Data processing method and device, electronic equipment and storage medium

Abstract

The invention relates to a data processing method and device, electronic equipment and a storage medium, and the data processing method comprises the steps: obtaining first putting accumulated data corresponding to first user equipment, and the first putting accumulated data is determined according to resources accumulated by first type information put to the first user equipment; determining whether the first release accumulated data reaches a first preset threshold value or not; if the first release accumulated data reaches a first preset threshold value, performing channel attribution on the first user equipment; and if the channel attribution is successful, generating return data for channel return based on the user related information of the first user corresponding to the first user equipment and the release related information of the first type of information. According to the embodiment of the invention, the type and quantity of the returned data can be enriched, user groups which are sensitive to prices but willing to watch advertisements are prevented from being filtered out, the diversity of the returned data is improved, and the finally determined user related information of the first user and the release related information can be more accurate.

Description

Technical Field

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

[0002] The Internet industry has already passed the rough development model of seeking big and more. Most apps have reached the deep end. How to refine the product more finely and transform from the previous daily active user (DAU) target to average revenue per user (ARPU) is the core of most development.

[0003] Based on this, the retention target assessment of performance advertising can no longer meet the needs of advertisers. For the video industry, membership income is currently commonly used as an assessment indicator for whether performance advertising has met the target.

[0004] However, when the user-related information of the member user and the advertising placement information of the performance advertisement delivered to the member user are transmitted to the media delivery model as training samples, the media delivery model cannot accurately predict the advertising position with good delivery effect for the performance advertisement to be predicted, and cannot obtain a good prediction effect. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a data processing method, device, electronic device and storage medium.

[0006] In a first aspect, the present application provides a data processing method, comprising:

[0007] Acquire first delivery accumulated data corresponding to the first user equipment, where the first delivery accumulated data is determined according to accumulated resources of the first type of information delivered to the first user equipment;

[0008] Determining whether the first delivery accumulated data reaches a first preset threshold;

[0009] If the first delivery cumulative data reaches a first preset threshold, performing channel attribution on the first user device;

[0010] If the channel attribution is successful, feedback data is generated based on the user-related information of the first user corresponding to the first user device and the delivery-related information of the first type of information for channel feedback.

[0011] Optionally, performing channel attribution on the first user device includes:

[0012] Acquire a delivery channel corresponding to the first preset threshold;

[0013] Obtaining an information delivery record of delivering the second type of information to multiple second user devices through the delivery channel;

[0014] Channel attribution is performed on the first user device based on the information delivery record.

[0015] Optionally, performing channel attribution on the first user device based on the information delivery record includes:

[0016] determining whether the first user equipment is the same as any of the second user equipments;

[0017] If the first user device is the same as any of the second user devices, determining that the first user corresponding to the first user device is converted through the delivery channel, and determining that the channel attribution is successful;

[0018] If the first user device is different from all the second user devices, it is determined that channel attribution fails.

[0019] Optionally, the method further comprises:

[0020] If the channel attribution fails, continue to deliver the first type of information to the first user device;

[0021] Obtaining second delivery cumulative data corresponding to the first user device;

[0022] Determining whether the delivery cumulative data reaches a second preset threshold;

[0023] If the accumulated delivery data reaches a second preset threshold, a step of performing channel attribution on the first user device is executed.

[0024] Optionally, generating the returned data based on the user-related information of the first user corresponding to the first user device and the delivery-related information of the first type of information includes:

[0025] Determine a second user in the information delivery record that meets the preset resource consumption condition;

[0026] The returned data is generated based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user.

[0027] Optionally, generating the returned data based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user includes:

[0028] Acquire a first weight coefficient corresponding to the first user and a second weight coefficient corresponding to the second user, wherein the second weight coefficient is greater than the first weight coefficient;

[0029] Generate a first sample based on the user-related information of the first user and the delivery-related information of the first type of information, and generate a second sample based on the user-related information of the second user;

[0030] The quantity of the first sample and the second sample is adjusted according to the first weight coefficient and the second weight coefficient to obtain the returned data.

[0031] Optionally, the method for determining the first delivery accumulated data includes:

[0032] Acquire the amount of first type of information delivered to the first user equipment;

[0033] Obtaining the unit resource corresponding to each first type of information;

[0034] The product of the unit resource and the quantity is determined as the first delivery cumulative data.

[0035] In a second aspect, the present application provides a data processing device, comprising:

[0036] A data acquisition module, configured to acquire first delivery accumulated data corresponding to a first user device, wherein the first delivery accumulated data is determined according to accumulated resources of first type information delivered to the first user device;

[0037] A threshold determination module, used to determine whether the first delivery cumulative data reaches a first preset threshold;

[0038] A channel attribution module, configured to perform channel attribution on the first user device if the first delivery cumulative data reaches a first preset threshold;

[0039] The data generation module is used to generate feedback data for channel feedback based on user-related information of the first user corresponding to the first user device and delivery-related information of the first type of information if channel attribution is successful.

[0040] Optionally, the channel attribution module includes:

[0041] A first acquisition unit, configured to acquire a delivery channel corresponding to the first preset threshold;

[0042] A second acquisition unit, configured to acquire an information delivery record of delivering second type information to multiple second user devices through the delivery channel;

[0043] A channel attribution unit is used to perform channel attribution on the first user device based on the information delivery record.

[0044] Optionally, the channel attribution unit is further used to:

[0045] determining whether the first user equipment is the same as any of the second user equipments;

[0046] If the first user device is the same as any of the second user devices, determining that the first user corresponding to the first user device is converted through the delivery channel, and determining that the channel attribution is successful;

[0047] If the first user device is different from all the second user devices, it is determined that channel attribution fails.

[0048] Optionally, the device further comprises:

[0049] an information delivery module, which continues to deliver the first type of information to the first user device if channel attribution fails;

[0050] A first acquisition module, used to acquire second delivery cumulative data corresponding to the first user equipment;

[0051] A first determination module, used to determine whether the delivery cumulative data reaches a second preset threshold;

[0052] The execution module is used to perform channel attribution on the first user device if the cumulative delivery data reaches a second preset threshold.

[0053] Optionally, the data generation module includes:

[0054] A first determining unit, used to determine a second user in the information delivery record that meets a preset resource consumption condition;

[0055] A generating unit is used to generate the feedback data based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user.

[0056] Optionally, the generating unit is further used for:

[0057] Acquire a first weight coefficient corresponding to the first user and a second weight coefficient corresponding to the second user, wherein the second weight coefficient is greater than the first weight coefficient;

[0058] Generate a first sample based on the user-related information of the first user and the delivery-related information of the first type of information, and generate a second sample based on the user-related information of the second user;

[0059] The quantity of the first sample and the second sample is adjusted according to the first weight coefficient and the second weight coefficient to obtain the returned data.

[0060] Optionally, the data acquisition module includes:

[0061] A third acquisition unit, configured to acquire the amount of first type information delivered to the first user equipment;

[0062] A fourth acquisition unit, used to acquire a unit resource corresponding to each first type of information;

[0063] The second determining unit is used to determine the product of the unit resource and the quantity as the first delivery cumulative data.

[0064] In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0065] Memory, used to store computer programs;

[0066] The processor is used to implement any data processing method described in the first aspect when executing a program stored in the memory.

[0067] In a fourth aspect, the present application provides a computer-readable storage medium, on which a program of a data processing method is stored. When the program of the data processing method is executed by a processor, the steps of any data processing method described in the first aspect are implemented.

[0068] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0069] The embodiment of the present application achieves targeted screening of users who are price-sensitive (non-paying or underpaying) but willing to spend time watching advertisements by statistically delivering the resources of the first type of information at the device granularity, and comparing the obtained first delivery cumulative data with the first preset threshold. The users who spend time watching advertisements are also equivalent to an invisible payment. When the invisible payment reaches a certain threshold, the first user device can be attributed to the channel. If the attribution is successful, the feedback data for training the media delivery model is generated based on the user-related data of the first user and the delivery-related information, so as to achieve the purpose of enriching the type and quantity of the feedback data, avoid filtering out the user group that is sensitive to prices but willing to watch advertisements, and improve the diversity of the feedback data. Moreover, by comparing the first delivery cumulative data with the first preset threshold, and performing two conditional judgments of channel attribution, the user-related information of the first user and the delivery-related information of the first type of information that are finally determined can be made more accurate, thereby facilitating the use of richer and more accurate training data to train the media delivery model, so that after the media delivery model is trained, it can output accurate recommendation data for the user group that is price-sensitive but willing to watch advertisements. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0071] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0072] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0073] Figure 2 A structural diagram of a data processing device provided in an embodiment of the present application;

[0074] Figure 3 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] 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 making creative work are within the scope of protection of this application.

[0076] Since the user-related information of the member user and the advertising placement information of the performance advertisement placed to the member user are transmitted to the media placement model as training samples, the media placement model cannot accurately predict the advertising position with good placement effect for the performance advertisement to be predicted, and cannot obtain a good prediction effect. To this end, the embodiments of the present application provide a data processing method, device, electronic device and storage medium.

[0077] The present application embodiment provides a data processing method, which can be applied to a server, such as Figure 1 As shown, the data processing method may include the following steps:

[0078] Step S101, obtaining first delivery cumulative data corresponding to a first user device, where the first delivery cumulative data is determined according to accumulated resources of first type information delivered to the first user device;

[0079] In an embodiment of the present application, the first user device may refer to a user device to which the first type of information is delivered, the information may refer to an advertisement, the first type of information may refer to a brand advertisement, and a brand advertisement is an advertisement placed by an advertiser on the website of the first entity (the company). The brand advertisement is used to promote the advertiser's designated products to help the brand attract users to purchase the designated products.

[0080] Since advertisers need to pay certain resources (such as payment) to place advertisements on the first entity, it can be considered that each brand advertisement corresponds to certain resources. Correspondingly, placing advertisements through the first user device will bring certain resources (income). Therefore, the accumulated resources of the first type of information cumulatively placed by the first user device can be counted to obtain the first placement cumulative data.

[0081] In one embodiment of the present application, the method for determining the first delivery cumulative data includes: obtaining the quantity of first type information delivered to the first user device; obtaining the unit resource corresponding to each first type information; and determining the product of the unit resource and the quantity as the first delivery cumulative data.

[0082] The unit resource can be determined by dividing the average of the revenue converted from non-paying (such as non-members, not purchasing other services) or under-paying (paying amount is less than a certain payment threshold) users watching advertisements through multiple distribution channels that have been successfully converted in historical records by the number of first type information delivered to users.

[0083] Since the query rate per second (QPS) of brand advertising is relatively high, this application adopts a cache storage solution (such as Redis, couchbase, etc.) to store the first delivery cumulative data of the first type of information. For example, the key can be used to store the unique identifier of the first type of information, and the value can be used to store the number of times the first type of information is delivered.

[0084] Different advertisers may deliver different first-type information for different products. In order to distinguish different products, the key can also include product information. The expiration time of the key can be used to control the cumulative duration. For example, it can be reset to zero every natural day or every week. The date can be added as a prefix to the key, and the cache time of the key can be set to 24 hours or 168 hours. By controlling the cumulative duration, the problem of excessive cumulative duration occupying too many storage resources can be avoided.

[0085] In this step, for at least one first user device, first delivery accumulated data corresponding to each first user device may be obtained respectively.

[0086] Step S102, determining whether the first delivery cumulative data reaches a first preset threshold;

[0087] In an embodiment of the present application, corresponding preset thresholds can be set in advance for different delivery channels, such as: aa platform corresponds to preset threshold 1, bb platform corresponds to preset threshold 2, and so on, so that when the cumulative delivery data reaches the preset threshold corresponding to the corresponding delivery channel, the user device is attributed to the channel to determine whether the user corresponding to the user device is converted through the delivery channel.

[0088] The setting of the preset thresholds corresponding to different delivery channels can be determined based on the average of the revenue converted from non-paying or under-paying users who watched the advertisements through multiple delivery channels that have been successfully converted in historical records.

[0089] In this step, the minimum preset threshold may be selected as the first threshold, and the first delivery cumulative data may be compared with the first preset threshold. When the first delivery cumulative data is equal to the first preset threshold, it is determined that the first delivery cumulative data reaches the first preset threshold.

[0090] Step S103: if the first delivery cumulative data reaches a first preset threshold, channel attribution is performed on the first user device;

[0091] When the accumulated data of the first delivery reaches the first preset threshold, channel attribution can be attempted, that is, determining through which channel the first user corresponding to the first user device was converted. If the attributed channel is a channel corresponding to the preset threshold, it can be determined that the channel attribution is successful.

[0092] Step S104: if the channel attribution is successful, feedback data is generated based on the user-related information of the first user corresponding to the first user device and the delivery-related information of the first type of information for channel feedback.

[0093] In the embodiment of the present application, user-related information may refer to information related to the first user, such as: region, gender, age group, preferred content, etc., and delivery-related information may refer to delivery information related to the first type of information, such as: advertising identifier, main object contained in the first type of information (such as advertising object), advertising position, delivery time, consumption capacity of the consumer group corresponding to the main object, etc.

[0094] After determining that the channel attribution is successful, it indicates that the first user converted by the delivery channel corresponding to the first preset threshold can bring certain benefits, which can be transmitted back to the corresponding delivery channel, so that after the media delivery model of the delivery channel is trained based on the returned data, the subsequent first type of information to be delivered can be delivered to users similar to the user-related information in a delivery method similar to the delivery-related information, in order to enable these similar users to generate similar benefits by viewing the delivered first type of information, as the first user corresponding to the first user device.

[0095] Therefore, user-related information of the first user corresponding to the first user device and delivery-related information of the first type of information can be obtained, feedback data can be generated based on the user-related information and delivery-related information, and fed back to the attributed channel for use in the media delivery model training of the channel.

[0096] The embodiment of the present application achieves targeted screening of users who are price-sensitive (non-paying or underpaying) but willing to spend time watching advertisements by statistically delivering the resources of the first type of information at the device granularity, and comparing the obtained first delivery cumulative data with the first preset threshold. The users who spend time watching advertisements are also equivalent to an invisible payment. When the invisible payment reaches a certain threshold, the first user device can be attributed to the channel. If the attribution is successful, the feedback data for training the media delivery model is generated based on the user-related data of the first user and the delivery-related information, so as to achieve the purpose of enriching the type and quantity of the feedback data, avoid filtering out the user group that is sensitive to prices but willing to watch advertisements, and improve the diversity of the feedback data. Moreover, by comparing the first delivery cumulative data with the first preset threshold, and performing two conditional judgments of channel attribution, the user-related information of the first user and the delivery-related information of the first type of information that are finally determined can be made more accurate, thereby facilitating the use of richer and more accurate training data to train the media delivery model, so that after the media delivery model is trained, it can output accurate recommendation data for the user group that is price-sensitive but willing to watch advertisements.

[0097] In another embodiment of the present application, step S103 performs channel attribution on the first user device, including:

[0098] Step S201, obtaining a delivery channel corresponding to the first preset threshold;

[0099] Step S202, obtaining an information delivery record of delivering the second type of information to multiple second user devices through the delivery channel;

[0100] In an embodiment of the present application, the second type of information may refer to performance advertising, which refers to advertisements placed by the first entity (the company) on other media channels (such as aa short video platform, bb video platform, etc.). Performance advertising can be used to promote information about the first entity, such as news about the first entity, new dramas of the first entity, etc., to help the first entity attract more new users, activate old users, etc.

[0101] Step S203: performing channel attribution on the first user device based on the information delivery record.

[0102] In this step, the information delivery record and the user device information of the first user device may be input into the channel attribution model so that the channel attribution model outputs an attribution result.

[0103] In one embodiment of the present application, whether the first user device is the same as any of the second user devices can be determined through an attribution model or not through an attribution model; if the first user device is the same as any of the second user devices, it is determined that the first user corresponding to the first user device is converted through the delivery channel, and the channel attribution is determined to be successful; if the first user device is different from all of the second user devices, it is determined that the channel attribution has failed.

[0104] The embodiment of the present application can determine whether the first user device is converted from the second type of information delivered to the delivery channel corresponding to the first preset threshold by performing channel attribution on the first user device. If so, it can be considered that the information (i.e., advertisement) of the delivery channel is successfully converted and feedback data can be generated.

[0105] In another embodiment of the present application, after step S103, the method further includes:

[0106] Step S301: If channel attribution fails, continue to deliver the first type of information to the first user device;

[0107] If channel attribution fails, it indicates that the first user may not be converted through the delivery channel corresponding to the first preset threshold, and a second preset threshold corresponding to other delivery channels can be obtained, and the second preset threshold is greater than the first preset threshold.

[0108] Step S302, obtaining second delivery cumulative data corresponding to the first user device;

[0109] After continuing to deliver the first type of information to the first user equipment, the first user equipment continues to accumulate all resources corresponding to the first type of information to obtain second delivery accumulated data.

[0110] Step S303, determining whether the cumulative delivery data reaches a second preset threshold;

[0111] The cumulative data of the investment is compared with the second preset threshold. For example, if the cumulative data of the investment is 0.3 yuan and the second preset threshold is 0.3 yuan, the cumulative data of the investment reaches the second preset threshold.

[0112] Step S304: if the cumulative delivery data reaches a second preset threshold, a step of performing channel attribution on the first user device is performed.

[0113] If the cumulative delivery data reaches the second preset threshold, it indicates that the first user may be converted through the delivery channel corresponding to the second preset threshold. For further verification, the step of channel attribution for the first user device can be executed. If the attribution is successful, it is determined that the first user is converted through the delivery channel corresponding to the second preset threshold, and feedback data can be generated.

[0114] In actual applications, multiple preset thresholds can be set according to the number of delivery channels. When the cumulative delivery data still cannot reach the second preset threshold, the third preset threshold, the fourth preset threshold, etc. can continue to be obtained. The principle is similar to that of this embodiment and will not be repeated here.

[0115] The embodiment of the present application can automatically obtain preset thresholds corresponding to other delivery channels when the attribution of the first user to the delivery channel corresponding to the first preset threshold fails, so as to ultimately determine the conversion channel of the first user and further facilitate the generation of feedback data.

[0116] In another embodiment of the present application, after step S103, the method further includes:

[0117] If channel attribution is successful, continue to deliver the first type of information to the first user device, and obtain the second delivery cumulative data corresponding to the first user device; determine whether the delivery cumulative data reaches the second preset threshold; if the delivery cumulative data reaches the second preset threshold, execute the step of channel attribution for the first user device.

[0118] If the channel attribution is successful, it indicates that the first user is converted through the delivery channel corresponding to the first preset threshold. In actual applications, there may be a situation where the first user is converted from at least two delivery channels. Therefore, even if the channel attribution is successful, the second preset threshold corresponding to other delivery channels can still be obtained. The second preset threshold is greater than the first preset threshold. After continuing to deliver the first type of information to the first user device, the first user device continues to accumulate all resources corresponding to the first type of information to obtain the second delivery cumulative data. The delivery cumulative data is compared with the second preset threshold. For example, if the delivery cumulative data is 0.3 yuan and the second preset threshold is 0.3 yuan, the delivery cumulative data reaches the second preset threshold. If the delivery cumulative data reaches the second preset threshold, it indicates that the first user may also be converted through the delivery channel corresponding to the second preset threshold. For further verification, the step of channel attribution for the first user device can be performed. If the attribution is successful, it is determined that the first user is converted through the delivery channel corresponding to the second preset threshold, and feedback data can be generated.

[0119] The embodiment of the present application can automatically obtain the preset thresholds corresponding to other delivery channels when the first user is successfully attributed to the delivery channel corresponding to the first preset threshold. When it is determined that the first user can be successfully attributed to other delivery channels, at least two conversion channels of the first user can be finally determined, thereby facilitating the generation of richer feedback data.

[0120] In another embodiment of the present application, step S104 generates feedback data based on user-related information of the first user corresponding to the first user device and delivery-related information of the first type of information, including:

[0121] Step S401, determining a second user in the information delivery record that meets a preset resource consumption condition;

[0122] In the embodiment of the present application, the second user who meets the preset resource consumption condition in the information delivery record may refer to a paying user.

[0123] Step S402 : generating the returned data based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user.

[0124] In this step, user-related information of the first user and delivery-related information of the first type of information can be returned at the same time as user-related information of the second user is returned; user-related information of the first user and delivery-related information of the first type of information that the advertiser needs second most can be returned at the same time as user-related information of the second user that the advertiser needs second most can be returned.

[0125] In one embodiment of the present application, the feedback data is generated based on user-related information of the first user, delivery-related information of the first type of information, and user-related information of the second user, including: obtaining a first weight coefficient corresponding to the first user and a second weight coefficient corresponding to the second user, the second weight coefficient being greater than the first weight coefficient; generating a first sample based on user-related information of the first user and delivery-related information of the first type of information, and generating a second sample based on user-related information of the second user; adjusting the quantity of the first sample and the second sample based on the first weight coefficient and the second weight coefficient to obtain the feedback data.

[0126] The implementation method of the present application can adjust the ratio of the two parts of information through the first weight coefficient and the second weight coefficient. The second weight coefficient is greater than the first weight coefficient so that the second user who actually pays occupies an absolute position in the entire returned data. Because advertisers relatively prefer paying users, more paying users are used when the media model is learned.

[0127] In another embodiment of the present application, a data processing device is also provided, such as Figure 2 As shown, including:

[0128] A data acquisition module 11 is used to acquire first delivery cumulative data corresponding to a first user device, where the first delivery cumulative data is determined according to accumulated resources of first type information delivered to the first user device;

[0129] A threshold determination module 12 is used to determine whether the first delivery cumulative data reaches a first preset threshold;

[0130] A channel attribution module 13, configured to perform channel attribution on the first user device if the first delivery cumulative data reaches a first preset threshold;

[0131] The data generation module 14 is used to generate feedback data for channel feedback based on user-related information of the first user corresponding to the first user device and delivery-related information of the first type of information if channel attribution is successful.

[0132] Optionally, the channel attribution module includes:

[0133] A first acquisition unit, configured to acquire a delivery channel corresponding to the first preset threshold;

[0134] A second acquisition unit, configured to acquire an information delivery record of delivering second type information to multiple second user devices through the delivery channel;

[0135] A channel attribution unit is used to perform channel attribution on the first user device based on the information delivery record.

[0136] Optionally, the channel attribution unit is further used to:

[0137] determining whether the first user equipment is the same as any of the second user equipments;

[0138] If the first user device is the same as any of the second user devices, determining that the first user corresponding to the first user device is converted through the delivery channel, and determining that the channel attribution is successful;

[0139] If the first user device is different from all the second user devices, it is determined that channel attribution fails.

[0140] Optionally, the device further comprises:

[0141] an information delivery module, which continues to deliver the first type of information to the first user device if channel attribution fails;

[0142] A first acquisition module, used to acquire second delivery cumulative data corresponding to the first user equipment;

[0143] A first determination module, used to determine whether the delivery cumulative data reaches a second preset threshold;

[0144] The execution module is used to perform channel attribution on the first user device if the cumulative delivery data reaches a second preset threshold.

[0145] Optionally, the data generation module includes:

[0146] A first determining unit, used to determine a second user in the information delivery record that meets a preset resource consumption condition;

[0147] A generating unit is used to generate the feedback data based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user.

[0148] Optionally, the generating unit is further used for:

[0149] Acquire a first weight coefficient corresponding to the first user and a second weight coefficient corresponding to the second user, wherein the second weight coefficient is greater than the first weight coefficient;

[0150] Generate a first sample based on the user-related information of the first user and the delivery-related information of the first type of information, and generate a second sample based on the user-related information of the second user;

[0151] The quantity of the first sample and the second sample is adjusted according to the first weight coefficient and the second weight coefficient to obtain the returned data.

[0152] Optionally, the data acquisition module includes:

[0153] A third acquisition unit, configured to acquire the amount of first type information delivered to the first user equipment;

[0154] A fourth acquisition unit, used to acquire a unit resource corresponding to each first type of information;

[0155] The second determining unit is used to determine the product of the unit resource and the quantity as the first delivery cumulative data.

[0156] In another embodiment of the present application, an electronic device is provided, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus;

[0157] Memory, used to store computer programs;

[0158] The processor is used to implement the data processing method described in any of the above method embodiments when executing the program stored in the memory.

[0159] In the electronic device provided by the embodiment of the present invention, the processor implements the resource of delivering the first type of information by executing the program stored in the memory, and compares the obtained first delivery cumulative data with the first preset threshold value, so as to screen out users who are price sensitive (non-paying or underpaying) but willing to spend time watching advertisements in a targeted manner. The time spent by these users watching advertisements is also equivalent to a kind of invisible payment. When the invisible payment reaches a certain threshold, the first user device can be channel attributed. If the attribution is successful, the feedback data for training the media delivery model is generated based on the user-related data and delivery-related information of the first user, so as to achieve the purpose of enriching the type and quantity of the feedback data, avoid filtering out the user group that is more sensitive to price but willing to watch advertisements, and improve the diversity of the feedback data. Moreover, by comparing the first delivery cumulative data with the first preset threshold value, and performing two conditional judgments of channel attribution, the user-related information of the first user and the delivery-related information of the first type of information that are finally determined can be made more accurate, so as to facilitate the use of richer and more accurate training data to train the media delivery model, so that after the media delivery model is trained, it can output accurate recommendation data for the user group that is more sensitive to price but willing to watch advertisements.

[0160] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0161] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0162] The memory 1130 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0163] The above-mentioned processor 1110 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0164] In another embodiment of the present application, a computer-readable storage medium is provided, on which a program of a data processing method is stored. When the program of the data processing method is executed by a processor, the steps of the data processing method described in any of the aforementioned method embodiments are implemented.

[0165] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0166] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A data processing method, characterized in that: include: Acquire first delivery cumulative data corresponding to the first user equipment, where the first delivery cumulative data is determined according to accumulated resources of the first type of information delivered to the first user equipment; Determining whether the first delivery accumulated data reaches a first preset threshold; If the first delivery cumulative data reaches a first preset threshold, performing channel attribution on the first user device; If the channel attribution is successful, feedback data is generated based on the user-related information of the first user corresponding to the first user device and the delivery-related information of the first type of information for channel feedback.

2. The data processing method according to claim 1, characterized in that: Performing channel attribution on the first user device includes: Acquire a delivery channel corresponding to the first preset threshold; Obtaining an information delivery record of delivering the second type of information to multiple second user devices through the delivery channel; Channel attribution is performed on the first user device based on the information delivery record.

3. The data processing method according to claim 2, characterized in that: Performing channel attribution on the first user device based on the information delivery record includes: determining whether the first user equipment is the same as any of the second user equipments; If the first user device is the same as any of the second user devices, determining that the first user corresponding to the first user device is converted through the delivery channel, and determining that the channel attribution is successful; If the first user device is different from all the second user devices, it is determined that channel attribution fails.

4. The data processing method according to claim 1, characterized in that: The method further comprises: If the channel attribution fails, continue to deliver the first type of information to the first user device; Obtaining second delivery cumulative data corresponding to the first user device; Determining whether the delivery cumulative data reaches a second preset threshold; If the accumulated delivery data reaches a second preset threshold, a step of performing channel attribution on the first user device is executed.

5. The data processing method according to claim 1, characterized in that: Generating return data based on user-related information of the first user corresponding to the first user device and delivery-related information of the first type of information includes: Determine a second user in the information delivery record that meets the preset resource consumption condition; The returned data is generated based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user.

6. The data processing method according to claim 5, characterized in that: Generating the returned data based on the user-related information of the first user, the delivery-related information of the first type of information, and the user-related information of the second user includes: Acquire a first weight coefficient corresponding to the first user and a second weight coefficient corresponding to the second user, wherein the second weight coefficient is greater than the first weight coefficient; Generate a first sample based on the user-related information of the first user and the delivery-related information of the first type of information, and generate a second sample based on the user-related information of the second user; The quantity of the first sample and the second sample is adjusted according to the first weight coefficient and the second weight coefficient to obtain the returned data.

7. The data processing method according to claim 1, characterized in that: The method for determining the first delivery cumulative data includes: Acquire the amount of first type of information delivered to the first user equipment; Obtaining the unit resource corresponding to each first type of information; The product of the unit resource and the quantity is determined as the first delivery cumulative data.

8. A data processing device, characterized in that: include: A data acquisition module, configured to acquire first delivery accumulated data corresponding to a first user device, wherein the first delivery accumulated data is determined according to accumulated resources of first type information delivered to the first user device; A threshold determination module, used to determine whether the first delivery cumulative data reaches a first preset threshold; A channel attribution module, configured to perform channel attribution on the first user device if the first delivery cumulative data reaches a first preset threshold; The data generation module is used to generate feedback data for channel feedback based on user-related information of the first user corresponding to the first user device and delivery-related information of the first type of information if channel attribution is successful.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the data processing method according to any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program of a data processing method, and when the program of the data processing method is executed by a processor, the steps of the data processing method described in any one of claims 1 to 7 are implemented.

Images