Information pushing method and device based on user expression and electronic equipment

Abstract

The present disclosure relates to a user expression-based information pushing method, device and electronic equipment, and belongs to the technical field of big data. The user expression-based information pushing method comprises: sending a pushing message to a target client; obtaining target user corresponding to the target client, expression information and operation data of the target user when the pushing message is displayed; identifying a target emotion type of the target user according to the expression information, and generating a first feedback quantization value of the pushing information based on the target expression type and the operation data; filtering candidate pushing information based on the first feedback quantization value to update a pushing information set corresponding to the target user; and selecting new pushing information for the target user from the pushing information set and returning to execute the step of sending the pushing message to the target client and subsequent steps. Thus, the present disclosure can adjust the pushing message in real time and continuously improve the mechanism of the pushing information by obtaining the user expression information and operation data in real time and analyzing the real-time user expression information and operation data, so that the pushing information is no longer limited to the user's behavior habits, the information content that can make the user happy can be pushed to the greatest extent, the accuracy and efficiency of sending the pushing message are improved, and the user experience is further improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of big data, and particularly relates to a method and device for pushing information based on user expressions and an electronic device. BACKGROUND

[0002] In the related art, when pushing information, it is often limited to recommending according to user behavior habits and user existing labels. In the optimization and improvement of recommended information, information is collected according to the user's continuous operation behavior, and then the optimization and improvement of the recommended information is completed. However, the above method is often limited by the user's personal specific information, resulting in low accuracy in information pushing. It is likely that the user does not like or need the information, and the user experience is poor. Therefore, how to improve the accuracy of information pushing and improve the user experience has become a problem to be solved. SUMMARY

[0003] The present disclosure provides a method and device for pushing information based on user expressions, an electronic device, a computer readable storage medium and a computer program product to at least solve the problem of low accuracy of information pushing and poor user experience in the related art.

[0004] The technical solutions of the present disclosure are as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a method for pushing information based on user expressions is provided, comprising: sending push information to a target client; obtaining expression information and operation data of a target user corresponding to the target client when the push information is displayed; identifying a target emotion type of the target user according to the expression information, and generating a first feedback quantization value of the push information based on the target emotion type and the operation data; based on the first feedback quantization value, screening candidate push information to update a push information set corresponding to the target user; and selecting new push information for the target user from the push information set and returning to perform the steps of sending push information to the target client and subsequent steps.

[0006] In an embodiment of the present disclosure, the generating of the first feedback quantization value of the push information based on the target emotion type and the operation data comprises: obtaining candidate combinations between candidate emotion types and candidate operation types, and a feedback quantization value corresponding to each candidate combination; matching the target emotion type and the operation data with the candidate combinations to determine a target combination corresponding to the target user from the candidate combinations; and determining the feedback quantization value of the target combination as the first feedback quantization value of the push information.

[0007] In an embodiment of the present disclosure, the filtering the candidate push information based on the first feedback quantization value to update the push information set corresponding to the target user comprises: if the first feedback quantization value is greater than or equal to a preset threshold, obtaining similar push information of the push information from the candidate push information; obtaining feedback quantization values of the similar push information under different historical push users, and averaging the feedback quantization values to obtain a second feedback quantization value of the similar push information; selecting the similar push information with the second feedback quantization value greater than the preset threshold as a first candidate push information; and updating the push information set corresponding to the target user based on the first candidate push information.

[0008] In an embodiment of the present disclosure, the filtering the candidate push information based on the first feedback quantization value to update the push information set corresponding to the target user comprises: if the first feedback quantization value is greater than or equal to a preset threshold, obtaining similar push information of the push information from the candidate push information; obtaining a first historical push user of the similar push information, and determining a first similar user of the target user from the first historical push user; obtaining a third feedback quantization value of the similar push information by the first similar user, and determining a second candidate push information from the similar push information based on the third feedback quantization value; and updating the push information set corresponding to the target user based on the second candidate push information.

[0009] In an embodiment of the present disclosure, the method further comprises: if the first feedback quantization value is less than the preset threshold, removing similar push information of the push information from the candidate push information to obtain the third candidate push information; obtaining a second historical push user of the third candidate push information, and determining a second similar user of the target user from the second historical push user; obtaining a fourth feedback quantization value of the third candidate push information by the second similar user; selecting the third candidate push information with the fourth feedback quantization value greater than or equal to the preset threshold as a fourth candidate push information; and updating the push information set corresponding to the target user based on the fourth candidate push information.

[0010] In an embodiment of the present disclosure, before the sending the push information to the target client, the method further comprises: obtaining an initial push information set of the target user according to a type of the target user corresponding to the target client; and selecting the push information from the initial push information set and pushing to the target client.

[0011] In an embodiment of the present disclosure, the obtaining the initial push information set of the target user according to the type of the target user corresponding to the target client comprises: if the type of the target user indicates that the target user is a new registered user, sending first interaction information to the target client; obtaining second interaction information corresponding to the first interaction information fed back by the target client; and determining the initial push information set according to the second interaction information.

[0012] In an embodiment of the present disclosure, the obtaining the initial push information set of the target user according to the type of the target user corresponding to the target client comprises: if the type of the target user indicates that the target user is a historical user, obtaining historical behavior information of the target user; and obtaining the initial push information set according to the historical behavior information.

[0013] According to a second aspect of the embodiments of the present disclosure, an information push device based on user expressions is provided, which comprises: a sending module configured to send push information to a target client; an obtaining module configured to obtain expression information and operation data of a target user corresponding to the target client at the time of display of the push information; a generating module configured to identify a target emotion type of the target user according to the expression information, and generate a first feedback quantization value of the push information based on the target emotion type and the operation data; an updating module configured to filter candidate push information based on the first feedback quantization value, so as to update a push information set corresponding to the target user; and a selecting module configured to select new push information for the target user from the push information set, and return to perform the sending push information to the target client and subsequent steps.

[0014] In an embodiment of the present disclosure, the generating module is further configured to: obtain candidate combinations between candidate emotion types and candidate operation types, and feedback quantization values corresponding to each of the candidate combinations; match the target emotion type and the operation data with the candidate combinations, to determine a target combination corresponding to the target user from the candidate combinations; and determine the feedback quantization value of the target combination as the first feedback quantization value of the push information.

[0015] In an embodiment of the present disclosure, the updating module is further configured to: if the first feedback quantization value is greater than or equal to a preset threshold, obtaining similar push information of the push information from the candidate push information; obtaining feedback quantization values of the similar push information under different historical push users, and averaging the feedback quantization values to obtain a second feedback quantization value of the similar push information; selecting similar push information with the second feedback quantization value greater than the preset threshold as first candidate push information; and updating the push information set corresponding to the target user based on the first candidate push information.

[0016] In an embodiment of the present disclosure, the updating module is further configured to: if the first feedback quantization value is greater than or equal to a preset threshold, obtaining similar push information of the push information from the candidate push information; obtaining a first historical push user of the similar push information, and determining a first similar user of the target user from the first historical push user; obtaining a third feedback quantization value of the similar push information by the first similar user, and determining second candidate push information from the similar push information based on the third feedback quantization value; and updating the push information set corresponding to the target user based on the second candidate push information.

[0017] In an embodiment of the present disclosure, the device is further configured to: if the first feedback quantization value is less than the preset threshold, removing similar push information of the push information from the candidate push information to obtain the third candidate push information; obtaining a second historical push user of the third candidate push information, and determining a second similar user of the target user from the second historical push user; obtaining a fourth feedback quantization value of the third candidate push information by the second similar user; selecting third candidate push information with the fourth feedback quantization value greater than or equal to the preset threshold as fourth candidate push information; and updating the push information set corresponding to the target user based on the fourth candidate push information.

[0018] In an embodiment of the present disclosure, before the device sends the push information to the target client, the device is further configured to: according to the type of the target user corresponding to the target client, obtaining an initial push information set of the target user; selecting the push information from the initial push information set and pushing to the target client.

[0019] In an embodiment of the present disclosure, the obtaining module is further configured to: if the type of the target user indicates that the target user is a newly registered user, sending first interaction information to the target client; obtaining second interaction information corresponding to the first interaction information fed back by the target client; and determining the initial push information set according to the second interaction information.

[0020] In an embodiment of the present disclosure, the obtaining module is further configured to: if the type of the target user indicates that the target user is a historical user, obtain historical behavior information of the target user; and obtain the initial push information set according to the historical behavior information.

[0021] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, including: a processor; a memory for storing instructions executable by the processor; and wherein the processor is configured to execute the instructions to implement the information push method based on user expressions according to the first aspect.

[0022] According to a fourth aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information push method based on user expressions according to the first aspect.

[0023] According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, when the computer program is executed by a processor, the information push method based on user expressions according to the first aspect is implemented.

[0024] The embodiments of the present disclosure provide at least the following beneficial effects: the target client is sent push information,

[0025] The target user corresponding to the target client, the expression information and the operation data of the target user in the push information display are obtained, the target emotion type of the target user is recognized according to the expression information, and the first feedback quantization value of the push information is generated based on the target emotion type and the operation data. The candidate push information is screened based on the first feedback quantization value, the push information set corresponding to the target user is updated, new push information is selected for the target user from the push information set, and the subsequent steps of sending the push information to the target client are returned. Thus, the present disclosure can adjust the push information in real time and continuously improve the mechanism of the push information by obtaining the user expression information and the operation data in real time and analyzing the real-time user expression information and the operation data. The push information will no longer be limited to the behavior habits of the user, and the information content that makes the user happy can be maximally pushed, the accuracy and efficiency of sending the push information are improved, and the user experience is further improved.

[0026] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0027] The accompanying drawings, which are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure and do not limit the present disclosure in any inapropriate manner.

[0028] Figure 1 is a flowchart of a user-expression-based information pushing method according to a first embodiment of the present disclosure.

[0029] Figure 2 is a flowchart of a user-expression-based information pushing method according to a second embodiment of the present disclosure.

[0030] Figure 3 is a flowchart of a user-expression-based information pushing method according to a third embodiment of the present disclosure.

[0031] Figure 4 is a flowchart of a user-expression-based information pushing method according to a fourth embodiment of the present disclosure.

[0032] Figure 5 is a block diagram of a user-expression-based information pushing apparatus according to a first embodiment of the present disclosure.

[0033] Figure 6 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0034] In order to make the ordinary person skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0036] It should be noted that the acquisition, storage, use, processing, etc. of data in the technical solutions of the present application comply with the relevant provisions of national laws and regulations.

[0037] Figure 1 is a flowchart of a user-expression-based information pushing method according to a first embodiment of the present disclosure.

[0038] As Figure 1As shown, the user expression-based information pushing method of the first embodiment of the present disclosure comprises the following steps:

[0039] In step S101, the push information is sent to the target client.

[0040] It should be noted that the push information can be any pre-set message.

[0041] For example, the push information can be push information for any financial service; the push information can be push information for any financial product.

[0042] It should be noted that the present disclosure does not limit the specific way of sending push information to the target client, which can be selected according to the actual situation.

[0043] Optionally, when the sending instruction is received, the push information is sent to the target client.

[0044] Optionally, the sending time of sending the push information to the target client can be pre-set, and the push information is sent to the target client when the sending time is reached.

[0045] In step S102, the target user corresponding to the target client, the expression information and the operation data of the target client at the time of push information display are obtained.

[0046] Among them, the expression information refers to facial expression information.

[0047] It should be noted that facial expression refers to the expression of various emotional states through changes in eye muscles, facial muscles and mouth muscles.

[0048] It should be noted that the present disclosure does not limit the specific way of obtaining the expression information of the target user corresponding to the target client at the time of push information display, which can be selected according to the actual situation.

[0049] Optionally, the camera in the target client can be used to obtain the expression information at the time of push information display.

[0050] For example, the camera can be used to collect the posture data of the facial organs of the target user in real time, and then analyze the posture data of the facial organs to obtain the expression information of the target user at the time of push information display.

[0051] It should be noted that the operation data can be any data at the time of push information display.

[0052] For example, the operation data can be closing the push information display page, clicking on the push information, clicking on the push information, etc.

[0053] In step S103, a target emotion type of the target user is identified according to the expression information, and a first feedback quantization value of the push information is generated based on the target emotion type and the operation data.

[0054] The emotion is an internal subjective experience, and when the emotion occurs, it is always accompanied by some external manifestations, that is, some observable behavior characteristics, which are called expressions.

[0055] In the embodiments of the present disclosure, after the expression information is obtained, the target emotion type of the target user can be identified according to the expression information.

[0056] For example, the target emotion type can be joy, anger, sadness, fear, disgust, surprise, admiration, etc.

[0057] It should be noted that when the first feedback quantization value of the push information is generated based on the target emotion type and the operation data, a feedback quantization value generation rule can be preset, and after the target emotion type and the operation data are obtained, the first feedback quantization value of the push information can be generated according to the feedback quantization value generation rule.

[0058] The first feedback quantization value can reflect the degree of love of the user for the push information.

[0059] In step S104, the candidate push information is screened based on the first feedback quantization value, so as to update the push information set corresponding to the target user.

[0060] It should be noted that the specific manner of screening the candidate push information based on the first feedback quantization value is not limited in the present disclosure, and can be selected according to actual conditions.

[0061] Optionally, a preset threshold can be preset, and the candidate push information with the first feedback quantization value lower than the preset threshold can be removed, so as to update the push information set corresponding to the target user.

[0062] In step S105, new push information is selected for the target user from the push information set, and the step of sending the push information to the target client and the subsequent steps are returned.

[0063] For example, after the push information set corresponding to the target user is updated, the first feedback quantization values of the candidate push information can be sorted in descending order, the push information with the highest sorting position in the push information set is taken as the to-be-pushed information, and the to-be-pushed information is sent to the target client.

[0064] According to the user expression-based information pushing method provided by the embodiment of the present disclosure, the target client is sent with the pushing information, the target user corresponding to the target client is acquired, the expression information and operation data of the target client at the time of the pushing information display are acquired, the target emotion type of the target user is identified according to the expression information, and the first feedback quantization value of the pushing information is generated based on the target emotion type and the operation data. The candidate pushing information is screened based on the first feedback quantization value, so as to update the pushing information set corresponding to the target user. The new pushing information is selected for the target user from the pushing information set, and the subsequent steps of sending the pushing information to the target client are returned. Thus, the present disclosure can adjust the pushing information in real time and constantly improve the mechanism of the pushing information by acquiring the expression information and operation data of the user in real time and analyzing the real-time expression information and operation data of the user. The pushing information is no longer limited to the behavior habits of the user, and the information content that can make the user happy can be maximally pushed, so that the accuracy and efficiency of sending the pushing information are improved, and the user experience is further improved.

[0065] Figure 2 is a flowchart of the user expression-based information pushing method according to the second embodiment of the present disclosure.

[0066] As shown in Figure 2 , the user expression-based information pushing method according to the second embodiment of the present disclosure includes the following steps:

[0067] In step S201, the initial pushing information set of the target user is acquired according to the type of the target user corresponding to the target client.

[0068] Optionally, if the type of the target user indicates that the target user is a newly registered user, the first interaction information can be sent to the target client, the second interaction information corresponding to the first interaction information fed back by the target client is acquired, and the initial pushing information set is determined according to the second interaction information.

[0069] For example, if the target user is a newly registered user, for the recommended financial product information, when the user behavior big data component cannot query the user historical behavior, a questionnaire pop-up window can be popped up to obtain the first interaction information, that is, the questionnaire inquires about the general situation of the user's interest, mainly involving the type of financial product of interest, risk level, and holding time, etc. According to the questionnaire content, the bottom-up display of the business operation configured content is performed, and the first round of user expression information is obtained, according to the emotion type corresponding to the user expression and the operation data of the user, that is, the second interaction information corresponding to the first interaction information is obtained, and according to the second interaction information, the initial push information set is determined, that is, the user behavior big data component records the feedback quantization value of the customer to the product. If the user expression is happy, other products that make the customer happy are recommended according to the high similarity of the financial product information, if the customer expression is not happy, the product with low similarity of the financial product is recommended, and then the subsequent steps of sending the push financial product message to the client are returned to execute until the user purchases the product or closes the push financial product message page.

[0070] Optionally, if the type of the target user indicates that the target user is a historical user, the historical behavior information of the target user can be obtained, and the initial push information set is obtained according to the historical behavior information.

[0071] For example, if the target user is a historical user, for the recommended financial product information, when the user behavior big data component finds the user historical behavior information, the corresponding financial product push information can be obtained through the user with high similarity in the historical behavior information, and the push information is displayed, the user expression is captured, the recommendation analysis is performed, the customer behavior big data component records the customer's happiness score of the financial product push information, and then the subsequent steps of sending the push financial product message to the client are returned to execute until the user purchases the product or closes the push financial product message page.

[0072] In step S202, the push information is selected from the initial push information set and pushed to the target client.

[0073] In the embodiment of the present disclosure, after the initial push information set is obtained, the push information can be selected from the initial push information set and pushed to the target client.

[0074] In step S203, the target user corresponding to the target client, the expression information and the operation data of the target user in the push information display are obtained.

[0075] The related content of step S203 can be referred to the above-mentioned embodiments, which will not be repeated here.

[0076] In step S204, the target emotion type of the target user is identified according to the expression information, the candidate combination between the candidate emotion type and the candidate operation type is obtained, and the feedback quantization value corresponding to each candidate combination is obtained.

[0077] It should be noted that the target emotion type can be divided in advance, that is, when the target emotion type is joy, surprise, and envy, it can be defined as positive feedback, and when the target emotion type is anger, sadness, fear, and disgust, it can be defined as negative feedback.

[0078] For example, candidate combination 1: when the target emotion type of the user is positive feedback, the operation type is to view the details of the financial product, and the feedback quantification value is set to 2 points; candidate combination 2: when the target emotion type of the user is positive feedback, and there is no operation type, the feedback quantification value is set to 1 point; candidate combination 3: when the target emotion type of the user cannot be divided into positive feedback or negative feedback, the feedback quantification value is set to 0 point; candidate combination 4: when the target emotion type of the user is negative feedback, and there is no operation type, the feedback quantification value is set to -1 point; candidate combination 5: when the target emotion type of the user is negative feedback, and the operation type is to close the page or quickly swipe away or click on the operation of not liking, the feedback quantification value is set to -2 points.

[0079] In step S205, the target emotion type and the operation data are matched with the candidate combinations, and the target combination corresponding to the target user is determined from the candidate combinations.

[0080] For example, when the target emotion type is joy and the operation data is to view the details of the financial product, it can be determined that the target combination corresponding to the target user is candidate combination 1.

[0081] In step S206, the feedback quantification value of the target combination is determined as the first feedback quantification value of the push information.

[0082] For example, when the target combination is candidate combination 1, the feedback quantification value of the target combination is 2 points, that is, the first feedback quantification value of the push information is 2 points.

[0083] In step S207, the candidate push information is screened based on the first feedback quantification value to update the push information set corresponding to the target user.

[0084] As a possible implementation manner, as shown in Figure 3 Based on the above embodiment, the specific process of screening the candidate push information based on the first feedback quantification value in step S207 to update the push information set corresponding to the target user includes the following steps:

[0085] In step S301, if the first feedback quantification value is greater than or equal to a preset threshold, the similar push information of the push information is obtained from the candidate push information.

[0086] Optionally, user information can be obtained in advance, such as: user expressions, user behavior (browsing time, click operations), user attribute tags, etc.; push information: the type of financial product, annualized rate of return, risk level, minimum purchase amount, industry sector, etc.; the context information corresponding to the push information: the page where the push information is currently displayed (financial products can be divided into wealth management products, funds, insurance, account precious metals, etc.).

[0087] It should be noted that this disclosure does not limit the specific method for obtaining similar push information from candidate push information, and the method can be selected according to the actual situation.

[0088] Optionally, similar recommendations can be calculated based on Euclidean distance.

[0089] In step S302, the feedback quantization value of similar push information under different historical push users is obtained, and the feedback quantization value is averaged to obtain the second feedback quantization value of similar push information.

[0090] For example, for users 1 to 7, Fund A information is pushed information. The feedback quantification values ​​of Fund A information for users 1 to 7 are 2, 1, 2, -2, -2, 2, 2 respectively. Then, the feedback quantification values ​​of different historical push users can be averaged to obtain the second feedback quantification value of similar push information.

[0091] In step S303, similar push information with a second feedback quantization value greater than a preset threshold is selected as the first candidate push information.

[0092] In this embodiment of the disclosure, after obtaining the second feedback quantization value, the second feedback quantization value can be compared with a preset threshold, and similar push information with a second feedback quantization value greater than the preset threshold can be used as the first candidate push information.

[0093] In step S304, the push information set corresponding to the target user is updated based on the first candidate push information.

[0094] It should be noted that after obtaining the first candidate push information, the push information set corresponding to the target user can be updated based on the first candidate push information.

[0095] As another possible way to achieve this, such as Figure 4 As shown, based on the above implementation, the specific process of filtering candidate push information based on the first feedback quantification value in step S207 to update the push information set corresponding to the target user includes the following steps:

[0096] In step S401, if the first feedback quantization value is greater than or equal to a preset threshold, similar push information of the push information is obtained from the candidate push information.

[0097] In step S402, a first historical push user of the similar push information is acquired, and a first similar user of the target user is determined from the first historical push user.

[0098] It should be noted that the specific manner of determining the first similar user of the target user from the first historical push user is not limited in the present disclosure, and can be selected according to actual conditions.

[0099] Optionally, the first similar user of the target user can be calculated according to the Euclidean distance.

[0100] For example, as shown in Table 1, the feedback quantization value of each user to different financial product push information can be acquired in advance, and then the similarity between the target user and user 1, user 2 and user 3 can be calculated according to the Euclidean distance respectively, to determine the first similar user of the target user. It is calculated that the distance between the target user and user 1, user 2 and user 3 is respectively: 、 、 Therefore, the first similar user of the target user is user 3.

[0101] Table 1

[0102]

[0103] In step S403, a third feedback quantization value of the first similar user to the similar push information is acquired, and a second candidate push information is determined from the similar push information based on the third feedback quantization value.

[0104] It should be noted that after the first similar user is acquired, the third feedback quantization value of the first similar user to the similar push information can be acquired, and the second candidate push information is determined from the similar push information based on the third feedback quantization value.

[0105] In step S404, the push information set corresponding to the target user is updated based on the second candidate push information.

[0106] Optionally, if the first feedback quantization value is less than a preset threshold, the similar push information of the target user is removed from the candidate push information to obtain third candidate push information, a second historical push user of the third candidate push information is acquired, a second similar user of the target user is determined from the second historical push user, a fourth feedback quantization value of the second similar user to the third candidate push information is acquired, the third candidate push information with the fourth feedback quantization value greater than or equal to the preset threshold is selected as a fourth candidate push information, and the push information set corresponding to the target user is updated based on the fourth candidate push information.

[0107] In step S208, new push information is selected for the target user from the push information set, and the step of sending push information to the target client and the subsequent steps are returned to be executed.

[0108] According to the information push method based on user expressions provided by the embodiments of the present disclosure, the expression information and operation data of the user are analyzed, the push information is adjusted in real time according to the analysis result, the similar users and similar push information are used for push, the information content that makes the user happy can be maximally pushed, the accuracy and efficiency of sending push information are improved, and the user experience is further improved.

[0109] Figure 5 A block diagram of the information push device based on user expressions according to the first embodiment of the present disclosure.

[0110] As shown in Figure 5 the information push device based on user expressions 500 of the embodiments of the present disclosure includes a sending module 501, an obtaining module 502, a generating module 503, an updating module 504, and a selecting module 505.

[0111] The sending module 501 is configured to send push information to a target client;

[0112] The obtaining module 502 is configured to obtain expression information and operation data of a target user corresponding to the target client at the time of displaying the push information;

[0113] The generating module 503 is configured to identify a target emotion type of the target user according to the expression information, and generate a first feedback quantization value of the push information based on the target emotion type and the operation data;

[0114] The updating module 504 is configured to filter candidate push information based on the first feedback quantization value, to update a push information set corresponding to the target user;

[0115] The selecting module 505 is configured to select new push information for the target user from the push information set, and return to execute the step of sending push information to the target client and the subsequent steps.

[0116] In an embodiment of the present disclosure, the generating module 503 is further configured to: obtain candidate combinations between candidate emotion types and candidate operation types, and feedback quantization values corresponding to each of the candidate combinations; match the target emotion type and the operation data with the candidate combinations, to determine a target combination corresponding to the target user from the candidate combinations; and determine the feedback quantization value of the target combination as the first feedback quantization value of the push information.

[0117] In an embodiment of the present disclosure, the updating module 504 is further configured to: if the first feedback quantization value is greater than or equal to a preset threshold, obtaining similar push information of the push information from the candidate push information; obtaining feedback quantization values of the similar push information under different historical push users, and averaging the feedback quantization values to obtain a second feedback quantization value of the similar push information; selecting similar push information with the second feedback quantization value greater than the preset threshold as a first candidate push information; and updating the push information set corresponding to the target user based on the first candidate push information.

[0118] In an embodiment of the present disclosure, the updating module 504 is further configured to: if the first feedback quantization value is greater than or equal to a preset threshold, obtaining similar push information of the push information from the candidate push information; obtaining a first historical push user of the similar push information, and determining a first similar user of the target user from the first historical push user; obtaining a third feedback quantization value of the similar push information by the first similar user, and determining a second candidate push information from the similar push information based on the third feedback quantization value; and updating the push information set corresponding to the target user based on the second candidate push information.

[0119] In an embodiment of the present disclosure, the apparatus 500 is further configured to: if the first feedback quantization value is less than the preset threshold, removing similar push information of the push information from the candidate push information to obtain the third candidate push information; obtaining a second historical push user of the third candidate push information, and determining a second similar user of the target user from the second historical push user; obtaining a fourth feedback quantization value of the third candidate push information by the second similar user; selecting third candidate push information with the fourth feedback quantization value greater than or equal to the preset threshold as fourth candidate push information; and updating the push information set corresponding to the target user based on the fourth candidate push information.

[0120] In an embodiment of the present disclosure, before sending the push information to the target client, the apparatus 500 is further configured to: obtaining an initial push information set of the target user according to a type of the target user corresponding to the target client; and selecting the push information from the initial push information set and pushing to the target client.

[0121] In an embodiment of the present disclosure, the obtaining module 502 is further configured to: if the type of the target user indicates that the target user is a new registered user, sending first interaction information to the target client; obtaining second interaction information corresponding to the first interaction information fed back by the target client; and determining the initial push information set according to the second interaction information.

[0122] In one embodiment of the present disclosure, the acquisition module 502 is further configured to: if the type of the target user indicates that the target user is a historical user, acquire historical behavior information of the target user; and acquire the initial push information set according to the historical behavior information.

[0123] As to the apparatus in the above embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0124] To sum up, the apparatus for pushing information based on user expressions provided by the embodiments of the present disclosure sends push information to a target client, acquires expression information and operation data of a target user corresponding to the target client at the time of display of the push information, identifies a target emotion type of the target user according to the expression information, generates a first feedback quantitative value of the push information based on the target emotion type and the operation data, screens candidate push information based on the first feedback quantitative value, updates a push information set corresponding to the target user, reselects new push information for the target user from the push information set, and returns to perform the step of sending push information to the target client and subsequent steps. Thus, the present disclosure can adjust push information in real time and constantly improve the mechanism of push information by acquiring user expression information and operation data in real time and analyzing the real-time user expression information and operation data, and can no longer be limited to push information according to the behavior habits of users, can maximize the push of information content that makes users happy, improves the accuracy and efficiency of sending push information, and further improves user experience.

[0125] Figure 6 is a block diagram of an electronic device according to an example embodiment.

[0126] As Figure 6 shown, the electronic device 600 includes:

[0127] a memory 610 and a processor 620, a bus 630 connecting different components (including the memory 610 and the processor 620), and the memory 610 stores a computer program which, when executed by the processor 620, implements the method for pushing information based on user expressions according to the first aspect of the present disclosure.

[0128] Bus 630 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0129] Electronic device 600 typically includes a variety of electronic device readable media. These media can be any available media that is located either internally or externally to electronic device 600, including both volatile and nonvolatile media, removable and non-removable media.

[0130] Memory 610 also can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 640 and / or cache memory 650. Electronic device 600 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 660 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 6 not shown, is typically provided as residual storage across electronic device 600, and can be used for storing data that is both written and read to / from memory 610. Figure 6 not shown, is typically provided as residual storage across electronic device 600, and can be used for storing data that is both written and read to / from memory 610.

[0131] Program / utility 680 having a set (at least one) of program modules 670, can be stored in, for example, memory 610 by way of example, such program modules 670 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of or some combination of which can include implementation of a network environment. Program modules 670 generally carry out the functions and / or methodologies of embodiments of the disclosure as described herein.

[0132] The electronic device 600 can also communicate with one or more external devices 690 such as a keyboard or pointing device, a display 691, etc.; one or more devices that enable a user to interact with the electronic device 600; and / or one or more devices (e.g., a networking module, a Figure 6 modulator, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 692. Still yet, such communication can occur electronically over a network 693 such as a local area network (LAN) and / or a wide area network (WAN) such as the Internet. As an example, the network 693 can be enabled by a modem, network adapter, or other means for communicating over the network 693.

[0133] The processor 620 can execute the various functional applications and data processing of the electronic device 600 by running programs stored in the memory 610.

[0134] It should be noted that the implementation process and technical principles of the electronic device of the present embodiment are described above in the explanation of the information push method based on user expression of the present disclosure, which will not be repeated here.

[0135] In summary, the electronic device provided by the present embodiment can execute the information push method based on user expression as described above, obtain the target user corresponding to the target client by sending the push information to the target client, obtain the expression information and operation data of the target user at the display time of the push information, identify the target emotion type of the target user according to the expression information, and generate the first feedback quantization value of the push information based on the target emotion type and the operation data. The candidate push information is filtered based on the first feedback quantization value to update the push information set corresponding to the target user, new push information is selected for the target user from the push information set, and the subsequent steps of sending the push information to the target client are returned. Thus, the present disclosure can adjust the push information in real time by obtaining the user expression information and operation data in real time and analyzing the real-time user expression information and operation data, and can continuously improve the mechanism of the push information according to the analysis results. The push information will no longer be limited to the behavior habits of the user, and the information content that makes the user happy can be pushed to the greatest extent, improving the accuracy and efficiency of sending the push information and further improving the user experience.

[0136] In order to realize the above-mentioned embodiments, the present disclosure further provides a computer readable storage medium.

[0137] The instructions in the computer-readable storage medium can be executed by a processor of the electronic device to enable the electronic device to perform the information pushing method based on user expression as previously described. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, etc.

[0138] To achieve the above-mentioned embodiments, the present disclosure further provides a computer program product comprising a computer program, characterized in that the computer program is executed by a processor to implement the information pushing method based on user expression of the first aspect.

[0139] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure following the general principles thereof and including such departures from the present disclosure that come within known, accepted, and / or customary practice in the art to which the present disclosure pertains. The specification and examples are to be regarded as illustrative only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0140] It should be understood that the present disclosure is not limited to the precise structures as herein described and illustrated in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present disclosure. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for pushing information based on user facial expressions, characterized in that, include: Send push notifications to the target client; Obtain the facial expressions and operation data of the target user corresponding to the target client when the push information is displayed; The target emotion type of the target user is identified based on the facial expression information, and a first feedback quantification value of the push message is generated based on the target emotion type and the operation data. Based on the first feedback quantification value, candidate push information is filtered to update the push information set corresponding to the target user; From the set of push notifications, select new push notifications for the target user and return to execute the steps of sending push notifications to the target client and subsequent steps. The step of filtering candidate push information based on the first feedback quantification value to update the push information set corresponding to the target user includes: If the first feedback quantization value is less than a preset threshold, similar push information that takes the push information is removed from the candidate push information to obtain the third candidate push information; Obtain the second historical push users of the third candidate push information, and determine the second similar users of the target user from the second historical push users; Obtain the fourth quantified value of the second similar user's feedback to the third candidate push information; The third candidate push information whose fourth feedback quantization value is greater than or equal to the preset threshold is selected as the fourth candidate push information; Based on the fourth candidate push information, update the push information set corresponding to the target user.

2. The method according to claim 1, characterized in that, The step of generating a first feedback quantification value for the push notification based on the target emotion type and the operation data includes: Obtain candidate combinations between candidate emotion types and candidate operation types, and the feedback quantization value corresponding to each candidate combination; The target emotion type and the operation data are matched with the candidate combinations to determine the target combination corresponding to the target user from the candidate combinations; The feedback quantization value of the target combination is determined as the first feedback quantization value of the push information.

3. The method according to claim 1, characterized in that, The step of filtering candidate push information based on the first feedback quantification value to update the push information set corresponding to the target user includes: If the first feedback quantization value is greater than or equal to a preset threshold, similar push information of the push information is obtained from the candidate push information; Obtain the feedback quantification value of the similar push information under different historical push users, and average the feedback quantification value to obtain the second feedback quantification value of the similar push information; Select similar push information whose second feedback quantization value is greater than the preset threshold as the first candidate push information; Based on the first candidate push information, update the push information set corresponding to the target user.

4. The method according to claim 1, characterized in that, The step of filtering candidate push information based on the first feedback quantification value to update the push information set corresponding to the target user further includes: If the first feedback quantization value is greater than or equal to a preset threshold, similar push information of the push information is obtained from the candidate push information; Obtain the first historical push users of the similar push information, and determine the first similar user of the target user from the first historical push users; Obtain the third feedback quantization value of the first similar user to the similar push information, and determine the second candidate push information from the similar push information based on the third feedback quantization value; Based on the second candidate push information, update the push information set corresponding to the target user.

5. The method according to any one of claims 1-4, characterized in that, Before sending the push information to the target client, the process also includes: Based on the type of the target user corresponding to the target client, obtain the initial push information set of the target user; The push information is selected from the initial push information set and pushed to the target client.

6. The method according to claim 5, characterized in that, The step of obtaining the initial push information set of the target user according to the type of the target user corresponding to the target client includes: If the type of the target user indicates that the target user is a newly registered user, send the first interactive information to the target client; Obtain the second interaction information corresponding to the first interaction information returned by the target client; The initial push information set is determined based on the second interaction information.

7. The method according to claim 5, characterized in that, The step of obtaining the initial push information set of the target user according to the type of the target user corresponding to the target client includes: If the type of the target user indicates that the target user is a historical user, obtain the historical behavior information of the target user; Based on the historical behavior information, obtain the initial push information set.

8. An information push device based on user facial expressions, characterized in that, include: The sending module is configured to send push information to the target client; The acquisition module is configured to acquire the facial expression information and operation data of the target user corresponding to the target client when the push information is displayed; The generation module is configured to identify the target emotion type of the target user based on the facial expression information, and generate a first feedback quantification value of the push information based on the target emotion type and the operation data; The update module is configured to filter candidate push information based on the first feedback quantification value in order to update the push information set corresponding to the target user; The selection module is configured to reselect new push information for the target user from the push information set, and then return to execute the steps of sending push information to the target client and subsequent steps. The update module is also configured to: If the first feedback quantization value is less than a preset threshold, similar push information that takes the push information is removed from the candidate push information to obtain the third candidate push information; Obtain the second historical push users of the third candidate push information, and determine the second similar users of the target user from the second historical push users; Obtain the fourth quantified value of the second similar user's feedback to the third candidate push information; The third candidate push information whose fourth feedback quantization value is greater than or equal to the preset threshold is selected as the fourth candidate push information; Based on the fourth candidate push information, update the push information set corresponding to the target user.

9. The apparatus according to claim 8, characterized in that, The generation module is further configured to: Obtain candidate combinations between candidate emotion types and candidate operation types, and the feedback quantization value corresponding to each candidate combination; The target emotion type and the operation data are matched with the candidate combinations to determine the target combination corresponding to the target user from the candidate combinations; The feedback quantization value of the target combination is determined as the first feedback quantization value of the push information.

10. The apparatus according to claim 8, characterized in that, The update module is also configured to: If the first feedback quantization value is greater than or equal to a preset threshold, similar push information of the push information is obtained from the candidate push information; Obtain the feedback quantification value of the similar push information under different historical push users, and average the feedback quantification value to obtain the second feedback quantification value of the similar push information; Select similar push information whose second feedback quantization value is greater than the preset threshold as the first candidate push information; Based on the first candidate push information, update the push information set corresponding to the target user.

11. The apparatus according to claim 8, characterized in that, The update module is also configured to: If the first feedback quantization value is greater than or equal to a preset threshold, similar push information of the push information is obtained from the candidate push information; Obtain the first historical push users of the similar push information, and determine the first similar user of the target user from the first historical push users; Obtain the third feedback quantization value of the first similar user to the similar push information, and determine the second candidate push information from the similar push information based on the third feedback quantization value; Based on the second candidate push information, update the push information set corresponding to the target user.

12. The apparatus according to any one of claims 8-11, characterized in that, Before sending the push information to the target client, the device is further configured to: Based on the type of the target user corresponding to the target client, obtain the initial push information set of the target user; The push information is selected from the initial push information set and pushed to the target client.

13. The apparatus according to claim 12, characterized in that, The acquisition module is further configured to: If the type of the target user indicates that the target user is a newly registered user, send the first interactive information to the target client; Obtain the second interaction information corresponding to the first interaction information returned by the target client; The initial push information set is determined based on the second interaction information.

14. The apparatus according to claim 12, characterized in that, The acquisition module is further configured to: If the type of the target user indicates that the target user is a historical user, obtain the historical behavior information of the target user; Based on the historical behavior information, obtain the initial push information set.

15. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the information push method based on user facial expressions as described in any one of claims 1-7.

16. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the information push method based on user facial expressions as described in any one of claims 1-7.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the information push method based on user facial expressions as described in any one of claims 1-7.

Images