Directional data pushing method and system applied to internet advertisements

Abstract

The invention provides a directional data pushing method and system applied to Internet advertisements, and belongs to the technical field of Internet advertisements. The data directional pushing method applied to the Internet advertisement comprises the following steps: acquiring historical advertisement putting data of each channel party; according to the historical advertisement putting data, analyzing basic benefit data of each channel party according to a last historical preset putting period recent to the current moment; calculating comprehensive benefit data of each channel party according to the historical advertisement putting data and the basic benefit data of a preset number of historical preset putting periods except the last historical preset putting period closest to the current moment; determining an advertisement putting cost adjustment mode of each channel party in a next preset putting period closest to the current moment according to the comprehensive benefit data of each channel party; by adopting the scheme, the push income of the internet advertisement can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet advertising, and in particular to a method and system for targeted data push applied to Internet advertising. Background Art

[0002] Internet advertising refers to commercial advertising that directly or indirectly promotes goods or provides services in the form of text, images, audio, video or other forms through Internet media such as websites, web pages, and Internet applications. Currently, people receive information in a variety of ways, and the information that can be passively or actively received from the Internet is also different. Generally speaking, when placing advertisements, multiple channels will be selected for placement. In the case of limited total advertising costs, in order to increase the revenue from the push of Internet advertisements, it is very important to allocate the advertising costs of each channel. Summary of the invention

[0003] The present application provides a data directional push method and system for Internet advertising, which can improve the push delivery revenue of Internet advertising.

[0004] In a first aspect, the present application provides a data directional push method for Internet advertising. The method comprises: Obtaining historical advertising data from each channel; the historical advertising data includes historical advertising costs and historical advertising push feedback data for multiple historical preset advertising cycles; the historical advertising push feedback data includes historical consultation volume and historical transaction volume; Analyze the basic benefit data of the most recent historical preset delivery cycle of each channel according to the historical advertising delivery data; the basic benefit data is associated with the historical advertising push feedback data; Calculate the comprehensive benefit data of each channel party according to the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data; The advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment is determined according to the comprehensive benefit data of each channel party.

[0005] Furthermore, the calculation method of the basic benefit data includes: ; In the formula, The basic benefit data for any channel party, The historical transaction volume of the corresponding channel party in the most recent historical preset delivery cycle at the current time. The historical consultation volume of the corresponding channel party in the most recent historical preset delivery cycle at the current moment. The historical advertising delivery cost of the corresponding channel party in the most recent historical preset delivery cycle at the current moment; is the preset profit coefficient; They are respectively the first preset adjustment parameter and the second preset adjustment parameter.

[0006] Furthermore, the comprehensive benefit data of each channel party is calculated based on the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data and includes: Calculate the historical basic benefit data of each channel party in each historical preset delivery cycle according to the calculation method of the basic benefit data and the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment; the preset number of historical preset delivery cycles are adjacent historical preset delivery cycles; Calculate the impact coefficient of the benefit change trend of each channel party based on the plurality of historical basic benefit data; Calculate the comprehensive benefit data of each channel party according to the benefit change trend impact coefficient and the basic benefit data; The calculation method of the comprehensive benefit data includes: ; In the formula, The comprehensive benefit data of any channel party, The basic benefit data of the corresponding channel party, is the impact coefficient of the benefit change trend of the corresponding channel party.

[0007] Furthermore, the calculation method of the benefit change trend impact coefficient includes: Assuming that the number of preset historical preset delivery cycles is n, the historical basic benefit data of any channel corresponding to the most recent historical preset delivery cycle closest to the current moment is The historical basic benefit data of any channel corresponding to the most distant historical preset delivery cycle from the last historical preset delivery cycle closest to the current moment is ; The n historical preset delivery cycles are historical preset delivery cycles that are continuous in time sequence; Calculate the historical basic benefit data difference of each adjacent historical preset delivery cycle; the historical basic benefit data difference is ;in, ; The number of historical preset delivery cycles is n, and the number of historical basic benefit data differences is indivual; Determine the sign of each of the historical basic benefit data differences. If each of the historical basic benefit data differences is positive or negative, the calculation method of the benefit change trend impact coefficient is: ; Otherwise, if the signs of all the historical basic benefit data differences include positive and negative, the calculation method of the benefit change trend impact coefficient is, ;in, is the number of historical basic benefit data differences with positive signs, is the number of historical base benefit data differences with negative sign.

[0008] Furthermore, the step of determining the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party includes: Determine the cost-increasing channel party and the cost-reducing channel party according to the comparison between the comprehensive benefit data and the preset benefit threshold; the cost-increasing channel party is the channel party whose comprehensive benefit data is greater than the preset benefit threshold; the cost-reducing channel party is the channel party whose comprehensive benefit data is not greater than the preset benefit threshold; Determining the number of the cost-increasing channel parties and the number of the cost-reducing channel parties; Determine the total increased cost data of the cost-increased channel parties according to the number of the cost-increased channel parties and the preset unit quantity cost adjustment data, and determine the increased cost data of each of the cost-increased channel parties based on the total increased cost data; The reduced total cost data is determined according to the increased total cost data, and the reduced cost data of each of the cost reduction channel parties is determined based on the reduced total cost data.

[0009] In a second aspect, the present application provides a data directional push system for Internet advertising, the system comprising: An acquisition module is used to acquire historical advertising delivery data of each channel party; the historical advertising delivery data includes historical advertising delivery costs and historical advertising push feedback data of multiple historical preset delivery cycles; the historical advertising push feedback data includes historical consultation volume and historical transaction volume; An analysis module is used to analyze the basic benefit data of the last historical preset delivery cycle of each channel at the current moment according to the historical advertising delivery data; the basic benefit data is associated with the historical advertising push feedback data; A calculation module, used to calculate the comprehensive benefit data of each channel party based on the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data; The determination module is used to determine the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party.

[0010] Furthermore, the analysis module is further configured such that the calculation method of the basic benefit data includes: ; In the formula, The basic benefit data for any channel party, The historical transaction volume of the corresponding channel party in the most recent historical preset delivery cycle at the current time. The historical consultation volume of the corresponding channel party in the most recent historical preset delivery cycle at the current moment. The historical advertising delivery cost of the corresponding channel party in the most recent historical preset delivery cycle at the current moment; is the preset profit coefficient; They are respectively the first preset adjustment parameter and the second preset adjustment parameter.

[0011] Furthermore, the calculation module is further configured to calculate the comprehensive benefit data of each channel party based on the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data and includes: Calculate the historical basic benefit data of each channel party in each historical preset delivery cycle according to the calculation method of the basic benefit data and the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment; the preset number of historical preset delivery cycles are adjacent historical preset delivery cycles; Calculate the impact coefficient of the benefit change trend of each channel party based on the plurality of historical basic benefit data; Calculate the comprehensive benefit data of each channel party according to the benefit change trend impact coefficient and the basic benefit data; The calculation method of the comprehensive benefit data includes: ; In the formula, The comprehensive benefit data of any channel party, The basic benefit data of the corresponding channel party, is the impact coefficient of the benefit change trend of the corresponding channel party.

[0012] Furthermore, the calculation module is further configured such that the calculation method of the benefit change trend influence coefficient includes: Assuming that the number of preset historical preset delivery cycles is n, the historical basic benefit data of any channel corresponding to the most recent historical preset delivery cycle closest to the current moment is The historical basic benefit data of any channel corresponding to the most distant historical preset delivery cycle from the last historical preset delivery cycle closest to the current moment is ; The n historical preset delivery cycles are historical preset delivery cycles that are continuous in time sequence; Calculate the historical basic benefit data difference of each adjacent historical preset delivery cycle; the historical basic benefit data difference is ;in, ; The number of historical preset delivery cycles is n, and the number of historical basic benefit data differences is indivual; Determine the sign of each of the historical basic benefit data differences. If each of the historical basic benefit data differences is positive or negative, the calculation method of the benefit change trend impact coefficient is: ; Otherwise, if the signs of all the historical basic benefit data differences include positive and negative, the calculation method of the benefit change trend impact coefficient is, ;in, is the number of historical basic benefit data differences with positive signs, is the number of historical base benefit data differences with negative sign.

[0013] Furthermore, the determination module is further configured to determine the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party, including: Determine the cost-increasing channel party and the cost-reducing channel party according to the comparison between the comprehensive benefit data and the preset benefit threshold; the cost-increasing channel party is the channel party whose comprehensive benefit data is greater than the preset benefit threshold; the cost-reducing channel party is the channel party whose comprehensive benefit data is not greater than the preset benefit threshold; Determining the number of the cost-increasing channel parties and the number of the cost-reducing channel parties; Determine the total increased cost data of the cost-increased channel parties according to the number of the cost-increased channel parties and the preset unit quantity cost adjustment data, and determine the increased cost data of each of the cost-increased channel parties based on the total increased cost data; The reduced total cost data is determined according to the increased total cost data, and the reduced cost data of each of the cost reduction channel parties is determined based on the reduced total cost data.

[0014] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A flow chart of a method for targeted data push applied to Internet advertisements in an embodiment of the present application is shown; Figure 2 A block diagram of a data directional push system applied to Internet advertising in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0018] The present application provides a data directional push method and system for Internet advertisements, which can improve the push efficiency of Internet advertisements.

[0019] In a first aspect, the present application provides a data targeting push method for Internet advertising. Figure 1 The specific steps included in the method are as follows.

[0020] Step S110: Acquire historical advertising delivery data of each channel; the historical advertising delivery data includes historical advertising delivery costs and historical advertising push feedback data of multiple historical preset delivery cycles; the historical advertising push feedback data includes historical consultation volume and historical transaction volume.

[0021] In the embodiments of the present application, an enterprise or user who wants to place an Internet advertisement will place the advertisement through various Internet platforms, that is, different channel parties, and the advertising cost given to each channel party is adjusted based on the feedback of the advertisements placed by different channel parties, so that the revenue brought by the advertisements placed by the enterprise or user is higher and more accurate, and can bring more transactions, indicating that the conversion rate of the placed advertisements is higher and the accuracy is also higher; it can be understood that the historical consultation volume here includes the number of clicks on the Internet platform, the amount of communication with online customer service, etc., and because different channel parties set different feedback modes for users to see the advertisements, they are represented as a whole here by the historical consultation volume. The historical consultation volume here refers to the number of customers who have seen the advertisement, paid attention to the product, and communicated with it. Similarly, the historical transaction volume refers to the number of customers who have successfully traded the product.

[0022] Step S120: analyzing the basic benefit data of the most recent historical preset delivery cycle of each channel at the current moment according to the historical advertisement delivery data; the basic benefit data is associated with the historical advertisement push feedback data.

[0023] In the embodiment of the present application, the calculation method of the basic benefit data specifically includes: ; In the formula, The basic benefit data for any channel party, The historical transaction volume of the corresponding channel party in the most recent historical preset delivery cycle at the current time. The historical consultation volume of the corresponding channel party in the most recent historical preset delivery cycle at the current moment. The historical advertising delivery cost of the corresponding channel party in the most recent historical preset delivery cycle at the current moment; is the preset profit coefficient; They are respectively the first preset adjustment parameter and the second preset adjustment parameter.

[0024] It can be understood that the basic benefits of advertising in different channels in the embodiments of the present application are reflected through the conversion rate of advertising. The conversion rate is obtained by dividing the transaction volume by the consultation volume, and the conversion rate represents the revenue data brought by the advertising. The investment-output ratio of the advertising, that is, the basic benefit data, can be obtained by dividing the revenue data by the cost. It should be noted that the method of the present application is essentially a machine learning model, in which the preset profit coefficient, the first preset adjustment parameter and the second preset adjustment parameter are all parameters that can be trained. By training the above parameters, the calculated basic benefit data is made more accurate, thereby making the following calculation process more accurate.

[0025] Step S130: Calculate the comprehensive benefit data of each channel party based on the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data.

[0026] In an embodiment of the present application, calculating the comprehensive benefit data of each channel party based on the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data specifically includes: calculating the historical basic benefit data of each channel party in each historical preset delivery cycle based on the calculation method of the basic benefit data and the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment; the preset number of historical preset delivery cycles are adjacent historical preset delivery cycles; calculating the benefit change trend influence coefficient of each channel party based on a plurality of the historical basic benefit data; calculating the comprehensive benefit data of each channel party based on the benefit change trend influence coefficient and the basic benefit data; The calculation method of the comprehensive benefit data includes: ; In the formula, The comprehensive benefit data of any channel party, The basic benefit data of the corresponding channel party, is the impact coefficient of the benefit change trend of the corresponding channel party.

[0027] The specific calculation method of the benefit change trend influence coefficient includes: assuming that the number of preset historical preset delivery cycles is n, then the historical basic benefit data of any channel corresponding to the most recent historical preset delivery cycle closest to the current moment is The historical basic benefit data of any channel corresponding to the most distant historical preset delivery cycle from the last historical preset delivery cycle closest to the current moment is ; n said historical preset delivery cycles are historical preset delivery cycles that are continuous in time series; calculate the historical basic benefit data difference of each adjacent historical preset delivery cycle; the historical basic benefit data difference is ;in, ; The number of historical preset delivery cycles is n, and the number of historical basic benefit data differences is ; determine the sign of each of the historical basic benefit data differences. If each of the historical basic benefit data differences is positive or negative, the calculation method of the benefit change trend impact coefficient is: Otherwise, if the signs of all the historical basic benefit data differences include positive and negative, the calculation method of the benefit change trend impact coefficient is, ;in, is the number of historical basic benefit data differences with positive signs, is the number of historical base benefit data differences with negative sign.

[0028] It can be understood that in the embodiment of the present application, the comprehensive benefit data is affected by the basic benefit data and the changing trend of the basic benefit; in this solution, the basic benefit data is taken as the basis, and the changing trend of the basic benefit, that is, the benefit changing trend influence coefficient is used to control the fluctuation of the comprehensive benefit data within a certain range; through the above method, the comprehensive benefit data of each channel party is more convenient to analyze and compare, and is more in line with actual changes.

[0029] Step S140: determining the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party.

[0030] In an embodiment of the present application, determining the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment based on the comprehensive benefit data of each channel party specifically includes: determining the cost-increasing channel party and the cost-reducing channel party based on the comparison between the comprehensive benefit data and the preset benefit threshold; the cost-increasing channel party is the channel party whose comprehensive benefit data is greater than the preset benefit threshold; the cost-reducing channel party is the channel party whose comprehensive benefit data is not greater than the preset benefit threshold; determining the number of the cost-increasing channel parties and the number of the cost-reducing channel parties; determining the increased total cost data of the cost-increasing channel parties based on the number of the cost-increasing channel parties and the preset unit quantity cost adjustment data, and determining the increased cost data of each of the cost-increasing channel parties based on the increased total cost data; determining the reduced total cost data based on the increased total cost data, and determining the reduced cost data of each of the cost-reducing channel parties based on the reduced total cost data.

[0031] In the embodiment of the present application, an average adjustment method is adopted for the cost adjustment mode; as mentioned above, the number of cost-increasing channel parties is 3, the number of cost-reducing channel parties is 2, and the preset unit quantity cost is 2%. Then the total cost data is increased by 6%, and the total cost data is correspondingly reduced by 6%. The increased cost data of each cost-increasing channel party is an increase of 2% in the advertising delivery cost, and the reduced cost data of each cost-reducing channel party is a reduction of 3% in the advertising delivery cost.

[0032] For the above situation, if the number of cost-reducing channel parties is zero, or the number of cost-increasing channel parties is zero, the cost-increasing channel parties and the cost-reducing channel parties are determined based on the ranking of the comprehensive benefit data of each channel party. At this time, the preset number of channel parties are the cost-increasing channel parties, and the remaining channel parties are the cost-reducing channel parties; for example, the total number of channel parties is 6, and the preset number of channel parties is 2, then the 2 channel parties with the highest comprehensive benefit data are selected as the cost-increasing channel parties, and the remaining 4 are the cost-reducing channel parties.

[0033] It should be noted that when the above-mentioned total cost reduction data is evenly distributed to each cost reduction channel party, if the total cost reduction data cannot be divided, then the total cost reduction data will be appropriately adjusted upward so that the minimum upward adjustment data that can satisfy the even distribution to each cost reduction channel party appears; for example, if the total cost reduction data is 8%, and there are 3 cost reduction channels, then the total cost reduction data will be adjusted upward to 9% so that the cost reduction data of each cost reduction channel party is 3%.

[0034] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, 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 embodiments of 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.

[0035] In the second aspect, the present application provides a data directional push system for Internet advertising. Figure 2As shown, the system includes an acquisition module 210, which is used to acquire historical advertising delivery data of each channel party; the historical advertising delivery data includes historical advertising delivery costs and historical advertising push feedback data of multiple historical preset delivery cycles; the historical advertising push feedback data includes historical consultation volume and historical transaction volume; an analysis module 220, which is used to analyze the basic benefit data of each channel party based on the most recent historical preset delivery cycle at the current moment according to the historical advertising delivery data; the basic benefit data is associated with the historical advertising push feedback data; a calculation module 230, which is used to calculate the comprehensive benefit data of each channel party based on the historical advertising delivery data and the basic benefit data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment; the comprehensive benefit data is associated with the basic benefit data; a determination module 240, which is used to determine the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party.

[0036] The analysis module 220 is further configured to calculate the basic benefit data in the following manner: ; In the formula, The basic benefit data for any channel party, The historical transaction volume of the corresponding channel party in the most recent historical preset delivery cycle at the current time. The historical consultation volume of the corresponding channel party in the most recent historical preset delivery cycle at the current moment. The historical advertising delivery cost of the corresponding channel party in the most recent historical preset delivery cycle at the current moment; is the preset profit coefficient; They are respectively the first preset adjustment parameter and the second preset adjustment parameter.

[0037] The calculation module 230 is further configured to calculate the comprehensive benefit data of each channel party according to the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data, including calculating the historical basic benefit data of each channel party in each historical preset delivery cycle according to the calculation method of the basic benefit data and the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment; the preset number of historical preset delivery cycles are adjacent historical preset delivery cycles; calculating the benefit change trend influence coefficient of each channel party according to a plurality of the historical basic benefit data; calculating the comprehensive benefit data of each channel party according to the benefit change trend influence coefficient and the basic benefit data; The calculation method of the comprehensive benefit data includes: ; In the formula, The comprehensive benefit data of any channel party, The basic benefit data of the corresponding channel party, is the impact coefficient of the benefit change trend of the corresponding channel party.

[0038] Furthermore, the calculation method of the benefit change trend influence coefficient includes: assuming that the number of preset historical preset delivery cycles is n, the historical basic benefit data of any channel corresponding to the most recent historical preset delivery cycle closest to the current moment is The historical basic benefit data of any channel corresponding to the most distant historical preset delivery cycle from the last historical preset delivery cycle closest to the current moment is ; n said historical preset delivery cycles are historical preset delivery cycles that are continuous in time series; calculate the historical basic benefit data difference of each adjacent historical preset delivery cycle; the historical basic benefit data difference is ;in, ; The number of historical preset delivery cycles is n, and the number of historical basic benefit data differences is ; determine the sign of each of the historical basic benefit data differences. If each of the historical basic benefit data differences is positive or negative, the calculation method of the benefit change trend impact coefficient is: Otherwise, if the signs of all the historical basic benefit data differences include positive and negative, the calculation method of the benefit change trend impact coefficient is, ;in, is the number of historical basic benefit data differences with positive signs, is the number of historical base benefit data differences with negative sign.

[0039] Among them, the determination module 240 is further configured to determine the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment based on the comprehensive benefit data of each channel party, including: determining the cost-increasing channel party and the cost-reducing channel party based on the comparison between the comprehensive benefit data and the preset benefit threshold; the cost-increasing channel party is the channel party whose comprehensive benefit data is greater than the preset benefit threshold; the cost-reducing channel party is the channel party whose comprehensive benefit data is not greater than the preset benefit threshold; determining the number of the cost-increasing channel parties and the number of the cost-reducing channel parties; determining the increased total cost data of the cost-increasing channel parties based on the number of the cost-increasing channel parties and the preset unit quantity cost adjustment data, and determining the increased cost data of each of the cost-increasing channel parties based on the increased total cost data; determining the reduced total cost data based on the increased total cost data, and determining the reduced cost data of each of the cost-reducing channel parties based on the reduced total cost data.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0041] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A data directional push method applied to Internet advertising, characterized in that: include: Obtaining historical advertising data from each channel; the historical advertising data includes historical advertising costs and historical advertising push feedback data for multiple historical preset advertising cycles; the historical advertising push feedback data includes historical consultation volume and historical transaction volume; Analyze the basic benefit data of the most recent historical preset delivery cycle of each channel according to the historical advertising delivery data; The basic benefit data is associated with the historical advertisement push feedback data; Calculate the comprehensive benefit data of each channel party according to the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data; The advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment is determined according to the comprehensive benefit data of each channel party.

2. The method for targeted data push applied to Internet advertisements according to claim 1, characterized in that: The calculation method of the basic benefit data includes: ； In the formula, The basic benefit data for any channel party, The historical transaction volume of the corresponding channel party in the most recent historical preset delivery cycle at the current time. The historical consultation volume of the corresponding channel party in the most recent historical preset delivery cycle at the current moment. The historical advertising delivery cost of the corresponding channel party in the most recent historical preset delivery cycle at the current moment; is the preset profit coefficient; They are respectively the first preset adjustment parameter and the second preset adjustment parameter.

3. The method for targeted data push applied to Internet advertisements according to claim 2, characterized in that: The comprehensive benefit data of each channel party is calculated based on the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data; The comprehensive benefit data associated with the basic benefit data include: Calculate the historical basic benefit data of each channel party in each historical preset delivery cycle according to the calculation method of the basic benefit data and the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment; the preset number of historical preset delivery cycles are adjacent historical preset delivery cycles; Calculate the impact coefficient of the benefit change trend of each channel party based on the plurality of historical basic benefit data; Calculate the comprehensive benefit data of each channel party according to the benefit change trend impact coefficient and the basic benefit data; The calculation method of the comprehensive benefit data includes: ； In the formula, The comprehensive benefit data of any channel party, The basic benefit data of the corresponding channel party, is the impact coefficient of the benefit change trend of the corresponding channel party.

4. The method for targeted data push applied to Internet advertisements according to claim 3, characterized in that: The calculation method of the benefit change trend impact coefficient includes: Assuming that the number of preset historical preset delivery cycles is n, the historical basic benefit data of any channel corresponding to the most recent historical preset delivery cycle closest to the current moment is The historical basic benefit data of any channel corresponding to the most distant historical preset delivery cycle from the last historical preset delivery cycle closest to the current moment is ; The n historical preset delivery cycles are historical preset delivery cycles that are continuous in time sequence; Calculate the historical basic benefit data difference of each adjacent historical preset delivery cycle; the historical basic benefit data difference is ;in, ; The number of historical preset delivery cycles is n, and the number of historical basic benefit data differences is indivual; Determine the sign of each of the historical basic benefit data differences. If each of the historical basic benefit data differences is positive or negative, the calculation method of the benefit change trend impact coefficient is: ; Otherwise, if the signs of all the historical basic benefit data differences include positive and negative, the calculation method of the benefit change trend impact coefficient is, ;in, is the number of historical basic benefit data differences with positive signs, is the number of historical base benefit data differences with negative sign.

5. The method for targeted data push applied to Internet advertisements according to claim 4, characterized in that: The method of determining the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party includes: Determine the cost-increasing channel party and the cost-reducing channel party according to the comparison between the comprehensive benefit data and the preset benefit threshold; the cost-increasing channel party is the channel party whose comprehensive benefit data is greater than the preset benefit threshold; the cost-reducing channel party is the channel party whose comprehensive benefit data is not greater than the preset benefit threshold; Determining the number of the cost-increasing channel parties and the number of the cost-reducing channel parties; Determine the total increased cost data of the cost-increased channel parties according to the number of the cost-increased channel parties and the preset unit quantity cost adjustment data, and determine the increased cost data of each of the cost-increased channel parties based on the total increased cost data; The reduced total cost data is determined according to the increased total cost data, and the reduced cost data of each of the cost reduction channel parties is determined based on the reduced total cost data.

6. A data directional push system applied to Internet advertising, characterized in that: include: An acquisition module (210) is used to acquire historical advertising delivery data of each channel party; the historical advertising delivery data includes historical advertising delivery costs and historical advertising push feedback data of multiple historical preset delivery cycles; the historical advertising push feedback data includes historical consultation volume and historical transaction volume; An analysis module (220) is used to analyze the basic benefit data of each channel in the most recent historical preset delivery cycle at the current moment according to the historical advertising delivery data; The basic benefit data is associated with the historical advertisement push feedback data; A calculation module (230) is used to calculate the comprehensive benefit data of each channel party based on the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data; the comprehensive benefit data is associated with the basic benefit data; The determination module (240) is used to determine the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment according to the comprehensive benefit data of each channel party.

7. The data directional push system for Internet advertising according to claim 6, characterized in that: The analysis module (220) is further configured such that the calculation method of the basic benefit data includes: ； In the formula, The basic benefit data for any channel party, The historical transaction volume of the corresponding channel party in the most recent historical preset delivery cycle at the current time. The historical consultation volume of the corresponding channel party in the most recent historical preset delivery cycle at the current moment. The historical advertising delivery cost of the corresponding channel party in the most recent historical preset delivery cycle at the current moment; is the preset profit coefficient; They are respectively the first preset adjustment parameter and the second preset adjustment parameter.

8. The data directional push system for Internet advertising according to claim 7, characterized in that: The calculation module (230) is further configured to calculate the comprehensive benefit data of each channel party based on the historical advertising delivery data of a preset number of historical preset delivery cycles other than the most recent historical preset delivery cycle at the current moment and the basic benefit data; The comprehensive benefit data associated with the basic benefit data include: Calculate the historical basic benefit data of each channel party in each historical preset delivery cycle according to the calculation method of the basic benefit data and the historical advertising delivery data of a preset number of historical preset delivery cycles except the most recent historical preset delivery cycle at the current moment; the preset number of historical preset delivery cycles are adjacent historical preset delivery cycles; Calculate the impact coefficient of the benefit change trend of each channel party based on the plurality of historical basic benefit data; Calculate the comprehensive benefit data of each channel party according to the benefit change trend impact coefficient and the basic benefit data; The calculation method of the comprehensive benefit data includes: ； In the formula, The comprehensive benefit data of any channel party, The basic benefit data of the corresponding channel party, is the impact coefficient of the benefit change trend of the corresponding channel party.

9. The data directional push system for Internet advertising according to claim 8, characterized in that: The calculation module (230) is further configured such that the calculation method of the benefit change trend influence coefficient includes: Assuming that the number of preset historical preset delivery cycles is n, the historical basic benefit data difference of any channel party corresponding to the most recent historical preset delivery cycle closest to the current moment is ;in, ; The number of historical preset delivery cycles is n, and the number of historical basic benefit data differences is indivual; Determine the sign of each of the historical basic benefit data differences. If each of the historical basic benefit data differences is positive or negative, the calculation method of the benefit change trend impact coefficient is: ; Otherwise, if the signs of all the historical basic benefit data differences include positive and negative, the calculation method of the benefit change trend impact coefficient is, ;in, is the number of historical basic benefit data differences with positive signs, is the number of historical base benefit data differences with negative sign.

10. The data directional push system for Internet advertising according to claim 9, characterized in that: The determination module (240) is further configured to determine, based on the comprehensive benefit data of each channel party, the advertising delivery cost adjustment mode of each channel party in the next preset delivery cycle closest to the current moment, including: Determine the cost-increasing channel party and the cost-reducing channel party according to the comparison between the comprehensive benefit data and the preset benefit threshold; the cost-increasing channel party is the channel party whose comprehensive benefit data is greater than the preset benefit threshold; the cost-reducing channel party is the channel party whose comprehensive benefit data is not greater than the preset benefit threshold; Determining the number of the cost-increasing channel parties and the number of the cost-reducing channel parties; Determine the total increased cost data of the cost-increased channel parties according to the number of the cost-increased channel parties and the preset unit quantity cost adjustment data, and determine the increased cost data of each of the cost-increased channel parties based on the total increased cost data; The reduced total cost data is determined according to the increased total cost data, and the reduced cost data of each of the cost reduction channel parties is determined based on the reduced total cost data.

Images