A Product Recommendation Method and Device Using Contact Marketing Evaluation

Abstract

The present application provides a product recommendation method and device using touchpoint marketing evaluation. The method includes: pushing a questionnaire to a target user and obtaining user feedback data of the target user for the questionnaire; obtaining user behavior index data and user purchase behavior data under different touchpoints, where the media and / or marketing methods corresponding to different touchpoints are different; for each touchpoint, based on the user feedback data, user behavior index data, and user purchase behavior data under the touchpoint, obtaining a touchpoint marketing contribution index for the touchpoint, where the touchpoint marketing contribution index refers to the contribution of the media and marketing method corresponding to the touchpoint to the overall preset product; according to the touchpoint marketing contribution indexes of all touchpoints, determining a target touchpoint to recommend the preset product according to the media and marketing method corresponding to the target touchpoint. Through the present application, it is possible to establish an evaluation of product recommendation methods across media and marketing methods, improving the accuracy of product recommendation.

Description

Technical Field

[0001] The present application relates to the field of Internet technologies, and in particular, to a product recommendation method and device using touchpoint marketing evaluation. Background Art

[0002] Currently, there are mainly the following several marketing effect evaluation methods:

[0003] 1) For a specific medium, technical means such as adding monitoring codes or crawlers are used to collect and analyze the data of the medium. By adopting the above method, corresponding monitoring codes need to be written for different media, and the evaluation methods between different media are not unified.

[0004] 2) Using the A / B test method, an experimental group and a control group are selected, and users are randomly divided into a group exposed to advertisements or content and a group not exposed, and then the differences between the two groups are compared to evaluate the marketing effect of the advertisements or content on users. By adopting the above method, a certain online test period for the experiment is required, increasing the upfront operation cost. In addition, the online test of the experiment is usually a short-term test of the experimental effect, and there is a certain deviation from the actual operation situation.

[0005] Therefore, in the prior art, it is only possible to evaluate for a single dimension (such as for a certain medium), and it is impossible to comprehensively evaluate different media, nor can it be achieved to evaluate different media with a unified evaluation standard. Summary of the Invention

[0006] In view of this, the purpose of the present application is to provide a product recommendation method and device using touchpoint marketing evaluation to overcome at least one of the above defects.

[0007] First aspect, an embodiment of the present application provides a product recommendation method using touchpoint marketing evaluation. The method includes: pushing a questionnaire to a target user and obtaining user feedback data of the target user for the questionnaire. The questionnaire is used to reflect the promotion situation of a preset product under different media and different marketing methods; obtaining user behavior index data and user purchase behavior data under different touchpoints, where different touchpoints correspond to different media and / or marketing methods. The user behavior index data refers to the acceptance degree of the user for the preset product recommended under the media and marketing method corresponding to the touchpoint, and the user purchase behavior data refers to the purchase situation of the user for the preset product recommended under the media and marketing method corresponding to the touchpoint; for each touchpoint, based on the user feedback data, user behavior index data and user purchase behavior data under this touchpoint, obtain the touchpoint marketing contribution index of this touchpoint. The touchpoint marketing contribution index refers to the contribution size of the media and marketing method corresponding to this touchpoint to the overall preset product; according to the touchpoint marketing contribution indexes of all touchpoints, determine the target touchpoint, so as to recommend the preset product according to the media and marketing method corresponding to the target touchpoint.

[0008] In an alternative embodiment of the present application, the touchpoint marketing contribution index of each touchpoint is determined by the following method: inputting the user feedback data, user behavior index data and user purchase behavior data of this touchpoint into the touchpoint product recommendation effect evaluation model to obtain the touchpoint marketing contribution index of this touchpoint.

[0009] In an alternative embodiment of the present application, the touchpoint marketing contribution index of each touchpoint is determined by the following method: setting a plurality of preset dimensions, and the plurality of preset dimensions include sales force, brand force, and user force; for each preset dimension, based on the user feedback data and user behavior index data under this touchpoint, obtain the touchpoint dimension index of this touchpoint under this preset dimension; for each preset dimension, perform a partial correlation analysis on this preset dimension and the user purchase behavior data under all touchpoints to obtain the dimension contribution index under this preset dimension, and determine the ratio of the dimension contribution index under this preset dimension to the overall dimension contribution index as the touchpoint contribution weight coefficient under this preset dimension; based on the touchpoint dimension indexes and touchpoint contribution weight coefficients of this touchpoint under each preset dimension, calculate the touchpoint marketing contribution index of this touchpoint.

[0010] In an alternative embodiment of the present application, the determining the target touchpoint according to the touchpoint marketing contribution indexes of all touchpoints includes: for each touchpoint, according to the touchpoint marketing contribution index and cost-effectiveness ratio of this touchpoint, obtain the touchpoint input energy index of this touchpoint. The cost-effectiveness ratio is used to characterize the relationship between the sales amount of the preset product and the investment degree for promoting the preset product within a predetermined time period; determine the touchpoint corresponding to the obtained maximum touchpoint input energy index as the target touchpoint.

[0011] In an alternative embodiment of the present application, the contact input energy index of each contact is determined in the following manner: By performing an exponential processing on the contact marketing contribution index of the contact, the contact marketing contribution index of the contact is obtained; The product of the contact marketing contribution index of the contact and the cost-effectiveness ratio is determined as the contact input energy index of the contact.

[0012] In an alternative embodiment of the present application, the cost-effectiveness ratio is determined in the following manner: Determine the sales amount of the preset product within the preset time period, where the preset time period refers to the promotion cycle of the preset product under different media and different marketing methods; Determine the contribution degree of all contacts to the sales amount within the preset time period; Determine the investment degree for promoting the preset product within the preset time period; Calculate the product of the sales amount and the contribution degree within the preset time period, and determine the ratio of the product to the investment degree as the cost-effectiveness ratio.

[0013] In an alternative embodiment of the present application, the preset time period includes multiple sub-time periods, and the contribution degree includes sub-contribution degrees corresponding to each sub-time period.

[0014] Among them, each sub-contribution degree is determined by the following formula:

[0015]

[0016] Among them, Y t represents the sub-contribution degree corresponding to the t-th sub-time period, β0 represents the basic sales amount, and the basic sales amount refers to the sales amount that naturally occurs for the preset product without media and marketing method promotion, β j represents the contribution coefficient of the j-th contact to the sales amount, Z jt represents the investment degree for the preset product under the j-th contact within the t-th sub-time period, 1 ≤ j ≤ Z, Z represents the total number of contacts, e t represents the random error of the t-th sub-time period.

[0017] In an alternative embodiment of the present application, the preset time period includes multiple sub-time periods, and the investment degree includes sub-investment degrees corresponding to each sub-time period. Among them, the sub-investment degree within each sub-time period is determined in the following manner: For each sub-interval within the historical time period, determine the actual investment degree for promoting the preset product within the historical time period, where the historical time period is earlier than the preset time period; Determine the decay weight coefficient corresponding to each sub-interval; For each sub-interval, calculate the product of the decay weight coefficient corresponding to the sub-interval and the actual investment degree; Determine the sum of the products corresponding to all sub-intervals as the sub-investment degree for promoting the preset product within the sub-time period.

[0018] In an alternative embodiment of the present application, for each sub-time period, each sub-interval under the sub-time period is the difference between the sub-time period and the corresponding preset value, and the preset values corresponding to each sub-interval are increasing. Among them, the decay weight coefficient corresponding to each sub-interval is determined in the following manner: Determine the first intermediate variable corresponding to the sub-interval, and the first intermediate variable is the preset value corresponding to the sub-interval; Taking the natural constant e as the base and the product of the first intermediate variable and the set constant as the exponent, obtain the second intermediate variable corresponding to the sub-interval; Determine the ratio of the second intermediate variable corresponding to the sub-interval to the total variable as the decay weight coefficient corresponding to the sub-interval, and the total variable is the sum of the second intermediate variables corresponding to all sub-intervals.

[0019] In a second aspect, an embodiment of the present application further provides a product recommendation device using touchpoint marketing evaluation. The device includes: a push module for pushing a questionnaire to a target user and obtaining user feedback data of the target user for the questionnaire. The questionnaire is used to reflect the promotion situation of a preset product under different media and different marketing methods; an acquisition module for acquiring user behavior index data and user purchase behavior data under different touchpoints, where the media and / or marketing methods corresponding to different touchpoints are different. The user behavior index data refers to the acceptance degree of the user for the preset product recommended under the media and marketing method corresponding to the touchpoint, and the user purchase behavior data refers to the purchase situation of the user for the preset product recommended under the media and marketing method corresponding to the touchpoint; a calculation module for obtaining the touchpoint marketing contribution index of each touchpoint based on the user feedback data, user behavior index data, and user purchase behavior data under the touchpoint. The touchpoint marketing contribution index refers to the contribution size of the media and marketing method corresponding to the touchpoint to the overall preset product; a determination module for determining a target touchpoint according to the touchpoint marketing contribution indexes of all touchpoints, so as to recommend the preset product according to the media and marketing method corresponding to the target touchpoint.

[0020] The embodiment of the present application provides a product recommendation method and device using touchpoint marketing evaluation. By calculating the touchpoint marketing contribution indexes of each touchpoint, it is possible to judge the accuracy of the media and marketing method corresponding to the touchpoint for product recommendation, and it is possible to establish an evaluation of the product recommendation method across media and marketing methods, improving the accuracy of product recommendation.

[0021] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a flowchart of the product recommendation method using touchpoint marketing evaluation provided by the embodiments of the present application;

[0024] Figure 2 It is a flowchart of the steps for determining the touchpoint marketing contribution index of each touchpoint provided by the embodiments of the present application;

[0025] Figure 3 It is a flowchart of the steps for determining the cost-effectiveness ratio provided by the embodiments of the present application;

[0026] Figure 4 It is a flowchart of the steps for determining the investment degree of promoting a preset product within a preset time period provided by the embodiments of the present application;

[0027] Figure 5 It is a schematic structural diagram of the product recommendation device using touchpoint marketing evaluation provided by the embodiments of the present application;

[0028] Figure 6 It is a curve graph of the weight distribution of the effective advertising investment in different months based on the exponential weighted average method. Specific embodiments

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Usually, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those skilled in the art without creative efforts belongs to the scope of protection of the present application.

[0030] First, the applicable application scenarios of the present application will be introduced. The present application can be applied to the field of Internet technology.

[0031] Currently, there are mainly the following several marketing effect evaluation methods:

[0032] 1) For a specific medium, use technical means such as adding monitoring codes or crawlers to collect and analyze the data of the medium. In the above manner, corresponding monitoring codes need to be written for different media, and the evaluation methods between different media are not unified.

[0033] 2) Use the A / B test method. Select the experimental group and the control group, randomly divide users into groups exposed to advertisements or content and groups not exposed, and then compare the differences between the two groups to evaluate the marketing effect of advertisements or content on users. In the above manner, a certain experimental online test cycle is required, increasing the upfront operation cost. In addition, the experimental online test is usually a short-term test of experimental effects, and there is a certain deviation from the actual operation situation.

[0034] Therefore, in the prior art, it is only possible to evaluate in a single dimension (e.g., for a certain medium), unable to comprehensively evaluate different media, nor to evaluate different media with a unified evaluation standard.

[0035] Aiming at the problems in at least one of the above aspects, the purpose of this application is to provide a product recommendation method and device using touchpoint marketing evaluation, which can calculate the touchpoint marketing contribution index of the touchpoint by obtaining user feedback data, user behavior index data, and user purchase behavior data under the touchpoint, so as to evaluate different touchpoints with a unified evaluation standard, and can establish a cross-media and cross-marketing method product recommendation method evaluation, improving the accuracy of product recommendation.

[0036] Please refer to Figure 1 , Figure 1 which is the flowchart of the product recommendation method using touchpoint marketing evaluation provided by the embodiment of this application. As Figure 1 shown, the product recommendation method using touchpoint marketing evaluation provided by the embodiment of this application specifically includes:

[0037] Step S100: Push a questionnaire to the target user and obtain the user feedback data of the target user for the questionnaire.

[0038] Here, the above target user can be obtained by randomly sampling all Internet users,

[0039] or, it can also be obtained by screening all Internet users according to pre-set screening conditions.

[0040] For example, with the user's authorization, relevant data of the user is obtained. This data includes multiple database tags of the user, such as age, gender, education level, industry, occupation, marital status, whether having children, whether having a car, longitude and latitude information where the device appears, device brand, device version, device number, etc. A database is established in advance, and the user data and multiple database tags of the user are stored in the database. When obtaining target users, a predetermined number of database tags are selected according to requirements, and a preset number of users are extracted from all Internet users based on these database tags as target users.

[0041] In the embodiments of the present application, the questionnaire is used to reflect the promotion situation of a preset product under different media and different marketing methods. Exemplarily, the preset product may include tangible items and intangible services.

[0042] Exemplarily, the questionnaire can design relevant questions from three dimensions: sales force, brand force, and user force. The questions mainly involve whether the user triggers the willingness or behavior to purchase after contacting customer information at each touchpoint; whether it touches the user from the bottom of the heart, such as increasing the brand favorability or liking the relevant information; whether it can reach more people or precipitate more brand users, such as recommending the brand to others, etc.

[0043] Among them, the questionnaire consists of multiple questions, and the user feedback data is the answer results of the target user for multiple questions in the questionnaire.

[0044] In one case, the questionnaire includes multiple questionnaires. At this time, the multiple questionnaires correspond to multiple touchpoints one by one.

[0045] In this case, if the user feedback data of the target user for the questionnaire is obtained, for each touchpoint, the questionnaire corresponding to this touchpoint needs to be obtained, and the answer results of the target user for the obtained questionnaire are used as the user feedback data corresponding to this touchpoint.

[0046] In another case, the questionnaire includes one questionnaire corresponding to multiple touchpoints.

[0047] In this case, if the user feedback data of the target user for the questionnaire is obtained, for each touchpoint, the answer results corresponding to this touchpoint need to be extracted from the questionnaire, and the extracted answer results are used as the user feedback data corresponding to this touchpoint.

[0048] Through the corresponding situations of the two questionnaires and touchpoints, the obtained user feedback data can be made more accurate, thereby improving the accuracy of the calculated touchpoint marketing contribution index.

[0049] Step S200: Obtain user behavior index data and user purchase behavior data under different touchpoints.

[0050] In this step, the media and / or marketing methods corresponding to different contacts are different.

[0051] Specifically, the user behavior metric data refers to the acceptance of the preset products recommended under the media and marketing methods corresponding to the contacts by the user. Multiple metrics are set for multiple user behaviors. The metrics can be the user's exposure rate, click-through rate, forwarding, commenting, liking, the number of participants in an event, the inquiry rate, etc.

[0052] The first user behavior metric data: Obtained through online metrics, and data on the metrics related to the contact are obtained from the media segment according to the user's exposure rate, click-through rate, forwarding, commenting, and liking.

[0053] The second user behavior metric data: Obtained through offline metrics, and data on the metrics related to the contact are obtained based on different events according to the number of participants in the event and the inquiry rate.

[0054] In this step, the user purchase behavior data refers to the purchase situation of the preset products recommended under the media and marketing methods corresponding to the contacts by the user.

[0055] Step S300: For each contact, based on the user feedback data, user behavior metric data, and user purchase behavior data under this contact, obtain the contact marketing contribution metric for this contact.

[0056] Here, the contact marketing contribution metric refers to the contribution size of the media and marketing method corresponding to this contact to the overall preset product.

[0057] In the first embodiment, the contact marketing contribution metric for each contact is determined through a contact product recommendation effect evaluation model. The user feedback data, user behavior metric data, and user purchase behavior data of this contact are input into the contact product recommendation effect evaluation model to obtain the contact marketing contribution metric for this contact.

[0058] In the second embodiment, by setting multiple preset dimensions, the contact marketing contribution metric under this preset dimension is calculated based on the user data under this preset dimension. The above contact product recommendation effect evaluation model can also be constructed through a calculation method.

[0059] The following combines Figure 2 to introduce the calculation method under the above preset dimension.

[0060] Please refer to Figure 2 , Figure 2 which shows a flowchart of the steps for determining the contact marketing contribution metric for each contact in an embodiment of the present application.

[0061] As Figure 2 shown, in step S301, multiple preset dimensions are set.

[0062] The multiple preset dimensions include sales force, brand force, and user force.

[0063] In step S302, for each preset dimension, based on the user feedback data and user behavior metric data under this contact point, the contact point dimension metric under this preset dimension is obtained.

[0064] Specifically, the preset dimensions include sales force, brand force, and user force. Each dimension includes its own different factors. Based on different preset dimensions, different user feedback data and user behavior metric data of users at different contact points are obtained. First, standardization processing is performed (after standardization, the factor index ranges between 50 - 100 or between 0 - 100), and then principal component analysis (a statistical analysis method, usually can be operated using statistical analysis software) is carried out to obtain the principal component scores of the three dimensions of sales force, brand force, and user force of each contact point, that is, the contact point dimension metric.

[0065] In step S303, for each preset dimension, partial correlation analysis is performed on this preset dimension and the user purchase behavior data under all contact points to obtain the dimension contribution metric under this preset dimension. The ratio of the dimension contribution metric under this preset dimension to the overall dimension contribution metric is determined as the contact point contribution weight coefficient under this preset dimension.

[0066] Exemplarily, partial correlation analysis is respectively performed on the three dimensions of sales force, brand force, and user force of each contact point and the user purchase behavior data (partial correlation analysis is also a statistical analysis method, usually can be operated using statistical analysis software) (controlling socio - economic demographic variables such as age, education level, income, occupation, etc.) to obtain the marketing contributions of each contact point to users, and then the marketing contributions are normalized to respectively obtain the proportion of the preset dimension contribution metric in the overall marketing contribution, that is, the contact point contribution weight coefficient under this preset dimension.

[0067] This application designs a questionnaire from three dimensions: sales force, brand force, and user force. Based on different preset dimensions, different user feedback data, user behavior metric data of users at different contact points, and the user purchase behavior data of this preset dimension and all contact points are calculated to obtain the contact point marketing contribution coefficient, so as to realize the evaluation of different contact points with a unified evaluation standard, and be able to establish an evaluation of product recommendation methods across media and marketing methods, improving the accuracy of product recommendation.

[0068] An example of partial correlation analysis is shown in Table 1 below. Table 1 is an example of partial correlation analysis:

[0069] Dimension 1 - Contact Point 1 Dimension 2 - Contact Point 1 Dimension 3 - Contact Point 1 Partial Correlation Coefficient 0.33 0.33 0.34

[0070] Table 1

[0071] In step S304, based on the contact dimension index and the contact contribution weight coefficient of the contact in each preset dimension, calculate the contact marketing contribution index of the contact.

[0072] Calculation formula: K i = A i ×E + B i ×F + C i ×G

[0073] Wherein, K i represents the contact marketing contribution index of the i-th contact, A i represents the contact dimension index of the i-th contact in terms of sales force dimension, B i represents the contact dimension index of the i-th contact in terms of brand force dimension, C i represents the contact dimension index of the i-th contact in terms of user force dimension, E represents the contact contribution weight coefficient in terms of sales force, F represents the contact contribution weight coefficient in terms of brand force, and G represents the contact contribution weight coefficient in terms of user force.

[0074] Return Figure 1 , step S400: Determine the target contact according to the contact marketing contribution indexes of all contacts, so as to recommend the preset product according to the medium and marketing method corresponding to the target contact.

[0075] In one case, the target contact includes one contact.

[0076] At this time, the target contact is the contact with the maximum contact marketing contribution index.

[0077] In another case, the target contact includes multiple contacts.

[0078] At this time, the multiple contacts can be sorted according to the size of the contact marketing contribution index. This sorting can be in ascending order according to the size of the contact marketing contribution index. At this time, the multiple contacts before the predetermined number are determined as the target contacts. It should be understood that the above sorting can also be in descending order according to the size of the contact marketing contribution index. At this time, the multiple contacts after the predetermined number are determined as the target contacts.

[0079] Specifically, for each contact, obtain the contact input energy index according to the contact marketing contribution index and the cost-effectiveness ratio of the contact. The cost-effectiveness ratio is used to characterize the relationship between the sales amount of the preset product and the investment degree of promoting the preset product within a predetermined time period. The target contact is the contact corresponding to the maximum contact input energy index obtained.

[0080] In an alternative embodiment, the contact input energy index of each contact can be determined in the following manner: by performing an exponential operation on the contact marketing contribution index of the contact, obtaining the contact marketing contribution index of the contact, and multiplying the contact marketing contribution index of the contact by the cost-effectiveness ratio to determine the contact input energy index of the contact.

[0081] Exemplarily, the following formula is used to determine the marketing contribution index of each contact:

[0082]

[0083] In formula (1), M i is the contact marketing contribution index of the i-th contact, N i is the contact marketing contribution index of the i-th contact, N max is the maximum value among the contact marketing contribution indexes corresponding to all contacts, N min is the minimum value among the contact marketing contribution indexes corresponding to all contacts, N1 is a fixed value that can be set according to actual needs. Finally, the range of M i is determined within the range of constant <M ii <100 + constant (e.g., 100 + N1).

[0084] The present application provides a product recommendation method using contact marketing evaluation, which can calculate the contact marketing contribution index of the contact by obtaining user feedback data, user behavior index data, and user purchase behavior data under the obtained contact, and then determine the contact input energy index of the contact, so as to realize the evaluation of different contacts with a unified evaluation standard, and can establish a cross-media and cross-marketing method for product recommendation evaluation, improving the accuracy of product recommendation.

[0085] The following will introduce the calculation method of the above cost-effectiveness ratio in conjunction with Figure 3 .

[0086] Please refer to Figure 3 , Figure 3 which shows a flowchart of the steps for determining the cost-effectiveness ratio according to an embodiment of the present application.

[0087] As shown in Figure 3 , in step S401, determine the sales amount of the preset product within the preset time period.

[0088] Specifically, the preset time period refers to the promotion period of the preset product under different media and different marketing methods.

[0089] In step S402, determine the contribution degree of all contacts to the sales amount within the preset time period.

[0090] Exemplarily, the preset time period includes a plurality of sub - time periods, and the contribution degree includes sub - contribution degrees corresponding to each sub - time period. Among them, each sub - contribution degree is determined by the following formula:

[0091]

[0092] Among them, Y t represents the sub - contribution degree corresponding to the t - th sub - time period, β0 represents the basic sales volume, and the basic sales volume refers to the sales volume that naturally occurs for the preset product without the promotion of media and marketing methods. β j represents the contribution coefficient of the j - th contact point to the sales volume, Z jt represents the input degree for the preset product under the j - th contact point within the t - th sub - time period, 1 ≤ j ≤ Z, and Z represents the total number of contact points. e t represents the random error of the t - th sub - time period.

[0093] In step S403, determine the input degree for promoting the preset product within the preset time period.

[0094] Preferably, the preset time period includes a plurality of sub - time periods, and the input degree includes sub - input degrees corresponding to each sub - time period. The sub - input degree within each sub - time period can be determined in the following way:

[0095] The following combines Figure 4 to determine the input degree for promoting the preset product within the preset time period.

[0096] Please refer to Figure 4 , Figure 4 which shows a flowchart of the steps for determining the input degree for promoting the preset product within the preset time period in the embodiment of the present application.

[0097] As Figure 4 shown, in step S501, for each sub - interval within the historical time period, determine the actual input degree for promoting the preset product within this historical time period.

[0098] Among them, the historical time period is earlier than the above - mentioned preset time period.

[0099] In step S502, determine the attenuation weight coefficient corresponding to each sub - interval.

[0100] In an alternative embodiment, for each sub - time period, each sub - interval under this sub - time period is the difference between this sub - time period and the corresponding preset value, and the preset values corresponding to each sub - interval are increasing.

[0101] Among them, the attenuation weight coefficient corresponding to each sub - interval is determined in the following way:

[0102] Determine the first intermediate variable corresponding to this sub - interval, and the first intermediate variable is the preset value corresponding to this sub - interval.

[0103] Taking the natural constant \(e\) as the base and the product of the first intermediate variable and the set constant as the exponent, the second intermediate variable corresponding to this sub-interval is obtained.

[0104] The ratio of the second intermediate variable corresponding to this sub-interval to the total variable is determined as the attenuation weight coefficient corresponding to this sub-interval, and the total variable is the sum of the second intermediate variables corresponding to all sub-intervals.

[0105] Exemplarily, the relevant content of the cost-effectiveness ratio model is as follows:

[0106] Advertising sales: The evaluation of the effect needs to consider the impact of the delay and persistence of the advertising sales effect. That is, the promotion of sales by advertising activities is not achieved overnight, but is gradually realized through users' recognition, understanding, and purchase. From the release of the advertisement to the user seeing the advertisement, understanding the advertisement, and finally deciding to purchase the product, etc., a series of processes take a certain amount of time, and the previous advertisements may also affect the current sales volume. In order to accurately measure the advertising sales effect, its delay and persistence should be considered in the measurement model.

[0107] Considering the impact of the delay and persistence of the advertising sales effect, it is necessary to consider the impact of the contribution of the advertising investment in the previous consecutive periods on the current sales. Calculating the impact of the advertising investment in the previous periods on the sales requires considering the situation that users' memory of the advertising information and brand awareness gradually decline over time, that is, the advertising sales effect gradually declines over time. Therefore, an exponentially weighted average method is adopted to calculate the impact of the advertising investment in each period on the sales volume:

[0108]

[0109] In formula (2), \(w_{Ad}\) T is the total effective advertising investment in the past 6 months that contributes to the sales in the current month (\(T\)), \(Ad\) t is the actual advertising investment in the \(t\)-th month, is an exponential function with the natural constant \(e\) as the base, and \(h\) is a constant. This curve is widely used in the study of human behaviors such as memory, learning, forgetting, and attention.

[0110] Based on the weight distribution of the effective advertising investment in different months using the exponentially weighted average method, as Figure 6 shown.

[0111] In step S503, for each sub-interval, calculate the product of the attenuation weight coefficient corresponding to this sub-interval and the actual investment degree.

[0112] In step S504, the sum of the products corresponding to all sub-intervals is determined as the sub-investment degree for promoting the preset product within this sub-time period.

[0113] Return Figure 3 , step S404: Calculate the product of the sales amount and the contribution degree within a preset time period, and determine the ratio of the product to the input degree as the cost-effectiveness ratio.

[0114] The sales amount is the actual data of the enterprise.

[0115] Each cost-effectiveness ratio can be calculated by the following formula: T = (S1 + S2 + S3) × U /

[0116] (R1 + R2 + R3) where U is the contribution degree of each contact point to the sales volume, T is the cost-effectiveness ratio, S e is the sales amount in the e-th month, R e is the sub-input degree in the e-th month, Q e is the actual input degree in the e-th month.

[0117] The present application provides a product recommendation method using contact point marketing evaluation, which can calculate the contact point input energy index of the contact point by obtaining user feedback data, user behavior index data, and user purchase behavior data under the obtained contact point, so as to realize the evaluation of different contact points with a unified evaluation standard, and can establish a product recommendation method evaluation across media and marketing methods, improving the accuracy of product recommendation.

[0118] Please refer to Figure 5 , Figure 5 which is the product recommendation device 600 corresponding to the product recommendation method using contact point marketing evaluation provided in the embodiment of the present application. As Figure 5 shown, the device 600 includes:

[0119] A push module 601, configured to push a questionnaire to a target user and obtain user feedback data of the target user for the questionnaire, where the questionnaire is used to reflect the promotion situation of a preset product under different media and different marketing methods;

[0120] An acquisition module 602, configured to acquire user behavior index data and user purchase behavior data under different contact points, where the media and / or marketing methods corresponding to different contact points are different, the user behavior index data refers to the acceptance degree of the user for the preset product recommended under the media and marketing methods corresponding to the contact point, and the user purchase behavior data refers to the purchase situation of the user for the preset product recommended under the media and marketing methods corresponding to the contact point;

[0121] A calculation module 603, configured to obtain a contact point marketing contribution index of each contact point based on the user feedback data, user behavior index data, and user purchase behavior data under the contact point, where the contact point marketing contribution index refers to the contribution size of the media and marketing methods corresponding to the contact point to the overall preset product;

[0122] A determination module 604, configured to determine a target contact according to the contact marketing contribution indexes of all contacts, so as to recommend a preset product according to the medium and marketing method corresponding to the target contact.

[0123] Since the principle of the device in the embodiment of the present application for solving problems is similar to the above product recommendation method using contact marketing evaluation in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and repeated parts will not be described again.

[0124] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described system, device, and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described again here.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces. The indirect coupling or communication connection of the device or unit may be in an electrical, mechanical, or other form.

[0126] The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application can be integrated in a processing unit, or each unit exists physically alone, or two or more units are integrated in one unit.

[0128] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device, which can be a personal computer, a server, or a network device, etc., to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0129] Finally, it should be noted that: the above-mentioned embodiments are only specific implementation manners of this application, used to illustrate the technical solutions of this application, rather than limiting it. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed in this application can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered by the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A product recommendation method using contact marketing evaluation, characterized in that The method includes: Pushing a questionnaire to a target user and obtaining user feedback data of the target user for the questionnaire, where the questionnaire is used to reflect the promotion situation of a preset product under different media and different marketing methods; Obtaining user behavior index data and user purchase behavior data under different touchpoints, where the media and / or marketing methods corresponding to different touchpoints are different, the user behavior index data refers to the acceptance degree of the user for the preset product recommended under the media and marketing method corresponding to the touchpoint, and the user purchase behavior data refers to the purchase situation of the user for the preset product recommended under the media and marketing method corresponding to the touchpoint; For each touchpoint, based on the user feedback data, user behavior index data and user purchase behavior data under this touchpoint, obtaining the touchpoint marketing contribution index of this touchpoint, where the touchpoint marketing contribution index refers to the contribution size of the media and marketing method corresponding to this touchpoint to the overall preset product; For each touchpoint, according to the touchpoint marketing contribution index and cost-effectiveness ratio of this touchpoint, obtaining the touchpoint input energy index of this touchpoint, and determining the target touchpoint for the touchpoint corresponding to the maximum touchpoint input energy index obtained, so as to recommend the preset product according to the media and marketing method corresponding to the target touchpoint, where the cost-effectiveness ratio is used to characterize the relationship between the sales amount of the preset product and the input degree of promoting the preset product within a predetermined time period; Among them, the cost-effectiveness ratio is determined by the following method: Determining the sales amount of the preset product within the preset time period, where the preset time period refers to the promotion cycle of the preset product under different media and different marketing methods; Determining the contribution degree of all touchpoints to the sales amount within the preset time period, the preset time period includes multiple sub-time periods, and the contribution degree includes sub-contribution degrees corresponding to each sub-time period, where each sub-contribution degree is determined by the following formula: Among them, Y t represents the sub - contribution corresponding to the t - th sub - time period, β0 represents the basic sales amount, which refers to the sales amount that the preset product naturally generates without the promotion of media and marketing methods, β j represents the contribution coefficient of the j - th contact point to the sales amount, Z jt represents the investment degree for the preset product under the j - th contact point within the t - th sub - time period, 1 ≤ j ≤ Z, Z represents the total number of contact points, e t represents the random error of the t - th sub - time period; Determining the input degree of promoting the preset product within the preset time period; Calculating the product of the sales amount and the contribution degree within the preset time period, and determining the ratio of the product to the input degree as the cost-effectiveness ratio.

2. The method according to claim 1, characterized in that, The touchpoint marketing contribution index of each touchpoint is determined by the following method: Inputting the user feedback data, user behavior index data and user purchase behavior data of this touchpoint into the touchpoint product recommendation effect evaluation model to obtain the touchpoint marketing contribution index of this touchpoint.

3. The method according to claim 1, wherein The touchpoint marketing contribution index of each touchpoint is determined by the following method: Setting multiple preset dimensions, where the multiple preset dimensions include sales force, brand force, and user force; For each preset dimension, based on the user feedback data and user behavior index data under this touchpoint, obtaining the touchpoint dimension index of this touchpoint under this preset dimension; For each preset dimension, performing a partial correlation analysis on this preset dimension and the user purchase behavior data under all touchpoints to obtain the dimension contribution index under this preset dimension, and determining the ratio of the dimension contribution index under this preset dimension to the overall dimension contribution index as the touchpoint contribution weight coefficient under this preset dimension; Calculate the contact marketing contribution index of the contact based on the contact dimension index and the contact contribution weight coefficient of the contact under each preset dimension.

4. The method according to claim 1, characterized in that Determine the contact input energy index of each contact in the following manner: Obtain the contact marketing contribution index of the contact by performing an exponential processing on the contact marketing contribution index of the contact. Determine the contact input energy index of the contact as the product of the contact marketing contribution index of the contact and the cost-effectiveness ratio.

5. The method according to claim 4, wherein The preset time period includes a plurality of sub-time periods, and the input degree includes sub-input degrees corresponding to the respective sub-time periods. Among them, determine the sub-input degree within each sub-time period in the following manner: For each sub-interval within the historical time period, determine the actual input degree for promoting the preset product within the historical time period, where the historical time period is earlier than the preset time period. Determine the decay weight coefficient corresponding to each sub-interval. For each sub-interval, calculate the product of the decay weight coefficient corresponding to the sub-interval and the actual input degree. Determine the sum of the products corresponding to all sub-intervals as the sub-input degree for promoting the preset product within the sub-time period.

6. The method according to claim 5, wherein For each sub-time period, each sub-interval under the sub-time period is the difference between the sub-time period and the corresponding preset value, and the preset values corresponding to each sub-interval are increasing. Among them, determine the decay weight coefficient corresponding to each sub-interval in the following manner: Determine the first intermediate variable corresponding to the sub-interval, where the first intermediate variable is the preset value corresponding to the sub-interval. Using the natural constant e as the base and the product of the first intermediate variable and the set constant as the exponent, obtain the second intermediate variable corresponding to the sub-interval. Determine the ratio of the second intermediate variable corresponding to the sub-interval to the total variable as the decay weight coefficient corresponding to the sub-interval, where the total variable is the sum of the second intermediate variables corresponding to all sub-intervals.

7. A product recommendation device using contact marketing evaluation, characterized in that, The device includes: A push module, configured to push a questionnaire to a target user and obtain user feedback data of the target user for the questionnaire, where the questionnaire is used to reflect the promotion situation of a preset product under different media and different marketing methods. An acquisition module, configured to acquire user behavior index data and user purchase behavior data under different contacts, where the media and / or marketing methods corresponding to different contacts are different, the user behavior index data refers to the acceptance degree of the user for the preset product recommended under the media and marketing method corresponding to the contact, and the user purchase behavior data refers to the purchase situation of the user for the preset product recommended under the media and marketing method corresponding to the contact. A calculation module, configured to obtain the contact marketing contribution index of each contact based on the user feedback data, user behavior index data, and user purchase behavior data under the contact, where the contact marketing contribution index refers to the contribution size of the media and marketing method corresponding to the contact to the overall preset product. A determination module, for each contact point, according to the contact point marketing contribution index and cost-effectiveness ratio of the contact point, obtains the contact point input energy index of the contact point, and determines the target contact point for the contact point corresponding to the maximum contact point input energy index obtained, so as to recommend the preset product according to the medium and marketing method corresponding to the target contact point, and the cost-effectiveness ratio is used to characterize the relationship between the sales amount of the preset product and the investment degree of promoting the preset product within a predetermined time period; Among them, the cost-effectiveness ratio is determined by the following method: Determine the sales amount of the preset product within the preset time period, and the preset time period refers to the promotion cycle of the preset product under different media and different marketing methods; Determine the contribution degree of all contact points to the sales amount within the preset time period, the preset time period includes multiple sub-time periods, and the contribution degree includes sub-contribution degrees corresponding to each sub-time period. Among them, each sub-contribution degree is determined by the following formula: Among them, Y t represents the sub - contribution corresponding to the t - th sub - time period, β0 represents the basic sales volume, and the basic sales volume refers to the sales volume that the preset product naturally generates without the promotion of media and marketing methods, β j represents the contribution coefficient of the j - th contact point to the sales volume, Z jt represents the investment degree for the preset product under the j - th contact point within the t - th sub - time period, 1 ≤ j ≤ Z, and Z represents the total number of contact points, e t represents the random error of the t - th sub - time period; Determine the investment degree of promoting the preset product within the preset time period; Calculate the product of the sales amount and the contribution degree within the preset time period, and determine the ratio of the product to the investment degree as the cost-effectiveness ratio.

Images