Methods, apparatus, devices, and storage media for recommending items

Abstract

According to an embodiment of the present disclosure, a method, apparatus, device and storage medium for item recommendation are provided. The method includes obtaining activity information of a target user within a target time period, the activity information is related to at least one type of interactive activity performed by the target user within the target time period, and the degree of participation of the target user in at least one type of interactive activity meets a preset condition; based on the activity information and sample information of at least one type of interactive activity, using a machine learning model, identifying one or more target items associated with the target user; and presenting recommendation information about one or more target items. In this way, according to user needs, the target user can be helped to quickly understand the target items he is concerned about, and the intelligence and efficiency of information processing can be improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for item recommendation. Background Art

[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. How to use terminal devices or applications to provide users with more convenient services is a technical issue that needs to be explored at present. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for recommending items is provided. The method includes: obtaining activity information of a target user within a target time period, the activity information being related to at least one type of interactive activity performed by the target user within the target time period, and the degree of participation of the target user in at least one type of interactive activity meeting a preset condition; based on the activity information and sample information of at least one type of interactive activity, using a machine learning model, identifying one or more target items associated with the target user; and presenting recommendation information about the one or more target items.

[0004] In a second aspect of the present disclosure, a device for item recommendation is provided. The device includes: an activity information acquisition module configured to acquire activity information of a target user within a target time period, the activity information being related to at least one type of interactive activity performed by the target user within the target time period, and the degree of participation of the target user in at least one type of interactive activity meeting a preset condition; a target item identification module configured to identify one or more target items associated with the target user using a machine learning model based on the activity information and sample information of at least one type of interactive activity; and a recommendation information presentation module configured to present recommendation information about the one or more target items.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figure 2 A flowchart of a method for recommending items according to some embodiments of the present disclosure is shown;

[0011] Figure 3 A flowchart showing an example item recommendation process according to some embodiments of the present disclosure is shown;

[0012] Figure 4 A schematic structural block diagram showing an apparatus for item recommendation according to some embodiments of the present disclosure; and

[0013] Figure 5 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0014] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of user information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0015] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's information. Thus, the user can autonomously choose whether to provide the user information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0016] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide the user information to the electronic device.

[0017] The activation of relevant functions of the embodiments of the present disclosure, the data obtained, the processing and storage methods of the data, etc., shall all be authorized in advance by the user and other rights holders associated with the user, and shall comply with the provisions of relevant laws and regulations and agreement rules between rights holders.

[0018] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0019] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0020] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0021] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0022] It is understandable that when adopting this technical solution, the data involved (including but not limited to the data itself, data acquisition, use, storage, and transmission) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0023] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0024] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0025] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0026] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0028] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", which are used interchangeably in this article. A model may also include different types of processing units or networks.

[0029] Example Environment

[0030] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100 , a component execution platform 110 can support the execution of a business component 125 . A user 140 can interact with the business component 125 via a client of the component execution platform 110 .

[0031] In some embodiments, the service component 125 can be downloaded and installed on the terminal device of the user 140. In some embodiments, the service component 125 can also be accessed through other means, such as through a web page. Figure 1In the environment 100 , in response to the business component 125 being started, the client of the component execution platform 110 may present the interface 150 of the business component 125 .

[0032] The business component 125 includes but is not limited to one or more of the following: a chat business component (also known as an instant messaging business IM component), a document business component, an audio and video conference business component, an email business component, a task business component, a calendar business component, an objective and key result (OKR) business component, etc. It can be understood that although Figure 1 A single business component is shown in FIG. 1 , but in fact, multiple business components can be installed on the component operation platform 110. Multiple business components can be integrated on the component operation platform 110, and such a component operation platform 110 can be regarded as a multifunctional collaboration platform. In the case where multiple business components are installed in the terminal device, these multiple business components can be integrated on one or more component operation platforms 110. In the component operation platform 110, people can start different business components as needed to complete corresponding information processing, sharing, communication, etc. The business component 125 can provide a content entity 126. The content entity 126 can be a content instance created by the user 140 or other users on the business component 125. For example, depending on the type of the business component 125, the content entity 126 can be a document (e.g., a word document, a pdf document, a presentation, a spreadsheet document, etc.), an email, a message (e.g., a conversation message on an instant messaging business component), a calendar, a schedule, a task, an audio, a video, an image, etc.

[0033] In some embodiments, the component operation platform 110 may provide a digital assistant 120. The digital assistant 120 may be provided by a separate business component, or may be integrated into a business component 125 that can provide a content entity. The business component for providing a client interface for a digital assistant may correspond to a single-function business component or a multi-function collaboration platform, such as an office suite or other collaboration platform that can integrate multiple components. It is understood that similar to the business component, although Figure 1 A single digital assistant is shown in the figure, but there may actually be multiple digital assistants.

[0034] In some embodiments, the digital assistant 120 supports the use of plug-ins. Each plug-in can provide one or more functions of a business component. Such plug-ins include, but are not limited to, one or more of the following: a search plug-in, a contact plug-in, a message plug-in, a document plug-in, a table plug-in, a mail plug-in, a calendar plug-in, a schedule plug-in, a task plug-in, and the like.

[0035] The digital assistant 120 may be an intelligent assistant of the user, having intelligent dialogue and information processing capabilities. In an embodiment of the present disclosure, the digital assistant 120 is used to interact with the user 140 to assist the user 140 in using a terminal device or a business component. An interaction window with the digital assistant 120 may be presented in the client interface. In the interaction window, the user 140 may communicate with the digital assistant 120 by inputting natural language, pictures, audio files, video files, web page files, etc., to instruct the digital assistant to assist in completing various tasks, including operations on the content entity 126.

[0036] In some embodiments, the digital assistant 120 can be included in the contact list of the current user 140 in the office suite as a contact of the user 140, or included in the information flow of the chat component. In some embodiments, the user 140 has a corresponding relationship with the digital assistant 120. For example, the first digital assistant corresponds to the first user, the second digital assistant corresponds to the second user, and so on. In some embodiments, the first digital assistant can correspond uniquely to the first user, the second digital assistant can correspond uniquely to the second user, and so on. That is, the first digital assistant of the first user can be specific to or exclusive to the first user. For example, in the process of the first digital assistant providing assistance or service to the first user, the first digital assistant can use its historical interaction information with the first user, the data authorized by the first user that it can access, and the current interaction context with the first user. If the first user is an individual or an individual, the first digital assistant can be regarded as a personal digital assistant. It can be understood that in the disclosed embodiments, the first digital assistant is based on the authorized access to the data to which the permission is granted by the first user. It should be understood that "uniquely corresponding" or similar expressions in the present disclosure are not intended to limit the first digital assistant to be updated accordingly based on the interaction process between the first user and the first digital assistant. Of course, depending on actual needs, the digital assistant 120 does not have to be specific to the current user 140, but can be a general digital assistant.

[0037] In some embodiments, multiple interaction modes between the user 140 and the digital assistant 120 can be provided, and the multiple interaction modes can be flexibly switched. When a certain interaction mode is triggered, the corresponding interaction area is presented to facilitate the interaction between the user 140 and the digital assistant 120. The user 140 and the digital assistant 120 interact in different ways in different interaction modes, so that it can be flexibly adapted to the interaction needs in different scenarios.

[0038] In some embodiments, information processing services specific to user 140 can be provided based on historical interaction information between user 140 and digital assistant 120 and / or a data range specific to user 140. In some embodiments, historical interaction information of user 140 interacting with digital assistant 120 in multiple interaction modes can be stored in association with user 140. In this way, in one interaction mode (any one or a designated one of the interaction modes) among the multiple interaction modes, digital assistant 120 can provide services to user 140 based on historical interaction information stored in association with user 140.

[0039] The digital assistant 120 can be called or awakened by an appropriate method (e.g., shortcut keys, buttons, or voice) to present an interaction window with the user 140. By selecting the digital assistant 120, the interaction window with the digital assistant 120 can be opened. The interaction window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. In other embodiments, the digital assistant 120 can be awakened through an entry control or menu provided in a page, or by inputting a preset instruction.

[0040] The interactive window between the digital assistant 120 and the user 140 may include a conversation window, such as a conversation window in an instant messaging service component or an instant messaging module of a target service component. In the conversation window, the interaction between the digital assistant 120 and the user 140 may be presented in the form of a conversation message. Alternatively or additionally, the interactive window between the digital assistant 120 and the user 140 may also include other types of windows, such as a window in a floating window mode, in which the user 140 may trigger the digital assistant 120 to perform a corresponding operation by inputting instructions, selecting shortcut instructions, etc.

[0041] In some embodiments, the digital assistant 120 may support an interactive mode of a conversation window, also referred to as a conversation mode. In this interactive mode, a conversation window between the user 140 and the digital assistant 120 is presented, in which the user 140 and the digital assistant 120 interact through conversation messages. In the conversation mode, the digital assistant 120 may perform tasks based on the conversation messages in the conversation window. In the interactive window, the user 140 inputs an interactive message, and the digital assistant 120 provides a reply message in response to the user input.

[0042] In some embodiments, the conversation mode between the user 140 and the digital assistant 120 can be called or awakened by an appropriate method (e.g., a shortcut key, a button, or voice) to present a conversation window. By selecting the digital assistant 120, a conversation window with the digital assistant 120 can be opened. The conversation window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like.

[0043] In some embodiments, the digital assistant 120 may support an interactive mode of a floating window (or floating window), also referred to as a floating window mode. When the floating window mode is triggered, an operation panel (also referred to as a floating window) corresponding to the digital assistant 120 is presented, and the user 140 may issue instructions to the digital assistant 120 based on the operation panel. In some embodiments, the operation panel may include at least one candidate shortcut instruction. Alternatively or additionally, the operation panel may include an input control for receiving instructions. In floating window mode, the digital assistant 120 may perform tasks according to instructions issued by the user 140 through the operation panel.

[0044] In some embodiments, the floating window mode of the user 140 and the digital assistant 120 can also be called or awakened by appropriate means (for example, shortcut keys, buttons, or voice) to present the corresponding operation panel. In some embodiments, the awakening of the digital assistant 120 can be supported in a specific business component, such as a document business component, to provide interaction in the floating window mode. In some embodiments, in order to trigger the floating window mode to present the operation panel corresponding to the digital assistant 120, an entry control for the digital assistant 120 can be presented in the business component interface. In response to detecting a trigger operation for the entry control, it can be determined that the floating window mode is triggered, and the operation panel corresponding to the digital assistant 120 is presented in the target interface area.

[0045] In some embodiments described below, for ease of discussion, the interaction window between the user and the digital assistant is mainly taken as an example of a conversation window.

[0046] The component operation platform 110 may be deployed locally on the terminal device of each user 140, and / or may be supported by a server-side device. For example, the terminal device of the user 140 may run a client of the component operation platform 110, which may support the interaction between the user 140 and the component operation platform 110 provided by the server. In the case where the component operation platform 110 runs locally on the user's terminal device, the user 145 may directly interact with the local component operation platform 110 using the terminal device. In the case where the component operation platform 110 runs on the server-side device, the server-side device may provide services to the client running in the terminal device based on the communication connection with the terminal device. The component operation platform 110 may present a corresponding interface 150 to the user 140 based on the operation of the user 140, so as to output to the user 140 and / or receive from the user 140 information related to the use of the component.

[0047] In some embodiments, at least some of the functions of business component 125 and / or at least some of the functions of digital assistant 120 may be implemented based on a target model. During the operation of business component 125, one or more target models 155 may be called. Target models 155 may be used to understand user input and provide services based on the output of target models 155, such as providing a response to the user.

[0048] Although shown as being independent of the component runtime platform 110, one or more target models 155 may run on the component runtime platform 110, or other remote servers. In some embodiments, the target model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). The language model can have question-answering capabilities by learning from a large amount of corpus. The target model 155 may also be based on other appropriate models.

[0049] The component operation platform 110 can be run on an appropriate electronic device. The electronic device here can be any type of device with computing capabilities, including a terminal device or a server device. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the component operation platform 110 can be implemented based on a cloud service.

[0050] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.

[0051] As mentioned above, applications can provide people with various services in work and life. The work summary function in some applications can organize and manage various information and knowledge to extract the matters that users have recently focused on (for example, projects). Then, it can recommend and display them to users in the form of cards, aiming to help users summarize their past work, reduce the cost of using the summary function, and allow users to better actively use the ability to generate matter summaries.

[0052] Extracting the items that users have recently focused on can enable users to better use the ability to generate project weekly reports. In order to extract or determine the items (also called projects) that users are concerned about, a key project recommendation algorithm is needed. The key project recommendation algorithm is a type of content (word) extraction, which extracts target entity words from document data. Currently, similar solutions mainly include named entity recognition (NER) and keyword extraction technology.

[0053] Named entity recognition technology refers to the technology of identifying entity content with specific meanings in text. These entities mainly include names of people, places, time, institutions, proper nouns, etc. The main implementation method of named entity recognition technology is to regard it as a sequence labeling task. A deep semantic model is established for named entity recognition and trained on a large amount of corpus, such as recurrent neural network (RNN) / convolutional neural network (CNN) and conditional random field (CRF) / hidden Markov model (HMM) technology.

[0054] Keyword extraction technology mainly refers to the technology of extracting key words from an article to be used as subject words, tags, etc. Most of the current mainstream technologies in this area are based on unsupervised algorithms, which are mainly divided into methods for calculating word weights based on document indicators, keyword discovery algorithms based on graph models, and discovery algorithms based on topic models. The method for calculating word weights based on document indicators calculates the weight of words by calculating the linguistic indicators of words and statistical features in the document (such as word position information, word frequency-inverse document frequency (TF-IDF) value, part of speech, mutual information, etc.). The higher the weight, the more important the word. The basic idea of ​​the keyword discovery algorithm based on the graph model is to segment the document, use the words as nodes, and define an edge between two words when they co-occur in a window of a certain length, and the frequency of co-occurrence is used as the weight on the edge. In this way, a graph can be formed, and keywords can be discovered by running a related analysis algorithm on the graph. The discovery algorithm based on the topic model can obtain the weight distribution of words in a document through topic model algorithms such as linear discriminant analysis (LDA), thereby obtaining the corresponding keywords.

[0055] However, project words are different from regular entity words. First, project words are not necessarily named entities, such as abbreviations, technical terms, etc. Since project words cover many types of words, it is difficult to perform strict entity distinction and annotation before named entity training. Secondly, project words are not necessarily keywords. A project word may be scattered across various documents, but it is not the core content in each document. Then, project words are not necessarily projects that the user himself is concerned about. Multiple project words may appear in a document or work content, but they may not be the ones that the current user is most concerned about. Therefore, traditional technologies cannot strictly meet the mining requests for key project words.

[0056] In order to solve the above problems, in the embodiments of the present disclosure, a solution for recommending items is proposed. According to various embodiments of the present disclosure, activity information of a target user in a target time period is obtained, the activity information is related to at least one type of interactive activity performed by the target user in the target time period, and the degree of participation of the target user in at least one type of interactive activity meets a preset condition. Based on the activity information and sample information of at least one type of interactive activity, a machine learning model is used to identify one or more target items associated with the target user. Recommendation information about one or more target items is presented.

[0057] According to the scheme disclosed in the present invention, the target user's unique activity information within the target time period can be filtered through the target user's behavior. Combined with the machine learning model, the matters that the target user is concerned about can be identified, thereby helping the target user to quickly review the key matters. In this way, the user can be helped to improve the efficiency of matter processing.

[0058] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0059] Figure 2 FIG. 2 is a flowchart of a method 200 for recommending items according to some embodiments of the present disclosure. The method 200 may be implemented in Figure 1 The components of the operating platform 110 will refer to Figure 1 The method 200 is described with reference to the environment 100 of FIG.

[0060] In box 210, the component operation platform 110 obtains the activity information of the target user within the target time period, and the activity information is related to at least one type of interactive activity performed by the target user within the target time period. The activity information here may refer to information that has undergone preprocessing operations, and the preprocessing operations may include data filtering, format conversion, data screening, data sorting and other operations. In some embodiments, the degree of participation of the target user in at least one type of interactive activity meets a preset condition. Such a preset condition indicates or explains that the user is active in the interactive activity. Depending on the type of interactive activity, the preset condition may be different. Thus, the work content that the user is concerned about can be filtered out. The activity information obtained in this way is conducive to the machine learning model to locate the matters that the user is concerned about.

[0061] In some embodiments, at least one type of interactive activity may include a conversation interaction between the target user and one or more users. Exemplarily, the interactive activity may include a single chat between the target user and one user and a group chat between the target user and multiple users. The activity information may include all conversation interaction records within the target time period. That is, for conversation-type interactive activities, the preset condition may be that the user participates in the conversation activity. If the user is only a member of a conversation and does not speak, such conversation information will not be considered. It should be noted that the activation of functions related to data acquisition, the acquired data, the processing and storage methods of the data, etc. in the embodiments of the present disclosure shall obtain the prior authorization of the user and other rights holders associated with the user, and shall comply with the relevant laws and regulations and the agreements between rights holders.

[0062] Alternatively or additionally, at least one type of interactive activity may include an editing operation of the target user on the content. The content may include various types of content, such as documents, emails, videos, etc. For example, the interactive activity may include editing operations such as supplementation and deletion, format adjustment, and paragraph reconstruction of the content in the document by the target user. The activity information may include the name of the document edited by the target user, the content edited by the target user, and the context information of the content edited by the target user. For another example, the interactive activity may also include the editing of the email by the target user. That is, for interactive activities related to content, the preset condition may be that the user edits the content. If the user only browses a certain content without editing it, then the information related to the content will not be taken into consideration. It should be noted that the activation of the data acquisition-related functions, the acquired data, the processing and storage methods of the data, etc. in the embodiments of the present disclosure shall obtain the advance authorization of the user and other rights holders associated with the user, and shall comply with the relevant laws and regulations and the agreement rules between the rights holders.

[0063] Alternatively or additionally, at least one type of interactive activity may include a real-time interactive scene in which the target user participates. Exemplarily, the interactive activity may include real-time interactive scenes such as the target user participating in a meeting and / or a live broadcast. Activity information may include information such as a summary of the meeting in which the user participated and / or a summary of the live broadcast. That is, for a real-time interactive scene, the preset condition may be that the user participates in the real-time interactive scene. If the user has only made an appointment for a real-time interactive scene or has been invited to participate in a real-time interactive scene but the user does not actually participate, then information about the real-time interactive scene will not be taken into consideration. It should be noted that the activation of functions related to data acquisition, the acquired data, the processing and storage methods of the data, etc. in the embodiments of the present disclosure shall obtain the advance authorization of the user and other rights holders associated with the user, and shall comply with the relevant laws and regulations and the agreements between rights holders.

[0064] At block 220, the component operation platform 110 uses a machine learning model to identify one or more target matters associated with the target user based on the activity information and the sample information of at least one type of interactive activity. The sample information may include an example of the corresponding target matter output by the machine learning model according to the activity information. The key items (also known as target matters) that the user is concerned about usually appear repeatedly in the user's daily work information, so the key item words can be identified by the machine learning model.

[0065] In some embodiments, prompt information can be generated based on the activity information and the sample information. The generation of prompt information will be described below with reference to Table 1, which is an example of the prompt information.

[0066] Table 1

[0067]

[0068] As shown in Table 1, the content between the start tag <work information> and the end tag < / work information> is the activity information, and the content between the start tag <item word> and the end tag < / item word> is the matter output by the machine learning model. The content between rows 17 and 32 of Table 1 is the sample information for at least one type of interactive activity, and this sample information shows an example of the corresponding target matter output by the machine learning model according to the activity information. Prompt information can be generated based on the activity information and the sample information.

[0069] After generating the prompt information, the component operation platform 110 can provide the prompt information to the machine learning model to obtain the model output of the machine learning model, and can determine one or more target matters based on the model output. In some embodiments, one or more target matters in the model output have a sorting order, and the target matters with a higher ranking are more closely associated with the target user. In this way, without large-scale annotation behavior, data mining work can be automatically completed based on the activity information of the target user and the machine learning model.

[0070] In some embodiments, initial information generated by the target user performing at least one type of interactive activity can be obtained, and at least one of filtering or format conversion can be performed on the initial information to obtain the activity information.

[0071] In some embodiments, when filtering the initial information, at least one of the following may be removed: information that is not related to the matter to be identified, or information about activities that have not yet started. The initial information here may include summaries of the target user's conversation interaction records, summaries of meetings, and documents, which may include work-irrelevant content (which may also be referred to as information that is not related to the matter to be identified) and to-do items (which may also be referred to as information about activities that have not yet started), and these initial information have different formats due to different data sources. Therefore, a filtering operation may be performed on the initial information to filter out content and to-do items that are not related to work in order to remove interference items and unify data from different data sources into activity information in the same format. In this way, the data quality of the activity information can be improved, making it easier for the machine learning model to understand, thereby improving the accuracy and stability of the output of the machine learning model.

[0072] In some embodiments, the sample information may include positive sample information related to the matter to be identified, and the positive sample information indicates the first sample of the interactive activity in at least one type of interactive activity. Exemplarily, in the case where the matter to be identified is work, the first sample may be a document, meeting, conversation, etc. related to the work. In some examples, the first sample may include various uses of the matter word. For example, rows 20 to 28 in Table 1 are positive samples. By providing positive sample information to the machine learning model, a clear learning goal can be provided for the machine learning model, which helps the machine learning model learn the correct behavior pattern, and can help the machine learning model optimize its decision boundary so that it can better distinguish between correct and incorrect outputs.

[0073] Alternatively or additionally, the sample information may include negative sample information that is unrelated to the matter to be identified, and the negative sample information indicates a second sample in at least one type of interactive activity. For example, in the case where the matter to be identified is work, the second sample may be noise, such as non-work information content. In the example of Table 1, row 29 is a negative sample. The output information sample in the prompt information (for example, row 32 in Table 1) does not have relevant words about this part of non-work information of the second sample, thereby prompting the machine learning model to ignore this part of non-work information. By providing negative sample information to the machine learning model, the discrimination ability of the machine learning model can be improved to avoid generating these negative sample outputs.

[0074] In some embodiments, the component execution platform 110 may determine a set of candidate items associated with the target user based on the activity information using a machine learning model. The machine learning model may determine the set of candidate items based on the input activity information and prompt information.

[0075] After determining the candidate item set, the component execution platform 110 may update the candidate item set based on the corresponding item names of the candidate items in the candidate item set, and determine one or more target items based on the updated candidate item set. In some examples, the component execution platform 110 may perform a deduplication operation on the candidate item set based on the similarity of the item names.

[0076] In some embodiments, in response to determining that the item name of the first candidate item in the candidate item set and the item name of the second candidate item meet a preset similarity condition, the component operation platform 110 can merge the first candidate item and the second candidate item into the same item. In some examples, there are items with relatively similar item names in the generated candidate item set, and the items that meet the preset similarity condition can be merged into the same item.

[0077] Alternatively or additionally, in response to determining that the item name of the third candidate item in the candidate item set and the item name of the target user's subscribed item meet a preset similarity condition, the third candidate item is removed from the candidate item set. In some examples, the item names of the items in the generated candidate item set are relatively similar to the item names of the target user's subscribed items, and the items that meet the preset similarity condition can be merged into the same item. In some examples, the item names of the items in the generated candidate item set are relatively similar to the keywords or aliases of the target user's subscribed items, and the items that meet the preset similarity condition can be merged into the same item.

[0078] In some embodiments, the preset similarity condition may include that the edit distance between the two compared item names is less than a threshold distance. For example, the threshold distance may be set to 2, and two candidate items whose edit distance between the item names is less than 2 are merged.

[0079] Alternatively or additionally, the preset similarity condition may include that the semantic similarity between the two item names being compared is less than a threshold similarity. In some examples, the two item names may be input into a predetermined similarity model to generate the semantic similarity between the two item names. When the semantic similarity between the two item names is less than a threshold similarity, the two candidate items corresponding to the two item names may be merged.

[0080] In some embodiments, the activity information is obtained at preset time intervals, and the time length of the target time period is not less than the time length of the preset time interval. In some examples, the activity information of the target user can be obtained every 3 days (as an example of the preset time interval), and the activity information of 5 days (as an example of the target time period) is taken each time to identify one or more target items associated with the target user. In this way, it can be ensured that the context for identifying the target item is sufficient.

[0081] In block 230 , the component execution platform 110 presents recommendation information about one or more target items. The component execution platform 110 may recommend the one or more target items to the user in a recommendation card.

[0082] In some embodiments, the component operation platform 110 may determine the first item from the one or more items based on the degree of association between the one or more items and the target user. In some examples, the degree of association between the one or more target items and the target user may be determined based on the model output of the machine learning model, and the target items that are closer to the front in the model output have a higher degree of association with the target user.

[0083] After determining the first matter, the component operation platform 110 can obtain summary information of the first matter within the target time period, and store the summary information for pushing to the target user in response to a viewing instruction for the first matter. In some examples, the target time period is 7 days, then a weekly report corresponding to the first matter can be generated and pushed to the target user. In this way, the target user can quickly identify key projects, clarify the progress of key projects, and quickly generate corresponding weekly reports based on this, saving manpower expenses and improving knowledge management efficiency. Although the pre-generation of the summary is described with reference to a single matter, summary information of the matter can be pre-generated for multiple first matters in an embodiment of the present disclosure.

[0084] In some embodiments, the remaining target items other than the first item in the candidate item set may only appear in the recommendation card, and the corresponding summary information is generated after the target user clicks on it, so as to avoid interfering with the target user.

[0085] Figure 3 A flow chart of an example item recommendation process 300 according to some embodiments of the present disclosure is shown. Process 300 may be viewed as an example implementation of process 200.

[0086] like Figure 3As shown, in box 310, work information (also called activity information) can be obtained. The work information here is the work information of the user, including user session information, meeting summary, and edited document information. The user session information can include all session information of the session in which the user participates, and can include the information of the speaker of each sentence. The meeting summary can include the summary of the meeting in which the user himself has participated. The edited document information can include the document content edited by the user himself and the context of the edited document content. In the stage of obtaining work information, filtering is performed according to user behavior operations, for example, only the user's active group chats, edited documents, and participated meetings are obtained. Work information that is weakly related to the user, such as documents with a short reading time, will not be obtained, so as to characterize the user's work identity and filter out the work content that the user cares about. The user's work information can be obtained once every M days, and after filtering, it is sent to the machine learning model to identify key project words (also called target items), and the work information of the most recent N days is obtained each time, and N can be greater than M. In this way, when the data of M days is small, obtaining N days of data can ensure sufficient context information.

[0087] In block 320, data preprocessing may be performed. Data preprocessing includes data filtering operations and format unification operations on the above work information. Data filtering operations are to filter out content not related to the work and to-do items to remove interference items. Format unification operations are to unify data from different data sources into the same format to facilitate the machine learning model to understand the input data.

[0088] In block 330, project extraction may be performed. The preprocessed work information is input into a machine learning model to obtain a model output of the machine learning model, which may include one or more project keywords.

[0089] In box 340, the extracted items may be deduplicated. In some examples, deduplication may be performed between generated key item words. In some examples, deduplication may be performed between generated item words and key item words that the user has subscribed to. In addition, keywords or aliases of the item words may be extracted from the weekly report generated by the key item words that the user has subscribed to. The keywords or aliases are used to assist in the deduplication operation between the generated item words and the key item words that the user has subscribed to.

[0090] In box 350, the deduplicated key words are saved and pushed regularly. For key words with high relevance to the user, a corresponding weekly report can be generated for the user by default. Key words with high user relevance can be key words that the user actively subscribes to or the top words in the model output of the machine learning model. The remaining words (for example, with relatively low confidence) can only appear in the recommendation card. The corresponding weekly report is generated only after the user clicks to avoid interference with the user.

[0091] Example devices and equipment

[0092] Figure 4 A schematic structural block diagram of an apparatus 400 for item recommendation according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented as or included in the component execution platform 110. Each module / component in the apparatus 400 may be implemented by hardware, software, firmware or any combination thereof.

[0093] like Figure 4 As shown, the device 400 includes an activity information acquisition module 410, which is configured to obtain activity information of a target user within a target time period, the activity information is related to at least one type of interactive activity performed by the target user within the target time period, and the degree of participation of the target user in at least one type of interactive activity meets a preset condition. The device 400 also includes a target item identification module 420, which is configured to identify one or more target items associated with the target user based on the activity information and sample information of the at least one type of interactive activity using a machine learning model. The device 400 also includes a recommendation information presentation module 430, which is configured to present recommendation information about one or more target items.

[0094] In some embodiments, the target item identification module 420 is further configured to generate prompt information based on activity information and sample information; provide the prompt information to the machine learning model to obtain a model output of the machine learning model; and determine one or more target items based on the model output.

[0095] In some embodiments, the sample information includes at least one of the following: positive sample information related to the matter to be identified, the positive sample information indicating a first sample of an interaction activity in at least one type of interaction activity, or negative sample information unrelated to the matter to be identified, the negative sample information indicating a second sample of an interaction activity in at least one type of interaction activity.

[0096] In some embodiments, at least one type of interactive activity includes at least one of the following: a conversational interaction between the target user and one or more users, an editing operation of the target user on the content, or participation of the target user in a real-time interactive scenario.

[0097] In some embodiments, the target item identification module 420 is further configured to determine a set of candidate items associated with the target user based on the activity information using a machine learning model; update the candidate item set based on the corresponding item names of the candidate items in the candidate item set; and determine one or more target items based on the updated candidate item set.

[0098] In some embodiments, the target item identification module 420 is further configured to merge the first candidate item and the second candidate item into the same item in response to determining that the item name of the first candidate item in the candidate item set and the item name of the second candidate item meet a preset similarity condition, or to remove the third candidate item from the candidate item set in response to determining that the item name of the third candidate item in the candidate item set and the item name of the subscribed item of the target user meet a preset similarity condition.

[0099] In some embodiments, the preset similarity condition includes at least one of the following: the edit distance between the two compared item names is less than a threshold distance, or the semantic similarity between the two compared item names is less than a threshold similarity.

[0100] In some embodiments, the activity information is acquired at preset time intervals, and the length of the target time period is not less than the length of the preset time interval.

[0101] In some embodiments, the device 400 also includes a push module, which is configured to determine a first item from one or more target items based on the degree of association between the one or more target items and the target user; obtain summary information of the first item within a target time period; and store the summary information for pushing to the target user in response to a viewing indication for the first item.

[0102] In some embodiments, the activity information acquisition module 410 is further configured to acquire initial information generated by the target user performing at least one type of interactive activity; and perform at least one of filtering or format conversion on the initial information to obtain the activity information.

[0103] In some embodiments, the activity information acquisition module 410 is further configured to remove at least one of the following from the initial information: information irrelevant to the matter to be identified, or information about an activity that has not yet started.

[0104] The units and / or modules included in the device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units and / or modules in the device 400 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0105] It should be understood that one or more steps in the above method can be performed by a suitable electronic device or a combination of electronic devices. Such an electronic device or a combination of electronic devices may include, for example, Figure 1 The components in the operating platform 110.

[0106] Figure 5 A block diagram of an electronic device 500 is shown in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 5 The electronic device 500 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can be used to implement Figure 1 The component operation platform 110.

[0107] like Figure 5 As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0108] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.

[0109] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0110] The communication unit 540 enables communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0111] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device (e.g., a network card, a modem, etc.) that allows the electronic device 500 to communicate with one or more other electronic devices. Such communication may be performed via an input / output (I / O) interface (not shown).

[0112] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0113] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0114] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0115] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0116] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0117] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for recommending an event, comprising: Acquiring activity information of a target user within a target time period, the activity information being related to at least one type of interactive activity performed by the target user within the target time period, the participation level of the target user in the at least one type of interactive activity satisfying a preset condition, and the preset condition indicating that the target user is active in the interactive activity; Based on the activity information and sample information of the at least one type of interactive activity, using a machine learning model, identifying one or more target items associated with the target user; presenting recommendation information about the one or more target items; Determining a first item from the one or more target items based on the degree of association between the one or more target items and the target user; as well as Pre-acquire summary information of the first matter within the target time period for pushing to the target user, wherein the summary information of the remaining target items in the one or more target items except the first item is configured to be generated in response to the target user triggering the recommendation information, The sample information includes positive sample information related to the matter to be identified and negative sample information unrelated to the matter to be identified, the positive sample information indicates a first sample of an interactive activity in the at least one type of interactive activity, and the negative sample information indicates a second sample of an interactive activity in the at least one type of interactive activity.

2. The method of claim 1, wherein identifying one or more target items associated with the target user comprises: Generate prompt information based on the activity information and the sample information; Providing the prompt information to the machine learning model to obtain a model output of the machine learning model; as well as Based on the model output, the one or more target items are determined.

3. The method of claim 1 , wherein identifying one or more target items associated with the target user during the target time period comprises: Based on the activity information, using the machine learning model, determining a set of candidate items associated with the target user; Updating the candidate item set based on corresponding item names of the candidate items in the candidate item set; as well as The one or more target items are determined based on the updated candidate item set.

4. The method according to claim 3, wherein updating the candidate item set comprises at least one of the following: In response to determining that the item name of the first candidate item in the candidate item set and the item name of the second candidate item meet a preset similarity condition, merging the first candidate item and the second candidate item into the same item, or In response to determining that the item name of the third candidate item in the candidate item set and the item name of the subscribed item of the target user meet the preset similarity condition, the third candidate item is removed from the candidate item set.

5. The method according to claim 4, wherein the preset similarity condition comprises at least one of the following: The edit distance between the two item names being compared is less than the threshold distance, or The semantic similarity between the two compared item names is less than the threshold similarity. 6 . The method according to claim 1 , wherein the activity information is acquired at a preset time interval, and the time length of the target time period is not less than the time length of the preset time interval.

7. The method according to claim 1, further comprising: In response to acquiring the summary information, the summary information is stored for being pushed to the target user in response to a viewing instruction for the first item.

8. The method according to claim 1, wherein obtaining the activity information comprises: Acquiring initial information generated by the target user performing the at least one type of interactive activity; as well as At least one of filtering and format conversion is performed on the initial information to obtain the activity information.

9. The method of claim 8, wherein filtering the initial information comprises removing at least one of the following from the initial information: Information that is not relevant to the matter being identified, or Information about events that have not yet started.

10. The method of claim 1, wherein the at least one type of interactive activity comprises at least one of the following: The target user interacts with one or more users in a session, The target user's editing operation on the content, or A real-time interactive scenario in which the target user participates.

11. A device for recommending items, comprising: an activity information acquisition module, configured to acquire activity information of a target user within a target time period, the activity information being related to at least one type of interactive activity performed by the target user within the target time period, the participation degree of the target user in the at least one type of interactive activity satisfying a preset condition, and the preset condition indicating that the target user is active in the interactive activity; a target item identification module, configured to identify one or more target items associated with the target user using a machine learning model based on the activity information and sample information of the at least one type of interactive activity; A recommendation information presentation module, configured to present recommendation information about the one or more target items; as well as A push module, configured to determine a first item from the one or more target items based on the relevance between the one or more target items and the target user; and obtaining summary information of the first matter within the target time period in advance for pushing to the target user, wherein the summary information of the remaining target items in the one or more target items except the first item is configured to be generated in response to the target user triggering the recommendation information, The sample information includes positive sample information related to the matter to be identified and negative sample information unrelated to the matter to be identified, the positive sample information indicates a first sample of an interactive activity in the at least one type of interactive activity, and the negative sample information indicates a second sample of an interactive activity in the at least one type of interactive activity.

12. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 10.

Images