An AI marketing method and system based on data driving

Abstract

The application provides an AI marketing method and system based on data driving. The method comprises the following steps: receiving attribute information of a target to be marketed, obtaining a plurality of efficient flow cases according to the attribute information; obtaining flow operation information from each efficient flow case, the flow operation information comprising a plurality of flow targets, a flow order of each flow target and a flow intensity; obtaining other flow information of each flow target in a recent period, optimizing and adjusting the flow operation information according to the other flow information to obtain target flow operation information; and performing marketing operation on the target to be marketed according to the target flow operation information. The application can quickly learn successful experience by using the attribute information of the target to be marketed, and provide effective reference for marketing. Meanwhile, the successful experience is adaptively adjusted based on the recent flow situation of each network platform to be flowed, so that the probability of obtaining a more optimal flow effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of marketing management technology, and in particular to a data-driven AI marketing method and system. Background Art

[0002] With the booming internet ecosystem, consumers' online behavior paths have become increasingly complex and diverse, and traffic investment has become a crucial marketing tool. However, traditional traffic investment models have exposed numerous problems when addressing complex consumer behaviors and the need for precise targeting. Traditional traffic investment often relies on crude audience targeting methods, such as advertising based on basic information such as age, gender, and region. This approach fails to accurately target potential customers with real needs, resulting in significant waste of advertising budget on ineffective impressions.

[0003] Therefore, how to improve marketing efficiency is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a data-driven AI marketing method, system, electronic device, computer storage medium and computer program product.

[0005] The present invention provides a data-driven AI marketing method, which is applied to a marketing agent. The method comprises the following steps:

[0006] Receive attribute information of a target to be marketed, and obtain several high-efficiency traffic investment cases based on the attribute information;

[0007] Extracting flow-casting operation information from each of the efficient flow-casting cases, the flow-casting operation information including a number of flow-casting targets, and a flow-casting order and flow-casting intensity of each flow-casting target; wherein the flow-casting target refers to a network platform;

[0008] Obtaining other flow-casting information of each of the flow-casting targets in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining target flow-casting operation information;

[0009] Perform marketing operations on the target to be marketed according to the target flow operation information.

[0010] Optionally, extracting the flow-throwing operation information from each of the efficient flow-throwing cases includes:

[0011] Identify each network platform in each of the efficient traffic delivery cases and perform time clustering on the traffic delivery data of each network platform;

[0012] Determining the first traffic delivery order for each network platform according to the earliest time of the time clustering, and evaluating the first traffic delivery intensity of each network platform based on the traffic delivery data;

[0013] Taking each network platform in the efficient traffic allocation case with the best traffic allocation effect as the traffic allocation target, and taking the first traffic allocation order corresponding thereto as the traffic allocation order;

[0014] Comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value, and fine-tuning the first flow injection intensity based on the flow injection intensity adjustment value to obtain a second flow injection intensity;

[0015] The second flow injection intensity is used as the flow injection intensity of the flow injection target.

[0016] Optionally, the comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value includes:

[0017] Determine the number of deviations between the types of network platforms included in each of the efficient traffic allocation cases and the efficient traffic allocation case with the best traffic allocation effect, and obtain corresponding weighting coefficients according to the number of deviations;

[0018] The weighted coefficient is used to perform weighted summation on the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases, and an average value of the weighted summation results is calculated, and the average value is used as the flow injection intensity adjustment value.

[0019] Optionally, the acquiring other flow-casting information of each flow-casting target in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining the target flow-casting operation information includes:

[0020] Obtaining the other flow-casting information having the same or similar attributes as the target to be marketed in a recent period, evaluating and obtaining a second flow-casting intensity of each of the other flow-casting information, and calculating a variance of each of the second flow-casting intensities;

[0021] A flow intensity adjustment coefficient is determined based on the variance, and a target flow intensity is obtained by multiplying the flow intensity adjustment coefficient with the corresponding flow intensity. The target flow intensity is used to replace the flow intensity in the flow operation information to obtain the target flow operation information.

[0022] Optionally, before performing a marketing operation on the target to be marketed according to the target flow operation information, the method further includes:

[0023] Outputting the target flow-casting operation information and the flow-casting operation information to the marketing personnel at the same time, and after receiving the confirmation information from the marketing personnel, determining to execute the target flow-casting operation information;

[0024] Alternatively, after receiving the modification information from the marketing personnel, the modified target flow operation information corresponding to the modification information is executed.

[0025] The present invention also provides a data-driven AI marketing system, which is applied to a marketing agent and includes a processor and a memory. The processor calls and executes a computer program in the memory to implement the following steps:

[0026] Receive attribute information of a target to be marketed, and obtain several high-efficiency traffic investment cases based on the attribute information;

[0027] Extracting flow-casting operation information from each of the efficient flow-casting cases, the flow-casting operation information including a number of flow-casting targets, and a flow-casting order and flow-casting intensity of each flow-casting target; wherein the flow-casting target refers to a network platform;

[0028] Obtaining other flow-casting information of each of the flow-casting targets in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining target flow-casting operation information;

[0029] Perform marketing operations on the target to be marketed according to the target flow operation information.

[0030] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute any of the methods described above.

[0031] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0032] The present invention further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program is executed by a processor to execute any of the above methods.

[0033] The beneficial effects of the present invention are:

[0034] The present invention obtains efficient traffic delivery cases by utilizing the attribute information of the target to be marketed, which can quickly draw on successful experiences and provide effective reference for marketing. At the same time, the present invention also analyzes the recent traffic delivery status of each network platform to be delivered, so as to adaptively adjust the successful experience, thereby increasing the probability of obtaining a better traffic delivery effect, and thus significantly improving the accuracy and effectiveness of traffic delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a flowchart of a data-driven AI marketing method disclosed in an embodiment of the present invention.

[0037] Figure 2 It is a schematic diagram of the flow casting operation disclosed in an embodiment of the present invention.

[0038] Figure 3 This is a structural diagram of a data-driven AI marketing system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0040] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0041] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0042] In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings, or is the orientation or position relationship in which the product of the invention is usually placed when in use. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present invention.

[0043] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0044] like Figure 1 As shown, an embodiment of the present invention discloses a data-driven AI marketing method applied to a marketing agent, the method comprising the following steps:

[0045] S100, receiving attribute information of a target to be marketed, and obtaining several high-efficiency traffic investment cases based on the attribute information.

[0046] The attribute information of a marketing target covers a wide range of aspects. For example, if the target is a fashion clothing brand targeting young women, the attribute information may include the target audience age range (e.g., 18-30 years old), gender (female), brand style (e.g., simple casual style), and product price range (e.g., 100-500 yuan). This attribute information of the target can be manually entered by marketers.

[0047] Based on this attribute information, we filter through a massive database of traffic-generating examples. For example, the database contains traffic-generating examples from various industries and product types. By setting filtering criteria, such as targeting young women, fashion categories, and similar price ranges, we can obtain a number of high-performance traffic-generating examples that have achieved good marketing results.

[0048] S200, extracting flow-casting operation information from each of the efficient flow-casting cases, wherein the flow-casting operation information includes a number of flow-casting targets, and a flow-casting order and flow-casting intensity of each flow-casting target; wherein the flow-casting target refers to a network platform.

[0049] Further in-depth analysis is conducted on the multiple high-efficiency traffic injection cases selected above to extract the traffic injection operation information of these cases, including the traffic injection targets, as well as the traffic injection order and traffic injection intensity of each traffic injection target.

[0050] Taking the above-selected high-efficiency traffic investment cases of multiple fashion clothing brands as an example, the traffic investment targets extracted from the first case are Xiaohongshu, Douyin and Weibo. In terms of the order of traffic investment, first promote it on Xiaohongshu, then publish creative short videos on Douyin, and finally start a topic discussion on Weibo. The intensity of traffic investment is reflected by the advertising budget invested, the frequency of content release, etc. For example, 40% of the total budget is invested in Xiaohongshu, and 10 grass-planting notes are released every week; 35% of the budget is invested in Douyin, and 5 short videos are released every week; 25% of the budget is invested on Weibo, and 2 topic discussions are held every week. Similar traffic investment operation information is also extracted from other cases, including different network platforms as traffic investment targets and the corresponding traffic investment order and intensity arrangement. The principle of traffic investment can be referred to Figure 2 shown.

[0051] The multiple groups of flow injection targets obtained above, the flow injection order and flow injection intensity of each flow injection target are integrated and analyzed to obtain the final flow injection operation information.

[0052] S300, obtaining other flow-casting information of each flow-casting target in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining target flow-casting operation information;

[0053] For each of the multiple traffic delivery targets determined above, their traffic delivery information for a recent period, such as the past month, is obtained. By analyzing other traffic delivery information for each traffic delivery target in the recent period, the previously obtained reference traffic delivery operation information is adjusted to suit the current actual situation, thereby obtaining adjusted target traffic delivery operation information.

[0054] For example, for the traffic target of Xiaohongshu, other traffic information in recent periods shows that the advertising volume of fashion categories on Xiaohongshu has increased significantly in the past month. Based on this information, it is necessary to adjust the traffic intensity on Xiaohongshu, such as reducing the budget share from 30% to 40%.

[0055] S400: Perform marketing operations on the target to be marketed according to the target flow operation information.

[0056] Using the target traffic flow information obtained above as a benchmark, we gradually implemented traffic flow operations across various online platforms. For example, we began by promoting the brand on Xiaohongshu according to the adjusted budget and content release frequency, publishing a series of notes highlighting the brand's style and suitable for the target audience's clothing scenarios. Next, we released short videos of lifestyle scenes on Douyin according to the new budget and content direction. Finally, we implemented a plan on Weibo based on the set budget and topics, organizing discussions on trending topics related to the brand. By systematically executing these marketing operations across various online platforms, we hoped to attract the target audience, increase brand awareness, and increase product sales.

[0057] The present invention obtains efficient traffic delivery cases by utilizing the attribute information of the target to be marketed, which can quickly draw on successful experiences and provide effective reference for marketing. At the same time, the present invention also analyzes the recent traffic delivery status of each network platform to be delivered, so as to adaptively adjust the successful experience, thereby increasing the probability of obtaining a better traffic delivery effect, and thus significantly improving the accuracy and effectiveness of traffic delivery.

[0058] Optionally, extracting the flow-throwing operation information from each of the efficient flow-throwing cases includes:

[0059] Identify each network platform in each of the efficient traffic delivery cases and perform time clustering on the traffic delivery data of each network platform;

[0060] Determining the first traffic delivery order for each network platform according to the earliest time of the time clustering, and evaluating the first traffic delivery intensity of each network platform based on the traffic delivery data;

[0061] Taking each network platform in the efficient traffic allocation case with the best traffic allocation effect as the traffic allocation target, and taking the first traffic allocation order corresponding thereto as the traffic allocation order;

[0062] Comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value, and fine-tuning the first flow injection intensity based on the flow injection intensity adjustment value to obtain a second flow injection intensity;

[0063] The second flow injection intensity is used as the flow injection intensity of the flow injection target.

[0064] In this embodiment, the traffic data in the above-mentioned high-efficiency traffic data cases selected include the time of advertising on each platform, advertising exposure, user clicks, user interactions (likes, comments, shares), etc.

[0065] First, from the aforementioned traffic data, we can directly extract the network platforms that traffic was delivered to, such as Xiaohongshu, Douyin, Weibo, etc. These network platforms are the traffic delivery targets selected in the corresponding high-efficiency traffic delivery cases.

[0066] Then, by performing time-based clustering on the traffic data for each platform, we can determine the time period for this traffic flow. The earliest time in this period is used as the start time for traffic flow to that platform, and the order of traffic flow to each platform is determined based on the earliest time. For example, through time-based clustering, we found that in a highly efficient traffic flow case, the earliest concentrated flow on Xiaohongshu was at the beginning of the month, on Douyin in the middle of the month, and on Weibo at the end of the month. Based on this earliest time order, the order of traffic flow to the platforms is determined to be Xiaohongshu, Douyin, and Weibo.

[0067] Next, the traffic data also includes data such as the proportion of advertising budget, the frequency of publishing content, the average exposure and interaction volume of each content, etc. The above content is evaluated using a preset evaluation method to obtain the corresponding first traffic intensity. For example, on Xiaohongshu, by calculating the proportion of advertising budget of the platform during the entire traffic period, the frequency of publishing content, the average exposure and interaction volume of each content, etc., a comprehensive evaluation is conducted to obtain its first traffic intensity. The same method is used to obtain the first traffic intensity of Douyin and Weibo. It should be noted that the present invention does not limit the specific calculation formula of traffic intensity, but the above-mentioned correlation parameters are positively correlated with traffic intensity.

[0068] Next, the most effective case is identified from the high-efficiency traffic injection cases, either manually or through other means. Each network platform involved in this case is used as the traffic injection target, and the corresponding first traffic injection order is used as the traffic injection order. For traffic injection intensity, the first traffic injection intensity corresponding to each network platform in the case with the best effect is used as the basis. A comprehensive analysis of the first traffic injection intensity of all cases corresponding to the same traffic injection target is also conducted to obtain multiple corresponding traffic injection intensity adjustment values. These traffic injection intensity adjustment values ​​are then integrated with the first traffic injection intensity of the corresponding optimal case, thus obtaining multiple corresponding second traffic injection intensities.

[0069] At this point, the flow operation information including several flow targets, the flow order and flow intensity of each flow target is obtained. This flow operation information is the reference for the flow operation on the flow target this time.

[0070] Optionally, the comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value includes:

[0071] Determine the number of deviations between the types of network platforms included in each of the efficient traffic allocation cases and the efficient traffic allocation case with the best traffic allocation effect, and obtain corresponding weighting coefficients according to the number of deviations;

[0072] The weighted coefficient is used to perform weighted summation on the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases, and an average value of the weighted summation results is calculated, and the average value is used as the flow injection intensity adjustment value.

[0073] In this embodiment, the efficient traffic allocation case with the best traffic allocation effect is still used as the basis. The deviations between the types of network platforms included in other efficient traffic allocation cases and the optimal case are analyzed (the deviation value is the absolute value of the positive and negative deviations). For example, if network platform A in the optimal case is missing from another efficient traffic allocation case, the corresponding deviation value is 1; if network platforms B and C are added to another efficient traffic allocation case compared to the optimal case, the corresponding deviation value is 2. The magnitude of the deviation value reflects the degree of difference in the selected traffic allocation targets between the other efficient traffic allocation cases and the optimal case. Based on this difference, i.e., the aforementioned deviation value, a corresponding weighting coefficient is obtained. This matching is based on a preset correlation relationship, and the weighting coefficient is negatively correlated with the deviation value.

[0074] In other words, the greater the difference in flow target selection between other efficient flow-injection cases and the optimal case, the worse the reference value, and the smaller the corresponding weighting coefficient; conversely, the better the reference value, the larger the corresponding weighting coefficient. The weighting coefficient of the optimal case is 1.

[0075] It should be noted that each weighting coefficient applies to all flow targets in each high-efficiency flow case. The average of the weighted summation results can be: weighted summation result / N or weighted summation result / nN, where N is the number of all high-efficiency flow cases, n = 2, 3, etc. Using n can set the flow intensity adjustment value to a smaller value to achieve the goal of fine-tuning, preferably n = 3.

[0076] Optionally, the acquiring other flow-casting information of each flow-casting target in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining the target flow-casting operation information includes:

[0077] Obtaining the other flow-casting information having the same or similar attributes as the target to be marketed in a recent period, evaluating and obtaining a second flow-casting intensity of each of the other flow-casting information, and calculating a variance of each of the second flow-casting intensities;

[0078] A flow intensity adjustment coefficient is determined based on the variance, and a target flow intensity is obtained by multiplying the flow intensity adjustment coefficient with the corresponding flow intensity. The target flow intensity is used to replace the flow intensity in the flow operation information to obtain the target flow operation information.

[0079] In this embodiment, the aforementioned method can be used to obtain traffic injection operation information based on the reference case, namely, which network platforms need to be injected, and what the injection order and injection intensity are on these network platforms. At the same time, the present invention further considers the marketing injection of similar products on these selected network platforms in the recent period, and optimizes and adjusts the injection intensity in the injection operation information accordingly. Specifically:

[0080] Obtain recent traffic information on the online platform for products with the same or similar attributes as the target. Use the same method as above to evaluate each other's traffic information to determine the second traffic intensity. Then, calculate the variance between these second traffic intensities. This variance represents the disparity in traffic intensity between identical or similar products on the same online platform. A larger disparity indicates less intense marketing competition among marketers of these identical or similar products on the online platform. A smaller disparity indicates greater competition among marketers of these identical or similar products on the online platform (especially when the second traffic intensity is high).

[0081] Based on the above-mentioned correspondence between variance and competition intensity, the present invention sets a flow intensity adjustment coefficient determined according to the variance. There is also a negative correlation between the flow intensity adjustment coefficient and the variance, that is, the larger the variance, the smaller the corresponding flow intensity adjustment coefficient, such as 1.0 or 1.1. At this time, there is no need to excessively increase the flow intensity, and the probability of obtaining a good marketing effect can basically be ensured; and the smaller the variance, the larger the corresponding flow intensity adjustment coefficient, such as 1.3 or 1.5. At this time, the flow intensity needs to be increased to increase the probability of obtaining a good marketing effect.

[0082] Finally, the obtained flow intensity adjustment coefficient is multiplied by the corresponding flow intensity to obtain the target flow intensity, and the target flow intensity is used to replace the flow intensity in the flow operation information, thus completing the above-mentioned optimization adjustment and obtaining the target flow operation information.

[0083] Optionally, before performing a marketing operation on the target to be marketed according to the target flow operation information, the method further includes:

[0084] Outputting the target flow-casting operation information and the flow-casting operation information to the marketing personnel at the same time, and after receiving the confirmation information from the marketing personnel, determining to execute the target flow-casting operation information;

[0085] Alternatively, after receiving the modification information from the marketing personnel, the modified target flow operation information corresponding to the modification information is executed.

[0086] In this embodiment, in order to ensure the accuracy of the marketing effect, before performing marketing operations on the target to be marketed according to the target flow operation information, the determined target flow operation information needs to be output to the marketing personnel for confirmation, and at the same time, the flow operation information derived based on typical cases is also output to the marketing personnel for comparison and analysis.

[0087] If the marketing staff approves the target traffic operation information, they will directly feedback the confirmation information, and the target traffic operation information will be executed later. If the marketing staff approves the target traffic operation information, they will modify the target traffic operation information, such as adjusting the traffic intensity for each traffic target, and then feedback the adjusted target traffic operation information, which will be executed later.

[0088] like Figure 3 As shown, an embodiment of the present invention further discloses a data-driven AI marketing system, which is applied to a marketing agent and includes a processor and a memory. The processor calls and executes a computer program in the memory to implement the following steps:

[0089] Receive attribute information of a target to be marketed, and obtain several high-efficiency traffic investment cases based on the attribute information;

[0090] Extracting flow-casting operation information from each of the efficient flow-casting cases, the flow-casting operation information including a number of flow-casting targets, and a flow-casting order and flow-casting intensity of each flow-casting target; wherein the flow-casting target refers to a network platform;

[0091] Obtaining other flow-casting information of each of the flow-casting targets in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining target flow-casting operation information;

[0092] Perform marketing operations on the target to be marketed according to the target flow operation information.

[0093] The technical principles and technical effects of the system of the present invention are the same as those of the aforementioned method and will not be described in detail here.

[0094] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in the above embodiment.

[0095] An embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0096] An embodiment of the present invention further discloses a computer program product, including a computer program stored on a non-transitory computer-readable medium, wherein the computer program is executed by a processor to perform any of the methods described above.

[0097] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / operations specified in the flowchart diagrams and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0099] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0100] It should be understood that various forms of flow shown above can be used with orders of the steps re-arranged, added to, or removed. For example, various steps recited in the present disclosure can be performed in parallel, in series, or in different orders, as long as the desired results of the present disclosure are achieved, which are not limited herein.

[0101] The specific embodiments discussed above do not limit the scope of the present disclosure. Various modifications, combinations, sub-combinations and alternatives can be apparent to one of ordinary skill in the art and can be made to the specific embodiments without departing from the spirit and the scope of the disclosure. Any modifications, equivalent substitutions, improvements, and the like, made within the spirit and principles of the present disclosure should be included in the scope of the present disclosure.

Claims

1. A data-driven AI marketing method, applied to a marketing agent, characterized in that: The method comprises the following steps: Receive attribute information of a target to be marketed, and obtain several high-efficiency traffic investment cases based on the attribute information; Extracting flow-casting operation information from each of the efficient flow-casting cases, the flow-casting operation information including a number of flow-casting targets, and a flow-casting order and flow-casting intensity of each flow-casting target; wherein the flow-casting target refers to a network platform; Obtaining other flow-casting information of each of the flow-casting targets in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining target flow-casting operation information; Perform marketing operations on the target to be marketed according to the target flow operation information; The flow-throwing operation information extracted from each of the efficient flow-throwing cases includes: Identify each network platform in each of the efficient traffic delivery cases and perform time clustering on the traffic delivery data of each network platform; Determining the first traffic delivery order for each network platform according to the earliest time of the time clustering, and evaluating the first traffic delivery intensity of each network platform based on the traffic delivery data; Taking each network platform in the efficient traffic allocation case with the best traffic allocation effect as the traffic allocation target, and taking the first traffic allocation order corresponding thereto as the traffic allocation order; Comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value, and fine-tuning the first flow injection intensity based on the flow injection intensity adjustment value to obtain a second flow injection intensity; Using the second flow injection intensity as the flow injection intensity of the flow injection target; The comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value includes: Determine the number of deviations between the types of network platforms included in each of the efficient traffic allocation cases and the efficient traffic allocation case with the best traffic allocation effect, and obtain corresponding weighting coefficients according to the number of deviations; Using the weighting coefficient, weighted sum is performed on the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases, and an average value of the weighted summation results is calculated, and the average value is used as the flow injection intensity adjustment value; The acquiring of other flow-casting information of each flow-casting target in a recent period, and optimizing and adjusting the flow-casting operation information according to the other flow-casting information to obtain target flow-casting operation information, includes: Obtaining other traffic flow information with the same or similar attributes as the target to be marketed in a recent period, evaluating and obtaining a second traffic flow intensity for each of the other traffic flow information, and calculating a variance of each of the second traffic flow intensities; the variance is used to characterize the intensity of marketing competition among marketers of the same or similar products on the corresponding network platform; A flow intensity adjustment coefficient is determined based on the variance, and a target flow intensity is obtained by multiplying the flow intensity adjustment coefficient with the corresponding flow intensity. The target flow intensity is used to replace the flow intensity in the flow operation information to obtain the target flow operation information.

2. The data-driven AI marketing method according to claim 1, characterized in that: Before performing a marketing operation on the target to be marketed according to the target flow operation information, the method further includes: Outputting the target flow-casting operation information and the flow-casting operation information to the marketing personnel at the same time, and after receiving the confirmation information from the marketing personnel, determining to execute the target flow-casting operation information; Alternatively, after receiving the modification information from the marketing personnel, the modified target flow operation information corresponding to the modification information is executed.

3. A data-driven AI marketing system, applied to a marketing agent, comprising a processor and a memory, characterized in that: The processor calls and executes the computer program in the memory to implement the following steps: Receive attribute information of a target to be marketed, and obtain several high-efficiency traffic investment cases based on the attribute information; Extracting flow-casting operation information from each of the efficient flow-casting cases, the flow-casting operation information including a number of flow-casting targets, and a flow-casting order and flow-casting intensity of each flow-casting target; wherein the flow-casting target refers to a network platform; Obtaining other flow-casting information of each of the flow-casting targets in a recent period, optimizing and adjusting the flow-casting operation information according to the other flow-casting information, and obtaining target flow-casting operation information; Perform marketing operations on the target to be marketed according to the target flow operation information; The flow-throwing operation information extracted from each of the efficient flow-throwing cases includes: Identify each network platform in each of the efficient traffic delivery cases and perform time clustering on the traffic delivery data of each network platform; Determining the first traffic delivery order for each network platform according to the earliest time of the time clustering, and evaluating the first traffic delivery intensity of each network platform based on the traffic delivery data; Taking each network platform in the efficient traffic allocation case with the best traffic allocation effect as the traffic allocation target, and taking the first traffic allocation order corresponding thereto as the traffic allocation order; Comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value, and fine-tuning the first flow injection intensity based on the flow injection intensity adjustment value to obtain a second flow injection intensity; Using the second flow injection intensity as the flow injection intensity of the flow injection target; The comprehensively analyzing the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases to obtain a flow injection intensity adjustment value includes: Determine the number of deviations between the types of network platforms included in each of the efficient traffic allocation cases and the efficient traffic allocation case with the best traffic allocation effect, and obtain corresponding weighting coefficients according to the number of deviations; Using the weighting coefficient, weighted sum is performed on the first flow injection intensity of the same flow injection target in each of the high-efficiency flow injection cases, and an average value of the weighted summation results is calculated, and the average value is used as the flow injection intensity adjustment value; The acquiring of other flow-casting information of each flow-casting target in a recent period, and optimizing and adjusting the flow-casting operation information according to the other flow-casting information to obtain target flow-casting operation information, includes: Obtaining other traffic flow information with the same or similar attributes as the target to be marketed in a recent period, evaluating and obtaining a second traffic flow intensity for each of the other traffic flow information, and calculating a variance of each of the second traffic flow intensities; the variance is used to characterize the intensity of marketing competition among marketers of the same or similar products on the corresponding network platform; A flow intensity adjustment coefficient is determined based on the variance, and a target flow intensity is obtained by multiplying the flow intensity adjustment coefficient with the corresponding flow intensity. The target flow intensity is used to replace the flow intensity in the flow operation information to obtain the target flow operation information.

4. An electronic device comprising: a memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-2.

5. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 2 is executed.

6. A computer program product comprising a computer program stored on a non-transitory computer-readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.

Images