Electronic contract signing and order settlement integrated platform in zero work system

Abstract

The invention discloses an electronic contract signing and order settlement integrated platform in a zero-work system, and relates to the technical field of electronic contract signing, and the technical scheme is characterized in that the method comprises the steps: obtaining the current task publishing information and historical task data information of a task publisher; performing training processing on historical task condition information and zero worker state information in the historical task data information to obtain a task matching model I; performing training processing on historical task element trends in the historical task data information to feature change trends to obtain a second task matching model; task condition information in the current task release information is input into a task matching model I to predict and obtain a dispatch prediction result I, and task elements in the current task release information are input into a task matching model II to predict and obtain a dispatch prediction result II; the method has the advantages that integration of electronic contract signing and order settlement is achieved, and one-stop service experience is provided for workers and task publishers.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic contract signing, and more specifically, to an integrated platform for electronic contract signing and order settlement in a gig system. Background Art

[0002] Amidst the rapid growth of today's digital economy, the gig economy, as an emerging economic model, is experiencing rapid growth. A large number of job postings and gig workers connect through gig systems. However, traditional gig systems have exposed a series of pressing operational issues, severely hindering the efficient development of the gig economy. Traditional gig systems often rely on simple rules or limited experience when dispatching jobs. For example, they simply match superficial task requirements (such as work hours and task type) with the basic skills of gig workers, failing to deeply explore the multi-dimensional compatibility between tasks and gig workers. They also fail to fully consider the correlation between actual task information, such as task complexity, urgency, and required collaboration skills, and the actual status of gig workers (such as their work efficiency, recent workload, and teamwork experience). This one-sided matching approach often leads to unsatisfactory dispatch results. It often results in gig workers being unqualified for the task or waiting too long for a suitable gig worker, significantly reducing the efficiency and quality of task execution. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an integrated platform for electronic contract signing and order settlement in the gig system.

[0004] To achieve the above object, the present invention provides the following technical solutions: The integrated platform for electronic contract signing and order settlement in the gig economy system includes: Acquisition module: obtains the current task release information and historical task data information of the task publisher; Training module: The historical task status information and the odd-job status information in the historical task data are trained to obtain the first task matching model; the historical task element trend feature change trend in the historical task data is trained to obtain the second task matching model; Prediction module: Input the task status information in the current task release information into task matching model 1 to obtain the dispatch prediction result 1, and input the task elements in the current task release information into task matching model 2 to obtain the dispatch prediction result 2; Processing module: Outputs pending dispatch information based on the comparison between dispatch prediction result 1 and dispatch prediction result 2. Based on the pending dispatch information, statistics are compiled on the overall trend of the development amplitude of all task demand-related elements in the historical task elements to obtain a historical task demand development trend set, and the current pending task demand trend to which dispatch prediction result 2 belongs is extracted. Contract signing and settlement module: The current task demand trend and historical task demand development trend set are processed and analyzed to obtain the dispatch confirmation result. Based on the dispatch confirmation result, an electronic contract is signed between the gig worker and the task publisher, and the order is settled according to the preset settlement plan when the task is completed.

[0005] Preferably, the task matching model 2 is obtained by training the historical task element trend feature change trend in the historical task data information, which specifically includes the following steps: Dividing the historical task data information into a first historical stage, a second historical stage, and a third historical stage; wherein the first historical stage includes at least two first task elements of the same type, the second historical stage includes at least two second task elements of the same type, and the third historical stage includes at least two third task elements of the same type; Extracting the change trend characteristics between at least two first task elements of the same type in the first historical stage to obtain a first change trend characteristic, extracting the change trend characteristics between at least two second task elements of the same type in the second historical stage to obtain a second change trend characteristic, and extracting the change trend characteristics between at least two third task elements of the same type in the third historical stage to obtain a third change trend characteristic; Counting the difference trend characteristics among the first change trend characteristic, the second change trend characteristic, and the third change trend characteristic to obtain a historical task element trend characteristic; A second task matching model is trained based on the trend characteristics of the historical task elements.

[0006] Preferably, outputting the order dispatch information to be verified based on the comparison between the first order dispatch prediction result and the second order dispatch prediction result specifically includes the following steps: Compare the similarity between the dispatch prediction result 1 and the dispatch prediction result 2 to obtain the similarity; Comparing the similarity with a preset similarity threshold; If the similarity is greater than or equal to the similarity threshold, the dispatch prediction result 1 is used as the dispatch determination result. Based on the dispatch determination result, an electronic contract is signed between the gig worker and the task publisher, and when the task is completed, the order is settled according to the preset settlement plan; If the similarity is less than the preset similarity threshold, the dispatch information to be verified is output.

[0007] Preferably, the historical task requirement development trend set includes a first task requirement development trend, a second task requirement development trend, and a third task requirement development trend, and specifically includes the following steps: The development trend of the first task requirement is the development extent of at least two first task elements of the same type in the first historical stage; The second task requirement development trend is the development extent of at least two second task elements of the same type in the second historical stage; The development trend of the third task requirement is the development extent of at least two third task elements of the same type in the third historical stage.

[0008] Preferably, the current task demand trend and the historical task demand development trend set are processed and analyzed to obtain the dispatch determination result, which specifically includes the following steps: Analyze whether the current demand trend of the task to be tested, the development trend of the first task demand, the development trend of the second task demand, and the development trend of the third task demand are all in a stable demand state to obtain a dispatch confirmation result or dispatch correction information; Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a revised difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; and filter the revised difference dispatch elements to obtain an adjusted dispatch element. Among them, the adjustment dispatch element and the confirmation dispatch element are combined to obtain the dispatch confirmation result.

[0009] Preferably, a situation analysis is performed to determine whether the current demand trend of the task to be tested, the development trend of the first task demand, the development trend of the second task demand, and the development trend of the third task demand are all in a stable demand state to obtain a dispatch determination result or dispatch correction information, specifically including the following steps: If the first task demand development trend, the second task demand development trend, and the third task demand development trend are all stable demand states, then determine whether the current task demand trend to be tested belongs to a stable demand state. If so, determine the predicted dispatch result 1 as the final dispatch optimization result and output the dispatch confirmation result. Otherwise, output the first demand trend continued judgment information; Based on the order confirmation result, an electronic contract signing process is carried out between the gig worker and the task publisher. After the contract is signed and the task is completed, the order is settled according to the preset settlement rules. Otherwise, a second demand situation continuation judgment information is output; The first demand situation continuation judgment information or the second demand situation continuation judgment information is processed and analyzed to obtain output dispatch correction information.

[0010] Preferably, processing and analyzing the first demand trend continuation information or the second demand trend continuation information to obtain output dispatch correction information specifically includes the following steps: According to the first demand trend continuation information, determine whether the current demand trend of the task to be tested belongs to the demand growth state. If so, output the dispatch correction information. If not, determine whether the current demand trend of the task to be tested belongs to the demand decline state according to the second demand trend continuation information. If not, re-predict the predicted dispatch result. If so, output the dispatch correction information.

[0011] Preferably, extracting the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain the revised difference dispatch elements, extracting the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain the confirmed dispatch elements, and screening the revised difference dispatch elements to obtain the adjusted dispatch elements, specifically comprising the following steps: Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a corrected difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; The development amplitude difference between each difference dispatch element in the statistically corrected difference dispatch element is used to obtain the development amplitude interval value; Filter out historical contracted task-completed gig workers from all gig workers who have participated in the task, count the remaining dispatch-related elements of the historical contracted task-completed gig workers in the current business structure after removing the confirmed dispatch elements to obtain a first pre-processed dispatch element, and count the development amplitudes of each dispatch-related element in the pre-processed dispatch element to obtain a pre-processed development amplitude value set; The first pre-processed dispatch element and the pre-processed development amplitude value set are processed and analyzed to obtain the adjusted dispatch element.

[0012] Preferably, processing and analyzing the first pre-processed dispatch element and the pre-processed development amplitude value set to obtain the adjusted dispatch element specifically includes the following steps: Filter out the corresponding dispatch-related elements whose preprocessing development amplitude values ​​are within the development amplitude interval value from the first preprocessing dispatch element to obtain the second preprocessing dispatch element; Associating the second pre-processed dispatch element with the corrected difference dispatch element to obtain an association relationship; Filtering the closest corresponding dispatch-related element from the second pre-processed dispatch element to obtain a third pre-processed dispatch element; The dispatch-related elements whose corresponding development amplitudes are selected from the third pre-processed dispatch elements and whose development amplitudes are integrated with the confirmed dispatch elements and whose results belong to a stable demand state are obtained to obtain adjusted dispatch elements.

[0013] Compared with the prior art, the present invention has the following beneficial effects: This application analyzes the relationship between tasks and gig workers from different perspectives through Task Matching Model 1 and Task Matching Model 2. Task Matching Model 1 focuses on the immediate matching of task status and gig worker status, while Task Matching Model 2 focuses on the impact of long-term changing trends of task elements on dispatching. Combining the dispatch prediction results of the two models, it is possible to comprehensively and accurately consider various factors and dispatch tasks to the most suitable gig workers more accurately. This avoids the unreasonable situations that may have occurred in the past when dispatching orders based on a single dimension or simple rules, greatly improves the efficiency and accuracy of task allocation, and reduces problems such as inefficient task execution or idle gig worker resources due to improper dispatching.

[0014] This application fully considers the changing trends of historical task element trends to construct Task Matching Model 2. This enables the platform to keenly perceive the dynamic changes in task requirements in the time dimension, such as the upgrade of skill requirements for tasks as the industry develops, and changes in the market environment that lead to changes in task resource requirements. When a new task is released, the dispatching strategy can be adjusted in a timely manner according to the changing trends of task elements to find gig workers that are more in line with future development needs for the task, rather than just being limited to the current task status. This adaptability to the evolution of task requirements has greatly enhanced the platform's competitiveness in the complex and changing gig market environment, and can better respond to various sudden and long-term changes in task requirements.

[0015] This application integrates electronic contract signing and order settlement, providing a one-stop service experience for gig workers and task publishers. After accepting a task, gig workers no longer need to seek other channels for contract signing and fee settlement, reducing cumbersome operational procedures; task publishers can also more conveniently manage task contracts and expenses. This convenience not only improves user satisfaction with the platform, but also attracts more gig workers and task publishers to use the platform, promoting the expansion of the platform's user base and business growth. At the same time, it can better monitor the entire task process, protect the legitimate rights and interests of both parties, and reduce the occurrence of contract disputes and settlement disputes. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an integrated platform for electronic contract signing and order settlement in a gig work system proposed by the present invention; Figure 2 The present invention provides a schematic diagram of the method steps for adjusting dispatch elements in an integrated platform for electronic contract signing and order settlement in a gig system. DETAILED DESCRIPTION

[0017] Reference Figures 1 to 2 .

[0018] The embodiment further illustrates the integrated platform for electronic contract signing and order settlement in the gig system proposed by the present invention.

[0019] The integrated platform for electronic contract signing and order settlement in the gig economy system includes: Acquisition module: obtains the current task release information and historical task data information of the task publisher; Training module: The historical task status information and the odd-job status information in the historical task data are trained to obtain the first task matching model; the historical task element trend feature change trend in the historical task data is trained to obtain the second task matching model; Prediction module: Input the task status information in the current task release information into task matching model 1 to obtain the dispatch prediction result 1, and input the task elements in the current task release information into task matching model 2 to obtain the dispatch prediction result 2; Processing module: Outputs pending dispatch information based on the comparison between dispatch prediction result 1 and dispatch prediction result 2. Based on the pending dispatch information, statistics are compiled on the overall trend of the development amplitude of all task demand-related elements in the historical task elements to obtain a historical task demand development trend set, and the current pending task demand trend to which dispatch prediction result 2 belongs is extracted. Contract signing and settlement module: The current task demand trend and historical task demand development trend set are processed and analyzed to obtain the dispatch confirmation result. Based on the dispatch confirmation result, an electronic contract is signed between the gig worker and the task publisher, and the order is settled according to the preset settlement plan when the task is completed.

[0020] In this application, the acquisition module acts as the data entry point for the entire system, and it actively interacts with the task publisher. On the one hand, it collects current task release information, which covers the detailed content of the task, such as the specific work items to be completed, the quality standards required for task execution, and the time limits for task start and end. On the other hand, it obtains historical task data information, which includes records of past task execution processes, such as the actual completion status of the task, whether there were delays or quality issues, and past changes in task elements, such as fluctuations in the task difficulty coefficient and increases or decreases in required resources. By comprehensively collecting this information, a solid data foundation is laid for the operation of subsequent modules.

[0021] Training Task Matching Model 1: The training module conducts in-depth analysis of historical task status information and gig worker status information within historical task data. Historical task status information covers various statuses during task execution, such as task completion progress and the degree of difficulty encountered during task execution. Gig worker status information includes information about the gig worker's skill level, previous work experience, and work efficiency. This information is repeatedly trained and learned using machine learning techniques to uncover potential matching patterns and patterns between tasks and gig worker status, ultimately constructing Task Matching Model 1. This model determines which gig workers, based on the input task status information, have a high degree of matching with the task.

[0022] The training module focuses on the changing trends of the characteristics of historical task elements. First, the historical stages are carefully divided into the first historical stage, the second historical stage, and the third historical stage. In each stage, at least two task elements of the same type are extracted. For example, the difficulty factors of multiple tasks are extracted in the first historical stage. Then, the changing trend characteristics of these task elements in their respective stages are determined, such as whether the difficulty factor gradually increases or decreases, and the first change trend characteristics, the second change trend characteristics, and the third change trend characteristics are obtained respectively. Then, the differences between these change trend characteristics are statistically analyzed to summarize the trend characteristics of historical task elements. Finally, based on this feature, repeated training is performed to generate the second task matching model, which can capture the evolution of task elements over time and be used to predict the impact of future changes in task elements on dispatching.

[0023] The prediction module inputs the task status information in the current task release information, such as the urgency and complexity of the task, into the previously trained task matching model 1. The task matching model 1 predicts which gig workers are suitable for undertaking the task based on the matching pattern of tasks and gig worker status it has learned, and then obtains the dispatch prediction result 1.

[0024] The prediction module inputs the task elements in the current task release information, such as the skill type and resource quantity required for the task, into the task matching model 2. The task matching model 2 processes the input task elements based on its understanding of the changing rules of the task elements and predicts a suitable dispatching plan based on the development trend of the task elements to obtain the dispatching prediction result 2.

[0025] The processing module calculates the similarity between dispatch prediction result 1 and dispatch prediction result 2, deriving a specific similarity value by comparing the similarities in the recommended gig workers, task allocation methods, and other aspects of the two results. This similarity value is then compared with a pre-set similarity threshold. If the similarity is greater than or equal to the threshold, the two predictions are relatively consistent. Dispatch prediction result 1 is then used as the final dispatch result, proceeding to the subsequent electronic contract signing and order settlement stages. If the similarity is less than the threshold, indicating a significant discrepancy between the two results, the dispatch information for verification is output for further analysis.

[0026] After receiving the pending dispatch information, the post-processing module compiles statistics on the development magnitude of all historical task elements related to task requirements. For example, it calculates the growth rate of skill requirements and resource requirements over the past period. By comprehensively analyzing the development magnitude of these elements, it obtains a set of historical task demand trends. It also extracts the current task demand trends associated with dispatch prediction result 2, providing detailed data support for more accurate dispatch results.

[0027] The contract settlement module comprehensively analyzes the current demand trend for the task under test and the historical demand trends for the task under test. If the demand trends for the first, second, and third tasks are all stable, the module further determines whether the current demand trend for the task under test is also stable. If so, the predicted dispatch result 1 is directly determined to be the final dispatch optimization result, i.e., the dispatch confirmation result. If not, the module outputs the first demand trend determination information for further analysis.

[0028] If the analysis reveals that the demand trends for the first, second, and third tasks are not all stable, information on the second demand trend is output. Further processing and analysis of the first or second demand trend information is then performed. Based on this information, it is determined whether the demand trend for the task under test is increasing or decreasing. If it is increasing or decreasing, revised dispatch information is output. Based on the revised dispatch information, discrepancies between the first and second predicted dispatch results (such as differences in recommended gig workers or number of assigned tasks) and common dispatch elements (such as recommended gig workers with the same skill set) are extracted. These discrepancies are then filtered and combined with information on gig workers who have previously signed and completed tasks. For example, historically completed gig workers are selected from all gig workers who have participated in tasks. The remaining dispatch elements for these gig workers in the current business structure, excluding confirmed dispatch elements, are counted, along with the magnitude of these elements' development. These elements are then processed to produce adjusted dispatch elements. Ultimately, the order adjustment and confirmation elements are combined to produce an accurate order confirmation result. Based on this order confirmation result, the gig worker and the task publisher can sign an electronic contract. After the task is completed, the order is settled according to the preset settlement plan.

[0029] The task matching model 2 is obtained by training the historical task element trend feature change trend in the historical task data information, which specifically includes the following steps: Dividing the historical task data information into a first historical stage, a second historical stage, and a third historical stage; wherein the first historical stage includes at least two first task elements of the same type, the second historical stage includes at least two second task elements of the same type, and the third historical stage includes at least two third task elements of the same type; Extracting the change trend characteristics between at least two first task elements of the same type in the first historical stage to obtain a first change trend characteristic, extracting the change trend characteristics between at least two second task elements of the same type in the second historical stage to obtain a second change trend characteristic, and extracting the change trend characteristics between at least two third task elements of the same type in the third historical stage to obtain a third change trend characteristic; The difference trend characteristics between the first change trend characteristic, the second change trend characteristic and the third change trend characteristic are statistically analyzed to obtain the trend characteristics of the historical task elements; Task matching model 2 is trained based on the trend characteristics of historical task elements.

[0030] This application first sorts out the historical task data information and divides the entire historical time span into the first historical stage, the second historical stage and the third historical stage. In each stage, find at least two task elements of the same type. For example, in a gig system, if the task elements include task difficulty, required skill level, etc., the task difficulty of two or more tasks can be selected as the same type of task elements in the first historical stage; the same applies to the second and third historical stages. This division and selection is to facilitate the study of the changes in task elements in different stages to provide a basis for subsequent analysis.

[0031] For each historical stage, we extract trend characteristics for the same type of task elements. For example, by comparing the difficulty values ​​and related attributes of at least two tasks in the first historical stage, we analyze whether the difficulty increases, decreases, or fluctuates, thereby obtaining the first trend characteristic. Similarly, we perform similar operations on the second task element in the second historical stage and the third task element in the third historical stage, respectively, to obtain the second and third trend characteristics. These characteristics reflect the specific trend characteristics of task elements within different historical stages.

[0032] After obtaining the trend characteristics of change in the three stages, we conducted a comprehensive statistical analysis of the first, second, and third trend characteristics. By analyzing the differences between them, such as the magnitude and direction of change, we summarized the overall trend characteristics of historical mission elements. This step aims to grasp the overall trend of change of mission elements throughout the entire historical process from a macro perspective, integrating and refining the characteristics of each stage.

[0033] Finally, the relevant models are trained using training rules based on the historical trend characteristics of task elements. During the training process, the model continuously learns the patterns inherent in these trends, adjusting its parameters and structure. Ultimately, a second task matching model is developed that accurately reflects the relationship between task element trends and business logic such as dispatching. This model can be used to predict dispatching based on the changing trends of task elements, assisting the gig system in allocating tasks more rationally.

[0034] Outputting the order information to be verified based on the comparison between the first order prediction result and the second order prediction result specifically includes the following steps: Compare the similarity between the dispatch prediction result 1 and the dispatch prediction result 2 to obtain the similarity; Comparing the similarity with a preset similarity threshold; If the similarity is greater than or equal to the similarity threshold, the dispatch prediction result 1 is used as the dispatch determination result. Based on the dispatch determination result, an electronic contract is signed between the gig worker and the task publisher, and when the task is completed, the order is settled according to the preset settlement plan; If the similarity is less than the preset similarity threshold, the dispatch information to be verified is output.

[0035] This application first analyzes dispatch prediction results 1 and 2, which are dispatch plans derived using different task matching models. These plans may include information such as recommended gig workers, the number of assigned tasks, and task assignment priorities. Using a specific algorithm (such as cosine similarity or edit distance, depending on the data type and structure), this information is comprehensively considered to calculate the degree of similarity between the two results and generate a specific similarity value. This value quantitatively reflects the similarity between the two dispatch prediction plans across various dimensions.

[0036] The calculated similarity is compared with a pre-set similarity threshold. This threshold is determined based on multiple factors, including the gig system's business needs, historical experience, and the accuracy requirements for dispatching orders. It serves as the criterion for determining whether two dispatch prediction results are sufficiently similar.

[0037] If the calculated similarity is greater than or equal to the preset similarity threshold, it indicates that dispatch prediction result 1 and dispatch prediction result 2 are largely consistent, meaning that the two predictions recommend similar dispatch scenarios. To improve efficiency, dispatch prediction result 1 is then used as the final dispatch result. Based on this result, an electronic contract signing process is initiated between the gig worker and the task publisher to clarify the rights and obligations of both parties. After the task is completed, settlement is conducted according to a pre-defined settlement plan (e.g., fees determined based on factors such as task completion volume, work duration, and work quality).

[0038] If the similarity is less than the preset similarity threshold, it indicates that there is a significant difference between the first and second prediction results, and the dispatch recommendations provided by the two prediction solutions are inconsistent in key aspects. In this case, the dispatch result cannot be directly determined, and instead, dispatch information for verification is output. This information is further processed to more accurately determine the appropriate dispatch solution, avoiding problems with subsequent task execution caused by unreasonable dispatch.

[0039] The historical task demand development trend set includes the first task demand development trend, the second task demand development trend, and the third task demand development trend, and specifically includes the following steps: The development trend of the first task requirement is the development extent of at least two first task elements of the same type in the first historical stage; The development trend of the second task requirement is the development extent of at least two second task elements of the same type in the second historical stage; The development trend of the third task requirement refers to the development extent of at least two third task elements of the same type in the third historical stage.

[0040] This application first focuses on the first historical stage, and finds at least two first task elements of the same type in this stage, such as task difficulty, required skill level and other elements. The development range of these elements is obtained by analyzing their numerical changes, attribute evolution and other conditions in the first historical stage. For example, if the first task element is task difficulty, the increase or decrease in difficulty is calculated by comparing the specific values ​​of task difficulty at different time points to determine the development trend of the first task requirement. This step is to clarify the changes in task elements in the first historical stage and reflect the development trend of task requirements in this stage.

[0041] Using the same methodology as the first historical phase, we analyze at least two of the same secondary task elements in the second historical phase. Again, using task difficulty as an example, we examine its changes during the second historical phase and determine its magnitude, thereby deriving the developmental trends of secondary task requirements. This helps us understand the developmental characteristics of task elements in the second historical phase, contrasting and extending the first historical phase, and further enhancing our overall understanding of the developmental trends of task requirements.

[0042] Perform similar operations for at least two third-mission elements of the same type in the third historical stage. By analyzing the changes in these elements and calculating their developmental range, determine the development trend of the third-mission requirements. This completes the analysis of the developmental range of the mission elements across the three historical stages.

[0043] The historical task demand development trend set is formed by integrating the first, second, and third task demand development trends. This set comprehensively covers the development of task elements at different historical stages, providing basic data for subsequent analysis of the relationship between current task demand trends and historical data. This facilitates the system's comprehensive assessment of the overall development trend of task demand and assists with dispatch decisions and other business operations.

[0044] The dispatch determination result is obtained by processing and analyzing the current task demand trend and the historical task demand development trend set, which specifically includes the following steps: Analyze whether the current demand trend of the task to be tested, the development trend of the first task demand, the development trend of the second task demand, and the development trend of the third task demand are all in a stable demand state to obtain a dispatch confirmation result or dispatch correction information; Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a revised difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; and filter the revised difference dispatch elements to obtain an adjusted dispatch element. Among them, the order dispatching element adjustment and order dispatching element confirmation are combined to obtain the order dispatching confirmation result.

[0045] This application evaluates the current demand trend of the task to be tested and the first, second, and third task demand development trends in the historical task demand development trends to determine whether they are all in a stable demand state. The stable demand state can be defined based on the fact that the task elements (such as task difficulty, required skills, resource requirements, etc.) fluctuate little and remain relatively constant within a certain period of time. If these four demand trends are all in a stable demand state, the current demand trend of the task to be tested is further judged. If it is also stable, the predicted dispatch result is determined to be the final dispatch optimization result, that is, the dispatch determination result is obtained; if the current demand trend of the task to be tested is unstable, the first demand trend continuation judgment information is output. If the first, second, and third task demand development trends are not all stable, the second demand trend continuation judgment information is output.

[0046] After receiving the first or second demand trend update information, an in-depth analysis is performed. If the first demand trend update information indicates that the demand trend for the task under test is increasing, or if the second demand trend update information indicates that the demand trend is decreasing, a revised dispatch information is output. Based on the revised dispatch information, the dispatch elements that differ between the first and second predicted dispatch results (such as different part-time job recommendations, different task allocation quantities, etc.) and the confirmed dispatch elements that are the same (such as both recommending part-time jobs with certain skills) are extracted.

[0047] The modified difference dispatch elements are screened. The development amplitude interval value is obtained by counting the development amplitude difference between each difference dispatch element in the modified difference dispatch element. The gig workers who have completed the historical contracted tasks are screened from the gig workers who have participated in the task, and the remaining dispatch-related elements of these gig workers in the current business structure excluding the confirmed dispatch elements are counted to obtain the first pre-processed dispatch element and their development amplitudes are counted to form a pre-processed development amplitude set. Then, the elements in the pre-processed development amplitude set that are within the development amplitude interval value are screened from the first pre-processed dispatch element to obtain the second pre-processed dispatch element. The second pre-processed dispatch element and the modified difference dispatch element are associated to find the element with the closest association relationship to obtain the third pre-processed dispatch element. Finally, the elements whose development amplitude and the development amplitude integration result of the confirmed dispatch element are screened from the third pre-processed dispatch element to obtain the adjusted dispatch element.

[0048] The final dispatch determination result is formed by combining the adjustment and confirmation elements. This result comprehensively considers the changes in current task demand and the development of historical task demand, providing an accurate basis for the electronic contract signing between gig workers and task publishers, ensuring reasonable and efficient task allocation.

[0049] Analyzing whether the current demand trend of the task to be tested, the development trend of the first task demand, the development trend of the second task demand, and the development trend of the third task demand are all in a stable demand state to obtain a dispatch determination result or dispatch correction information, specifically including the following steps: If the first task demand development trend, the second task demand development trend, and the third task demand development trend are all stable demand states, then determine whether the current task demand trend to be tested belongs to a stable demand state. If so, determine the predicted dispatch result 1 as the final dispatch optimization result and output the dispatch confirmation result. Otherwise, output the first demand trend continued judgment information; Based on the order confirmation result, an electronic contract signing process is carried out between the gig worker and the task publisher. After the contract is signed and the task is completed, the order is settled according to the preset settlement rules. Otherwise, a second demand situation continuation judgment information is output; The first demand situation continuation judgment information or the second demand situation continuation judgment information is processed and analyzed to obtain output dispatch correction information.

[0050] This application first checks whether the demand trends for the first, second, and third tasks are all stable. A stable demand state means that task-related factors (such as task difficulty, resource requirements, and skill requirements) fluctuate minimally and remain relatively stable over a period of time. For example, the skill level required for the task does not change significantly, and resource requirements remain within a certain range. If all three historical demand trends meet the criteria for a stable demand state, the application proceeds to the next step. If not, the application directly outputs the second demand trend re-judgment information, and the subsequent processing flow begins.

[0051] After confirming that the three historical task demand trends are stable, the process begins to determine whether the current task demand trend is also stable. This determination is based on similar criteria as the historical task demand trends, focusing on the fluctuations in task elements. If the current task demand trend is stable, it indicates that the current task demand is consistent with historical conditions and has not changed much. At this point, the predicted dispatch result 1 is determined to be the final dispatch optimization result, and the dispatch confirmation result is output. Based on this result, the gig worker and the task publisher are prompted to sign an electronic contract. After the task is completed, the order is settled according to the preset settlement rules. If the current task demand trend is unstable, the first demand trend continuation judgment information is output.

[0052] After receiving the first or second demand trend renewal information, this information is processed and analyzed. By thoroughly analyzing the changing trends of task requirements, it is determined whether the current task demand trend is experiencing growth (e.g., increasing task difficulty, increasing resource requirements, or improving skill requirements) or decline (e.g., decreasing task difficulty, decreasing resource requirements, or reducing skill requirements). Based on this determination, dispatch correction information is output, providing a basis for subsequent adjustments to the dispatch plan to ensure that dispatch can adapt to changing task requirements and achieve more reasonable task allocation.

[0053] Processing and analyzing the first demand situation continuation judgment information or the second demand situation continuation judgment information to obtain output dispatch correction information specifically includes the following steps: According to the first demand trend continuation information, determine whether the demand trend of the current task to be tested belongs to the demand growth state. If so, output the dispatch correction information. If not, determine whether the demand trend of the current task to be tested belongs to the demand decline state according to the second demand trend continuation information. If not, re-predict the predicted dispatch result. If so, output the dispatch correction information.

[0054] This application begins to analyze the demand trend of the current task to be tested after receiving the first demand trend continuation information. The core of the judgment is to determine whether the task demand is in a growing state, such as whether the task's demand for resources has increased, whether the skill requirements have increased, whether the task difficulty has increased, etc. If it is determined through analysis that the current demand trend of the task to be tested belongs to a demand growth state, this means that the requirements of the current task have increased compared to before, and the original dispatch forecast results may no longer apply. At this point, the system will output dispatch correction information to provide a basis for subsequent adjustments to the dispatch plan.

[0055] If the first demand trend determination indicates that the current task's demand is not increasing, the system will conduct further analysis based on the second demand trend determination. This determination focuses on determining whether the task's demand is decreasing, such as if the task's resource requirements, skill requirements, or difficulty level are decreasing. If the current task's demand is decreasing, indicating a decrease in task requirements, adjustments to the dispatch plan are also necessary, and the system will output dispatch correction information.

[0056] If the second demand trend assessment indicates that the current task demand trend is neither increasing nor decreasing, this indicates that the task demand is changing in a complex manner and cannot be simply categorized as increasing or decreasing. In this case, the original forecast dispatch result (1) may not accurately reflect the actual task demand. To determine a more reasonable dispatch solution, the forecast dispatch result (1) will be re-forecasted, taking into account more factors and data to accommodate the uncertainty of task demand. Based on the new analysis results, a decision will be made whether to output revised dispatch information.

[0057] Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a revised difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; and filter the revised difference dispatch elements to obtain an adjusted dispatch element. Specifically, the following steps are included: Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a corrected difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; The development amplitude difference between each difference dispatch element in the statistically corrected difference dispatch element is used to obtain the development amplitude interval value; Filter out historical contracted task-completed gig workers from all gig workers who have participated in the task, count the remaining dispatch-related elements of the historical contracted task-completed gig workers in the current business structure after removing the confirmed dispatch elements to obtain a first pre-processed dispatch element, and count the development amplitudes of each dispatch-related element in the pre-processed dispatch element to obtain a pre-processed development amplitude value set; The first pre-processed dispatch element and the pre-processed development amplitude value set are processed and analyzed to obtain the adjusted dispatch element.

[0058] After obtaining the corrected dispatch information, this application analyzes the predicted dispatch results 1 and 2 based on this information. Within the extensive dispatch-related content, the inconsistent portions are extracted to form a corrected differential dispatch element, such as different recommended gig options or differences in the number of assigned tasks. Simultaneously, the consistent portions are extracted to form a confirmed dispatch element. This process clearly distinguishes the differences and consensus between the two prediction results, providing a foundation for subsequent processing.

[0059] For modified differential dispatch elements, we conduct in-depth research on each of them. Specifically, we calculate the difference in the development range of these elements in related attributes. For example, if the differential dispatch element involves skill level requirements for gig workers, we calculate the difference between different skill level requirements. By comprehensively analyzing these differences, we determine a development range value, which reflects the range of attribute changes in the modified differential dispatch element.

[0060] Filter out those gig workers who have completed historical contracted tasks from all gig workers who have participated in tasks. Then, for these gig workers who have completed historical contracted tasks, count the remaining dispatch-related elements after removing the confirmed dispatch element in the current business structure to obtain the first pre-processed dispatch element. For example, if the confirmed dispatch element is to recommend gig workers with skill A, then count other factors of these gig workers besides the dispatch factor related to skill A, such as work efficiency, task completion quality, etc. At the same time, count the development amplitude of each dispatch-related element in these first pre-processed dispatch elements to form a pre-processed development amplitude set, providing data support for subsequent screening and adjustment of dispatch elements.

[0061] Further processing and analysis is performed based on the first pre-processed dispatch element, pre-processed development amplitude set, and development amplitude interval value obtained previously. Through specific screening rules, the corresponding dispatch-related elements in the pre-processed development amplitude set that are within the development amplitude interval value are selected from the first pre-processed dispatch element to obtain the second pre-processed dispatch element. Then, an association relationship is established between the second pre-processed dispatch element and the corrected difference dispatch element to find the most closely associated corresponding dispatch-related element to obtain the third pre-processed dispatch element. Finally, the dispatch-related elements whose development amplitude and the development amplitude integration result of the confirmed dispatch element are in a stable demand state are screened out from the third pre-processed dispatch element. These elements are the final adjusted dispatch elements, which are used to optimize the dispatch plan.

[0062] Processing and analyzing the first pre-processed dispatch element and the pre-processed development amplitude value set to obtain an adjusted dispatch element specifically includes the following steps: Filter out the corresponding dispatch-related elements whose preprocessing development amplitude values ​​are within the development amplitude interval value from the first preprocessing dispatch element to obtain the second preprocessing dispatch element; Associating the second pre-processed dispatch element with the corrected difference dispatch element to obtain an association relationship; Filtering the closest corresponding dispatch-related element from the second pre-processed dispatch element to obtain a third pre-processed dispatch element; The dispatch-related elements whose corresponding development amplitudes are selected from the third pre-processed dispatch elements and whose development amplitudes are integrated with the confirmed dispatch elements and whose results belong to a stable demand state are obtained to obtain adjusted dispatch elements.

[0063] The first pre-processed dispatch element of this application contains relevant dispatch elements counted from the odd jobs completed in historical contracted tasks, and the pre-processed development amplitude set records the development amplitudes corresponding to these elements. The development amplitude interval value is the attribute change range previously calculated based on the modified difference dispatch element. Based on these data, dispatch-related elements whose development amplitudes fall within the development amplitude interval value are selected from the first pre-processed dispatch element to form the second pre-processed dispatch element. This step is to screen out dispatch elements that match the attribute change range of the modified difference dispatch element to narrow the scope of subsequent processing.

[0064] After obtaining the second pre-processed dispatch element, perform correlation analysis on it and the revised difference dispatch element. Determine the connection between them (e.g., correlation strength, matching degree, etc.) to form a correlation relationship. This helps understand the inherent connection between the second pre-processed dispatch element and the revised difference dispatch element, providing a basis for further screening.

[0065] Based on the established relationships, the dispatch-related elements most closely associated with the corrected discrepancy dispatch elements are identified from the second pre-processed dispatch elements to form the third pre-processed dispatch elements. The emphasis on "closest" relationships is to select the elements that are most representative and influential in dispatch adjustments, making subsequent dispatch plans more precise and effective.

[0066] Finally, the third pre-processed dispatch elements are analyzed, and the development amplitudes of these elements are integrated with the development amplitudes of the confirmed dispatch elements. The integrated results are then determined to determine whether they represent a stable demand state. If so, these dispatch-related elements are identified as adjusted dispatch elements. These adjusted dispatch elements are used to refine and optimize the dispatch plan, ensuring that dispatches better meet task requirements and achieve reasonable task allocation.

[0067] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0068] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. The integrated platform for electronic contract signing and order settlement in the gig economy system is characterized by: include: Acquisition module: obtains the current task release information and historical task data information of the task publisher; Training module: The historical task status information and the odd-job status information in the historical task data are trained to obtain the first task matching model; the historical task element trend feature change trend in the historical task data is trained to obtain the second task matching model; Prediction module: Input the task status information in the current task release information into task matching model 1 to obtain the dispatch prediction result 1, and input the task elements in the current task release information into task matching model 2 to obtain the dispatch prediction result 2; Processing module: Outputs pending dispatch information based on the comparison between dispatch prediction result 1 and dispatch prediction result 2. Based on the pending dispatch information, statistics are compiled on the overall trend of the development amplitude of all task demand-related elements in the historical task elements to obtain a historical task demand development trend set, and the current pending task demand trend to which dispatch prediction result 2 belongs is extracted. Contract signing and settlement module: The current task demand trend and historical task demand development trend set are processed and analyzed to obtain the dispatch confirmation result. Based on the dispatch confirmation result, an electronic contract is signed between the gig worker and the task publisher, and the order is settled according to the preset settlement plan when the task is completed.

2. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 1 is characterized in that: The task matching model 2 is obtained by training the historical task element trend feature change trend in the historical task data information, which specifically includes the following steps: Dividing the historical task data information into a first historical stage, a second historical stage, and a third historical stage; wherein the first historical stage includes at least two first task elements of the same type, the second historical stage includes at least two second task elements of the same type, and the third historical stage includes at least two third task elements of the same type; Extracting the change trend characteristics between at least two first task elements of the same type in the first historical stage to obtain a first change trend characteristic, extracting the change trend characteristics between at least two second task elements of the same type in the second historical stage to obtain a second change trend characteristic, and extracting the change trend characteristics between at least two third task elements of the same type in the third historical stage to obtain a third change trend characteristic; Counting the difference trend characteristics among the first change trend characteristic, the second change trend characteristic, and the third change trend characteristic to obtain a historical task element trend characteristic; A second task matching model is trained based on the trend characteristics of the historical task elements.

3. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 1 is characterized in that: Outputting the order information to be verified based on the comparison between the first order prediction result and the second order prediction result specifically includes the following steps: Compare the similarity between the dispatch prediction result 1 and the dispatch prediction result 2 to obtain the similarity; Comparing the similarity with a preset similarity threshold; If the similarity is greater than or equal to the similarity threshold, the dispatch prediction result 1 is used as the dispatch determination result. Based on the dispatch determination result, an electronic contract is signed between the gig worker and the task publisher, and when the task is completed, the order is settled according to the preset settlement plan; If the similarity is less than the preset similarity threshold, the dispatch information to be verified is output.

4. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 2 is characterized in that: The historical task requirement development trend set includes a first task requirement development trend, a second task requirement development trend, and a third task requirement development trend, and specifically includes the following steps: The development trend of the first task requirement is the development extent of at least two first task elements of the same type in the first historical stage; The second task requirement development trend is the development extent of at least two second task elements of the same type in the second historical stage; The development trend of the third task requirement is the development extent of at least two third task elements of the same type in the third historical stage.

5. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 4 is characterized in that: The dispatch determination result is obtained by processing and analyzing the current task demand trend and the historical task demand development trend set, which specifically includes the following steps: Analyze whether the current demand trend of the task to be tested, the development trend of the first task demand, the development trend of the second task demand, and the development trend of the third task demand are all in a stable demand state to obtain a dispatch confirmation result or dispatch correction information; Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a revised difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; and filter the revised difference dispatch elements to obtain an adjusted dispatch element. Among them, the adjustment dispatch element and the confirmation dispatch element are combined to obtain the dispatch confirmation result.

6. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 5 is characterized in that: Analyzing whether the current demand trend of the task to be tested, the development trend of the first task demand, the development trend of the second task demand, and the development trend of the third task demand are all in a stable demand state to obtain a dispatch determination result or dispatch correction information, specifically including the following steps: If the first task demand development trend, the second task demand development trend, and the third task demand development trend are all stable demand states, then determine whether the current task demand trend to be tested belongs to a stable demand state. If so, determine the predicted dispatch result 1 as the final dispatch optimization result and output the dispatch confirmation result. Otherwise, output the first demand trend continued judgment information; Based on the order confirmation result, an electronic contract signing process is carried out between the gig worker and the task publisher. After the contract is signed and the task is completed, the order is settled according to the preset settlement rules. Otherwise, a second demand situation continuation judgment information is output; The first demand situation continuation judgment information or the second demand situation continuation judgment information is processed and analyzed to obtain output dispatch correction information.

7. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 6 is characterized in that: Processing and analyzing the first demand situation continuation judgment information or the second demand situation continuation judgment information to obtain output dispatch correction information specifically includes the following steps: According to the first demand trend continuation information, determine whether the current demand trend of the task to be tested belongs to the demand growth state. If so, output the dispatch correction information. If not, determine whether the current demand trend of the task to be tested belongs to the demand decline state according to the second demand trend continuation information. If not, re-predict the predicted dispatch result. If so, output the dispatch correction information.

8. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 7 is characterized in that: Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a revised difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; and filter the revised difference dispatch elements to obtain an adjusted dispatch element. Specifically, the following steps are included: Extract the difference dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a corrected difference dispatch element; extract the same dispatch elements between the predicted dispatch result 1 and the predicted dispatch result 2 according to the dispatch correction information to obtain a confirmed dispatch element; The development amplitude difference between each difference dispatch element in the statistically corrected difference dispatch element is used to obtain the development amplitude interval value; Filter out historical contracted task-completed gig workers from all gig workers who have participated in the task, count the remaining dispatch-related elements of the historical contracted task-completed gig workers in the current business structure after removing the confirmed dispatch elements to obtain a first pre-processed dispatch element, and count the development amplitudes of each dispatch-related element in the pre-processed dispatch element to obtain a pre-processed development amplitude value set; The first pre-processed dispatch element and the pre-processed development amplitude value set are processed and analyzed to obtain the adjusted dispatch element.

9. The integrated electronic contract signing and order settlement platform in the gig economy system according to claim 8 is characterized in that: Processing and analyzing the first pre-processed dispatch element and the pre-processed development amplitude value set to obtain an adjusted dispatch element specifically includes the following steps: Filter out the corresponding dispatch-related elements whose preprocessing development amplitude values ​​are within the development amplitude interval value from the first preprocessing dispatch element to obtain the second preprocessing dispatch element; Associating the second pre-processed dispatch element with the corrected difference dispatch element to obtain an association relationship; Filtering the closest corresponding dispatch-related element from the second pre-processed dispatch element to obtain a third pre-processed dispatch element; The dispatch-related elements whose corresponding development amplitudes are selected from the third pre-processed dispatch elements and whose development amplitudes are integrated with the confirmed dispatch elements and whose results belong to a stable demand state are obtained to obtain adjusted dispatch elements.

Images