Application content pushing method and device, computer equipment and storage medium

Abstract

The invention relates to an application content pushing method and device, computer equipment and a storage medium, and the method comprises the steps: constructing a corresponding user portrait marking dictionary according to the basic information of each platform user; analyzing the feature data of each platform user, and updating a user portrait marking dictionary based on an analysis result; wherein the feature data comprises one or more combinations of operation behavior data, application evaluation data and real-time emotion features; furthermore, a corresponding user portrait is constructed based on the updated user portrait marking dictionary, and corresponding application content is pushed to the platform user according to the user portrait. Through the content pushing method and device, the problem that the content pushing of the platform is inaccurate due to the fact that the preferences of different users cannot be accurately predicted is solved, the preferences of different users are accurately predicted, and the content pushing accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an application content push method, apparatus, computer equipment and storage medium. Background Art

[0002] With the rapid development of mobile Internet, various fields have launched platforms that centrally provide related applications to meet users' usage and communication needs. For example, in the medical field, the magnetic resonance application platform is used to provide various types of magnetic resonance applications. Users can upload magnetic resonance applications to the platform by themselves, download and install other magnetic resonance applications on the platform, and comment and share their experience of using the applications. However, in the era of big data, information overload has become a normal problem. Users need to face and process a large amount of data on various application platforms, and they cannot quickly and accurately obtain the content they need by relying on personal browsing.

[0003] In order to solve the above problems, application platforms usually use content push systems to enable users to receive application content of interest. Existing push methods include content push based on user behavior data, such as user dwell time, search information, and favorite content, etc.; or based on each user's preferences, similar users are found in the user group to push similar product content. However, in the early stage of the launch of an application product, the number of users is small, and the system can only collect a small amount of user behavior data. Based on this, the above push methods cannot accurately predict the preferences of different users, resulting in inaccurate content push on the platform.

[0004] There is currently no effective solution to the problem that related technologies cannot accurately predict the preferences of different users, resulting in inaccurate content push on the platform. Summary of the invention

[0005] In this embodiment, a method, apparatus, computer device and storage medium for pushing application content are provided to solve the problem in the related art that the preferences of different users cannot be accurately predicted, resulting in inaccurate content push on the platform.

[0006] In a first aspect, a method for pushing application content is provided in this embodiment, and the method includes:

[0007] According to the basic information of each user, build a corresponding user portrait tag dictionary;

[0008] Analyze the characteristic data of each user, and update the user portrait tag dictionary based on the analysis results; the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics;

[0009] Based on the updated user portrait tag dictionary, construct a corresponding user portrait;

[0010] According to the user portrait, corresponding application content is pushed to the user.

[0011] In some embodiments, analyzing the characteristic data of each user and updating the user portrait tag dictionary based on the analysis result includes:

[0012] When it is detected that the real-time emotion feature matches the emotion feature information entered by the user, analyzing the real-time emotion feature; the real-time emotion feature includes the facial expression feature and the acoustic fingerprint feature of the user;

[0013] Based on the analysis result, determining the application content preference of each of the users;

[0014] The user portrait tag dictionary is updated according to the application content preference of the user.

[0015] In some embodiments, when it is detected that the real-time emotional feature matches the emotional feature information entered by the user, analyzing the emotional feature data; and determining the application content preference of each user based on the analysis result, includes:

[0016] When it is detected that the facial expression feature matches the facial feature information entered by the user, converting the facial expression feature into a corresponding feature parameter;

[0017] Matching the characteristic parameters with a preset facial emotion library to obtain the emotional changes caused by the user operating the current application;

[0018] According to the emotion change, the application content preference of each of the users is determined.

[0019] In some embodiments, when it is detected that the real-time emotional feature matches the emotional feature information entered by the user, analyzing the emotional feature data; and determining the application content preference of each user based on the analysis result, includes:

[0020] When it is detected that the acoustic fingerprint feature matches the voiceprint feature information entered by the user, converting the acoustic fingerprint feature into a corresponding feature parameter;

[0021] Matching the characteristic parameters with a preset voiceprint emotion library to obtain the emotion changes caused by the user operating the current application;

[0022] According to the emotion change, the application content preference of each of the users is determined.

[0023] In some embodiments, analyzing the characteristic data of each user and updating the user portrait tag dictionary based on the analysis result includes:

[0024] Analyzing the operation behavior data and the application evaluation data of each user;

[0025] Based on the analysis result, determining the application content preference of each of the users;

[0026] The user portrait tag dictionary is updated according to the application content preference of the user.

[0027] In some of the embodiments, constructing a corresponding user portrait tag dictionary based on basic information of each user includes:

[0028] Obtaining basic information entered by each user; the basic information includes the user's personal identity information and tags of interest;

[0029] According to the personal identity information and interest tags of each user, a corresponding user portrait tag dictionary is constructed.

[0030] In some of the embodiments, after pushing the corresponding application content to the user according to the user portrait, the method further includes:

[0031] Calculating similarities between the users based on the application content uploaded by each of the users;

[0032] Determining similar users associated with each of the users according to the similarities between the users;

[0033] Push the application content published by the corresponding similar user to each of the users.

[0034] In a second aspect, an application content push device is provided in this embodiment, the device comprising: a construction module, an update module, a characterization module and a push module;

[0035] The construction module is used to construct a corresponding user portrait tag dictionary based on the basic information of users on each platform;

[0036] The updating module is used to analyze the characteristic data of each platform user and update the user portrait tag dictionary based on the analysis results; the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics;

[0037] The characterization module is used to construct a corresponding user portrait based on the updated user portrait tag dictionary;

[0038] The push module is used to push corresponding application content to the platform user according to the user portrait.

[0039] In a third aspect, a computer device is provided in this embodiment, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the application content push method described in the first aspect when executing the computer program.

[0040] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the application content push method described in the first aspect is implemented.

[0041] Compared with the related art, the application content push method, apparatus, computer equipment and storage medium provided in this embodiment build a corresponding user portrait tag dictionary based on the basic information of each user; analyze the characteristic data of each user, and update the user portrait tag dictionary based on the analysis results; wherein the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics; further, based on the updated user portrait tag dictionary, a corresponding user portrait is built, and according to the user portrait, the corresponding application content is pushed to the user, thereby solving the problem that the preferences of different users cannot be accurately predicted, resulting in inaccurate content push on the platform, and achieving accurate prediction of the preferences of different users and improving the accuracy of content push.

[0042] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 This is a hardware structure block diagram of a terminal device of an application content push method provided in an embodiment of the present application;

[0045] Figure 2 is a flow chart of an application content push method provided by an embodiment of the present application;

[0046] Figure 3 This is a flow chart of application content push provided by an embodiment of the present application;

[0047] Figure 4 This is a flow chart of an application content push method provided by a preferred embodiment of the present application;

[0048] Figure 5 It is a structural block diagram of an application content push device provided in one embodiment of the present application.

[0049] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 10, construction module; 20, update module; 30, characterization module; 40, push module. DETAILED DESCRIPTION

[0050] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0051] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0052] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the application content push method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0053] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the application content push method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0054] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0055] In this embodiment, a method for pushing application content is provided. Figure 2 is a flow chart of the application content push method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0056] Step S210, constructing a corresponding user portrait tag dictionary based on the basic information of each user.

[0057] Specifically, the user portrait tag dictionary is used to establish and manage user portraits, which contains tag words related to user characteristics, needs, behaviors, etc. to accurately describe the characteristics of each user, such as age, gender, interests and hobbies.

[0058] In this embodiment, the basic information entered by each user when registering on the application platform is obtained, and the basic information includes the user's personal identity information and tags of interest. Based on the basic information of each user, an initial user portrait tag dictionary is constructed.

[0059] Step S220, analyzing the characteristic data of each user, and updating the user portrait tag dictionary based on the analysis results; the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics.

[0060] Specifically, characteristic data of each user is obtained, which includes one or more combinations of user's operation behavior data, application evaluation data and real-time emotional characteristics. Among them, the operation behavior data is the magnetic resonance application (or other medical imaging applications, such as CT applications, PET applications, etc.) uploaded by the user to the platform and its application description, application label and other related data, and the application description includes the introduction of magnetic resonance application and application example diagram, etc.; the application evaluation data is the user's subjective comments on various magnetic resonance applications on the platform and the Emoji expressions used in the comments, etc.; and the real-time emotional characteristics are the user's facial expression characteristics and acoustic fingerprint characteristics collected by the system within the scope of the authority permitted by the user with the authorization of the user.

[0061] Based on the above different categories of feature data, the feature data of each user is processed in different ways to accurately and comprehensively update the user portrait tag dictionary. First, the operation behavior data and application evaluation data of each user can be analyzed, and the application content preference of each user can be determined based on the analysis results, and the user portrait tag dictionary can be updated according to the user's application content preference.

[0062] In addition, when it is detected that the real-time emotional features match the emotional feature information entered by the user, the real-time emotional features are analyzed, and the application content preference of each user is determined based on the analysis results, and the user portrait tag dictionary is updated according to the user's application content preference.

[0063] Step S230: construct a corresponding user portrait based on the updated user portrait tag dictionary.

[0064] Specifically, the user portrait tag dictionary contains tag words used to describe user characteristics, needs, behaviors, etc. By analyzing the tag words associated with each user in the user portrait tag dictionary, all users are divided into different categories of user groups. The user portrait of each user group contains the key characteristics, content preferences, etc. of the group, so as to comprehensively and clearly describe different user groups.

[0065] It should be noted that the user portrait is a labeled user model abstracted from information such as user attributes and user behaviors. It comprehensively describes the target user group based on the various tag words in the user portrait tag dictionary. It is used to represent the common characteristics and behavior patterns of the target user group, and can deeply understand and predict user needs or preferences, including predicting application content that users are interested in.

[0066] Step S240: Push corresponding application content to the user based on the user portrait.

[0067] Specifically, based on the updated user portrait tag dictionary, after drawing the user portrait, the application content that the user is interested in is accurately pushed to each user according to the user portrait; or based on the application content uploaded to the platform by each user, the similarity between different users is calculated, and based on the similarity between users, similar users associated with each user are determined, so that application content posted by similar users can be pushed to each user.

[0068] In the era of big data, information overload has become a normal problem. Users need to face and process a large amount of data in various application platforms. It is impossible to quickly and accurately obtain the content they need by relying on personal browsing. In order to solve the above problems, application platforms usually use content push systems to enable users to receive application content of interest. The existing push methods include content push based on user behavior data, such as user stay time, search information and favorite content, etc.; or based on each user's preferences, find similar users in the user group to push similar product content. However, in the early stage of the launch of the application product, the number of users is small, and the system can only collect a small amount of user behavior data.

[0069] Based on this, the above push method cannot accurately predict the preferences of different users, resulting in inaccurate content push on the platform. Compared with the prior art, this application constructs a user portrait tag dictionary based on the user's basic information, and selects the user's feature data as the basis for updating the user portrait tag dictionary. Among them, the feature data is various subjective data provided by the user, including operation behavior data, application evaluation data, and real-time emotional characteristics. By analyzing a large amount of subjective data, the user's application content preference can be accurately obtained for tag dictionary update, and then a comprehensive and reliable user portrait is constructed to improve the accuracy of subsequent content push.

[0070] Through this embodiment, a corresponding user portrait tag dictionary is constructed based on the basic information of each user; the feature data of each user is analyzed, and the user portrait tag dictionary is updated based on the analysis results; wherein the feature data includes operation behavior data, application evaluation data, and real-time emotional features; further, based on the updated user portrait tag dictionary, a corresponding user portrait is constructed, and based on the user portrait, the corresponding application content is pushed to the user, thereby solving the problem of inaccurate content push caused by the inability to accurately predict the preferences of different users, and achieving accurate prediction of the preferences of different users, thereby improving the accuracy of content push.

[0071] In some embodiments, the characteristic data of each user is analyzed, and based on the analysis results, the user portrait tag dictionary is updated, including the following steps:

[0072] Step S221, when it is detected that the real-time emotion feature matches the emotion feature information entered by the user, the real-time emotion feature is analyzed; the real-time emotion feature includes the user's facial expression feature and acoustic fingerprint feature;

[0073] Step S222, determining the application content preference of each user based on the analysis result;

[0074] Step S223, updating the user portrait tag dictionary according to the user's application content preference.

[0075] Specifically, when a user successfully registers a personal account on the application platform and obtains the user's authorization, the system collects the user's emotional feature information within the scope of permission, including facial feature information and voiceprint feature information. For example, the user enters facial posture data and voiceprint fluctuation data under different emotions.

[0076] After the collection is completed, the collected facial feature information and voiceprint feature information will be bound to the corresponding user personal account to initialize the record of the user's facial information and voiceprint information as identity matching conditions and sentiment analysis references in the subsequent analysis process.

[0077] Furthermore, with the knowledge and authorization of the user, the real-time emotional characteristics of the user when browsing or using the platform application are captured using a device for collecting user emotional characteristics, and the real-time emotional characteristics are matched with the emotional characteristic information initially entered by the user. If it is detected that the real-time emotional characteristics match the emotional characteristic information initially entered by the user, the collected real-time emotional characteristics are analyzed to determine the application content preferences of each user, and the user portrait tag dictionary is updated according to the user's application content preferences.

[0078] Through this embodiment, when it is detected that the real-time emotional features match the emotional feature information entered by the user, the real-time emotional features are analyzed; the real-time emotional features include the user's facial expression features and acoustic fingerprint features, and based on the analysis results, the application content preferences of each user are determined, so that the user portrait tag dictionary can be accurately updated according to the user's application content preferences.

[0079] In some of the embodiments, when it is detected that the real-time emotion feature matches the emotion feature information entered by the user, the emotion feature data is analyzed; and based on the analysis result, the application content preference of each user is determined, including the following steps:

[0080] When it is detected that the facial expression feature matches the facial feature information entered by the user, the facial expression feature is converted into a corresponding feature parameter;

[0081] Match the feature parameters with the preset facial emotion library to obtain the emotional changes caused by the user operating the current application;

[0082] Determine each user's app content preferences based on sentiment changes.

[0083] Specifically, with the user's knowledge and authorization, the facial expression features of the user when browsing or using the platform application are captured by an imaging device, and expression parameters are extracted from the collected facial expression features through a data acquisition module to match the facial feature information entered by the user. If the facial expression features are detected to match the facial feature information entered by the user, it means that the user currently using the platform application has passed the account verification, and then each set of facial expression features is converted into corresponding feature parameters using a data analysis module, and the feature parameters are matched with a preset facial emotion library to obtain the emotional changes caused by the user operating the current application.

[0084] It should be noted that the facial emotion library in the above data analysis module is a database for detecting and identifying facial expressions. It is obtained by machine learning training of a large number of facial images and corresponding emotion labels, and contains facial posture emotion parameters corresponding to various races, age groups and different genders. Among them, the facial posture emotion parameters include information on facial shape, skin color, eyes, mouth and other areas under different emotion labels.

[0085] Furthermore, the feature parameters are matched with the facial gesture emotion parameters in the facial emotion library, so as to determine the emotional changes caused by the user operating the current application based on the matching results. For example, when the user uses different platform applications, he or she may show emotions such as happiness, excitement, frustration or boredom. At the same time, the facial feature information initially entered by the user can be used as reference information to determine the emotional changes caused by the user browsing or using the platform application.

[0086] Through this embodiment, when it is detected that the facial expression features match the facial feature information entered by the user, the facial expression features are converted into corresponding feature parameters, and the feature parameters are matched with the preset facial emotion library to obtain the emotional changes caused by the user operating the current application, thereby accurately judging the degree of preference of each user for different application content based on the emotional changes.

[0087] In some of the embodiments, when it is detected that the real-time emotion feature matches the emotion feature information entered by the user, the emotion feature data is analyzed; and based on the analysis result, the application content preference of each user is determined, including the following steps:

[0088] When it is detected that the acoustic fingerprint feature matches the voiceprint feature information entered by the user, the acoustic fingerprint feature is converted into a corresponding feature parameter;

[0089] Match the characteristic parameters with the preset voiceprint emotion library to obtain the emotional changes caused by the user operating the current application;

[0090] Determine each user's app content preferences based on sentiment changes.

[0091] Specifically, with the user's knowledge and authorization, the voiceprint recognition device is used to capture the acoustic fingerprint features of the user when browsing or using the platform application, and the voiceprint parameters are extracted from the collected acoustic fingerprint features through the data acquisition module to match the voiceprint feature information entered by the user. If the acoustic fingerprint features are detected to match the voiceprint feature information entered by the user, it means that the user currently using the platform application has passed the account verification, and then the data analysis module is used to convert each set of acoustic fingerprint features into corresponding feature parameters, and the feature parameters are matched with the preset voiceprint emotion library to obtain the emotional changes caused by the user operating the current application.

[0092] It is important to know that the voiceprint emotion library in the above data analysis module is a database used to detect and identify acoustic fingerprints. It is obtained by training a large amount of sound data and corresponding emotion labels through machine learning, and contains voiceprint emotion parameters corresponding to various races, age groups and genders. Among them, the voiceprint emotion parameters include the fundamental frequency of the sound under different emotion labels, the duration and energy of the sound, etc.

[0093] Furthermore, the above characteristic parameters are matched with the voiceprint emotion parameters in the voiceprint emotion library, so as to determine the emotional changes caused by the user operating the current application according to the matching results. At the same time, the voiceprint characteristic information initially entered by the user can be used as reference information to determine the emotional changes caused by the user browsing or using the platform application.

[0094] Through this embodiment, when it is detected that the acoustic fingerprint feature matches the voiceprint feature information entered by the user, the acoustic fingerprint feature is converted into corresponding feature parameters, and the feature parameters are matched with the preset voiceprint emotion library to obtain the emotional changes caused by the user operating the current application, so as to accurately judge the preference of each user for different application content based on the emotional changes.

[0095] In some embodiments, the characteristic data of each user is analyzed, and based on the analysis results, the user portrait tag dictionary is updated, including the following steps:

[0096] Step S221, analyzing the operation behavior data and application evaluation data of each user;

[0097] Step S222, determining the application content preference of each user based on the analysis result;

[0098] Step S223, updating the user portrait tag dictionary according to the user's application content preference.

[0099] It is important to know that the operational behavior data refers to the magnetic resonance applications uploaded by users to the platform and their application descriptions, application tags and other related data; the application description includes relevant introductions to the magnetic resonance applications and application example diagrams, etc.; and the application evaluation data refers to users' subjective comments on various magnetic resonance applications on the platform and Emoji expressions used in comments, etc., and the application evaluation data includes text type data and image type data.

[0100] When a user uploads an MRI application to the platform, the data collection module extracts the application description, application tags and other data of the MRI application, and the data analysis module analyzes and processes the extracted data, thereby determining the degree of preference of each user for various application contents based on the analysis results, so as to accurately update the user portrait tag dictionary. Among them, the application description includes the relevant introduction of the MRI application and application example diagrams.

[0101] In addition, the data collection module can be used to obtain users' personal comments on various platform applications, as well as data such as Emoji expressions used in comments, and the data analysis module can be used to analyze and process the obtained data. Based on the analysis results, the degree of preference of each user for various application content can be determined to accurately update the user portrait tag dictionary.

[0102] Among them, the above-mentioned data analysis module can be a machine learning model for sentiment analysis based on text type data, which is used to analyze, process, summarize and reason subjective texts with emotional colors, and use deep learning to extract users' emotional attitudes towards different application contents. Exemplarily, the subjective text provided by the user is disassembled into multiple single sentences, and the words appearing in each single sentence are analyzed and matched with the sentiment dictionary, while paying attention to the logical relationships such as selection, negation and transition contained in the text. Finally, the sentiment score of each word is weighted and summed according to the conditions such as the frequency of word occurrence and the sentiment polarity of the word, and the sentiment score of the whole text is obtained, so that the user's emotional tendency can be output based on the sentiment score of the whole text, that is, the degree of preference of the user for different application contents can be represented.

[0103] Through this embodiment, the operation behavior data and application evaluation data of each user are analyzed, and based on the analysis results, the application content preference of each user is determined. Then, according to the user's application content preference, the user portrait tag dictionary is updated to improve the accuracy of user tag words.

[0104] In some of the embodiments, a corresponding user portrait tag dictionary is constructed according to the basic information of each user, including the following steps:

[0105] Step S211, obtaining basic information entered by each user; the basic information includes the user's personal identity information and tags of interest;

[0106] Step S212, constructing a corresponding user portrait tag dictionary based on each user's personal identity information and interest tags.

[0107] Specifically, the basic information entered by each user when registering on the application platform is obtained, and the basic information includes the user's personal identity information and tags of interest, and based on the basic information of each user, an initial user portrait tag dictionary is constructed.

[0108] Among them, personal identity information includes user age, user gender, user occupation, etc. Interest tags can be set according to actual user needs; for example, based on the application field of magnetic resonance, they can be divided into clinical medicine and scientific research, etc., or based on the disease categories involved in magnetic resonance applications, interest tags can be set including gynecology, cardiovascular medicine, and liver diseases, etc.

[0109] Through this embodiment, the basic information entered by each user is obtained, and the basic information includes the user's personal identity information and interest tags. Based on the personal identity information and interest tags of each user, a user portrait tag dictionary is constructed to facilitate the subsequent drawing of user portraits of each user based on the user portrait tag dictionary.

[0110] In some of the embodiments, after pushing corresponding application content to the user according to the user portrait, the following steps are included:

[0111] Step S251, calculating the similarity between users based on the application content uploaded by each user;

[0112] Step S252, determining similar users associated with each user based on the similarity between the users;

[0113] Step S253: Pushing application content published by corresponding similar users to each user.

[0114] Specifically, based on the magnetic resonance application-related content uploaded by each user to the platform, the similarity between different users is calculated, and the similarity measurement methods include but are not limited to cosine similarity and Pearson correlation coefficient. Among them, a higher similarity between users indicates that the application content that the users are interested in is closer.

[0115] Furthermore, users with higher similarity are selected as associated similar users, each user is recommended to follow similar users associated with himself, and application content published by the corresponding similar users is pushed to each user.

[0116] Through this embodiment, based on the application content uploaded by each user, the similarity between users is calculated, and based on the similarity between users, similar users associated with each user are determined, so that application content published by similar users is pushed to each user, so that users can accurately receive the content of interest.

[0117] Figure 3 FIG. 1 is a flow chart of the application content push method of this embodiment. Figure 3 As shown, the specific process of the application content push method includes the following steps:

[0118] Step S301, construct an initial user portrait tag dictionary based on the basic information entered by each user, and the basic information includes the user's personal identity information and interest tags; step S302, and bind the facial feature information and voiceprint feature information entered by the user to the user's personal account; step S303, when the user uploads the magnetic resonance application to the platform, the user's operation behavior data is obtained through the data acquisition module, that is, the application description, application label and other data of the magnetic resonance application are extracted; step S304, obtain the user's subjective comments on various magnetic resonance applications on the platform and application evaluation data such as Emoji expressions used in the comments.

[0119] Step S305, with the user's knowledge and authorization, obtain the user's real-time emotional characteristics, and use an imaging device to capture the user's facial expression characteristics when browsing or using platform applications; Step S306, use a voiceprint recognition device to capture the acoustic fingerprint characteristics of the user when browsing or using platform applications; Step S307, through the data acquisition module, extract parameters from the collected facial expression characteristics and acoustic fingerprint characteristics, and match them with the facial feature information and voiceprint feature information initially entered by the user, respectively. If the user's facial expression characteristics and acoustic fingerprint characteristics match the user account, it indicates that the user account verification has passed, and the currently collected real-time emotional characteristics can be used to update the user portrait tag dictionary.

[0120] Step S308, analyzing and processing the collected operation behavior data, application evaluation data, and facial expression features and acoustic fingerprint features of users when browsing or using platform applications through the data analysis module to obtain each user's preference for different application content; Step S309, updating the initial user portrait tag dictionary according to the user's application content preference; Step S310, accurately drawing the user portrait corresponding to each user based on the updated user portrait tag dictionary, and then accurately pushing the application content of interest to each user based on the user portrait.

[0121] The present embodiment is described and illustrated below through preferred embodiments.

[0122] Figure 4 is a flow chart of the application content push method of this preferred embodiment. Figure 4 As shown, the application content push method includes the following steps:

[0123] Step S410, obtaining basic information entered by each user; the basic information includes personal identity information and tags of interest;

[0124] Step S420, constructing a corresponding user portrait tag dictionary based on the personal identity information and interest tags of each user;

[0125] Step S430, when it is detected that the real-time emotion feature matches the emotion feature information entered by the user, the real-time emotion feature is analyzed; the real-time emotion feature includes the user's facial expression feature and acoustic fingerprint feature;

[0126] Step S440, determining the application content preference of each user based on the analysis result;

[0127] Step S450, updating the user portrait tag dictionary according to the user's application content preference;

[0128] Step S460, constructing a corresponding user portrait based on the updated user portrait tag dictionary;

[0129] Step S470: Push corresponding application content to the user based on the user portrait.

[0130] Through this embodiment, an initial user portrait tag dictionary is constructed based on each user's personal identity information and interest tags, and when it is detected that the user's real-time emotional features match the emotional feature information initially entered by the user, the user's facial expression features and acoustic fingerprint features in the real-time emotional features are analyzed to accurately obtain each user's application content preferences. Further, the user portrait tag dictionary is updated according to the user's application content preferences, and based on the updated user portrait tag dictionary, an accurate and comprehensive user portrait is drawn, so that the application content of interest to the user can be pushed to the user based on the user portrait, solving the problem of inaccurate content push on the platform due to the inability to accurately predict the preferences of different users, and effectively improving the accuracy of application content push.

[0131] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0132] In this embodiment, an application content push device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0133] Figure 5 is a structural block diagram of the application content push device of this embodiment, such as Figure 5 As shown, the device includes: a construction module 10, an update module 20, a characterization module 30 and a push module 40;

[0134] A construction module 10 is used to construct a corresponding user portrait tag dictionary based on the basic information of users on each platform;

[0135] An updating module 20 is used to analyze the characteristic data of each platform user and update the user portrait tag dictionary based on the analysis results; the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics;

[0136] A characterization module 30, configured to construct a corresponding user portrait based on the updated user portrait tag dictionary;

[0137] The push module 40 is used to push corresponding application content to platform users based on user portraits.

[0138] Through the device provided by this embodiment, a corresponding user portrait tag dictionary is constructed according to the basic information of each platform user; the feature data of each platform user is analyzed, and the user portrait tag dictionary is updated based on the analysis result; wherein the feature data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional features; further, based on the updated user portrait tag dictionary, a corresponding user portrait is constructed, and according to the user portrait, the corresponding application content is pushed to the platform user, thereby solving the problem that the preferences of different users cannot be accurately predicted, resulting in inaccurate content push on the platform, and achieving accurate prediction of the preferences of different users and improving the accuracy of content push.

[0139] In some of these embodiments, Figure 5 On the basis of, the device also includes a first matching module, which is used to analyze the real-time emotional features when it is detected that the real-time emotional features match the emotional feature information entered by the user; the real-time emotional features include the user's facial expression features and acoustic fingerprint features; based on the analysis results, determine the application content preference of each user; according to the user's application content preference, update the user portrait tag dictionary.

[0140] In some of these embodiments, Figure 5 On the basis of this, the device also includes a second matching module, which is used to convert the facial expression features into corresponding feature parameters when it is detected that the facial expression features match the facial feature information entered by the user; match the feature parameters with a preset facial emotion library to obtain the emotional changes caused by the user operating the current application; and determine the application content preference of each user based on the emotional changes.

[0141] In some of these embodiments, Figure 5 On the basis of this, the device also includes a third matching module, which is used to convert the acoustic fingerprint features into corresponding feature parameters when it is detected that the acoustic fingerprint features match the voiceprint feature information entered by the user; match the feature parameters with a preset voiceprint emotion library to obtain the emotional changes caused by the user operating the current application; and determine the application content preference of each user based on the emotional changes.

[0142] In some of these embodiments, Figure 5 On the basis of, the device also includes an analysis module for analyzing the operation behavior data and application evaluation data of each user; based on the analysis results, determining the application content preference of each user; and updating the user portrait tag dictionary according to the user's application content preference.

[0143] In some of these embodiments, Figure 5On the basis of, the device also includes a creation module for obtaining basic information entered by each user; the basic information includes the user's personal identity information and interest tags; according to the personal identity information and interest tags of each user, a corresponding user portrait tag dictionary is constructed.

[0144] In some of these embodiments, Figure 5 On the basis of, the device also includes an association module, which is used to calculate the similarity between users based on the application content uploaded by each user; determine the similar users associated with each user according to the similarity between the users; and push the application content published by the corresponding similar users to each user.

[0145] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0146] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0147] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0148] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0149] In addition, in combination with the application content push method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the application content push methods in the above embodiments is implemented.

[0150] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0151] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0152] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0153] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for pushing application content, characterized in that: The method comprises: According to the basic information of each user, build a corresponding user portrait tag dictionary; Analyze the characteristic data of each user, and update the user portrait tag dictionary based on the analysis results; the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics; Based on the updated user portrait tag dictionary, construct a corresponding user portrait; According to the user portrait, corresponding application content is pushed to the user.

2. The method for pushing application content according to claim 1, characterized in that: The analyzing the characteristic data of each user and updating the user portrait tag dictionary based on the analysis result includes: When it is detected that the real-time emotion feature matches the emotion feature information entered by the user, analyzing the real-time emotion feature; the real-time emotion feature includes the facial expression feature and the acoustic fingerprint feature of the user; Based on the analysis result, determining the application content preference of each of the users; The user portrait tag dictionary is updated according to the application content preference of the user.

3. The method for pushing application content according to claim 2, characterized in that: When it is detected that the real-time emotional feature matches the emotional feature information entered by the user, analyzing the emotional feature data; Based on the analysis result, determining the application content preference of each user includes: When it is detected that the facial expression feature matches the facial feature information entered by the user, converting the facial expression feature into a corresponding feature parameter; Matching the characteristic parameters with a preset facial emotion library to obtain the emotional changes caused by the user operating the current application; According to the emotion change, the application content preference of each of the users is determined.

4. The method for pushing application content according to claim 2, characterized in that: When it is detected that the real-time emotional feature matches the emotional feature information entered by the user, analyzing the emotional feature data; Based on the analysis result, determining the application content preference of each user includes: When it is detected that the acoustic fingerprint feature matches the voiceprint feature information entered by the user, converting the acoustic fingerprint feature into a corresponding feature parameter; Matching the characteristic parameters with a preset voiceprint emotion library to obtain the emotion changes caused by the user operating the current application; According to the emotion change, the application content preference of each of the users is determined.

5. The method for pushing application content according to claim 1, characterized in that: The analyzing the characteristic data of each user and updating the user portrait tag dictionary based on the analysis result includes: Analyzing the operation behavior data and the application evaluation data of each user; Based on the analysis result, determining the application content preference of each of the users; The user portrait tag dictionary is updated according to the application content preference of the user.

6. The method for pushing application content according to claim 1, characterized in that: The method of constructing a corresponding user portrait tag dictionary based on the basic information of each user includes: Obtaining basic information entered by each user; the basic information includes the user's personal identity information and tags of interest; According to the personal identity information and interest tags of each user, a corresponding user portrait tag dictionary is constructed.

7. The method for pushing application content according to claim 1, characterized in that: After pushing the corresponding application content to the user according to the user portrait, the method includes: Calculating similarities between the users based on the application content uploaded by each of the users; Determining similar users associated with each of the users according to the similarities between the users; Push the application content published by the corresponding similar user to each of the users.

8. An application content push device, characterized in that: The device comprises: a construction module, an update module, a characterization module and a push module; The construction module is used to construct a corresponding user portrait tag dictionary based on the basic information of users on each platform; The updating module is used to analyze the characteristic data of each platform user and update the user portrait tag dictionary based on the analysis results; the characteristic data includes one or more combinations of operation behavior data, application evaluation data and real-time emotional characteristics; The characterization module is used to construct a corresponding user portrait based on the updated user portrait tag dictionary; The push module is used to push corresponding application content to the platform user according to the user portrait.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the steps of the application content pushing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the application content pushing method described in any one of claims 1 to 7 are implemented.

Images