Consumption probability prediction method, equipment, medium and system based on hesitation degree analysis

Abstract

The invention discloses a consumption probability prediction method, device, medium and system based on hesitation degree analysis, and belongs to the technical field of consumption probability prediction, and the method comprises the steps: collecting data, including consumer online activity data and offline navigation software use data, and determining a sales point space position and commodity brand information from the collected data; preprocessing the collected data to form sale point dimension data; and mining relevance and mutual influence among the sale point dimension data, and performing consumption probability prediction based on hesitation degree analysis. According to the method, key factors of the whole behavior process of the consumer are considered on the basis of analysis of the change of the consumption ability, the correlation between travel and related positioning information of the consumer and online activities can be fully revealed, and the accuracy and practicability of consumption prediction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of consumption probability prediction, and more specifically, to a consumption probability prediction method, device, medium and system based on hesitation analysis. Background Art

[0002] With the popularity of smartphones and the widespread use of navigation software, consumers are increasingly inclined to use navigation software to plan routes to offline stores. In the field of bulk commodities, when consumers use navigation software to go to stores, there may be a close connection between their online activities (such as searching, browsing, consulting, etc.) and their offline store behaviors. However, there is currently a lack of an effective method in the market to comprehensively and systematically analyze this correlation.

[0003] The existing consumption probability prediction schemes have the following difficulties: because they do not pay attention to changes in consumption capacity and key factors in the entire consumer behavior process, existing analysis methods are insufficient in revealing the correlation between travel and related positioning information and online activities, resulting in poor analysis accuracy and low practicality, making it difficult to provide companies with more refined market insights. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and to provide a consumption probability prediction method, device, medium and system based on hesitation analysis. Based on the analysis of changes in consumption capacity, the key factors of the entire consumer behavior process are taken into consideration, and the correlation between consumer travel and related positioning information and online activities can be fully revealed, thereby improving the accuracy and practicality of consumption prediction.

[0005] The object of the present invention is achieved through the following solutions:

[0006] A consumption probability prediction method based on hesitation analysis includes the following steps:

[0007] Collect data, including consumer online activity data and offline navigation software usage data, and determine the point-of-sale space location and product brand information from the collected data;

[0008] The collected data is pre-processed based on a computer processor running a program to form point-of-sale dimension data;

[0009] The computer processor runs a program to mine the correlation and mutual influence between the point-of-sale dimension data, and makes consumption probability prediction based on hesitation analysis.

[0010] Furthermore, the step of determining the spatial location of the point of sale from the collected data specifically includes the sub-steps of searching the collected data through the Internet, cross-checking and comparing the names disclosed on the official website and the recommended names to determine the accurate name of the point of sale and the longitude and latitude coordinates, and finally circling the target location, adjusting the range, and cross-checking with third-party data to finally determine the spatial location of the point of sale.

[0011] Furthermore, the consumer's online activity data includes search records, browsing history and consultation content; the offline navigation software usage data includes departure location, arrival time, route selection, entry and exit time, length of stay, portrait information, arrival method, corresponding sales point search, viewing, route planning and navigation travel data; the product brand information includes independent sub-brands; the adjustment range specifically includes the capture range of visit behavior of the sales point destination, which includes the store showroom and public areas outside the store.

[0012] Furthermore, the preprocessing of the collected data to form point-of-sale dimension data specifically includes sub-steps: preprocessing operations such as cleaning, deduplication, and time alignment of the collected data to ensure consistency and comparability of the data, and finally associating the destination data with the brand, category, and surrounding environment to form data as the point-of-sale dimension data.

[0013] Furthermore, the preprocessing of the collected data specifically includes preprocessing of basic information data of the point of sale, and the preprocessing of basic information data of the point of sale specifically includes the following sub-steps:

[0014] a) Use the spatial search interface to search for keywords in the city where the store is located using the permutations and combinations of brand, name, and address. Each spatial query will return multiple results. The IDs obtained from all permutations and combinations are summarized and counted for their occurrences.

[0015] b) Sort the aggregated IDs by the number of occurrences, select the number of occurrences of the first set value of the ID in the ranking for comparison, if the number of occurrences of the first place is ≥ the second set value, it is considered that the ID of this store in the spatial data of the professional map provider is this ID, otherwise, the store address is reverse geocoded and the distance is compared with the coordinates corresponding to the ID, and a comprehensive score is given based on the distance between the reverse geocoding and the coordinates corresponding to the ID and the number of ID occurrences, and finally the one with the highest score is selected as the store ID;

[0016] c) Check the ID determined by distance comparison on the maps of each map provider and make corrections based on the check results;

[0017] d) Compare the basic information data of the sales points collected by the vertical media platform to determine their relevance, and then complete the missing information on the official website, which includes the categories and models of products sold.

[0018] Furthermore, the preprocessing of the collected data specifically includes arrival data preprocessing, and the arrival data preprocessing specifically includes the following sub-steps:

[0019] Arrival data includes duration of stay and entry and exit time. Within the capture range, visit records with a duration less than the set value and entry and exit time outside the store's business hours are removed as abnormal data. If the duration of stay is null, the mode is used to fill it in.

[0020] Dimension reduction based on store arrival time: According to the customer flow curve of the merchandise store, the arrival data is reduced to peak-time store arrivals and off-peak-time store arrivals;

[0021] Dimensionality reduction based on store arrival date: Based on the characteristics of store arrival on weekdays and holidays, store arrival data is divided into store arrival on weekdays and store arrival on non-workdays;

[0022] Dimensionality reduction based on store arrival judgment accuracy: accurate store arrival and inaccurate store arrival are distinguished based on the store arrival method; the distinction method includes: if the navigation destination is consistent with the store entering the capture fence, it is regarded as accurate store arrival, otherwise it is regarded as inaccurate store arrival.

[0023] Furthermore, the basic information data of the sales points collected by the vertical media platform is compared to determine the relevance, and then the missing information of the official website is supplemented, which specifically includes the following sub-steps:

[0024] 1) Normalize and standardize names and addresses;

[0025] 2) In the same province or city, the similarity of addresses and names is calculated and compared, and the scores are used to distinguish between absolute match, very good match, need for spot check, and need for manual intervention.

[0026] Furthermore, the mining of the correlation and mutual influence between the point-of-sale dimension data and the prediction of consumption probability based on hesitation analysis specifically include the following sub-steps:

[0027] Construct a consumer hesitation model, which specifically includes destination search hesitation, destination planning hesitation, destination arrival hesitation, and destination arrival and departure hesitation, and use the analysis of consumer hesitation to predict consumption probability.

[0028] Furthermore, the method for determining the destination search hesitation degree specifically includes the following sub-steps:

[0029] a1: Get the user's real destination from the preprocessed data;

[0030] a2: De-link destinations and compare categories and brands;

[0031] a3: Analyze the search behavior from the point-of-sale dimension data; specifically, the following situations are included:

[0032] i. If the search behavior is for multiple brands and multiple stores, the current consumption probability is judged to be particularly hesitant, and multiple brands and multiple stores are further distinguished as follows:

[0033] If the multiple brands are from completely different categories: The hesitancy level is the highest, which means that consumers are in the early exploration stage, their needs are unclear, they are conducting research, and they are in the overall planning stage;

[0034] If the multiple brands are multiple brands of similar categories: the degree of hesitation is lower than the highest, the consumer's search behavior is concentrated, the comparison is between multiple brands, there is a clear understanding of the product category, there is uncertainty in brand selection, and in-depth brand and product comparisons are being conducted to find the best choice;

[0035] The determination of the destination search hesitation is used to confirm that consumers have transitioned from online preparation to offline travel, and some brands and categories have been preliminarily selected for on-site inspection;

[0036] ii. If the search behavior is to search for only a single brand, the current consumption probability is judged to be generally hesitant, and the degree of hesitation is further subdivided according to the search frequency as follows:

[0037] If the search frequency is lower than the first set frequency, it is considered a low-frequency search, which is used to indicate that the consumer has a certain degree of knowledge of the brand and is only making a preliminary understanding or confirming the information, and is still considering it;

[0038] If the search frequency is lower than the second set frequency, it is judged as a medium frequency search, which is used to indicate that the consumer is interested in the product and is seriously considering purchasing it, but has not made up his mind and is comparing different models or waiting for the right time;

[0039] If the search frequency is lower than the third set frequency, it is judged as a high-frequency search, which is used to indicate that the consumer is very interested in the brand, but is obviously hesitant and is struggling with the specific model, price or whether to buy it;

[0040] The search frequency can indicate that consumers have already decided on a brand, or that they are loyal to the brand, are hesitant about the category and price, and want to compare the categories and prices of multiple stores of the same brand. The more hesitant a consumer is, the closer he is to making a decision at the current stage.

[0041] iii. If the search behavior is for multiple stores of a single brand, the current consumption probability is judged to be generally hesitant, and the inclination to choose a store is judged based on the distance between the residence and workplace and the store as follows:

[0042] If the distance between the residence and the workplace and the store is less than the first set distance, it is judged that the selection tendency is the highest, and the convenience of going to the store is the main consideration;

[0043] If the distance between the residence and the workplace and the store is less than the second set distance, it is judged that the selection tendency is to weigh the convenience of going to the store and other factors, and to seek better options or specific services;

[0044] If the distance between the residence and the workplace and the store is less than the third set distance, it is judged that the selection tendency is the lowest among the selection tendencies. However, if the store is chosen as the subsequent travel destination, it will be of great significance. Such consumers must have reasons for giving up convenience.

[0045] By combining the distance between the residence and the workplace and the store, it can be shown that the consumer has a clear brand choice in mind, or plans to compare prices, is hesitant on the price, plans to compare the price of the same brand among multiple stores, or is still considering factors such as geographical location and service quality;

[0046] iv. If the search behavior is a clear single store, the current consumption probability is judged as no hesitation. At this time, the consumer has a clear target brand and store in mind. This type of search indicates that the consumer has a clear purpose. Although the purpose is clear, there may still be hesitation or change at the last moment;

[0047] a4: Based on the analysis of search behavior, a judgment conclusion is formed at the decision-making stage of search: the hesitation of destination search is divided into particularly hesitant, generally hesitant, and not hesitant, and sorted according to the search hesitation. The lower the hesitation, the closer it is to the final brand category and travel plan decision;

[0048] According to the hesitancy analysis of search behavior, the higher the hesitancy of search, the earlier the offline store visit, the less clear the target store is, or even there is no target; the lower the hesitancy, the clearer the target of consumers' attention, and the greater the possibility of subsequent store consumption; different marketing and promotion strategies are formulated according to different levels of hesitation to promote the reduction of consumer hesitation and influence the direction of consumer decision-making. The hesitant consumer group is more advanced in the decision-making process, and it can be considered to provide detailed brand and product comparison information in marketing and promotion activities, highlight the unique advantages of its own brand, provide more experience and trial services, and launch price matching or other preferential policies.

[0049] Furthermore, the method for determining the destination planning hesitation degree specifically includes the following sub-steps:

[0050] b1: Analyze travel planning behavior based on point-of-sale data; specifically, the following situations:

[0051] i. If the destination travel planning behavior is a multi-brand and multi-store situation, it is judged as particularly hesitant, which is used to indicate that the consumer is hesitant among a limited number of brand categories, but has a strong willingness to travel and visit stores;

[0052] ii. If the destination travel planning behavior is single-brand multi-store, it is judged as general hesitation, which is used to indicate that the consumer has already selected a brand, and has even actually visited multiple brands, preliminarily determined the category, and the planning behavior is comparing and screening the distance, travel mode, and store visit sequence, or has entered the price comparison stage;

[0053] iii. If the destination travel planning behavior is a single brand and a single store, it is judged as no hesitation, which is used to indicate that the consumer's destination is very clear, and the planning behavior is to confirm the travel route or determine the public transportation transfer method, and further analysis is combined with the planned travel mode as follows:

[0054] If the consumer is traveling by car, they already have a car, and the hesitation factor is the road conditions. This purchase is a replacement or additional purchase;

[0055] If they travel by public transportation, such consumers may be first-time buyers, and their hesitation factors may be the number of changes and the total time taken to arrive;

[0056] If they are walking or cycling, these customers prefer stores that are close by, but they are usually in the early stages of traveling to explore stores. Combined with subsequent planning data, if there are plans for stores of the same brand that are far away, it means that the decision-making stage is continuing to advance and is closer to the final decision;

[0057] b2: Based on planning behavior analysis, a judgment conclusion is formed in the planning decision-making stage: the destination planning hesitation is divided into special hesitation, general hesitation and no hesitation, and the destinations are sorted according to the planning hesitation. The lower the hesitation, the closer to the final store selection decision. Optionally, different targeted marketing methods are used to guide consumers' decisions according to different levels of hesitation and consumers' target brands and stores.

[0058] Furthermore, the method for determining the destination arrival hesitation specifically includes the following sub-steps:

[0059] c1: Analyze the destination arrival hesitation based on the point of sale dimension data; specifically, it includes the following situations:

[0060] i. If the consumer only arrives at the planned store, it is judged as not hesitant, which is used to indicate that the consumer has a clear goal, knows what he wants to buy, has done sufficient research, and his store behavior is highly consistent with the expected plan. The final decision is imminent and the purchase intention is strong. The expected consumption probability is set as high;

[0061] ii. If the consumer not only arrives at the planned store but also visits other unplanned stores, it is judged as general hesitation, which is used to indicate that the consumer has not yet made up his mind. In addition to the planned stores, he wants to make more comparisons. The decision is affected by the new information after the field investigation. The consumer is close to the final decision, but is still making the final comparison. The expected consumption probability is set to medium;

[0062] iii. If the consumer arrives at an unplanned store, or does not arrive at the originally planned store, but arrives at other stores, then it is judged as particularly hesitant, which is used to indicate that the consumer has only preliminary interest, or the original plan has changed for various reasons, or the pre-selected brand has been replaced, and is in the early stage of decision-making. Demand or preference may change significantly, and the consumption probability expectation is set to low;

[0063] iv. If the consumer has not arrived at any store, he / she is considered to be particularly hesitant, which means that he / she may have just checked the store information on impulse and has no strong desire to buy. He / she is just making preliminary explorations, or is limited by objective factors such as time and distance. His / her decision-making process is at the earliest stage and he / she has not yet entered the actual purchase consideration stage. The consumption probability is set to the lowest.

[0064] c2: Based on the hesitation analysis of whether the destination has been reached, a judgment conclusion is formed at the decision-making stage of reaching the destination: the hesitation of reaching the destination is divided into special hesitation, general hesitation, and no hesitation. The destinations are sorted according to the hesitation degree. The lower the hesitation degree, the closer to the final purchase decision.

[0065] In the above scheme, from the perspective of time dimension analysis: the longer the time interval between planning and arrival, the higher the hesitation usually is; the difference between the arrival time on weekdays and weekends may reflect different purchase urgency, with the urgency on weekdays being higher; from the perspective of space dimension analysis: the closer the residence / workplace is to the target store, the higher the convenience and the lower the hesitation may be; on the contrary, if the original plan is still adhered to, it may indicate a strong purchase intention; from the perspective of visit frequency analysis: multiple visits to the store may indicate strong interest and deeper hesitation; from the perspective of the number of brands visited in the store: the same brand may indicate a high degree of loyalty to the brand or that the brand has been selected, and it is very likely that the brand is being compared and the final decision is very close; visits to stores of different brands may indicate that the intended model has been determined and the final comparison and decision is being made;

[0066] In the further plan, the marketing strategies are matched according to different analysis results: For the group without hesitation, strengthen the purchasing confidence and provide a convenient transaction process; for the group with general hesitation, provide detailed product comparison information and highlight the unique advantages; for the group with special hesitation, increase brand exposure, provide more experience opportunities, and provide more choices and comparison tools.

[0067] Furthermore, the method for determining the hesitation degree of arriving at and then leaving the destination specifically comprises the following sub-steps:

[0068] d1: Analyze the hesitation of arriving at the destination and then leaving the destination based on the point of sale dimension data; specifically, it includes the following situations: Analyze the length of time consumers stay in the store:

[0069] i. If the consumer stays in the store for longer than the first set time and has a deep understanding of the product but ultimately does not purchase it, it is judged as general hesitation, which is used to indicate that the consumer has a strong interest in the product and is close to purchasing the decision-making stage, but still has final concerns. The possibility of returning to the store is set to high;

[0070] ii. If the consumer stays in the store within the set range and checks out the product but leaves without further understanding, it is considered as general hesitation, which indicates that the consumer is interested in the product but not strongly enough. The decision-making stage is still in the consideration stage and needs more information or time. The possibility of returning to the store is set as medium;

[0071] iii. If the consumer stays in the store for less than the second set time and leaves after a quick browse, it is judged as particularly hesitant, which is used to indicate that the consumer is not very interested in the product and is in the decision-making stage where he needs to re-evaluate his needs or consider other options. The possibility of returning to the store is set to low;

[0072] d2: Based on the analysis of the length of time consumers stay in the store, a conclusion is formed: the hesitation to leave after arrival is divided into very hesitant, generally hesitant, and no hesitation, and sorted according to the hesitation degree of the destination. The lower the hesitation degree, the higher the conversion rate.

[0073] Furthermore, the method for determining the hesitation degree of arriving at and then leaving the destination further includes the following sub-steps:

[0074] Combined with the analysis of consumer behavior patterns after leaving the store, the specific situations include the following:

[0075] iv. If the consumer returns to the store after leaving it and does not visit any other stores in between, it is considered as no hesitation;

[0076] v. If the consumer visits 1-3 more stores after leaving the store, it is considered as general hesitation;

[0077] vi. If the consumer visits more than 3 stores after leaving the store or does not visit any store, it is judged as particularly hesitant.

[0078] Furthermore, the method for determining the hesitation degree of arriving at and then leaving the destination further includes the following sub-steps:

[0079] Combined with the analysis of the number of times consumers return to the store, the specific situations include the following:

[0080] i. If a customer returns to the store 1-2 times after leaving the store, he / she will be deemed as not hesitating;

[0081] ii. If the customer returns to the store three times after leaving the store, it will be considered as general hesitation;

[0082] iii. Return to the store more than 3 times after leaving the store: particularly hesitant.

[0083] Furthermore, after using the analysis of consumer hesitation to predict the consumption probability, the method further includes the steps of formulating different marketing and promotion strategies according to different hesitation levels to reduce consumer hesitation and influence the decision-making direction of consumers, including the following situations:

[0084] Offer discounts or limited-time promotions to the undecided group to promote quick decision-making, strengthen product advantages, provide dedicated customer service, and simplify the purchase process and provide convenient payment options;

[0085] Provide detailed product comparison information, arrange in-depth experience activities, and provide flexible purchasing plans for the general hesitant group;

[0086] For particularly hesitant groups, we increase brand exposure, provide basic educational content, offer pressure-free consulting services, invite them to participate in brand activities, and enhance emotional connections.

[0087] A consumption probability prediction device based on hesitation analysis, comprising:

[0088] A data collection module is used to collect data, including consumer online activity data and offline navigation software usage data, and determine the point of sale space location and product brand information from the collected data;

[0089] A data preprocessing module, used to preprocess the collected data based on a computer processor running a program to form point-of-sale dimension data;

[0090] The data mining module is used to mine the correlation and mutual influence between the sales point dimension data based on the computer processor running the program, and to predict the consumption probability based on the hesitation analysis.

[0091] A computer-readable storage medium stores a computer program, wherein the computer program executes any of the above methods when loaded by a processor.

[0092] A consumption probability prediction system based on hesitation analysis includes the consumption probability prediction device based on hesitation analysis as described above.

[0093] The beneficial effects of the present invention include:

[0094] (1) The present invention provides a new consumption probability prediction technology solution, which can determine the relationship between Internet positioning data and human consumption behavior (especially large consumer goods, such as automobiles), and conduct pre-behavior analysis, such as search, planning and browsing data of related APPs, as well as stay analysis, including duration, frequency and distance, and correlation analysis, such as 4S store data of the same brand, the number of 4S stores of the same grade, and license plate or used car transaction data, etc. Based on the above analysis, macro or micro sales forecasts, store management, and precise advertising delivery can be carried out.

[0095] (2) The present invention can help merchants gain insight into the real potential customers among store visitors, study customer decision-making paths, identify and analyze competitors, and assist in optimizing sales funnels and adjusting sales strategies through sales forecast data.

[0096] (3) The present invention can exclude non-potential purchasing customers through analysis of the relationship between people and places, thereby more accurately determining the number of "consumers" visiting the store, thereby improving the accurate insight into the number of people entering the store and predicting future sales based on the number of consumers. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation cases of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0098] Figure 1 Mining data flows for potential customers in embodiments of the present invention;

[0099] Figure 2 This is a flowchart of preprocessing basic information data of a point of sale in an embodiment of the present invention;

[0100] Figure 3 The destination retrieval hesitation in the embodiment of the present invention;

[0101] Figure 4 The destination planning hesitation in the embodiment of the present invention;

[0102] Figure 5 is the destination arrival hesitation in the embodiment of the present invention;

[0103] Figure 6 is the hesitation degree of arriving at and then leaving the destination in the embodiment of the present invention;

[0104] Figure 7 4 is a structural block diagram of a device in an embodiment of the present invention. DETAILED DESCRIPTION

[0105] All features disclosed in all embodiments in this specification, or steps in all methods or processes implicitly disclosed, except for mutually exclusive features and / or steps, can be combined and / or expanded or replaced in any manner.

[0106] In a preferred embodiment, it particularly relates to the fields of Internet positioning data analysis, consumer behavior and location-based service technology, and specifically proposes a technical solution for analyzing the correlation between the travel behavior of bulk commodity consumers and online activities, and proposes a consumption probability prediction model solution based on hesitation analysis. The present invention provides a consumption probability prediction method based on hesitation analysis, and the overall process is as follows: Figure 1 As shown, in the input, the upstream data includes the arrival data table, the portrait data table, the portrait data appendix (place of residence) and the arrival method data table, and the self-built data includes the whitelist data table, the blacklist data table and the store dimension data table. In the intermediate results, a logical blacklist data table and a potential customer data table can be formed, and a business output table can be formed in the output. More specifically, in one embodiment, the following steps are included:

[0107] Step S1: Data collection

[0108] In the data collection step of the present invention, the consumer's online activity data (such as search records, browsing history, consultation content, etc.) and offline navigation software usage data (such as departure location, arrival time, route selection, etc.) are integrated, and the data is retrieved for navigation purposes. The Internet is searched and the names published on the official website and the recommended names are cross-checked and cross-compared to determine the accurate name and longitude and latitude coordinates. Finally, the target place is circled, the range is adjusted, and then cross-checked with third-party data to finally determine the spatial location of the point of sale.

[0109] Furthermore, the specific implementation methods of data collection include but are not limited to the following methods:

[0110] (1) Use the Internet to search and collect basic information about the sales outlets of each brand;

[0111] (2) Collect the mainstream brands of the commodity currently on the domestic market (including independent sub-brands);

[0112] (3) Use crawlers, customized interfaces and other data collection methods to collect basic information data of sales points from official websites and mainstream vertical media platforms (including sales point name, province, city, detailed address, map latitude and longitude coordinates), product categories, etc.;

[0113] (4) Determine the unique spatial correspondence between the sales points on the map;

[0114] (5) Determine the scope of visit behavior capture at the point of sale destination, including the store showroom and public areas outside the store (such as parking areas, parking lot entrances and exits, etc.);

[0115] (6) The third party provides the visit information (entry and exit time and length of stay) of the people entering the visit capture range, portrait information, arrival method, search, viewing, route planning and navigation travel data of the corresponding sales points.

[0116] Step S2: Data preprocessing

[0117] In the data preprocessing step of the present invention, the collected data is subjected to preprocessing operations such as cleaning, deduplication, and time alignment to ensure the consistency and comparability of the data. Finally, the destination data is associated with the brand, category, and surrounding environment to form data as point of sale dimension data.

[0118] Furthermore, in the specific implementation of data preprocessing, Figure 2 As shown, it includes the preprocessing of basic information data of the point of sale and the preprocessing of arrival data.

[0119] (1) Preprocessing of basic information data of sales points, including the following sub-steps:

[0120] a) Use the spatial search interface to search for keywords in the city where the store is located using the permutations and combinations of brand, name, and address. Each spatial query of each combination usually returns multiple results. The IDs obtained from all permutations and combinations are aggregated and counted for their occurrence times.

[0121] b) Sort the aggregated IDs by the number of occurrences, select the number of occurrences of the IDs ranked before the set value (e.g., 2) for comparison, if the number of occurrences of the first place is ≥ the set value (e.g., 7 times), it is considered that the ID of this store in the spatial data of the professional map vendor is this ID, otherwise, the store address is reverse geocoded and the distance is compared with the coordinates corresponding to the ID, and a comprehensive score is given based on the distance between the reverse geocoding and the coordinates corresponding to the ID and the number of ID occurrences, and finally the one with the highest score is selected as the store ID;

[0122] c) Check the ID determined by distance comparison on the maps of each map provider and make corrections based on the check results;

[0123] d) Compare the basic information data of the sales points collected by the vertical media platform to determine their relevance, and then complete the information such as sales categories and models that may be missing on the official website. Specifically, it includes:

[0124] 1) Use CPCA to normalize and standardize names and addresses;

[0125] 2) In the same province or city, the address and name are compared by similarity calculation. A score of 1 indicates an absolute match, a score of 0.8 or above indicates a very good match, a score of 0.7-0.8 requires spot check, and a score of less than 7 requires manual intervention.

[0126] 3) Through the above steps, the relationship between the stores on the vertical domain platform and the stores announced on the official website can be determined.

[0127] (2) Arrival data preprocessing, including the following sub-steps:

[0128] a) Arrival data includes arrival time, stay time, and departure time. Because the user's location information collection results are affected by multiple factors such as the positioning usage of the app, the user's usage habits, and network conditions, the stay time may be very short or even missing when collected within the capture range. This part of the abnormal data needs to be processed; the visit records with a stay time that is too short (less than 5 minutes) and entry and exit times outside the store's business hours are removed as abnormal data, and the stay time is null. Fill it with the mode;

[0129] b) Dimension reduction based on arrival time: According to the usual customer flow curve of commodity stores, 10:30-12:00 and 13.30-16:00 are usually the peak times for customers to arrive at the store. Therefore, the arrival data is reduced to peak-time store visits and non-peak-time store visits;

[0130] c) Dimensionality reduction based on store arrival date: Similarly, based on the characteristics of store arrivals on weekdays and holidays, the store arrival data is divided into store arrivals on weekdays and non-workdays;

[0131] d) Dimension reduction based on store arrival accuracy: Based on the method of arrival at the store, if the navigation destination is consistent with the store entering the capture fence, it is considered to be accurate store arrival, and other methods are considered to be inaccurate store arrival.

[0132] Step S3: Hesitation Analysis

[0133] Use statistical and machine learning algorithms (such as time series analysis, path analysis, cluster analysis, etc.) to conduct in-depth analysis of the pre-processed online and offline data, and establish a consumer hesitation model to explore the correlation and mutual influence between them.

[0134] Specifically, the method for determining the consumption hesitation model includes sub-steps: constructing hesitation indicators: destination search hesitation, destination planning hesitation, destination arrival hesitation, and destination arrival and departure hesitation.

[0135] A: If Figure 3 As shown, the destination search hesitation is determined as follows:

[0136] a1: Get the user's real destination from the preprocessed data;

[0137] a2: De-link destinations and compare categories and brands;

[0138] a3: Analyze the search behavior based on the point of sale dimension data, including:

[0139] i. Multiple brands and multiple stores: especially hesitant;

[0140] This may also mean that consumers are conducting extensive market research or are not clear about their needs. Further segmentation:

[0141] Multiple brands in completely different categories: extremely hesitant, in the early stages of exploration, with unclear consumer needs, conducting extensive research, and may still be in the overall planning stage;

[0142] Multiple brands in similar categories: The degree of hesitation is high. Consumers’ search behavior is relatively concentrated, but they are still comparing multiple brands. They have a clear understanding of the product category, but are uncertain about brand selection. They are conducting in-depth brand and product comparisons to find the best choice.

[0143] Consumers have moved from online preparation to offline travel, and have preliminarily selected some brands and categories and plan to check them out in person.

[0144] ii. Search only a single brand: generally hesitant;

[0145] Consumers have already determined the brand in their mind, which may also mean that they have a high degree of loyalty to the brand, are hesitant about the category and price, and hope to compare the categories and prices among multiple stores of the same brand. The degree of hesitation of such hesitant consumers can be further subdivided by combining the search frequency:

[0146] Low-frequency searches (1-2 times / week): Consumers have a certain level of knowledge about the brand and may only be doing preliminary research or confirming information. They are still considering the brand and are more likely to make decisions about going out to visit stores.

[0147] Medium frequency searches (3-4 times / week): The consumer is interested in the product and is seriously considering purchasing it, but has not yet made up his mind. He may be comparing different models or waiting for the right time.

[0148] High frequency search (5 times or more per week): Consumers are very interested in the brand, but are obviously hesitant and may be struggling with the specific model, price or whether to buy it;

[0149] Combined with the search frequency, the more hesitant and conflicted consumers are, the closer they are to making a decision at the current stage.

[0150] iii. Single brand with multiple stores: generally hesitant;

[0151] Consumers already have a clear brand choice in mind and may plan to compare prices. At this time, they are hesitant about the price and plan to compare the prices of products of the same brand among multiple stores. They may also be considering factors such as geographical location and service quality.

[0152] These hesitant consumers consider the distance between their residence and work place and the store to determine their inclination to choose a store:

[0153] Short distance (within 5km): The preference is high, and the convenience of going to the store is the main consideration;

[0154] Medium distance (5-15km): In the middle of the choice process, consumers weigh convenience and other factors and may be looking for better options or specific services;

[0155] Long distance (more than 15km): The preference is low, but if the store is chosen as the subsequent travel destination, it will be of great significance. Such consumers must have special reasons for giving up convenience, such as looking for unique products, better prices or services.

[0156] iv. Clear single store: no hesitation;

[0157] Consumers already have clear target brands and stores in mind. This type of search shows that consumers have clear goals. Although the goals are clear, there may still be last-minute hesitations or changes.

[0158] According to the analysis of search behavior hesitation, the higher the search hesitation, the earlier the consumer is in the offline store visit stage, the less clear the target store is, or even there is no target at all; the lower the hesitation, the clearer the consumer's target is, and the greater the possibility of subsequent visit to the store.

[0159] a4: Judgment conclusion in the decision-making stage of retrieval: Retrieval hesitation is divided into special hesitation, general hesitation, and no hesitation. The retrieval hesitation is sorted. The lower the hesitation, the closer it is to the final brand category and travel plan decision. Different marketing and promotion strategies can be formulated according to different hesitation levels to promote the reduction of consumer hesitation and influence the direction of consumer decision-making.

[0160] The hesitant consumer group is at the forefront of the decision-making process. Consider providing detailed brand and product comparison information in marketing promotion activities, highlighting the unique advantages of your own brand, providing more experience and trial services, and launching price matching or other preferential policies.

[0161] B: If Figure 4 As shown in Figure 2, the destination planning hesitation is determined as follows:

[0162] After choosing the brand and category, determine the destination planning hesitation. Usually, the consumption of bulk commodities is often planned to visit stores, so before the trip, we will make a plan in advance, planning what time and how to go to which stores.

[0163] b1: Analyze travel planning behavior based on point of sale data, including:

[0164] i.Multiple brands and multiple stores: especially hesitant;

[0165] Consumers are hesitant among a limited number of brand categories, but their willingness to travel and visit stores is already strong.

[0166] ii. Single brand, multiple stores: generally hesitant;

[0167] Consumers have already selected a brand, and have even visited multiple brands, preliminarily determined the category. Their planning behavior may include comparing and screening distances, travel methods, and the order of store visits. They may even have entered the price comparison stage.

[0168] iii. Single brand, single store: no hesitation;

[0169] Consumers have a very clear destination, and their planning behavior may be to confirm travel routes or determine public transportation transfer methods.

[0170] Combined with the planned travel mode analysis:

[0171] Driving: This type of consumer may already have a car, and the hesitation factor may be the road conditions. This purchase may be a replacement or additional purchase;

[0172] Public transportation: This type of consumer may be a first-time buyer, and the hesitation factors may be the number of changes and the total time taken to arrive;

[0173] Walking / cycling: This type of customer prefers nearby stores, but is usually in the early stages of traveling to explore stores. Combined with subsequent planning data, if there are plans for distant stores of the same brand, it means that the decision-making stage is continuing to advance and is closer to the final decision;

[0174] b2: Judgment conclusions in the planning decision-making stage: Planning hesitation is divided into special hesitation, general hesitation, and no hesitation. The plans are sorted according to the planning hesitation. The lower the hesitation, the closer it is to the final store selection decision. Different targeted marketing methods can be used to guide consumers' decisions based on different levels of hesitation and consumers' target brands and stores.

[0175] C: Figure 5 As shown, the hesitation of reaching the destination is determined as follows:

[0176] Destination arrival hesitation is a comprehensive indicator that reflects the degree of uncertainty in the process from the consumer's purchase intention to the actual visit to the store. This indicator is affected by multiple factors:

[0177] Planning cycle: the length of time from initial idea to actual action;

[0178] Geographical factors: store location, transportation convenience, etc.

[0179] Destination search behavior: frequency and depth of online searches for store information;

[0180] Store route planning: select travel mode and plan route;

[0181] Actual travel behavior: whether the trip was made as planned, whether there were any additional visits, etc.

[0182] Usually when consumers decide to visit a store, their travel behavior consists of three actions: store search, store route planning, and travel navigation. First, determine the store's geographical location, then select a travel method (such as driving, public transportation, cycling, etc.) to plan the route, check the distance to the destination, the difficulty of reaching the destination, and determine the pre-selected travel route; finally, actually go to visit the store on the planned travel date.

[0183] Analyze the arrival hesitation of the destination based on the point of sale dimension data, including:

[0184] i. Arrive only at the planned store: no hesitation;

[0185] Characteristics: Consumers have clear goals and know what they want to buy; they may have done sufficient research;

[0186] Store visit behavior is highly consistent with expected plans;

[0187] Decision-making stage: The final decision is imminent and the purchase intention is strong;

[0188] Conversion rate expectation: High

[0189] ii. Not only arrived at the planned stores, but also visited other unplanned stores: generally hesitant;

[0190] Characteristics: Haven't made up their mind yet; want to make more comparisons in addition to the planned stores; decision may be affected by new information after field investigation;

[0191] Decision stage: close to the final decision, but still making final comparisons;

[0192] Conversion rate expectation: Medium

[0193] iii. Arrival at unplanned stores, not arriving at the originally planned stores, but arriving at other stores: particularly hesitant;

[0194] Characteristics: Consumers may only have preliminary interest; original plans may change due to various reasons (such as long distance, inconvenience in arrival); pre-selected brands may be changed;

[0195] Decision stage: Early in the decision stage, needs or preferences may change significantly;

[0196] Conversion rate expectation: Low.

[0197] iv. No arrival, no arrival at any store: Very hesitant

[0198] Characteristics: They may just check the store information on impulse; they may not have a strong desire to buy and may just be exploring; they may be limited by objective factors such as time and distance;

[0199] Decision stage: the earliest stage of the decision-making process, which may not yet have entered the actual purchase consideration stage. Conversion rate expectation: extremely low.

[0200] c2: Judgment conclusion at the decision-making stage when arriving at the destination: The destination hesitation degree is divided into special hesitation, general hesitation, and no hesitation. The destinations are sorted according to the hesitation degree. The lower the hesitation degree, the closer to the final purchase decision. It can be based on different hesitation degrees and consumers.

[0201] From the time dimension analysis: the longer the time interval between planning and arrival, the higher the hesitation level. The arrival time on weekdays vs. weekends may reflect different purchase urgency, with higher urgency on weekdays.

[0202] From the spatial dimension: the closer the distance between the residence / workplace and the target store is, the higher the convenience is and the lower the hesitation is likely to be; on the contrary, if the original plan is still adhered to, it may indicate a strong purchase intention;

[0203] From the visit frequency analysis: multiple visits to the store may indicate strong interest and deeper hesitation;

[0204] Analyzing the number of brands visiting stores: Visits to the same brand may indicate that customers have a high degree of loyalty to the brand or have already selected the brand, and are likely to be comparing prices and are very close to making a final decision; visits to stores of different brands may indicate that customers have already determined their preferred model and are making the final comparison and decision;

[0205] Marketing strategy: For the group without hesitation, we should strengthen the purchasing confidence and provide a convenient transaction process; for the group with general hesitation, we should provide detailed product comparison information and highlight the unique advantages; for the group with special hesitation, we should increase brand exposure, provide more experience opportunities, and provide more choices and comparison tools;

[0206] D: If Figure 6 As shown, the method for determining the hesitation of arriving at the destination and leaving is as follows:

[0207] The hesitation model determines consumer behavior.

[0208] Destination hesitation includes not only in-store behavior, but also a range of behaviors after leaving the store, including visits to other stores and possible return visits.

[0209] Analyze the hesitation of arriving and leaving the destination based on the point of sale dimension data, including:

[0210] Analysis of the length of time consumers stay in the store:

[0211] i. They stayed in the store for a long time (more than 30 minutes) and learned about the products in depth, but ultimately did not buy:

[0212] General hesitation

[0213] Characteristics: Show strong interest in the product; Learn more about the product; Decision stage: Close to purchase, but still have final concerns

[0214] Likelihood of returning to the store: High

[0215] ii. They stay in the store for a normal time (20-30 minutes), check out the products but leave without further understanding: generally hesitant

[0216] Characteristics: Interested in the product, but not strong enough;

[0217] Decision stage: Still in the consideration stage, need more information or time

[0218] Possibility of returning to the store: Medium

[0219] iii. Stay in the store for a short time (less than 20 minutes), quickly browse and leave quickly: very hesitant

[0220] Characteristics: Shows little interest in the product; leaves quickly, seemingly losing interest;

[0221] Decision stage: May re-evaluate needs or consider other options

[0222] Likelihood of returning to the store: Low

[0223] Combined with the analysis of consumer behavior patterns after leaving the store:

[0224] iv. Returning to the store after leaving it without visiting any other stores in between: no hesitation;

[0225] The behavior of returning to the store after leaving the store has positive significance, especially when there is no visit to other stores. It shows that consumers are relatively satisfied with the visit experience of the target store and the chance of conversion is very high;

[0226] v. Visit 1-3 more stores after leaving the store: generally hesitant;

[0227] vi. Visit more than 3 stores after leaving the store: especially hesitant;

[0228] vii. No visit to the store after leaving the store: particularly hesitant;

[0229] Combined with the analysis of the number of times consumers return to the store:

[0230] i. Return to the store 1-2 times after leaving the store: no hesitation;

[0231] Consumers visit the store for the first time to learn more.

[0232] According to the survey results of automobile sales stores, the conversion rate of first-time store visits is less than 10%, while the conversion rate of second and third visits is as high as 30%. As the number of visits increases, the conversion rate decreases significantly, indicating that consumers maintain a low level of hesitation during the first three visits. At this time, through appropriate marketing methods, consumers are most likely to consume at the first destination;

[0233] ii. Return to the store 3 times after leaving the store: generally hesitant;

[0234] iii. Return to the store more than 3 times after leaving the store: particularly hesitant;

[0235] Conclusion on the hesitation degree of leaving after arriving at the destination: The hesitation degree of leaving after arrival is divided into special hesitation, general hesitation, and no hesitation, and is sorted according to the hesitation degree of the destination. The lower the hesitation degree, the higher the conversion rate.

[0236] Marketing strategy suggestions:

[0237] The group that does not hesitate: provide discounts or limited-time promotions to promote quick decision-making; strengthen product advantages and provide exclusive customer service; simplify the purchase process and provide convenient payment options;

[0238] Generally hesitant groups: provide detailed product comparison information; arrange in-depth experience activities; provide flexible purchase plans;

[0239] Special hesitant groups: increase brand exposure, provide basic educational content, and provide pressure-free consulting services;

[0240] Invite people to participate in brand activities and enhance emotional connections.

[0241] In other embodiments of the present invention, a device for running the above method is also provided, such as Figure 7 As shown, including:

[0242] A data collection module is used to collect data, including consumer online activity data and offline navigation software usage data, and determine the point of sale space location and product brand information from the collected data;

[0243] A data preprocessing module is used to preprocess the collected data to form point-of-sale dimension data;

[0244] The data mining module is used to mine the correlation and mutual influence between the sales point dimension data and make consumption probability prediction based on hesitation analysis.

[0245] In other embodiments of the present invention, a computer-readable storage medium for running the above method is also provided.

[0246] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, limit the units themselves.

[0247] According to one aspect of an embodiment of the present invention, a computer program product or a computer program is provided, the computer program product or the computer program includes a computer instruction, and the computer instruction is stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in the above various optional implementations.

[0248] As another aspect, an embodiment of the present invention further provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

Claims

1. A consumption probability prediction method based on hesitation analysis, characterized in that: The following steps are involved: Collect data, including consumer online activity data and offline navigation software usage data, and determine the point-of-sale space location and product brand information from the collected data; The collected data is pre-processed based on a computer processor running a program to form point-of-sale dimension data; The computer processor runs a program to mine the correlation and mutual influence between the point-of-sale dimension data, and makes consumption probability prediction based on hesitation analysis.

2. The consumption probability prediction method based on hesitation analysis according to claim 1 is characterized in that: The method of determining the spatial location of the point of sale from the collected data specifically includes the following sub-steps: searching the collected data through the Internet, cross-checking and comparing the names disclosed on the official website and the recommended names to determine the accurate name of the point of sale and the longitude and latitude coordinates, and finally circling the target location, adjusting the range, and cross-checking with third-party data to finally determine the spatial location of the point of sale.

3. The consumption probability prediction method based on hesitation analysis according to claim 2 is characterized in that: The consumer's online activity data includes search records, browsing history and consultation content; the offline navigation software usage data includes departure location, arrival time, route selection, entry and exit time, length of stay, portrait information, arrival method, corresponding sales point search, viewing, route planning and navigation travel data; the product brand information includes independent sub-brands; the adjustment range specifically includes the capture range of visit behavior of the designated sales point destination, which includes the store showroom and public areas outside the store.

4. The consumption probability prediction method based on hesitation analysis according to claim 1 is characterized in that: The preprocessing of the collected data to form point-of-sale dimension data specifically includes sub-steps: preprocessing operations such as cleaning, deduplication, and time alignment of the collected data to ensure consistency and comparability of the data, and finally associating the destination data with the brand, category, and surrounding environment to form the data as the point-of-sale dimension data.

5. The consumption probability prediction method based on hesitation analysis according to claim 4 is characterized in that: The preprocessing of the collected data specifically includes preprocessing of basic information data of the point of sale, and the preprocessing of basic information data of the point of sale specifically includes sub-steps: a) Use the spatial search interface to search for keywords in the city where the store is located using the permutations and combinations of brand, name, and address. Each spatial query will return multiple results. The IDs obtained from all permutations and combinations are summarized and counted for their occurrences. b) Sort the aggregated IDs by the number of occurrences, select the number of occurrences of the first set value of the ID in the ranking for comparison, if the number of occurrences of the first place is ≥ the second set value, it is considered that the ID of this store in the spatial data of the professional map provider is this ID, otherwise, the store address is reverse geocoded and the distance is compared with the coordinates corresponding to the ID, and a comprehensive score is given based on the distance between the reverse geocoding and the coordinates corresponding to the ID and the number of ID occurrences, and finally the one with the highest score is selected as the store ID; c) Check the ID determined by distance comparison on the maps of each map provider and make corrections based on the check results; d) Compare the basic information data of the sales points collected by the vertical media platform to determine their relevance, and then complete the missing information on the official website, which includes the categories and models of products sold.

6. The consumption probability prediction method based on hesitation analysis according to claim 4 is characterized in that: The preprocessing of the collected data specifically includes arrival data preprocessing, and the arrival data preprocessing specifically includes sub-steps: Arrival data includes stay duration and entry and exit time. Within the capture range, visit records with a stay duration less than the set value and entry and exit time outside the store's business hours are removed as abnormal data. If the stay duration is null, the mode is used to fill it in. Dimension reduction based on store arrival time: According to the customer flow curve of the merchandise store, the arrival data is reduced to peak-time store arrivals and off-peak-time store arrivals; Dimensionality reduction based on store arrival date: Based on the characteristics of store arrival on weekdays and holidays, store arrival data is divided into store arrival on weekdays and store arrival on non-workdays; Dimensionality reduction based on store visit accuracy: distinguish accurate store visits and inaccurate store visits based on store visit methods; The methods of distinction include: if the navigation destination is consistent with the store entering the capture fence, it is regarded as accurate store, otherwise it is regarded as inaccurate store.

7. The consumption probability prediction method based on hesitation analysis according to claim 5 is characterized in that: The above method compares the basic information data of the sales points collected by the vertical media platform to determine their relevance, and then completes the missing information on the official website, specifically including the following sub-steps: 1) Normalize and standardize names and addresses; 2) In the same province or city, the similarity of addresses and names is calculated and compared, and the scores are used to distinguish between absolute matches, very similar matches, situations that require spot checks, and situations that require manual intervention.

8. The consumption probability prediction method based on hesitation analysis according to any one of claims 1 to 7, characterized in that: The mining of the correlation and mutual influence between the point-of-sale dimension data and the prediction of consumption probability based on hesitation analysis specifically include the following sub-steps: Construct a consumer hesitation analysis model, which specifically includes destination search hesitation, destination planning hesitation, destination arrival hesitation, and destination arrival and departure hesitation, and use the analysis of consumer hesitation to predict consumption probability.

9. The consumption probability prediction method based on hesitation analysis according to claim 8 is characterized in that: The method for determining the destination search hesitation specifically includes the following sub-steps: a1: Get the user's real destination from the preprocessed data; a2: De-link destinations and compare categories and brands; a3: Analyze retrieval behavior from point-of-sale dimension data; a4: Based on the analysis of retrieval behavior, a judgment conclusion is formed in the decision-making stage of retrieval: the retrieval hesitation is divided into special hesitation, general hesitation, and no hesitation, and sorted according to the retrieval hesitation. The lower the hesitation, the closer it is to the final brand category and travel plan decision.

10. The consumption probability prediction method based on hesitation analysis according to claim 8, characterized in that: The method for determining the destination planning hesitation degree specifically includes the following sub-steps: b1: Analyze travel planning behavior based on point-of-sale dimension data; b2: Based on planning behavior analysis, a judgment conclusion is formed in the planning decision-making stage: the destination planning hesitation is divided into special hesitation, general hesitation and no hesitation, and is sorted according to the planning hesitation. The lower the hesitation, the closer it is to the final store selection decision.

11. The consumption probability prediction method based on hesitation analysis according to claim 8, characterized in that: The method for determining the destination arrival hesitation specifically includes the following sub-steps: c1: Analyze the destination arrival hesitation based on the point of sale dimension data; c2: Based on the hesitation analysis of whether the destination has been reached, a judgment conclusion is formed at the decision-making stage of reaching the destination: the hesitation of reaching the destination is divided into special hesitation, general hesitation, and no hesitation. The destinations are sorted according to the hesitation degree. The lower the hesitation degree, the closer to the final purchase decision.

12. The consumption probability prediction method based on hesitation analysis according to claim 8, characterized in that: The method for determining the hesitation degree of arriving at and then leaving the destination specifically comprises the following sub-steps: d1: Analyze the arrival hesitation of arriving at the destination and then leaving the destination based on the point of sale dimension data; d2: Based on the analysis of the length of time consumers stay in the store, a conclusion is formed: the hesitation to leave after arrival is divided into very hesitant, generally hesitant, and no hesitation, and sorted according to the hesitation degree of the destination. The lower the hesitation degree, the higher the conversion rate.

13. The consumption probability prediction method based on hesitation analysis according to claim 8, characterized in that: The method for determining the hesitation degree of arriving at the destination and then leaving the destination also includes the following sub-steps: combining the analysis of the consumer's behavior pattern after leaving the store, specifically including the following situations: If the consumer returns to the store after leaving it and does not visit other stores in between, it is judged as no hesitation; If consumers visit 1-3 more stores after leaving the store, it is judged as general hesitation; If the consumer visits more than three stores after leaving the store or does not visit any store, they are judged to be particularly hesitant.

14. The consumption probability prediction method based on hesitation analysis according to claim 8, characterized in that: The method for determining the hesitation degree of arriving at the destination and then leaving the destination also includes the following sub-steps: combining the analysis of the number of times the consumer returns to the store, specifically including the following situations: If they return to the store 1-2 times after leaving the store, they are judged as not hesitating; If the customer returns to the store three times after leaving the store, he / she will be judged as having general hesitation; Returning to the store more than 3 times after leaving: Very hesitant.

15. The consumption probability prediction method based on hesitation analysis according to claim 8, characterized in that: After using the analysis of consumer hesitation to predict the probability of consumption, the following steps are also included: formulating different marketing and promotion strategies according to different levels of hesitation to reduce consumer hesitation and influence the direction of consumer decision-making, including the following situations: Offer discounts or limited-time promotions to the undecided group to promote quick decision-making, strengthen product advantages, provide dedicated customer service, and simplify the purchase process and provide convenient payment options; Provide detailed product comparison information, arrange in-depth experience activities, and provide flexible purchasing plans for the general hesitant group; For particularly hesitant groups, increase brand exposure, provide basic educational content, offer pressure-free consulting services, invite them to participate in brand activities, and enhance emotional connections.

16. A consumption probability prediction device based on hesitation analysis, characterized in that: include: A data collection module is used to collect data, including consumer online activity data and offline navigation software usage data, and determine the point of sale space location and product brand information from the collected data; A data preprocessing module, used to preprocess the collected data based on a computer processor running a program to form point-of-sale dimension data; The data mining module is used to mine the correlation and mutual influence between the sales point dimension data based on the computer processor running the program, and to predict the consumption probability based on the hesitation analysis.

17. A computer-readable storage medium, characterized in that: A computer program is stored in a readable storage medium, and when the computer program is loaded by a processor, the method according to any one of claims 1 to 8 is executed.

18. A consumption probability prediction system based on hesitation analysis, characterized in that: Including the consumption probability prediction device based on hesitation analysis as described in claim 16.

Images