Item processing method and device, electronic equipment and storage medium
The target model is used to evaluate the probability of existing tasks of the target personnel and intelligently recommend the target task time period, which solves the conflict problem in the arrangement of tasks for multiple people and improves the efficiency of task arrangement.
Patent Information
- Application Number
- CN202510896735.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-30
- Publication Date
- 2025-10-17
Smart Images
Figure CN120806903A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of computer, and particularly relates to a processing method and device of an event, an electronic device and a storage medium. BACKGROUND
[0002] In work and life, there are often situations where multiple personnel meet together to participate in the same event, such as participating in the same online meeting, participating in the same discussion group, etc. However, multiple personnel may each have an existing event that has been arranged, and the automatically recommended setting period when generating the event may conflict with the setting period of the existing event, causing inconvenience. SUMMARY
[0003] The present disclosure provides a processing method and device of an event, an electronic device and a storage medium.
[0004] The present disclosure adopts the following technical solutions.
[0005] In some embodiments, the present disclosure provides a processing method of an event, comprising:
[0006] In response to identifying that there is an intention to arrange a target event among multiple conversation members, acquiring the identification of each target personnel participating in the target event;
[0007] determining the probability score of each target personnel participating in the respective existing event by using a target model, wherein the input of the target model includes: the identification of the to-be-calculated personnel and the identification of the associated personnel of the to-be-calculated event; the output of the target model includes: the probability score of the to-be-calculated personnel participating in the to-be-calculated event; the to-be-calculated personnel is any target personnel, and the to-be-calculated event is any existing event of the to-be-calculated personnel;
[0008] determining the recommended period for performing the target event according to the probability score of each target personnel participating in the respective existing event and the setting period of the existing event;
[0009] wherein the associated personnel of the to-be-calculated event includes: the owner of the to-be-calculated event, the invitee of the to-be-calculated event, and other participating personnel of the to-be-calculated event other than the owner and the invitee of the to-be-calculated event.
[0010] In some embodiments, the present disclosure provides a processing device of an event, comprising:
[0011] an acquisition unit, configured to acquire the identification of each target personnel participating in a target event in response to identifying that there is an intention to arrange the target event among multiple conversation members;
[0012] The control unit is configured to determine a probability score of each target person participating in a respective existing matter by using a target model, wherein an input of the target model comprises an identifier of the to-be-calculated person and identifiers of associated persons of the to-be-calculated matter, and an output of the target model comprises the probability score of the to-be-calculated person participating in the to-be-calculated matter, the to-be-calculated person is any target person, and the to-be-calculated matter is any existing matter of the to-be-calculated person.
[0013] The control unit is further configured to determine a recommended time period for performing the target matter according to the probability score of each target person participating in a respective existing matter and a set time period of the existing matter.
[0014] The associated persons of the to-be-calculated matter include an owner of the to-be-calculated matter, an invitee of the to-be-calculated matter, and other participants of the to-be-calculated matter other than the owner and the invitee.
[0015] In some embodiments, the present disclosure provides an electronic device, comprising at least one memory and at least one processor.
[0016] The memory is configured to store program code, and the processor is configured to invoke the program code stored in the memory to execute the above method.
[0017] In some embodiments, the present disclosure provides a computer-readable storage medium for storing program code, which, when executed by a processor, causes the processor to execute the above method.
[0018] The method provided by the embodiments of the present disclosure can predict target persons participating in existing matters possessed by the target persons, calculate probability scores of each target person participating in respective existing matters possessed by the target persons, and obtain the most reasonable recommended time period, thereby facilitating reasonable determination of a set time period of a target matter. BRIEF DESCRIPTION OF DRAWINGS
[0019] The above and other features, advantages, and aspects of the present disclosure will become more apparent by describing in detail some embodiments thereof with reference to the annexed drawings in which:
[0020] Figure 1 is a flowchart of a matter processing method according to an embodiment of the present disclosure.
[0021] Figure 2 and Figure 3 is a use scenario diagram of a matter processing method according to an embodiment of the present disclosure.
[0022] Figure 4 is a structural schematic diagram of a target model of an embodiment of the present disclosure.
[0023] Figure 5 is a structural schematic diagram of an electronic device of an embodiment of the present disclosure. DETAILED DESCRIPTION
[0024] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained in a proper manner according to relevant laws and regulations.
[0025] For example, in response to receiving an active request of the user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can voluntarily choose whether to provide personal information to the electronic device, application program, server or storage medium, etc. software or hardware performing the operation of the technical solutions of the present disclosure according to the prompt information.
[0026] As an optional but non-limiting implementation manner, in response to receiving an active request of the user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information may, for example, be presented in the form of text in the pop-up window. In addition, the pop-up window may, for example, also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.
[0027] It can be understood that the above notification and obtaining of user authorization process is only illustrative, and does not limit the implementation manner of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.
[0028] It can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solutions should comply with the requirements of relevant laws and regulations and relevant provisions.
[0029] 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 drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, rather these embodiments are provided to more thoroughly and completely understand 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.
[0030] It should be understood that each step recorded in the method implementation manner of the present disclosure can be executed in series and / or in parallel. In addition, the method implementation manner can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.
[0031] The term "includes" and its variants are open-ended, meaning that "includes but is not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment." The term "another embodiment" means "at least one additional embodiment." The term "some embodiments" means "at least some embodiments." Related terms have analogous meanings.
[0032] It should be noted that the terms "first", "second", and the like in the present disclosure are merely intended to distinguish different devices, modules or units, and do not imply the order or interdependence of the functions performed by these devices, modules or units.
[0033] It should be noted that the modification "one" mentioned in the present disclosure is illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise explicitly indicated in the context, it should be understood as "one or more".
[0034] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.
[0035] The scheme provided by the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.
[0036] In work or life, the scenario of creating a target matter (meeting, schedule) in a chat software often occurs. When creating a matter, a time period is automatically recommended to be set, but the target person participating in the matter may have an existing matter that has been arranged. Therefore, how to intelligently recommend a time period so that the target person can participate in the target matter as much as possible, especially when the target matter inevitably conflicts with the set time period of part of the existing matters, becomes a problem to be solved.
[0037] As shown in Figure 1 , Fig. 1 is a flowchart of a matter processing method according to an embodiment of the present disclosure, including the following steps. Figure 1
[0038] S11, in response to identifying that there is an intention to arrange a target matter among a plurality of conversation members, obtaining the identity of each target person participating in the target matter.
[0039] In some embodiments, the executor of the method can be a computer, a mobile phone, a tablet computer, or the like electronic device. More specifically, the executor of the method can be an application software in the electronic device that has a scheduled event (the event can be a meeting or the like), and the application software can be an instant messaging software or a collaborative office software integrated with instant messaging function. In some embodiments, the identification of the intention of the multiple conversation members to schedule the target event can be the identification of the generation of the conversation content in the conversation interface (the conversation interface can be a single chat or a group chat interface) for scheduling the target event, or the identification of the operation event on the text or the control of the target event in the conversation interface. As shown in Figure 2 , the identification of the intention of the multiple conversation members to schedule the target event can be the identification of the generation of the conversation content (the conversation content in Figure 2 “Zhang Yi” is one of the target persons, and Zhang Yi can be the creator of the target event) by the conversation member (Zhang Yi) for scheduling the target event (the conversation content in Figure 2 “Let’s discuss the project content at a certain time”), that is, the detection of the intention of the multiple conversation members to schedule the target event, and the identification of the identification of the target persons of the target event in response to the intention; or, the identification of the generation of the conversation content by the conversation member, the automatic marking of the content in the conversation content for scheduling the target event (for example, the generation of the dashed underline under “Let’s discuss the project content at a certain time” in Figure 2 ), the indication of the intention of the multiple conversation members to schedule the target event after the marking is triggered, the identification of the identification of the target persons of the target event, and the automatic entering of the setting interface of the target event as shown in Figure 3 . The target event can be an online meeting or other schedule, and the persons participating in the target event are the target persons, so the target persons can be multiple, and the identification of the target persons can be the identity code (id) of the target persons or the index of the identity code.
[0040] S12, determining the probability score of each target person participating in the respective existing event by using the target model.
[0041] In some embodiments, the target model can be a pre-trained neural network model, the target person can have existing matters, the existing matters being matters in the schedule of the target person that have not yet started, of course, some target persons can not have existing matters, different target persons can have the same or different existing matters, although the existing matters are in the schedule of the target person, the target person can not finally participate in the existing matters. An existing matter of a target person corresponds to a probability score, the probability score can be a probability value of the target person participating in the existing matter, or can be an importance score of the existing matter to the target person. Therefore, the higher the probability score, the greater the probability that the target person will participate in the existing matter (or the more important the existing matter is to the target person). The input of the target model includes: the identification of the person to be calculated and the identification of the associated person of the matter to be calculated; the output of the target model includes: the probability score of the target person participating in the matter to be calculated; the target person to be calculated is any target person, and the matter to be calculated is any existing matter of the target person to be calculated; the target model calculates one probability score at a time, and calculates the identification of one target person and the identification of each associated person of an existing matter of the target person at a time. Among them, the associated person of the matter to be calculated includes: the owner of the matter to be calculated, the invitee of the matter to be calculated, and other participants of the matter to be calculated, the owner of the matter to be calculated is usually the creator of the matter to be calculated, the invitee of the matter to be calculated can be the person who invites the target person to participate in the matter to be calculated, the invitee of the matter to be calculated and the owner of the matter to be calculated can be the same or different person, and the participant of the matter to be calculated is the person participating in the matter to be calculated, and the person other than the owner and the invitee is the other participant. For example, the target person A has existing matter 1 and existing matter 2, and the target person B has existing matter 3, then there are three probability scores, which are the probability score of the target person A participating in the existing matter 1, the probability score of the target person A participating in the existing matter 2, and the probability score of the target person B participating in the existing matter 3. Three times of calculation are required using the target model, the first time is to input the identification of the target person A and the identification of the associated person of the existing matter 1, the second time is to input the identification of the target person A and the identification of the associated person of the existing matter 2, and the third time is to input the identification of the target person B and the identification of the associated person of the existing matter 3. In some embodiments, due to the sensitivity of the data, the data that can be used is limited due to the need to protect privacy, therefore, in the calculation of the probability score, the identification of the target person and the identification of the associated person of the existing matter are used to determine the probability score, without the need for additional use of other data, so as to maximize the protection of the privacy of the user.
[0042] S13, according to the probability score of each target person participating in the respective existing matter and the set period of the existing matter, determine the recommended period of performing the target matter.
[0043] In some embodiments, existing events have set time periods, which are typically the time periods for agreeing to execute the events. For example, if the existing event is a meeting and the set time period is 1:00 PM to 3:00 PM, this indicates that the meeting is scheduled to be held between 1:00 PM and 3:00 PM. After obtaining the probability scores of each target person's participation in their respective existing events and the set time periods for the existing events, it is possible to determine whether each target person has an existing event within each time period, as well as the likelihood of each target person participating in the existing event or the importance of the existing event to the target person. This allows the recommended time period for the target event (the recommended time period can be the set time period recommended as the target event) to avoid the time period for existing events, or, if the recommended time period for the target event cannot avoid the set time periods for all existing events, the existing event that cannot be avoided can be the existing event with the lowest likelihood of participation for the target person. This method can be automatically executed when it is recognized that there is an intention to arrange a target event among multiple conversation members, so that the recommended time period is automatically displayed on the target event setting interface, and the target person can use the recommended time period as the set time period for the target event, thereby helping the target person automatically and intelligently select the set time period for the target event.
[0044] In some embodiments, for example Figure 2 and Figure 3 As shown, there is a conversation content ( Figure 2 The mark of "make an appointment" in Figure 2 When the target person (underlined in ) is triggered, the intention of arranging the target event is recognized, and then the method can be automatically executed and the setting interface of the target event is entered. Figure 3 After identifying the "Zhang Yi" and "Zhang Er" in the list, the participation of each target person in their existing matters (see Figure 3 On the right side, the probability scores of the existing events that Zhang Yi and Zhang Er have already arranged, including Meeting 1 and Meeting 2, and the time periods of the existing events. Then, the recommended time period can be automatically filled in the setting interface of the target event ( Figure 3 In some embodiments, the recommended time period automatically written in the setting interface can be changed.
[0045] The method provided by the embodiment of the present disclosure can predict the target person's participation in existing matters, calculate the probability score of each target person's participation in the existing matters, and thus obtain the most reasonable recommended time period, which is conducive to reasonably determining the set time period of the target matter.
[0046] In some embodiments of the present disclosure, the target model is used to determine the probability score of each target person participating in the respective existing matter, including: using a natural language processing algorithm to calculate the association between the identification of the target person and the identification of the associated person of the existing matter of the target person, and determining the probability score of the target person participating in the existing matter of the target person according to the association.
[0047] In some embodiments, the natural language processing-based algorithm is used to treat the identification of the target person and the associated person as text in natural language, and if there is a list of personnel in the management personnel, the list of personnel is treated as a list of text. In this way, the identification can be embedded and coded to obtain a meaningful vector, and the relationship between the identifications can be determined through the vector, that is, in the present embodiment, a method similar to natural language processing is used, and in natural language processing, a word vector represents the position coding of a word in a semantic space. In the present embodiment, the identification of the personnel is represented as a vector, that is, the position identification of a personnel in an association relationship space, which indicates that the association relationship can be calculated, so as to determine the probability score according to the association relationship. In the present embodiment, the natural language processing algorithm is proposed to be used for mining the association relationship of the personnel, so as to realize the effect that the probability score can be determined only through the identification of the target person and the associated person.
[0048] In some embodiments of the present disclosure, the natural language processing algorithm is used to calculate the association between the identification of the target person and the identification of the associated person of the existing matter of the target person, and determine the probability score of the target person participating in the existing matter of the target person according to the association, including: converting the identification of the target person and the identification of the associated person of the existing matter of the target person into vectors; calculating a first relationship vector between the vector corresponding to the identification of the target person and the vector corresponding to the identification of the owner of the existing matter, and a second relationship vector between the vector corresponding to the identification of the target person and the vector corresponding to the identification of the inviter of the existing matter; calculating a third relationship vector between the vector corresponding to the identification of the target person and the vector corresponding to the identification of the other participants of the existing matter; and calculating the probability score of the target person participating in the existing matter according to the first relationship vector, the second relationship vector and the third relationship vector.
[0049] In some embodiments, the associated person of the existing matter includes: the owner of the existing matter, the inviter of the existing matter, and the other participants of the existing matter. After obtaining the identification of the target person (user) and the associated person, the identification is converted into a vector (vec), which can be realized by an embedding layer (Embedding layer). The identification is converted into a dense vector, and the identification of the other participants can be converted into a vector list. Figure 4As shown, in order to calculate the association between the target person and the owner and the inviter, respectively, a vector projection layer is designed in the target model, and the vector of the target person's identity and the vector of the owner's identity are input, and the vector of the target person's identity and the vector of the inviter's identity are input. The first relationship vector and the second relationship vector are calculated through the vector projection layer in the target model, wherein the first relationship vector represents the relationship between the vector of the target person's identity (user_vec) and the vector of the owner's identity (owner_vec) of the existing matter, and the second relationship vector represents the relationship between the vector of the target person's identity and the vector of the inviter's identity (inviter_vec) of the existing matter. The owner of the existing matter is the person who creates the existing matter, and the inviter of the existing matter is the person who invites the target person to participate in the existing matter. In the target model, the third relationship vector is calculated through the multi-head attention layer in the target model. The multi-head attention layer (MultiheadAttention) can mine the association between the target person and other participants, and the other participants are participants other than the owner and the inviter. Here, the attention mechanism in natural language processing is adopted, which is similar to mining the association between each text and the input text from a sentence. After obtaining the first relationship vector, the second relationship vector and the third relationship vector, the linear transformation of the fusion layer is performed, and the output layer can output a probability value between 0 and 1 as a probability score. The probability score is the probability of the target person participating in the existing matter under the influence of the owner, the inviter and other participants, and it can also be regarded as the importance score of the existing matter to the target person.
[0050] In some embodiments of the present disclosure, the target model is pre-trained by the following method: obtaining training personnel identity, identity of associated personnel of the training personnel's historical matter, and label indicating whether the training personnel participated in the historical matter; inputting the training personnel identity and the identity of the associated personnel of the training personnel's historical matter into the target model to obtain a training probability score of the training personnel participating in the historical matter; and adjusting the parameters of the target model according to the training probability score and the label.
[0051] In some embodiments, the target model needs to be trained before use. The training data includes the identity of the training personnel, the identity of the associated personnel of the historical event of the training personnel, and the label. The historical event is an event in the past schedule of the training personnel. The training personnel may or may not eventually participate in the historical event. The label is used to indicate whether the training personnel eventually participated in the historical event, for example, 0 indicates that the training personnel did not eventually participate, and 1 indicates that the training personnel eventually participated. The identity of the training personnel and the identity of the associated personnel of the historical event are input into the target model to output a training probability score, i.e., the probability score of the training personnel participating in the historical event, which is then compared with the label. According to the comparison result, the parameters of the target model are adjusted. Specifically, the probability score is between 0 and 1. If the probability score is higher than 0.5, it means that the training personnel should have participated in the historical event, otherwise, the training personnel did not participate. The parameters of the target model are adjusted so that the label and the representation result of the training probability score are consistent, i.e., if the training personnel really participated in a historical event, the training probability score of the historical event should be higher than 0.5, and vice versa.
[0052] In some embodiments of the present disclosure, before determining the probability score of each target personnel participating in each existing event by using the target model, the target time range of the target event is determined, and the set time period of the existing event of the target personnel is located in the target time range.
[0053] In some embodiments, the target event has not started, but it is generally not possible to be postponed to a very distant future, for example, it is generally not set to be held several months or a year later. A time range is usually specified, for example, the target event is a meeting, and it is usually required that the meeting be held within a week or several weeks in the future. The target time range is the time range in which the set time period of the target event is located, which is usually several days or weeks in the future, so the existing event to be determined at this time should also be the existing event whose set time period is located in the target time range. The existing event whose set time period is not located in the target time range does not need to be calculated, reducing the amount of calculation. For example, the target event is a meeting, and the target time range of the meeting is within a week in the future, indicating that the meeting needs to be held within a week in the future. At this time, the existing event to be determined is the existing event in the schedule of the target personnel whose set time period is within a week in the future.
[0054] In some embodiments of the present disclosure, the recommended time period for performing the target event is determined according to the probability scores of each target person participating in the respective existing event and the setting time period of the existing event, including: calculating the cumulative probability score of each sub-period within the target time range according to the probability scores of each target person participating in the respective existing event and the setting time period of the existing event, wherein the cumulative probability score of any sub-period is the sum of the probability scores of the existing events whose setting time periods of each target person are located in the sub-period; taking the sub-period with the lowest cumulative probability score as the recommended time period, or taking the sub-period with the lowest cumulative probability score as the recommended time period if there is no existing event with a probability score greater than a preset probability score in the sub-period with the lowest cumulative probability score.
[0055] In some embodiments, after calculating the respective probability scores of each target person participating in the respective existing event, the cumulative probability score is calculated according to the setting time period of the existing event and the distribution of each sub-period. When calculating the cumulative probability score, each probability score can be classified into each sub-period according to the setting time period of the corresponding existing event, and then the sum of the probability scores classified in each sub-period is calculated. Assuming that target person A has event 1 and event 2, target person B has existing event 3 and event 4, the setting time period of event 1 and event 3 is located in the first sub-period, and the setting time period of event 2 and event 4 is located in the second sub-period, then the cumulative probability score of the first sub-period is the sum of the probability score of target person A participating in existing event 1 and the probability score of target person B participating in existing event 3. The cumulative probability score of the second sub-period is the sum of the probability score of target person A participating in existing event 2 and the probability score of target person B participating in existing event 4. Then, the sub-period with the lowest cumulative probability score is found from each sub-period as the recommended time period. Alternatively, after finding the sub-period with the lowest cumulative probability score, it is judged whether the probability scores classified into the sub-period are all less than a preset probability score (for example, 0.5). If so, it is taken as the recommended time period. If there is a probability score higher than the preset probability score in the sub-period with the lowest cumulative probability score, it is considered that there is no recommended time period, and the recommended time period can not be displayed at this time, so as to avoid the existence of the existing event in the recommended time period which the target person will probably participate in.
[0056] In the embodiments of the present disclosure, the target model is a neural network model for mining correlation relationship based on natural language processing algorithm, which can be used to predict the probability of target person participating in the existing schedule, help the target person to intelligently select the recommended time period of the target event, and avoid the conflict with the existing event in the schedule of the target person as much as possible, so as to help intelligently create the target event.
[0057] The present disclosure also provides a processing device for an event, including:
[0058] The acquisition unit is configured to, in response to identifying that there is an intention of arranging the target event among the plurality of conversation members, acquire an identifier of each target person participating in the target event;
[0059] The control unit is configured to determine a probability score of each target person participating in a respective existing event by using a target model, wherein an input of the target model comprises an identifier of a to-be-calculated person and an identifier of an associated person of a to-be-calculated event; and an output of the target model comprises a probability score of the to-be-calculated person participating in the to-be-calculated event; the to-be-calculated person is any target person, and the to-be-calculated event is any existing event of the to-be-calculated person;
[0060] The control unit is further configured to determine a recommended time period for performing the target event according to the probability score of each target person participating in a respective existing event and a set time period of the existing event.
[0061] The associated person of the to-be-calculated event comprises an owner of the to-be-calculated event, an invitee of the to-be-calculated event, and other participants of the to-be-calculated event other than the owner and the invitee.
[0062] In some embodiments, the target model is used to determine the probability score of each target person participating in a respective existing event, comprising:
[0063] An algorithm of natural language processing is used to calculate an association between the identifier of the target person and the identifier of the associated person of the existing event of the target person, and determine the probability score of the target person participating in the existing event of the target person according to the association.
[0064] In some embodiments, the algorithm of natural language processing is used to calculate an association between the identifier of the target person and the identifier of the associated person of the existing event of the target person, and determine the probability score of the target person participating in the existing event of the target person according to the association, comprising:
[0065] The identifier of the target person and the identifier of the associated person of the existing event of the target person are converted into vectors;
[0066] A first relationship vector between the vector corresponding to the identifier of the target person and the vector corresponding to the identifier of the owner of the existing event, and a second relationship vector between the vector corresponding to the identifier of the target person and the vector corresponding to the identifier of the invitee of the existing event are calculated;
[0067] A third relationship vector between the vector corresponding to the identifier of the target person and the vector corresponding to the identifier of the other participant of the existing event is calculated;
[0068] calculate a probability score of the existing matter in which the target person participates according to the first relationship vector, the second relationship vector and the third relationship vector;
[0069] The associated person of the existing matter includes an owner of the existing matter, an inviter of the existing matter, and other participants of the existing matter.
[0070] In some embodiments, the first relationship vector and the second relationship vector are calculated by a vector projection layer in the target model; and / or the third relationship vector is calculated by a multi-head attention layer in the target model.
[0071] In some embodiments, the target model is pre-trained by the following method:
[0072] obtain a training person identifier, an identifier of an associated person of a historical matter of the training person, and a label indicating whether the training person participates in the historical matter;
[0073] input the training person identifier and the identifier of the associated person of the historical matter of the training person into the target model to obtain a training probability score of the training person participating in the historical matter;
[0074] adjust parameters of the target model according to the training probability score and the label.
[0075] In some embodiments, before determining the probability score of each target person participating in the respective existing matter by using the target model, the control unit is further configured to: determine a target time range of the target matter; and the set time period of the existing matter of the target person is located within the target time range.
[0076] In some embodiments, the recommended time period for performing the target matter is determined according to the probability score of each target person participating in the respective existing matter and the set time period of the existing matter, including:
[0077] calculate a cumulative probability score of each sub-period within the target time range according to the probability score of each target person participating in the respective existing matter and the set time period of the existing matter, wherein the cumulative probability score of any sub-period is the sum of the probability scores of the existing matters of each target person whose set time period is located within the sub-period.
[0078] take the sub-period with the lowest cumulative probability score as the recommended time period, or take the sub-period with the lowest cumulative probability score as the recommended time period if there is no existing matter with a probability score greater than a preset probability score in the sub-period with the lowest cumulative probability score.
[0079] For the embodiment of the apparatus, since it basically corresponds to the embodiment of the method, the relevant part can be seen from the part of the embodiment of the method. The above-described apparatus embodiment is only illustrative, wherein the modules described as separate modules can or can not be separated. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment. Those skilled in the art can understand and implement without creative labor.
[0080] The above describes the method and apparatus of the present disclosure based on the embodiments and application examples. In addition, the present disclosure also provides an electronic device and a computer readable storage medium, which are described below.
[0081] The following refers to Figure 5 which shows a structural schematic diagram of an electronic device (such as a terminal device or a server) 800 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Personal Computers), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in the figure is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.
[0082] The electronic device 800 can include a processing device (such as a central processor, a graphics processor, etc.) 801, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 802 or loaded into a random access memory (RAM) 803 from a storage device 808. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0083] Generally, the following devices can be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 808 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 809. The communication devices 809 can allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 800 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the shown devices. More or less devices can be alternatively implemented or possessed.
[0084] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication device 809, or installed from the storage device 808, or installed from the ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.
[0085] It should be noted that the computer readable medium described above in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus or device. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, optical fiber, RF, etc., or any suitable combination of the foregoing.
[0086] In some embodiments, the client, server, or other computing machines utilized by the system can communicate information using any known or future developed end-to-end communication protocol, such as the HyperText Transfer Protocol (HTTP), and can be interconnected via any form or medium of digital data communication (for example, a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet, and peer-to-peer networks (for example, ad hoc peer-to-peer networks), as well as any current or future developed network.
[0087] The computer-readable medium described above can be included in the electronic device described above; alternatively, the computer-readable medium can exist as a standalone entity.
[0088] The computer-readable medium described above can be included in the electronic device described above; alternatively, the computer-readable medium can exist as a standalone entity.
[0089] Computer program code for carrying out operations of the present disclosure can be written in any of one or more programming languages, including object oriented programming languages such as Java, Smalltalk, C++, or conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network ("LAN") or a wide area network ("WAN"), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).
[0090] The flow and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow and block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or combinations of hardware and software.
[0091] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself.
[0092] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, example 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), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.
[0093] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can 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 the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0094] According to one or more embodiments of the present disclosure, a method for processing a matter is provided, comprising:
[0095] In response to identifying that there is an intention of arranging the target event among the plurality of conversation members, obtaining an identification of each target person participating in the target event;
[0096] Determining a probability score of each of the target persons participating in the respective existing event by using a target model, wherein an input of the target model comprises: an identification of the to-be-calculated person and an identification of an associated person of the to-be-calculated event; an output of the target model comprises: a probability score of the to-be-calculated person participating in the to-be-calculated event; the to-be-calculated person is any of the target persons, and the to-be-calculated event is any of the existing events of the to-be-calculated person;
[0097] Determining a recommended time period for performing the target event according to the probability score of each of the target persons participating in the respective existing event and a set time period of the existing event;
[0098] The associated person of the to-be-calculated event comprises: an owner of the to-be-calculated event, an invitee of the to-be-calculated event, and other participating persons of the to-be-calculated event except the owner and the invitee of the to-be-calculated event.
[0099] According to one or more embodiments of the present disclosure, a processing method of an event is provided, and a probability score of each of target persons participating in a respective existing event is determined by using a target model, comprising:
[0100] An algorithm of natural language processing is used to calculate an association relationship between the identification of the target person and the identification of an associated person of the existing event of the target person, and a probability score of the target person participating in the existing event of the target person is determined according to the association relationship.
[0101] According to one or more embodiments of the present disclosure, a processing method of an event is provided, and an algorithm of natural language processing is used to calculate an association relationship between the identification of the target person and the identification of an associated person of the existing event of the target person, and a probability score of the target person participating in the existing event of the target person is determined according to the association relationship, comprising:
[0102] Converting the identification of the target person and the identification of the associated person of the existing event of the target person into vectors;
[0103] Calculating a first relationship vector between the vector corresponding to the identification of the target person and the vector corresponding to the identification of the owner of the existing event, and a second relationship vector between the vector corresponding to the identification of the target person and the vector corresponding to the identification of the invitee of the existing event;
[0104] Calculating a third relationship vector between the vector corresponding to the identification of the target person and the vector corresponding to the identification of the other participating person of the existing event.
[0105] calculate a probability score of the existing matter in which the target person participates according to the first relationship vector, the second relationship vector and the third relationship vector;
[0106] The associated persons of the existing matter include an owner of the existing matter, an invitee of the existing matter and other participants of the existing matter.
[0107] According to one or more embodiments of the present disclosure, a matter processing method is provided, the first relationship vector and the second relationship vector are calculated by a vector projection layer in the target model; and / or, the third relationship vector is calculated by a multi-head attention layer in the target model.
[0108] According to one or more embodiments of the present disclosure, a matter processing method is provided, the target model is pre-trained by the following method:
[0109] obtain a training person identifier, identifiers of associated persons of historical matters of the training person and a label indicating whether the training person participates in the historical matters;
[0110] input the training person identifier and the identifiers of the associated persons of the historical matters of the training person into the target model to obtain a training probability score of the training person participating in the historical matters;
[0111] adjust parameters of the target model according to the training probability score and the label.
[0112] According to one or more embodiments of the present disclosure, a matter processing method is provided, before determining the probability score of each target person participating in the existing matter by using the target model, the method further includes determining a target time range of the target matter;
[0113] The set time period of the existing matter of the target person is located in the target time range.
[0114] According to one or more embodiments of the present disclosure, a matter processing method is provided, a recommended time range for performing the target matter is determined according to the probability score of each target person participating in the existing matter and the set time period of the existing matter, including:
[0115] According to the probability score of each target person participating in the existing matter and the set time period of the existing matter, a cumulative probability score of each sub time period in the target time range is calculated, wherein the cumulative probability score of any sub time period is the sum of the probability scores of the existing matters of each target person whose set time period is located in the sub time period;
[0116] The sub-period with the lowest cumulative probability score is used as the recommended period. Alternatively, if there is no existing event with a probability score greater than a preset probability score in the sub-period with the lowest cumulative probability score, the sub-period with the lowest cumulative probability score is used as the recommended period.
[0117] According to one or more embodiments of the present disclosure, there is provided a device for processing a matter, comprising:
[0118] an acquiring unit, configured to acquire, in response to recognizing that there is an intention to arrange a target event among a plurality of conversation members, an identification of each target person who participates in the target event;
[0119] a control unit, configured to determine, using a target model, a probability score of each target person participating in their respective existing events, wherein the input of the target model includes: an identifier of the person to be calculated and an identifier of a person associated with the event to be calculated; the output of the target model includes: a probability score of the person to be calculated participating in the event to be calculated; the person to be calculated is any target person, and the event to be calculated is any existing event of the person to be calculated;
[0120] The control unit is further configured to determine a recommended time period for executing the target event based on the probability score of each target person participating in their respective existing events and the set time period of the existing events;
[0121] The associated persons of the item to be calculated include: the owner of the item to be calculated, the inviter of the item to be calculated, and other participants of the item to be calculated except the owner and inviter of the item to be calculated.
[0122] According to one or more embodiments of the present disclosure, there is provided an electronic device, including: at least one memory and at least one processor;
[0123] The at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute any one of the above methods.
[0124] According to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the processor is prompted to perform the above method.
[0125] The above description merely illustrates the preferred embodiments of the disclosure and a principle for applying the technologies. It is understood by those skilled in the art that the disclosed scope of the disclosure is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by the combinations of the technical features described above or their equivalent features without departing from the disclosed concept. For example, the technical solutions formed by the mutual replacement of the above-described features and the technical features with similar functions disclosed in the disclosure (but not limited to) can be formed.
[0126] Further, although operations are depicted in a particular, sequential order, this should not be understood as requiring or implying that the operations are performed in the order illustrated or sequentially. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, although specific implementation details are contained in the above discussion, these should not be construed as limiting the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0127] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims
1. A method for handling matters, characterized in that: include: In response to recognizing that there is an intention to arrange a target event among the plurality of conversation members, obtaining an identification of each target person who participates in the target event; A target model is used to determine the probability score of each target person participating in their respective existing events, wherein the input of the target model includes: an identifier of the person to be calculated and an identifier of a person associated with the event to be calculated; the output of the target model includes: a probability score of the person to be calculated participating in the event to be calculated; the person to be calculated is any target person, and the event to be calculated is any existing event of the person to be calculated; Determining a recommended time period for executing the target event based on the probability score of each target person participating in their respective existing events and the set time period of the existing events; The associated persons of the item to be calculated include: the owner of the item to be calculated, the inviter of the item to be calculated, and other participants of the item to be calculated except the owner and inviter of the item to be calculated.
2. The method according to claim 1, characterized in that The target model is used to determine the probability score of each target person participating in their respective existing matters, including: A natural language processing algorithm is used to calculate the association relationship between the identifier of the target person and the identifiers of the associated persons of the target person's existing affairs, and the probability score of the target person's participation in the target person's existing affairs is determined based on the association relationship.
3. The method according to claim 2, characterized in that A natural language processing algorithm is used to calculate the association relationship between the identifier of the target person and the identifiers of the associated persons of the target person's existing affairs, and a probability score of the target person's participation in the target person's existing affairs is determined based on the association relationship, including: Converting the identifier of the target person and the identifiers of the persons associated with the target person's existing matters into vectors; Calculating a first relationship vector between a vector corresponding to the target person's identifier and a vector corresponding to the identifier of the owner of the existing event, and a second relationship vector between a vector corresponding to the target person's identifier and a vector corresponding to the identifier of the inviter of the existing event; Calculating a third relationship vector between the vector corresponding to the identifier of the target person and the vectors corresponding to the identifiers of other participants in the existing event; Calculate a probability score of the target person's participation in existing matters based on the first relationship vector, the second relationship vector, and the third relationship vector; The associated persons of the existing matter include: the owner of the existing matter, the inviter of the existing matter, and other participants of the existing matter.
4. The method according to claim 3, characterized in that The first relationship vector and the second relationship vector are calculated by a vector projection layer in the target model; and / or the third relationship vector is calculated by a multi-head attention layer in the target model.
5. The method according to claim 1, wherein The target model is pre-trained using the following method: Obtaining a trainer ID, IDs of persons associated with the trainer's historical events, and a tag indicating whether the trainer participated in the historical events; Inputting the trainee identification and the identifications of persons associated with the trainee's historical events into the target model to obtain a training probability score of the trainee's participation in the historical events; Parameters of the target model are adjusted based on the training probability scores and the labels.
6. The method according to claim 1, characterized in that Before using the target model to determine the probability score of each target person participating in the respective existing events, the method further includes: determining the target time range of the target event; The set time period of the existing matters of the target person is within the target time range.
7. The method according to claim 6, characterized in that Determining a recommended time period for executing the target event based on the probability score of each target person participating in their respective existing events and the set time period of the existing events includes: Based on the probability score of each target person participating in their respective existing events and the set time period of the existing events, the cumulative probability score of each sub-period within the target time range is calculated, wherein the cumulative probability score of any sub-period is: the sum of the probability scores of the existing events whose set time period of each target person falls within the sub-period; The sub-period with the lowest cumulative probability score is used as the recommended period, or if there is no existing event with a probability score greater than a preset probability score in the sub-period with the lowest cumulative probability score, the sub-period with the lowest cumulative probability score is used as the recommended period.
8. A device for processing matters, characterized in that: include: an acquiring unit, configured to acquire, in response to recognizing that there is an intention to arrange a target event among a plurality of conversation members, an identification of each target person who participates in the target event; a control unit, configured to determine, using a target model, a probability score of each target person participating in their respective existing events, wherein the input of the target model includes: an identifier of the person to be calculated and an identifier of a person associated with the event to be calculated; the output of the target model includes: a probability score of the person to be calculated participating in the event to be calculated; the person to be calculated is any target person, and the event to be calculated is any existing event of the person to be calculated; The control unit is further configured to determine a recommended time period for executing the target event based on the probability score of each target person participating in their respective existing events and the set time period of the existing events; The associated persons of the item to be calculated include: the owner of the item to be calculated, the inviter of the item to be calculated, and other participants of the item to be calculated except the owner and inviter of the item to be calculated.
9. An electronic device comprising: at least one memory and at least one processor; The at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute the method according to any one of claims 1 to 7. 10 . A computer-readable storage medium, configured to store program code, wherein when the program code is executed by a processor, the processor is prompted to execute the method according to claim 1 .