Task collaborative management method and system based on offline application

Abstract

The invention discloses a task cooperation management method and system based on an offline application, and relates to the technical field of offline data management, and the method comprises the steps: determining a task cooperation type, and obtaining a cooperation task resource package; generating a task collaboration system environment based on the collaboration task resource bundle; receiving collaborative data, predicting the modification probability of the collaborative data through a pre-trained prediction model in the collaborative task resource packet, and performing early warning and verification on the collaborative data with a high risk prediction result; and compressing and packaging the collaborative data according to the collaborative task type, and uploading the packaged collaborative data through a priority scheduling mechanism when network connection is recovered. Through the fusion technical scheme of intelligent resource packet matching, generation of a system environment with edge calculation, pre-training model early warning verification and priority scheduling uploading, the resource packet mismatching and parameter error rate are effectively reduced, meanwhile, the uploading delay is reduced, and the offline cooperation efficiency and the data reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of offline data management, and in particular to a task collaborative management method and system based on offline applications. Background Art

[0002] In the field of collaborative project management, traditional collaborative systems rely on a network environment for task initiation and data processing. This exposes multiple technical bottlenecks in scenarios with no or weak network connectivity, such as construction sites. Existing solutions require users to manually match task types with resource packages. When faced with technically jargon-laden task descriptions, such as "bridge pile foundation concrete pouring quality inspection," manual judgment can easily lead to mismatches between data models and business rules. For example, incorrectly selecting a road construction resource package can cause quality inspection standards to become out of sync with bridge project requirements. Furthermore, traditional offline systems only record data passively and lack the ability to predict the risks of parameter modifications. Construction workers often rework data due to forgetting to modify key parameters or failing to detect the impact of parameter correlations. Industry statistics show that this problem occurs in approximately 19% of cases, particularly in multi-person collaborative scenarios. Furthermore, when the network is restored, traditional systems rely on direct upload. The simultaneous transmission of large amounts of offline data can easily cause network congestion, delaying the upload of critical data such as quality rectification orders. Furthermore, compression strategies are not optimized for specific data types, further increasing network burden. In addition, the system environment generation relies on static template loading and cannot be dynamically adjusted according to task semantics and device types. It also lacks edge computing capabilities to verify the collected data in real time and requires manual review after connecting to the Internet, which seriously restricts the efficiency of offline collaboration. Summary of the Invention

[0003] In view of this, the present invention proposes a task collaborative management method and system based on offline applications, which can effectively solve the problems of inefficient resource matching and data errors caused by unverified data upload in offline scenarios. The present invention provides the following technical solutions: A task collaborative management method based on offline applications, the method comprising: Determine the task collaboration type based on user information and task semantic analysis results, and obtain the corresponding collaborative task resource package; initialize and generate the task collaboration system environment based on the collaborative task resource package; Receive collaborative data uploaded by users through the task collaborative system environment, predict the modification probability of the collaborative data through the pre-trained prediction model in the collaborative task resource package, and issue early warning and verification for collaborative data with high-risk prediction results; The collaborative data is compressed and packaged according to the collaborative task type, and the packaged collaborative data is uploaded through a priority scheduling mechanism when the network connection is restored.

[0004] Optionally, determining the task collaboration type according to the user information and the task semantic analysis result, and obtaining the corresponding collaborative task resource package includes: Obtaining a task description input by a user, and performing semantic parsing on the task description using natural language processing technology to extract task keywords; Based on the task keywords and the user authority level corresponding to the user information, matching the preset task type mapping rules to determine the corresponding task collaboration type; Based on the task collaboration type, the corresponding collaborative task resource package is retrieved.

[0005] Optionally, the collaborative task resource package includes a data model preset file, a business model preset file, a collaborative form style preset file, and a collaborative task flow rule file.

[0006] Optionally, the initializing and generating a task collaborative system environment based on the collaborative task resource package includes: Decompress the collaborative task resource package to obtain a data model preset file, a business model preset file, and a collaborative form style preset file; Automatically create a data structure of the task collaboration system in the device's offline database according to the data model preset file, the data structure including a master-slave table relationship and initialization parameters; Automatically generate a business model object entity containing business rules in an offline application of the device according to the business model preset file, wherein the business rules include value verification logic and process control rules; Automatically create a collaborative task form interface in an offline application of the device according to the collaborative form style preset file, wherein the form interface is associated with the data structure and the business model object entity; Load the edge computing module to complete the generation of the task collaboration system environment.

[0007] Optionally, the prediction model training method includes: Extracting historical collaborative data and corresponding modification records from the collaborative task resource package or offline database, wherein the modification records include the modification timestamp of the historical collaborative data, the modification frequency of each parameter, and the modification records of the associated parameters; A single-parameter modification frequency prediction model is trained using an LSTM time series algorithm, wherein the LSTM algorithm weights historical modification frequencies by a time decay factor; The associated parameter modification records are trained using the FP-Growth association rule algorithm to generate a parameter association modification prediction model. The FP-Growth algorithm mines the correlation between parameters through confidence and improvement quantitative indicators, and determines whether there is a strong correlation between parameters through preset trigger conditions; The single parameter modification frequency prediction model and the parameter association modification prediction model are stored in a local device for real-time prediction in an offline state.

[0008] Optionally, receiving collaborative data uploaded by a user through the task collaborative system environment, predicting the modification probability of the collaborative data through a pre-trained prediction model in the collaborative task resource package, and issuing an early warning and verifying the collaborative data with a high-risk prediction result includes: Calculate the modification probability value of the current collaborative data based on the single parameter modification frequency prediction model, and analyze the modification correlation between collaborative data based on the parameter association modification prediction model; When the modification probability value exceeds a preset threshold or it is detected that the associated parameter has been modified, a visual warning mark is made for the corresponding data field in the collaborative form interface; Call the edge computing module in the task collaboration system environment to perform numerical logic verification or image feature recognition verification on the warning data, generate verification results and associate them with the collaborative data.

[0009] Optionally, compressing and packaging the collaborative data according to the collaborative task type, and uploading the packaged collaborative data through a priority scheduling mechanism when the network connection is restored includes: Identify the type of the current collaborative task and obtain the corresponding compression strategy configuration file; According to the compression strategy configuration file, the collaborative data is compressed, packaged and encapsulated; Determine the business priority level based on the collaborative task type; Obtaining a modification probability value of the current collaborative data from the prediction model, and calculating a prediction risk priority based on the confidence and improvement of the parameter-associated modification prediction model; Generate a comprehensive priority index based on the business priority level and the predicted risk priority, and arrange the encapsulated collaborative data in descending order according to the comprehensive priority index to form an upload queue; Real-time monitoring of network quality status, dynamic adjustment of upload strategies based on network quality, use accelerated transmission protocols to upload collaborative data with high comprehensive priority indexes, cache collaborative data with medium and low comprehensive priority indexes in local queues and upload them in queue order; The uploaded data is recorded with a blockchain hash value, and the data consistency is verified through a consensus algorithm after connecting to the network.

[0010] The present invention further discloses a task collaborative management system based on offline applications, comprising: The resource package acquisition module is used to determine the task collaboration type based on user information and task semantic analysis results, and obtain the corresponding collaborative task resource package; An environment initialization module, configured to initialize and generate a task collaboration system environment based on the collaborative task resource package; A data warning module is used to receive collaborative data uploaded by users through the task collaboration system environment, predict the modification probability of the collaborative data using the pre-trained prediction model in the collaborative task resource package, and issue warnings and verify collaborative data with high-risk prediction results; The data uploading module is used to compress and package the collaborative data according to the collaborative task type, and upload the packaged collaborative data through a priority scheduling mechanism when the network connection is restored.

[0011] The present invention further discloses a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0012] The present invention further discloses an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the program.

[0013] According to the technical solution of the present invention, the intelligent identification of task collaboration types and the precise acquisition of resource packages are achieved through semantic analysis and user authority matching. Compared with the traditional manual matching method, the error matching rate of resource packages can be greatly reduced. Relying on the preset files in the resource package, the data structure, business model and form interface are automatically constructed, and by loading the edge computing module, the system can perform real-time logical verification on the uploaded collaborative data in an offline state, effectively reducing the problem of parameter upload errors. Furthermore, the prediction model trained by the LSTM and FP-Growth algorithms can predict the modification probability and parameter correlation impact of the current collaborative data based on historical modification data. When a high-risk modification is detected, a visual warning is triggered and the edge computing module is linked to perform a secondary verification, significantly reducing the omission of parameter modifications due to forgetfulness or negligence of construction personnel. Finally, a comprehensive priority index is generated based on the task type and predicted risk, avoiding network congestion and key data delay problems caused by traditional data upload methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] For purposes of illustration and not limitation, the present invention will now be described with reference to embodiments thereof and the accompanying drawings, in which: Figure 1 is a flowchart of a task collaborative management method based on offline applications in an embodiment of the present invention; Figure 2 Schematic diagram of component modules of the offline application-based task collaborative management system in an embodiment of the present invention; Figure 3 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0016] It should be noted that the features in the embodiments of the present application and the embodiments can be combined with each other without conflict. The embodiments of the present application will be described in detail in conjunction with the accompanying drawings.

[0017] Reference Figure 1 The embodiments of the present application disclose a task cooperation management method based on an offline application, which is used for realizing task data cooperation management in an offline state, and specifically includes the following steps: S100: determining a task cooperation type according to user information and a task semantic analysis result, and obtaining a corresponding cooperation task resource package. Through the cooperation task resource package, the starting, filling and processing of the cooperation task in the offline state can be realized.

[0018] Specifically, when a user initiates the task collaboration system on an offline device, the user first selects a collaboration task or inputs a task description through an interactive interface, for example, in a construction site scenario, the user inputs "K12+300 bridge pile foundation concrete pouring quality inspection". The system performs semantic analysis on the description through an integrated natural language processing (NLP) module, extracts key terms such as "bridge pile foundation", "concrete pouring", and "quality inspection" using a word segmentation algorithm, and eliminates ambiguities by combining a pre-set professional vocabulary, for example, "pile foundation" is explicitly defined as "bridge pile foundation" rather than "house pile foundation". At the same time, the system reads the current user's identity information, which at least includes the current user's permission level. The extracted key terms and the user's permission level are jointly input into a pre-set task type mapping rule library. The rule library is constructed based on historical project data. For example, set the task type "bridge concrete construction quality inspection", which corresponds to "bridge pile foundation-concrete pouring-quality inspection-inspector permission". After successfully matching the task type with the mapping rule library, the system loads the corresponding collaboration task resource package from the local cache according to the task type. The resource package has been filtered by permission, for example, ordinary construction workers cannot obtain resource packages containing design drawings. The collaboration task resource package includes a data model preset file for defining the table structure of the example pile foundation detection data, a business model preset file for embedding the business logic of the example concrete strength calculation formula, a collaboration form style preset file for adapting the inspection form template of the offline device interface, and a collaboration task flow rule file for specifying the process that requires review after user reporting. In the entire processing flow, the system automatically associates similar terms (such as "pouring" matching "pouring") through the context understanding ability of semantic analysis, ensuring the accuracy of task type recognition and avoiding the resource package mismatch problem caused by traditional manual selection.

[0019] S200: Initialize the task collaboration system environment based on the collaboration task resource package.

[0020] After obtaining the collaborative task resource package, firstly, it is encrypted and decrypted and integrity is checked, and after confirming that it is correct, the data model preset file, business model preset file and collaborative form style file are decompressed. Taking the "bridge pile foundation concrete pouring quality inspection" task in step S100 as an example, the data model preset file contains the structure definition of the pile foundation detection master table and the concrete strength slave table, and the system automatically executes the table creation statement through the SQLite offline database engine to create a complete data structure containing the master-slave foreign key association in the local device, and initializes the default field according to the preset parameters. The business model preset file encapsulates business rules such as concrete strength conversion formula and age correction coefficient, and the system automatically generates a business object entity containing the above rules in the application layer through Java reflection mechanism, for example, "concrete strength detection" class. The entity can call the CPU computing power of the edge computing module in real time to perform numerical verification to determine whether the measured strength meets the design requirements. The collaborative form style file defines the interface elements in JSON format, and the system parses and generates a form interface according to the device type, for example, in the tablet end, the pile foundation number, detection point and other fields are displayed in a grid layout, and the photographing control is integrated to associate the "defect image" field, and the form input item is bidirectionally bound with the data structure table field and the business object attribute through JavaScript script. Further, load the lightweight edge computing module from the resource package, which is automatically registered to the business model entity, for example, when the user takes a photo of the concrete surface, the edge computing module calls the preset crack recognition model to classify the image in real time, and the recognition result is automatically filled into the "defect type" field of the form. Finally, a complete task collaborative system environment containing data storage, business logic and interactive interface is formed, which supports real-time data processing and rule verification in offline state.

[0021] S300: Receive user uploaded collaborative data through the task collaborative system environment, predict the modification probability of the collaborative data through the pre-trained prediction model in the collaborative task resource package, and perform early warning and verification on the collaborative data with high risk prediction results.

[0022] The user uploads collaborative data through a collaborative form interface, and real-time data input events are captured and a prediction model is triggered. Before the prediction model is called, the embodiment discloses a training method of the prediction model. Specifically, historical collaborative data and corresponding modification records are extracted from a collaborative task resource package or an offline database, and the modification records include a historical collaborative data modification timestamp, a parameter modification frequency, and associated parameter modification records. The historical modification period of each parameter in the historical collaborative data is trained by an LSTM time series algorithm to generate a single-parameter modification frequency prediction model. The associated parameter modification records are trained by an FP-Growth association rule algorithm to mine the modification association between parameters and generate a parameter associated modification prediction model. The single-parameter modification frequency prediction model and the parameter associated modification prediction model are stored in a local device for real-time prediction in an offline state.

[0023] The single-parameter modification frequency prediction model is trained by an LSTM time series algorithm, wherein the LSTM algorithm weights the historical modification frequency by a time decay factor. Specifically, the calculation formula for weighting the historical modification frequency is: wherein P S (t) is the modification probability of a single parameter at time t, a is a time decay factor for controlling the weight decay of historical data, t i is the timestamp of the i-th parameter modification, f i is the frequency of the i-th parameter modification.

[0024] The parameter associated modification prediction model is generated by training the associated parameter modification records by an FP-Growth association rule algorithm. The FP-Growth algorithm quantifies the association between parameters by confidence and lift indicators, and determines whether there is a strong association between parameters by a preset trigger condition.

[0025] wherein the confidence formula is: used to represent the probability that parameter A is modified and parameter B is modified simultaneously; and the lift formula is: used to represent the lift of parameters A and B to measure whether the association is significantly higher than the independent modification probability; S AB is the frequency support of the simultaneous occurrence of parameters A and B, S A is the frequency support of the occurrence of parameter A alone, and S B is the frequency support of the occurrence of parameter B alone. In the embodiment, the preset trigger condition is C AB > θ and L AB > 1, wherein θ is a preset confidence threshold. By setting C AB > θ, it is ensured that the confidence of the association rule is high to avoid accidental association. By setting L AB>1 to ensure that the relevance of A and B is significantly higher than that of random independence, thereby reducing false positives. For example, in an engineering construction project, if parameters A (concrete strength) and B (age correction factor) satisfy C AB = 0.85 and L AB = 1.2, the system triggers a warning, prompting the user to modify B synchronously to avoid data inconsistency caused by modifying A alone.

[0026] The trained LSTM single-parameter modification frequency model and the FP-Growth association model are loaded. The system inputs the current input collaborative data into the LSTM model to calculate its modification probability through time series pattern analysis, and the FP-Growth model detects the association between the current collaborative data and other recorded data. When the modification probability exceeds the preset threshold or strong associated data anomalies are detected, the system warns in a visual manner next to the corresponding data field in the form, and pops up a prompt message "the collaborative data has high modification risk, please review". Then, the edge computing module in the task collaboration system environment is called to perform multi-dimensional verification on the warning data: the data logic consistency is verified through the rule engine in the business model, and a lightweight AI model is enabled to perform feature recognition on image-type collaborative data. The verification results are associated to the collaborative data record in the form of encrypted timestamp, forming an intelligent processing flow covering prediction, warning, and verification, to ensure the accuracy and risk controllability of offline reporting of various collaborative data.

[0027] S400: According to the type of the collaborative task, the collaborative data is compressed and packaged, and when the network connection is restored, the packaged collaborative data is uploaded through a priority scheduling mechanism.

[0028] Specifically, after the system identifies the current collaborative task type, it retrieves the corresponding configuration file from the pre-set compression strategy library, which includes, for example, WebP format compression for image data in quality rectification single-type tasks, and GZIP algorithm compression for text data, forming a classification compression strategy. Then, the system performs differential compression on the collaborative data according to the strategy, and encapsulates it into a data packet containing task type identification, compression timestamp, and embedding the parameter modification risk label generated by the prediction model in the packet metadata. When the network connection is restored, the business priority level is first determined according to the task type, and a comprehensive priority index is generated by combining the modification probability value output by the prediction model, and all data packets are arranged in descending order of comprehensive priority index to form an upload queue. In this embodiment, the business priority level is defined as P biz , and P biz ∈[1, 5]. For example, the priority level of the quality rectification task is 5, and the priority level of the progress reporting task is 3. The modification probability value P S(t), and modifying the confidence C of the prediction model based on the parameter association AB and the lift L AB , calculating the prediction risk priority P risk , the calculation formula is: Wherein, τ is a preset modification probability threshold, C max is the upper threshold of the associated risk factor. The comprehensive priority index P total is generated by a nonlinear combination formula, and the calculation formula is: Wherein, β ∈ [0, 1], is the business priority weight coefficient. The encapsulated collaborative data is arranged in descending order of P total to form an upload queue.

[0029] At the same time, the network quality state is monitored in real time, and when network congestion is detected, the high-priority data packet is enabled to use the accelerated transmission protocol, for example, using segmented encryption transmission to ensure that the key data with high comprehensive priority index is uploaded in priority, and the medium and low priority data packets are cached to the local queue, and uploaded in order when the network is idle. During the uploading process, the system calculates the blockchain hash value of each data packet and records it locally, and after networking, the consistency of the data is verified through the consensus algorithm and the cloud to ensure the integrity and reliability of the data in the transmission process.

[0030] In summary, the embodiment realizes intelligent recognition of task collaboration type and accurate acquisition of resource package through semantic analysis and user permission matching, effectively reduces the resource package error rate under the traditional manual matching mode, and solves the resource package mismatch problem caused by complex task description. Based on the resource package preset file, a task collaboration system environment containing data structure, business model and form interface is automatically generated, and an edge computing module is integrated, so that the system can perform real-time logical verification and AI feature recognition on engineering detection values, images and other collaborative data to ensure the accuracy of the collaborative data. With the help of the "prediction-early warning-checking" closed-loop mechanism constructed by the LSTM and FP-Growth pre-training model, the data modification risk can be predicted based on the time sequence characteristics and association rules of historical collaborative data, and when high-risk data is detected, visual warning is triggered and the edge computing module is linked to perform double checking, effectively reducing data errors caused by human negligence. In the data uploading stage, the comprehensive priority index is generated according to the task type and the prediction risk, and the transmission strategy is dynamically adjusted according to the network quality, the accelerated transmission protocol is enabled for key data, which greatly reduces the data uploading delay, and at the same time, through classification compression, the problem of network congestion caused by uploading of key data with high comprehensive priority index is avoided.

[0031] With reference to Figure 2 , the embodiment further discloses a task collaboration management system based on offline application, which comprises a resource package acquisition module 21, an environment initialization module 22, a data early warning module 23 and a data uploading module 24. The following will be described in detail: The resource package acquisition module 21 is used to determine the task collaboration type based on user information and task semantic analysis results, and obtain the corresponding collaborative task resource package, including: obtaining the task description input by the user, and performing semantic analysis on the task description through natural language processing technology to extract task keywords; based on the task keywords and the user authority level corresponding to the user information, matching the preset task type mapping rules to determine the corresponding task collaboration type; based on the task collaboration type, calling the corresponding collaborative task resource package.

[0032] The environment initialization module 22 is used to initialize and generate a task collaborative system environment based on the collaborative task resource package, including: decompressing the collaborative task resource package to obtain a data model preset file, a business model preset file and a collaborative form style preset file; automatically creating a data structure of the task collaborative system in the offline database of the device according to the data model preset file, the data structure including a master-slave table relationship and initialization parameters; automatically generating a business model object entity containing business rules in the offline application of the device according to the business model preset file, the business rules including numerical verification logic and process control rules; automatically creating a form interface of the collaborative task in the offline application of the device according to the collaborative form style preset file, the form interface associating the data structure and the business model object entity; loading the edge computing module to complete the generation of the task collaborative system environment.

[0033] The data warning module 23 is used to receive collaborative data uploaded by users through the task collaborative system environment, predict the modification probability of the collaborative data through the pre-trained prediction model in the collaborative task resource package, and warn and verify the collaborative data with high-risk prediction results, including: calculating the modification probability value of the current collaborative data based on the single-parameter modification frequency prediction model, and analyzing the modification correlation between collaborative data based on the parameter association modification prediction model; when the modification probability value exceeds the preset threshold or it is detected that the associated parameter has been modified, the corresponding data field is visually warned in the collaborative form interface; calling the edge computing module in the task collaborative system environment to perform numerical logic verification or image feature recognition verification on the warning data, generate a verification result and associate it with the collaborative data.

[0034] The data upload module 24 is used to compress and package the collaborative data according to the collaborative task type, and upload the packaged collaborative data through the priority scheduling mechanism when the network connection is restored, including: identifying the type of the current collaborative task and obtaining the corresponding compression strategy configuration file; compressing, packaging and encapsulating the collaborative data according to the compression strategy configuration file; determining the business priority level according to the collaborative task type; obtaining the modification probability value of the current collaborative data from the prediction model, and generating a predicted risk priority according to the modification probability value; generating a comprehensive priority index based on the business priority level and the predicted risk priority, and arranging the encapsulated collaborative data in descending order according to the comprehensive priority index to form an upload queue; monitoring the network quality status in real time, dynamically adjusting the upload strategy according to the network quality, using an accelerated transmission protocol to upload collaborative data with a high comprehensive priority index, caching collaborative data with medium and low comprehensive priority indexes to a local queue and uploading them in queue order; performing blockchain hash value recording on the uploaded data, and verifying data consistency through a consensus algorithm after connecting to the network.

[0035] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503; The processor 501 and the memory 502 communicate with each other via the bus 503 ; the processor 501 is used to call program instructions in the memory 502 to execute the methods provided by the above-mentioned method implementation methods.

[0036] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments.

[0037] Those skilled in the art will understand that all or part of the steps for implementing the above-mentioned method implementation method can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method implementation method; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various storage media that can store program codes.

[0038] The apparatus embodiments described above are merely illustrative, units illustrated as separate components can or can not be physically separate, components illustrated as units can or can not be physical units, i.e. can be located in one place or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0039] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of the embodiments or some parts of the embodiments.

[0040] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can occur depending on design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A task collaborative management method based on offline application, characterized in that: The method comprises: Determine the task collaboration type based on user information and task semantic analysis results, and obtain the corresponding collaborative task resource package; Initialize and generate a task collaboration system environment based on the collaborative task resource package; Receive collaborative data uploaded by users through the task collaborative system environment, predict the modification probability of the collaborative data through the pre-trained prediction model in the collaborative task resource package, and issue early warning and verification for collaborative data with high-risk prediction results; The collaborative data is compressed and packaged according to the collaborative task type, and the packaged collaborative data is uploaded through a priority scheduling mechanism when the network connection is restored.

2. The offline application-based task collaborative management method according to claim 1, characterized in that: Determining the task collaboration type based on user information and task semantic analysis results, and obtaining the corresponding collaborative task resource package includes: Obtaining a task description input by a user, and performing semantic parsing on the task description using natural language processing technology to extract task keywords; Based on the task keywords and the user authority level corresponding to the user information, matching the preset task type mapping rules to determine the corresponding task collaboration type; Based on the task collaboration type, the corresponding collaborative task resource package is retrieved.

3. The offline application-based task collaborative management method according to claim 2, characterized in that: The collaborative task resource package includes a data model preset file, a business model preset file, a collaborative form style preset file and a collaborative task flow rule file.

4. The offline application-based task collaborative management method according to claim 1, characterized in that: The initialization and generation of the task collaboration system environment based on the collaborative task resource package includes: Decompress the collaborative task resource package to obtain a data model preset file, a business model preset file, and a collaborative form style preset file; Automatically create a data structure of the task collaboration system in the device's offline database according to the data model preset file, the data structure including a master-slave table relationship and initialization parameters; Automatically generate a business model object entity containing business rules in an offline application of the device according to the business model preset file, wherein the business rules include value verification logic and process control rules; Automatically create a collaborative task form interface in an offline application of the device according to the collaborative form style preset file, wherein the form interface is associated with the data structure and the business model object entity; Load the edge computing module to complete the generation of the task collaboration system environment.

5. The offline application-based task collaborative management method according to claim 1, characterized in that: The training method of the prediction model includes: Extracting historical collaborative data and corresponding modification records from the collaborative task resource package or offline database, wherein the modification records include modification timestamps of the historical collaborative data, modification frequencies of various parameters, and modification records of associated parameters; A single-parameter modification frequency prediction model is trained using an LSTM time series algorithm, wherein the LSTM algorithm weights historical modification frequencies by a time decay factor; The associated parameter modification records are trained using the FP-Growth association rule algorithm to generate a parameter association modification prediction model. The FP-Growth algorithm mines the correlation between parameters through confidence and improvement quantitative indicators, and determines whether there is a strong correlation between parameters through preset trigger conditions; The single parameter modification frequency prediction model and the parameter association modification prediction model are stored in a local device for real-time prediction in an offline state.

6. The offline application-based task collaborative management method according to claim 5, characterized in that: The receiving of collaborative data uploaded by the user through the task collaborative system environment, predicting the modification probability of the collaborative data through the pre-trained prediction model in the collaborative task resource package, and issuing early warning and verification for collaborative data with high-risk prediction results include: Calculate the modification probability value of the current collaborative data based on the single parameter modification frequency prediction model, and analyze the modification correlation between collaborative data based on the parameter association modification prediction model; When the modification probability value exceeds a preset threshold or it is detected that the associated parameter has been modified, a visual warning mark is made for the corresponding data field in the collaborative form interface; Call the edge computing module in the task collaboration system environment to perform numerical logic verification or image feature recognition verification on the warning data, generate verification results and associate them with the collaborative data.

7. The offline application-based task collaborative management method according to claim 5, characterized in that: The compressing and packaging the collaborative data according to the collaborative task type, and uploading the packaged collaborative data through a priority scheduling mechanism when the network connection is restored, includes: Identify the type of the current collaborative task and obtain the corresponding compression strategy configuration file; According to the compression strategy configuration file, the collaborative data is compressed, packaged and encapsulated; Determine the business priority level based on the collaborative task type; Obtaining a modification probability value of the current collaborative data from the prediction model, and calculating a prediction risk priority based on the confidence and improvement of the parameter-associated modification prediction model; Generate a comprehensive priority index based on the business priority level and the predicted risk priority, and arrange the encapsulated collaborative data in descending order according to the comprehensive priority index to form an upload queue; Real-time monitoring of network quality status, dynamic adjustment of upload strategies based on network quality, use of accelerated transmission protocols to upload collaborative data with high comprehensive priority indexes, cache collaborative data with medium and low comprehensive priority indexes into local queues and upload them in queue order; The uploaded data is recorded with a blockchain hash value, and the data consistency is verified through a consensus algorithm after connecting to the network.

8. A task collaborative management system based on offline application, characterized in that: include: The resource package acquisition module is used to determine the task collaboration type based on user information and task semantic analysis results, and obtain the corresponding collaborative task resource package; An environment initialization module, configured to initialize and generate a task collaborative system environment based on the collaborative task resource package; A data warning module is used to receive collaborative data uploaded by users through the task collaboration system environment, predict the modification probability of the collaborative data using the pre-trained prediction model in the collaborative task resource package, and issue warnings and verify collaborative data with high-risk prediction results; The data uploading module is used to compress and package the collaborative data according to the collaborative task type, and upload the packaged collaborative data through a priority scheduling mechanism when the network connection is restored.

9. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

Images