Data processing method, device, system, electronic device and storage medium

Abstract

Embodiments of the present invention provide a data processing method, device, system, electronic device and storage medium. The method includes: obtaining client identifiers that have browsed a target display link position within a target time period; dividing the client identifiers that have browsed the target display link among the client identifiers into a test group, and dividing the client identifiers that have browsed other display links except the target display link among the client identifiers into a control group; obtaining test behavior data of each client identifier in the test group after browsing the target display link, and control behavior data of each client identifier in the control group after browsing the other display links; generating display effect data of the target display link according to the test behavior data and the control behavior data; and sending the display effect data to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data processing method, a data processing device, a data processing system, an electronic device, and a computer-readable storage medium. Background Art

[0002] In modern business society, many businesses will place display links (e.g., advertisements) on various media or platforms to increase the exposure and popularity of their products and attract consumers to buy their products. Usually, such advertising investment is expensive, and advertisers hope to be able to quantify the return or benefits brought by their advertising investment, but the current evaluation accuracy of advertising effects cannot fully meet the requirements of advertisers.

[0003] Therefore, a new data processing method, device, system, electronic device and computer-readable storage medium are needed.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a data processing method, a data processing device, a data processing system, an electronic device and a computer-readable storage medium, thereby at least to a certain extent overcoming the technical problem of insufficient accuracy of display effect evaluation results caused by the limitations and defects of related technologies.

[0006] According to a first aspect of an embodiment of the present invention, a data processing method is provided, comprising: obtaining client identifiers that have browsed a target display link position within a target time period; dividing the client identifiers that have browsed the target display link among the client identifiers into a test group, and dividing the client identifiers that have browsed display links other than the target display link among the client identifiers into a control group; obtaining test behavior data of each client identifier in the test group after browsing the target display link, and control behavior data of each client identifier in the control group after browsing the other display links; generating display effect data of the target display link according to the test behavior data and the control behavior data; and sending the display effect data to a display link-affiliated client, so that the display link-affiliated client displays the display effect data.

[0007] In some exemplary embodiments of the present invention, based on the aforementioned scheme, the data processing method further includes: allocating the target display link position to N display links, N is a positive integer greater than or equal to 2, and the N display links include the target display link and the other display links; if a request to access the page where the target display link position is located is received, randomly selecting a display link from the N display links to display at the target display link position, and recording it in the display link exposure log of the target display link position.

[0008] In some exemplary embodiments of the present invention, based on the aforementioned scheme, obtaining the client identifier that has browsed the target display link position within the target time period includes: obtaining the display link exposure log of the target display link position within the target time period; and extracting the client identifier that has browsed the target display link position within the target time period according to the display link exposure log.

[0009] In some exemplary embodiments of the present invention, based on the aforementioned solution, the client identifiers in the test group and the control group are homogeneous.

[0010] In some exemplary embodiments of the present invention, based on the aforementioned scheme, the display effect data of the target display link is generated according to the test behavior data and the control behavior data, including: calculating the test expected value of the test behavior data; calculating the control expected value of the control behavior data; generating the display effect data of the target display link according to the test expected value and the control expected value.

[0011] In some exemplary embodiments of the present invention, based on the above-mentioned solution, the data processing method further includes: calculating the accuracy of the display effect data of the target display link.

[0012] In some exemplary embodiments of the present invention, based on the aforementioned solution, the test behavior data and the control behavior data include any one or more of browsing behavior, adding to cart behavior, searching behavior and ordering behavior.

[0013] According to a second aspect of an embodiment of the present invention, there is provided a data processing device, comprising: a client identification acquisition module, configured to acquire client identifications that have browsed a target display link position within a target time period; a client identification grouping module, configured to group client identifications that have browsed the target display link among the client identifications into a test group, and group client identifications that have browsed display links other than the target display link among the client identifications into a control group; a behavior data acquisition module, configured to acquire test behavior data of each client identification in the test group after browsing the target display link, and control behavior data of each client identification in the control group after browsing the other display links; an effect data generation module, configured to generate display effect data of the target display link according to the test behavior data and the control behavior data; and an effect data sending module, configured to send the display effect data to a display link-affiliated client, so that the display link-affiliated client displays the display effect data.

[0014] According to a third aspect of an embodiment of the present invention, a data processing system is provided, the system comprising: a memory, for storing N display links assigned to a target display link position, N being a positive integer greater than or equal to 2, the N display links including a target display link and other display links; a client, for sending a display request to a server when the client identifies access to a page where the target display link position is located; a server, for receiving and sending a selection request to the memory according to the display request, and receiving a first display link returned by the memory, and sending the first display link to the client for display at the target display link position, and recording it in a display link exposure log of the target display link position, wherein the first display link is randomly selected from the N display links; and a computing end, for calculating display effect data of the target display link according to the display link exposure log.

[0015] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the data processing method as described in any one of the above is implemented.

[0016] According to a fifth aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the data processing method as described in any one of the above is implemented.

[0017] In the technical solutions provided by some embodiments of the present invention, on the one hand, by dividing the client identifiers that have browsed the target display link position within the target time period into a test group (client identifiers that have browsed the target display link) and a control group (client identifiers that have not browsed the target display link but have browsed other display links) according to whether they have viewed the target display link at the target display link position within the target time period, a suitable counterfactual environment is defined for the actual situation where the current target display link position is limited in supply and there is competition among different display link masters, thereby improving the evaluation accuracy of the display effect of the target display link calculated based on the test behavior data of each client identifier in the test group and the control behavior data of each client identifier in the control group; on the other hand, in the present solution, the control group is not unable to see any display link during the evaluation process, but can browse other display links except the target display link, therefore, the display link traffic of the target display link position can be effectively utilized, and the display link revenue loss caused by the evaluation of the display effect can be reduced or eliminated.

[0018] In the technical solutions provided by other embodiments of the present invention, by allocating the target display link position to N display links, where N is a positive integer greater than or equal to 2, the N display links include the target display link and the other display links, and when a request to access the page where the target display link position is located is received, a display link is randomly selected from the N display links to be displayed at the target display link position. On the one hand, since the N display links are randomly played at the target display link position in turn, it can be ensured that the client identifiers in the test group and the control group are homogeneous, which can solve the technical problem of unreliable display effect evaluation results caused by different users in the related art, and eliminate possible human interference; on the other hand, the system automatically randomly selects a display link from the N display links for playback, and the displayed display links can be automatically measured and reported without the need for display link master settings.

[0019] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 A schematic flow chart of a data processing method according to some embodiments of the present invention is shown;

[0022] Figure 2 A schematic flow chart showing a data processing method according to some other embodiments of the present invention;

[0023] Figure 3 A schematic diagram of an interface of a target display link position according to some embodiments of the present invention is shown;

[0024] Figure 4 A schematic diagram showing randomly displaying display links at target display link positions according to some embodiments of the present invention is shown;

[0025] Figure 5 Shows Figure 1 A flowchart of some embodiments of step S110 in FIG.

[0026] Figure 6 A schematic diagram showing a control group and a test group according to some embodiments of the present invention;

[0027] Figure 7 A schematic diagram showing a test group user and a control group user according to some embodiments of the present invention;

[0028] Figure 8 A schematic diagram showing a process of generating a test group user set and a control group user set according to some embodiments of the present invention;

[0029] Fig. 9 Shows Figure 1 A flowchart of some embodiments of step S140 in FIG. 1 ;

[0030] Fig.10 A schematic block diagram showing a data processing apparatus according to some exemplary embodiments of the present invention;

[0031] Fig.11 A schematic block diagram of a data processing system according to some exemplary embodiments of the present invention is shown;

[0032] Fig.12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0033] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0034] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0035] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0036] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0037] In the related art, in the face of a highly competitive bidding environment for display links (such as advertisements), there are usually two ways to measure the display effect:

[0038] The first technical method: first establish a display link follow-up system, then after the experimental display link is actually released, obtain various user behavior data by recording the user's click path, and then determine whether the user's order is related to the release of the experimental display link based on the user behavior data and the follow-up system. Finally, count all orders related to the experimental display link to obtain the overall order effect brought by the experimental display link.

[0039] However, in the first technical method mentioned above, the display link order tracking technology cannot clearly determine that there is a very clear direct correlation between the order and the experimental display link. For example, the user may have a strong desire to buy, and even if the experimental display link is not inserted in the user's purchase path, the user will buy the product corresponding to the experimental display link. The display link evaluation effect given by the first technical method may be questioned by the display link owner (such as an advertiser).

[0040] The second technical method: The display link system randomly divides users into a test group (seeing the experimental display link) and a control group (not seeing any display link) through A / B testing. The effectiveness of the experimental display link is measured by comparing the differences in orders and shopping cart addition behaviors between the test group and the control group.

[0041] Although the second technical method mentioned above can ensure the homogeneity of users in the test group and the control group (using random user allocation) and is not easily affected by human interference, first of all, for a certain platform or media, the overall display link traffic (such as the overall advertising traffic) is roughly fixed. If the control group users cannot see any display links, then the random allocation of users may lead to a waste of display link traffic, affecting the overall display link revenue of the platform or media; secondly, in a highly competitive environment with limited display link positions, if a display link owner does not place its display link in the target display link position, there will be other display link owners to fill the position of the target display link position. Therefore, in the second technical method mentioned above, the control group cannot see any display link, which is not a true counterfactual environment, which will lead to inaccurate evaluation results of the final display effect. That is, in the second technical method mentioned above, the control group cannot see any display link, which will cause a waste of display link traffic and is not in line with the actual situation. In addition, the experiment of the second technical method currently relies on the application of the display link owner, which cannot be automated, and is inconvenient for the display link owner.

[0042] In the embodiment of the present invention, the counterfactual environment is a state opposite to the actual situation that we can observe. For example, if the user does not see the display link of this display link owner, but the display link of another display link owner, then the user's behavior may be different. And this condition is the counterfactual situation (Neyman, (1923) and Rubin (1980)).

[0043] Figure 1 The data processing method provided by the embodiment of the present invention can be executed by any device with computing and processing capabilities, such as a server and / or a terminal device, and the present invention is not limited to this.

[0044] like Figure 1 As shown, the data processing method provided by the embodiment of the present invention may include the following steps.

[0045] In step S110, the client identifiers that have browsed the target display link position within the target time period are obtained.

[0046] In the embodiment of the present invention, the client identifier may be, for example, a user ID (identification) of a user logging into the client or other information (such as a mobile phone number, user name, ID card number, or any other information that can uniquely identify the user's identity).

[0047] In the embodiment of the present invention, the target time period may be an arbitrarily selected period of time, such as the month from December 1, 2018 to December 31, 2018, or the year from January 1, 2018 to December 31, 2018, or the day of January 1, 2018, and the like.

[0048] In some embodiments, the target time period may be selected based on the time period of the target display link to be evaluated. For example, if display link owner A released a display link of product A on an e-commerce platform in the first half of 2018, the target time period may be determined as the first half of 2018.

[0049] In other embodiments, the selection of the target time period may also be determined based on the time period of the target display link to be evaluated. For example, display link owner A placed a display link of product A on an e-commerce platform in the first half of 2018. In order to evaluate the display effect during the promotion period on June 18, 2018, display link owner A may also select June 18, 2018 or a few days before and after as the target time period.

[0050] It should be noted that the present invention does not limit the method for determining the target time period.

[0051] In the embodiment of the present invention, a platform or media that can place display links, for example, an e-commerce platform, can pre-determine some positions on its user interface as display link positions, and merchants can purchase these display link positions to place corresponding display links, so that the merchants who purchase the display link positions become display link owners. The display link position where the target display link is placed can be called the target display link position.

[0052] In the embodiment of the present invention, the position of the display link on the user interface is not limited, for example, it can be the top of the user interface, or the bottom of the user interface, or both sides or one side of the user interface.

[0053] It should be noted that, usually, due to the limited supply of display link positions and the strong willingness of merchants to place display links, in the embodiment of the present invention, the target display link position is competitive, that is, if the display link owner A does not purchase the target display link position for placing the target display link, then other merchants will also purchase the target display link position for placing other display links.

[0054] In the embodiment of the present invention, the client identifier may correspond to a consumer, a user, etc. of an e-commerce platform, for example, and the present invention is not limited to this.

[0055] In step S120, the client identifiers that have browsed the target display link among the client identifiers are divided into a test group, and the client identifiers that have browsed other display links except the target display link among the client identifiers are divided into a control group.

[0056] In an exemplary embodiment, the client identifications in the test group and the control group are homogeneous.

[0057] In the embodiment of the present invention, homogeneity means that the distribution and nature of the users corresponding to the client identifiers in the test group and the control group are the same or similar. Taking the e-commerce platform as an example, for example, the purchasing behavior, browsing behavior, etc. of the users corresponding to the client identifiers in the two groups are consistent. If the purchasing behavior of the users corresponding to the two groups of client identifiers before viewing the display link (including the target display link or any other display link) is similar, then the users corresponding to the two groups of client identifiers can be considered to be homogeneous groups. For example, User A and User B both like computing devices, that is, they have the same interests. Then, for the display link owner of computer devices, User A and User B are homogeneous groups. Usually, the display link owner of computer devices is only interested in homogeneous groups of people who are interested in computer devices.

[0058] It should be noted that, here, whether the client identifiers in the two groups are homogeneous does not need to be determined by calculation. In actual operation, it is sufficient to ensure that the client identifiers in the two groups are randomly assigned.

[0059] In the embodiment of the present invention, any client identifier that has browsed the target display link at the target display link position within the target time period is divided into the test group, regardless of whether the client identifier has browsed other display links at the target display link position within the target time period.

[0060] In the embodiment of the present invention, as long as a certain client identifier has not browsed the target display link at the target display link position within the target time period, the client identifier may have browsed one or more other display links at the target display link position within the target time period, and the client identifier may be classified into the control group.

[0061] In step S130, test behavior data of each client identifier in the test group after browsing the target display link and control behavior data of each client identifier in the control group after browsing the other display links are obtained.

[0062] In an exemplary embodiment, the test behavior data and the control behavior data may include any one or more of browsing behavior, adding to a shopping cart behavior, searching behavior, and ordering behavior.

[0063] Here we still take the e-commerce platform as an example. Usually, after a user opens the user interface where the target display link position is located and browses the display link of the target display link position (which can be the target display link or other display links), he / she will browse the product details page of the product corresponding to the corresponding display link, add the product to the shopping cart, search for the product in the search bar of the e-commerce platform, place an order for the product, or a series of the above behaviors.

[0064] It should be noted that the above only uses the example of placing display links on e-commerce platforms. If the scenarios for placing target display links are different, different user behavior data can be tracked accordingly to evaluate the display effect.

[0065] In step S140, display effect data of the target display link is generated according to the test behavior data and the control behavior data.

[0066] In step S150, the display effect data is sent to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

[0067] In the embodiment of the present invention, the display link affiliated client may be, for example, a client used by a display link owner, such as an advertiser, who has purchased the target display link position and is used to place the target display link in the target display link position for display. After the display link affiliated client receives the display effect data of the target display link, it may display it on its display screen, so that the advertiser can intuitively and conveniently know the display effect of the target display link placed in the target display link position.

[0068] The data processing method provided by the embodiment of the present invention, on the one hand, divides the client identifiers that have browsed the target display link position within the target time period into a test group (client identifiers that have browsed the target display link) and a control group (client identifiers that have not browsed the target display link but have browsed other display links) according to whether they have viewed the target display link at the target display link position within the target time period, and defines a suitable counterfactual environment for the actual situation where the current target display link position is limited in supply and there is competition among different display link masters, thereby improving the evaluation accuracy of the display effect of the target display link calculated based on the test behavior data of each client identifier in the test group and the control behavior data of each client identifier in the control group; on the other hand, in the present scheme, the control group is not unable to see any display link during the evaluation process, but can browse other display links except the target display link, so that the display link traffic of the target display link position can be effectively utilized, and the display link income loss caused by the evaluation of the display effect can be reduced or eliminated.

[0069] Figure 2 The flowchart of the data processing method according to some other embodiments of the present invention is shown. The data processing method provided by the embodiment of the present invention can be executed by any device with computing processing capability, such as a server and / or a terminal device, and the present invention is not limited to this.

[0070] like Figure 2 As shown above Figure 1 The difference between the illustrated embodiments is that the data processing method provided by the embodiments of the present invention may further include the following steps.

[0071] In step S210, the target display link is allocated to N display links, where N is a positive integer greater than or equal to 2, and the N display links include the target display link and the other display links.

[0072] In the embodiment of the present invention, a display link service mechanism is pre-set in the system, and a target display link position can be sold to N display links at the same time (which can be N display links sold to one or more display link masters). Each time a user visits the target display link position, only one display link is displayed to the user.

[0073] In the embodiment of the present invention, due to the scarcity of display link traffic, if a display link owner does not place a display link at the target display link position, then the position will be purchased by other display link owners. This mechanism can ensure that all users who visit the target display link position will see the display link at the target display link position, the display link traffic will be fully utilized, and the display link income will not be affected.

[0074] In step S220, if a request to access the page where the target display link position is located is received, a display link is randomly selected from the N display links to be displayed at the target display link position, and is recorded in the display link exposure log of the target display link position.

[0075] In the embodiment of the present invention, the system can record and store the display link exposure log of each display link position, and the display link exposure log can record the exposure time, exposure duration, exposure times and other information of each display link placed in each display link position. Here, the display link exposure log of the target display link position in the target time period can be obtained from the stored data.

[0076] In an embodiment of the present invention, an A / B test module can be added to the display link server in advance. When a user browses the page where the target display link position is located, it can trigger the client (on which an e-commerce application is installed or the website of the e-commerce platform can be opened through a browser, etc.) to send a display link request to the display link server, and the display link server randomly extracts a display link from the above N display links and displays it to the user. Since the display link is randomly extracted, users who see any display link at the target display link position are homogeneous. The display link service mechanism provided by the embodiment of the present invention has a built-in display link random selection and playback function, which provides a rigorous and scientific A / B test basis for the display effect measurement system.

[0077] The data processing method provided by the embodiment of the present invention allocates a target display link position to N display links, wherein N is a positive integer greater than or equal to 2, and the N display links include the target display link and the other display links, and when a request to access the page where the target display link position is located is received, a display link is randomly selected from the N display links to be displayed at the target display link position. On the one hand, since the N display links are randomly played at the target display link position in turn, it can be ensured that the client identifiers in the test group and the control group are homogeneous, which can solve the technical problem of untrustworthy display effect evaluation results caused by different users in the related art, and eliminate possible human interference; on the other hand, the system automatically randomly selects a display link from the N display links for playback, and the displayed display links can be automatically measured and reported without the need for display link master settings.

[0078] Figure 3 A schematic diagram of an interface of a target display link position according to some embodiments of the present invention is shown.

[0079] like Figure 3 As shown, here we take the target display link position as the first focus display link position as an example for explanation.

[0080] In the embodiment of the present invention, the first focus display link position refers to the display link position at the most conspicuous position at the top of the user interface, usually the top or upper left corner of the webpage, which is the part that can attract the user's attention the most. Focus refers to the focus, which means the focus point. For example, Figure 3 The crab position on the top can be considered as a target display link position. Assuming that N display links purchase the target display link position at the same time, the N display links will be randomly played in turn at the target display link position.

[0081] The first-focus display link position is in a highly competitive environment because it easily attracts the attention of users. By using the data processing method provided in the embodiment of the present invention, on the one hand, the display link traffic utilization rate of the first-focus display link position can be greatly improved, and the display link income of the platform can be increased; on the other hand, the automation of measuring the digital display effect in a highly competitive environment can be achieved.

[0082] It should be noted that the data processing method provided in the embodiment of the present invention is not limited to Figure 3 The first focus display link position in a highly competitive environment cited as an example, as long as any display link position in a competitive environment can be applied to the method provided by the embodiment of the present invention, that is, for the same display link position, if a display link owner does not purchase it, other display link owners will purchase it, not necessarily the first focus display link position.

[0083] Figure 4 A schematic diagram of randomly displaying display links at target display link positions according to some embodiments of the present invention is shown.

[0084] like Figure 4 As shown, assuming that display link 1, display link 2, ... display link N (N is a positive integer greater than or equal to 2) purchase the target display link position at the same time, the system automatically and randomly displays any one of the N display links to the target display link position, and the probability of each display link being displayed is 1 / N.

[0085] Figure 5 Shows Figure 1 A flowchart of some embodiments of step S110 in FIG.

[0086] like Figure 5 As shown, in the embodiment of the present invention, the above step S110 may further include the following steps.

[0087] In step S111, the display link exposure log of the target display link position within the target time period is obtained.

[0088] In step S112, the client identifiers that have browsed the target display link position within the target time period are extracted according to the display link exposure log.

[0089] Figure 6 A schematic diagram showing a control group and a test group according to some embodiments of the present invention is shown.

[0090] In the embodiment of the present invention, each display link placed in the target display link position and all users who have seen the target display link position can be grouped by the display effect measurement system. The meanings of the two groups of users after grouping are as follows: Figure 6 shown.

[0091] like Figure 6 As shown, when display link 1 is the target display link, if the client identifier A corresponding to user A has not browsed display link 1 at the target display link position within the target time period, that is, display link 1 has no exposure relative to the client identifier A corresponding to user A, then the client identifier A corresponding to user A is divided into the control group of display link 1. When display link 2 is the target display link, if the client identifier A corresponding to user A has browsed display link 2 at the target display link position within the target time period, that is, display link 2 has exposure relative to the client identifier A corresponding to user A, then the client identifier A corresponding to user A is divided into the test group of display link 2.

[0092] When display link 1 is the target display link, if the client identifier B corresponding to user B has browsed display link 1 at the target display link position within the target time period, that is, display link 1 has exposure relative to the client identifier B corresponding to user B, then the client identifier B corresponding to user B is divided into the test group of display link 1. When display link 2 is the target display link, if the client identifier B corresponding to user B has not browsed display link 2 at the target display link position within the target time period, that is, display link 2 has no exposure relative to the client identifier B corresponding to user B, then the client identifier B corresponding to user B is divided into the control group of display link 2.

[0093] In the embodiment of the present invention, the calculation of the client identifiers corresponding to users in different groups can all be done using offline calculations, and the data source can use the exposure log of the target display link position in the target period. Taking the target display link position as the first focus display link position as an example, the client identifiers corresponding to all users participating in the experiment can be extracted according to whether the client identifier corresponding to the user has viewed the first focus display link position in the target period, and then the client identifiers corresponding to the user can be divided into a test group and a control group according to whether the target display link has been viewed in the target period of the target display link position. Taking display link 1 as the target display link as an example, the client identifiers corresponding to the users who have viewed display link 1 through the target display link position in the target period are all in the test group, regardless of whether the client identifier corresponding to the user has also viewed other display links through the target display link position in the target period. According to the display link exposed by the client identifier corresponding to the user, the client identifier corresponding to the user who sees the target display link of the display link master is divided into the test group, and the client identifier corresponding to the user who sees other display links (which may be other display link masters or the same display link master) is divided into the control group.

[0094] For example, there are four display links 1 to 4. When calculating the display effect of display link 1, the client identifier corresponding to the user who sees display link 1 through the target display link position during the target period is the test group, and the client identifier corresponding to the user who sees display link 2, display link 3, and display link 4 is the control group. Similarly, when calculating the display effect of display link 2, the client identifier corresponding to the user who sees display link 2 through the target display link position during the target period is the test group, and the client identifier corresponding to the user who sees display link 1, display link 3, and display link 4 is the control group.

[0095] In the embodiment of the present invention, after the client identifiers corresponding to the users are grouped, the client identifiers corresponding to the two groups of users are homogeneous due to the randomness of display links.

[0096] Figure 7 A schematic diagram showing test group users and control group users according to some embodiments of the present invention is shown.

[0097] like Figure 7 As shown, the test group users viewed display link 1 and display link 4 through the target display link position within the preset period, wherein display link 1 is assumed to be the target display link. The control group users viewed display link 3 and display link 5 through the target display link position within the preset period.

[0098] In the embodiment of the present invention, because each display link among the N display links that purchase the target display link position at the same time only occupies 1 / N traffic, the above-mentioned grouping method can be used for any display link of the target display link position, that is, the display effect can be measured, and because each user can see the display link, the display link traffic is not wasted, and the display link master is allowed to compete for the user traffic of the first-focus display link position.

[0099] Moreover, in actual situations, due to the scarcity of resources in the top display link position, if a display link owner does not purchase a display link in the top display link position, other display link owners will purchase a display link in the top display link position, so the user sees other display links as the correct counterfactual situation. The data processing method provided by the embodiment of the present invention effectively utilizes this condition and realizes automatic measurement of the effect of digital display links in a highly competitive environment.

[0100] Figure 8 A schematic diagram of a process for generating a test group user set and a control group user set according to some embodiments of the present invention is shown.

[0101] like Figure 8 As shown, it is assumed here that display link 1 is the target display link. The target display link will be randomly played at the target display link position and other (N-1) display links within the target period, and various display link playback information of the target display link position will be stored in the display link exposure log of the target display link position. Then, through the display link exposure log, all users who have browsed the display link at the target display link position within the target period can be extracted; the client identifiers corresponding to the users who have viewed display link 1 are used to generate the test group user set; the client identifiers corresponding to the users who have viewed other display links at the target display link position but have not viewed display link 1 are used to generate the control group user set.

[0102] Fig. 9 Shows Figure 1 A flowchart of some embodiments of step S140 in FIG.

[0103] like Fig. 9 As shown, in the embodiment of the present invention, the above step S140 may further include the following steps.

[0104] In step S141, the test expected value of the test behavior data is calculated.

[0105] In step S142, the control expected value of the control behavior data is calculated.

[0106] In step S143, the display effect data of the target display link is generated according to the test expected value and the control expected value.

[0107] In the embodiment of the present invention, since the test group and the control group are homogeneous, if Y1 represents the behavior of the user after seeing the target display link of the display link master at the target display link position (such as browsing, adding to shopping cart, searching and purchasing, etc.), Y0 represents the behavior of the user after seeing other display links except the target display link. It can be concluded that the expected values ​​of the user behaviors of the test group and the control group are equal when seeing the target display link:

[0108] E[Y 1|test group] = E[Y 1|control group] (1)

[0109] Similarly, the expected behavior of users in the test and control groups when they see other displayed links is equal:

[0110] E[Y 0|test group] = E[Y 0|control group] (2)

[0111] The above formulas (1) and (2) are an approximate relationship for the homogeneity of the two groups of users. Although the actual data of the Y1 control group does not exist, under the homogeneity condition, if the control group sees the target display link, its behavior should be similar to that of the test group.

[0112] Therefore, the display effect data of the target display link that the user sees can be:

[0113] Δ=E[Y1]-E[Y0]=E[Y1|test group]-E[Y0|control group] (3)

[0114] Assuming E[Y1|test group] is 0.5 and E[Y0|control group] is 0.6, Δdeta is equal to -0.1.

[0115] In an exemplary embodiment, the method may further include: calculating the accuracy of the display effect data of the target display link.

[0116] Assuming that the total sample size in one test is 1 million users and the total sample size in another test is 10 users, it is necessary to calculate t to determine the accuracy of the display effect data obtained from the two tests. The larger t is, the more accurate the calculation result is.

[0117] It should be noted that in the embodiment of the present invention, it is not required that the sample size of the test group and the sample size of the control group be the same in one test. For example, if the total number of users is 100, 10 users can be randomly assigned to one group and 90 users can be randomly assigned to the other group.

[0118] In the embodiment of the present invention, the display effect data can be inferred by comparing the difference between the test group and the control group. The specific inference method can use Welch's t-test, and the specific algorithm can be:

[0119]

[0120] The degree of freedom ν of the t-distribution can be calculated as:

[0121]

[0122] By finding the t-distribution with the corresponding degrees of freedom, we can know the accuracy of the true difference between the test group and the control group. If the t value is relatively large, the probability that the difference between the test group and the control group is caused by random distribution will be small.

[0123] In addition, in an embodiment of the present invention, a data processing device is also provided. Fig.10 As shown, the data processing device 1000 may include: a client identification acquisition module 1010 , a client identification grouping module 1020 , a behavior data acquisition module 1030 , an effect data generation module 1040 and an effect data sending module 1050 .

[0124] Among them, the client identification acquisition module 1010 can be configured to obtain the client identification that has browsed the target display link position within the current time. The client identification grouping module 1020 can be configured to divide the client identifications that have browsed the target display link among the client identifications into a test group, and divide the client identifications that have browsed other display links except the target display link among the client identifications into a control group. The behavior data acquisition module 1030 can be configured to obtain the test behavior data of each client identification in the test group after browsing the target display link, and the control behavior data of each client identification in the control group after browsing the other display links. The effect data generation module 1040 can be configured to generate the display effect data of the target display link according to the test behavior data and the control behavior data. The effect data sending module 1050 can be configured to send the display effect data to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

[0125] In an exemplary embodiment, the data processing device 1000 may further include: a display link allocation module, which may be configured to allocate the target display link position to N display links, where N is a positive integer greater than or equal to 2, and the N display links include the target display link and the other display links; a display link display module, which may be configured to randomly select a display link from the N display links to display at the target display link position if a request to access the page where the target display link position is located is received, and record it in the display link exposure log of the target display link position.

[0126] In an exemplary embodiment, the client identification acquisition module 1010 may include: a log acquisition unit, which may be configured to acquire a display link exposure log of the target display link position within the current time; and a client identification extraction unit, which may be configured to extract the client identification that has browsed the target display link position within the current time according to the display link exposure log.

[0127] In an exemplary embodiment, the client identifications in the test group and the control group are homogeneous.

[0128] In an exemplary embodiment, the effect data generation module 1040 may include: a test calculation unit, which can be configured to calculate a test expected value of the test behavior data; a control calculation unit, which can be configured to calculate a control expected value of the control behavior data; and an effect data generation unit, which can be configured to generate display effect data of the target display link based on the test expected value and the control expected value.

[0129] In an exemplary embodiment, the data processing device 1000 may further include an effect inference module, which may be configured to calculate the accuracy of the display effect data of the target display link.

[0130] In an exemplary embodiment, the test behavior data and the control behavior data include any one or more of browsing behavior, adding to a shopping cart behavior, searching behavior, and ordering behavior.

[0131] Since the functional modules of the data processing device 1000 of the exemplary embodiment of the present invention correspond to the steps of the exemplary embodiment of the above-mentioned data processing method, they are not described in detail here.

[0132] Furthermore, in an embodiment of the present invention, a data processing system is also provided, such as Fig.11 As shown, the data processing system 1100 may include a memory 1110 , a client 1120 , a server 1130 , and a computing end 1140 .

[0133] Among them, the memory 1110 can be used to store N display links assigned to the target display link position, N is a positive integer greater than or equal to 2, and the N display links include the target display link and other display links. The client 1120 can be used to send a display request to the server when the client identifies the page where the target display link position is accessed. The server 1130 can be used to receive and send a selection request to the memory according to the display request, and receive the first display link returned by the memory, and send the first display link to the client for display at the target display link position, and record it in the display link exposure log of the target display link position, wherein the first display link is randomly selected from the N display links. The computing end 1140 can be used to calculate the display effect data of the target display link according to the display link exposure log.

[0134] Continue to refer Fig.11 The data processing system 1100 may further include a display link affiliated client 1150 , and the computing end 1140 sends the display effect data of the target display link obtained by calculation to the display link affiliated client 1150 , so as to display the display effect data on the display link affiliated client 1150 .

[0135] In the embodiment of the present invention, the target display link position on the client 1120 can be pre-allocated to N display links, and the N display links can be stored in the memory 1110, wherein the N display links include the target display link and (N-1) other display links other than the target display link. When a client identifier browses the page where the target display link position is located on the client 1120, the client 1120 will be triggered to send a display request to the server 1130. After receiving the display request, the server 1130 can send a selection request to the memory 1110. After receiving the selection request, the memory 1110 can randomly select any one of the N stored display links as the first display link, that is, the probability of any one of the N display links being selected each time is 1 / N. Then, the memory 1110 returns the first display link to the server 1130, and the server 1130 returns the first display link to the client 1120 as a response to the display request. After receiving the first display link, the client 1120 displays it at the target display link position.

[0136] In the embodiment of the present invention, when the server 1130 sends the first display link to the client 1120 for display, the server 1130 may store the relevant information in the display link exposure log corresponding to the target display link position, wherein the relevant information may include the client identification information corresponding to the client that sends the display request, for example, the client identification logs in to the client through the user name, and the user name of the client identification may be recorded, and the relevant information may also include the information of the first display link, the time information and duration information of the first display link displayed at the target display link position, etc. Further, the relevant information may also include the behavior data of the client identification after browsing the first display link.

[0137] In an embodiment of the present invention, the computing end can obtain the client identifications that have browsed the target display link position within the target time period based on the display link exposure log of the target display link position; and can divide the client identifications that have browsed the target display link among the client identifications into a test group, and divide the client identifications that have browsed other display links except the target display link among the client identifications into a control group; and can also obtain the test behavior data of each client identification in the test group after browsing the target display link, and the control behavior data of each client identification in the control group after browsing the other display links; thereby, the display effect data of the target display link can be generated based on the test behavior data and the control behavior data.

[0138] For other contents in the embodiments of the present invention, reference may be made to the other embodiments described above.

[0139] In an exemplary embodiment of the present invention, an electronic device capable of implementing the above method is also provided.

[0140] Reference below Fig.12 , which shows a schematic diagram of the structure of a computer system 1200 of an electronic device suitable for implementing an embodiment of the present invention. Fig.12 The computer system 1200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0141] like Fig.12As shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage part 1208 into a random access memory (RAM) 1203. Various programs and data required for system operation are also stored in the RAM 1203. The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0142] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN card, a modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed, so that a computer program read therefrom is installed into the storage section 1208 as needed.

[0143] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 1209, and / or installed from a removable medium 1211. When the computer program is executed by a central processing unit (CPU) 1201, the above-mentioned functions defined in the system of the present application are executed.

[0144] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0145] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0146] The modules and / or units involved in the embodiments of the present invention may be implemented by software or hardware, and the modules and / or units described may also be arranged in a processor. The names of these modules and / or units do not, in some cases, limit the modules and / or units themselves.

[0147] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the data processing method described in the above embodiment.

[0148] For example, the electronic device may implement Figure 1 As shown in: Step S110, obtaining the client identifiers that have browsed the target display link position within the target time period; Step S120, dividing the client identifiers that have browsed the target display link among the client identifiers into a test group, and dividing the client identifiers that have browsed other display links except the target display link among the client identifiers into a control group; Step S130, obtaining the test behavior data of each client identifier in the test group after browsing the target display link, and the control behavior data of each client identifier in the control group after browsing the other display links; Step S140, generating the display effect data of the target display link according to the test behavior data and the control behavior data; Step S150, sending the display effect data to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

[0149] It should be noted that, although several modules or units of the equipment or device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0150] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0151] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0152] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A data processing method, characterized in that: include: Allocate the target display link position to N display links, where N is a positive integer greater than or equal to 2, and the N display links include the target display link and other display links; If a request to access the page where the target display link position is located is received, a display link is randomly selected from the N display links to be displayed at the target display link position, and is recorded in the display link exposure log of the target display link position; Obtain the client ID that has browsed the target display link position within the target time period; Classifying the client identifiers that have browsed the target display link among the client identifiers into a test group, and classifying the client identifiers that have browsed other display links except the target display link among the client identifiers into a control group; Acquire test behavior data of each client identifier in the test group after browsing the target display link, and control behavior data of each client identifier in the control group after browsing the other display links; Generate display effect data of the target display link according to the test behavior data and the control behavior data; The display effect data is sent to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

2. The data processing method according to claim 1, characterized in that: Get the client IDs that have browsed the target display link position within the target time period, including: Obtaining a display link exposure log of the target display link position within the target time period; The client identifier that has browsed the target display link position within the target time period is extracted according to the display link exposure log.

3. The data processing method according to claim 1, characterized in that: The client identifiers in the test group and the control group are homogeneous.

4. The data processing method according to claim 1, characterized in that: Generating display effect data of the target display link according to the test behavior data and the control behavior data includes: Calculating a test expected value of the test behavior data; Calculating a control expected value of the control behavior data; The display effect data of the target display link is generated according to the test expected value and the control expected value.

5. The data processing method according to claim 1, characterized in that: Also includes: Calculate the accuracy of the display effect data of the target display link.

6. The data processing method according to claim 1, characterized in that: The test behavior data and the control behavior data include any one or more of browsing behavior, adding to shopping cart behavior, searching behavior and ordering behavior.

7. A data processing device, characterized in that: include: A display link allocation module, configured to allocate a target display link bit to N display links, where N is a positive integer greater than or equal to 2, and the N display links include the target display link and other display links; a display link display module configured to randomly select a display link from the N display links to display it at the target display link position, and record it in the display link exposure log of the target display link position if a request to access the page where the target display link position is located is received; A client identification acquisition module configured to acquire the identification of a client that has browsed the target display link position within a target time period; a client identification grouping module configured to group the client identifications that have browsed the target display link among the client identifications into a test group, and group the client identifications that have browsed other display links except the target display link among the client identifications into a control group; A behavior data acquisition module configured to acquire test behavior data of each client identifier in the test group after browsing the target display link, and control behavior data of each client identifier in the control group after browsing the other display links; An effect data generating module, configured to generate display effect data of the target display link according to the test behavior data and the control behavior data; The effect data sending module is configured to send the display effect data to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

8. A data processing system, characterized in that: include: A memory, used to store N display links allocated to the target display link position, where N is a positive integer greater than or equal to 2, and the N display links include the target display link and other display links; The client is used to send a display request to the server when the client identifies the page where the target display link is located; The server is configured to receive and send a selection request to the storage according to the display request, receive a first display link returned by the storage, send the first display link to the client so as to be displayed at the target display link position, and record the first display link in the display link exposure log of the target display link position, wherein the first display link is randomly selected from the N display links; A computing end, for calculating display effect data of the target display link according to the display link exposure log, comprising: obtaining client identifiers that have browsed the target display link position within a target time period; dividing the client identifiers that have browsed the target display link among the client identifiers into a test group, and dividing the client identifiers that have browsed other display links except the target display link among the client identifiers into a control group; obtaining test behavior data of each client identifier in the test group after browsing the target display link, and control behavior data of each client identifier in the control group after browsing the other display links; generating display effect data of the target display link according to the test behavior data and the control behavior data; and sending the display effect data to the display link-affiliated client, so that the display link-affiliated client displays the display effect data.

9. An electronic device, characterized in that: include: processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the data processing method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the data processing method according to any one of claims 1 to 6.

Images