Message pushing, display method and device, electronic equipment and computer storage medium

Abstract

The application provides a message pushing method, device, apparatus, electronic device and computer storage medium. In the message pushing method, based on a first preset parameter, a to-be-pushed message and target user characteristics of a target user, target signal strength information of the to-be-pushed message relative to the target user is calculated. At the same time, based on a second preset parameter, the to-be-pushed message and the target user characteristics of the target user, target noise strength information of the to-be-pushed message relative to the target user is calculated. After the target signal strength information and the target noise strength information are obtained, the target signal-to-noise ratio of the to-be-pushed message relative to the target user can be more accurately calculated. Therefore, when the target signal-to-noise ratio meets a preset signal-to-noise ratio condition, the to-be-pushed message is pushed to the target user. Thus, the message pushed to the target user is more matched with the target user, and the use experience of the target application program is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to message push methods, message display methods, message push devices, message display devices, electronic devices, and computer storage media. Background Technology

[0002] In existing push notification mechanisms, messages are typically pushed uniformly to the user's terminal device. However, since different users have different information needs, if the pushed content does not effectively match the user's needs, it will not only reduce the efficiency of information delivery and consume network transmission resources, but may also affect the user's experience of using the application.

[0003] Therefore, how to improve the matching degree between push messages and user needs has become a technical problem that urgently needs to be solved in the current technology field. Summary of the Invention

[0004] This application provides a message push method to push messages that are highly relevant to user needs. This application also provides a message display method, a message push device, a message display device, an electronic device, and a computer storage medium.

[0005] This application provides a message push method applied to a server, the method comprising: Identify the messages to be pushed and the target users; Based on the first preset parameters, the message to be pushed and the target user characteristics of the target user, the target signal strength information of the message to be pushed relative to the target user is calculated; Based on the second preset parameter, the message to be pushed and the target user characteristics of the target user, the target noise intensity information of the message to be pushed relative to the target user is calculated; The target signal-to-noise ratio of the message to be pushed relative to the target user is calculated using the target signal strength information and the target noise strength information. If the target signal-to-noise ratio meets the preset signal-to-noise ratio condition, then it is determined that the message to be pushed will be pushed to the target user; The message to be pushed is provided as a target message to the client used by the target user, so as to display a reminder message associated with the target message in the client. In response to detecting a trigger operation by the target user on the reminder message, the target message is displayed in the target application.

[0006] Optionally, the first preset parameter includes at least one of the following: a value parameter representing the value of the message, a demand matching parameter representing the degree of matching between the message and the user's needs, and a timeliness parameter representing the timeliness of the message. The step of calculating the target signal strength information of the message to be pushed relative to the target user based on the first preset parameter, the message to be pushed, and the target user characteristics of the target user includes: Based on the message to be pushed and the characteristics of the target user, the score of the message to be pushed for the value parameter, the score of the message to be pushed relative to the target user for the demand matching parameter, and the score of the message to be pushed for the timeliness parameter are determined. The target signal strength information of the message to be pushed relative to the target user is obtained by multiplying the score of the message to be pushed for the value parameter, the score of the message to be pushed relative to the target user for the demand matching parameter, and the score of the message to be pushed for the timeliness parameter.

[0007] Optionally, the second preset parameter includes at least one of the following: a redundancy parameter for indicating the degree of redundancy in the message content, an interference parameter for indicating the degree of interference in the message content, and an information saturation parameter for indicating the degree of saturation of the message relative to the user's information reception. The step of calculating the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed, and the target user characteristics of the target user includes: Based on the message to be pushed and the characteristics of the target user, the scores of the message to be pushed for the redundancy parameter, the scores of the message to be pushed for the interference parameter, and the scores of the message to be pushed relative to the target user for the information saturation parameter are determined. The target noise intensity information of the message to be pushed relative to the target user is obtained by multiplying the score of the message to be pushed for the redundancy parameter, the score of the message to be pushed for the interference parameter, and the score of the message to be pushed relative to the target user for the information saturation parameter.

[0008] Optionally, calculating the target signal strength information of the message to be pushed relative to the target user based on the first preset parameters, the message to be pushed, and the target user characteristics of the target user includes: The message to be pushed, the target user characteristics, and the first score prediction strategy are used as input information for a preset score evaluation model to obtain the score of the message to be pushed relative to the target user for the first preset parameter. Based on the score of the message to be pushed relative to the target user for the first preset parameter, the target signal strength information is obtained; The step of calculating the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed, and the target user characteristics of the target user includes: The message to be pushed, the target user characteristics, and the second score prediction strategy are used as input information for the preset score evaluation model to obtain the score of the message to be pushed relative to the target user for the second preset parameter. The target noise intensity information is obtained based on the score of the message to be pushed relative to the target user for the second preset parameter.

[0009] Optionally, calculating the target signal-to-noise ratio of the message to be pushed relative to the target user using the target signal strength information and the target noise strength information includes: An initial ratio is obtained by dividing the target signal strength information by the target noise strength information; The initial ratio is divided into a common logarithm and multiplied by 10 to obtain the target signal-to-noise ratio.

[0010] Optional, also includes: Determine the first preset parameter and the second preset parameter; Determine the first initial weight corresponding to each first sub-parameter in the first preset parameters and the second initial weight corresponding to each second sub-parameter in the second preset parameters; Based on the first sub-parameter, the first initial weight, the second sub-parameter, and the second initial weight, an initial signal-to-noise ratio (SNR) prediction model is constructed to calculate the SNR of a message relative to a user. Obtain the message sample to be processed, the user feature sample, and the signal-to-noise ratio sample corresponding to the message sample to be processed; The initial signal-to-noise ratio (SNR) prediction model is trained using the message sample to be processed, the user feature sample, and the SNR sample to obtain the target SNR prediction model.

[0011] Optionally, training the initial signal-to-noise ratio (SNR) prediction model using the message sample to be processed, the user feature sample, and the SNR sample to obtain the target SNR prediction model includes: The message sample to be processed, the user feature sample, the first score prediction strategy, and the second score prediction strategy are used as input information for a preset score evaluation model to obtain the signal-to-noise ratio reference value of the message sample to be processed relative to the sample user. Based on the deviation between the signal-to-noise ratio reference value and the signal-to-noise ratio sample, the first initial weight and the second initial weight are adjusted, and the adjusted first weight corresponding to each first sub-parameter and the adjusted second weight corresponding to each second sub-parameter are determined. Based on the first sub-parameter, the adjusted first weight, the second sub-parameter, and the adjusted second weight, a target signal-to-noise ratio prediction model is obtained.

[0012] This application provides a message display method, applied to a client used by a target user, the method comprising: The system obtains a target message provided by the server, wherein the target message is a message to be pushed whose target signal-to-noise ratio (SNR) meets a preset SNR condition. The server is configured to: determine the message to be pushed and the target user; calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target noise intensity information of the message to be pushed relative to the target user based on a second preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target SNR of the message to be pushed relative to the target user using the target signal strength information and the target noise intensity information; and if the target SNR meets the preset SNR condition, determine to push the message to the target user. Display a notification message associated with the target message.

[0013] This application provides a message push device applied to a server, the device comprising: The unit for determining the message to be pushed and the target user is used to determine the message to be pushed and the target user. The target signal strength information calculation unit is used to calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed and the target user characteristics of the target user; The target noise intensity information calculation unit is used to calculate the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed and the target user characteristics of the target user; A target signal-to-noise ratio calculation unit is used to calculate the target signal-to-noise ratio of the message to be pushed relative to the target user using the target signal strength information and the target noise strength information; The push unit is configured to determine to push the message to be pushed to the target user if the target signal-to-noise ratio meets a preset signal-to-noise ratio condition. A providing unit is configured to provide the message to be pushed as a target message to the client used by the target user, so as to display a reminder message associated with the target message in the client, and to display the target message in the target application in response to detecting a trigger operation of the target user on the reminder message.

[0014] This application provides a message display device, applied to a client used by a target user, the device comprising: A target message acquisition unit is used to acquire a target message provided by a server, wherein the target message is a message to be pushed whose target signal-to-noise ratio (SNR) meets a preset SNR condition. The server is used to determine the message to be pushed and the target user; calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target noise intensity information of the message to be pushed relative to the target user based on a second preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target SNR of the message to be pushed relative to the target user using the target signal strength information and the target noise intensity information; and if the target SNR meets the preset SNR condition, determine to push the message to the target user. The reminder information display unit is used to display reminder information associated with the target message.

[0015] This application provides an electronic device, including: a processor; and a memory for storing a computer program, which is executed by the processor to perform the above-described message push method and message display method.

[0016] This application provides a computer storage medium storing a computer program, which is executed by a processor to perform the aforementioned message push method and message display method.

[0017] Compared with the prior art, the embodiments of this application have the following advantages: This application discloses a message push method, in which: a message to be pushed and a target user are determined; based on a first preset parameter, the message to be pushed, and the target user characteristics of the target user, target signal strength information of the message to be pushed relative to the target user is calculated; based on a second preset parameter, the message to be pushed, and the target user characteristics of the target user, target noise intensity information of the message to be pushed relative to the target user is calculated; a target signal-to-noise ratio (SNR) of the message to be pushed relative to the target user is calculated using the target signal strength information and the target noise intensity information; if the target SNR meets a preset SNR condition, the message to be pushed is determined to be pushed to the target user; the message to be pushed is provided as a target message to the client used by the target user to display a reminder message associated with the target message in the client; and in response to detecting a trigger operation by the target user on the reminder message, the target message is displayed in the target application. In this method, the target signal strength information of the message to be pushed relative to the target user is calculated based on the first preset parameters, the message to be pushed, and the target user characteristics of the target user. At the same time, the target noise intensity information of the message to be pushed relative to the target user is calculated based on the second preset parameters, the message to be pushed, and the target user characteristics of the target user. After obtaining the target signal strength information and the target noise intensity information, the target signal-to-noise ratio of the message to be pushed relative to the target user can be calculated more accurately. Thus, when the target signal-to-noise ratio meets the preset signal-to-noise ratio condition, the message to be pushed is pushed to the target user, thereby making the message pushed to the target user more matched with the target user and improving the user experience of the target application. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0019] Figure 1 A flowchart of the message push method provided in the first embodiment of this application.

[0020] Figure 2 This is a schematic diagram of a scenario for the message push method provided in the first embodiment of this application.

[0021] Figure 3 A flowchart of the message display method provided in the second embodiment of this application.

[0022] Figure 4 A schematic diagram of a message push device provided in the third embodiment of this application.

[0023] Figure 5 A schematic diagram of a message display device provided in the fourth embodiment of this application.

[0024] Figure 6 A schematic diagram of an electronic device provided in the fifth embodiment of this application. Detailed Implementation

[0025] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific implementations disclosed below.

[0026] This application provides a message push method, a message display method, a message push device, a message display device, an electronic device, and a computer storage medium. The following specific embodiments describe the message push method, message display method, message push device, message display device, electronic device, and computer storage medium. To more clearly demonstrate the message push method provided by the embodiments of this application, the application scenarios of the message push method provided by the embodiments of this application are first introduced.

[0027] The message push method of this application can be used in scenarios where messages are pushed to users, aiming to make the pushed messages more relevant to user needs, facilitate users to view the pushed messages in the target application, and improve the user experience of the target application.

[0028] Specifically, for example, when there are messages to be pushed, it is necessary to determine whether to push the messages to the target user; the messages to be pushed can be one message or multiple messages; if the matching degree between the messages to be pushed and the target user's needs is high, then the messages to be pushed can be pushed to the target user. In this application, the target signal-to-noise ratio of the messages to be pushed relative to the target user is used to characterize the matching degree between the messages to be pushed and the target user, that is, the higher the target signal-to-noise ratio, the higher the matching degree between the messages to be pushed and the target user.

[0029] Signal-to-noise ratio (SNR) is an important parameter for measuring signal quality. It represents the ratio of the intensity of the useful signal to the intensity of the background noise, and can be expressed as SNR. The SNR can be calculated using the following formula: in, Indicates the signal-to-noise ratio. Indicates the strength of the useful signal. This indicates the intensity of background noise.

[0030] Specifically in the field of push notifications Obtained using the first preset parameters. The second preset parameter is used to obtain the result. There can be multiple first preset parameters, and the result is obtained by multiplying multiple first preset parameters. The number of second preset parameters can be multiple, and the result is obtained by multiplying multiple second preset parameters. The multiple first preset parameters include at least one of the following: a value parameter representing the value of the message, a demand matching parameter representing the degree of matching between the message and the user's needs, and a timeliness parameter representing the timeliness of the message; the multiple second preset parameters include at least one of the following: a redundancy parameter representing the degree of redundant information contained in the message content, an interference parameter representing the degree of interference information contained in the message content, and an information saturation parameter representing the degree of information saturation of the message relative to the user's information reception saturation.

[0031] In practice, for a specific message to be pushed and a target user, the score of each of the multiple first preset parameters can be calculated, as can the score of each of the multiple second preset parameters. Then, the score of each of the multiple first preset parameters can be multiplied together to obtain the desired result. The value is obtained by multiplying the scores of each of the multiple second preset parameters. The value of is then used to calculate the target signal-to-noise ratio using the formula above.

[0032] When calculating the target signal-to-noise ratio of a message to be pushed relative to a target user, the message to be pushed, the characteristics of the target user, and the score prediction strategy can all be input into a preset score evaluation model. This yields the score for each of the multiple first preset parameters and the score for each of the multiple second preset parameters. The preset score evaluation model can then assign scores based on the score prediction strategy.

[0033] Specifically, each first preset parameter can be quantified by multiple first sub-parameters, and the preset score evaluation model can score based on the multiple first sub-parameters to obtain the score of the first preset parameter. Similarly, each second preset parameter can be quantified by multiple second sub-parameters, and the preset score evaluation model can score based on the multiple second sub-parameters to obtain the score of the second preset parameter.

[0034] The score prediction strategy includes a first scoring strategy that scores each first preset parameter and a second scoring strategy that scores each second preset parameter. The first scoring strategy includes strategies for scoring value parameters, demand matching parameters, and timeliness parameters. The second scoring strategy includes strategies for scoring redundancy information parameters, interference information parameters, and information saturation parameters.

[0035] For the three signal parameters—value parameter, demand matching parameter, and timeliness parameter—they can be obtained by weighted summation of each sub-indicator and its corresponding weight, based on the overall quality of the message, the degree of matching with user needs, and the timeliness. The scoring strategy for each parameter can be set as follows: Value parameters: These comprehensively consider credibility, randomness, and content value. Credibility is scored based on the reliability of the source or data support (e.g., low 1 point, medium 2 points, high 3 points); randomness is scored based on the frequency of the event; and content value is scored based on content attributes such as usability. Demand matching parameters: These comprehensively consider interactive behavior (e.g., click-through rate) and intent matching (e.g., search match rate) for scoring. Timeliness parameters: These comprehensively consider the message's timestamp information and its relevance to current trending topics for scoring.

[0036] For the three noise parameters of redundancy, interference, and information saturation, they can be obtained by weighted summation of each sub-indicator and its corresponding weight, based on the degree of redundancy of the message content (such as content compactness), the proportion of promotional content (such as the proportion of external jump elements), and the degree of user saturation in receiving information (such as the activity of interactive feedback).

[0037] The above description illustrates one application scenario of the message push method of this application. The embodiments of this application do not specifically limit the application scenario of the message push method. The above application scenario is merely one embodiment of the message push method provided in this application. The purpose of providing this application scenario embodiment is to facilitate understanding of the message push method provided in this application, and not to limit the message push method provided in this application. Other application scenarios of the message push method in the embodiments of this application will not be elaborated upon one by one.

[0038] First Embodiment This embodiment provides a message push method, and the execution entity of this embodiment is the server. Please refer to [link / reference] for details. Figure 1 This is a flowchart of the message push method provided in the first embodiment of this application. For some examples and detailed descriptions of this embodiment, please refer to the above scenario embodiment.

[0039] The message push method of this application includes the following steps.

[0040] Step S101: Determine the message to be pushed and the target user.

[0041] The message push method in this embodiment determines whether to push the message to the target user based on the target signal-to-noise ratio of the message to be pushed relative to the target user. Therefore, it is necessary to pre-determine the message to be pushed and the target user. The message to be pushed can be one or more messages, and the target user can be a group of users.

[0042] Step S102: Based on the first preset parameters, the message to be pushed and the target user characteristics of the target user, calculate the target signal strength information of the message to be pushed relative to the target user.

[0043] In this embodiment, the signal-to-noise ratio (SNR) is mainly used to characterize the matching degree between the message to be pushed and the target user. Therefore, it is necessary to calculate the target SNR of the message to be pushed relative to the target user. Before calculating the target SNR, it is necessary to calculate the target signal strength information and target noise strength information used to calculate the target SNR.

[0044] In this embodiment, the first preset parameter includes at least one of the following parameters: a value parameter representing the value of the message, a demand matching parameter representing the degree of matching between the message and the user's needs, and a timeliness parameter representing the timeliness of the message. As a method for calculating the target signal strength information of the message to be pushed relative to the target user based on the first preset parameter, the message to be pushed, and the target user's characteristics, it can be as follows: First, based on the message to be pushed and the target user's characteristics, determine the score of the message to be pushed for the value parameter, the score of the message to be pushed relative to the target user for the demand matching parameter, and the score of the message to be pushed for the timeliness parameter; then, multiply the scores of the message to be pushed for the value parameter, the score of the message to be pushed relative to the target user for the demand matching parameter, and the score of the message to be pushed for the timeliness parameter to obtain the target signal strength information of the message to be pushed relative to the target user.

[0045] In this embodiment, based on the first preset parameter, the message to be pushed, and the target user characteristics of the target user, the target signal strength information of the message to be pushed relative to the target user is calculated. Specifically, this can mean: using the message to be pushed, the target user characteristics, and the first score prediction strategy as input information to the preset score evaluation model to obtain the score of the message to be pushed relative to the target user with respect to the first preset parameter; and obtaining the target signal strength information based on the score of the message to be pushed relative to the target user with respect to the first preset parameter.

[0046] The first score prediction strategy can be the first scoring strategy mentioned in the above scenario embodiment, such as a scoring strategy for value parameters, a scoring strategy for demand matching parameters, a scoring strategy for timeliness parameters, etc.

[0047] In this embodiment, the value parameter, demand matching parameter, and timeliness parameter are obtained in the following ways.

[0048] Value parameters: These comprehensively consider credibility, randomness, and content value. The credibility parameter is scored based on the reliability of the source or data support (e.g., low 1 point, medium 2 points, high 3 points); the randomness parameter is scored based on the frequency of the event; and the content value parameter is scored based on content attributes such as usability. The credibility, randomness, and content value parameters are weighted and summed to obtain the value parameter. For example, when the weights of the credibility, randomness, and content value parameters are respectively... w 1. w 2. w 3, then the value parameter = w 1 Credibility parameter + w 2 Occasional parameters + w 3 Content value parameters w 1. w 2. w The sum of 3 can be 1.

[0049] Demand matching parameters: The criteria are graded and scored by comprehensively considering indicators such as interactive behavior (e.g., click-through rate) and intent matching (e.g., search matching degree).

[0050] Timeliness parameter: The message is graded and scored by comprehensively considering the timestamp information of the message and its relevance to the current hot news.

[0051] Step S103: Based on the second preset parameters, the message to be pushed and the target user characteristics of the target user, calculate the target noise intensity information of the message to be pushed relative to the target user.

[0052] In this embodiment, the second preset parameter includes at least one of the following parameters: a redundancy parameter indicating the degree of redundancy in the message content, an interference parameter indicating the degree of interference in the message content, and an information saturation parameter indicating the degree of information saturation of the message relative to the user's information reception. As one implementation method for calculating the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed, and the target user's characteristics, it can be as follows: First, based on the message to be pushed and the target user's characteristics, determine the score of the message to be pushed for the redundancy parameter, the score of the message to be pushed for the interference parameter, and the score of the message to be pushed relative to the target user for the information saturation parameter; then, multiply the scores of the message to be pushed for the redundancy parameter, the score of the message to be pushed for the interference parameter, and the score of the message to be pushed relative to the target user for the information saturation parameter to obtain the target noise intensity information of the message to be pushed relative to the target user.

[0053] Specifically, calculating the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameters, the message to be pushed, and the target user's target user characteristics can refer to: using the message to be pushed, the target user characteristics, and the second score prediction strategy as input information to the preset score evaluation model to obtain the score of the message to be pushed relative to the target user for each of the second preset parameters; and obtaining the target noise intensity information based on the score of the message to be pushed relative to the target user for each of the second preset parameters.

[0054] The second score prediction strategy can be the second scoring strategy mentioned in the above scenario embodiment, such as a scoring strategy for redundant information parameters, a scoring strategy for interference information parameters, and a scoring strategy for information saturation parameters.

[0055] For the three noise parameters of redundancy, interference, and information saturation, they can be obtained by weighted summation of each sub-indicator and its corresponding weight, based on the degree of redundancy of the message content (such as content compactness), the proportion of promotional content (such as the proportion of external jump elements), and the degree of user saturation in receiving information (such as the activity of interactive feedback).

[0056] Step S104: Calculate the target signal-to-noise ratio of the message to be pushed relative to the target user using the target signal strength information and the target noise strength information.

[0057] After obtaining the target signal strength information and the target noise strength information, the target signal-to-noise ratio (SNR) of the message to be pushed relative to the target user is calculated using these two information. Specifically, calculating the target SNR of the message to be pushed relative to the target user using the target signal strength information and the target noise strength information can refer to: quotienting the target signal strength information and the target noise strength information to obtain an initial ratio; taking the common logarithm of the initial ratio and multiplying it by ten to obtain the target SNR. The initial ratio can refer to the ratio between the target signal strength information and the target noise strength information.

[0058] In fact, in this embodiment, a target signal-to-noise ratio (SNR) prediction model for calculating the SNR can be constructed based on the first preset parameters and the second preset parameters, and the target SNR prediction model is used in subsequent processes to obtain the target SNR of the message to be pushed relative to the target user.

[0059] Specifically, in constructing the target signal-to-noise ratio (SNR) prediction model, firstly, the first preset parameters and the second preset parameters are determined; simultaneously, the first initial weights corresponding to each first sub-parameter in the first preset parameters and the second initial weights corresponding to each second sub-parameter in the second preset parameters are determined; then, based on the first sub-parameters, the first initial weights, the second sub-parameters, and the second initial weights, an initial SNR prediction model for calculating the SNR of a message relative to a user is constructed; the message sample to be processed, the user feature sample, and the SNR sample corresponding to the message sample to be processed are obtained; the initial SNR prediction model is trained using the message sample to be processed, the user feature sample, and the SNR sample to obtain the target SNR prediction model.

[0060] Specifically, the initial signal-to-noise ratio (SNR) prediction model is trained using the message sample to be processed, user feature sample, and SNR sample to obtain the target SNR prediction model. This includes: using the message sample to be processed, user feature sample, first score prediction strategy, and second score prediction strategy as input information to the preset score evaluation model to obtain the SNR reference value of the message sample to be processed relative to the sample user; adjusting the first initial weight and the second initial weight based on the deviation between the SNR reference value and the SNR sample, and determining the adjusted first weight corresponding to each first sub-parameter and the adjusted second weight corresponding to each second sub-parameter; and obtaining the target SNR prediction model based on the first sub-parameter, the adjusted first weight, the second sub-parameter, and the adjusted second weight.

[0061] Based on the first sub-parameter, the adjusted first weight, the second sub-parameter, and the adjusted second weight, the target signal-to-noise ratio (SNR) prediction model is obtained. In fact, the first sub-parameter and the adjusted first weight are weighted and summed to obtain the score of each first preset parameter. Then, the scores of each first preset parameter are multiplied to obtain the first product (i.e., target signal strength information). Similarly, the second sub-parameter and the adjusted second weight are weighted and summed to obtain the score of each second preset parameter. Then, the scores of each second preset parameter are multiplied to obtain the second product (i.e., target noise intensity information). The above SNR formula is then used as the target SNR prediction model.

[0062] To facilitate understanding of the various first sub-parameters in the first preset parameter, please refer to the following example. For instance, when the first preset parameter is a value parameter, the corresponding first sub-parameters are credibility parameter, randomness parameter, and content value parameter. Therefore, when constructing the initial signal-to-noise ratio prediction model, the following approach is adopted: w 1 Credibility parameter + w 2 Occasional parameters + w 3 Value parameters can be represented in the same way as content value parameters. Similarly, parameters such as demand matching degree, timeliness, redundancy information degree, interference information degree, and information saturation degree can also be represented in a similar way.

[0063] Specifically, to facilitate understanding of the process of obtaining the target signal-to-noise ratio prediction model, please refer to... Figure 2 This is a schematic diagram of a scenario for the message push method provided in the first embodiment of this application. In fact, in Figure 2 In this process, an initial signal-to-noise ratio (SNR) prediction model is constructed using each first sub-parameter, each second sub-parameter, each first initial weight, and each second initial weight. Then, the first initial weight and each second initial weight are adjusted using the message samples to be processed, user feature samples, SNR samples, and SNR reference values ​​obtained from the preset score evaluation model. This process trains the initial SNR prediction model to obtain the target SNR prediction model.

[0064] The message sample to be processed can be a message to be processed by a sample user through annotation (the annotation process can be as follows). Figure 2As shown, the signal-to-noise ratio (SNR) sample can be the SNR of the message sample to be processed, obtained based on the annotation processing results. For example, when there are 200 messages to be processed, namely message 1, message 2, ... message 200, different user groups are used as samples to evaluate and score the 200 messages respectively. The scoring criteria are also based on the scoring strategy described above. Based on the evaluation results, the SNR of the 200 messages can be obtained as the SNR sample; the user feature sample is the feature of the sample user. In order to enrich the dataset during the training process, the message sample to be processed can be a sample with a relatively uniform SNR distribution, such as the messages with high, medium, and low SNRs mentioned above.

[0065] Simultaneously, the message sample to be processed, user feature sample, first score prediction strategy, and second score prediction strategy are used as input information to the preset score evaluation model to obtain the signal-to-noise ratio (SNR) reference value of the message sample to be processed relative to the sample user. In fact, the SNR sample is obtained based on labeled data, while the SNR reference value is calculated using the preset score evaluation model. Then, based on the deviation between the SNR reference value and the SNR sample, the first initial weights and the second initial weights are adjusted, and the preset score evaluation model is used again for re-scoring to update the SNR reference value. This process is repeated until the deviation between the updated SNR reference value and the SNR sample is within a preset range.

[0066] In fact, adjusting the first initial weights and the second initial weights can be done according to... Figure 2 The method used in this study is to verify the consistency between the signal-to-noise ratio (SNR) reference value and the SNR sample. Specifically, the SNR sample calculated using labeled data corresponds to the first ranking of the message samples to be processed, while the SNR reference value calculated using a preset score evaluation model corresponds to the second ranking of the message samples to be processed. Consistency verification is performed based on the first and second rankings. If the first and second rankings meet the consistency conditions, the target SNR prediction model is released. Otherwise, the initial weights of the first and second rankings are adjusted until the deviation between the updated SNR reference value and the SNR sample is within a preset range.

[0067] Step S105: If the target signal-to-noise ratio meets the preset signal-to-noise ratio condition, then determine to push the message to the target user.

[0068] If the target signal-to-noise ratio meets the preset signal-to-noise ratio condition, then the message to be pushed will be sent to the target user.

[0069] Step S106: Provide the message to be pushed as the target message to the client used by the target user, so as to display the reminder information associated with the target message in the client. In response to the detection of the target user's trigger operation on the reminder information, display the target message in the target application.

[0070] For example, the title of the message to be pushed can be displayed as a reminder on the client side. When the target user triggers the reminder, they are directly redirected to the target application page, where the target message is displayed.

[0071] This application provides a message push method. In this method, based on a first preset parameter, the message to be pushed, and the target user characteristics of the target user, the target signal strength information of the message to be pushed relative to the target user is calculated. Simultaneously, based on a second preset parameter, the message to be pushed, and the target user characteristics of the target user, the target noise intensity information of the message to be pushed relative to the target user is calculated. After obtaining the target signal strength information and the target noise intensity information, the target signal-to-noise ratio (SNR) of the message to be pushed relative to the target user can be calculated more accurately. Therefore, when the target SNR meets the preset SNR condition, the message to be pushed is pushed to the target user, making the message pushed to the target user more closely matched to the target user and improving the user experience of the target application.

[0072] Second Embodiment The second embodiment of this application provides a message display method. The executing entity of this embodiment is a client. The parts of the second embodiment that are the same as those in the scenario embodiment and the first embodiment will not be described again; please refer to the relevant parts of the scenario embodiment and the first embodiment for details.

[0073] Please refer to Figure 3 This is a flowchart of the message display method provided in the second embodiment of this application.

[0074] The message display method of this application includes the following steps.

[0075] Step S301: Obtain the target message provided by the server.

[0076] In this embodiment, the target message is a message to be pushed whose target signal-to-noise ratio (SNR) meets a preset SNR condition. The server determines the message to be pushed and the target user. Based on a first preset parameter, the target user characteristics of the message to be pushed and the target user, it calculates the target signal strength information of the message to be pushed relative to the target user. Based on a second preset parameter, the target user characteristics of the message to be pushed and the target user, it calculates the target noise intensity information of the message to be pushed relative to the target user. The target SNR of the message to be pushed relative to the target user is calculated using the target signal strength information and the target noise intensity information. If the target SNR meets the preset SNR condition, it is determined that the message to be pushed will be sent to the target user.

[0077] Step S302: Display the reminder information associated with the target message.

[0078] In this embodiment, it also includes: In response to detecting a trigger action by the target user on the reminder message, display the target message in the target application.

[0079] This application provides a message display method. In this method, a target message provided by a server is obtained, and a reminder message associated with the target message is displayed. In response to a detected trigger operation by a target user on the reminder message, the target message is displayed in the target application. Since the server calculates the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed, and the target user's characteristics, and simultaneously calculates the target noise intensity information of the message to be pushed relative to the target user based on a second preset parameter, the message to be pushed, and the target user's characteristics, after obtaining the target signal strength information and the target noise intensity information, the target signal-to-noise ratio (SNR) of the message to be pushed relative to the target user can be calculated more accurately. Therefore, when the target SNR meets the preset SNR condition, the message to be pushed is sent to the target user, making the message pushed to the target user more closely matched to the target user and improving the user experience of the target application.

[0080] Third Embodiment Corresponding to the message push method provided in the first embodiment of this application, the third embodiment of this application also provides a message push device. Since the device embodiment is basically similar to the first embodiment, the description is relatively simple; relevant details can be found in the description of the first embodiment. The device embodiments described below are merely illustrative.

[0081] Please refer to Figure 4 This is a schematic diagram of the message push device provided in the third embodiment of this application.

[0082] The message push device 400, applied to a server, includes: a message to be pushed and target user determination unit 401, used to determine the message to be pushed and the target user; a target signal strength information calculation unit 402, used to calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the target user characteristics of the message to be pushed and the target user; and a target noise intensity information calculation unit 403, used to calculate the target noise intensity information of the message to be pushed relative to the target user based on a second preset parameter, the target user characteristics of the message to be pushed and the target user; and a target signal-to-noise ratio (SNR) calculation unit. The comparison calculation unit 404 is used to calculate the target signal-to-noise ratio of the message to be pushed relative to the target user using the target signal strength information and the target noise strength information; the push unit 405 is used to determine to push the message to be pushed to the target user if the target signal-to-noise ratio meets a preset signal-to-noise ratio condition; the providing unit 406 is used to provide the message to be pushed as a target message to the client used by the target user, so as to display a reminder message associated with the target message in the client, and in response to detecting the target user's trigger operation on the reminder message, display the target message in the target application.

[0083] Fourth embodiment Corresponding to the message display method provided in the second embodiment of this application, the fourth embodiment of this application also provides a message display device. Since the device embodiment is basically similar to the second embodiment, the description is relatively simple; relevant details can be found in the description of the second embodiment. The device embodiments described below are merely illustrative.

[0084] Please refer to Figure 5 This is a schematic diagram of the message display device provided in the fourth embodiment of this application.

[0085] The message display device 500 is applied to a client used by a target user. The device includes: a target message acquisition unit 501, used to acquire a target message provided by a server, wherein the target message is a message to be pushed whose target signal-to-noise ratio (SNR) meets a preset SNR condition; the server, used to determine the message to be pushed and the target user; calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target noise intensity information of the message to be pushed relative to the target user based on a second preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target SNR of the message to be pushed relative to the target user using the target signal strength information and the target noise intensity information; if the target SNR meets the preset SNR condition, then determine to push the message to the target user; and a reminder information display unit 502, used to display reminder information associated with the target message.

[0086] Fifth Embodiment Corresponding to the methods of the first to second embodiments of this application, the fifth embodiment of this application also provides an electronic device.

[0087] like Figure 6 As shown, Figure 6 A schematic diagram of an electronic device provided in the fifth embodiment of this application.

[0088] In this embodiment, an optional hardware structure of the electronic device 600 may be as follows: Figure 6 As shown, it includes: at least one processor 601, at least one memory 602 and at least one communication bus 605; the memory 602 contains a program 603 and data 604.

[0089] Bus 605 can be a communication device for transmitting data between components within electronic device 600, such as an internal bus (e.g., CPU-memory bus, where the processor is the central processing unit, or CPU for short) or an external bus (e.g., a universal serial bus port or a peripheral component interconnection fast port).

[0090] Additionally, the electronic device also includes at least one network interface 606 and at least one peripheral interface 607. The network interface 606 provides wired or wireless communication with an external network 608 (e.g., the Internet, intranet, local area network, mobile communication network, etc.). In some embodiments, the network interface 606 may include any number of network interface controllers (NICs), radio frequency (RF) modules, repeaters, transceivers, modems, routers, gateways, any combination of wired network adapters, wireless network adapters, Bluetooth adapters, infrared adapters, near field communication (NFC) adapters, cellular network chips, etc.

[0091] Peripheral interface 607 is used to connect to peripherals, such as peripheral 1 in the figure. Figure 6 609 in the middle), peripheral 2 ( Figure 6 (610 in the middle) and peripheral 3 ( Figure 6 (611 in the original text). Peripherals are peripheral devices, which may include, but are not limited to, cursor control devices (such as mice, touchpads, or touchscreens), keyboards, displays (such as cathode ray tube displays, liquid crystal displays), monitors or light-emitting diode displays, video input devices (such as cameras or input interfaces coupled to video files), etc.

[0092] The processor 601 may be a CPU, an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0093] The memory 602 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage device.

[0094] In this embodiment, the processor 601 calls the program and data stored in the memory 602 to execute the methods of the first to second embodiments of this application.

[0095] Sixth Embodiment Corresponding to the methods of the first to second embodiments of this application, the sixth embodiment of this application also provides a computer storage medium storing a computer program that is executed by a processor to perform the methods of the first to second embodiments of this application.

[0096] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

[0097] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, a network interface, and memory. Memory may include non-persistent storage in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0098] 1. Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically-erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in this article, computer-readable media do not include non-transitory computer-readable storage media, such as modulated data signals and carrier waves.

[0099] 2. Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

Claims

1. A message push method, characterized in that, Applied to the server side, the method includes: Identify the messages to be pushed and the target users; Based on the first preset parameters, the message to be pushed and the target user characteristics of the target user, the target signal strength information of the message to be pushed relative to the target user is calculated; Based on the second preset parameter, the message to be pushed and the target user characteristics of the target user, the target noise intensity information of the message to be pushed relative to the target user is calculated; The target signal-to-noise ratio of the message to be pushed relative to the target user is calculated using the target signal strength information and the target noise strength information. If the target signal-to-noise ratio meets the preset signal-to-noise ratio condition, then it is determined that the message to be pushed will be pushed to the target user; The message to be pushed is provided as a target message to the client used by the target user, so as to display a reminder message associated with the target message in the client. In response to detecting a trigger operation by the target user on the reminder message, the target message is displayed in the target application.

2. The method according to claim 1, characterized in that, The first preset parameter includes at least one of the following: a value parameter representing the value of the message, a demand matching parameter representing the degree of matching between the message and the user's needs, and a timeliness parameter representing the timeliness of the message. The step of calculating the target signal strength information of the message to be pushed relative to the target user based on the first preset parameter, the message to be pushed, and the target user characteristics of the target user includes: Based on the message to be pushed and the characteristics of the target user, the score of the message to be pushed for the value parameter, the score of the message to be pushed relative to the target user for the demand matching parameter, and the score of the message to be pushed for the timeliness parameter are determined. The target signal strength information of the message to be pushed relative to the target user is obtained by multiplying the score of the message to be pushed for the value parameter, the score of the message to be pushed relative to the target user for the demand matching parameter, and the score of the message to be pushed for the timeliness parameter.

3. The method according to claim 1, characterized in that, The second preset parameter includes at least one of the following: a redundancy parameter indicating the degree of redundancy in the message content, an interference parameter indicating the degree of interference in the message content, and an information saturation parameter indicating the degree of saturation of the message relative to the user's information reception. The step of calculating the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed, and the target user characteristics of the target user includes: Based on the message to be pushed and the characteristics of the target user, the scores of the message to be pushed for the redundancy parameter, the scores of the message to be pushed for the interference parameter, and the scores of the message to be pushed relative to the target user for the information saturation parameter are determined. The target noise intensity information of the message to be pushed relative to the target user is obtained by multiplying the score of the message to be pushed for the redundancy parameter, the score of the message to be pushed for the interference parameter, and the score of the message to be pushed relative to the target user for the information saturation parameter.

4. The method according to claim 1, characterized in that, The step of calculating the target signal strength information of the message to be pushed relative to the target user based on the first preset parameter, the message to be pushed, and the target user characteristics of the target user includes: The message to be pushed, the target user characteristics, and the first score prediction strategy are used as input information for a preset score evaluation model to obtain the score of the message to be pushed relative to the target user for the first preset parameter. Based on the score of the message to be pushed relative to the target user for the first preset parameter, the target signal strength information is obtained; The step of calculating the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed, and the target user characteristics of the target user includes: The message to be pushed, the target user characteristics, and the second score prediction strategy are used as input information for the preset score evaluation model to obtain the score of the message to be pushed relative to the target user for the second preset parameter. The target noise intensity information is obtained based on the score of the message to be pushed relative to the target user for the second preset parameter.

5. The method according to claim 1, characterized in that, Also includes: Determine the first preset parameter and the second preset parameter; Determine the first initial weight corresponding to each first sub-parameter in the first preset parameters and the second initial weight corresponding to each second sub-parameter in the second preset parameters; Based on the first sub-parameter, the first initial weight, the second sub-parameter, and the second initial weight, an initial signal-to-noise ratio (SNR) prediction model is constructed to calculate the SNR of a message relative to a user. Obtain the message sample to be processed, the user feature sample, and the signal-to-noise ratio sample corresponding to the message sample to be processed; The initial signal-to-noise ratio (SNR) prediction model is trained using the message sample to be processed, the user feature sample, and the SNR sample to obtain the target SNR prediction model.

6. The method according to claim 5, characterized in that, The step of training the initial signal-to-noise ratio (SNR) prediction model using the message sample to be processed, the user feature sample, and the SNR sample to obtain the target SNR prediction model includes: The message sample to be processed, the user feature sample, the first score prediction strategy, and the second score prediction strategy are used as input information for a preset score evaluation model to obtain the signal-to-noise ratio reference value of the message sample to be processed relative to the sample user. Based on the deviation between the signal-to-noise ratio reference value and the signal-to-noise ratio sample, the first initial weight and the second initial weight are adjusted, and the adjusted first weight corresponding to each first sub-parameter and the adjusted second weight corresponding to each second sub-parameter are determined. Based on the first sub-parameter, the adjusted first weight, the second sub-parameter, and the adjusted second weight, a target signal-to-noise ratio prediction model is obtained.

7. A message display method, characterized in that, The method, applied to a client used by the target user, includes: The system obtains a target message provided by the server, wherein the target message is a message to be pushed whose target signal-to-noise ratio (SNR) meets a preset SNR condition. The server is configured to: determine the message to be pushed and the target user; calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target noise intensity information of the message to be pushed relative to the target user based on a second preset parameter, the message to be pushed, and the target user characteristics of the target user; calculate the target SNR of the message to be pushed relative to the target user using the target signal strength information and the target noise intensity information; and if the target SNR meets the preset SNR condition, determine to push the message to the target user. Display a notification message associated with the target message.

8. A message push device, characterized in that, Applied to the server side, the device includes: The unit for determining the message to be pushed and the target user is used to determine the message to be pushed and the target user. The target signal strength information calculation unit is used to calculate the target signal strength information of the message to be pushed relative to the target user based on a first preset parameter, the message to be pushed and the target user characteristics of the target user; The target noise intensity information calculation unit is used to calculate the target noise intensity information of the message to be pushed relative to the target user based on the second preset parameter, the message to be pushed and the target user characteristics of the target user; A target signal-to-noise ratio calculation unit is used to calculate the target signal-to-noise ratio of the message to be pushed relative to the target user using the target signal strength information and the target noise strength information; The push unit is configured to determine to push the message to be pushed to the target user if the target signal-to-noise ratio meets a preset signal-to-noise ratio condition. A providing unit is configured to provide the message to be pushed as a target message to the client used by the target user, so as to display a reminder message associated with the target message in the client, and to display the target message in the target application in response to detecting a trigger operation of the target user on the reminder message.

9. An electronic device, characterized in that, include: processor; A memory for storing a computer program that is executed by a processor to perform the method described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer program that is executed by a processor to perform the method described in any one of claims 1-7.

Images