Intelligent cooperation method and system based on mobile internet

Abstract

The invention discloses an intelligent cooperation method and system based on the mobile internet, and relates to the technical field of intelligent collaboration.The intelligent cooperation method comprises the steps that cooperation task data are input, and task feature data containing task complexity, time windows and dependency relationships are extracted; historical task records and social network data of participants are obtained, an initial capability vector is generated through a capability evaluation neural network model, feature fusion is carried out in combination with a cooperation capability vector generated by a graph convolutional neural network, a task matching degree score is calculated, and participant capability portrait data are obtained; according to the ability portrait data, screening and sorting the participants by adopting a preset task allocation rule, and generating a task allocation scheme; and sending a task invitation to the selected participant, and updating a task state according to a response condition. According to the method, the flexibility and the adaptability of task allocation are realized, so that the overall cooperation efficiency and the task completion quality are remarkably improved, and an innovative technical solution is provided for the field of intelligent cooperation.

Description

Technical Field

[0001] The present invention relates to the field of intelligent collaboration technology, and in particular to an intelligent collaboration method and system based on mobile Internet. Background Art

[0002] With the rapid development and popularization of mobile Internet technology, collaborative office has become an indispensable and important part of modern enterprise operations. In recent years, intelligent collaboration technology has evolved from a simple task allocation system to an intelligent collaboration platform that integrates artificial intelligence. Traditional collaboration systems mainly rely on manual judgment and fixed rules to allocate tasks, and then develop semi-automatic task allocation systems based on rule engines. At present, the introduction of deep learning technology enables collaborative systems to deeply mine task features through neural network models and analyze the collaborative relationship network between participants in combination with graph computing technology, which greatly improves the intelligence level of task allocation. However, existing intelligent collaboration systems still have limitations in task complexity assessment, participant capability portrait construction, and task-participant matching. Traditional methods often use a simple feature superposition method to evaluate task complexity, which makes it difficult to accurately characterize the multi-dimensional characteristics of tasks; when constructing participant capability models, most of them only consider the historical task completion status, ignoring the impact of social network relationships between participants on collaboration effects; in addition, existing systems fail to fully utilize the advantages of graph neural networks to mine task dependencies during task allocation, resulting in low efficiency in task allocation.

[0003] The main problems of the existing technology include: the extraction of task features is not comprehensive enough, and it fails to effectively integrate multi-dimensional features such as task complexity, time window and dependency; the participant ability assessment model is too simple and lacks in-depth use of social network data; the task allocation decision-making mechanism is single and fails to achieve intelligent and accurate matching between tasks and participants. The intelligent collaboration method based on mobile Internet provided by the present invention belongs to the field of collaborative office technology. It effectively solves the above technical problems by constructing a multi-level task feature extraction mechanism, a participant ability assessment model integrating social networks, and a task allocation optimization strategy based on graph neural networks. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides an intelligent collaboration method and system based on mobile Internet, which can solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides an intelligent collaboration method based on mobile Internet, which includes inputting collaboration task data, extracting collaboration task feature data according to the collaboration task data, wherein the collaboration task feature data includes task complexity data, time window data, and task dependency relationship data;

[0009] Obtain the historical task records and social network data of the participants, generate the initial vector of the participant's ability through the ability evaluation neural network model, and perform feature fusion with the collaborative ability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant's ability portrait data;

[0010] According to the participant capability profile data, the participants are screened and sorted using preset task allocation rules to generate a task allocation plan;

[0011] Based on the task allocation scheme, task invitations are sent to selected participants, and task statuses are updated according to responses from the participants.

[0012] As a preferred solution of the mobile Internet-based intelligent collaboration method of the present invention, wherein: extracting task complexity data includes receiving collaborative task data, and extracting task description text and task time parameters from the collaborative task data according to a preset task feature extraction rule;

[0013] Extracting the time window data includes constructing a task timeline based on the task time parameters to generate the time window data;

[0014] Extracting task dependency data includes using a graph neural network to process the collaborative task data, identifying pre-dependencies between tasks, and generating task dependency data.

[0015] As a preferred solution of the mobile Internet-based intelligent collaboration method of the present invention, wherein: the generating of the participant capability initial vector includes:

[0016] Obtain the historical task records and social network data of the participants, and extract the basic characteristic data of the participants from the historical task records of the participants. The basic characteristic data of the participants include the task completion rate, task quality score and task response time. The calculation formula for extracting the basic characteristic data of the participants is as follows:

[0017]

[0018]

[0019] Among them, TCR is the task completion rate, N c is the number of completed tasks, N c is the total number of tasks, TQS is the task quality score, Q i Score the quality of the i-th task, w i is the task weight coefficient, TRT is the task response time, T is the task response end time, T is the task release time, and N is the total number of tasks.

[0020] As a preferred solution of the mobile Internet-based intelligent collaboration method of the present invention, the feature fusion includes:

[0021] Construct a deep neural network model, input the basic feature data of the participants into the deep neural network model, generate the initial vector of the participant's ability, and obtain the calculation formula of the initial vector of the participant's ability as follows:

[0022] v init =σ(W2·ReLU(W1·x+b1)+b2)

[0023] Among them, v init is the initial vector of the participant's ability, x is the basic characteristic data of the participant, W1 and W2 are weight matrices, b1 and b2 are bias vectors, and σ is the tanh activation function;

[0024] Construct a capability evaluation neural network model, input the participant social network data into the graph convolutional neural network to generate a collaborative capability vector, and generate a collaborative capability vector through feature aggregation. The calculation formula for feature aggregation is as follows:

[0025]

[0026] in, is the adjacency matrix with self-loops added, A is the adjacency matrix of the social network, I is the identity matrix, is the degree matrix, H (l+1) is the feature matrix of the l+1th layer node, H (l) is the feature matrix of the l-th layer node, W (l) is the learnable weight matrix, σ1 is the ReLU activation function;

[0027] The initial capability vector of the participant is fused with the collaborative capability vector to generate the comprehensive capability vector of the participant. The calculation formula for feature fusion is as follows:

[0028] v f =λ·v init +(1-λ)·v c

[0029] λ = sigmoid(MLP([v init ||v c ]))

[0030] Among them, v f is the comprehensive ability vector of the participants, v c is the collaboration capability vector, and λ is the fusion weight coefficient.

[0031] As a preferred solution of the mobile Internet-based intelligent collaboration method of the present invention, the obtaining of the participant capability portrait data includes:

[0032] According to the task complexity data in the collaborative task feature data, the comprehensive ability vector of the participants is weighted to generate a task matching score. The weighted calculation formula is as follows:

[0033]

[0034] Among them, s is the task matching score, f(c i ) is the complexity adjustment function, which is used to adjust the score according to the complexity of the task. is the i-th component of the comprehensive ability vector of the participant, w i is the weight coefficient of the i-th capability dimension, c i is the i-th component of the task complexity index, α and β are adjustment parameters;

[0035] The task matching score is combined with the comprehensive ability vector of the participant to form the ability profile data of the participant, that is, p = [v f ,s], where P is the participant’s ability profile data.

[0036] As a preferred solution of the mobile Internet-based intelligent collaboration method of the present invention, the screening and sorting of participants includes:

[0037] Extract participants with free time periods according to the time window data, and filter the list of participants whose task load is less than the preset parallel upper limit;

[0038] Calculate the task linkage degree for each participant in the participant list according to the task dependency data, wherein the task linkage degree is obtained by weighting the similarity between the current task and the participant's historical completed tasks;

[0039] Performing a weighted combination of the task link degree and the task matching score to obtain a comprehensive score of the participant, sorting the participant list based on the comprehensive score of the participant, and selecting N participants with the highest comprehensive scores as candidate participants;

[0040] The task allocation scheme includes a task ID, a candidate participant ID, an expected start time, and an expected end time.

[0041] As a preferred solution of the mobile Internet-based intelligent collaboration method of the present invention, the updating of the task status according to the response of the participants includes:

[0042] According to the candidate participant ID in the task allocation plan, sending task invitation information to the candidate participant via the mobile Internet, wherein the task invitation information includes a task description, an expected start time and an expected end time;

[0043] receiving response data from the candidate participant, the response data including an acceptance mark or a rejection mark, and reselecting the candidate participant when the response data including the rejection mark is returned;

[0044] After receiving the response data including the acceptance mark, a task execution record is established, the task execution record includes the task status mark, the actual start time and the estimated completion time, and the task execution record is stored in the participant's historical task record.

[0045] In a second aspect, the present invention provides an intelligent collaboration system based on mobile Internet, which includes: a task feature extraction module, a participant capability assessment module, a task allocation optimization module and a task interactive collaboration module;

[0046] The task feature extraction module is used to input collaborative task data and extract collaborative task feature data according to the collaborative task data, wherein the collaborative task feature data includes task complexity data, time window data and task dependency data;

[0047] The participant capability assessment module is used to obtain the historical task records and social network data of the participants, generate the initial capability vector of the participants through the capability assessment neural network model, and perform feature fusion in combination with the collaborative capability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant capability portrait data;

[0048] The task allocation optimization module is used to screen and sort the participants according to the participant capability profile data using preset task allocation rules to generate a task allocation plan;

[0049] The task interactive collaboration module is used to send task invitations to selected participants based on the task allocation scheme, and update task status according to the responses of the participants.

[0050] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of the intelligent collaboration method based on mobile Internet are implemented.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of an intelligent collaboration method based on mobile Internet are implemented.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows: by constructing a multi-dimensional task feature extraction mechanism, combined with preset task feature extraction rules and graph neural network technology, a comprehensive analysis of task features is achieved, providing accurate data support for task allocation; by integrating the capability evaluation neural network model and the graph convolutional neural network, the personal capabilities of the participants and social network data are innovatively integrated to construct a comprehensive participant capability portrait; based on the participant capability portrait data, a multi-dimensional screening and sorting mechanism is adopted, and the concept of task linkage degree is introduced to achieve intelligent matching between tasks and participants; finally, by establishing a complete task invitation and response mechanism, combined with the real-time update function of task status, dynamic management of the task allocation process is achieved; the organic combination of the various steps of the present invention not only improves the accuracy and completeness of task feature extraction, enhances the comprehensiveness of participant capability evaluation, optimizes the rationality of task allocation and collaboration efficiency, but also achieves the flexibility and adaptability of task allocation, thereby significantly improving the overall collaboration efficiency and task completion quality, and providing an innovative technical solution for the field of intelligent collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 A method flow chart of a mobile Internet-based intelligent collaboration method and system provided by one embodiment of the present invention;

[0055] Figure 2 An internal structure diagram of a computer device of a mobile Internet-based intelligent collaboration method and system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides an intelligent collaboration method based on mobile Internet, including:

[0060] Before describing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.

[0061] Graph Convolutional Network: A deep learning model that specializes in processing graph structured data. It can learn the structured representation of nodes by iteratively aggregating the information of nodes and their neighboring nodes in the graph. In the present invention, it is mainly used to analyze the collaborative relationship in the social network of participants, and generate a vector representation that reflects the collaborative ability of participants by feature aggregation.

[0062] Task Linkage Degree: A quantitative indicator used to measure the degree of association between the current task and the participant's historically completed tasks. This indicator is obtained by calculating the similarity of task features and combining them with a weight coefficient. It reflects the participant's professionalism and persistence in a specific type of task, and helps to achieve continuity and specialization in task allocation.

[0063] Complexity Adjustment Function: A mathematical function used to dynamically adjust the participant's ability score according to the complexity of the task. This function takes into account the multidimensional complexity indicators of the task and corrects the participant's ability score through nonlinear transformation, so that the final task matching degree more accurately reflects the participant's actual ability to complete tasks of specific complexity.

[0064] This application provides an effective solution to the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the intelligent collaboration method based on mobile Internet.

[0065] Figure 1 A method flow chart of an intelligent collaboration method and system based on mobile Internet is shown, including:

[0066] S1: input collaborative task data, and extract collaborative task feature data according to the collaborative task data, wherein the collaborative task feature data includes task complexity data, time window data, and task dependency data;

[0067] Furthermore, the extracted task complexity data includes:

[0068] Receive collaborative task data, and extract task description text and task time parameters from the collaborative task data according to preset task feature extraction rules;

[0069] The preset task feature extraction rules include task time rules, task keyword rules, task dependency rules, and resource requirement rules;

[0070] Task time rules include:

[0071] Extracting the task start time, task deadline and task duration based on the task description text, calculating the task available time through the task start time and task deadline, and taking the ratio of the task duration to the task available time as the complexity index of the time dimension;

[0072] Task keyword rules include:

[0073] Preset the task keyword dictionary and the corresponding weight coefficient, and calculate the complexity index of the task semantic dimension according to the keywords and their frequency appearing in the task description text and the weight coefficient;

[0074] Task dependency rules include:

[0075] Based on the number of pre-dependent tasks of the task description text recognition task, the number of pre-dependent tasks is used as a complexity index of the task dependency dimension;

[0076] The resource requirement rules include extracting the number of human resources and equipment resource types required for the task based on the task description text, and calculating the complexity index of the resource dimension according to the number of human resources and equipment resource types;

[0077] The task description text is input into a pre-trained natural language processing model to obtain a task semantic feature vector, a task complexity score is calculated based on the task semantic feature vector, and the task complexity score is compared with a preset complexity threshold to generate task complexity data. It should be noted that the natural language processing model in the present invention is a prior art and will not be described in detail here.

[0078] Specifically, the present invention performs weighted summation on the complexity indicators of each dimension to obtain a task complexity score, and the weight coefficients of the complexity indicators of each dimension are obtained through training with historical task data; based on the comparison result of the task complexity score with a preset complexity threshold, task complexity data including the task complexity level is generated.

[0079] Furthermore, extracting time window data includes:

[0080] A task timeline is constructed based on the task time parameters to generate time window data.

[0081] Furthermore, the extracted task dependency data includes:

[0082] Use graph neural networks to process collaborative task data, identify pre-dependencies between tasks, and generate task dependency data;

[0083] It should be noted that the graph neural network used to extract task dependency data in the present invention includes but is not limited to any of the following: a graph attention network GAT, wherein the graph attention network GAT calculates the attention coefficient between task nodes, and the attention coefficient of each task node is calculated by the feature vector of the node and its adjacent nodes through the attention mechanism, and the attention coefficient is used to characterize the dependency strength between task nodes; a graph convolution network GCN, wherein the graph convolution network GCN adopts a spatial domain convolution method to aggregate the feature vector of each task node with the feature vector of its first-order neighbor node, and extracts the local dependency between task nodes through multi-layer convolution operations; a graph isomorphism network GIN, wherein the graph isomorphism network GIN adopts a learnable neighbor aggregation function, and the neighbor aggregation function includes a trainable parameter ε, and the discrimination of the task node representation is improved by adjusting the value of the parameter ε; a message passing neural network MPNN, wherein the message passing neural network MPNN includes a message passing stage and a readout stage, in which the message passing stage, message vectors containing dependency information are transmitted between task nodes, and in the readout stage, all message vectors are aggregated to generate a global task dependency representation.

[0084] Specifically, the present invention preferably uses a graph attention network GAT to extract task dependency data. The input of the GAT network is the word vector matrix corresponding to the task description text, and the output of the GAT network is the dependency vector of the task node. The numerical value of each element in the dependency vector represents the dependency strength of the corresponding task node pair.

[0085] Furthermore, the task complexity data, the time window data and the task dependency data are combined to form collaborative task feature data.

[0086] S2: Obtain the historical task records and social network data of the participants, generate the initial vector of the participant's ability through the ability evaluation neural network model, and perform feature fusion with the collaborative ability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant's ability portrait data;

[0087] Furthermore, generating the initial vector of participant capabilities includes:

[0088] Obtain the historical task records and social network data of the participants, and extract the basic characteristic data of the participants from the historical task records of the participants. The basic characteristic data of the participants include the task completion rate, task quality score and task response time. The calculation formula for extracting the basic characteristic data of the participants is as follows:

[0089]

[0090] Among them, TCR is the task completion rate, N c is the number of completed tasks, N c is the total number of tasks, TQS is the task quality score, Q i Score the quality of the i-th task, w i is the task weight coefficient, TRT is the task response time, T is the task response end time, T is the task release time, and N is the total number of tasks.

[0091] Furthermore, feature fusion includes,

[0092] Construct a deep neural network model, input the basic feature data of the participants into the deep neural network model, generate the initial vector of the participant's ability, and obtain the calculation formula of the initial vector of the participant's ability as follows:

[0093] v init =σ(W2·ReLU(W1·x+b1)+b2)

[0094] Among them, v init is the initial vector of the participant's ability, x is the basic characteristic data of the participant, W1 and W2 are weight matrices, b1 and b2 are bias vectors, and σ is the tanh activation function;

[0095] Construct a capability evaluation neural network model, input the participant social network data into the graph convolutional neural network to generate a collaborative capability vector, and generate a collaborative capability vector through feature aggregation. The calculation formula for feature aggregation is as follows:

[0096]

[0097] in, is the adjacency matrix with self-loops added, A is the adjacency matrix of the social network, I is the identity matrix, is the degree matrix, H (l+1) is the feature matrix of the l+1th layer node, H (l) is the feature matrix of the l-th layer node, W (l) is the learnable weight matrix, σ1 is the ReLU activation function;

[0098] The initial capability vector of the participant is fused with the collaborative capability vector to generate the comprehensive capability vector of the participant. The calculation formula for feature fusion is as follows:

[0099] v f =λ·v init +(1-λ)·v c

[0100] λ = sigmoid(MLP([v init ||v c ]))

[0101] Among them, v f is the comprehensive ability vector of the participants, v c is the collaboration capability vector, and λ is the fusion weight coefficient.

[0102] Furthermore, the data of the participants' ability portraits include:

[0103] According to the task complexity data in the collaborative task feature data, the comprehensive ability vector of the participants is weighted and calculated to generate the task matching score. The weighted calculation formula is as follows:

[0104]

[0105] Among them, s is the task matching score, f(c i ) is the complexity adjustment function, which is used to adjust the score according to the complexity of the task. is the comprehensive capability vector v of the participant f The i-th component of i is the weight coefficient of the i-th capability dimension, c i is the i-th component of the task complexity index, α and β are adjustment parameters;

[0106] The task matching score is combined with the comprehensive ability vector of the participant to form the ability profile data of the participant, that is, p = [v f ,s], where P is the participant’s ability profile data.

[0107] S3: Based on the participant capability profile data, the participants are screened and sorted using preset task allocation rules to generate a task allocation plan;

[0108] Furthermore, screening and sorting of participants include,

[0109] Extract participants with free time periods according to the time window data, and filter the list of participants whose task load is less than the preset parallel upper limit;

[0110] Calculate the task linkage degree for each participant in the participant list according to the task dependency data, wherein the task linkage degree is obtained by weighting the similarity between the current task and the participant's historical completed tasks;

[0111] The task linkage degree and the task matching degree score are weightedly combined to obtain a comprehensive score of the participant, the participant list is sorted based on the comprehensive score of the participant, and N participants with the highest comprehensive scores are selected as candidate participants.

[0112] Furthermore, the task allocation scheme includes a task ID, a candidate participant ID, an expected start time, and an expected end time.

[0113] S4: Based on the task allocation scheme, a task invitation is sent to the selected participants, and the task status is updated according to the response of the participants.

[0114] Further, updating the task status according to the participant's response includes:

[0115] According to the candidate participant ID in the task allocation plan, sending task invitation information to the candidate participant via the mobile Internet, wherein the task invitation information includes a task description, an expected start time and an expected end time;

[0116] receiving response data from the candidate participant, the response data including an acceptance mark or a rejection mark, and reselecting the candidate participant when the response data including the rejection mark is returned;

[0117] After receiving the response data including the acceptance mark, a task execution record is established, the task execution record includes the task status mark, the actual start time and the estimated completion time, and the task execution record is stored in the participant's historical task record.

[0118] Embodiment 2: This embodiment further provides an intelligent collaboration system based on mobile Internet, including: a task feature extraction module, a participant capability assessment module, a task allocation optimization module, and a task interactive collaboration module;

[0119] The task feature extraction module is used to input collaborative task data and extract collaborative task feature data according to the collaborative task data, wherein the collaborative task feature data includes task complexity data, time window data and task dependency relationship data;

[0120] The participant capability assessment module is used to obtain the historical task records and social network data of the participants, generate the initial capability vector of the participants through the capability assessment neural network model, and perform feature fusion with the collaborative capability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant capability portrait data;

[0121] The task allocation optimization module is used to screen and sort the participants according to the participant capability profile data using preset task allocation rules to generate a task allocation plan;

[0122] The task interaction and collaboration module is used to send task invitations to selected participants based on the task allocation scheme and update the task status according to the participants' responses.

[0123] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a smart collaboration method based on mobile Internet is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0124] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented: inputting collaborative task data, extracting collaborative task feature data according to the collaborative task data, the collaborative task feature data including task complexity data, time window data, and task dependency relationship data;

[0125] Obtain the historical task records and social network data of the participants, generate the initial vector of the participant's ability through the ability evaluation neural network model, and perform feature fusion with the collaborative ability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant's ability portrait data;

[0126] According to the participant capability profile data, the participants are screened and sorted using preset task allocation rules to generate a task allocation plan;

[0127] Based on the task allocation scheme, task invitations are sent to selected participants, and task statuses are updated according to responses from the participants.

[0128] Example 3, reference Figure 1 - Figure 2 , which is the third embodiment of the present invention. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0129] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent collaboration method based on mobile Internet, characterized in that: The method comprises inputting collaborative task data, and extracting collaborative task feature data according to the collaborative task data, wherein the collaborative task feature data comprises task complexity data, time window data, and task dependency relationship data; Obtain the historical task records and social network data of the participants, generate the initial vector of the participant's ability through the ability evaluation neural network model, and perform feature fusion with the collaborative ability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant's ability portrait data; According to the participant capability profile data, the participants are screened and sorted using preset task allocation rules to generate a task allocation plan; Based on the task allocation scheme, task invitations are sent to selected participants, and task statuses are updated according to responses from the participants.

2. The intelligent collaboration method based on mobile Internet as claimed in claim 1, characterized in that: Extracting task complexity data includes receiving collaborative task data, and extracting task description text and task time parameters from the collaborative task data according to preset task feature extraction rules; Extracting the time window data includes constructing a task timeline based on the task time parameters to generate the time window data; Extracting task dependency data includes using a graph neural network to process the collaborative task data, identifying pre-dependencies between tasks, and generating task dependency data.

3. The intelligent collaboration method based on mobile Internet as claimed in claim 2, characterized in that: The generating of the participant capability initial vector comprises: Obtain the historical task records and social network data of the participants, and extract the basic characteristic data of the participants from the historical task records of the participants. The basic characteristic data of the participants include the task completion rate, task quality score and task response time. The calculation formula for extracting the basic characteristic data of the participants is as follows: Among them, TCR is the task completion rate, N c is the number of completed tasks, N c is the total number of tasks, TQS is the task quality score, Q i The quality score of the i-th task, w i is the task weight coefficient, TRT is the task response time, T is the task response end time, T is the task release time, and N is the total number of tasks.

4. The intelligent collaboration method based on mobile Internet as claimed in claim 3, characterized in that: The feature fusion includes: Construct a deep neural network model, input the basic feature data of the participants into the deep neural network model, generate the initial vector of the participant's ability, and obtain the calculation formula of the initial vector of the participant's ability as follows: v init =σ(W2·ReLU(W1·x+b1)+b2) Among them, v init is the initial vector of the participant's ability, x is the basic characteristic data of the participant, W1 and W2 are weight matrices, b1 and b2 are bias vectors, and σ is the tanh activation function; Construct a capability evaluation neural network model, input the participant social network data into the graph convolutional neural network to generate a collaborative capability vector, and generate a collaborative capability vector through feature aggregation. The calculation formula for feature aggregation is as follows: in, is the adjacency matrix with self-loops added, A is the adjacency matrix of the social network, I is the identity matrix, is the degree matrix, H (l+1) is the feature matrix of the l+1th layer node, H (l) is the feature matrix of the l-th layer node, W (l) is the learnable weight matrix, σ1 is the ReLU activation function; The initial capability vector of the participant is fused with the collaborative capability vector to generate the comprehensive capability vector of the participant. The calculation formula for feature fusion is as follows: v f =λ·v init +(1-λ)·v c λ=sigmoid(MLP([v init ||v c ])) Among them, v f is the comprehensive ability vector of the participants, v c is the collaboration capability vector, and λ is the fusion weight coefficient.

5. The intelligent collaboration method based on mobile Internet as claimed in claim 4, characterized in that: The participant capability portrait data obtained includes: According to the task complexity data in the collaborative task feature data, the comprehensive ability vector of the participants is weighted to generate a task matching score. The weighted calculation formula is as follows: Among them, s is the task matching score, f(c i ) is the complexity adjustment function, which is used to adjust the score according to the complexity of the task. is the i-th component of the comprehensive ability vector of the participant, w i is the weight coefficient of the i-th capability dimension, c i is the i-th component of the task complexity index, α and β are adjustment parameters; The task matching score is combined with the comprehensive ability vector of the participant to form the ability profile data of the participant, that is, p = [v f ,s], where P is the participant’s ability profile data.

6. The intelligent collaboration method based on mobile Internet as claimed in claim 5, characterized in that: The screening and sorting of participants includes: Extract participants with free time periods according to the time window data, and filter the list of participants whose task load is less than the preset parallel upper limit; Calculate the task linkage degree for each participant in the participant list according to the task dependency data, wherein the task linkage degree is obtained by weighting the similarity between the current task and the participant's historical completed tasks; Performing a weighted combination of the task link degree and the task matching score to obtain a comprehensive score of the participant, sorting the participant list based on the comprehensive score of the participant, and selecting N participants with the highest comprehensive scores as candidate participants; The task allocation scheme includes a task ID, a candidate participant ID, an expected start time, and an expected end time.

7. The intelligent collaboration method based on mobile Internet as claimed in claim 6, characterized in that: The updating of the task status according to the response of the participant includes: According to the candidate participant ID in the task allocation plan, sending task invitation information to the candidate participant via the mobile Internet, wherein the task invitation information includes a task description, an expected start time and an expected end time; receiving response data from the candidate participant, the response data including an acceptance mark or a rejection mark, and reselecting the candidate participant when the response data including the rejection mark is returned; After receiving the response data including the acceptance mark, a task execution record is established, the task execution record includes the task status mark, the actual start time and the estimated completion time, and the task execution record is stored in the participant's historical task record.

8. An intelligent collaboration system based on mobile Internet, based on the intelligent collaboration method based on mobile Internet according to any one of claims 1 to 7, characterized in that: It includes task feature extraction module, participant capability assessment module, task allocation optimization module and task interaction and collaboration module; The task feature extraction module is used to input collaborative task data and extract collaborative task feature data according to the collaborative task data, wherein the collaborative task feature data includes task complexity data, time window data and task dependency data; The participant capability assessment module is used to obtain the historical task records and social network data of the participants, generate the initial capability vector of the participants through the capability assessment neural network model, and perform feature fusion in combination with the collaborative capability vector generated by the graph convolutional neural network, calculate the task matching score according to the task complexity data, and obtain the participant capability portrait data; The task allocation optimization module is used to screen and sort the participants according to the participant capability profile data using preset task allocation rules to generate a task allocation plan; The task interactive collaboration module is used to send task invitations to selected participants based on the task allocation scheme, and update task status according to the responses of the participants.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the mobile Internet-based intelligent collaboration method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of any one of claims 1 to 7 of the intelligent collaboration method based on mobile Internet are implemented.

Images