CN114118937A

CN114118937A - Information recommendation method and device based on task, electronic equipment and storage medium

Info

Publication number: CN114118937A
Application number: CN202111215907.6A
Authority: CN
Inventors: 姚向民; 王保卫; 刘洋
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-10-19
Filing date: 2021-10-19
Publication date: 2022-03-01

Abstract

The disclosure provides a task-based information recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of natural language processing, intelligent search and cloud service. The specific implementation scheme is as follows: performing semantic analysis on at least one piece of conversation content in the conversation to determine a task keyword; matching the task keywords with task tags of the existing tasks; under the condition that the task tags are matched, recommending that a subtask to be handled is added in the existing task according to at least one piece of conversation content; under the condition that the task labels are not matched, the target task is recommended to be created according to the task keywords, therefore, the maintenance and the new creation of the task are realized by performing semantic analysis on the session, the process that a user manually creates the task and the condition that the task follow-up cannot be completed in time are avoided, and the creation efficiency and the timeliness of the task follow-up are improved.

Description

Information recommendation method and device based on task, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to the field of natural language processing, intelligent search, and cloud service technologies, and in particular, to a task-based information recommendation method and apparatus, an electronic device, and a storage medium.

Background

At present, the intelligent office field is developed more and more quickly, more users and enterprises abandon the traditional office mode and begin to turn to a novel intelligent office platform, so that the requirement of communication and cooperative work can be met anytime and anywhere, and communication are more convenient and faster; in the scene of work cooperation, a lot of requirements are that a plurality of users cooperate to complete the processing of one work task; and many tasks are generated in the process of communication and communication of the messages, the messages are often scattered in each chat group, how to complete task aggregation and automatically sense potential tasks in the chat process, so that automatic help prompts are generated in the communication process, users can be promoted in an early stage according to a task cooperation mode, and the work cooperation efficiency is very important to improve.

Disclosure of Invention

The disclosure provides a method and a device for task-based information recommendation, an electronic device and a storage medium.

According to an aspect of the present disclosure, there is provided a task-based information recommendation method, including: acquiring at least one piece of conversation content in a conversation; performing semantic analysis on the at least one piece of dialogue content to determine task keywords; matching the task keywords with task tags of existing tasks; under the condition that the task tags are matched, recommending that a sub-task to be handled is added into the existing task according to the at least one piece of dialogue content; and under the condition that the task labels are not matched, recommending and creating a target task according to the task keyword.

According to another aspect of the present disclosure, there is provided a task-based information recommendation apparatus including: the acquisition module is used for acquiring at least one piece of conversation content in the conversation; the analysis module is used for performing semantic analysis on the at least one piece of conversation content to determine task keywords; the matching module is used for matching the task keywords with task labels of the existing tasks; the first recommending module is used for recommending that a sub-task to be handled is added to the existing task according to the at least one piece of dialogue content under the condition that the task tags are matched; and the second recommending module is used for recommending and creating the target task according to the task keyword under the condition that the task labels are not matched.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of the method of an embodiment of the first aspect of the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;

FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;

FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;

FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

FIG. 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

FIG. 6 is a schematic diagram according to a sixth embodiment of the present disclosure;

FIG. 7 is a flowchart illustration of a method of task-based information recommendation in accordance with an embodiment of the present disclosure;

FIG. 8 is a schematic diagram according to a seventh embodiment of the present disclosure;

FIG. 9 is a block diagram of an electronic device for implementing a task-based information recommendation method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the related technology, a user needs to manually establish a task card and timely follow-up and update tasks. However, when the user communicates and discusses the task card, the maintenance of the task card may be omitted, and the upgrade follow-up cannot be completed in time.

In order to solve the above problems, the present disclosure provides a task-based information recommendation method, apparatus, electronic device, and storage medium.

Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure. It should be noted that the task-based information recommendation method according to the embodiment of the present disclosure may be applied to a task-based information recommendation device according to the embodiment of the present disclosure, and the device may be configured in an electronic device. The electronic device may be a mobile terminal, for example, a mobile phone, a tablet computer, a personal digital assistant, and other hardware devices with various operating systems.

As shown in fig. 1, the task-based information recommendation method may include the steps of:

step 101, at least one piece of dialog content in a session is acquired.

In an embodiment of the present disclosure, at least one piece of dialog content may be obtained from the session content of the session group.

Step 102, performing semantic analysis on at least one piece of conversation content to determine task keywords.

Further, in the embodiment of the present disclosure, a semantic analysis technique in a natural language processing technique may be adopted to perform semantic analysis on at least one piece of dialog content to obtain a keyword in the dialog content, where the keyword is, for example, a project name, a team name, a task name, and the like, and then, the obtained keyword may be used as a task keyword, where the semantic analysis technique mainly understands semantic information such as words in the dialog content, topics of previous and next dialog contents, and a meaning of the whole dialog content, and belongs to one of natural language processing techniques.

And 103, matching the task keywords with the task tags of the existing tasks.

And then, performing similarity matching on the task keywords and the task tags of the existing tasks by adopting a similarity algorithm to obtain the matching degree of the task keywords and the task tags of the existing tasks.

And 104, under the condition that the task labels are matched, recommending to-do subtasks to be added into the existing tasks according to at least one piece of conversation content.

As an example, in the case of matching the task tags, that is, when the matching degree between the task keyword and the task tag of the existing task is greater than the set matching threshold, indicating that the task keyword has an association relationship with the existing task, the related content of the to-be-handled subtask, for example, the original text of the chat conversation, may be extracted according to at least one piece of conversation content, and the to-be-handled subtask, the status information of the to-be-handled subtask, and the related participant information of the to-be-handled subtask may be extracted from the original text. And then, adding the sub-task to be handled to the existing task.

And 105, under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword.

As another example, in the case that the task tags do not match, that is, when the matching degree of the task keyword and the task tags of the existing tasks is less than or equal to the set matching threshold, the creation of the target task may be recommended to the user according to the task keyword.

In summary, by acquiring at least one piece of dialog content in a session; performing semantic analysis on at least one piece of conversation content to determine task keywords; matching the task keywords with task tags of the existing tasks; under the condition that the task tags are matched, recommending that a subtask to be handled is added in the existing task according to at least one piece of conversation content; and under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword. Therefore, new establishment and maintenance of tasks are achieved through semantic analysis of the session. The process of manual creation by a user and the condition that the task follow-up cannot be completed in time are avoided, and the creation efficiency and the timeliness of the task follow-up are improved.

To clearly illustrate how to recommend adding the to-do sub-task to the existing task according to at least one dialog content, as shown in fig. 2, fig. 2 is a schematic diagram according to a second embodiment of the present disclosure, in the embodiment of the present disclosure, the to-do sub-task content and the participants may be extracted according to the dialog content, the description information of the to-do sub-task may be generated according to the to-do sub-task content and the participants, and the description information of the to-do sub-task and the to-do sub-task may be added to the existing task, the embodiment shown in fig. 2 may include the following steps:

step 201, at least one dialog content in the session is acquired.

At least one piece of dialog content is semantically analyzed to determine task keywords, step 202.

Step 203, matching the task keywords with the task tags of the existing tasks.

And 204, under the condition that the task tags are matched, extracting at least one of the subtask content to be handled and the participators according to at least one piece of conversation content.

As an example, part-of-speech recognition is performed on words contained in at least one piece of conversation content; and extracting the subtask content to be handled from at least one piece of conversation content according to the part of speech of each word.

That is, at least one dialog content may be segmented, and each word included in the segmentation result may be subjected to part-of-speech recognition, so as to extract the to-be-handled subtask content from the at least one dialog content. For example, each word contained in the dialog content is divided into real words and imaginary words according to the actual meaning and the grammar structure, and irrelevant content of the dialog content is removed, so that the to-be-handled subtask content is extracted from at least one dialog content.

Optionally, the participant of the pending subtask is determined according to the speaker of the at least one piece of dialog content, the related person included in the at least one piece of dialog content, and the creator of the existing task.

For example, person a creates an existing task to go to an amusement park on weekends, speaker B publishes a piece of conversation content in the conversation group that instructs person C to perform the existing task group, and person a, speaker B, and person C are all participants of the pending subtasks.

Step 205, generating description information of the to-be-handled subtask according to at least one of the at least one dialog content, the to-be-handled subtask content, and the participant.

In the embodiment of the disclosure, after the content of the sub-task to be handled is extracted and the participants of the sub-task to be handled are determined, the description information of the sub-task to be handled can be generated according to at least one of the at least one piece of conversation content, the content of the sub-task to be handled and the participants, and the related information of the sub-task to be handled can be intuitively acquired according to the description information. It should be noted that the description information of the to-be-handled subtask may include state information of the to-be-handled subtask, tag information, source information of the to-be-handled subtask, information of a participant of the to-be-handled subtask, and content information of the to-be-handled subtask. The state information of the sub-task to be handled may include running state information of the sub-task to be handled, cancellation state information of the sub-task to be handled, or completion state information of the sub-task to be handled; the source information of the to-do subtask may be related information of a source of the to-do subtask, for example, group chat information from which the to-do subtask originates; the content description information of the subtask to be handled can be related text description information of the content of the subtask to be handled; the tag information of the to-do sub-task may be a task keyword, such as "blob" or "Disney", etc.

And step 206, outputting the prompt information for adding the to-be-handled subtasks and outputting the description information of the to-be-handled subtasks.

Further, in order to better recommend the to-do subtasks to the user, after the description information of the to-do subtasks is generated, the prompt information for adding the to-do subtasks can be generated, and the prompt information for adding the to-do subtasks and the description information of the to-do subtasks are output, so that the user is reminded to follow up and maintain the added to-do subtasks.

And step 207, under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword.

It should be noted that the execution processes of steps 201 to 203 and step 207 may be implemented by any one of the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this, and are not described again.

In conclusion, under the condition that the task tags are matched, at least one of the subtask content to be handled and the participators is extracted according to at least one piece of conversation content; generating description information of the subtask to be handled according to at least one of the at least one piece of conversation content, the subtask content to be handled and the participators; and outputting prompt information for adding the to-be-handled subtasks and outputting description information of the to-be-handled subtasks. Therefore, the to-do subtasks added to the existing tasks can be recommended.

In order to recommend a target task created according to a task keyword under the condition that the task tags are not matched, as shown in fig. 3, fig. 3 is a schematic diagram according to a third embodiment of the present disclosure, in the embodiment of the present disclosure, a plurality of recommended tags of the target task may be generated according to the task keyword and tags of existing tasks, and prompt information for creating the target task and the plurality of recommended tags are output, where the embodiment shown in fig. 3 may include the following steps:

step 301, at least one piece of dialog content in a session is acquired.

At step 302, semantic analysis is performed on at least one piece of dialog content to determine task keywords.

Step 303, matching the task keywords with the task tags of the existing tasks.

And 304, under the condition that the task labels are matched, recommending that a to-do subtask is added to the existing task according to at least one piece of conversation content.

And 305, under the condition that the task labels are not matched, generating a plurality of recommended labels of the target task according to the task keywords and the labels of the existing tasks.

In the embodiment of the present disclosure, in a case that the task tags are not matched, in order to avoid duplication of the recommended tags with the tags of the existing tasks, a plurality of recommended tags of the target task may be generated according to the task keywords and the tags of the existing tasks, for example, the task keywords are "clique" and "disney", the tags of the existing tasks are "disney", and the recommended tags may be "clique".

And step 306, outputting prompt information for creating the target task and outputting a plurality of recommended labels.

Further, in order to create the target task when the task tags do not match, after the plurality of recommended tags of the target task are generated, prompt information for creating the target task may be generated, and the prompt information for creating the target task and the plurality of recommended tags may be output to prompt the user to create the target task according to the recommended tags.

It should be noted that the execution processes of steps 301 to 304 may be implemented by any one of the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and are not described again.

In conclusion, under the condition that the task labels are not matched, a plurality of recommended labels of the target task are generated according to the task keywords and the labels of the existing tasks; and outputting prompt information for creating the target task and outputting a plurality of recommendation labels. Therefore, the target task can be created according to the recommended label under the condition that the task labels are not matched, the manual creation process of the user is avoided, and the labor is saved.

In order to more accurately create a target task in the case that task tags do not match, as shown in fig. 4, fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure, and after outputting prompt information for creating the target task and outputting a plurality of recommended tags, a target tag may be determined in response to a selection operation on the plurality of recommended tags, and a target task marked with the target tag may be created, where the embodiment shown in fig. 4 may include the following steps:

step 401, at least one dialog content in a session is acquired.

At least one piece of dialog content is semantically analyzed to determine task keywords, step 402.

And step 403, matching the task keywords with the task tags of the existing tasks.

And step 404, under the condition that the task labels are matched, recommending to add the to-be-handled subtask into the existing task according to at least one piece of conversation content.

And 405, under the condition that the task labels are not matched, generating a plurality of recommended labels of the target task according to the task keywords and the labels of the existing tasks.

And step 406, outputting prompt information for creating the target task and outputting a plurality of recommended labels.

Step 407, in response to the selection operation of the plurality of recommended tags, determining the target tag.

In the embodiment of the disclosure, in response to a selection operation of a client on a plurality of recommended tags, a target tag is determined according to a selection operation result, for example, the plurality of recommended tags include a recommended tag a, a recommended tag B, and a recommended tag C, and in response to the selection operation of the client on the recommended tag a, the recommended tag a is taken as the target tag.

And step 408, creating the target task marked with the target label.

And further, according to the target label, creating the target task marked with the target label.

It should be noted that the execution processes of steps 401 to 406 may be implemented by any one of the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and are not described again.

In conclusion, the target label is determined by responding to the selection operation of the plurality of recommended labels; and creating the target task marked with the target label, so that the target task can be created more accurately under the condition that the task labels are not matched.

In order to improve the matching degree between the task keyword and the task tag of the existing task, as shown in fig. 5, fig. 5 is a schematic diagram according to a fifth embodiment of the present disclosure, before the task keyword is matched with the task tag of the existing task, the existing task may be obtained first, and the embodiment shown in fig. 5 may include the following steps:

step 501, at least one piece of dialog content in a session is acquired.

Step 502, performing semantic analysis on at least one piece of dialog content to determine task keywords.

Step 503, query the existing task.

As an example, within the group to which the session belongs, an existing task is queried. For example, in a group to which the session belongs, the query is performed according to the name of the group, the session content in the group, or the group members in the group, so as to obtain the existing task.

As another example, queries may be made for each client participating in the session to obtain existing tasks.

As another example, in a group to which the session belongs, query may be performed according to a name of the group, session content in the group, or group members in the group, and meanwhile, query is performed on each client participating in the session to obtain an existing task.

And step 504, matching the task keywords with the task tags of the existing tasks.

And 505, under the condition that the task tags are matched, recommending to add the to-be-handled subtask into the existing task according to at least one piece of conversation content.

And step 506, under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword.

It should be noted that the execution processes of steps 501 to 502 and steps 504 to 506 may be implemented by any one of the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and are not described again.

In conclusion, the existing tasks can be accurately acquired by inquiring the existing tasks, so that the matching degree of the task keywords and the task labels of the existing tasks can be improved.

In order to accurately determine a task keyword, as shown in fig. 6, fig. 6 is a schematic diagram according to a sixth embodiment of the present disclosure, in the embodiment of the present disclosure, keyword extraction may be performed on at least one piece of dialog content including task words in a task word library to determine the task keyword, and the embodiment shown in fig. 6 may include the following steps:

step 601, at least one piece of dialogue content in the conversation is obtained.

Step 602, performing keyword extraction on at least one piece of dialogue content containing task words in the task word library to determine task keywords.

In order to filter out conversation contents containing useless information, each participle in the conversation contents can be compared with task words in a task word bank to screen the conversation contents containing the task words in the task word bank, and then keyword extraction is carried out on at least one conversation content containing the task words in the task word bank to determine task keywords.

Step 603, matching the task keywords with the task tags of the existing tasks.

And step 604, under the condition that the task tags are matched, recommending to-do subtasks to be added into the existing tasks according to at least one piece of conversation content.

And step 605, under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword.

It should be noted that the execution processes of step 601 and steps 603 to 605 may be implemented by any one of the embodiments of the present disclosure, and the embodiments of the present disclosure do not limit this and are not described again.

In summary, the task keyword can be accurately determined by performing keyword extraction on at least one piece of dialog content including the task word in the task thesaurus to determine the task keyword.

In order to more clearly illustrate the above embodiments, the description will now be made by way of example.

For example, as shown in fig. 7, performing semantic analysis on a session message in a group, determining a task keyword, combining the task keyword with associated information of a group where the session message is located and a personal task card, a task card of a message originator, scene information of a public task card of a collaborating party, and the like, and simultaneously combining the task keyword with an existing task card, group properties, active keyword information discussed by the group, and the like to generate a recommendation tag, then performing task card management based on the recommendation tag, for example, recording all task card data associated with the person and all task cards associated in a specific scene (a certain group), and performing matching through the recommended tag to recommend and associate the task cards with the corresponding group; or a new task card is created, the precipitation of key information and the generation of the task card in the group discussion process are solved, and the valuable task card production process is effectively improved.

The task-based information recommendation method of the embodiment of the disclosure acquires at least one piece of conversation content in a conversation; performing semantic analysis on at least one piece of conversation content to determine task keywords; matching the task keywords with task tags of the existing tasks; under the condition that the task tags are matched, recommending that a subtask to be handled is added in the existing task according to at least one piece of conversation content; and under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword. Therefore, new establishment and maintenance of tasks are achieved through semantic analysis of the session. The method and the device avoid the process of manual creation of the user and the condition that the task follow-up cannot be completed in time, and improve the creation efficiency of the task and the timeliness of the task follow-up.

In order to realize the embodiment, the disclosure further provides a task-based information recommendation device.

Fig. 8 is a schematic diagram according to a seventh embodiment of the present disclosure, and as shown in fig. 8, a task-based information recommendation apparatus 800 includes: an obtaining module 810, an analyzing module 820, a matching module 830, a first recommending module 840 and a second recommending module 850.

The obtaining module 810 is configured to obtain at least one piece of dialog content in a session; an analysis module 820 for performing semantic analysis on at least one piece of dialog content to determine task keywords; the matching module 830 is configured to match the task keyword with a task tag of an existing task; the first recommending module 840 is used for recommending that a sub-task to be handled is added to an existing task according to at least one piece of dialogue content under the condition that the task tags are matched; and a second recommending module 850, configured to recommend and create the target task according to the task keyword under the condition that the task labels are not matched.

As a possible implementation manner of the embodiment of the present disclosure, the first recommending module 840 is configured to: under the condition that the task tags are matched, extracting at least one of the subtask content to be handled and the participators according to at least one piece of conversation content; generating description information of the subtask to be handled according to at least one of the at least one piece of conversation content, the subtask content to be handled and the participators; and outputting prompt information for adding the to-be-handled subtasks and outputting description information of the to-be-handled subtasks.

As a possible implementation manner of the embodiment of the present disclosure, the first recommending module 840 is further configured to: and determining the participants of the to-be-handled subtask according to the speaker of the at least one conversation content, the relatives contained in the at least one conversation content and the creator of the existing task.

As a possible implementation manner of the embodiment of the present disclosure, the first recommending module 840 is further configured to: performing part-of-speech recognition on each word contained in the at least one piece of dialogue content; and extracting the subtask content to be handled from at least one piece of conversation content according to the part of speech of each word.

As a possible implementation manner of the embodiment of the present disclosure, the second recommending module 850 is configured to: under the condition that the task labels are not matched, generating a plurality of recommended labels of the target task according to the task keywords and the labels of the existing tasks; and outputting prompt information for creating the target task and outputting a plurality of recommendation labels.

As a possible implementation manner of the embodiment of the present disclosure, the task-based information recommendation apparatus 800 further includes: a determining module and a creating module.

The determining module is used for responding to the selection operation of the plurality of recommended labels and determining a target label; and the creating module is used for creating the target task marked with the target label.

As a possible implementation manner of the embodiment of the present disclosure, the task-based information recommendation apparatus 800 further includes: and (5) a query module.

Wherein the query module is configured to perform at least one of: inquiring the existing tasks in the group to which the session belongs; and querying each client participating in the session for the existing task.

As a possible implementation manner of the embodiment of the present disclosure, the analysis module 820 is configured to: and extracting keywords of the at least one piece of dialogue content containing the task words in the task word library to determine the task keywords.

The task-based information recommendation device of the embodiment of the disclosure acquires at least one piece of conversation content in a conversation; performing semantic analysis on at least one piece of conversation content to determine task keywords; matching the task keywords with task tags of the existing tasks; under the condition that the task tags are matched, recommending that a subtask to be handled is added in the existing task according to at least one piece of conversation content; and under the condition that the task labels are not matched, recommending and creating the target task according to the task keyword. Therefore, new establishment and maintenance of tasks are achieved through semantic analysis of the session. The process that the user manually creates the task and the condition that the task follow-up cannot be completed in time are avoided, and the task creation efficiency and the task follow-up timeliness are improved.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all carried out on the premise of obtaining the consent of the user, and all accord with the regulation of related laws and regulations without violating the good custom of the public order.

In order to implement the above embodiments, the present disclosure also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the embodiments of fig. 1-7.

To achieve the above embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method according to the embodiments shown in fig. 1 to 7.

In order to implement the above embodiments, the present disclosure also proposes a computer program product comprising a computer program which, when executed by a processor, implements the method described in the embodiments shown in fig. 1 to 7.

According to an embodiment of the present disclosure, the present disclosure also proposes an electronic device, a readable storage medium, and a computer program product.

FIG. 9 illustrates a schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 9, the apparatus 900 includes a computing unit 901 that can perform various appropriate actions and processes in accordance with a computer program stored in a ROM (Read-Only Memory) 902 or a computer program loaded from a storage unit 908 into a RAM (Random Access Memory) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The calculation unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An I/O (Input/Output) interface 905 is also connected to the bus 904.

A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, and the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing Unit 901 include, but are not limited to, a CPU (Central Processing Unit), a GPU (graphics Processing Unit), various dedicated AI (Artificial Intelligence) computing chips, various computing Units running machine learning model algorithms, a DSP (Digital Signal Processor), and any suitable Processor, controller, microcontroller, and the like. The calculation unit 801 executes the respective methods and processes described above, such as the task-based information recommendation method. For example, in some embodiments, the task-based information recommendation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 900 via ROM 902 and/or communications unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the task-based information recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the task-based information recommendation method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be realized in digital electronic circuitry, Integrated circuitry, FPGAs (Field Programmable Gate arrays), ASICs (Application-Specific Integrated circuits), ASSPs (Application Specific Standard products), SOCs (System On Chip, System On a Chip), CPLDs (Complex Programmable Logic devices), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or flash Memory, an optical fiber, a CD-ROM (Compact Disc Read-Only-Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a Display device (e.g., a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), internet, and blockchain Network.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be noted that artificial intelligence is a subject for studying a computer to simulate some human thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware and software technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A task-based information recommendation method includes:

acquiring at least one piece of conversation content in a conversation;

performing semantic analysis on the at least one piece of dialogue content to determine task keywords;

matching the task keywords with task tags of existing tasks;

under the condition that the task tags are matched, recommending that a sub-task to be handled is added into the existing task according to the at least one piece of dialogue content;

and under the condition that the task labels are not matched, recommending and creating a target task according to the task keyword.

2. The method of claim 1, wherein the recommending, in the event that the task tag matches, to add a to-do sub-task in the existing task according to the at least one piece of dialog content comprises:

under the condition that the task tags are matched, extracting at least one of subtask content to be handled and participators according to the at least one piece of conversation content;

generating description information of the subtask to be handled according to at least one of the at least one piece of conversation content, the subtask content to be handled and the participator;

and outputting prompt information for adding the to-be-handled subtasks and outputting description information of the to-be-handled subtasks.

3. The method of claim 2, wherein the extracting at least one of to-do subtask content and participants from the at least one piece of dialog content comprises:

and determining the participants of the to-be-handled subtask according to the speaker of the at least one conversation content, the relatives contained in the at least one conversation content and the creator of the existing task.

4. The method of claim 2, wherein the extracting at least one of to-do subtask content and participants from the at least one piece of dialog content comprises:

performing part-of-speech recognition on each word contained in the at least one piece of dialogue content;

and extracting the subtask content to be handled from the at least one piece of conversation content according to the part of speech of each word.

5. The method of claim 1, wherein the creating a target task according to the task keyword recommendation in the case that the task tags do not match comprises:

under the condition that the task labels are not matched, generating a plurality of recommended labels of the target task according to the task keywords and the labels of the existing tasks;

and outputting prompt information for creating the target task and outputting the plurality of recommended labels.

6. The method of claim 5, wherein after the outputting the prompt to create the target task and outputting the plurality of recommended tags, further comprising:

in response to the selection operation of the plurality of recommended labels, determining a target label;

and creating the target task marked with the target label.

7. The method of any of claims 1-6, wherein prior to matching the task keyword with a task tag of an existing task, further comprising at least one of:

querying the existing task in the group to which the session belongs;

and inquiring the existing tasks for each client participating in the session.

8. The method of any of claims 1-6, wherein the semantically analyzing the at least one dialog content to determine task keywords comprises:

and extracting keywords of the at least one piece of dialogue content containing the task words in the task word library to determine the task keywords.

9. A task-based information recommendation apparatus comprising:

the acquisition module is used for acquiring at least one piece of conversation content in the conversation;

the analysis module is used for performing semantic analysis on the at least one piece of conversation content to determine task keywords;

the matching module is used for matching the task keywords with task labels of the existing tasks;

the first recommending module is used for recommending that a sub-task to be handled is added to the existing task according to the at least one piece of dialogue content under the condition that the task tags are matched;

and the second recommending module is used for recommending and creating the target task according to the task keyword under the condition that the task labels are not matched.

10. The apparatus of claim 9, wherein the first recommendation module is to:

11. The apparatus of claim 10, wherein the first recommending module is further configured to:

12. The apparatus of claim 10, wherein the first recommending module is further configured to:

13. The apparatus of claim 9, wherein the second recommendation module is to:

14. The apparatus of claim 13, wherein the apparatus further comprises:

the determining module is used for responding to the selection operation of the plurality of recommended labels and determining a target label;

and the creating module is used for creating the target task marked with the target label.

15. The apparatus of any of claims 9-14, wherein the apparatus further comprises:

a query module to perform at least one of:

querying the existing task in the group to which the session belongs;

and inquiring the existing tasks for each client participating in the session.

16. The apparatus of any of claims 9-14, wherein the analysis module is to:

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.

19. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-8.