Personnel classification method, electronic equipment, medium and program product
By screening mismatched target personnel and personalized discount strategy analysis, the problem of low push efficiency among large-scale consumers is solved, the push rate and accuracy are improved, and the gift inventory management is optimized.
Patent Information
- Application Number
- CN202410886770.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-03
AI Technical Summary
Among large-scale consumers, the data processing volume when determining the discount strategy is too large, resulting in the reduction of the efficiency of pushing the discount strategy and the inability to effectively personalize the discount push.
By obtaining historical shopping data, identifying shopping characteristics and feature values, matching preset discount strategies, filtering out mismatched target personnel, joining the strategy customization queue, reducing data processing volume, and analyzing the total consumption amount, purchase type ratio and purchase frequency , determine personalized discount strategies.
It improves the speed and accuracy of promotional strategies, reduces data processing volume, enhances consumer satisfaction, and reasonably manages the gift inventory.
Smart Images

Figure CN118941332A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data management, and in particular to a personnel classification method, electronic equipment, medium and program product. Background Art
[0002] In a highly competitive market environment, promotional activities are an important means for merchants to distinguish themselves from their competitors. By providing more attractive and personalized promotions, they can attract more consumers' attention and participation, thereby increasing brand exposure and popularity, and leading merchants to stand out in the market. During promotional activities, merchants can increase sales, expand brand awareness and influence, attract new customers and retain old customers, and promote inventory clearance and new product promotion.
[0003] In the related art, generally after multiple data calculations and comparisons are performed on the total consumption, shopping type, purchase frequency, etc. contained in the consumer's shopping data, a preferential strategy suitable for the consumer is determined and the preferential strategy is pushed. However, when the number of consumers is large, the amount of data processing that needs to be calculated and compared will also increase. Therefore, this may lead to a decrease in the efficiency of pushing preferential strategies to consumers. Summary of the invention
[0004] In order to reduce the amount of data processing when determining consumer preferential policies and to increase the rate at which preferential policies are pushed to consumers, the present application provides a personnel classification method, electronic device, medium and program product.
[0005] In the first aspect, the present application provides a personnel classification method, which adopts the following technical solution: A personnel classification method, comprising: Acquire historical shopping data corresponding to the person to be identified, and identify shopping features corresponding to the historical shopping data and feature values corresponding to each shopping feature; Determine the degree of match between the person to be identified and each preset preferential policy based on the shopping features and the feature values corresponding to each shopping feature, and the matching data corresponding to each preset preferential policy, wherein the matching data corresponding to each preset preferential policy includes matching features and the matching feature values corresponding to each matching feature; When the matching degree between the person to be identified and each preset preferential policy is lower than the corresponding preset standard matching degree, the person to be identified is determined as a target person; The target person is added to a policy customization queue, and the policy customization queue is fed back. The person in the policy customization queue is a person who needs to customize preferential policies.
[0006] By adopting the above technical solution, the historical shopping data of the person to be identified is matched with the matching data corresponding to each preset preferential policy, so as to quickly identify the target person who does not match the current preset preferential policy, thereby narrowing the target range of subsequent data processing, and effectively reducing the amount of data processing when determining consumer preferential policies. In addition, by classifying the persons to be identified who match the current preset preferential policy and the persons to be identified who do not match the current preset preferential policy, it is convenient to directly feedback the preset preferential policies that match the persons to be identified, without the need to determine and push the corresponding preferential policies after multiple data identification and calculation for all persons to be identified, thereby facilitating the improvement of the rate of pushing preferential policies to the persons to be identified.
[0007] In a possible implementation manner, after adding the target person to the policy customization queue, the method further includes: Identify the total amount of consumption, the proportion of purchased commodity types, and the purchase frequency contained in the historical shopping data of the target person, wherein the historical shopping data is the shopping data within a first preset time period, and the purchased commodity types are the proportion between high-selling commodities and low-selling commodities; Determine the preferential value of the target person based on the total consumption, the proportion of the purchased commodity types and the purchase frequency; According to the mapping relationship between the preferential value and the preset strategy, the target preferential strategy corresponding to the target person is determined, and the target preferential strategy is pushed to the target person. The preset strategy mapping relationship is the corresponding relationship between the preferential value and the target preferential strategy.
[0008] By adopting the above technical solution, by identifying and analyzing the total consumption, purchased product types and purchase frequency in the historical shopping data of the target person, it is easy to understand the consumption habits and preferences of the target person, so as to determine personalized preferential strategies for the target person. By improving the compatibility between the historical shopping situation of the target person and the pushed preferential strategies, it is also easy to enhance the satisfaction of the target person during the consumption process.
[0009] In a possible implementation, determining the preferential value of the target person based on the total consumption, the proportion of the purchased commodity types, and the purchase frequency includes: Determine a first representative value corresponding to the total consumption amount according to the mapping relationship between the total consumption amount and the first conversion ratio, wherein the first conversion ratio mapping relationship is a corresponding relationship between the total consumption amount and the first representative value; Determine a second representative value corresponding to the purchase commodity type ratio according to the mapping relationship between the purchase commodity type ratio and the second conversion ratio, wherein the second conversion ratio mapping relationship is a corresponding relationship between the purchase commodity type ratio and the second representative value; Determine a third representative value corresponding to the purchase frequency according to the mapping relationship between the purchase frequency and the third conversion ratio, wherein the third conversion ratio mapping relationship is a corresponding relationship between the purchase frequency and the third representative value; The preferential value of the target person is determined based on the first representative value, the second representative value, and the third representative value.
[0010] By adopting the above technical solution, the original shopping data is converted into more representative values, namely the first representative value, the second representative value and the third representative value, by performing numerical conversion on the three key indicators of total consumption, proportion of purchased commodity types and purchase frequency. This numerical conversion helps to evaluate the consumption habits of the target personnel in a more refined manner. In addition, by converting multiple feature values into one representative value, it is convenient to integrate and calculate multiple features, thereby providing more accurate data support for the subsequent determination of preferential strategies.
[0011] In a possible implementation, determining the preferential value of the target person based on the first representative value, the second representative value, and the third representative value includes: Determine a preset conversion coordinate system according to the total consumption amount, the proportion of the purchased commodity types, and the purchase frequency, wherein the preset conversion coordinate system includes the turnover representative values corresponding to the total consumption amount, the proportion of the purchased commodity types, and the purchase frequency respectively; Importing the first representative value into the preset conversion coordinate system, and determining a first value to be superimposed according to the flow representative value corresponding to the first representative value; Importing the second representative value and the first value to be superimposed into the preset conversion coordinate system, and determining the second value to be superimposed according to the flow representative value corresponding to the second representative value; The third representative value and the second value to be superimposed are imported into the preset conversion coordinate system to obtain the preferential value of the target person.
[0012] By adopting the above technical solution, since the total consumption, the proportion of purchased product types and the purchase frequency will all affect the process of determining the final preferential strategy, when determining the preferential value of the target personnel, the correlation between multi-dimensional numerical values is established by superimposing numerical values. This correlated multi-dimensional evaluation method facilitates improving the accuracy and comprehensiveness of the evaluation results.
[0013] In a possible implementation, determining the first value to be superimposed according to the flow representative value corresponding to the first representative value includes: determining an overflow representative value according to the first representative value and the flow representative value corresponding to the first representative value, wherein the overflow representative value is a portion of the first representative value that is higher than the corresponding flow representative value; The overflow representative value is averaged to obtain an average overflow representative value, and the average overflow representative value is determined as the first value to be superimposed.
[0014] By adopting the above technical solution, since the preferential strategy for the target personnel is determined based on the preferential value determined by superimposing various representative values, and is selected and determined from a large number of preset preferential strategies, when a single representative value is abnormal or mutated, it may directly affect the final determination result. By calculating the mean of the overflow representative values and then determining the value to be superimposed, it is convenient to reduce the impact of data anomalies or mutations on the determination result.
[0015] In one possible implementation, the method further includes: Obtaining completed orders within a second preset time period and the used preferential policies corresponding to each completed order; Identify the gift content included in each used discount policy, wherein the gift content includes the gift name and gift quantity; The gift inventory data is obtained, and the preferential policy to be adjusted is determined according to the content of each gift and the gift inventory data, and the preferential policy to be adjusted is fed back.
[0016] By adopting the above technical solution, by identifying the content and quantity of gifts in the used preferential strategies, and combining it with the current gift inventory data, it is convenient to accurately grasp the consumption of gifts, which helps merchants to reasonably arrange the purchase and inventory of gifts and avoid inventory backlogs or shortages. In addition, by obtaining and analyzing the completed orders within the second preset time period and their corresponding used preferential strategies, it is also possible to understand the actual application effect of the preferential strategies in real time, so that merchants can adaptively adjust the preferential strategies to adapt to market changes and consumer needs.
[0017] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned personnel classification method.
[0018] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned personnel classification method.
[0019] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the above-mentioned personnel classification method is implemented.
[0020] In summary, the present application includes at least one of the following beneficial technical effects: By matching the historical shopping data of the person to be identified with the matching data corresponding to each preset discount policy, it is possible to quickly identify the target person who does not match the current preset discount policy, thereby narrowing the target range of subsequent data processing, and effectively reducing the amount of data processing when determining consumer discount policies. In addition, by classifying the persons to be identified who match the current preset discount policy and the persons to be identified who do not match the current preset discount policy, it is convenient to directly feedback the preset discount policies that match the persons to be identified, without the need to determine and push the corresponding discount policies after multiple data identification and calculation for all persons to be identified, thereby facilitating the improvement of the rate of pushing discount policies to the persons to be identified.
[0021] By converting the three key indicators of total consumption, proportion of purchased product types and purchase frequency into numerical values, the original shopping data is converted into more representative values, namely the first representative value, the second representative value and the third representative value. This numerical conversion helps to evaluate the consumption habits of the target personnel in a more refined manner. In addition, by converting multiple feature values into one representative value, it is convenient to integrate and calculate multiple features, thereby providing more accurate data support for the subsequent determination of preferential strategies. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 It is a flowchart of a personnel classification method in an embodiment of the present application; Figure 2 It is a flowchart of a method for determining push content in an embodiment of the present application; Figure 3 is a schematic diagram of a transformation coordinate system in an embodiment of the present application; Figure 4 It is a structural schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0023] The following is combined with Figure 1-4 This application is described in further detail.
[0024] After reading this specification, those skilled in the art may make modifications to this embodiment without any creative contribution as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.
[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0026] Specifically, the embodiment of the present application provides a personnel classification method, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or 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 laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application.
[0027] refer to Figure 1 , Figure 1 : is a flow chart of a personnel classification method in an embodiment of the present application, the method comprises steps S110 to S140, wherein: Step S110: Acquire historical shopping data corresponding to the person to be identified, and identify shopping features corresponding to the historical shopping data and feature values corresponding to each shopping feature.
[0028] Specifically, the person to be identified may be a person who has purchased goods in the historical period, that is, an old customer, or a person who has browsed the corresponding goods but did not purchase the goods, that is, a new customer. Since the person to be identified may be an old customer or a new customer, the historical shopping data corresponding to the person to be identified may not be empty or may be empty. The historical period may be 30 days or 45 days before the current moment, and the specific historical period is not specifically limited in the embodiment of the present application. Shopping features may include total consumption, that is, the total consumption in the historical period, the proportion of purchased commodity types, that is, the proportion of different types of commodities in the purchased commodities in the historical period, and may also include purchase frequency. The specific shopping features are not specifically limited in the embodiment of the present application and can be set by relevant staff. The feature value corresponding to each shopping feature can be determined from the historical shopping data by feature recognition.
[0029] 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 policy, determine the matching degree between the person to be identified and each preset preferential policy. The matching data corresponding to each preset preferential policy contains matching features and the matching feature values corresponding to each matching feature.
[0030] Specifically, the preset preferential strategy is determined by the relevant staff according to a large amount of actual use data and then uploaded to the electronic device. The number of preset preferential strategies is not specifically limited in the embodiment of the present application. The actual use data contains the user 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 the preset preferential strategy. The personnel applicable to each preset preferential strategy may be different. For example, the number of personnel using preset preferential strategy a exceeds the preset number, and the total consumption amount corresponding to most of the users is less than 10,000 yuan. At this time, the preset preferential strategy a can be determined as one of the preset preferential strategies. Although the total consumption amount corresponding to most of the personnel using preset preferential strategy a is less than 10,000 yuan, it cannot be explained that the personnel with a total consumption amount of less than 10,000 yuan are all applicable to the preset preferential strategy a. What can be explained is that the preset preferential strategy a can be used as the first choice for the personnel to be identified with a total consumption amount of less than 10,000 yuan. Different preset preferential strategies may be applicable to different groups of people, but they can be used as the first choice when facing the corresponding applicable groups.
[0031] Different preset preferential strategies also have corresponding usage conditions, that is, when the person to be identified needs to use a preset preferential strategy, he needs to match the historical shopping data with the preset preferential strategy, and then determine whether it can be used according to the matching result. Each preset preferential strategy also includes a matching feature value and a matching feature value corresponding to each matching feature value. For example, the matching feature corresponding to preset preferential strategy a is the matching total consumption. Only consumers whose matching total consumption is between 8k and 1w have the opportunity to use the preset preferential strategy.
[0032] The historical shopping data of the person to be identified is matched with the matching data of each preset preferential policy to obtain the matching degree between the person to be identified and each preset preferential policy. The higher the matching degree, the higher the adaptability of the person to be identified and the corresponding preset preferential policy. The shopping features correspond to the matching features. The matching degree between the person to be identified and each preset preferential policy is calculated as the sum of the sub-matching degrees of all shopping features and the corresponding matching features. The specific method of calculating the matching degree is not specifically limited in the embodiments of this application.
[0033] Step S130: When the matching degree between the person to be identified and each preset preferential policy is lower than the corresponding preset standard matching degree, the person to be identified is determined to be a target person.
[0034] Step S140: adding the target person to a policy customization queue and providing feedback to the policy customization queue. The person in the policy customization queue is the person who needs to customize the preferential policy.
[0035] Specifically, each preset preferential policy has a corresponding preset standard matching degree. The specific preset standard matching degree is not specifically limited in the embodiment of the present application. When the matching degree between the historical shopping data characteristics of the person to be identified and each preset preferential policy is not higher than any preset standard matching degree, it indicates that the existing preset preferential policies are not compatible with the actual shopping situation of the person to be identified. At this time, the person to be identified can be determined as the target person. The policy customization queue is used to store the historical shopping data of the target person. When the person to be identified is the target person, it indicates that the preferential policy cannot be pushed to the person to be identified by directly feeding back the preferential policy, but it needs to be calculated and processed later, and then the preferential policy suitable for the target person is selected from multiple preset preferential policies. After the target person is identified, the current processing operation of the electronic device is not stopped, but the target person is written into the policy customization queue to wait for subsequent operations, so as to reduce the impact on the push efficiency.
[0036] By matching the historical shopping data of the person to be identified with the matching data corresponding to each preset discount policy, it is possible to quickly identify the target person who does not match the current preset discount policy, thereby narrowing the target range of subsequent data processing, and effectively reducing the amount of data processing when determining consumer discount policies. In addition, by classifying the persons to be identified who match the current preset discount policy and the persons to be identified who do not match the current preset discount policy, it is convenient to directly feedback the preset discount policies that match the persons to be identified, without the need to determine and push the corresponding discount policies after multiple data identification and calculation for all persons to be identified, thereby facilitating the improvement of the rate of pushing discount policies to the persons to be identified.
[0037] Furthermore, after adding the target person to the policy customization queue, the process further includes steps S1 to S3, such as Figure 2 As shown, where: Step S1: Identify the total consumption, proportion of purchased commodity types and purchase frequency contained in the historical shopping data of the target person, where the historical shopping data is the shopping data within a first preset time period, and the purchased commodity types are the proportion between high-selling commodities and low-selling commodities.
[0038] Specifically, the first preset time period can be 30 days before the current moment, or 45 days before the current moment. The specific duration corresponding to the first preset time period is not specifically limited in the embodiment of the present application. The total consumption amount, the proportion of the types of purchased goods, and the purchase frequency are represented in different forms in the historical shopping data, and can be identified from the historical shopping data through their corresponding identifiers. The specific identification method is not specifically limited in the embodiment of the present application.
[0039] Among them, high-selling goods are goods whose sales volume is before the first preset ranking in the first preset time period, and low-selling goods are goods whose sales volume is after the second preset noun in the first preset time period. The number of high-selling goods and low-selling goods can be one or more. Since popular goods may be different in different periods, high-selling goods and low-selling goods may change over time. The proportion of purchased goods types is the ratio of the number of high-selling goods purchased to the number of low-selling goods purchased in historical shopping data. Since low-selling goods have sales pressure on merchants, the proportion of purchased goods types needs to be taken into account when determining the appropriate preferential strategy for consumers, i.e., target personnel.
[0040] Step S2: Determine the discount value for the target person based on the total consumption, the proportion of purchased commodity types, and the purchase frequency.
[0041] Specifically, by analyzing the total amount of consumption, the proportion of purchased commodity types, and the purchase frequency of the target person, the consumption situation of the consumer can be directly reflected. The total amount of consumption is an important indicator to measure the purchasing power and consumption level of consumers. By analyzing the total amount of consumption, we can understand the purchasing power of consumers. The proportion of purchased commodity types can reflect the purchasing preferences and demand structure of consumers. The purchase frequency is an important indicator to measure consumer loyalty and purchasing habits. Therefore, when determining the appropriate preferential strategy for the target person, it is necessary to analyze and determine it based on the total amount of consumption, the proportion of purchased commodity types, and the purchase frequency.
[0042] Furthermore, in order to facilitate the fusion calculation of multiple features, the discount value of the target person is determined based on the total consumption, the proportion of purchased product types and the purchase frequency, including: According to the mapping relationship between the total consumption amount and the first conversion ratio, the first representative value corresponding to the total consumption amount is determined, and the first conversion ratio mapping relationship is the corresponding relationship between the total consumption amount and the first representative value; according to the mapping relationship between the purchased commodity type ratio and the second conversion ratio, the second representative value corresponding to the purchased commodity type ratio is determined, and the second conversion ratio mapping relationship is the corresponding relationship between the purchased commodity type ratio and the second representative value; according to 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 third conversion ratio mapping relationship is the corresponding relationship between the purchase frequency and the third representative value; based on the first representative value, the second representative value and the third representative value, the preferential value of the target person is determined.
[0043] Specifically, before fusing the data of multiple dimensions, the multi-dimensional data needs to be normalized so that the multi-dimensional data can be expressed in the same way. Converting the total consumption, the proportion of purchased commodity types, and the purchase frequency into representative values is a way of data normalization. The specific method of normalizing the multi-dimensional data is not specifically limited in the embodiments of the present application, as long as the multi-dimensional data can be fused and calculated after the data normalization processing.
[0044] Different total consumption amounts correspond to different conversion ratios. The first conversion ratio mapping relationship includes conversion ratios corresponding to different total consumption amounts. The first representative value corresponding to the total consumption amount can be directly obtained according to the conversion ratio corresponding to the total consumption amount. The higher the total consumption amount, the higher the corresponding conversion ratio. However, in order to reduce the impact of abnormal data on the final result, different total consumption amounts do not grow in direct proportion. For example, when the total consumption amount is 100,000, the corresponding conversion ratio may be 0.01; when the total consumption amount is 200,000, the corresponding conversion ratio may be 0.02; when the total consumption amount is 500,000, the corresponding conversion ratio may be 0.045. The specific content of the first conversion ratio mapping relationship is not specifically limited in the embodiment of the present application, and can be analyzed and determined by relevant staff based on actual conditions and then uploaded to the electronic device.
[0045] Different shopping commodity type ratios correspond to different conversion ratios. Since the shopping commodity type ratio is the ratio of the number of high-selling commodities purchased to the number of low-selling commodities purchased in the historical shopping data, and the purchase of low-selling commodities can also reflect that a customer is willing to try or continue to purchase the brand's low-selling commodities, which may be newly launched commodities or non-main commodities, while purchasing high-selling commodities, which are usually flagship commodities or popular commodities. This can also show the consumer's comprehensive recognition and trust in the brand. Therefore, when determining the appropriate preferential strategy for consumers, it is also necessary to consider the consumer's shopping commodity type ratio. The higher the shopping commodity type ratio, the more high-selling commodities the consumer purchases during the shopping process, the fewer low-selling commodities, and the lower the corresponding conversion ratio. The second conversion ratio mapping relationship contains the conversion ratios corresponding to different shopping commodity type ratios. According to the conversion ratio corresponding to the shopping commodity type ratio, the second representative value corresponding to the shopping commodity type ratio can be directly obtained. The specific content of the second conversion ratio mapping relationship is not specifically limited in the embodiment of the present application, and can be set by relevant technical personnel.
[0046] Different purchase frequencies correspond to different conversion ratios. The third conversion ratio mapping relationship includes conversion ratios corresponding to different purchase frequencies. The third representative value corresponding to the purchase frequency can be directly obtained based on 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 relevant technical personnel.
[0047] After the first conversion ratio mapping relationship, the second conversion ratio mapping relationship, and the third conversion ratio mapping relationship respectively perform data normalization transformation on the total consumption, the proportion of purchased commodity types, and the purchase frequency, the obtained first representative value, the second representative value, and the third representative value can be directly fused and superimposed. When performing fusion and superposition processing, the first representative value, the second representative value, and the third representative value can be directly summed to determine the preferential value of the target person. The calculation can also be performed by circulation and superposition, and the specific process may include: A preset conversion coordinate system is determined according to the total consumption amount, the proportion of purchased commodity types and the purchase frequency, and the preset conversion coordinate system includes the circulation representative values corresponding to the total consumption amount, the proportion of purchased commodity types and the purchase frequency respectively; the first representative value is imported into the preset conversion coordinate system, and the first value to be superimposed is determined according to the circulation representative value corresponding to the first representative value; the second representative value and the first value to be superimposed are imported into the preset conversion coordinate system, and the second value to be superimposed is determined according to the circulation representative value corresponding to the second representative value; the third representative value and the second value to be superimposed are imported into the preset conversion coordinate system to obtain the preferential value of the target personnel.
[0048] Specifically, the preset conversion coordinate system corresponds to the number of shopping features, that is, the preset conversion coordinate system includes the total amount of consumption, the proportion of purchased commodity types, and the purchase frequency, such as Figure 3 As shown, Figure 3 It contains three indicators, each indicator corresponds to a shopping feature. The order of arrangement between different indicators can be preset or set at will. In the embodiment of the present application, the total consumption amount is placed before the proportion of the types of goods purchased, and the proportion of the types of goods purchased is placed before the purchase frequency. Different shopping features correspond to different representative values of circulation. When the representative value corresponding to the shopping feature is higher than the representative value of circulation, the excess part needs to be transferred to the next indicator. The representative value of circulation corresponding to the previous indicator is the starting value of the next indicator. After the representative value corresponding to the previous indicator is transferred, the value to be superimposed is obtained. The representative value corresponding to the next indicator is superimposed on the superimposed value corresponding to the previous indicator. The first representative value and the second representative value are imported into the preset conversion coordinate system using the same circulation method. The representative value displayed in the third indicator area is the final preferential value of the target person.
[0049] When determining the value to be superimposed corresponding to each indicator, the part exceeding the corresponding turnover representative value can be directly determined as the value to be superimposed. For example, when the first representative value is 7 and the corresponding turnover representative value is 5, the part exceeding the turnover representative value by 2 can be directly used as the first value to be superimposed. Since the final determination result may be directly affected when a single representative value is abnormal or mutated, when determining the value to be superimposed, the value exceeding the turnover representative value can be determined first, and then the value to be superimposed is determined after the mean calculation of the exceeding value. Among them, different indicators have different impacts on the final determination result when they are abnormal. When the mean calculation is performed for the exceeding values corresponding to different indicators, the corresponding mean ratio can be determined according to historical experience data, that is, the mean ratio corresponding to the exceeding value of the first representative value is 50%. When the exceeding value is 2, the first value to be superimposed corresponding to the first representative value can be determined to be 1; the mean ratio corresponding to the exceeding value corresponding to the second representative value can be 25%. When the exceeding value is 2, the second value to be superimposed corresponding to the second representative value can be determined to be 0.5. Different indicators, that is, the mean ratio corresponding to different representative values are not specifically limited in the embodiments of the present application.
[0050] Figure 3 There are three indicators, namely the first indicator, the second indicator and the third indicator. According to the above, the value of each indicator exceeding the corresponding turnover representative value is first determined, and then the average of the exceeding values is calculated to determine the corresponding value to be superimposed for each indicator, such as Figure 3 The first indicator area contains two sub-areas, wherein the display color of the first sub-area is lighter than that of the second sub-area, the numerical value corresponding to the first sub-area is a representative value that does not exceed the corresponding turnover representative value, and the numerical value corresponding to the second sub-area is a representative value that exceeds the corresponding turnover representative value. The corresponding preferential strategy is determined according to the representative value corresponding to the third indicator area.
[0051] Step S3: According to the mapping relationship between the preferential value and the preset strategy, determine the target preferential strategy corresponding to the target person, and push the target preferential strategy to the target person. The preset strategy mapping relationship is the corresponding relationship between the preferential value and the target preferential strategy.
[0052] Specifically, the third indicator area includes a preferential policy indicator, and the preset policy mapping relationship includes preferential values corresponding to different preferential policies. The preferential policies in the third indicator area are sorted from bottom to top. When the representative value corresponding to the third indicator area is between the preferential values corresponding to two preferential policies, the preferential policy indicator below the representative value is determined as the final preferential policy for the target person. The preferential policies included in the preset policy mapping relationship are set in advance by relevant staff, and the specific content is not specifically limited in the embodiments of this application, and can be adjusted according to the sales quarter.
[0053] By identifying and analyzing the total consumption, types of purchased goods, and purchase frequency in the target person's historical shopping data, it is easier to understand the target person's consumption habits and preferences, thereby facilitating the determination of personalized discount strategies for the target person. By improving the compatibility between the target person's historical shopping situation and the discount strategies pushed, it is also easier to enhance the target person's satisfaction during the consumption process.
[0054] Furthermore, the method provided in the embodiment of the present application also includes: Obtain the completed orders within the second preset time period, and the used preferential strategies corresponding to each completed order; identify the gift content contained in each used preferential strategy, the gift content includes the gift name and gift quantity; obtain the gift inventory data, determine the preferential strategy to be adjusted according to each gift content and gift inventory data, and provide feedback on the preferential strategy to be adjusted.
[0055] Specifically, the second preset time period can be 5 days before the current moment, or 7 days before the current moment, and the duration corresponding to the second preset time period is not specifically limited in the embodiment of the present application. The transaction order contains the purchased commodity information and the used preferential policies, wherein the used preferential policies contain discounts, full reductions, coupons and gifts, and the contents contained in different preferential policies may be different. After obtaining each transaction order, feature recognition can be used. When multiple transaction orders are obtained, the name and quantity of gifts contained in each used preferential policy can be determined by feature recognition, and after integrating them, a list of all gifts that have been sent out within the second preset time period is obtained, and the list of sent gifts is matched with the gift inventory data to determine the remaining gifts in the inventory, as well as the surplus of each gift. When the surplus corresponding to the gifts contained in the preferential policy is lower than the standard surplus, the preferential policy is determined as the preferential policy to be adjusted, and the preferential policy to be adjusted, the gift list and the remaining situation are fed back together. After receiving the gift list and the remaining situation fed back by the electronic device, the relevant staff can adjust the gift conditions of the gifts in the preferential policy to be adjusted to adapt to the inventory situation.
[0056] In addition, the number of times each preferential strategy is used within the second preset time period can be counted, and the importance of each preferential strategy can be determined based on the number of times each preferential strategy is used. The used preferential strategies that are ranked before the preset importance can be counted and determined as key preferential strategies. The key gifts included in the key preferential strategies can be identified. When the key gifts included in the key preferential strategies are in short supply, related preferential strategies can be identified from other preferential strategies. When the inventory of the key gifts is lower than the preset inventory limit, it is determined that the key gifts included in the key preferential strategies are in short supply.
[0057] Filter out the associated transaction orders that use the associated discount strategy from the transaction orders within the second preset time period, identify the product features contained in each associated transaction order, including product style, product price, product purpose, etc., build product portraits corresponding to multiple associated transaction orders based on the identified product features corresponding to each associated transaction order, determine a replacement gift from other gifts based on the product portrait, determine the replacement gift as a recommended gift in the associated discount strategy, and generate replacement suggestion information. The generated replacement suggestion information can be fed back together with the discount strategy to be adjusted. Each gift corresponds to a gift portrait. When determining a replacement gift from other gifts based on the product portrait, the product portrait can be matched with the gift portrait corresponding to each other gift, and the other gifts with the highest matching degree can be determined as replacement gifts. Other gifts are gifts other than the key gifts.
[0058] An electronic device is provided in an embodiment of the present application, such as Figure 4 Show, Figure 4 The electronic device 400 shown includes: a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, such as through a bus 402. Optionally, the electronic device 400 may also include a transceiver 404. It should be noted that in actual applications, the transceiver 404 is not limited to one, and the structure of the electronic device 400 does not constitute a limitation on the embodiments of the present application.
[0059] Processor 401 may 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 may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.
[0060] The bus 402 may include a path to transmit information between the above components. The bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 402 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.
[0061] The memory 403 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
[0062] The memory 403 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 401. The processor 401 is used to execute the application code stored in the memory 403 to implement the contents shown in the above method embodiment.
[0063] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0064] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.
[0065] The embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the method in any of the above embodiments is implemented. Compared with the related art, in the embodiment of the present application, the historical shopping data of the person to be identified is matched with the matching data corresponding to each preset preferential policy, so as to quickly identify the target person who does not match the current preset preferential policy, thereby facilitating the narrowing of the target range of subsequent data processing, and effectively reducing the amount of data processing when determining the consumer preferential policy. In addition, by classifying the person to be identified who matches the current preset preferential policy and the person to be identified who does not match the current preset preferential policy, it is convenient to directly feedback the preset preferential policy that matches the person to be identified, without the need to determine and push the corresponding preferential policy after multiple data identification and calculation for all the persons to be identified, thereby facilitating the improvement of the rate of pushing preferential policies to the persons to be identified.
[0066] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0067] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A personnel classification method, characterized in that: include: Acquire historical shopping data corresponding to the person to be identified, and identify shopping features corresponding to the historical shopping data and feature values corresponding to each shopping feature; Determine the degree of match between the person to be identified and each preset preferential policy based on the shopping features and the feature values corresponding to each shopping feature, and the matching data corresponding to each preset preferential policy, wherein the matching data corresponding to each preset preferential policy includes matching features and the matching feature values corresponding to each matching feature; When the matching degree between the person to be identified and each preset preferential policy is lower than the corresponding preset standard matching degree, the person to be identified is determined as a target person; The target person is added to a policy customization queue, and the policy customization queue is fed back. The person in the policy customization queue is a person who needs to customize preferential policies.
2. A personnel classification method according to claim 1, characterized in that: After adding the target person to the strategy customization queue, the method further includes: Identify the total amount of consumption, the proportion of purchased commodity types, and the purchase frequency contained in the historical shopping data of the target person, wherein the historical shopping data is the shopping data within a first preset time period, and the purchased commodity types are the proportion between high-selling commodities and low-selling commodities; Determine the preferential value of the target person based on the total consumption, the proportion of the purchased commodity types and the purchase frequency; According to the mapping relationship between the preferential value and the preset strategy, the target preferential strategy corresponding to the target person is determined, and the target preferential strategy is pushed to the target person. The preset strategy mapping relationship is the corresponding relationship between the preferential value and the target preferential strategy.
3. A personnel classification method according to claim 2, characterized in that: The determining of the preferential value of the target person based on the total consumption amount, the proportion of the purchased commodity types and the purchase frequency includes: Determine a first representative value corresponding to the total consumption amount according to the mapping relationship between the total consumption amount and the first conversion ratio, wherein the first conversion ratio mapping relationship is a corresponding relationship between the total consumption amount and the first representative value; Determine a second representative value corresponding to the purchase commodity type ratio according to the mapping relationship between the purchase commodity type ratio and the second conversion ratio, wherein the second conversion ratio mapping relationship is a corresponding relationship between the purchase commodity type ratio and the second representative value; Determine a third representative value corresponding to the purchase frequency according to the mapping relationship between the purchase frequency and the third conversion ratio, wherein the third conversion ratio mapping relationship is a corresponding relationship between the purchase frequency and the third representative value; The preferential value of the target person is determined based on the first representative value, the second representative value, and the third representative value.
4. A personnel classification method according to claim 3, characterized in that: The determining the preferential value of the target person based on the first representative value, the second representative value, and the third representative value includes: Determine a preset conversion coordinate system according to the total consumption amount, the proportion of the purchased commodity types, and the purchase frequency, wherein the preset conversion coordinate system includes the turnover representative values corresponding to the total consumption amount, the proportion of the purchased commodity types, and the purchase frequency respectively; Importing the first representative value into the preset conversion coordinate system, and determining a first value to be superimposed according to the flow representative value corresponding to the first representative value; Importing the second representative value and the first value to be superimposed into the preset conversion coordinate system, and determining the second value to be superimposed according to the flow representative value corresponding to the second representative value; The third representative value and the second value to be superimposed are imported into the preset conversion coordinate system to obtain the preferential value of the target person.
5. A personnel classification method according to claim 4, characterized in that: The determining the first value to be superimposed according to the flow representative value corresponding to the first representative value includes: determining an overflow representative value according to the first representative value and the flow representative value corresponding to the first representative value, wherein the overflow representative value is a portion of the first representative value that is higher than the corresponding flow representative value; The overflow representative value is averaged to obtain an average overflow representative value, and the average overflow representative value is determined as the first value to be superimposed.
6. A personnel classification method according to claim 2, characterized in that: Also includes: Obtaining completed orders within a second preset time period and the used preferential policies corresponding to each completed order; Identify the gift content included in each used discount policy, wherein the gift content includes the gift name and gift quantity; The gift inventory data is obtained, and the preferential policy to be adjusted is determined according to the content of each gift and the gift inventory data, and the preferential policy to be adjusted is fed back.
7. 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 a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a personnel classification method according to any one of claims 1-6.
8. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and executes a personnel classification method according to any one of claims 1 to 6.
9. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of a personnel classification method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Discount coupon delivery method and system
CN107862549A
E-commerce tags in multimedia content
CN116018608A
Analysis method and device based on historical data and medium
CN116151875A
