Advertisement bidding method and device, electronic equipment and storage medium

Abstract

The invention provides an advertisement bidding method and device, electronic equipment and a storage medium, and relates to the technical field of advertisements, and the method comprises the steps: receiving an advertisement space bidding request from a media server; wherein the advertisement space bidding request comprises a user identifier of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement space corresponding to the advertisement space bidding request; obtaining user portrait data of the user according to the user identifier; inputting the user portrait data into a user value evaluation model, and obtaining a value score of the user for the to-be-delivered advertisement output by the user value evaluation model; under the condition that the value score is greater than a set value score threshold value, calculating an advertisement bid of the to-be-put advertisement according to the value score, the page information and the condition reference information; and sending the advertisement bid to a media server to instruct the media server to determine the advertisement of the target advertisement position according to the advertisement bid. The bidding advertisement putting accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of advertising technology, and in particular to an advertising bidding method and device, an electronic device and a storage medium. Background Art

[0002] Bidding advertising is an advertisement that obtains the opportunity to be displayed on the media platform through bidding competition. Advertising bidding strategy refers to the reasonable bidding strategy formulated in the process of placing bidding advertising, so that the media platform can determine whether to place the advertisement based on the bid obtained by the advertising bidding strategy, maximize the advertising effect, and improve the efficiency and cost of advertising. At present, the importance of advertising bidding strategy for enterprises to attract potential customers and enhance brand awareness is gradually increasing.

[0003] In actual situations, when bidding ads are placed based on an advertising bidding strategy, there is often a problem of uneven distribution of advertising resources, resulting in low accuracy in advertising placement. Summary of the invention

[0004] The present invention provides an advertisement bidding method and device, an electronic device and a storage medium, which are used to solve the defect of low accuracy in bidding advertisement delivery in the prior art and achieve the purpose of improving the accuracy of bidding advertisement delivery.

[0005] The present invention provides an advertisement bidding method, comprising the following steps.

[0006] Receive an ad space bidding request from a media server; wherein the ad space bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target ad space corresponding to the ad space bidding request; obtain user portrait data of the user according to the user ID; input the user portrait data into a user value evaluation model to obtain a user value score for the ad to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculate an ad bid for the ad to be placed according to the value score, page information and condition reference information; send the ad bid to the media server to instruct the media server to determine the ad to be placed in the target ad space according to the ad bid.

[0007] According to an advertising bidding method provided by the present invention, after inputting user portrait data into a user value evaluation model and obtaining the user's value score for the advertisement to be placed output by the user value evaluation model, the method further includes: when the value score is less than or equal to a value score threshold, stopping participating in the bidding for the target advertising position.

[0008] According to an advertising bidding method provided by the present invention, when the value score is greater than a set value score threshold, before calculating the advertising bid of the advertisement to be placed according to the value score, page information and condition reference information, the method further includes: when the value score is in a first value score interval, obtaining a first product of the value score and a first coefficient, and updating the value score to the first product; when the value score is in a second value score interval, obtaining a second product of the value score and a second coefficient, and updating the value score to the second product; wherein all value scores in the first value score interval are greater than all value scores in the second value score interval, the first coefficient is greater than 1, and the second coefficient is less than 1.

[0009] According to an advertising bidding method provided by the present invention, an advertising bid for an advertisement to be placed is calculated based on a value score, page information and condition reference information, including: inputting the page information and condition reference information into a user relevance evaluation model to obtain a relevance score between the user and the advertisement to be placed output by the user relevance evaluation model; inputting the value score and the relevance score into an advertising bid evaluation model to obtain an advertising bid output by the advertising bid evaluation model.

[0010] According to an advertising bidding method provided by the present invention, after sending an advertising bid to a media server to instruct the media server to determine the advertisement to be placed in a target advertising position based on the advertising bid, the method further includes: receiving tracking information of the target advertising position fed back by the media server; wherein the tracking information includes: click-through rate, conversion rate, user dwell time and purchase behavior information; and adjusting model parameters of a user value evaluation model, a user relevance evaluation model and an advertising bid evaluation model based on the tracking information.

[0011] According to an advertising bidding method provided by the present invention, before calculating the advertising bid of the advertisement to be placed based on the value score, page information and condition reference information, it also includes: obtaining market decision information, enterprise decision information, and decision information of the same industry in which the advertisement to be placed is located; adjusting the model parameters of the target model based on the market decision information, enterprise decision information and decision information of the same industry; wherein the target model includes at least one of the following: a user value evaluation model, a user relevance evaluation model and an advertising bid evaluation model.

[0012] The present invention also provides an advertisement bidding device, comprising the following modules: a receiving module, a first obtaining module, a second obtaining module, a processing module and a sending module.

[0013] The receiving module is used to receive an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement corresponding to the advertisement bidding request.

[0014] The first acquisition module is used to acquire user portrait data of the user according to the user identifier.

[0015] The second acquisition module is used to input the user portrait data into the user value evaluation model to obtain the user's value score for the advertisement to be placed output by the user value evaluation model.

[0016] The processing module is used to calculate the advertisement bid of the advertisement to be placed according to the value score, page information and condition reference information when the value score is greater than a set value score threshold.

[0017] The sending module is used to send the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement position according to the advertisement bid.

[0018] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the above-mentioned advertising bidding methods is implemented.

[0019] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any one of the above-mentioned advertising bidding methods is implemented.

[0020] The present invention also provides a computer program product, including a computer program, which implements any of the above-mentioned advertising bidding methods when executed by a processor.

[0021] The advertisement bidding method and device, electronic device and storage medium provided by the present invention receive an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user identification of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement corresponding to the advertisement bidding request; obtain user portrait data of the user according to the user identification; input the user portrait data into a user value evaluation model to obtain the user value score for the advertisement to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculate the advertisement bid of the advertisement to be placed according to the value score, page information and condition reference information; and send the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement according to the advertisement bid. The present invention can evaluate user value based on user portrait data, obtain the user's value score for the advertisement to be placed, and calculate the advertisement bid of the advertisement to be placed based on the value score, page information and condition reference information. Based on the above process, the present invention can fully tap the individual differences of users, calculate the advertisement bid based on the user's specific behavior patterns and personalized needs, and solve the defect of low accuracy of bidding advertisement placement in the prior art, thereby achieving the purpose of improving the accuracy of bidding advertisement placement. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is one of the flow charts of the advertisement bidding method provided by the present invention.

[0024] Figure 2 This is the second flow chart of the advertisement bidding method provided by the present invention.

[0025] Figure 3 It is a structural schematic diagram of the advertisement bidding device provided by the present invention.

[0026] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] In the related technologies, current advertising bidding strategies are often limited by extensive algorithms and fixed rules, and fail to fully tap into individual differences among users. This one-size-fits-all approach ignores the specific behavior patterns and personalized needs of users, resulting in uneven distribution of advertising resources, affecting the optimization of advertising effects, and making the accuracy of bidding advertising delivery low.

[0029] In order to solve the above problems, an embodiment of the present invention provides an advertisement bidding method to effectively improve the accuracy of bidding advertisement delivery.

[0030] Combine the following Figure 1-Figure 2 The advertisement bidding method of the present invention is described.

[0031] Figure 1 It is one of the flow charts of the advertising bidding method provided by the present invention, such as Figure 1 As shown, the method includes the following S110~S150.

[0032] S110: receiving an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement corresponding to the advertisement bidding request.

[0033] The user identification of a user is information that can uniquely identify the user, such as a user identity document (ID).

[0034] The page information of the current page browsed by the user may include, for example, the page content of the current page, such as keywords in the text content of the current page, image features in the image content, and other information.

[0035] The conditional reference information of the target advertising space corresponding to the advertising space bidding request may include, for example, at least one of the following: user device usage data (such as the device type, the operating system of the device, etc.), user network access type (such as WIFI or traffic), user location information (such as the user's (Internet Protocol, IP) Internet Protocol address location, user's positioning area, etc.) and other user-related information.

[0036] The media server is the server of the media platform. The media platform is a platform with advertising slots for advertisers to place advertisements.

[0037] In a specific implementation, the condition reference information comes from a media server, and the condition reference information carried in the advertising space bidding requests of different media servers may be the same or different.

[0038] The ad slot bidding request is used to invite advertisers to bid for the ad slot on the current page.

[0039] S120: Obtain user portrait data of the user according to the user identifier.

[0040] User portrait data can be obtained in the following ways.

[0041] First, data of multiple dimensions of the user may be acquired in advance; the multiple dimensions include: basic information dimension, behavior dimension, interest preference dimension, and device usage dimension.

[0042] For example, data based on the information dimension may include: age, gender, geographic location, and other information that can describe the individual user and his or her environment; information based on the behavior dimension may include: online shopping records, online browsing records, search history information, social interaction information, and other related information on the user's behavior in response to information on the media platform; information based on the interest and preference dimension may include: music, movies, reading categories, and other information related to the user's interests or preferences; the device usage dimension may include: device type, device operating system, and other device-related information.

[0043] After obtaining the user's data in multiple dimensions, the data in the above multiple dimensions can be cleaned and preprocessed to eliminate redundant information and erroneous information to ensure the accuracy of the data. After that, the preprocessed data in multiple dimensions can be subjected to correlation analysis based on a preset algorithm, and the user portrait data can be determined based on the results of the correlation analysis.

[0044] The above-mentioned preset algorithm may be, for example, an algorithm that can analyze the correlation between data, such as cluster analysis, association rule learning, and deep neural network algorithm. The correlation between data of multiple dimensions can be obtained through the preset algorithm, thereby obtaining user portrait data containing data of multiple dimensions and correlation information between data of multiple dimensions.

[0045] After establishing the user portrait data of the user, a user ID is set for each user, and a corresponding relationship is established between the user ID of each user and the user portrait data of the user. After obtaining the user ID of the user, the user portrait data of the user can be obtained based on the user ID and the above corresponding relationship.

[0046] S130: Input the user portrait data into the user value evaluation model, and obtain the user's value rating for the advertisement to be placed output by the user value evaluation model.

[0047] The user value evaluation model is a model obtained by pre-training the initial value evaluation model based on multiple sample user portrait data.

[0048] The initial value assessment model can be, for example, a logistic regression model based on a logistic regression algorithm, a random forest model based on a random forest algorithm, or a deep learning model based on a deep learning algorithm.

[0049] The user's value rating for the advertisement to be placed is: the rating obtained based on the evaluation result after the user evaluates the value of the advertisement to be placed. The higher the rating, the higher the value the user places on the advertisement; the lower the rating, the lower the value the user places on the advertisement.

[0050] The evaluation factors may include: the matching degree between the user and the advertisement to be delivered in each dimension of the above-mentioned multiple dimensions. The higher the matching degree, the higher the value score; the lower the matching degree, the lower the value score.

[0051] In a specific implementation, after the user portrait data is input into the user value evaluation model, the user value evaluation model can predict the user's behavior based on the user portrait data. The prediction results may include, for example, the probability of the user purchasing the product to be advertised and the user's total life cycle value (LTV) of the product to be advertised.

[0052] In some embodiments, the user portrait data may also include data of the credit dimension, such as whether the user is a brushing user, whether the user has brushed orders, whether the user has been blacklisted by a merchant or enterprise, the user's credit score in various media platforms, etc. When training the initial value assessment model, it is set that when the user credit represented by the data related to the user's credit is low, for example, the user is a brushing user, the user has brushed orders, the user is blacklisted by a merchant or enterprise, the user's credit score in various media platforms is low, etc., the output value score is lower. In this case, when the user credit represented by the data of the credit dimension in the user portrait data is low, the user's value score for the advertisement to be placed is lower, so that users with low credit can be excluded in the subsequent process (corresponding to S140), thereby filtering out users with higher risks and lower value to merchants or enterprises.

[0053] S140: When the value score is greater than a set value score threshold, the advertisement bid of the advertisement to be placed is calculated according to the value score, the page information and the condition reference information.

[0054] The value scoring threshold may be set by those skilled in the art according to actual conditions, and the embodiment of the present invention does not limit this.

[0055] When the value score is greater than the set value score threshold, it means that the user has a high value for the advertisement to be placed, and the advertisement bid of the advertisement to be placed can be calculated based on the value score, page information and condition reference information.

[0056] In some embodiments, when calculating an advertising bid, page information and condition reference information can be input into a user relevance evaluation model to obtain a relevance score between the user and the advertisement to be placed output by the user relevance evaluation model; then the value score and relevance score can be input into an advertising bid evaluation model to obtain an advertising bid output by the advertising bid evaluation model.

[0057] The user relevance evaluation model can calculate the first relevance between the page information and the advertising content of the advertisement to be placed, and calculate the second relevance between the conditional reference information and the advertising content of the advertisement to be placed, and then perform weighted fusion processing on the first relevance and the second relevance based on the preset first weighting coefficient and the second weighting coefficient respectively to obtain a relevance score.

[0058] The above-mentioned weighted fusion processing of the first correlation and the second correlation is performed on the first weighting coefficient and the second weighting coefficient respectively based on the preset first weighting coefficient, and obtaining the correlation score can be specifically: obtaining the product of the first weighting coefficient and the first correlation as the first weighted result, and obtaining the product of the second weighting coefficient and the second correlation as the second weighted result, summing the first weighted result and the second weighted result to obtain a first summation result, and determining the first summation result as the correlation score.

[0059] Inputting the value score and the relevance score into the advertising bid evaluation model, and obtaining the advertising bid output by the advertising bid evaluation model can specifically be: obtaining the product of the third weighting coefficient and the value score as the third weighted result, and obtaining the product of the fourth weighting coefficient and the relevance score as the fourth weighted result, summing the third weighted result and the fourth weighted result to obtain a second summation result, determining the second summation result as the advertising bid coefficient, inputting the advertising bid coefficient into a preset advertising bid calculation function, and determining the calculation result of the advertising bid calculation function as the advertising bid.

[0060] If the value score is less than or equal to the value score threshold, stop participating in the bidding for the target ad space. If the value score is less than or equal to the value score threshold, it means that the user's value of the ad to be placed is low or has a high risk, then stop participating in the bidding for the target ad space, that is, end this process to reduce the risk of ad placement.

[0061] In some embodiments, before executing S140, different value score intervals may be set so as to perform weighted processing on the value scores of users falling into different value score intervals, so as to increase the value scores of users with higher value scores and further reduce the value scores of users with lower value scores.

[0062] Specifically, a first value score interval and a second value score interval can be set. When the value score is in the first value score interval, a first product of the value score and the first coefficient is obtained, and the value score is updated to the first product; when the value score is in the second value score interval, a second product of the value score and the second coefficient is obtained, and the value score is updated to the second product; wherein all value scores in the first value score interval are greater than all value scores in the second value score interval, the first coefficient is greater than 1, and the second coefficient is less than 1.

[0063] The specific numerical values ​​of the first value scoring interval and the second value scoring interval can be set by those skilled in the art according to actual conditions, and the embodiment of the present invention is not limited to this.

[0064] It is understandable that, in a specific implementation, the number of value scoring intervals may include but is not limited to 2, 3, 4, etc., and may be specifically set by skilled technicians according to actual conditions.

[0065] In some embodiments, before executing S140, in order to combine the actual market situation, market decision information, enterprise decision information, and decision information of the same industry in which the advertisement is to be placed can also be obtained; then, according to the market decision information, enterprise decision information and decision information of the same industry, the model parameters of the target model are adjusted; wherein the target model includes at least one of the following: a user value evaluation model, a user relevance evaluation model and an advertising bid evaluation model.

[0066] Market decision information can be, for example, information related to market decisions obtained from news content released by various media platforms, such as information about bank interest rate cuts and regulation of a certain industry, etc. Enterprise decision information refers to decision information made within the enterprise, such as information about the important development of a module field of the enterprise and enterprise structural adjustment, etc.; decision information of the same industry in which the advertisement is to be placed refers to decision information released by other enterprises in the same industry in which the advertisement is to be placed, etc. In specific implementation, the industry trends and fluctuations of various indicators in the industry environment can be analyzed based on the above information to adjust the model parameters of the target model accordingly. So that when calculating the advertising bid, the current market conditions can be combined to calculate the advertising bid that best meets the current conditions.

[0067] S150: Send the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement position according to the advertisement bid.

[0068] Send the advertising bid to the media server. On the media server side, after the media server receives the advertising bid for the advertisement to be placed, it will also receive the advertising bids given by other advertisers for the target advertisement space based on the advertising space bidding request it received. The media server will select the highest advertising bid among all the advertising bids and place the advertisement corresponding to the advertising bid. In this case, if the advertising bid for the advertisement to be placed calculated in this application is the highest advertising bid among all the advertising bids (bids for the target advertisement space) received by the media server, the media server will place the above-mentioned advertisement to be placed.

[0069] The present application can complete the calculation of the advertising bid for the advertisement to be placed within milliseconds (e.g., 10 milliseconds) upon receiving an advertising space bidding request from a media server, and send the calculated advertising bid to the media server for the media server to make a decision, thereby increasing the probability of the advertisement being displayed to the user at the best time, and ensuring that the current advertising bid can bring the maximum profit to the enterprise.

[0070] In some embodiments, in order to make the advertising bidding method in the present application sustainable and highly adaptable, after executing S150, as shown in FIG. Figure 2 As shown, the embodiment of the present invention can also perform the following S210~S220.

[0071] S210: Receive tracking information of the target advertisement position fed back by the media server; wherein the tracking information includes: click rate, conversion rate, user stay time and purchase behavior information.

[0072] The click-through rate is the ratio of the number of users who clicked on the target ad slot to the number of users who browsed the target ad slot. The conversion rate can be the ratio of the number of users who completed the conversion to the number of ad clicks. The user stay time can be the time the target ad slot stays on the browsing page. The purchase behavior information can be, for example, whether the behavior of purchasing the product corresponding to the advertisement of the target ad slot occurs, the number of times the behavior occurs, and other related information.

[0073] It will be understood that the above only illustrates several common tracking information. In specific implementations, the tracking information includes but is not limited to the click-through rate, conversion rate, user dwell time, and purchase behavior information listed above. Any relevant information generated after the advertisement is placed in the target ad space can be used as tracking information for the target ad space.

[0074] S220: Adjust model parameters of the user value evaluation model, the user relevance evaluation model, and the advertisement bid evaluation model according to the tracking information.

[0075] According to the tracking information, the model parameters of the user value evaluation model, the user relevance evaluation model and the advertising bid evaluation model are adjusted to further improve the accuracy of the output results of each model.

[0076] Through continuous iteration of model parameters, it is possible to accurately identify user portrait data related to high conversion rates, advertising elements that attract target users, and information such as the time period and platform that are most suitable for advertising. Based on these analyses, the weight of user portrait data (such as the third weighting coefficient mentioned above) can be dynamically adjusted to optimize the advertising bid evaluation model. New model parameters (such as parameters related to factors such as advertising elements and advertising positioning) can also be added to the user value evaluation model, the user relevance evaluation model, and the advertising bid evaluation model to further improve the accuracy of advertising bids.

[0077] The advertisement bidding method provided by the present invention receives an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement corresponding to the advertisement bidding request; obtains user portrait data of the user according to the user ID; inputs the user portrait data into a user value evaluation model, obtains the user's value score for the advertisement to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculates the advertisement bid of the advertisement to be placed according to the value score, page information and condition reference information; sends the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement according to the advertisement bid. The present invention can evaluate the user value based on the user portrait data, obtain the user's value score for the advertisement to be placed, and calculate the advertisement bid of the advertisement to be placed based on the value score, page information and condition reference information. Based on the above process, the present invention can fully tap the individual differences of users, calculate the advertisement bid based on the specific behavior patterns and personalized needs of users, solve the defect of low accuracy of the bidding advertisement placement in the prior art, and achieve the purpose of improving the accuracy of the bidding advertisement placement.

[0078] The advertisement bidding device provided by the present invention is described below. The advertisement bidding device described below and the advertisement bidding method described above can be referenced to each other.

[0079] Figure 3 Schematic diagram of the structure of the advertising bidding device provided by the present invention. Figure 3 As shown, the advertisement bidding device 300 includes: a receiving module 301 , a first obtaining module 302 , a second obtaining module 303 , a processing module 304 and a sending module 305 .

[0080] The receiving module 301 is used to receive an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user ID of a user, page information of a current page browsed by the user, and conditional reference information of a target advertisement corresponding to the advertisement bidding request.

[0081] The first acquisition module 302 is used to acquire user portrait data of the user according to the user identifier.

[0082] The second acquisition module 303 is used to input the user portrait data into the user value evaluation model, and obtain the user's value score for the advertisement to be placed output by the user value evaluation model.

[0083] The processing module 304 is used to calculate the advertisement bid of the advertisement to be placed by the advertiser according to the value score, the page information and the condition reference information when the value score is greater than the set value score threshold.

[0084] The sending module 305 is used to send the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement position according to the advertisement bid.

[0085] The advertisement bidding method provided by the present invention receives an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement corresponding to the advertisement bidding request; obtains user portrait data of the user according to the user ID; inputs the user portrait data into a user value evaluation model, obtains the user's value score for the advertisement to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculates the advertisement bid of the advertisement to be placed according to the value score, page information and condition reference information; sends the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement according to the advertisement bid. The present invention can evaluate the user value based on the user portrait data, obtain the user's value score for the advertisement to be placed, and calculate the advertisement bid of the advertisement to be placed based on the value score, page information and condition reference information. Based on the above process, the present invention can fully tap the individual differences of users, calculate the advertisement bid based on the specific behavior patterns and personalized needs of users, solve the defect of low accuracy of the bidding advertisement placement in the prior art, and achieve the purpose of improving the accuracy of the bidding advertisement placement.

[0086] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 complete mutual communication through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the advertising bidding method, which includes: receiving an advertising space bidding request from a media server; wherein the advertising space bidding request includes: a user identification of a user, page information of a current page browsed by a user, and condition reference information of a target advertising space corresponding to the advertising space bidding request; obtaining user portrait data of the user according to the user identification; inputting the user portrait data into a user value evaluation model to obtain the user's value score for the advertisement to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculating the advertisement bid of the advertisement to be placed according to the value score, page information and condition reference information; and sending the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertising space according to the advertisement bid.

[0087] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0088] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the advertising bidding method provided by the above-mentioned methods, which method includes: receiving an advertising space bidding request from a media server; wherein the advertising space bidding request includes: a user identifier of a user, page information of a current page browsed by a user, and conditional reference information of a target advertising space corresponding to the advertising space bidding request; obtaining user portrait data of the user according to the user identifier; inputting the user portrait data into a user value evaluation model to obtain a value score of the user for the advertisement to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculating the advertising bid of the advertisement to be placed according to the value score, page information and conditional reference information; and sending the advertising bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertising space according to the advertising bid.

[0089] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the advertising bidding method provided by the above-mentioned methods, the method comprising: receiving an advertising space bidding request from a media server; wherein the advertising space bidding request comprises: a user identifier of a user, page information of a current page browsed by a user, and conditional reference information of a target advertising space corresponding to the advertising space bidding request; obtaining user portrait data of the user according to the user identifier; inputting the user portrait data into a user value evaluation model to obtain a value score of the user for the advertisement to be placed output by the user value evaluation model; when the value score is greater than a set value score threshold, calculating an advertisement bid for the advertisement to be placed according to the value score, page information and conditional reference information; and sending the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertising space according to the advertisement bid.

[0090] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0091] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An advertisement bidding method, characterized in that: include: Receiving an advertisement space bidding request from a media server; wherein the advertisement space bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement space corresponding to the advertisement space bidding request; According to the user identifier, obtaining user portrait data of the user; Inputting the user portrait data into a user value evaluation model, and obtaining the user's value rating for the advertisement to be placed output by the user value evaluation model; When the value score is greater than a set value score threshold, calculating the advertisement bid of the advertisement to be placed according to the value score, the page information and the condition reference information; The advertisement bid is sent to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement position according to the advertisement bid.

2. The advertisement bidding method according to claim 1, characterized in that: After inputting the user portrait data into a user value evaluation model and obtaining the user's value rating of the advertisement to be placed output by the user value evaluation model, the method further includes: When the value score is less than or equal to the value score threshold, stop participating in the bidding for the target advertising space.

3. The advertisement bidding method according to claim 1, characterized in that: In the case where the value score is greater than a set value score threshold, before calculating the advertisement bid of the advertisement to be placed according to the value score, the page information and the condition reference information, the method further includes: When the value score is within a first value score interval, obtaining a first product of the value score and a first coefficient, and updating the value score to the first product; When the value score is within the second value score interval, obtaining a second product of the value score and a second coefficient, and updating the value score to the second product; Among them, all value scores in the first value score interval are greater than all value scores in the second value score interval, the first coefficient is greater than 1, and the second coefficient is less than 1.

4. The advertisement bidding method according to claim 1, characterized in that: The calculating the advertisement bid of the advertisement to be placed according to the value score, the page information and the condition reference information includes: Inputting the page information and the condition reference information into a user relevance evaluation model, and obtaining a relevance score between the user and the advertisement to be placed output by the user relevance evaluation model; The value score and the relevance score are input into an advertisement bid evaluation model to obtain the advertisement bid output by the advertisement bid evaluation model.

5. The advertisement bidding method according to claim 4, characterized in that: After sending the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement position according to the advertisement bid, the method further includes: Receive tracking information of the target advertising position fed back by the media server; wherein the tracking information includes: click rate, conversion rate, user stay time and purchase behavior information; According to the tracking information, model parameters of the user value evaluation model, the user relevance evaluation model and the advertisement bid evaluation model are adjusted.

6. The advertisement bidding method according to claim 4, characterized in that: Before calculating the advertisement bid of the advertisement to be placed according to the value score, the page information and the condition reference information, the method further includes: Obtaining market decision information, enterprise decision information, and decision information of the same industry in which the advertisement to be placed is located; According to the market decision information, the enterprise decision information and the same industry decision information, the model parameters of the target model are adjusted; wherein the target model includes at least one of the following: The user value evaluation model, the user relevance evaluation model and the advertisement bid evaluation model.

7. An advertising bidding device, characterized in that: include: A receiving module, configured to receive an advertisement bidding request from a media server; wherein the advertisement bidding request includes: a user ID of a user, page information of a current page browsed by the user, and condition reference information of a target advertisement corresponding to the advertisement bidding request; A first acquisition module, used to acquire user portrait data of the user according to the user identifier; The second acquisition module is used to input the user portrait data into a user value evaluation model to obtain the user's value score for the advertisement output by the user value evaluation model; A processing module, configured to calculate the advertisement bid of the advertisement to be placed according to the value score, the page information and the condition reference information when the value score is greater than a set value score threshold; The sending module is used to send the advertisement bid to the media server to instruct the media server to determine the advertisement to be placed in the target advertisement position according to the advertisement bid.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the advertising bidding method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the advertising bidding method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the advertising bidding method according to any one of claims 1 to 6 is implemented.

Images