically analyzed, including the number of bus stops and subway station data. The transportation accessibility score calculation formula is expressed as: Transportation Accessibility Score = (Distance to Transportation Hub × 0.8 + Transportation Facility Density × 0.2) × 10, where, Transportation Hub Distance = Σ(1 / (Distance from the Target Geographical Location to the i-th Transportation Facility Service Distance (km) + 1)) / Service Distance of All Transportation Facilities within the First Preset Range, and Transportation Facility Density = Total Number of POIs Served by Transportation Facilities within the First Preset Range / Total Number of POIs.

[0062] In addition, the number of other geographical locations within the first preset range, including integrated commercial complexes, residential communities, industrial parks, and the total number of POIs belonging to the same category as the target geographical location, are counted, and a business synergy coefficient score is calculated, specifically expressed as follows:

[0063] in, This is represented by the business synergy coefficient score. This is represented as an industry diversity index. Represented as industry-wide collaborative weighting, This is expressed as the number of industries.

[0064] The formula for calculating the industry diversity index is as follows:

[0065] in, Let represent the industry percentage of the i-th industry POI. , Let N be the number of POIs in the i-th industry, and N be the total number of POIs within the first preset range.

[0066] The formula for calculating industry synergy weight is as follows:

[0067] in, Let represent the industry weight of the i-th industry POI. For example, the industry weight of the financial industry is 0.9, the industry weight of the medical industry is 0.8, and the industry weight of the scientific research / education industry is 0.7.

[0068] Finally, the average of the traffic accessibility score and the business synergy coefficient score is taken to obtain the geographical location dimension score, which is specifically expressed as: geographical location dimension score = (traffic accessibility score + business synergy coefficient score) / 2.

[0069] S303. Based on the consumption level data of other geographical locations within the first preset range, determine the consumption agglomeration dimension score.

[0070] Specifically, based on the consumption level data of other geographical locations within the first preset range, the consumption capacity index, industry clustering degree, and industry vitality coefficient are calculated.

[0071] Among them, per capita consumption based on other geographical locations and the average per capita consumption of the district / county where the target geographical location is located The ratio is calculated and expressed as follows:

[0072] The default score for the spending power index is 7. (When missing...) or At that time, the consumption capacity index was 7 points, and the ratio was... When the ratio is greater than 1, for every increase of 0.1, 0.1 is added to the base score of 7. When the score is less than 1, for every 0.1 decrease, 0.1 is subtracted from the base score of 7 to obtain the final consumption capacity index. The consumption capacity is then mapped to a label according to the threshold, for example, (0,4] is low, (4,7] is medium, and (7,10] is high, and this is written into the scoring details.

[0073] Secondly, the density of similar POIs within the current first preset range is statistically analyzed to obtain the industry clustering degree. The calculation formula is expressed as: Industry Clustering Degree = Math.min((ln(current location number of similar POIs + 1) / ln(citywide number of similar POIs + 1))×general industry weight, 10).

[0074] In addition, the industry vitality coefficient is obtained by statistically analyzing the proportion of each type of POI. The calculation formula is: Industry vitality coefficient = 5 × Σ((number of POIs of each type / total number of locations) × industry weight).

[0075] Finally, the average of the consumption capacity index, industry clustering, and industry vitality coefficient is taken to obtain the consumption clustering dimension score, which is specifically expressed as: Consumption clustering dimension score = (consumption capacity index + industry clustering + industry vitality coefficient) / 3.

[0076] The method provided in this application focuses on key operational data within a first preset scope, and refines the scoring logic from three core dimensions: occupational suitability, transportation and business value, and consumption and agglomeration characteristics. This enables in-depth mining and precise quantification of factors related to the core value of geographical locations, making the evaluation of geographical location and surrounding related characteristics more hierarchical and targeted, providing high-quality dimensional input for subsequent comprehensive scoring, and helping to accurately identify potential marketing points.

[0077] This application also provides another possible implementation of a geographic location-based marketing suggestion generation method. The operational data also includes: financial data and overdue data. Figure 4 A flowchart illustrating a marketing suggestion generation method based on geographic location, as provided in this application embodiment, is shown in Figure 4. Figure 4 As shown, based on the operational data of other geographical locations within the second preset range, a multi-dimensional evaluation module is used to determine the loan popularity dimension score and the regional risk dimension score, including: S401. Determine the loan popularity dimension score based on the financial data of other geographical locations within the second preset range.

[0078] In this embodiment, the loan demand heat score, risk adjustment factor, and regional economic weight are determined based on the financial data of other geographical locations within the second preset range.

[0079] Within the second preset range, financial data statistics based on other geographical locations include: number of borrowers (L), number of users with approved credit (C), number of users with verified identities (R), and total number of users (T). The formula for calculating loan demand popularity score is as follows:

[0080] Further statistics are compiled on the number of users with failed credit granting (F), the number of users with cancelled credit limits (X), and the number of users with overdue payments (O). The risk adjustment factor is calculated using the following formula:

[0081] Then, the total number of existing users and the total number of existing users at the district / county level are calculated. The formula for calculating the regional economic weight is: Regional economic weight = ln(1 + total number of existing users at the district / county level / average total number of users at the city / district / county level) × 0.5 + 8. It can be mapped and normalized to [0, 10] by indicators such as regional disposable income, consumption level or industrial park intensity.

[0082] Finally, the average of the loan demand popularity score, risk adjustment factor, and regional economic weight is taken to obtain the loan popularity dimension score, which is specifically expressed as: Loan Popularity Dimension Score = (Loan Demand Popularity Score + Risk Adjustment Factor + Regional Economic Weight) / 3.

[0083] It should be noted that the loan popularity dimension score is mapped to labels according to thresholds: (0,4] low, (4,7] medium, (7,10] high; and the risk factor is mapped to risk labels according to thresholds: (0,4] high, (4,7] medium, (7,10] low. The threshold hit interval, contributing factors, and parameter versions are recorded in the scoring details.

[0084] S402. Based on the overdue data of other geographical locations, determine the number of target overdue geographical locations within the second preset range, and determine the regional risk dimension score based on the number of target overdue geographical locations.

[0085] Specifically, GPS trajectory points for credit granting / withdrawal of existing overdue users are extracted from the bank's risk management system, covering the area where the target POI is located. The spatial distance between the coordinates of the target geographical point and the coordinates of multiple overdue geographical points is calculated, and target overdue geographical points with a distance less than a second preset range are selected. The regional risk dimension score RiskSafe calculation expression is as follows: RiskSafe=9 0.1*n The base score is 9. The base score is linearly reduced based on the number of overdue geographic locations (n), and then cropped to [0,10]. Furthermore, the regional risk dimension score is mapped to risk level labels: (0,6) warning, [6,8] observation, (8,10) low. The scoring details also include the number of overdue geographic locations, the second preset range, and the version of the deduction rules.

[0086] In the method provided in this application embodiment, based on financial data and overdue data within a second preset range, quantitative assessment models for loan popularity and regional risk are constructed respectively. This not only accurately captures the loan demand potential and regional economic support of a location, but also effectively identifies potential credit risks, achieving a synergistic assessment of marketing value and risk level. It solves the drawback of traditional marketing that only focuses on demand and ignores risk, and provides risk-controllable decision support for credit marketing.

[0087] This application also provides another possible implementation of a marketing suggestion generation method based on geographic locations. The operational data further includes: event data; based on operational data from other geographic locations within a third preset range, a multi-dimensional evaluation module is used to determine event activity dimension scores, including: The event activity dimension score is determined based on the activity event data of other geographical locations within the third preset range and the weight of each activity type.

[0088] In this embodiment, activity event information within a third preset range is extracted from the POI event interface and the news public data platform, and classified according to event type. For example, positive events include exhibitions, conferences, etc.; negative events include emergencies, natural disasters, etc., and duplicate or invalid events are removed.

[0089] Then, preset weights are matched according to the type of event. For example, the weight for an exhibition is 0.4, the weight for a large conference is 0.3, and the weight for an emergency is -0.3. The expression for calculating the event activity dimension score is as follows:

[0090] in, We assign weights to each event type and crop the results to a score of [0, 10], adding points for positive events and deducting points for negative events. Finally, we retain the event type, quantity, and corresponding weight in the scoring details.

[0091] The method provided in this application incorporates activity event data within a third preset range into the evaluation system. By combining preset weights for different activity types, it calculates event activity dimension scores, effectively capturing the dynamic impact of various activities within the region on the marketing value of geographic locations. This method distinguishes between the promoting effect of positive activities and the suppressive effect of negative events, and achieves precise quantification of the degree of influence through weight configuration. It makes up for the shortcomings of traditional evaluations that neglect regional dynamic event factors, making the marketing value evaluation of geographic locations more timely and comprehensive, and providing key references for marketing timing selection and strategy adjustment.

[0092] This application also provides another possible implementation of a marketing suggestion generation method based on geographic location. The basic information includes: marketing project configuration information, business product element information, and competitor product element information; based on the marketing recommendation score and potential user profile of the target geographic location, a preset artificial intelligence model is used to generate marketing suggestions for the target geographic location, including: Based on the marketing recommendation score, potential user profile, marketing project configuration information, business product element information, competitor product element information, and compliance risk information of the target geographical location, a pre-set artificial intelligence model is used to generate marketing suggestions and recommended product descriptions for the target geographical location.

[0093] In this embodiment, the marketing project configuration information includes: activity period, target customer group, marketing objectives, channel strategy, etc.; the business product element information includes: target product access, quota / term, fee range, risk preference, etc.; the competitor product element information includes: competitor selling points, pricing strategy, etc.

[0094] The marketing recommendation score, potential user profile, marketing campaign configuration information, business product element information, competitor product element information, and compliance risk information for the target geographic location are input into a preset artificial intelligence model. The model then generates marketing suggestions and recommended product descriptions for the target geographic location. The marketing suggestions include: reasons for recommendation and advantages (corresponding to the scoring criteria); risk warnings and compliance notification points (corresponding to risk dimensions and access constraints); scenario-specific communication points (initial contact / secondary follow-up / objection handling, etc.); and next steps suggestions (guiding lead generation, supplementary information list, scheduling follow-up appointments, etc.). In an optional implementation, the marketing suggestions output fixed fields according to a preset template and reference the scoring criteria fields to enhance interpretability and controllability.

[0095] For example, marketing recommendations are presented as a list of recommendations, sorted by category, with each recommended product accompanied by the rationale and key information (entry requirements, risk warnings, key data points, etc.). Taking project promotion content as an example, the specific output is as follows: {"production":{"name":"The name of the product that best matches this target location","min_rate":"The lowest interest rate that this target location can offer, without returning the unit","avg_rate":"The average interest rate that this target location can offer, without returning the unit","max_amount":"The highest amount that this target location can offer, in yuan, without returning the unit","avg_amount":"The average amount that this target location can offer, in yuan, without returning the unit","reason":"Explains why this product matches this target location, such as why this product and this target location are a good match"},"entity":{"area":"Determines the area where this entity is located based on the name and address of the target location, such as a commercial area, residential area, or transportation hub; and describes the characteristics of the surrounding environment.}} "business":{"Describe the main business, main consumer group, and consumption level of the target geographical location."},"telemarketing":{"time":"When conducting telephone sales of loan products to the target geographical location, provide the most suitable time period within one year and the most suitable time each day based on the industry cycle characteristics of the target geographical location."","target":"Analyze the capital demand cycle of customers in this industry, industry type, main business, operating characteristics, main consumer group, etc., and propose marketing entry points."},"groundmarketing":{"method":"When conducting ground marketing of loan products to the target geographical location, explain the methods or means of marketing based on the specific characteristics of the target geographical location and industry."","how":"For account managers, what specific steps are needed, such as what marketing materials need to be prepared and specific execution steps."}}

[0096] The method provided in this application integrates marketing project configuration, business product elements, competitor product elements, and compliance risk information on the basis of marketing recommendation scoring and potential user profiles. It generates marketing suggestions and recommended product descriptions through a pre-set artificial intelligence model, achieving multi-dimensional collaborative matching. This not only makes marketing suggestions more aligned with specific marketing goals and product positioning, accurately highlighting product advantages and responding to competitor differences, but also ensures the compliance and feasibility of the suggestions. Furthermore, the structured product description information reduces communication costs for account managers, solving the problems of traditional marketing suggestions lacking specificity and being out of touch with products and the market, significantly increasing the likelihood of marketing conversion.

[0097] This application also provides another possible implementation of a marketing suggestion generation method based on geographic location. Figure 5 This is the fifth flowchart illustrating a method for generating marketing suggestions based on geographic locations, as provided in this application embodiment; Figure 5 As shown, the method also includes: S501. During the marketing execution phase based on marketing recommendations, obtain customer interaction content corresponding to the target geographic locations.

[0098] S502. Analyze customer interaction content to obtain loan intention analysis results.

[0099] S503. Based on the loan intention analysis results, adjust the multi-dimensional evaluation module and / or the preset artificial intelligence model to adjust the marketing recommendations.

[0100] In this embodiment, during the marketing execution phase based on marketing recommendations, a pre-set AI-powered automatic dialogue module and intelligent follow-up module are used, with the conversation as the smallest processing unit. After the initial contact is initiated, the module receives and loads basic user attribute information and object information associated with the current conversation from the pre-processing stage. This information includes the account manager's identifier and contact information, merchant or business entity identifier, basic user attribute fields, historical contact and conversation summaries, project information related to the current target geographic location recommendation, and product elements. The above information is structured and encapsulated to generate a set of conversation context variables, which are then written to conversation-level storage to ensure consistency and traceability across multiple rounds of dialogue.

[0101] Subsequently, relying on a pre-built database of credit marketing questions and scenario-based dialogue templates, the module routes conversations through intent recognition and topic classification, ensuring responses converge to loan and activity-related domains. Simultaneously, it dynamically adjusts the intensity of follow-up questions and dialogue branches based on sentiment assessment. When preset conditions such as high user intent and inquiry into key details are met, the module automatically guides the user to add an account manager and completes the manual takeover transition. Furthermore, the module integrates customer interaction content—including the clarity of user needs, focus areas, and emotional changes—to generate interpretable loan intent analysis results. A conversation state machine enables event-driven transitions between states such as reached, needs exploration, and eligibility confirmation. Structured data, including sentiment scores and loan intent analysis results, is then written back to the target geographic location data.

[0102] The AI ​​marketing and lead generation module is implemented based on an external AI outbound calling interface. After an account manager triggers an outbound call on the target geographic location details page, a marketing lead is automatically initialized, containing core elements such as the target geographic location identifier, account manager information, and target phone number. During the outbound call, call data is collected and transcribed for analysis via a callback interface to identify user concerns, needs, and attitudes, generating targeted follow-up suggestions and storing them. During or after the call, the user is guided to add the account manager's corporate communication account. Upon completion, the lead status is updated to "continuous follow-up," and the user is seamlessly transferred to the AI-automated dialogue module for continued interaction. Finally, based on the call results, loan intention analysis results, and user addition status, the system updates the lead to the corresponding status (e.g., called, interested, pending follow-up) and writes the relevant data back to the target geographic location's associated record, providing data support for adjusting parameters of the multi-dimensional evaluation module and / or preset artificial intelligence models. These two modules work together to build a fully intelligent credit marketing system, from lead generation, intelligent outreach, and dialogue interaction to intention conversion and closed-loop optimization.

[0103] The method provided in this application embodiment acquires and analyzes customer interaction content in real time during the marketing execution phase, accurately identifies loan intentions and core demands, and then adjusts the multi-dimensional evaluation module and artificial intelligence model in reverse, so that marketing suggestions can dynamically adapt to changes in customer needs, avoiding the problems of rigid strategies and lack of feedback optimization in traditional marketing, and continuously improving the adaptability and conversion efficiency of marketing.

[0104] The following will continue to explain the geographic location-based marketing suggestion generation device and computer equipment provided in any of the above embodiments of this application. The specific implementation process and the resulting technical effects are the same as those in the corresponding method embodiments. For the sake of brevity, parts not mentioned in this embodiment can be referred to the corresponding content in the method embodiments.

[0105] Figure 6 This is a schematic diagram of the functional modules of a marketing suggestion generation device based on geographic location, provided as an embodiment of this application. Figure 6 As shown, the location-based marketing suggestion generation device 100 includes: The acquisition module 110 is used to acquire the basic information of the target geographic location. The basic information includes: the geographic coordinate information of the target geographic location and the basic user attribute information corresponding to the target geographic location. The acquisition module 110 is also used to acquire operational data of other geographical locations within a preset range based on geographical coordinate information; The generation module 120 is used to generate a marketing recommendation score for the target geographical location based on the operating data of other geographical locations within a multiple preset range, using a multi-dimensional evaluation module. Module 130 is used to construct a potential user profile corresponding to the target geographic location based on basic user attribute information. The generation module 120 is also used to generate marketing suggestions for the target geographical location based on the marketing recommendation score and potential user profile of the target geographical location, using a preset artificial intelligence model.

[0106] Optionally, the generation module 120 is further configured to determine, based on the operating data of other geographical locations within a first preset range, a multi-dimensional evaluation module to determine the industry / position dimension score, geographical location dimension score, and consumption concentration dimension score; based on the operating data of other geographical locations within a second preset range, a multi-dimensional evaluation module to determine the loan popularity dimension score and regional risk dimension score; based on the operating data of other geographical locations within a third preset range, a multi-dimensional evaluation module to determine the event / activity dimension score; and based on the industry / position dimension score, geographical location dimension score, consumption concentration dimension score, loan popularity dimension score, regional risk dimension score, and event / activity dimension score, generate a marketing recommendation score for the target geographical location.

[0107] Optionally, the operational data includes: industry occupational categories, transportation facility data, and consumption level data. The generation module 120 is also used to determine the occupational dimension score based on the industry occupational categories, quantities, and industry weights of other geographical locations within the first preset range; determine the geographical location dimension score based on the density of transportation facilities within the first preset range and the distance between the target geographical location and each transportation facility; and determine the consumption agglomeration dimension score based on the consumption level data of other geographical locations within the first preset range.

[0108] Optionally, the operational data also includes: financial data and overdue data. The generation module 120 is also used to determine the loan popularity dimension score based on the financial data of other geographical locations within the second preset range; to determine the number of target overdue geographical locations within the second preset range based on the overdue data of other geographical locations; and to determine the regional risk dimension score based on the number of target overdue geographical locations.

[0109] Optionally, the operational data also includes: activity event data. The generation module 120 is also used to determine the event activity dimension score based on the activity event data of other geographical locations within the third preset range and the weight of each activity event type.

[0110] Optionally, the basic information also includes: marketing project configuration information, business product element information, and competitor product element information; the generation module 120 is also used to generate marketing suggestions and recommended product descriptions for the target geographical location based on the marketing recommendation score, potential user profile, marketing project configuration information, business product element information, competitor product element information, and compliance risk information of the target geographical location, using a preset artificial intelligence model.

[0111] Optionally, the device further includes: The acquisition module 110 is also used to acquire customer interaction content corresponding to the target geographic location during the marketing execution phase based on marketing recommendations. The analysis module is used to analyze customer interaction content to obtain loan intention analysis results; The adjustment module is used to adjust the multi-dimensional evaluation module and / or the preset artificial intelligence model based on the loan intention analysis results, so as to adjust the marketing recommendations.

[0112] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0113] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0114] Figure 7 This is a schematic diagram of a computer device provided as an embodiment of this application. This computer device can be used to generate marketing suggestions based on geographic locations. Figure 7 As shown, the computer device includes: a processor 210, a storage medium 220, and a bus 230.

[0115] Storage medium 220 stores machine-readable instructions executable by processor 210. When the computer device is running, processor 210 communicates with storage medium 220 via bus 230, and processor 210 executes the machine-readable instructions to perform the steps of the above method embodiment. The specific implementation and technical effects are similar, and will not be described again here.

[0116] Optionally, this application also provides a storage medium 220, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the above-described method embodiments. The specific implementation and technical effects are similar, and will not be repeated here.

[0117] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0118] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0119] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0120] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0121] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for generating marketing suggestions based on geographic locations, characterized in that, include: Obtain basic information about the target geographic location, including: geographic coordinates of the target geographic location and basic user attribute information corresponding to the target geographic location; Based on the geographic coordinate information, obtain the operating data of other geographic locations within a preset range; Based on the operational data of other geographical locations within the preset range, a multi-dimensional evaluation module is used to generate a marketing recommendation score for the target geographical location. Based on the basic user attribute information, a potential user profile corresponding to the target geographical location is constructed. Based on the marketing recommendation score of the target geographical location and the potential user profile, a preset artificial intelligence model is used to generate marketing suggestions for the target geographical location.

2. The method according to claim 1, characterized in that, The step of generating a marketing recommendation score for the target geographical location based on operational data from other geographical locations within a preset range, using a multi-dimensional evaluation module, includes: Based on the operational data of other geographical locations within the first preset range, the multi-dimensional evaluation module is used to determine the job-related dimension score, geographical location dimension score, and consumption concentration dimension score. Based on the operational data of other geographical locations within the second preset range, the multi-dimensional assessment module is used to determine the loan popularity dimension score and the regional risk dimension score. Based on the operational data of other geographical locations within the third preset range, the multi-dimensional evaluation module is used to determine the event activity dimension score; Based on the job-related score, the geographical location score, the consumption concentration score, the loan popularity score, the regional risk score, and the event / activity score, a marketing recommendation score for the target geographical location is generated.

3. The method according to claim 2, characterized in that, The operational data includes: industry occupation categories, transportation facility data, and consumption level data. The process of determining industry occupation dimension scores, geographical location dimension scores, and consumption concentration dimension scores using the multi-dimensional evaluation module based on operational data from other geographical locations within the first preset range includes: The job category score is determined based on the job category, number, and industry weight of each job category of other geographical locations within the first preset range. The geographical location dimension score is determined based on the density of transportation facilities within the first preset range and the distance between the target geographical location and each transportation facility. The consumption clustering dimension score is determined based on the consumption level data of other geographical locations within the first preset range.

4. The method according to claim 2, characterized in that, The operational data also includes: financial data and overdue data. Based on the operational data from other geographical locations within the second preset range, the multi-dimensional evaluation module is used to determine the loan popularity dimension score and the regional risk dimension score, including: Based on the financial data of other geographical locations within the second preset range, determine the loan popularity dimension score; Based on the overdue data of the other geographical locations, determine the number of target overdue geographical locations within the second preset range, and determine the regional risk dimension score based on the number of target overdue geographical locations.

5. The method according to claim 2, characterized in that, The operational data also includes: event data. The process of determining event activity dimension scores using the multi-dimensional evaluation module based on operational data from other geographical locations within the third preset range includes: The event activity dimension score is determined based on the activity event data of other geographical locations within the third preset range and the weight of each activity event type.

6. The method according to claim 1, characterized in that, The basic information also includes: marketing project configuration information, business product element information, and competitor product element information; the step of generating marketing suggestions for the target geographical location based on the marketing recommendation score of the target geographical location and the potential user profile, using a preset artificial intelligence model, includes: Based on the marketing recommendation score of the target geographic location, the potential user profile, the marketing project configuration information, the business product element information, the competitor product element information, and the compliance risk information, the preset artificial intelligence model is used to generate marketing suggestions and recommended product descriptions for the target geographic location.

7. The method according to claim 1, characterized in that, The method further includes: During the marketing execution phase based on the marketing recommendations, customer interaction content corresponding to the target geographic location is obtained; The customer interaction content was analyzed to obtain loan intention analysis results; Based on the loan intention analysis results, the multi-dimensional evaluation module and / or the preset artificial intelligence model are adjusted to adjust the marketing recommendations.

8. A marketing suggestion generation device based on geographic location, characterized in that, The device includes: The acquisition module is used to acquire basic information of the target geographic location, including: geographic coordinate information of the target geographic location and basic user attribute information corresponding to the target geographic location; The acquisition module is also used to acquire operational data of other geographical locations within a preset range based on the geographical coordinate information; The generation module is used to generate a marketing recommendation score for the target geographical location based on the operating data of other geographical locations within the preset range and using a multi-dimensional evaluation module. The construction module is used to construct a potential user profile corresponding to the target geographic location based on the basic user attribute information. The generation module is also used to generate marketing suggestions for the target geographical location based on the marketing recommendation score of the target geographical location and the potential user profile, using a preset artificial intelligence model.

9. A computer device, characterized in that, include: The computer device includes a processor, a storage medium, and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the geographic location-based marketing suggestion generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, performs the steps of the geographic location-based marketing suggestion generation method as described in any one of claims 1 to 7.

Images