Activity recommendation method and device based on user data, equipment and medium

Abstract

The invention discloses an activity recommendation method and device based on user data, equipment and a medium. The method is applied to the intelligent calendar system and comprises the steps that when a user logs in the intelligent calendar system, environment perception information is acquired according to a preset perception mode, and the environment perception information comprises spatio-temporal information; a to-do activity set is determined according to the authorization information and login information of the user, and the login information comprises equipment information; screening in the to-do activity set according to the equipment information and the spatio-temporal information to obtain a primary activity set; and sorting the plurality of to-do activities in the primary activity set according to a preset user preference tag and the obtained scene matching degree, determining a target to-do activity according to a sorting result, and recommending the target to-do activity to the user. By implementing the method provided by the invention, the problems that a traditional calendar tool cannot provide intelligent suggestions based on user activity information and cannot efficiently perform time management and resource allocation can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of schedule management, and particularly relates to an activity recommendation method and device based on user data, equipment and a medium. BACKGROUND

[0002] With the rapid development of science and technology, digital office and intelligent equipment are deeply integrated into life, and the complexity of personal and organizational schedule management has increased greatly, and the demand for efficient and intelligent schedule management tools is urgent. Although there are many calendar tools in the market, most of them have single functions and poor adaptability. Traditional calendar tools such as Google Calendar can only meet the basic time recording and reminding, and are difficult to cope with complex scenarios, resulting in obvious drawbacks of existing calendar tools, for example, multi-platform data fragmentation, personal, enterprise and third-party application activity data is scattered, users need to switch and integrate between different platforms, which consumes a lot of energy; passive management, relying on manual input, unable to real-time perceive user behavior and environmental state, difficult to dynamically adjust activities, etc., resulting in that the existing technology cannot provide intelligent suggestions based on user activity information, and cannot optimize the schedule. The user's efficiency is low when using the traditional tool, and it is difficult to achieve efficient time management and resource allocation. SUMMARY

[0003] The embodiments of the present application provide an activity recommendation method and device based on user data, equipment and a medium, which aims to solve the problem that the existing calendar tool cannot provide intelligent suggestions based on user activity information, and cannot efficiently manage time and allocate resources.

[0004] In a first aspect, the embodiments of the present application provide an activity recommendation method based on user data, which is applied to a smart calendar system, and the method comprises: when a user logs in to the smart calendar system, acquiring environmental perception information according to a preset perception mode, wherein the environmental perception information comprises space-time information; determining a to-do activity of the user according to authorization information and login information of the user, and constructing a to-do activity set, wherein the login information comprises device information; filtering in the to-do activity set according to the device information and the space-time information, and acquiring a primary activity set; sorting a plurality of to-do activities in the primary activity set according to a preset user preference label and a matched degree of a scenario, determining a target to-do activity according to a sorting result, and recommending the target to-do activity to the user.

[0005] In a second aspect, the embodiments of the present application further provide an activity recommendation device based on user data, which is applied to a smart calendar system and comprises: an acquisition unit, configured to acquire environmental perception information according to a preset perception mode when a user logs in the smart calendar system, wherein the environmental perception information comprises space-time information; a determination unit, configured to determine a to-do activity of the user according to authorization information and login information of the user, and construct a to-do activity set, wherein the login information comprises device information; a screening unit, configured to screen the to-do activity set according to the device information and the space-time information, and acquire a primary activity set; and a recommendation unit, configured to sort a plurality of to-do activities in the primary activity set according to a preset user preference label and a matching degree of a scenario, determine a target to-do activity according to a sorting result, and recommend the target to-do activity to the user.

[0006] In a third aspect, the embodiments of the present application further provide a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the above method when executing the computer program.

[0007] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program, the computer program comprises program instructions, and the program instructions can implement the above method when executed by a processor.

[0008] The embodiment of the present application provides an activity recommendation method, device and equipment based on user data and a medium. The method is applied to an intelligent calendar system, and comprises the following steps: when a user logs in the intelligent calendar system, acquiring environmental sensing information according to a preset sensing mode, wherein the environmental sensing information comprises space-time information; determining a to-do activity of the user according to authorization information and login information of the user, and constructing a to-do activity set, wherein the login information comprises device information; screening a plurality of to-do activities in the to-do activity set according to the device information and the space-time information, and acquiring a primary activity set; sorting a plurality of to-do activities in the primary activity set according to a preset user preference label and a matching degree of a scene, determining a target to-do activity according to a sorting result, and recommending the target to-do activity to the user. The embodiment of the present application acquires all to-do activities and current environmental sensing information according to authorization information of the user when the user logs in, so as to acquire real-time and latest information, and facilitate accurate activity recommendation. The to-do activities are screened according to the device information and the space-time information, so as to acquire an initial activity set most suitable for a current scene. On this basis, the activities in the initial activity set are sorted according to the preset user preference label and the matching degree of the scene, and the target to-do activity is determined, so as to determine a to-do activity most suitable for the user. The to-do activity set is determined by acquiring all to-do data and environmental sensing information, and the target activity is determined through layer-by-layer screening, so as to realize automatic acquisition of all-scene data, dynamic algorithm optimization and seamless collaboration across platforms, fundamentally break through the bottleneck of passive response and lack of intelligent decision-making ability of traditional tools, and effectively provide intelligent suggestions based on user activity information, and help the user to efficiently manage time and allocate resources. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0010] Figure 1 The flowchart of the activity recommendation method based on user data provided by the embodiment of the present application is shown in the figure. Figure 2 The first sub-flowchart of the activity recommendation method based on user data provided by the embodiment of the present application is shown in the figure. Figure 3 The second sub-flowchart of the activity recommendation method based on user data provided by the embodiment of the present application is shown in the figure. Figure 4 The third sub-flowchart of the activity recommendation method based on user data provided by the embodiment of the present application is shown in the figure. Figure 5 A fourth sub-process schematic diagram of the activity recommendation method based on user data provided by the embodiment of the present application is shown in FIG. 4; Figure 6 A fifth sub-process schematic diagram of the activity recommendation method based on user data provided by the embodiment of the present application is shown in FIG. 5; Figure 7 A sixth sub-process schematic diagram of the activity recommendation method based on user data provided by the embodiment of the present application is shown in FIG. 6; Figure 8 A schematic block diagram of the activity recommendation device based on user data provided by the embodiment of the present application is shown in FIG. 7; Figure 9 A schematic block diagram of the computer device provided by the embodiment of the present application is shown in FIG. 8. DETAILED DESCRIPTION

[0011] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0012] It should be understood that when used in the specification and the appended claims, the terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0013] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0014] It should be further understood that the term "and / or" used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations thereof, and includes these combinations.

[0015] Please refer to Figure 1 , Figure 1A flowchart of a user data-based activity recommendation method provided by an embodiment of the present application is shown. The user data-based activity recommendation method in this embodiment can be applied to a smart calendar system, such as a schedule management application of a personal smart terminal. The smart calendar system includes an environment perception layer, a data processing layer, and an application layer. The environment perception layer is configured to acquire current environment perception information, chat information, and organization information according to the authorization of a user, and to transmit the perceived data to the data processing layer for analysis and processing to determine a target to-do activity of the user and display the target to-do activity by the application layer. By using the method, automatic collection of full-scene data can be effectively realized, and the bottleneck of passive response of a traditional tool and lack of intelligent decision-making capability can be fundamentally broken through, thereby helping the user to efficiently manage time and allocate resources.

[0016] Figure 1 A flowchart of a user data-based activity recommendation method provided by an embodiment of the present application is shown. As shown in the figure, the method includes the following steps S110-S140.

[0017] S110, when a user logs in the smart calendar system, acquiring environment perception information according to a preset perception mode, wherein the environment perception information includes space-time information.

[0018] In this embodiment, the environment perception information is information about the current environment of the user, including but not limited to time, space, weather, and the like. The space-time information includes time and space information, wherein the time information is a specific time point when the user logs in the system, and is the basis for the smart calendar system to manage time and arrange schedules. The space information is the geographical position or spatial range where the user is currently located, which helps the smart calendar system to understand the environment where the user is located. When the user logs in the smart calendar system, the environment perception information is acquired according to the preset perception mode. Specifically, when the user logs in the smart calendar system by inputting a username and password or the like, the current environment perception information is acquired by the preset perception mode, for example, the current specific time is acquired by a time synchronization function, the geographical position information of the user, such as longitude, latitude, city name, and the like, is acquired by GPS positioning, and the corresponding environment information can also be acquired by a microphone input, a camera code scanning, NFC perception, and the like. The specific preset perception mode is not limited, and the corresponding environment perception information can be acquired according to the authorization of the user. By acquiring the environment perception information according to the preset perception mode when the user logs in the smart calendar system, a data basis is provided for subsequent implementation of personalized services, intelligent reminders, and efficient time management functions.

[0019] In an embodiment, as shown in Figure 2 the step S110 further includes steps S111-S112.

[0020] S111, obtaining real-time initial environment perception information according to the authorization information in an authorized manner; S112, normalizing the initial environment perception information to determine the environment perception information.

[0021] In the embodiment, the authorization information is information about which data or resources the user authorizes the system to access, for example, the authorization information can include information about allowing obtaining the current location and running a query chat content. The authorized manner refers to accessing and obtaining data in a legal and compliant manner according to the permissions and rules specified in the authorization information. For example, if the authorization information shows that the current location is allowed to be obtained, the system can obtain the current spatial information according to the GPS. According to the authorization information, real-time initial environment perception information is obtained in an authorized manner, for example, according to the authorization, the location information can be obtained through the mobile positioning system (such as network positioning / GPS positioning), and the elements, activities, spatial positions, etc. are input through the calendar front-end interface (including microphone, keyboard and mouse input). The obtained information is collectively referred to as the initial environment perception information. The initial environment perception information is normalized to determine the environment perception information, wherein the normalization converts data of different sources, different formats or different dimensions into a unified and standardized processing manner. In the embodiment, data cleaning (removing noise, outliers, etc.), data conversion (such as converting temperature from Celsius to Fahrenheit, or uniting units), data standardization (such as scaling data to a specific range or distribution), etc. can be performed. The processed information is the environment perception information, and the specific processing manner is not limited. By obtaining real-time initial environment perception information in a legal manner according to the authorization information, and then normalizing these information, the environment perception information that is more standardized and easier to process and analyze is obtained, so as to provide more accurate data for subsequent schedule recommendation.

[0022] S120, determining the to-do activities of the user according to the authorization information and the login information of the user to construct a to-do activity set, wherein the login information includes device information.

[0023] In the embodiment, the authorization information defines the permission of data and resources that the application can access. The login information is the credential and related information provided by the user when logging into the system, including username, password, device information, login time, IP address, and other information. The device information is the information of the device used by the user to log into the system, which includes device types, such as mobile phones, tablets, computers, and other devices. The pending activities of the user are determined according to the authorization information and the login information of the user, and the pending activity set is constructed. Specifically, the corresponding information is queried according to the authorization information to obtain the pending activities, and the pending activities of the organization to which the user belongs are obtained according to the login information, and the obtained pending activities are determined as the pending activity set. The pending activities have six dimensions, namely, the time of the activity, the organization to which the activity belongs, the personnel participating in the activity, the spatial location of the activity, the elements required by the activity, and the details (content) of the activity. The activity details are designed by the activity creator, and each activity participant has a backup of his own activity data. By combining the authorization information and the login information (especially the device information) to construct the pending activity set, a more secure, efficient, and personalized task management experience can be provided for the user.

[0024] In an embodiment, as shown in FIG. 12, the step S120 includes steps S121-S123. Figure 3

[0025] S121, searching in the authorized chat information according to the authorization information and the preset keyword, and constructing the daily pending activity according to the searched target word; S122, determining the organization information of the user according to the login information, accessing and querying the preset organization calendar database according to the organization information, and obtaining the organization pending activity; S123, determining the pending activity set according to the daily pending activity and the organization pending activity.

[0026] ​In the embodiment, the preset keywords are keywords related to activities and schedules, such as "task", "meeting", "deadline", etc. According to the authorized information and the preset keywords, the authorized chat information is searched, and the target words are constructed according to the target words. Specifically, first, according to the user's authorization information, it is verified whether the system has the right to access specific chat information. This ensures the security and privacy of data and prevents unauthorized access to chat content. In the authorized chat information, these keywords are used for retrieval to find the relevant conversation content related to the to-do activity, and the conversation content is used as the target word. According to the target word, the user's daily to-do activity is automatically constructed, including task name, description, deadline, etc. Specifically, the chat content can be parsed by LangChain (a framework for building large language model (LLM) applications) to identify sentences containing keywords such as "meeting" and "deadline", and automatically generate daily to-do activities. According to the login information, the organization information of the user is determined, and the preset organization calendar database is accessed and queried according to the organization information to obtain the organization to-do activity. Specifically, according to the user's login information, the personal identity is identified (whether it is a personal or organizational member), if it is a personal identity, the system accesses the personal calendar database through the personal ID and domain name address, and the recommendation algorithm obtains the to-do activity from the user's activity in the database, if it is an organizational member, the user's organization information is determined according to the login information such as username, department, position, etc., wherein the user can also have multiple organizations, and the user's all organization information can be obtained through the user's operation such as switching the current organization, joining the organization, creating the organization, etc. According to the user's organization information, the organization to-do activity related to the user is queried in the preset organization calendar database, such as department meeting, project task, etc. The preset organization calendar database is the database within the organization, which stores various activities, meetings, tasks, etc. within the organization. The constructed daily to-do activity and the obtained organization to-do activity are combined to construct a to-do activity set. By determining the to-do activity set according to the daily to-do activity and the organization to-do activity, the personal task and the organization task are integrated, and the activity content in the to-do activity set is ensured to be comprehensive.

[0027] S130, according to the device information and the spatio-temporal information, the to-do activity set is filtered to obtain a primary activity set.

[0028] In the embodiment, the device information is information of a login device acquired when a user logs in the system, for example, device type and operating system version and the like, and the space-time information is specific time information and geographic location information. The to-be-completed activities are filtered according to the device information and the space-time information. Specifically, according to the device information, to-be-completed activities compatible with the current device are filtered. For example, if the user uses a mobile phone, tasks suitable for mobile phone processing, such as photograph uploading, mobile terminal approval and the like, are preferentially displayed. According to the time information and the space information, to-be-completed activities related to the current time and the current location are filtered. To-be-completed tasks meeting the current device information and the space-time information are constructed into a primary activity set, and the set includes a task list most meeting the current information of the user. The primary activity set is filtered according to the device information and the space-time information, so as to formulate a primary activity set personalized for the user, which can improve user experience and facilitate the user to quickly locate and process important tasks, thereby intelligently helping the user to efficiently manage time and allocate resources.

[0029] In an embodiment, as shown in FIG. 13, Figure 4 the step S130 includes steps S131-S132.

[0030] S131, filtering device executable activities from the to-be-completed activities according to the device information, to construct a first primary activity set; S132, filtering space executable activities from the first primary activity set according to the current space-time information, to determine the primary activity set.

[0031] In this embodiment, the to-do activities can all have specific device requirements, for example, some tasks can only be completed on a computer, and some other tasks can be more suitable for processing on a mobile phone. Therefore, the device executable activities are filtered from the to-do activity set according to the device type in the device information, that is, each activity in the to-do activity set is traversed to check whether its device requirement matches the current device information, and for the activity that meets the device requirement, it is added to the first primary activity set. For example, if the current device is a mobile phone, and a to-do activity is "take a photo and upload", the activity will be added to the first primary activity set; and if a to-do activity is "edit a video using professional software", and the current device does not support the software, the activity will not be added. After filtering, the first primary to-do activity that can be executed on the current device is obtained. The spatial executable activities are filtered from the first primary activity set according to the current spatio-temporal information, specifically, each activity in the first primary activity set is traversed to check whether its time requirement and space requirement match the current time and space information. For the activity that meets the time and space requirements, it is retained in the first primary activity set. For example, if the current time is 10 am, and a to-do activity is "meet in the conference room at 11 am", and the user's current location is close to the conference room, the activity will be retained in the primary activity set; and if a to-do activity is "attend an activity in another city at 3 pm", and the user cannot reach the city in time, the activity will be removed from the primary activity set. After layer-by-layer filtering, the to-do activity that can be executed under the current device, time and space conditions is obtained, and it is determined as the primary activity set. By combining device information, time information and space information, the to-do activity that can be executed by the user at present can be accurately filtered, thereby improving the user's use experience and work efficiency.

[0032] In S140, the to-do activities in the primary activity set are sorted according to the matching degree of the preset user preference label and the obtained scene, the target to-do activity is determined according to the sorting result, and the target to-do activity is recommended to the user.

[0033] In the embodiment, the preset user preference label is a label with user preference according to historical behavior, feedback or explicit setting of the user. The scene matching degree refers to the degree of fit of the to-do activity and the current scene (including device, time, space, etc.). According to the preset user preference label and the obtained scene matching degree, the several to-do activities in the primary activity set are sorted. Specifically, the to-do activities are sorted according to the matching degree of the to-do activities and the preset user preference label, and then the activities are sorted according to the scene matching degree of each activity. According to the two sorting results, a comprehensive judgment is made to determine the to-do activity that best meets the user as the target to-do activity, and the target to-do activity is displayed in the display area of the system for recommendation to the user. By combining the user preference label and the scene matching degree, personalized to-do activity recommendation can be provided, and user experience and work efficiency can be improved.

[0034] In addition, the embodiment also includes that the application layer of the intelligent calendar provides a display interface and a template through UI, which includes a historical activity, a real-time activity, an activity recommendation, an activity element and the like. The user can quickly switch to view the activity statistics of different organization dimensions through an "organization filtering option". The display page can also include a resource area (an area for displaying user personal information and organization information), an interaction area (an area for filtering and managing activities based on time), and an activity area (an area for displaying activity classification, content and activity dynamic update). In the embodiment, it is also included that whether there is an abnormal activity is filtered and detected according to activity change information of the to-do activity. The abnormal activity refers to an event deviating from the expected behavior, for example, the meeting location of a certain meeting suddenly changes, which is an abnormal activity. The abnormal activity is displayed in an abnormal time tab of the activity area. The activity area can include an activity tab (an area for displaying normal activities) and an abnormal time tab (an area for displaying abnormal activities). Different to-do activities are displayed on the display page of the application to help the user efficiently manage time and allocate resources.

[0035] In an embodiment, as shown in Figure 5 The step S140 before the step S1401-S402 is further included.

[0036] S1401, creating an activity label of each to-do activity; S1402, creating the preset user preference label according to historical activity data of the user and the corresponding activity label.

[0037] In the embodiment, the activity label is a corresponding label created for each to-do activity, wherein a label category can be defined according to dimensions such as type, priority, scenario, and the like of the to-do activity, for example, labels such as learning, fitness, and entertainment, and labels such as urgent and high priority, or labels such as work, family, personal, and team can be created. For example, a to-do activity is “meet with the team at 10 o'clock tomorrow morning”, and the corresponding activity label can be meeting, work, urgent, and short-term. Among them, the label can be dynamically updated as the state of the to-do activity changes (such as completion, postponement, and priority adjustment). The preset user preference label is created according to the historical activity data of the user and the corresponding activity label. Specifically, all completed to-do activities and their labels in a preset time period of the user are obtained, the behavior pattern and preference of the user are identified through data analysis, and the preset preference label of the user is created according to the analysis result. For example, the user often handles activities of the type “meeting”, and a user preference label of “preference for meeting” can be created for the user. The preset user preference label can be dynamically adjusted as the user behavior changes. For example, the user recently starts to frequently handle activities of the type “learning”, and the user preference label can be the learning label. By determining the preset user preference label, to-do activities that are more in line with the preference of the user can be efficiently recommended to the user.

[0038] In an embodiment, as shown in FIG. 13, the step S140 further includes steps S1403-S1404. Figure 6

[0039] S1403, a behavior habit model of the user is constructed according to the historical activity data through a preset network algorithm; S1403, a scenario matching degree of each to-do activity is calculated according to the behavior habit model.

[0040] ​In this embodiment, the preset network algorithm is a preset neural network algorithm. An appropriate neural network architecture, such as a long short-term memory network or a convolutional neural network, can be selected based on the complexity of the data and the number of features. A user's behavior habit model is constructed using the preset network algorithm based on the historical activity data. This algorithm collects all of the user's historical activity data (including activity type, time, location, priority, and tags) within a preset time period (which can be customized as needed). Key features are extracted from the historical activity data, and the behavior habit model is constructed based on the extracted features and the preset neural network algorithm. While the exemplary construction method is not limiting, a scenario matching score can be generated based on the to-do activities, current spatiotemporal information, and device information. The scenario matching score for each to-do activity is calculated based on the behavior habit model. Specifically, the scenario matching score for each activity is calculated based on the current temporal and spatial context data and outputted. By constructing a user behavior habit model and calculating the scenario matching score, more accurate and personalized time management services can be provided, improving time management efficiency.

[0041] In one embodiment, if Figure 7 As shown, step S140 includes steps S141-S143.

[0042] S141. Convert the preset user preference label and the activity label into a user semantic vector and an activity vector respectively through a preset deep learning algorithm; S142, calculating similarity values ​​between the user semantic vector and different activity vectors using a preset similarity calculation method; S143 , sorting the to-do activities according to the similarity value, the scene matching degree, and a preset weight.

[0043] In this embodiment, the preset deep learning algorithm is a method and algorithm that can convert text into vectors, such as Word2Vec, transformers algorithm, etc. The preset user preference label and the activity label are respectively converted into user semantic vectors and activity vectors through the preset deep learning algorithm, wherein the vector representation of each label is a numerical vector of a fixed length, which captures the semantic information of the label. For example, through the BERT model, each label can be converted into a 768-dimensional vector. The similarity value between the user semantic vector and the different activity vectors is calculated by the preset similarity calculation method, wherein the preset similarity calculation method is a method for calculating vector similarity. In this embodiment, it can be cosine similarity (a measure of the similarity between two vectors in direction, ranging from -1 to 1, the closer the value is to 1, the more similar it is). If it is a semantic vector A, the activity vector of each activity label is B1, B2....B i , similarity is calculated by cosine similarity, where B ia semantic vector of a label of the i-th activity in the primary activity set, is a dot product of two vectors, |a| and |b i is a module of two vectors: ; wherein, is a similarity value of the user semantic vector and different activity vectors. According to the similarity value and the scene matching degree and a preset weight, a plurality of the to-be-performed activities are sorted, specifically, the similarity value and the scene matching degree are combined to calculate a comprehensive score of each to-be-performed activity, wherein the similarity value and the scene matching degree are given different weights, and the comprehensive score is sorted according to the weights, for example, comprehensive score = w1 x similarity value + w2 x scene matching degree. Then the comprehensive score is sorted, and the to-be-performed activity with the highest score is taken as the target to-be-performed activity. By combining the semantic similarity and the scene matching degree, the system can recommend to-be-performed activities that are more in line with the preferences of the user, thereby improving the recommendation efficiency.

[0044] In order to further understand the activity recommendation method based on user data of the present application, the following describes the processing flow of the intelligent calendar system: The intelligent calendar system comprises an environment perception layer, a data processing layer and an application layer. The environment perception layer acquires real-time environment perception information such as position and time by using perception devices such as a microphone, a camera, code scanning, NFC perception, GPS positioning and the like, and parses chat records according to authorization conditions, identifies keywords to automatically create to-be-performed activities, and acquires corresponding organization information according to user organization switching. The above-acquired information and activities are transmitted to a multi-dimensional environment data management center of the data processing layer. The multi-dimensional environment data management center is used for managing various data including text, spatial position, audio and video, pictures, cameras, health information, motion information, distance information, direction information, network status and the like, and sends the data to a calendar engine part of the data processing layer after uniform processing. The calendar engine performs activity screening and sorting according to the acquired data, determines target to-be-performed activities, and transmits the target to-be-performed activities to the application layer for display. After a user logs in the intelligent calendar through a personal organization, the user can click a time axis on the application layer to select a time scale (such as day / month / week), and the system displays the number of activities according to the selected time range. The number of activities of the current organization, a joined organization and a created organization can be counted and displayed. The user can also enter a multi-dimensional analysis interface on the page of the application layer, including spatial dimension, activity dimension, element dimension, role dimension and person dimension. The system also supports providing optimization suggestions (such as adjusting time and allocating resources) according to user problem details, and the user can click the suggestions to handle the problems in time. By using the method, full-scene data can be automatically collected, and the bottleneck of passive response and lack of intelligent decision-making ability of traditional tools can be fundamentally broken through, thereby helping the user to efficiently manage time and allocate resources.

[0045] Figure 8 is a schematic block diagram of an activity recommendation device 200 based on user data provided by an embodiment of the present application. As shown in Figure 8 corresponding to the above activity recommendation method based on user data, the present application also provides an activity recommendation device based on user data. The activity recommendation device based on user data comprises units for executing the above activity recommendation method based on user data, and the device can be configured in a desktop computer, a tablet computer, a laptop computer, etc. terminal. Specifically, please refer to Figure 8 , the activity recommendation device based on user data comprises an acquisition unit 210, a determination unit 220, a screening unit 230 and a recommendation unit 240.

[0046] The acquisition unit 210 is configured to acquire environment perception information according to a preset perception mode when a user logs in the intelligent calendar system, wherein the environment perception information comprises space-time information.

[0047] In an embodiment, the acquisition unit 210 comprises an initial acquisition unit and a uniform unit.

[0048] An initial acquisition unit is configured to acquire real-time initial environment perception information in an authorized manner according to the authorization information. A normalization unit is configured to normalize the initial environment perception information to determine the environment perception information.

[0049] A determination unit 220 is configured to determine a to-do activity of a user according to authorization information and login information of the user, and construct a to-do activity set, wherein the login information includes device information.

[0050] In an embodiment, the determination unit 220 includes a retrieval unit, a query unit, and a determination subunit.

[0051] The retrieval unit is configured to search for target words in authorized chat information according to the authorization information and a preset keyword, and construct a daily to-do activity according to the target words. The query unit is configured to determine organization information of the user according to the login information, access and query a preset organization calendar database according to the organization information, and acquire an organization to-do activity. The determination subunit is configured to determine the to-do activity set according to the daily to-do activity and the organization to-do activity.

[0052] A screening unit 230 is configured to screen the to-do activity set according to device information and spatio-temporal information to acquire a primary activity set.

[0053] In an embodiment, the screening unit 230 includes a first screening unit and a second screening unit.

[0054] The first screening unit is configured to screen device-executable activities from the to-do activity set according to the device information to construct a first primary activity set. The second screening unit is configured to screen space-executable activities from the first primary activity set according to current spatio-temporal information to determine the primary activity set.

[0055] A recommendation unit 240 is configured to sort a plurality of to-do activities in the primary activity set according to a preset user preference label and a matching degree of an acquired scenario, determine a target to-do activity according to a sorting result, and recommend the target to-do activity to the user.

[0056] In an embodiment, the recommendation unit 240 includes a first creation unit and a second creation unit.

[0057] The first creation unit is configured to create an activity label of each to-do activity. The second creation unit is configured to create the preset user preference label according to historical activity data of the user and the corresponding activity label.

[0058] In an embodiment, the recommendation unit 240 comprises a model construction unit and a similarity calculation unit.

[0059] The model construction unit is configured to construct a behavior habit model of the user according to the historical activity data through a preset network algorithm. The similarity calculation unit is configured to calculate a scenario matching degree of each of the to-be-performed activities according to the behavior habit model.

[0060] In an embodiment, the recommendation unit 240 comprises a conversion unit, a vector calculation unit and a sorting unit.

[0061] The conversion unit is configured to convert the preset user preference label and the activity label into a user semantic vector and an activity vector, respectively, through a preset deep learning algorithm. The vector calculation unit is configured to calculate a similarity value of the user semantic vector and different activity vectors through a preset similarity calculation method. The sorting unit is configured to sort a plurality of to-be-performed activities according to the similarity value, the scenario matching degree and a preset weight.

[0062] It should be noted that the specific implementation process of the above-mentioned activity recommendation device based on user data 200 and each unit can be clearly understood by those skilled in the art, which can be referred to the corresponding description in the foregoing method embodiments. For the convenience and brevity of description, it will not be repeated here.

[0063] The above-mentioned activity recommendation device based on user data can be realized in the form of a computer program, which can run on a computer device as shown in Figure 9 .

[0064] Please refer to Figure 9 , Figure 9 is a schematic block diagram of a computer device provided by an embodiment of the present application. The computer device 500 can be a terminal or a server, wherein the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant and a wearable device, etc. The server can be a stand-alone server or a server cluster composed of multiple servers.

[0065] Refer to Figure 9 , the computer device 500 comprises a processor 502, a memory and a network interface 505 connected through a system bus 501, wherein the memory can comprise a non-volatile storage medium 503 and an internal memory 504.

[0066] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, which, when executed, can enable the processor 502 to perform an activity recommendation method based on user data.

[0067] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0068] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503 . When the computer program 5032 is executed by the processor 502 , the processor 502 can execute an activity recommendation method based on user data.

[0069] The network interface 505 is used to communicate with other devices through the network. Figure 9 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0070] The processor 502 is configured to run a computer program 5032 stored in the memory to implement the steps of the above method.

[0071] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0072] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program includes program instructions, which can be stored in a storage medium that is computer-readable. The program instructions are executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0073] Therefore, the present application also provides a storage medium. The storage medium can be a computer readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. The program instructions are executed by a processor to make the processor execute the steps of the above method.

[0074] The storage medium can be a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, and various computer readable storage media that can store program codes.

[0075] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in general terms. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0076] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0077] The steps in the method embodiments of the present application can be adjusted, combined and reduced in sequence according to actual needs. The units in the device embodiments of the present application can be combined, divided and reduced according to actual needs. In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0078] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a storage medium. Based on such understanding, the technical solutions of the present application essentially or say the parts that make contributions to the prior art, or all or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to make a computer device (which can be a personal computer, a terminal or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application.

[0079] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An activity recommendation method based on user data, characterized in that: The method is applied to an intelligent calendar system, and includes: When a user logs into the smart calendar system, environmental perception information is obtained according to a preset perception method, wherein the environmental perception information includes time and space information; Determining the user's to-do activities based on the authorization information and the user's login information, and constructing a to-do activity set, wherein the login information includes device information; Filter the to-do activity set according to the device information and the time-space information to obtain a primary activity set; According to the preset user preference tags and the obtained scene matching degree, several to-do activities in the primary activity set are sorted, a target to-do activity is determined according to the sorting result, and the target to-do activity is recommended to the user.

2. The method according to claim 1, characterized in that The step of acquiring environmental perception information according to a preset perception method includes: Acquiring real-time initial environmental perception information in an authorized manner according to the authorization information; The initial environmental perception information is normalized to determine the environmental perception information.

3. The method according to claim 1, characterized in that The step of determining the user's to-do activities based on the authorization information and the user's login information includes: Searching the authorized chat messages based on the authorization information and preset keywords, and constructing daily to-do activities based on the retrieved target words; Determine the user's organization information based on the login information, access and query a preset organization calendar database based on the organization information, and obtain the organization's to-do activities; The to-do activity set is determined according to the daily to-do activities and the organizational to-do activities.

4. The method according to claim 1, wherein The step of filtering the to-do activity set according to the device information and the spatiotemporal information to obtain a primary activity set includes: Filtering the device-executable activities from the to-do activity set according to the device information to construct a first primary activity set; According to the current spatiotemporal information, spatially executable activities are screened from the first primary activity set to determine the primary activity set.

5. The method according to claim 1, wherein Before the step of sorting the to-do activities in the primary activity set according to the preset user preference tags and the obtained scenario matching degree, the method includes: Creating an activity tag for each of the to-do activities; The preset user preference tag is created according to the user's historical activity data and the corresponding activity tag.

6. The method according to claim 5, characterized in that Before the step of sorting the to-do activities in the primary activity set according to the preset user preference tags and the obtained scenario matching degree, the method further includes: Building a user's behavior habit model based on the historical activity data through a preset network algorithm; The scenario matching degree of each of the to-do activities is calculated according to the behavior habit model.

7. The method according to claim 6, characterized in that The step of sorting the to-do activities in the primary activity set according to the preset user preference tags and the obtained scenario matching degree includes: Converting the preset user preference label and the activity label into a user semantic vector and an activity vector respectively through a preset deep learning algorithm; Calculating similarity values ​​between the user semantic vector and different activity vectors using a preset similarity calculation method; The to-do activities are sorted according to the similarity value, the scene matching degree and the preset weight.

8. An activity recommendation device based on user data, characterized in that: The device is applied to an intelligent calendar system, and comprises: an acquiring unit, configured to acquire environmental perception information according to a preset perception method when a user logs into the smart calendar system, wherein the environmental perception information includes time and space information; a determining unit, configured to determine the user's to-do activities based on the authorization information and the user's login information, and construct a to-do activity set, wherein the login information includes device information; a screening unit, configured to screen the to-do activity set according to the device information and the spatiotemporal information to obtain a primary activity set; A recommendation unit is used to sort the to-do activities in the primary activity set according to the preset user preference tags and the obtained scene matching degree, determine the target to-do activity according to the sorting result, and recommend the target to-do activity to the user.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images