Strategy effect evaluation method and device

Abstract

The invention relates to a strategy effect evaluation method and device. The method comprises the following steps: collecting a behavior log of a user in a strategy operation process; determining contacts experienced by the user in the conversion path according to the behavior log; determining the occurrence frequency of each pair of contacts in the conversion path; according to the occurrence frequency of each pair of contacts, calculating the transfer probability of transferring one contact to the other contact in the conversion path; and transmitting the preset value of each contact in the conversion path to an upstream contact of the contacts according to the transition probability, and calculating the value of the upstream contact, thereby determining the first value of each contact in the conversion path. According to the method, attribution from a single effect to multiple contacts is expanded to attribution from multiple effects to multiple contacts, meanwhile, the discrete problem of conversion or not is converted into the continuous problem of value, and attribution redistribution of the total value is achieved. Therefore, the contact which has the greatest influence on strategy conversion can be more accurately determined, and the strategy optimization direction is further determined.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for evaluating the effectiveness of a strategy. Background Art

[0002] The Markov model is a statistical model used to represent the probability of transition between different states. In the attribution of strategic effects, touchpoints can be regarded as "states", and the process of users switching from one touchpoint to another is modeled as a state transition on a chain. The Markov model can consider the sequential relationship between touchpoints, that is, how one touchpoint affects the user's behavior to the next touchpoint, and can also handle loops in the conversion path, that is, users may contact the same touchpoint multiple times.

[0003] In the field of e-commerce and sales, it is crucial to understand the user's behavior path and attribution contribution during the purchase journey. Traditional practices are usually based on manual surveys and empirical judgments. The limitation of this method is that it is difficult to quantify and systematically analyze user behavior. Therefore, a more effective method is needed to attribute the impact of sales activities on conversions. The Markov model is a method for strategic attribution that can help e-commerce and sales teams better understand user behavior paths and attribution contributions. By converting buyer behavior into a mathematical model, it can be pointed out which specific behaviors have made significant contributions to achieving conversion goals, providing data support for sales strategies. The advantage of this method is that it can consider the sequential relationship between touchpoints and handle loops in the conversion path, such as:

[0004] 1. Analyze user behavior paths and understand the user’s decision-making process during the purchase journey;

[0005] 2. Attribute the impact of sales activities on conversions and find out which sales touchpoints contribute the most to conversions;

[0006] 3. Optimize sales strategies and make adjustments based on user behavior paths and attribution contributions;

[0007] 4. Evaluate the effectiveness of sales activities and compare the conversion rates and attribution contributions of different sales strategies.

[0008] In the prior art, existing attribution models include:

[0009] 1. Linear Attribution Model

[0010] Methodology description: Conversions are distributed equally across all touchpoints in the customer journey, and each advertiser will share the reward for the conversion equally.

[0011] Advantages: Easy to understand and implement. Emphasizes the importance of all touch points and is suitable for multi-channel coordination.

[0012] Disadvantages: It cannot accurately reflect the actual contribution of certain touchpoints to conversions. It ignores the different influences between touchpoints, which may lead to unreasonable resource allocation.

[0013] 2. Time decay attribution model

[0014] Method description: The value is assigned based on the time distribution between the contact point and the actual conversion. The closer the contact point is to the conversion time, the higher the attribution value it obtains.

[0015] Advantages: Emphasizes touch points close to conversion, which may more accurately reflect the user decision-making process. Better adapt to rapidly changing user behavior patterns.

[0016] Disadvantages: It ignores the role of early contact points in improving brand awareness and initially attracting users. The implementation is complex and requires determining the appropriate attenuation coefficient.

[0017] 3. U-Shaped Attribution Model

[0018] Method description: Emphasize the first and last touch points. Usually the first and last touch points in the user journey will get most of the attribution value, while the middle touch points will get relatively less attribution value.

[0019] Advantages: It emphasizes the importance of the first and last touch points, and helps identify the key points of the user's initial contact and final conversion. It has a certain guiding role in the optimization of sales strategies, especially the analysis of the effect of early brand attraction and the final touch.

[0020] Disadvantages: It ignores the impact of the intermediate process and cannot fully reflect the user's entire conversion journey. It is suitable for specific sales scenarios and may not be suitable for all types of customer paths.

[0021] 4. Multi-touch attribution model

[0022] Method description: The multi-touch attribution model simultaneously evaluates multiple points of contact of users in the conversion process, and determines the contribution of each touch point through complex algorithms and statistical models. The Markov chain model is one of them, which analyzes the impact of each touch point based on the statistical modeling of the user behavior path.

[0023] Advantages: It can fully reflect the contribution value of each contact point of the user in the conversion process. It helps to analyze and understand the specific role of each contact point in detail, and provide more accurate guidance for optimization strategies.

[0024] Disadvantages: high model complexity, large data requirements, poor interpretability of the final results, high requirements for data quality and integrity, and high fees and implementation costs. Summary of the invention

[0025] This application provides a new strategy effect evaluation scheme, which extends the attribution of a single effect to multiple touchpoints to the attribution of multiple effects to multiple touchpoints, and at the same time transforms discrete issues such as conversion or not into continuous issues of high or low value, thus achieving the redistribution of the attribution of the overall value. Thus, it is possible to more accurately identify the touchpoints that have the greatest impact on strategy conversion, and further clarify the direction of strategy optimization.

[0026] According to a first aspect of the present application, a method for evaluating the effectiveness of a strategy is provided, characterized by comprising:

[0027] Collect user behavior logs during the execution of the strategy;

[0028] Determine the touchpoints experienced by the user in the conversion path based on the behavior log;

[0029] Determining the frequency of each pair of touchpoints in the conversion path;

[0030] Calculating a transfer probability of one touch point transferring to another touch point in the conversion path according to the frequency of occurrence of each pair of touch points; and

[0031] According to the transfer probability, the preset value of any touch point in the conversion path is transferred to the upstream touch point of the touch point, and the value of the upstream touch point is calculated, so as to determine the first value of each touch point in the conversion path.

[0032] According to a second aspect of the present application, a device for evaluating the effectiveness of a strategy is provided, characterized in that it includes:

[0033] The collection module is used to collect user behavior logs during the operation of the strategy;

[0034] A first determination module, configured to determine the touch points experienced by the user in the conversion path according to the behavior log;

[0035] A second determination module is used to determine the frequency of occurrence of each pair of contacts in the conversion path;

[0036] A first calculation module is used to calculate the transfer probability of one touch point transferring to another touch point in the conversion path according to the frequency of occurrence of each pair of touch points; and

[0037] The second calculation module is used to transfer the preset value of each touch point in the conversion path to the upstream touch point of the touch point according to the transfer probability, calculate the value of the upstream touch point, and thus determine the first value of each touch point in the conversion path.

[0038] According to a third aspect of the present application, there is provided an electronic device, comprising:

[0039] Processor; and

[0040] A memory storing computer instructions, which, when executed by the processor, causes the processor to execute the method described in the first aspect.

[0041] According to a fourth aspect of the present application, a non-transitory computer storage medium is provided, storing a computer program, which, when executed by multiple processors, enables the processors to execute the method described in the first aspect.

[0042] According to the strategy effect evaluation method and device provided by the present application, by considering the sequential relationship between the touch points in the conversion path, that is, how one touch point affects the user's behavior to the next touch point, the contribution of the touch points is characterized by value, thereby overcoming the shortcoming of the traditional model that only has a single-target attribution of conversion; and, the concept of value flow is creatively proposed, which can accurately measure the contribution of each touch point to the final conversion. While accurately obtaining the impact of each touch point on the strategy conversion, it also provides an important basis for optimizing the direction of the strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without exceeding the scope of protection required by the present application.

[0044] Figure 1 It is a flowchart of the method for evaluating the policy effect according to the first embodiment of the present application.

[0045] Figure 2 It is a schematic diagram of determining the touch points experienced by a user in a conversion path according to an embodiment of the present application.

[0046] Figure 3 is a schematic diagram of determining the frequency of occurrence of each pair of contacts in a conversion path according to an embodiment of the present application.

[0047] Figure 4 It is a schematic diagram of determining the first value of a contact according to an embodiment of the present application.

[0048] Figure 5 It is a flowchart of a method for evaluating the effectiveness of a strategy according to the second embodiment of the present application.

[0049] Figure 6 is a schematic diagram of removing a specified touch point in a conversion path according to an embodiment of the present application.

[0050] Figure 7 It is a flowchart of a method for evaluating the effectiveness of a strategy according to the third embodiment of the present application.

[0051] Figure 8 It is a schematic diagram of determining the average contribution value of a contact according to an embodiment of the present application.

[0052] Fig. 9 It is a schematic diagram of a device for evaluating the effectiveness of a strategy according to the first embodiment of the present application.

[0053] Fig.10 It is a schematic diagram of a device for evaluating the effectiveness of a strategy according to a second embodiment of the present application.

[0054] Fig.11 It is a schematic diagram of a device for evaluating the effectiveness of a strategy according to the first embodiment of the present application.

[0055] Fig.12 It is a structural diagram of an electronic device provided by this application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present application.

[0057] Figure 1 FIG. 1 is a flow chart of a method for evaluating the effect of a strategy according to the first embodiment of the present application. Figure 1 As shown, the method includes:

[0058] Step S101, collecting user behavior logs during the strategy execution process;

[0059] Step S102, determining the touch points experienced by the user in the conversion path according to the behavior log;

[0060] Step S103, determining the frequency of occurrence of each pair of contacts in the conversion path;

[0061] Step S104, calculating the transfer probability of one touch point transferring to another touch point in the conversion path according to the frequency of occurrence of each pair of touch points; and

[0062] Step S105: according to the transfer probability, the preset value of each touch point in the conversion path is transferred to the upstream touch point of the touch point, and the value of the upstream touch point is calculated, so as to determine the first value of each touch point in the conversion path.

[0063] According to some implementations, the "strategy" described in this application may be a strategy applied to any economic activity, such as a sales strategy, etc., and this application does not impose any restrictions on this. For example, a sales strategy may refer to a strategy adopted by an advertiser to attract and retain customers, such as cost-per-view advertising (CPM), cost-per-click advertising (CPC), and cost-per-action advertising (CPA).

[0064] During the execution of a determined strategy, a processing device (such as a computer, PAD, etc.) can collect user behavior logs in real time or at regular intervals, and determine the touch points experienced by the user in the conversion path based on the behavior logs. Figure 2 Schematic diagram of determining the touch points experienced by a user in a conversion path according to an embodiment of the present application. In the present application, a "touch point" may also be referred to as a "state" or a state in a Markov chain. Figure 2 As shown, for a buyer's behavior chain, the corresponding conversion path includes "start-recommendation exposure-click-inquiry-transaction", etc., and the states in the conversion path include "start", "recommendation", "exposure", "click", "inquiry", "transaction", "loss", etc.

[0065] After determining the touchpoints in the conversion path, calculate the frequency of behavior between each touchpoint by counting the frequency of occurrence of each pair of touchpoints in the user path. Figure 3 is a schematic diagram of determining the frequency of occurrence of each pair of contacts in a conversion path according to an embodiment of the present application. Figure 3 As shown in the figure, after splitting the buyer's behavior chain, the contact pairs formed include "start" and "recommendation exposure", "click" and "transaction", "fixed pit exposure" and "loss", etc.

[0066] According to a specific embodiment, the behavior frequency from contact point i to contact point j is defined as:

[0067] f ij = frequency (i→j) (1)

[0068] According to an optional embodiment, before determining the frequency of each pair of touchpoints in the conversion path, the user's behavior log can be cleaned. According to a specific embodiment, the steps of data cleaning may include: 1. parsing the user log to extract various behaviors and time; 2. removing dirty data, deleting duplicate logs, and filtering cheating traffic; 3. integrating the date and behavior formats of logs from different sources.

[0069] Then, based on the frequency of each pair of touchpoints, the transition probability of one touchpoint to another in the conversion path is calculated. For example, the transition probability from touchpoint i to touchpoint j is shown in equation (2):

[0070]

[0071] According to the transition probability of each pair of contacts, a state transition probability matrix can be formed.

[0072] According to the transfer probability, the preset value of any touch point in the conversion path is transferred to the upstream touch point of the touch point, and the value of the upstream touch point is calculated.

[0073] According to a specific embodiment, based on the Markov chain model, the value of a valuable touchpoint is reversely transferred to the upstream touchpoint using a recursive method, such as Figure 4 As shown, first calculate the sum of the probabilities of all paths from contact s to target contact e, where the weight of each edge represents the probability of a part of the path, and then assign the value val(s) of contact s to the target contact e according to the total probability, as shown in equation (3):

[0074] P(s,e)=∑ n∈N(s) val(s)·p(s,n)·p(n,e) (3)

[0075] Among them, val(s) represents the value of contact s, which is a preset value. P(s,e) represents the total probability from contact s to contact e. p(s,e) represents the weight (probability) of the direct edge from contact s to contact e. If another contact n is passed in the middle, then p(s,e) = p(s,n)p(n,e), p(s,n) and p(n,e) represent the probabilities from s to n and from n to e respectively; N(s) represents the set of all adjacent contacts starting from contact s.

[0076] According to a specific embodiment, each contact point in the conversion path has value and contribution. For example: in the conversion path A->B->C->D->B, contact point D is the final transaction, and contact point B is clicking on an advertisement. When the behaviors of D and B occur, there will be a phenomenon of deduction. The value of contact point D val(D) will be distributed to contact points C, B, and A according to probability. At the same time, the value of contact point B val(B) will also be distributed to contact points A and D, C, B, and A according to probability. There may be a chance of looping, and the distribution will be reduced in a recursive manner; according to an optional embodiment, it can be set that when the value is less than a preset value (for example, 1e-3), the recursion stops, and the value of the next contact point is calculated, and it is carried out in sequence, and finally all the value redistribution is realized.

[0077] In this way, the value of each touchpoint in the conversion path is determined by passing the preset value of any touchpoint in the conversion path to the upstream touchpoint.

[0078] Figure 5 is a flow chart of a method for evaluating the effect of a strategy according to a second embodiment of the present application. Figure 1 compared to, Figure 5 Steps S501 to S505 of the method shown are Figure 1 Steps S101 to S105 of the method shown are substantially the same, except that: Figure 5 The method shown also includes:

[0079] Step S506, when one designated touch point in the conversion path is removed, calculating the second values ​​of other touch points in the conversion path except the designated touch point;

[0080] Step S507: determining the attribution contribution of the designated touch point according to the second value of the other touch points and the first value of each touch point in the conversion path.

[0081] In order to determine the contribution of a specific touchpoint in the conversion path, according to some embodiments, the specific touchpoint is removed, the conversion probability of the user path is recalculated, and its impact on the overall path is analyzed. The actual contribution of the touchpoint is evaluated by comparing the path conversion rates before and after the removal. Figure 6 Shows the change in conversion path after removing the "Inquiry" touchpoint.

[0082] According to a specific embodiment, the contact k is set as the contact to be removed. After the contact k is removed, according to the Markov chain model, the value val(e,-k) of the contact e is as shown in equation (4):

[0083]

[0084] in,

[0085] Among them, val(s) represents the value of touch point s, which is a preset value. P(s,e) represents the total probability from touch point s to touch point e. P(s,e) represents the weight (probability) of the direct edge from touch point s to touch point e. If another touch point n is passed in the middle, then P(s,e) = p(s,n)p(n,e), p(s,n) and p(n,e) represent the probabilities from s to n and from n to e respectively; N(s) represents the set of all adjacent touch points starting from touch point s, and S represents the set of all valuable touch points.

[0086] The value of each touch point in the conversion path where the touch point is not removed is set as the first value, such as val(e). After removing the specific touch point, the value of each remaining touch point in the conversion path is calculated and set as the second value, such as val(e,-k).

[0087] According to a specific embodiment, the attribution contribution of the removed touch point is determined according to the first value and the second value, as shown in equation (5):

[0088]

[0089] Among them, valn is the first value of contact n, is the second value of touch point n after removing touch point i, N represents the set of all touch points in the conversion path, C i Represents the attribution contribution of touch point i.

[0090] Figure 7 is a flow chart of a method for evaluating the effect of a strategy according to the third embodiment of the present application. Figure 5 compared to, Figure 7 Steps S701 to S707 of the method shown are Figure 5 Steps S501 to S507 of the method shown are substantially the same, except that: Figure 7 The method shown also includes:

[0091] Step S708: determining the average contribution value of the designated touch point according to the attribution contribution of the designated touch point, the frequency of occurrence of the designated touch point, and the total value of the conversion path.

[0092] According to some embodiments, the average contribution value of each touchpoint is calculated based on the total value of the conversion path and the attribution contribution of the touchpoint, and is calculated by weighted average of the behavioral frequencies of the touchpoints, wherein the total value of the conversion path is the sum of the values ​​of each valuable touchpoint in the conversion path, which is pre-set and can represent, for example, the total revenue in a sales scenario. Figure 8 is a schematic diagram of determining the average contribution value of a contact according to an embodiment of the present application. Figure 8 In the figure, the process of determining the single contribution value of touchpoints such as "recommended exposure" and "inquiry" is shown respectively.

[0093] According to a specific embodiment, the average contribution value of the contact is as shown in equation (6):

[0094]

[0095] Among them, V i is the average single contribution value of touchpoint i, R is the total value of the conversion path, C i is the attribution contribution of touchpoint i, R·C i represents the value of touchpoint i in the conversion path, f i is the frequency of contact i, such as the frequency of behavior, R·C i Divide by f i Represents the single value of contact i.

[0096] After the attribution contribution and the average contribution value of the touch points are obtained, the attribution contribution and the average contribution value of the relevant touch points may be displayed through a display device (eg, a display).

[0097] Based on the above method, according to another aspect of the present application, a device for evaluating the effectiveness of a strategy is provided. Fig. 9 Schematic diagram of a device for evaluating the effect of a strategy according to the first embodiment of the present application. Fig. 9 As shown, the device comprises:

[0098] Collection module 901, used to collect user behavior logs during the policy execution process;

[0099] A first determination module 902, configured to determine the touch points experienced by the user in the conversion path according to the behavior log;

[0100] A second determination module 903 is used to determine the frequency of occurrence of each pair of contacts in the conversion path;

[0101] A first calculation module 904 is used to calculate the transfer probability of one touch point transferring to another touch point in the conversion path according to the frequency of occurrence of each pair of touch points; and

[0102] The second calculation module 905 is used to transfer the preset value of each touch point in the conversion path to the upstream touch point of the touch point according to the transfer probability, calculate the value of the upstream touch point, and thus determine the first value of each touch point in the conversion path.

[0103] Fig.10 is a schematic diagram of a device for evaluating the effect of a strategy according to a second embodiment of the present application. Fig. 9 compared to, Fig.10 Modules 1001 to 1005 of the device shown in FIG. Fig. 9 Modules 901 to 905 of the device shown are substantially the same, except that: Fig.10 The device shown also includes:

[0104] A third calculation module 1006, configured to calculate, when a designated touch point in the conversion path is removed, second values ​​of other touch points in the conversion path except the designated touch point;

[0105] The third determination module 1007 is used to determine the attribution contribution of the designated touch point according to the second value of the other touch points and the first value of each touch point in the conversion path.

[0106] Fig.11 is a schematic diagram of a device for evaluating the effect of a strategy according to a third embodiment of the present application. Fig.10 compared to, Fig.11 Modules 1101 to 1107 of the device shown in FIG. Fig.10 Modules 1001 to 1007 of the device shown are substantially the same, except that: Fig.11 The device shown also includes:

[0107] The fourth determination module 1108 is configured to determine an average contribution value of the designated touch point according to the attribution contribution of the designated touch point, the frequency of occurrence of the designated touch point, and the total value of the conversion path.

[0108] According to the strategy effect evaluation method and device provided by the present application, by considering the sequential relationship between the touch points in the conversion path, that is, how one touch point affects the user's behavior to the next touch point, the contribution of the touch points is characterized by value, thereby overcoming the shortcoming of the traditional model that only has a single-target attribution of conversion; and, the concept of value flow is creatively proposed, which can accurately measure the contribution of each touch point to the final conversion. While accurately obtaining the impact of each touch point on the strategy conversion, it also provides an important basis for optimizing the direction of the strategy.

[0109] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0110] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0111] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical connection or other forms.

[0112] See also Fig.12 , Fig.12 An electronic device is provided, comprising a processor and a memory. The memory stores computer instructions, and when the computer instructions are executed by the processor, the processor executes the computer instructions to achieve the following Figure 1 , Figure 5 and Figure 7 The method and refinement scheme shown.

[0113] It should be understood that the above device embodiments are only illustrative, and the device disclosed in the present invention can also be implemented in other ways. For example, the division of units / modules described in the above embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0114] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present invention may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0115] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not otherwise specified, the processor or chip may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not otherwise specified, the on-chip cache, the off-chip memory, and the memory may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0116] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer electronic device (which can be a personal computer, a server or a network electronic device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0117] The present application also provides a non-transitory computer storage medium storing a computer program. When the computer program is executed by a plurality of processors, the processors execute the following Figure 1 , Figure 5 and Figure 7 The method and refinement scheme shown.

[0118] The embodiments of the present application are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application. At the same time, changes or deformations made by those skilled in the art based on the ideas of the present application, the specific implementation methods and the scope of application of the present application, all belong to the scope of protection of the present application. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. A method for evaluating the effectiveness of a strategy, characterized in that: include: Collect user behavior logs during the execution of the strategy; Determine the touchpoints experienced by the user in the conversion path based on the behavior log; Determining the frequency of each pair of touchpoints in the conversion path; Calculating a transfer probability of one touch point transferring to another touch point in the conversion path according to the frequency of occurrence of each pair of touch points; as well as According to the transfer probability, the preset value of each touch point in the conversion path is transferred to the upstream touch point of the touch point, and the value of the upstream touch point is calculated, so as to determine the first value of each touch point in the conversion path.

2. The method according to claim 1, characterized in that Also includes: When a designated touch point in the conversion path is removed, calculating second values ​​of other touch points in the conversion path except the designated touch point; The attribution contribution of the designated touch point is determined according to the second value of the other touch points and the first value of each touch point in the conversion path.

3. The method according to claim 2, characterized in that Also includes: An average contribution value of the designated touch point is determined according to the attribution contribution of the designated touch point, the frequency of occurrence of the designated touch point, and the total value of the conversion path.

4. The method according to claim 3, characterized in that Also includes: The attribution contribution and the average contribution value of the designated touch point are displayed through a display device.

5. The method according to any one of claims 1 to 3, characterized in that: Before determining the frequency of occurrence of each pair of contacts in the conversion path, the method further includes: Perform data cleaning on the user's behavior log.

6. The method according to claim 2, characterized in that In the process of determining the first value of each touch point in the conversion path and the second value of other touch points except the designated touch point, a Markov chain model is used for determination.

7. A device for evaluating the effectiveness of a strategy, characterized in that: include: The collection module is used to collect user behavior logs during the operation of the strategy; A first determination module, configured to determine the touch points experienced by the user in the conversion path according to the behavior log; A second determination module is used to determine the frequency of occurrence of each pair of contacts in the conversion path; A first calculation module, configured to calculate a transfer probability of one touch point transferring to another touch point in the conversion path according to the frequency of occurrence of each pair of touch points; as well as The second calculation module is used to transfer the preset value of each touch point in the conversion path to the upstream touch point of the touch point according to the transfer probability, calculate the value of the upstream touch point, and thus determine the first value of each touch point in the conversion path.

8. The device according to claim 7, characterized in that Also includes: A third calculation module, configured to calculate, when a designated touch point in the conversion path is removed, second values ​​of other touch points in the conversion path except the designated touch point; The third determination module is used to determine the attribution contribution of the designated touch point according to the second value of the other touch points and the first value of each touch point in the conversion path.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images