A person classification method, electronic device, medium, and program product

Abstract

The application relates to the technical field of data management, in particular to a personnel classification method, an electronic device, a medium and a program product. The method comprises the following steps: obtaining historical shopping data of a to-be-identified personnel, and identifying shopping features of the historical shopping data and feature values corresponding to each shopping feature; determining matching degrees between the to-be-identified personnel and each preset preferential strategy based on the shopping features, the feature values corresponding to each shopping feature, and matching data corresponding to each preset preferential strategy, wherein the matching data corresponding to each preset preferential strategy comprises matching features and matching feature values corresponding to each matching feature; when the matching degrees between the to-be-identified personnel and each preset preferential strategy are all lower than corresponding preset standard matching degrees, determining that the to-be-identified personnel is a target personnel; adding the target personnel to a strategy customization queue, and feeding back the strategy customization queue. The application reduces the data processing amount when determining the preferential strategy of a consumer, so that the rate of pushing the preferential strategy to the consumer is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data management, in particular to a personnel classification method, an electronic device, a medium and a program product. BACKGROUND

[0002] In a competitive market environment, preferential activities are an important means for merchants to distinguish themselves from competitors. By providing more attractive and personalized preferential activities, more consumer attention and participation can be attracted, thereby improving brand exposure and recognition while leading the merchant to stand out in the market. During the preferential activities, the merchant can increase sales, expand brand awareness and influence, attract new customers and retain old customers, promote inventory clearance and new product promotion, etc.

[0003] In related technologies, the total consumption, shopping type, purchase frequency, etc. contained in the shopping data of consumers are generally calculated and compared multiple times to determine the appropriate preferential strategy for the consumer and push the preferential strategy. However, when the number of consumers is large, the amount of data processing required for calculation and comparison will also increase, which may result in a decrease in efficiency when pushing the preferential strategy to the consumer. SUMMARY

[0004] In order to reduce the amount of data processing when determining the preferential strategy for the consumer and improve the rate of pushing the preferential strategy to the consumer, the present application provides a personnel classification method, an electronic device, a medium and a program product.

[0005] In a first aspect, the present application provides a personnel classification method, which adopts the following technical solution:

[0006] A personnel classification method comprises:

[0007] Obtaining historical shopping data corresponding to a to-be-identified person, and identifying shopping features corresponding to the historical shopping data and feature values corresponding to each shopping feature;

[0008] Based on the shopping features and the feature values corresponding to each shopping feature, and matching data corresponding to each preset preferential strategy, determining a matching degree between the to-be-identified person and each preset preferential strategy, wherein the matching data corresponding to each preset preferential strategy comprises matching features and matching feature values corresponding to each matching feature;

[0009] When the matching degree between the to-be-identified person and each preset preferential strategy is lower than a corresponding preset standard matching degree, determining that the to-be-identified person is a target person;

[0010] Adding the target person to a strategy customization queue, and feeding back the strategy customization queue, wherein the personnel in the strategy customization queue are personnel who need to customize a preferential strategy.

[0011] By adopting the technical scheme, the historical shopping data of the to-be-identified person is matched with the matching data corresponding to each preset preferential strategy, so as to quickly identify the target person who does not match the current preset preferential strategy, thereby narrowing the target range of subsequent data processing, effectively reducing the data processing amount when determining the preferential strategy of the consumer, and classifying the to-be-identified person who matches the current preset preferential strategy and the to-be-identified person who does not match the current preset preferential strategy, so as to facilitate subsequent feedback of the preset preferential strategy matching the to-be-identified person without the need of determining and pushing the corresponding preferential strategy after multiple data identification and calculation for all to-be-identified persons, thereby improving the rate of pushing the preferential strategy to the to-be-identified person.

[0012] In a possible implementation manner, after the target person is added to the strategy customization queue, the method further includes:

[0013] identifying a total consumption amount, a purchase commodity type proportion, and a purchase frequency contained in historical shopping data of the target person, the historical shopping data being shopping data in a first preset time period, the purchase commodity type being a proportion between high-sales commodity and low-sales commodity;

[0014] determining a preferential value of the target person based on the total consumption amount, the purchase commodity type proportion, and the purchase frequency;

[0015] determining a target preferential strategy corresponding to the target person according to the preferential value and a preset strategy mapping relationship, and pushing the target preferential strategy to the target person, the preset strategy mapping relationship being a corresponding relationship between a preferential value and a target preferential strategy.

[0016] By adopting the technical scheme, the total consumption amount, the purchase commodity type, and the purchase frequency in the historical shopping data of the target person are identified and analyzed, so as to understand the consumption habit and preference of the target person, thereby facilitating determination of the individualized preferential strategy for the target person, improving the adaptation degree between the historical shopping situation of the target person and the pushed preferential strategy, and facilitating enhancement of the satisfaction degree of the target person in the consumption process.

[0017] In a possible implementation manner, the determining of the preferential value of the target person based on the total consumption amount, the purchase commodity type proportion, and the purchase frequency includes:

[0018] determining a first representative value corresponding to the total consumption amount according to a first conversion proportion mapping relationship, the first conversion proportion mapping relationship being a corresponding relationship between a total consumption amount and a first representative value;

[0019] According to the purchase commodity type proportion and the second conversion proportion mapping relationship, a second representative value corresponding to the purchase commodity type proportion is determined, and the second conversion proportion mapping relationship is a corresponding relationship between the purchase commodity type proportion and the second representative value.

[0020] According to the purchase frequency and the third conversion proportion mapping relationship, a third representative value corresponding to the purchase frequency is determined, and the third conversion proportion mapping relationship is a corresponding relationship between the purchase frequency and the third representative value.

[0021] Based on the first representative value, the second representative value, and the third representative value, the target person's preferential value is determined.

[0022] By using the above technical solution, by converting the three key indicators of total consumption, purchase commodity type proportion, and purchase frequency into numerical values, the original shopping data is converted into more representative numerical values, i.e. first representative value, second representative value, and third representative value. This numerical conversion helps to more finely evaluate the consumption habits of the target person. In addition, by converting multiple characteristic values into a representative value, it is convenient to fuse and calculate multiple characteristics, thereby providing more accurate data support for subsequent preferential strategy determination.

[0023] In a possible implementation manner, the determination of the target person's preferential value based on the first representative value, the second representative value, and the third representative value comprises:

[0024] A preset conversion coordinate system is determined according to the total consumption, the purchase commodity type proportion, and the purchase frequency, and the preset conversion coordinate system includes flow-through representative values corresponding to the total consumption, the purchase commodity type proportion, and the purchase frequency respectively;

[0025] The first representative value is introduced into the preset conversion coordinate system, and a first to-be-stacked value is determined according to the flow-through representative value corresponding to the first representative value;

[0026] The second representative value and the first to-be-stacked value are introduced into the preset conversion coordinate system, and a second to-be-stacked value is determined according to the flow-through representative value corresponding to the second representative value;

[0027] The third representative value and the second to-be-stacked value are introduced into the preset conversion coordinate system, and the target person's preferential value is obtained.

[0028] By using the above technical solution, since the total consumption, the purchase commodity type proportion, and the purchase frequency all affect the determination process of the final preferential strategy, when the target person's preferential value is determined, the correlation degree between multiple dimensions is established by numerical stacking, and this multi-dimensional evaluation method with correlation facilitates improving the accuracy and comprehensiveness of the evaluation result.

[0029] In a possible implementation, the first to-be-stacked value is determined according to the flow representative value corresponding to the first representative value, including:

[0030] According to the first representative value and the flow representative value corresponding to the first representative value, an overflow representative value is determined, the overflow representative value being a part of the first representative value that is higher than the corresponding flow representative value;

[0031] The overflow representative value is subjected to mean value calculation to obtain an average overflow representative value, and the average overflow representative value is determined as the first to-be-stacked value.

[0032] By using the above technical solution, since the discount strategy of the target person is determined according to the discount value obtained by stacking each representative value, the discount strategy is selected and determined from a large number of preset discount strategies, and therefore, when a single representative value is abnormal or mutated, the final determination result can be directly affected. By determining the to-be-stacked value after mean value calculation of the overflow representative value, it is convenient to reduce the influence of data abnormality or mutation on the determination result.

[0033] In a possible implementation, the method further includes:

[0034] Obtaining a transaction order in a second preset time period and a used discount strategy corresponding to each transaction order;

[0035] Identifying a gift content included in each used discount strategy, the gift content including a gift name and a gift quantity;

[0036] Obtaining a gift inventory data, determining a to-be-adjusted discount strategy according to each gift content and the gift inventory data, and feeding back the to-be-adjusted discount strategy.

[0037] By using the above technical solution, by identifying the gift content and quantity in the used discount strategy and combining the current gift inventory data, it is convenient to accurately grasp the consumption of the gift, which helps the merchant to reasonably arrange the procurement and inventory of the gift, so as to avoid the situation of inventory accumulation or shortage. In addition, by obtaining and analyzing the transaction order in the second preset time period and the used discount strategy corresponding thereto, the actual application effect of the discount strategy can be understood in real time, so that the merchant can adaptively adjust the discount strategy to adapt to market changes and consumer demand.

[0038] In a second aspect, the application provides an electronic device, which adopts the following technical solution:

[0039] An electronic device, the electronic device including:

[0040] At least one processor;

[0041] a memory;

[0042] at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to perform the above-mentioned personnel classification method.

[0043] In a third aspect, the present application provides a computer-readable storage medium, which adopts the technical scheme as follows:

[0044] A computer-readable storage medium, comprising: a computer program stored therein and capable of being loaded and executed by a processor to perform the above-mentioned personnel classification method.

[0045] In a fourth aspect, the present application provides a computer program product, which adopts the technical scheme as follows:

[0046] A computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the above-mentioned personnel classification method.

[0047] In summary, the present application has at least one of the following beneficial technical effects:

[0048] By matching the historical shopping data of the to-be-identified personnel with the matching data corresponding to each preset preferential policy, the target personnel who do not match the current preset preferential policy can be quickly identified, so that the target range of subsequent data processing can be narrowed, the data processing amount when determining the preferential policy of the consumer can be effectively reduced, in addition, by classifying the to-be-identified personnel who match the current preset preferential policy and the to-be-identified personnel who do not match the current preset preferential policy, the preset preferential policy that matches the to-be-identified personnel can be directly fed back in the subsequent process, without the need to determine and push the corresponding preferential policy after multiple data identification and calculation for all to-be-identified personnel, so that the rate of pushing the preferential policy to the to-be-identified personnel can be improved.

[0049] By converting the three key indicators of the total consumption amount, the proportion of the purchased commodity type and the purchase frequency into numerical values, the original shopping data is converted into more representative numerical values, i.e. the first representative value, the second representative value and the third representative value, which helps to more finely evaluate the consumption habits of the target personnel, in addition, by converting a plurality of characteristic values into a representative value, a plurality of characteristics can be fused and calculated, so as to provide more accurate data support for subsequent preferential policy determination. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 is a flowchart of a personnel classification method in an embodiment of the present application;

[0051] Figure 2is a flowchart of a method for determining push content in an embodiment of the present application.

[0052] Figure 3 is a schematic diagram of coordinate system conversion in an embodiment of the present application.

[0053] Figure 4 is a structural schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be described in detail below with reference to the accompanying drawings. Figures 1-4 The present application will be further described in detail.

[0055] Those skilled in the art can make modifications to the present embodiments without creative contribution after reading the present specification, and as long as the modifications are within the scope of the claims of the present application, they are protected by the patent law.

[0056] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative contribution fall within the scope of protection of the present application.

[0057] Specifically, the present embodiments provide a personnel classification method, which is executed by an electronic device. The electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication, and the present embodiments do not limit this.

[0058] Reference Figure 1 , Figure 1 is a flowchart of a personnel classification method in an embodiment of the present application. The method comprises steps S110-S140, wherein:

[0059] Step S110: Obtain historical shopping data corresponding to a to-be-identified person, and identify shopping features corresponding to the historical shopping data and feature values corresponding to each shopping feature.

[0060] Specifically, the to-be-identified personnel can be personnel who have purchased goods in a historical period, i.e., old customers, or can be personnel who have browsed corresponding goods but have not purchased the goods, i.e., new customers. Since the to-be-identified personnel can be old customers or new customers, the historical shopping data corresponding to the to-be-identified personnel can be empty or not empty. The historical period can be 30 days or 45 days before the current time, and the specific historical period is not limited in the embodiments of the present application. The shopping features can include a total consumption, i.e., a total consumption in the historical period, a purchase type proportion, i.e., a proportion of different types of goods in the purchased goods in the historical period, and a purchase frequency. The specific shopping features are not limited in the embodiments of the present application, and can be set by relevant staff. The feature values corresponding to each shopping feature can be determined from the historical shopping data through feature recognition.

[0061] Step S120: Based on the shopping features and the feature values corresponding to each shopping feature, and the matching data corresponding to each preset preferential strategy, the matching degree between the to-be-identified personnel and each preset preferential strategy is determined. The matching data corresponding to each preset preferential strategy includes matching features and matching feature values corresponding to each matching feature.

[0062] Specifically, the preset preferential strategy is uploaded to the electronic device by the relevant staff according to a large amount of actual use data. The number of preset preferential strategies is not limited in the embodiments of the present application. The actual use data includes the use object of each preferential strategy. The relevant staff can determine the preferential strategy that is used more frequently according to a large amount of actual use data, and use it as a preset preferential strategy. The personnel suitable for each preset preferential strategy can be different. For example, the number of personnel using the preset preferential strategy a exceeds a preset number, and most of the users correspond to a total consumption of 1w or less. At this time, the preset preferential strategy a can be determined as one of the preset preferential strategies. Although most of the users using the preset preferential strategy a correspond to a total consumption of 1w or less, it does not mean that the personnel with a total consumption of 1w or less are suitable for the preset preferential strategy a. It can be explained that the preset preferential strategy a can be the first choice for the to-be-identified personnel with a total consumption of 1w or less. Different preset preferential strategies can be aimed at different suitable populations, but can be the first choice when aiming at the corresponding suitable population.

[0063] Different preset preferential strategies also correspond to use conditions, i.e., when the to-be-identified personnel needs to use a certain preset preferential strategy, the historical shopping data needs to be matched with the preset preferential strategy, and then it is judged whether it can be used according to the matching result. Each preset preferential strategy also includes matching feature values and matching feature values corresponding to each matching feature value. For example, the matching feature corresponding to the preset preferential strategy a is the matching total consumption, and only the consumer whose matching total consumption is within 8k-1w has the opportunity to use the preset preferential strategy.

[0064] The historical shopping data of the to-be-identified person is matched with the matching data of each preset preferential policy, to obtain a matching degree between the to-be-identified person and each preset preferential policy, and the higher the matching degree is, the higher the adaptability between the to-be-identified person and the corresponding preset preferential policy is. The shopping features correspond to the matching features, the matching degree between the to-be-identified person and each preset preferential policy is calculated as the sum of the sub-matching degrees of all the shopping features and the corresponding matching features, and the specific manner of calculating the matching degree is not limited in the embodiments of the present application.

[0065] Step S130: When the matching degrees between the to-be-identified person and each preset preferential policy are all lower than the corresponding preset standard matching degrees, it is determined that the to-be-identified person is the target person.

[0066] Step S140: The target person is added to a strategy customization queue, and the strategy customization queue is fed back, and the person in the strategy customization queue is a person who needs to customize a preferential policy.

[0067] Specifically, each preset preferential policy has a corresponding preset standard matching degree, and the specific preset standard matching degree is not limited in the embodiments of the present application. When the matching degrees between the historical shopping data features of the to-be-identified person and each preset preferential policy are not higher than any preset standard matching degree, it is indicated that the existing preset preferential policy is not adapted to the actual shopping situation of the to-be-identified person, and at this time, the to-be-identified person can be determined as the target person. The strategy customization queue is used to store the historical shopping data of the target person, and when the to-be-identified person is the target person, it is indicated that the to-be-identified person cannot be pushed the preferential policy by directly feeding back the preferential policy, but needs to be selected the preferential policy suitable for the target person from the multiple preset preferential policies after subsequent calculation and processing. When the target person is identified, the target person is not written into the strategy customization queue to wait for subsequent operation, but the processing operation of the electronic device is stopped, so as to reduce the influence on the pushing efficiency.

[0068] By matching the historical shopping data of the to-be-identified person with the matching data corresponding to each preset preferential policy, the target person who does not match the current preset preferential policy can be quickly identified, so as to narrow the target range of subsequent data processing, effectively reduce the data processing amount when determining the preferential policy of the consumer, and further, by classifying the to-be-identified person who matches the current preset preferential policy and the to-be-identified person who does not match the current preset preferential policy, the preset preferential policy matching the to-be-identified person can be directly fed back in the subsequent process, without the need of determining and pushing the corresponding preferential policy after multiple data identification and calculation for all the to-be-identified persons, so as to improve the rate of pushing the preferential policy to the to-be-identified person.

[0069] Further, after the target person is added to the strategy customization queue, steps S1-S3 are further included, as shown in Figure 2 wherein:

[0070] Step S1: identifying a total consumption amount, a purchase product type proportion, and a purchase frequency contained in historical shopping data of the target person, the historical shopping data being shopping data in a first preset time period, the purchase product type being a proportion between a high-sales product and a low-sales product.

[0071] Specifically, the first preset time period can be 30 days before the current time or 45 days before the current time, and a specific duration corresponding to the first preset time period is not limited in the embodiments of the present application. The total consumption amount, the purchase product type proportion, and the purchase frequency have different representation forms in the historical shopping data, and can be identified from the historical shopping data through respective corresponding identifiers, and a specific identification manner is not limited in the embodiments of the present application.

[0072] The high-sales product is a product whose sales volume is before a first preset rank in the first preset time period, and the low-sales product is a product whose sales volume is after a second preset rank in the first preset time period. The number of the high-sales product and the low-sales product can be one or more. Since popular products can be different in different periods, the high-sales product and the low-sales product can change over time. The purchase product type proportion is a ratio between a number of the high-sales products purchased and a number of the low-sales products purchased in the historical shopping data. Since the low-sales product has sales pressure for a merchant, the purchase product type proportion needs to be considered when determining a suitable preferential strategy for the target person.

[0073] Step S2: determining a preferential value of the target person based on the total consumption amount, the purchase product type proportion, and the purchase frequency.

[0074] Specifically, the total consumption amount, the purchase product type proportion, and the purchase frequency of the target person can intuitively reflect the consumption situation of the consumer. The total consumption amount is an important index for measuring the purchasing power and consumption level of the consumer, and the purchasing power of the consumer can be understood by analyzing the total consumption amount. The purchase product type proportion can reflect the purchase preference and demand structure of the consumer, and the purchase frequency is an important index for measuring the loyalty and purchase habit of the consumer. Therefore, the total consumption amount, the purchase product type proportion, and the purchase frequency need to be analyzed and determined when determining the suitable preferential strategy for the target person.

[0075] Further, in order to facilitate the fusion calculation of multiple features, the preferential value of the target person is determined based on the total consumption amount, the purchase product type proportion, and the purchase frequency, and specifically includes:

[0076] According to the total consumption and the first conversion proportion mapping relationship, a first representative value corresponding to the total consumption is determined, the first conversion proportion mapping relationship being a corresponding relationship between the total consumption and the first representative value; according to the purchase commodity type proportion and the second conversion proportion mapping relationship, a second representative value corresponding to the purchase commodity type proportion is determined, the second conversion proportion mapping relationship being a corresponding relationship between the purchase commodity type proportion and the second representative value; according to the purchase frequency and the third conversion proportion mapping relationship, a third representative value corresponding to the purchase frequency is determined, the third conversion proportion mapping relationship being a corresponding relationship between the purchase frequency and the third representative value; and the discount value of the target person is determined based on the first representative value, the second representative value and the third representative value.

[0077] Specifically, before the fusion of the multi-dimensional data, the multi-dimensional data needs to be normalized, so that the multi-dimensional data can adopt the same expression. Converting the total consumption, the purchase commodity type proportion and the purchase frequency into representative values is a way of data normalization. The specific way of normalizing the multi-dimensional data is not limited in the embodiments of the present application, as long as the multi-dimensional data can be fused after the data normalization.

[0078] The conversion proportion corresponding to different total consumption is different, and the first conversion proportion mapping relationship contains the conversion proportion corresponding to different total consumption. According to the conversion proportion corresponding to the total consumption, the first representative value corresponding to the total consumption can be directly obtained. The higher the total consumption, the higher the conversion proportion. However, in order to reduce the influence of abnormal data on the final result, the total consumption between different total consumption is not in direct proportion, for example, when the total consumption is 100,000, the corresponding conversion proportion may be 0.01; when the total consumption is 200,000, the corresponding conversion proportion may be 0.02; when the total consumption is 500,000, the corresponding conversion proportion may be 0.045. The specific content of the first conversion proportion mapping relationship is not limited in the embodiments of the present application, and can be analyzed and determined by relevant staff according to the actual situation and uploaded to the electronic device.

[0079] The conversion ratio corresponding to different shopping commodity type proportions is also different. The shopping commodity type proportion is the ratio of the number of high-selling commodities purchased to the number of low-selling commodities purchased in historical shopping data. Purchasing low-selling commodities can also reflect that a customer is willing to try or continuously purchase low-selling commodities of the brand, which can be new products or non-main products, while purchasing high-selling commodities, which are usually main products or popular products. This can also show that consumers fully recognize and trust the brand. Therefore, when determining the appropriate discount strategy for consumers, the shopping commodity type proportion of consumers also needs to be considered. The higher the shopping commodity type proportion, the more high-selling commodities and the fewer low-selling commodities a consumer purchases during shopping, and the lower the corresponding conversion ratio. The second conversion ratio mapping relationship includes the conversion ratio corresponding to different shopping commodity type proportions. The second representative value corresponding to the shopping commodity type proportion can be directly obtained according to the conversion ratio corresponding to the shopping commodity type proportion. The specific content of the second conversion ratio mapping relationship is not specifically limited in the embodiments of the present application and can be set by a person skilled in the relevant art.

[0080] The conversion ratio corresponding to different purchase frequencies is different. The third conversion ratio mapping relationship includes the conversion ratio corresponding to different purchase frequencies. The third representative value corresponding to the purchase frequency can be directly obtained according to the conversion ratio corresponding to the purchase frequency. The higher the purchase frequency, the higher the corresponding conversion ratio. The specific content of the third conversion ratio mapping relationship is not specifically limited in the embodiments of the present application and can be set by a person skilled in the relevant art.

[0081] After the data normalization conversion of the total consumption, the purchase commodity type proportion, and the purchase frequency is performed through the first conversion ratio mapping relationship, the second conversion ratio mapping relationship, and the third conversion ratio mapping relationship, the first representative value, the second representative value, and the third representative value can be directly fused and superimposed. When the fusion and superimposition processing is performed, the first representative value, the second representative value, and the third representative value can be directly summed to determine the discount value of the target person. The calculation can also be performed in a flow conversion superimposition manner. The specific process can include:

[0082] A preset conversion coordinate system is determined according to the total consumption, the purchase commodity type proportion, and the purchase frequency. The preset conversion coordinate system includes the flow conversion representative value corresponding to each of the total consumption, the purchase commodity type proportion, and the purchase frequency. The first representative value is introduced into the preset conversion coordinate system, and the first to-be-superimposed value is determined according to the flow conversion representative value corresponding to the first representative value. The second representative value and the first to-be-superimposed value are introduced into the preset conversion coordinate system, and the second to-be-superimposed value is determined according to the flow conversion representative value corresponding to the second representative value. The third representative value and the second to-be-superimposed value are introduced into the preset conversion coordinate system to obtain the discount value of the target person.

[0083] Specifically, the preset conversion coordinate system corresponds to the number of shopping features, that is, the preset conversion coordinate system includes the total consumption, the purchase commodity type proportion, and the purchase frequency, as shown in Figure 3 Figure 3 The three indexes correspond to three shopping features, and the arrangement order between different indexes can be pre-set or randomly set. In the embodiment of the present application, the total consumption is located before the purchase commodity type proportion, and the purchase commodity type proportion is located before the purchase frequency. Different shopping features correspond to different flow representative values. When the representative value corresponding to a shopping feature is higher than the flow representative value, the excess part needs to be flowed to the next index. The flow representative value corresponding to the previous index is the starting value of the next index. After the representative value corresponding to the previous index is flowed, the to-be-stacked value is obtained. The representative value corresponding to the next index is stacked on the basis of the to-be-stacked value corresponding to the previous index. The first representative value and the second representative value are introduced into the preset conversion coordinate system in the same flow manner, and the representative value displayed in the third index area is the final discount value of the target person.

[0084] When determining the to-be-stacked value corresponding to each index, the part exceeding the corresponding flow representative value can be directly determined as the to-be-stacked value. For example, when the first representative value is 7 and the corresponding flow representative value is 5, the excess of 2 of the flow representative value can be directly determined as the first to-be-stacked value. Since a single representative value may be directly affected when an anomaly or mutation occurs, the to-be-stacked value can be determined by first determining the excess value of the flow representative value, and then performing mean value calculation on the excess value to determine the to-be-stacked value. Different indexes have different influences on the final determination result when an anomaly occurs. When the excess value corresponding to different indexes is subjected to mean value calculation, the corresponding mean value proportion can be determined according to historical experience data, that is, the mean value proportion corresponding to the excess value of the first representative value is 50%. When the excess value is 2, the first to-be-stacked value corresponding to the first representative value is 1. The mean value proportion corresponding to the excess value of the second representative value can be 25%. When the excess value is 2, the second to-be-stacked value corresponding to the second representative value is 0.5. The mean value proportion corresponding to different indexes, that is, different representative values, is not limited in the embodiment of the present application.

[0085] Figure 3 The three indexes correspond to three shopping features, and the arrangement order between different indexes can be pre-set or randomly set. In the embodiment of the present application, the total consumption is located before the purchase commodity type proportion, and the purchase commodity type proportion is located before the purchase frequency. Different shopping features correspond to different flow representative values. When the representative value corresponding to a shopping feature is higher than the flow representative value, the excess part needs to be flowed to the next index. The flow representative value corresponding to the previous index is the starting value of the next index. After the representative value corresponding to the previous index is flowed, the to-be-stacked value is obtained. The representative value corresponding to the next index is stacked on the basis of the to-be-stacked value corresponding to the previous index. The first representative value and the second representative value are introduced into the preset conversion coordinate system in the same flow manner, and the representative value displayed in the third index area is the final discount value of the target person. Figure 3 ​The first index region includes two sub-regions, a first sub-region has a display color lighter than a display color of a second sub-region, the first sub-region corresponds to a representative value not exceeding a corresponding flow representative value, and the second sub-region corresponds to a representative value exceeding the corresponding flow representative value, and a corresponding preferential policy is determined according to a representative value corresponding to the third index region.

[0086] Step S3: determining a target preferential policy corresponding to the target person according to the preferential value and the preset policy mapping relationship, and pushing the target preferential policy to the target person, the preset policy mapping relationship being a corresponding relationship between the preferential value and the target preferential policy.

[0087] Specifically, the third index region includes preferential policy indexes, the preset policy mapping relationship includes preferential values corresponding to different preferential policies, the preferential policies in the third index region are sequentially sorted from bottom to top, and when the representative value corresponding to the third index region is located between preferential values corresponding to two preferential policies, a preferential policy index below the representative value is determined as a final preferential policy of the target person. The preferential policies included in the preset policy mapping relationship are set in advance by relevant staff, and specific contents are not limited in the embodiments of the present application and can be adjusted according to sales seasons.

[0088] By identifying and analyzing the total consumption, the purchased product type and the purchase frequency in the historical shopping data of the target person, the consumption habit and the preference of the target person are facilitated to be understood, so that the personalized preferential policy of the target person is facilitated to be determined, the adaptation degree between the historical shopping situation of the target person and the pushed preferential policy is facilitated to be improved, and the satisfaction degree of the target person in the consumption process is facilitated to be enhanced.

[0089] Further, the method provided in the embodiments of the present application further includes:

[0090] obtaining a transaction order in a second preset time period and a used preferential policy corresponding to each transaction order, identifying a gift content included in each used preferential policy, the gift content including a gift name and a gift quantity, obtaining gift inventory data, determining an adjusted preferential policy according to each gift content and the gift inventory data, and feeding back the adjusted preferential policy.

[0091] Specifically, the second preset time period can be 5 days before the current time or 7 days before the current time, and the duration corresponding to the second preset time period is not limited in the embodiments of the present application. The transaction order contains purchase commodity information and used discount strategies, wherein the used discount strategies contain discounts, full-price reductions, coupons and gifts, and different discount strategies can contain different contents. After obtaining each transaction order, the feature recognition method can be used to determine the gift name and the number of gifts contained in each used discount strategy, and after integrating the gift name and the number of gifts, a list of all gifts sent out in the second preset time period is obtained. The list of sent-out gifts is matched with the gift inventory data to determine the remaining gifts and the amount of each gift. When the amount of the gift corresponding to the used discount strategy is lower than the standard amount, the discount strategy is determined as a discount strategy to be adjusted. The discount strategy to be adjusted, the list of gifts and the remaining amount are fed back together, and the relevant staff can adjust the gift sending conditions in the discount strategy to be adjusted to adapt to the inventory situation after receiving the list of gifts and the remaining amount fed back by the electronic device.

[0092] In addition, the number of times each used discount strategy is used in the second preset time period can be counted, the importance of each used discount strategy is determined according to the number of times each used discount strategy is used, and the used discount strategies located before the preset important degree are counted and determined as key discount strategies. The key gifts contained in the key discount strategies are identified, and when the key gifts contained in the key discount strategies are in short supply, the associated discount strategies are identified from other discount strategies. When the inventory amount of the key gift is lower than the preset inventory amount limit, it is determined that the key gift contained in the key discount strategy is in short supply.

[0093] The associated transaction orders using the associated discount strategies are filtered from the transaction orders in the second preset time period, the commodity features contained in each associated transaction order are identified, including commodity style, commodity price, commodity purpose and the like, the commodity portraits corresponding to the plurality of associated transaction orders are constructed based on the identified commodity features corresponding to each associated transaction order, the replacement gift is determined from other gifts based on the commodity portrait, the replacement gift is determined as the recommended gift in the associated discount strategy, and the replacement suggestion information is generated. The replacement suggestion information generated can be fed back together with the discount strategy to be adjusted. Each gift corresponds to a gift portrait, and when the replacement gift is determined from other gifts based on the commodity portrait, the commodity portrait is matched with the gift portrait corresponding to each other gift, and the other gift with the highest matching degree is determined as the replacement gift. The other gift is a gift other than the key gift.

[0094] The embodiments of the present application provide an electronic device, such as Figure 4 As shown in the figure, Figure 4The electronic device 400 shown includes a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, for example, via a bus 402. Optionally, the electronic device 400 can also include a transceiver 404. It should be noted that the transceiver 404 is not limited to one in actual applications, and the structure of the electronic device 400 does not constitute a limitation on the embodiments of the present application.

[0095] The processor 401 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor 401 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0096] The bus 402 can include a path for transmitting information between the above-mentioned components. The bus 402 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 402 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience, Figure 4 only one line is used to represent it, but it does not mean that there is only one bus or only one type of bus.

[0097] The memory 403 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0098] The memory 403 is configured to store application program codes for implementing the solutions of the present application, and the processor 401 is configured to control the execution of the application program codes. The processor 401 is configured to execute the application program codes stored in the memory 403 to implement the content shown in the foregoing method embodiments.

[0099] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (for example, a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. It can also be a server or the like. Figure 4 The electronic device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0100] The embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program runs on a computer, the computer can execute the corresponding content in the foregoing method embodiments.

[0101] The embodiment of the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the method in any of the above embodiments. Compared with the prior art, in the embodiment of the present application, the historical shopping data of the to-be-identified person is matched with the matching data corresponding to each preset preferential strategy, so that the target person who does not match the current preset preferential strategy is quickly identified, the target range of subsequent data processing is reduced, the data processing amount when the consumer preferential strategy is determined can be effectively reduced, in addition, the to-be-identified person who matches the current preset preferential strategy and the to-be-identified person who does not match the current preset preferential strategy are classified, the preset preferential strategy matched with the to-be-identified person is directly fed back subsequently, and the corresponding preferential strategy does not need to be determined and pushed after all to-be-identified persons are subjected to multiple data identification and calculation, so that the rate of pushing the preferential strategy to the to-be-identified person is improved.

[0102] It should be understood that, although each step in the flowchart of the accompanying drawings is displayed in sequence according to the indication of the arrow, these steps are not necessarily executed in sequence according to the indication of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately executed with other steps or at least part of the sub-steps or stages of other steps.

[0103] The above only describes some embodiments of the present application, and it should be pointed out that, for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A method for classifying personnel, characterized in that, include: Obtain the historical shopping data corresponding to the person to be identified, and identify the shopping features corresponding to the historical shopping data and the feature value corresponding to each shopping feature; Based on the shopping features and the feature values ​​corresponding to each shopping feature, as well as the matching data corresponding to each preset discount strategy, the matching degree between the person to be identified and each preset discount strategy is determined. The matching data corresponding to each preset discount strategy includes matching features and matching feature values ​​corresponding to each matching feature. When the matching degree between the person to be identified and each preset preferential strategy is lower than the corresponding preset standard matching degree, the person to be identified is determined to be the target person. Add the target personnel to the strategy customization queue and provide feedback on the strategy customization queue. The personnel in the strategy customization queue are those who need customized preferential strategies. The process of adding the target personnel to the strategy customization queue further includes: Identify the total amount of consumption, the proportion of purchased product types, and the purchase frequency contained in the target person's historical shopping data. The historical shopping data is shopping data within a first preset time period, and the purchased product types are the ratio between high-selling and low-selling products. The discount value for the target personnel is determined based on the total consumption amount, the proportion of the types of goods purchased, and the purchase frequency. Based on the discount value and the preset strategy mapping relationship, the target discount strategy corresponding to the target person is determined, and the target discount strategy is pushed to the target person. The preset strategy mapping relationship is the correspondence between the discount value and the target discount strategy. The step of determining the discount value for the target individual based on the total consumption amount, the proportion of purchased product types, and the purchase frequency includes: Based on the mapping relationship between the total consumption amount and the first conversion ratio, a first representative value corresponding to the total consumption amount is determined, wherein the first conversion ratio mapping relationship is the correspondence between the total consumption amount and the first representative value; Based on the mapping relationship between the purchase product type ratio and the second conversion ratio, a second representative value corresponding to the purchase product type ratio is determined, and the second conversion ratio mapping relationship is the correspondence between the purchase product type ratio and the second representative value; Based on the mapping relationship between the purchase frequency and the third conversion ratio, the third representative value corresponding to the purchase frequency is determined, and the mapping relationship between the third conversion ratio is the correspondence between the purchase frequency and the third representative value. The preferential value for the target personnel is determined based on the first representative value, the second representative value, and the third representative value; The step of determining the discount value for the target personnel based on the first representative value, the second representative value, and the third representative value includes: A preset conversion coordinate system is determined based on the total consumption amount, the proportion of purchased product types, and the purchase frequency. The preset conversion coordinate system includes the turnover representative value corresponding to each of the total consumption amount, the proportion of purchased product types, and the purchase frequency. The first representative value is imported into the preset transformation coordinate system, and the first superimposed value is determined according to the flowing representative value corresponding to the first representative value. The second representative value and the first value to be superimposed are imported into the preset transformation coordinate system, and the second value to be superimposed is determined according to the flowing representative value corresponding to the second representative value; The third representative value and the second value to be superimposed are imported into the preset transformation coordinate system to obtain the discount value for the target personnel.

2. The personnel classification method according to claim 1, characterized in that, The step of determining the first value to be superimposed based on the circulating representative value corresponding to the first representative value includes: Based on the first representative value and the corresponding circulation representative value, an overflow representative value is determined, wherein the overflow representative value is the portion of the first representative value that is higher than the corresponding circulation representative value. The average overflow representative value is calculated by averaging the overflow representative value, and the average overflow representative value is determined as the first value to be superimposed.

3. The personnel classification method according to claim 1, characterized in that, Also includes: Obtain the completed orders within the second preset time period, and the discount strategies used for each completed order; Identify the gift content included in each used offer strategy, the gift content including the gift name and the quantity of the gift; Obtain gift inventory data, determine the discount strategy to be adjusted based on the contents of each gift and the gift inventory data, and provide feedback on the discount strategy to be adjusted.

4. An electronic device, characterized in that, The electronic device includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform a personnel classification method according to any one of claims 1-3.

5. A computer-readable storage medium, characterized in that, include: The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1-3.

6. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of a personnel classification method according to any one of claims 1-3.

Images