Information processing method and device, electronic equipment and readable medium

Abstract

An information processing method, device, equipment and medium, the method comprises: generating feature data of a plurality of business objects in T time periods according to the use of the plurality of business objects in the T time periods for navigating a service icon; generating a first input vector according to the feature data of the plurality of business objects in the T time periods; estimating the feature data of the T+2 time period according to the feature data of the T-1 time periods before the T time period, and generating a second input vector according to the feature data of the T+2 time period; predicting the prediction probability of the navigation service for displaying the icon corresponding to each business object in the T+1 time period according to the mapping relationship between the feature data of the business object use and the navigation service for displaying the business object icon through the first input vector and the second input vector; and determining a target business object from the plurality of business objects according to the prediction probability of each business object. The method can improve the accuracy of information processing.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly to an information processing method, apparatus, electronic device, and readable medium. Background Technology

[0002] With the development of mobile devices and mobile networks, people are increasingly relying on map navigation software for driving. Navigation information in navigation software often includes navigation objects, which are typically icons or markers used to indicate the current vehicle.

[0003] In related technologies, map navigation software sorts icons related to the input key information and recommends suitable icons for selection based on the sorting results.

[0004] However, the recommendation process described above relies on a pre-built matching relationship between business and business objects for ranking. Therefore, the ranking results provided are difficult to reflect changes in preferences for icons or tags, which reduces the degree of matching between the provided icons and actual preferences, thus affecting the accuracy of information processing. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides an information processing method to improve the matching degree between displayed icons and actual preferences, thereby enhancing the accuracy of information processing.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to one aspect of the embodiments of this application, an information processing method, apparatus, electronic device, and readable medium are provided, including:

[0008] Based on the use of navigation service icons by multiple business objects over T time periods, feature data of multiple business objects over T time periods is generated, where T is an integer greater than 0;

[0009] A first input vector is generated based on the feature data of the multiple business objects in the Tth time period;

[0010] Based on the feature data of the multiple business objects in the T-1 time period before the T-th time period, the feature data of the T+2 time period is estimated, and a second input vector is generated based on the feature data of the T+2 time period.

[0011] Based on the mapping relationship between the feature data of the usage of business objects and the icons of the business objects displayed by the navigation service, the predicted probability of the navigation service displaying the corresponding icons of each business object in the T+1 time period is predicted by the first input vector and the second input vector.

[0012] Based on the predicted probability of each business object, a target business object is determined from the plurality of business objects, so that the icon corresponding to the target business object is displayed in the navigation service in the T+1 time period.

[0013] According to one aspect of the embodiments of this application, an information processing apparatus is provided, comprising:

[0014] The feature generation module is used to generate feature data of multiple business objects in T time periods based on the use of navigation service icons by multiple business objects in T time periods, where T is an integer greater than 0.

[0015] The first vector generation module is used to generate a first input vector based on the feature data of the multiple business objects in the Tth time period;

[0016] The second vector generation module is used to estimate the feature data of the T+2 time period based on the feature data of the multiple business objects in the T-1 time period before the T-th time period, and generate a second input vector based on the feature data of the T+2 time period.

[0017] The prediction module is used to predict the probability that the navigation service will display the corresponding icon of each business object in the T+1 time period based on the mapping relationship between the feature data of the usage of the business object and the icon of the business object displayed by the navigation service, using the first input vector and the second input vector.

[0018] The object determination module is used to determine the target business object from the plurality of business objects based on the predicted probability of each business object, so as to display the icon corresponding to the target business object in the navigation service in the T+1 time period.

[0019] In some embodiments of this application, based on the above technical solutions, the prediction module includes:

[0020] The model prediction unit is used to make predictions based on the first input vector and the second input vector using a trained probability prediction model to obtain a multi-class probability vector, wherein the multi-class probability vector includes the predicted probability that the navigation service will display the corresponding icons of each business object in the T+1 time period.

[0021] In some embodiments of this application, based on the above technical solutions, the information processing apparatus further includes:

[0022] The sample acquisition module is used to acquire object feature samples of each business object in a preset business database. The object feature samples include training sample sequences and test sample sequences.

[0023] The model training module is used to train a preset probability prediction model based on the object feature samples to obtain the trained probability prediction model.

[0024] In some embodiments of this application, based on the above technical solutions, the sample acquisition module includes:

[0025] The feature acquisition unit is used to acquire usage data and feature data of multiple business objects in the T time periods from the preset business database;

[0026] The tag generation unit is used to generate tag data for the multiple business objects in the T time periods based on the usage data of the multiple business objects;

[0027] The sample generation unit is used to generate object feature samples of the multiple business objects based on the feature data of the multiple business objects in the T time periods and the tag data.

[0028] In some embodiments of this application, based on the above technical solutions, the sample generation unit includes:

[0029] The sample combination subunit is used to combine the feature data of the TM-th time period with the label data of the T-M+1-th time period to form the sample data of the TM-th time period, thereby obtaining the sample data of the T-1-th time period, where M is an integer greater than 0 and less than T.

[0030] The data partitioning subunit is used to divide the sample data of the T-1 time periods into training samples and test samples according to a preset ratio, so as to obtain the training sample sequence and test sample sequence of the multiple business objects, which serve as object feature samples.

[0031] In some embodiments of this application, based on the above technical solutions, the model training module includes:

[0032] The model training unit is used to train the preset probability prediction model based on the training samples and test samples of the object feature samples for T-1 time periods, respectively, to obtain T-1 sets of model parameters.

[0033] The mean calculation unit is used to calculate the mean value of each model parameter based on the T-1 group of model parameters;

[0034] The parameter import unit is used to import the mean values ​​of the various parameters into a preset probability prediction model to obtain the trained probability prediction model.

[0035] In some embodiments of this application, based on the above technical solutions, the preset probability prediction model includes a hidden layer; the parameter import unit includes:

[0036] The first processing subunit is used to obtain T hidden layer vectors corresponding to T time periods by processing the hidden layer of a preset probability prediction model based on the T-1 set of model parameters and the object feature samples.

[0037] The hidden layer vector determination subunit is used to determine the hidden layer vector for the (T+2)th time period based on the T-1 hidden layer vectors.

[0038] The parameter configuration unit is used to configure the hidden layer according to the mean value of each parameter, the hidden layer vector of the (T+2)th time period, and the hidden layer vector of the Tth time period, so as to obtain the trained probability prediction model.

[0039] In some embodiments of this application, based on the above technical solutions, the model prediction unit includes:

[0040] The hidden layer subunit is used to obtain the hidden layer vector of the (T+1)th time period by processing the first input vector and the second input vector through the trained probability prediction model.

[0041] The probability prediction subunit is used to calculate the predicted probability corresponding to each business object based on the hidden layer vector of the (T+1)th time period through the trained probability prediction model, so as to obtain a multi-class probability vector.

[0042] In some embodiments of this application, based on the above technical solutions, the feature generation module includes:

[0043] A login information acquisition unit is used to acquire the login information of the navigation service;

[0044] A business data filtering unit is used to filter out business data of each target business associated with the login information in the T time periods from a preset business database;

[0045] The feature extraction unit is used to extract features from the business objects contained in the business data of each target business in the T time periods, and use them as business information for the navigation business.

[0046] In some embodiments of this application, based on the above technical solutions, the second vector generation module includes:

[0047] The feature mean calculation unit is used to calculate the feature mean of the corresponding feature in the feature data of the first T-1 time periods for each feature in the second input vector.

[0048] The estimation unit is used to take the mean of each feature as the estimated value of the feature in the (T+2)th time period to obtain the second input vector.

[0049] In some embodiments of this application, based on the above technical solutions, the object determination module includes:

[0050] The target business object determination unit is used to determine the target business object to be displayed based on the predicted probabilities of each business object included in the multi-class probability vector.

[0051] The icon replacement unit is used to replace the navigation icon of the navigation service with the object icon of the target service object.

[0052] According to one aspect of the embodiments of this application, an electronic device is provided, the electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the information processing method as described above by executing the executable instructions.

[0053] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the information processing method as described in the above technical solutions.

[0054] According to one aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information processing methods provided in the various optional implementations described above.

[0055] In the embodiments of this application, when determining the icon to be displayed in the (T+1)th time period, feature data for the (T+2)th time period is generated based on the feature data of the previous (T-1)th time period. Then, the icon to be displayed in the (T+1)th time period is determined based on the feature data of the (T)th and (T+2)th time periods. This allows the determined target business object to take into account the bidirectional influence of the current time period context, which is beneficial for reflecting the preference changes for each icon or mark in the feature data, thereby improving the matching degree between the displayed icon and the actual preference and improving the accuracy of information processing.

[0056] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0058] In the attached diagram:

[0059] Figure 1 This is a schematic diagram of an implementation environment in one of the embodiments of this application;

[0060] Figure 2 This is a schematic flowchart illustrating the overall solution in the embodiments of this application;

[0061] Figure 3 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0062] Figure 4 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0063] Figure 5 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0064] Figure 6 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0065] Figure 7 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0066] Figure 8 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0067] Figure 9 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0068] Figure 10 This is a schematic flowchart of an information processing method according to an embodiment of this application;

[0069] Figure 11 A schematic block diagram of the information processing apparatus in an embodiment of this application is shown.

[0070] Figure 12 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0071] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0072] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0073] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0074] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0075] It should be understood that the solution in this application can be applied to map applications, specifically to scenarios where map applications modify or replace icons used in navigation services. In the navigation service of a map application, when a user begins navigation, the client or application displays navigation information on the interface and shows an icon to indicate the client's current location. This icon is typically an arrow, indicating the direction of travel. Using the solution in this application, the map application's navigation service obtains related object information from other services such as games based on the map application's login information. Then, based on the object information, it determines the associated business objects, such as game characters used in recently running game applications. Then, based on the icons corresponding to the determined business objects, it replaces the original icons in the navigation service (i.e., arrow icons or other currently used icons) with the icons of the business objects, such as replacing them with game character avatar icons, thereby allowing for personalized customization of navigation icons in the navigation service to enhance the diversity of the navigation display process and the user experience. It is understood that, with relevant authorization and permission, map applications can collect object information from multiple related services and select the most frequently used or most associated business objects based on object access patterns or usage records. This application can also be applied to the Internet of Vehicles (IoV) environment. Specifically, after a map application on an in-vehicle terminal successfully logs in, the terminal can obtain the usage information of each game character in the corresponding game application based on the login information, and then select one or more game characters based on the game application's play history and the usage of each character. Subsequently, when the map application needs to perform navigation services, it will use the icon corresponding to the selected game character as the navigation icon in the navigation service.

[0076] The concept of the Internet of Vehicles (IoV) originates from the Internet of Things (IoT), which uses vehicles in motion as information sensing objects and leverages next-generation information and communication technologies to achieve network connections between vehicles, people, roads, service platforms, etc., thereby improving the overall intelligent driving level of vehicles, providing users with a safe, comfortable, intelligent, and efficient driving experience and transportation services, while improving traffic operation efficiency and enhancing the level of intelligence in social transportation services.

[0077] The technical solution provided in this application will be described in detail below with reference to specific embodiments. Please refer to... Figure 1 , Figure 1This is a schematic diagram of an implementation environment in an embodiment of this application. The implementation environment includes a terminal side and a service side. The terminal side includes a client, an in-vehicle terminal, and a mobile terminal 110, while the service includes a server 120. The terminal side and the service side communicate via a wired or wireless network. The information processing method described in this application can be executed by either the terminal-side device or the server-side device. Specifically, the in-vehicle terminal 110 on the terminal side can obtain the data required for information processing from the server 120. Then, the information processing method provided in this application is executed locally on the in-vehicle terminal 110, thereby applying the icon of the business object provided in the processing result of the information processing method in the navigation service. The server 120 can also run the solution provided in this application. Specifically, when the terminal side starts the navigation service, it requests the server 120 to provide the relevant target business object or its corresponding icon. The server 120 then obtains the required business data from the relevant service server to perform the information processing process, thereby determining the corresponding target business object and providing the target business object or its corresponding icon to the map application for application in the navigation service.

[0078] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. This document does not impose any restrictions on this.

[0079] The vehicle-mounted terminal 110 can be a mobile phone, computer, intelligent voice interaction device, smart home appliance, vehicle-mounted terminal equipment, aircraft, etc., but is not limited to these. The vehicle-mounted terminal 110 and the server 120 can be directly or indirectly connected through wired or wireless communication, which is not limited herein. The number of client 110 and server 120 is also not limited.

[0080] The following section uses the Internet of Vehicles (IoV) as an example to introduce the overall process of the solution in this application. Please refer to [link / reference]. Figure 2 , Figure 2 This is a schematic flowchart illustrating the overall solution in an embodiment of this application. Figure 2As shown, the overall process of the solution includes 10 stages: database construction stage 201, association stage 202, data input stage 203, label construction stage 204, sample construction node 205, model construction stage 206, model training and testing stage 207, comprehensive model construction stage 208, model prediction stage 209, and car logo replacement stage 210. Specifically, in this overall process, the function to be achieved by the solution is to replace the car logo in the navigation service with the icon of the game character with the highest degree of association with the login information of the navigation service in the P+1th time period. Therefore, the database construction stage 201 will build a game service-game character database. This database will include information on various game services that the map service has been authorized to obtain or access, as well as information on business objects such as game characters involved in each game service, such as the icons and descriptions of game characters, the acquisition and transfer status of game virtual resources, and other related content. This database will also contain a mapping data table between game services and game characters, which stores game service identifiers, game names, character images, character names, character identifiers, etc., to facilitate the retrieval of relevant correspondences. In the association phase 202, the map application is associated with the data established in the database construction phase 201 to obtain the necessary information later. Specifically, the login information of the map application can be associated with the corresponding data in the database, allowing the map application to obtain relevant game information. In the data input phase 203, the necessary information is obtained from the database as data input. For example, data for q time periods is typically obtained from the database as needed, such as data from the Pq-th time period to the P-th time period, and features are extracted from this data to obtain feature data from the Pq-th time period to the P-th time period. In the label construction phase 204, the usage information of each game service and corresponding game character obtained in the data input phase 203 is used to label the data, resulting in a multi-class label sequence from the Pq-th time period to the P-th time period, where each label corresponds to a character or a set of characters. Subsequently, in the sample construction node 205, training samples, training test samples, and prediction samples for prediction are divided based on the feature data in the data input phase 203 and the label data in the label construction phase 204. Subsequently, in model building phase 206, a predictive model for prediction is constructed. This model includes hidden layers and an output layer, and it utilizes data from periods P-1 and P+1. It can be understood that the data for period P+1 can be estimated based on the feature data obtained from the q time periods, or, in actual construction, the data from period P+1 can be directly obtained for model building.In the model training and testing phase 207, the constructed prediction model is trained using the training samples and training / test samples obtained in the sample construction node 205, thereby obtaining model parameters for each time period. In the comprehensive model construction phase 208, the model parameters for each time period obtained in the model training and testing phase 207 are comprehensively calculated, for example, by calculating the mean, to obtain the final model parameters used for prediction. Subsequently, in the model prediction phase 209, the model parameters from the model training and testing phase 207 are fed into the prediction model, and the previously obtained test samples from the Pth time period and the calculated samples from the P+2th time period are used as input values ​​to predict the model, thereby obtaining the multi-class probability vector for the use of each game character in the P+1th time period. Finally, in the logo replacement phase 210, the game character with the highest correlation is determined based on the obtained multi-class probability vector, and the navigation icon in the map application is replaced with the icon corresponding to that game character, thus completing the logo replacement process.

[0081] The data analysis methods described in the embodiments of this application are further explained below. Please refer to... Figure 3 , Figure 3 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. This information processing method can run on the server or terminal described above, and is executed by an information processing device on the server or terminal. The method described below will be explained using a server configured with an information processing device as the executing entity. Figure 3 As shown, this information processing method includes at least steps S310 to S350, which are described in detail below:

[0082] Step S310: Based on the use of navigation service icons by multiple business objects in T time periods, generate feature data of multiple business objects in T time periods, where T is an integer greater than 0.

[0083] In this embodiment, the information processing device acquires business information about the navigation service, which includes feature data of multiple business objects over T time periods. A business object is an object that can be used or has been used in the navigation service, such as a virtual character or icon. The information processing device generates feature data for multiple business objects over the T time periods based on their use as navigation service icons. The feature data of a business object describes its usage within that time period, including data such as click characteristics, favorite characteristics, download characteristics, cancel download characteristics, purchase characteristics, usage characteristics, and switching characteristics. Furthermore, the business information typically includes descriptive information about the business objects themselves, such as their name, identifier, and category. The T time periods are determined according to preset rules and are the time periods preceding the execution of the information processing method of this application.

[0084] In one embodiment, the business information of the navigation service may further include business information from other related services. The business objects included in the business information may also originate from business objects of other related services, such as audio / video playback services that have a single sign-on relationship with the navigation service or share login information. Other related services and the navigation service may belong to the same application or come from different applications. Specifically, obtaining the business information of the navigation service includes the following steps: filtering business data of each target service associated with the login information in the T time periods from a preset business database; extracting features from the business objects contained in the business data of each target service in the T time periods, using this as the business information of the navigation service. In this embodiment, the business information of the navigation service will include business data of multiple target services. Specifically, the identifier in the login information of the map application is obtained, and the map backend system associates this identifier with data in the preset business database, enabling the map to obtain the game's feature data.

[0085] Step S320: Generate a first input vector based on the feature data of the multiple business objects in the Tth time period.

[0086] In this embodiment, the information processing device generates a first input vector based on business information. This first input vector includes feature data of multiple business objects in the T-th time period. Specifically, the information processing device can filter business information associated with the requester from the business information of multiple business objects based on the requester's identifier for the navigation service, and extract features from the obtained business information according to the features required for the first input vector, thereby obtaining the first input vector. The T-th time period is a time period determined according to preset rules. When filtering business information, the information processing device filters the business information according to the time period, thereby obtaining business data within the T-th time period. Step S330: Based on the feature data of the multiple business objects in the T-1 time period prior to the T-th time period, the feature data for the T+2 time period is estimated, and a second input vector is generated based on the feature data of the T+2 time period.

[0087] In this embodiment, the information processing device estimates the feature data for the (T+2)th time period based on the feature data from the (T-1)th time periods preceding the Tth time period, and generates a second input vector based on the estimated feature data for the (T+2)th time period. The second input vector includes feature data of multiple business objects for the (T+2)th time period. Specifically, the information processing device estimates the feature data for the (T+2)th time period based on the feature data from each of the preceding (T-1)th time periods. The estimation method can employ the mean, median, or modeling based on the data changes of each feature over the (T-1)th time period to calculate the estimated value.

[0088] In one embodiment, generating the second input vector based on the feature data of the (T+2)th time period specifically includes the following steps:

[0089] For each feature in the second input vector, calculate the feature mean of the corresponding feature in the feature data of the first T-1 time periods;

[0090] The mean of each feature is used as the estimated value of the feature in the (T+2)th time period to obtain the second input vector.

[0091] Step S340: Based on the mapping relationship between the feature data of the usage of business objects and the icons of the business objects displayed by the navigation service, predict the probability of the navigation service displaying the corresponding icons of each business object in the T+1 time period using the first input vector and the second input vector.

[0092] The information processing device uses a first input vector and a second input vector to predict the probability of each business object. This predicted probability represents the probability that a business object will be used as a navigation icon in the (T+1)th time period. Specifically, for each feature, based on the feature data in the Tth time period of the first input vector and the feature data in the (T+2)th time period of the second input vector, and according to the mapping relationship between the changing trends of the feature data and other feature changes in these two time periods, its feature in the (T+1)th time period can be estimated. Subsequently, based on the mapping relationship between the feature data in the (T+1)th time period and the usage or usage tag of the business object, the predicted probability of each business object can be predicted. The mapping relationship between feature data and the mapping relationship between feature data and usage or usage tag can be simulated according to pre-established formulas or data models.

[0093] Step S350: Based on the predicted probability of each business object, determine the target business object from the plurality of business objects, so as to display the icon corresponding to the target business object in the navigation service in the T+1 time period.

[0094] The information processing device determines the target business object from multiple business objects based on the predicted probability of each business object. Specifically, the information processing device typically selects the business object with the highest predicted probability as the target business object. In one embodiment, the business objects can be sorted according to their predicted probabilities, and the top few can be selected as the target business objects. The icon corresponding to the target business object will be used as a navigation icon in the navigation service during the T+1 time period. If there are multiple target business objects, the navigation service can display the icons corresponding to each target business object in turn according to rules, or display the icons corresponding to multiple target business objects on the terminal, and determine the final icon used in the navigation service based on the icon selection information. The server can send the icon corresponding to the target business object to the terminal, so that the terminal replaces the navigation icon in the navigation service with the icon of the target business object.

[0095] In the embodiments of this application, when determining the icon to be displayed in the (T+1)th time period, feature data for the (T+2)th time period is generated based on the feature data of the previous (T-1)th time periods. Then, the icon to be displayed in the (T+1)th time period is determined based on the feature data of the (T)th and (T+2)th time periods. This allows the determined target business object to take into account the bidirectional influence of the current time period context, which is beneficial for reflecting the preference changes for each icon or mark in the feature data, thereby improving the matching degree between the displayed icon and the actual preference and improving the accuracy of information processing.

[0096] In one embodiment of this application, based on the above technical solution, please refer to... Figure 4 , Figure 4 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. Figure 4 As shown, step S340 above, based on the mapping relationship between the feature data of the usage of business objects and the icons of the business objects displayed by the navigation service, predicts the probability of the navigation service displaying the corresponding icons of each business object in the T+1 time period using the first input vector and the second input vector, including the following steps:

[0097] Step S410: Based on the first input vector and the second input vector, a multi-class probability vector is obtained by predicting using the trained probability prediction model. The multi-class probability vector includes the predicted probability that the navigation service will display the corresponding icon of each business object in the T+1 time period.

[0098] In this embodiment, the information processing device is equipped with a trained probabilistic prediction model. This trained probabilistic prediction model is typically trained based on historical business data, and specifically, it can be trained on business data collected over T time periods. The trained probabilistic prediction model receives a first input vector and a second input vector as inputs, and outputs a multi-class probability vector, which includes the predicted probabilities for each business object.

[0099] In one embodiment of this application, based on the above technical solution, please refer to... Figure 5 , Figure 5 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. Figure 5 As shown, before step S410 above, which involves predicting using the trained probability prediction model based on the first input vector and the second input vector to obtain a multi-class probability vector, the method further includes:

[0100] Step S510: Obtain object feature samples of each business object in the preset business database, wherein the object feature samples include training sample sequences and test sample sequences;

[0101] Step S520: Based on the object feature samples, train the preset probability prediction model to obtain the trained probability prediction model.

[0102] In this embodiment, before making predictions using the probabilistic prediction model, the information processing model must first train a preset probabilistic prediction model to obtain the trained probabilistic prediction model. Specifically, the information processing device obtains object feature samples of each business object from a preset business database. The preset business database is a database of businesses and business objects built on a server. This database contains business data for each business, from which corresponding business features can be extracted. Taking the game business as an example, the preset business database may contain data features such as game ID, game name, character image, character name, character ID, game character click features, collection features, download features, undownload features, purchase features, usage features, transfer features, and character switching features for each game. The preset business database also includes a mapping data table between businesses and business objects. Again, taking the game business as an example, this mapping data table stores the game ID, game name, character image, character name, and character ID for that game. The specific method for obtaining object feature samples of each business object from the preset business database can be as follows: For example, based on the login information of the navigation service, determine the business identifiers of other logged-in game businesses; then, based on the mapping data table between businesses and business objects, filter out the business objects corresponding to these business identifiers from the preset business database; and finally, extract the corresponding business data of these business objects from the preset business database to perform feature extraction and obtain object feature samples of each business object. Subsequently, the information processing device will train a preset probability prediction model based on the object feature samples to obtain the trained probability prediction model.

[0103] In one embodiment of this application, based on the above technical solution, please refer to... Figure 6 , Figure 6 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. Figure 6 As shown, step S510 above, which obtains object feature samples of each business object in the preset business database, includes the following steps:

[0104] Step S610: Obtain usage data and feature data of multiple business objects in the T time periods from the preset business database;

[0105] Step S620: Generate tag data for the multiple business objects in the T time periods based on the usage data of the multiple business objects;

[0106] Step S630: Generate object feature samples of the multiple business objects based on the feature data of the multiple business objects in the T time periods and the tag data.

[0107] In this embodiment, the information processing device generates feature data and tag data for specific business objects based on a preset business database. The preset business database contains usage data and feature data of business objects used in the navigation service, for example, usage data and feature data of business objects used over T time periods. Then, based on the order of the usage data for each business object, the tags for each business object are determined, thus forming tag data for each business object over T time periods. Next, the information processing device combines the feature data and tag data into object feature samples according to the time periods and divides them proportionally, thereby obtaining object feature samples containing training sample sequences and test sample sequences. Specifically, taking the game business as an example, the information processing device obtains the usage data of game businesses used on the map and their corresponding game characters from the data of periods 1, ..., Tn, ..., T. The usage data for each game character is sorted to obtain the multi-class tag sequence {...,Y} for periods Tn, ..., T. t-n ,...,Y t ,...}, where Y t-i = {0, 1, ..., m}, where m represents the category with the highest usage, and i = 0, ..., n.

[0108] In one embodiment of this application, based on the above technical solution, please refer to... Figure 7 , Figure 7 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. Figure 7 As shown, step S630 above, which generates object feature samples of the multiple business objects based on the feature data and tag data of the multiple business objects in the T time periods, includes the following steps:

[0109] Step S710: For the feature data and label data of each time period in the T time periods, combine the feature data of the TM-th time period with the label data of the T-M+1-th time period to form the sample data of the TM-th time period, and obtain the sample data of the T-1-th time period, where M is an integer greater than 0 and less than T.

[0110] Step S720: According to a preset ratio, the sample data of the T-1 time periods are divided into training samples and test samples respectively to obtain the training sample sequence and test sample sequence of the multiple business objects, which are used as object feature samples.

[0111] In this embodiment, for the feature data {...,X} of each time period in the T time periods t-n ,...,X t ,...} and label data {...,Y t-n ,...,Yt ...}, using the labels from period T-i+1 and the feature data from period Ti to construct the sample for period Ti, and randomly dividing it into training samples according to a certain ratio. (ratio of a) and test samples (The ratio is 1-a). For example, according to general experience, the samples are randomly divided into training samples and test samples in a ratio of 8:2 (i.e., the training samples and test samples are randomly divided in an 8:2 ratio). This process is repeated to obtain the training sample sequence. and test sample sequence Using the characteristic X of period T t As a sample for model prediction Output training sample sequence and test sample sequence and prediction samples

[0112] In one embodiment of this application, based on the above technical solution, please refer to... Figure 8 , Figure 8 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. Figure 8 As shown, step S520 above, which trains a preset probability prediction model based on the object feature samples to obtain a trained probability prediction model, includes the following steps:

[0113] Step S810: Train the preset probability prediction model based on the training samples and test samples of the object feature samples for T-1 time periods respectively, and obtain T-1 sets of model parameters.

[0114] Step S820: Calculate the mean value of each model parameter based on the model parameters of group T-1;

[0115] Step S830: Import the mean values ​​of each parameter into the preset probability prediction model to obtain the trained probability prediction model.

[0116] In this embodiment, the information processing device trains a preset probability prediction model using training samples and test samples over a time period of T-1, and then synthesizes the training results to obtain the trained probability prediction model. Specifically, the input training sample sequence... and test samples The model is trained on a pre-defined probability prediction model to obtain the sequence of model parameter matrices {W}. Y,t-i |i=1,...,n},{W H,t-i |i=1,...,n},{W′ H,t-i |i=1,...,n},{U H,t-i |i=1,...,n},{U′ H,t-i|i=1,...,n} represent parameter matrices respectively; {B H,t-i |i=1,...,n},{B Y,t-i |i=1,...,n} represent parameter vectors; hidden layer sequence {H t-i |i=1,...,n}.

[0117] In one embodiment of this application, based on the above technical solution, please refer to... Figure 9 , Figure 9 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. In this embodiment, the preset probability prediction model includes a hidden layer. Figure 9 As shown, step S830 above, which imports the mean values ​​of each parameter into a preset probability prediction model to obtain the trained probability prediction model, includes the following steps:

[0118] Step S910: Based on the T-1 set of model parameters and the object feature samples, obtain T hidden layer vectors corresponding to T time periods through the hidden layer processing of the preset probability prediction model;

[0119] Step S920: Determine the hidden layer vector for the T+2th time period based on the T-1 hidden layer vectors;

[0120] Step S930: Configure the hidden layer according to the mean value of each parameter, the hidden layer vector of the (T+2)th time period, and the hidden layer vector of the Tth time period to obtain the trained probability prediction model.

[0121] In this embodiment, the preset probabilistic prediction model includes a hidden layer. The hidden layer is used to perform prediction calculations based on the input features, thereby obtaining the hidden layer vector for each time period. Specifically, during the training process, the training results based on the training data for each time period will include a hidden layer vector H. The hidden layer vector for the Tth time period is calculated based on the mean or median of the hidden layer vectors for the first T periods, such as Tn, ..., T-1. Finally, the hidden layer is configured based on the mean of each parameter, the hidden layer vector for the T+2th time period, and the hidden layer vector for the Tth time period, resulting in the trained probabilistic prediction model. For example, the integrated model parameter matrix... Indicate parameter vector Mean values ​​of hidden layers in periods Tn, ..., T-1 (It serves as an estimate of the hidden layer in period T+2) and the hidden layer H in period T. T The values ​​are then input into a preset probability prediction model to obtain the trained probability prediction model.

[0122] In one embodiment of this application, based on the above technical solution, please refer to... Figure 10 , Figure 10 This is a schematic flowchart illustrating an information processing method according to an embodiment of this application. Figure 10 As shown, step S410 above, which involves predicting using the trained probability prediction model based on the first input vector and the second input vector to obtain a multi-class probability vector, includes the following steps:

[0123] Step S1010: Based on the first input vector and the second input vector, the hidden layer vector of the (T+1)th time period is obtained by processing it through the trained probability prediction model.

[0124] Step S1020: Based on the hidden layer vector of the (T+1)th time period, calculate the predicted probability corresponding to each business object through the trained probability prediction model to obtain a multi-class probability vector.

[0125] In this embodiment, the information processing device first processes the trained probabilistic prediction model to obtain the hidden layer vector for the (T+1)th time period, and then calculates the predicted probability corresponding to each business object based on the hidden layer vector for the (T+1)th time period. Specifically, the model structure of the trained probabilistic prediction model is as follows:

[0126]

[0127] Among them, the characteristic mean of Tn, ..., T-1 periods As an estimate of the characteristics of period T+2 T-period characteristics X T As a prediction sample, These represent the parameter matrices respectively; Let Tn, ..., T-1 represent the parameter vectors, and let the mean of the hidden layer vectors at T+2 be used as estimates of the hidden layer vector at T+2. H T Let P{Y} be the hidden layer vector at time T. The model outputs the result P{Y}. t+1} represents the multi-class probability vector used by the business objects in period T+1.

[0128] It should be noted that although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0129] The following describes the implementation of the apparatus of this application, which can be used to execute the information processing method in the above embodiments of this application. Figure 11 A schematic block diagram illustrating the composition of an information processing apparatus according to an embodiment of this application is shown. For example... Figure 11 As shown, the information processing device 1100 mainly includes:

[0130] The feature generation module 1110 is used to generate feature data of multiple business objects in T time periods based on the use of navigation service icons by multiple business objects in T time periods, where T is an integer greater than 0.

[0131] The first vector generation module 1120 is used to generate a first input vector based on the feature data of the multiple business objects in the Tth time period.

[0132] The second vector generation module 1130 is used to estimate the feature data of the T+2 time period based on the feature data of the multiple business objects in the T-1 time period before the T-th time period, and generate a second input vector based on the feature data of the T+2 time period.

[0133] The prediction module 1140 is used to predict the probability that the navigation service will display the corresponding icon of each business object in the T+1 time period based on the mapping relationship between the feature data of the usage of the business object and the icon of the business object displayed by the navigation service, using the first input vector and the second input vector.

[0134] The object determination module 1150 is used to determine the target business object from the plurality of business objects based on the predicted probability of each business object, so as to display the icon corresponding to the target business object in the navigation service in the T+1 time period.

[0135] In some embodiments of this application, based on the above technical solutions, the prediction module includes:

[0136] The model prediction unit is used to make predictions based on the first input vector and the second input vector using a trained probability prediction model to obtain a multi-class probability vector, wherein the multi-class probability vector includes the predicted probability that the navigation service will display the corresponding icons of each business object in the T+1 time period.

[0137] In some embodiments of this application, based on the above technical solutions, the information processing apparatus further includes:

[0138] The sample acquisition module is used to acquire object feature samples of each business object in a preset business database. The object feature samples include training sample sequences and test sample sequences.

[0139] The model training module is used to train a preset probability prediction model based on the object feature samples to obtain the trained probability prediction model.

[0140] In some embodiments of this application, based on the above technical solutions, the sample acquisition module includes:

[0141] The feature acquisition unit is used to acquire usage data and feature data of multiple business objects in the T time periods from the preset business database;

[0142] The tag generation unit is used to generate tag data for the multiple business objects in the T time periods based on the usage data of the multiple business objects;

[0143] The sample generation unit is used to generate object feature samples of the multiple business objects based on the feature data of the multiple business objects in the T time periods and the tag data.

[0144] In some embodiments of this application, based on the above technical solutions, the sample generation unit includes:

[0145] The sample combination subunit is used to combine the feature data of the TM-th time period with the label data of the T-M+1-th time period to form the sample data of the TM-th time period, thereby obtaining the sample data of the T-1-th time period, where M is an integer greater than 0 and less than T.

[0146] The data partitioning subunit is used to divide the sample data of the T-1 time periods into training samples and test samples according to a preset ratio, so as to obtain the training sample sequence and test sample sequence of the multiple business objects, which serve as object feature samples.

[0147] In some embodiments of this application, based on the above technical solutions, the model training module includes:

[0148] The model training unit is used to train the preset probability prediction model based on the training samples and test samples of the object feature samples for T-1 time periods, respectively, to obtain T-1 sets of model parameters.

[0149] The mean calculation unit is used to calculate the mean value of each model parameter based on the T-1 group of model parameters;

[0150] The parameter import unit is used to import the mean values ​​of the various parameters into a preset probability prediction model to obtain the trained probability prediction model.

[0151] In some embodiments of this application, based on the above technical solutions, the preset probability prediction model includes a hidden layer; the parameter import unit includes:

[0152] The first processing subunit is used to obtain T hidden layer vectors corresponding to T time periods by processing the hidden layer of a preset probability prediction model based on the T-1 set of model parameters and the object feature samples.

[0153] The hidden layer vector determination subunit is used to determine the hidden layer vector for the (T+2)th time period based on the T-1 hidden layer vectors.

[0154] The parameter configuration unit is used to configure the hidden layer according to the mean value of each parameter, the hidden layer vector of the (T+2)th time period, and the hidden layer vector of the Tth time period, so as to obtain the trained probability prediction model.

[0155] In some embodiments of this application, based on the above technical solutions, the model prediction unit includes:

[0156] The hidden layer subunit is used to obtain the hidden layer vector of the (T+1)th time period by processing the first input vector and the second input vector through the trained probability prediction model.

[0157] The probability prediction subunit is used to calculate the predicted probability corresponding to each business object based on the hidden layer vector of the (T+1)th time period through the trained probability prediction model, so as to obtain a multi-class probability vector.

[0158] In some embodiments of this application, based on the above technical solutions, the feature generation module includes:

[0159] A login information acquisition unit is used to acquire the login information of the navigation service;

[0160] A business data filtering unit is used to filter out business data of each target business associated with the login information in the T time periods from a preset business database;

[0161] The feature extraction unit is used to extract features from the business objects contained in the business data of each target business in the T time periods, and use them as business information for the navigation business.

[0162] In some embodiments of this application, based on the above technical solutions, the second vector generation module includes:

[0163] The feature mean calculation unit is used to calculate the feature mean of the corresponding feature in the feature data of the first T-1 time periods for each feature in the second input vector.

[0164] The estimation unit is used to take the mean of each feature as the estimated value of the feature in the (T+2)th time period to obtain the second input vector.

[0165] In some embodiments of this application, based on the above technical solutions, the object determination module includes:

[0166] The target business object determination unit is used to determine the target business object to be displayed based on the predicted probabilities of each business object included in the multi-class probability vector.

[0167] The icon replacement unit is used to replace the navigation icon of the navigation service with the object icon of the target service object. It should be noted that the apparatus and method provided in the above embodiments belong to the same concept, and the specific manner in which each module performs its operation has been described in detail in the method embodiments, and will not be repeated here.

[0168] Figure 12 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0169] It should be noted that, Figure 12 The computer system 1200 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0170] like Figure 12 As shown, the computer system 1200 includes a Central Processing Unit (CPU) 1201, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1202 or programs loaded from Storage Unit 1208 into Random Access Memory (RAM) 1203. The RAM 1203 also stores various programs and data required for system operation. The CPU 1201, ROM 1202, and RAM 1203 are interconnected via a bus 1204. An Input / Output (I / O) interface 1205 is also connected to the bus 1204.

[0171] The following components are connected to I / O interface 1205: an input section 1206 including a keyboard, mouse, etc.; an output section 1207 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to I / O interface 1205 as needed. Removable media 1211, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1210 as needed so that computer programs read from them can be installed into storage section 1208 as needed.

[0172] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1209, and / or installed from removable medium 1211. When the computer program is executed by central processing unit (CPU) 1201, it performs various functions defined in the system of this application.

[0173] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0174] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0175] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0176] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0177] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0178] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An information processing method, characterized in that, The method includes: Based on the use of navigation service icons by multiple business objects in T time periods, feature data of multiple business objects in T time periods is generated, where T is an integer greater than 0; A first input vector is generated based on the feature data of the multiple business objects in the Tth time period; Based on the feature data of the multiple business objects in the T-1 time period before the T-th time period, the feature data of the T+2 time period is estimated, and a second input vector is generated based on the feature data of the T+2 time period. Based on the mapping relationship between the feature data of the usage of business objects and the icons of the business objects displayed by the navigation service, the predicted probability of the navigation service displaying the corresponding icons of each business object in the T+1 time period is predicted by the first input vector and the second input vector. Based on the predicted probabilities of each business object, a target business object is determined from the plurality of business objects, so that the icon corresponding to the target business object is displayed in the navigation service in the T+1 time period.

2. The method according to claim 1, characterized in that, The step of predicting the probability of the navigation service displaying the corresponding icon for each business object in the T+1 time period by using the first input vector and the second input vector, based on the mapping relationship between the feature data of the business object usage and the icons of the business objects displayed by the navigation service, includes: Based on the first input vector and the second input vector, a multi-class probability vector is obtained by using the trained probability prediction model. The multi-class probability vector includes the predicted probability that the navigation service will display the corresponding icon of each business object in the T+1 time period.

3. The method according to claim 2, characterized in that, Before obtaining the multi-class probability vector by making predictions using the trained probability prediction model based on the first input vector and the second input vector, the method further includes: Obtain object feature samples of each business object in a preset business database, wherein the object feature samples include training sample sequences and test sample sequences; Based on the object feature samples, a preset probability prediction model is trained to obtain the trained probability prediction model.

4. The method according to claim 3, characterized in that, The step of obtaining object feature samples of each business object in the preset business database includes: Retrieve usage data and feature data of multiple business objects in the T time periods from the preset business database; Based on the usage data of the multiple business objects, generate tag data for the multiple business objects in the T time periods; Based on the feature data of multiple business objects in the T time periods and the tag data, object feature samples of the multiple business objects are generated.

5. The method according to claim 4, characterized in that, The step of generating object feature samples for the multiple business objects based on the feature data and tag data of the multiple business objects in the T time periods includes: For the feature data and label data of each time period in the T time periods, the feature data of the TM-th time period is combined with the label data of the T-M+1-th time period to form the sample data of the TM-th time period, and the sample data of the T-1-th time period is obtained, where M is an integer greater than 0 and less than T. According to a preset ratio, the sample data of the T-1 time periods are divided into training samples and test samples respectively to obtain the training sample sequence and test sample sequence of the multiple business objects, which are used as object feature samples.

6. The method according to claim 5, characterized in that, The step of training a preset probability prediction model based on the object feature samples to obtain a trained probability prediction model includes: The preset probability prediction model is trained based on the training samples and test samples of the object feature samples for T-1 time periods, respectively, to obtain T-1 sets of model parameters; Based on the parameters of the T-1 group of models, calculate the mean values ​​of the parameters for each model. The mean values ​​of each parameter are imported into the preset probability prediction model to obtain the trained probability prediction model.

7. The method according to claim 6, characterized in that, The preset probability prediction model includes a hidden layer; the step of importing the mean values ​​of each parameter into the preset probability prediction model to obtain the trained probability prediction model includes: Based on the T-1 set of model parameters and the object feature samples, T hidden layer vectors corresponding to T time periods are obtained through hidden layer processing of a preset probability prediction model. Based on the T-1 hidden layer vectors, determine the hidden layer vector for the T+2th time period; The hidden layer is configured based on the mean values ​​of each parameter, the hidden layer vector of the (T+2)th time period, and the hidden layer vector of the Tth time period to obtain the trained probability prediction model.

8. The method according to claim 2, characterized in that, Based on the first input vector and the second input vector, a multi-class probability vector is obtained by using the trained probability prediction model, including: Based on the first input vector and the second input vector, the hidden layer vector for the (T+1)th time period is obtained by processing it through the trained probability prediction model. Based on the hidden layer vector of the (T+1)th time period, the predicted probability corresponding to each business object is calculated through the trained probability prediction model to obtain a multi-class probability vector.

9. An information processing device, characterized in that, include: The feature generation module is used to generate feature data of multiple business objects in T time periods based on the use of navigation service icons by multiple business objects in T time periods, where T is an integer greater than 0. The first vector generation module is used to generate a first input vector based on the feature data of the multiple business objects in the Tth time period; The second vector generation module is used to estimate the feature data of the T+2 time period based on the feature data of the multiple business objects in the T-1 time period before the T-th time period, and generate a second input vector based on the feature data of the T+2 time period. The prediction module is used to predict the probability that the navigation service will display the corresponding icon of each business object in the T+1 time period based on the mapping relationship between the feature data of the usage of the business object and the icon of the business object displayed by the navigation service, using the first input vector and the second input vector. The object determination module is used to determine the target business object from the multiple business objects based on the predicted probability of each business object, so as to display the icon corresponding to the target business object in the navigation service in the T+1 time period.

10. An electronic device, characterized in that, include: processor; Memory for storing the executable instructions of the processor; The processor is configured to execute the information processing method of any one of claims 1 to 8 by executing the executable instructions.

11. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the information processing method as described in any one of claims 1 to 8.

12. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, a processor of a computer device reading the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to cause the computer device to perform the information processing method as described in any one of claims 1 to 8.

Images