Engineering employment matching service platform and method based on geographic position updating

Abstract

The invention discloses an engineering employment matching service platform and method based on geographic position updating, and the method comprises the steps: a worker terminal module is mainly used for obtaining the real-time data of a worker and an employer in real time, and pushing the matching information to the worker; the geographic position updating module is mainly used for dynamically correcting a positioning error through a multi-source fusion algorithm, triggering position updating once every 10 seconds, and predicting a worker activity range in real time based on worker activity parameters; the demand analysis and division module is mainly used for classifying demands of an employer into preset engineering type labels; and the dynamic matching module is mainly used for obtaining the worker with the highest matching degree based on the obtained structured parameters and obtaining the optimal path time consumption. The method has the advantages that the worker position and demand information are tracked in real time, the worker and project demands are intelligently matched, and the matching precision and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to big data processing, and in particular to an engineering employment matching service platform and method based on geographic location updates. Background Art

[0002] As the scale and technical requirements of engineering projects continue to increase, the demand for specialized skilled workers is becoming increasingly urgent. The construction industry, in fields such as structural construction, electrical installation, and rebar processing, requires a large number of workers with specific skills and experience. However, the supply of these workers is often in short supply due to regional differences and skill mismatches, especially given the increasing number of large-scale engineering projects and their increasing complexity.

[0003] Most current engineering labor matching service platforms rely on manual input and static data, resulting in delayed updates on worker location and status, which can easily lead to inaccurate or delayed matching. Furthermore, traditional systems often fail to account for workers' dynamic ranges and real-time changes in their geographic location, often relying solely on fixed information for matching, resulting in unnecessary idle time and resource waste. Furthermore, many systems fail to adequately differentiate between the urgency of demand requests, often employing a uniform matching logic that fails to prioritize urgent needs and hinders project progress. In contrast, matching platforms based on location updates integrate multi-source positioning data, correct for worker location errors in real time, and accurately predict worker ranges, enabling a more efficient and accurate matching process. Prioritizing based on the demander's urgency ensures timely responses to urgent needs, optimizing resource utilization and matching efficiency. Summary of the Invention

[0004] In order to improve the existing engineering labor matching service platform, this paper provides an engineering labor matching service platform and method based on geographic location updates. This method intelligently matches workers and project needs by tracking workers' location and demand information in real time, improving matching accuracy and efficiency. It also uses Kalman filtering and Brownian motion models, combined with the degree of urgency and the scope of workers' activities, to achieve refined matching and ensure a rapid response to engineering needs.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An engineering employment matching service platform based on geographic location updates, including:

[0007] Worker terminal module: The worker terminal module is mainly used to obtain the real-time geographic location data and job skill tags of workers and employers in real time, and push matching information to workers;

[0008] Geographic location update module: The geographic location update module integrates BDS, base station positioning and inertial navigation data. It is mainly used to dynamically correct positioning errors through a multi-source fusion algorithm, trigger a location update every 10 seconds, and predict the worker's activity range in real time based on the worker's activity parameters;

[0009] Demand analysis and classification module: The demand analysis and classification module is mainly used to classify the employer's needs into preset engineering work type labels and extract structured parameters such as skill level, working hours, and urgency;

[0010] Dynamic matching module: The dynamic matching module is mainly used to obtain the worker with the highest matching degree based on the obtained structured parameters, and calculate the optimal path time from the worker's current location to the employment location in combination with the Dijkstra path planning algorithm to obtain the optimal solution worker for the current employment demand.

[0011] Preferably, the worker terminal module specifically includes:

[0012] Multi-source positioning data acquisition unit: The multi-source positioning data acquisition unit integrates BDS, base station positioning and inertial navigation unit to obtain the real-time location of workers:

[0013] Work type skill label management unit: The work type skill label management unit uploads the worker's skill certificate data to the database and supports blockchain evidence verification;

[0014] Matching information push unit: The matching information push unit is mainly used to push the matching results to the worker end, and the worker accepts the order and confirms it, and updates the matching status and location data in real time.

[0015] Preferably, the geographic location updating module specifically includes:

[0016] Worker geographic location correction unit: This unit performs unified data source timestamp processing based on the acquired multi-source positioning data, fuses the unified multi-source data using the extended Kalman filter algorithm, and dynamically adjusts the data source weights based on the confidence level of each data source to correct the worker's geographic location.

[0017] Worker activity range prediction unit: The worker activity range prediction unit calculates the worker's activity radius based on the worker's real-time movement speed and movement direction obtained by the worker terminal module and the Brownian motion model calculation theory. The worker's activity range is obtained based on the activity radius prediction, and the deviation between the predicted and measured positions is compared every 5 minutes to dynamically correct the prediction result;

[0018] The worker's activity range is a circular range.

[0019] Preferably, the demand analysis and division module specifically includes:

[0020] Work type division unit: The work type division unit adopts a multi-level classification strategy based on the engineering field to divide the work types, and divides the technical levels based on the skills of the work types;

[0021] The first-level classification of the types of work includes major categories such as construction engineering, decoration engineering, and mechanical and electrical engineering. The second-level classification is further subdivided into types of work, such as electricians include strong current electricians and weak current electricians;

[0022] The technical level includes: junior, intermediate, senior or professional level certificate name;

[0023] Text processing unit: The text processing unit is mainly used to normalize the original text data of the project's employment requirements, identify and process the implicit expressions in the requirements description, and extract the workers required for the project.

[0024] Preferably, the dynamic matching module specifically includes:

[0025] Labor allocation unit: The labor allocation unit divides labor demands into urgent demands and ordinary demands based on the urgency of labor demands;

[0026] Worker matching unit: The worker matching unit matches urgent needs with general needs based on the types of needs of the labor allocation unit;

[0027] The urgent demand matching specifically includes: obtaining all workers who match the skills of the urgently needed jobs, obtaining their real-time geographic locations, and matching the workers who are the shortest distance from the project location;

[0028] The common requirements specifically include: obtaining the remaining time required for workers to arrive, predicting and obtaining the activity range of the workers within the remaining time based on the specific locations of all workers in the geographic location update module, and obtaining the worker with the shortest distance to the project location based on the activity range of all workers;

[0029] Path screening calculation unit: The path screening calculation unit is mainly implemented through the Dijkstra algorithm, taking the current position of the worker as the seven points and the project location as the target node, iteratively calculating to obtain the shortest time path and calculate the shortest time path.

[0030] Furthermore, a method for providing engineering employment matching services based on geographic location updates includes:

[0031] The worker terminal module collects BDS, base station positioning and inertial navigation data to obtain the worker's current geographic location, and uses the Kalman filter algorithm to correct the worker's geographic location;

[0032] Based on the workers' real-time movement speed and direction, the Brownian motion model is used to predict the workers' activity radius and range in the future time period;

[0033] Receive demand information from employers, perform text structured processing to extract job types, skill levels, duration, and urgency, and label the demand by job type and skill level;

[0034] The matching logic is divided based on the urgency of the demand, and workers are screened with different priorities. Urgent needs are screened based on real-time geographic location, while ordinary needs are finely matched based on the activity range of candidate workers within the remaining available time.

[0035] The matching results are pushed to the worker side, who then accepts the order, confirms it, and updates the matching status and location data in real time.

[0036] Compared with the prior art, the advantages of the present invention are:

[0037] By integrating BDS, base station positioning, and inertial navigation data, workers' locations are acquired in real time. A Kalman filter algorithm is used to correct positioning errors and ensure accuracy. Furthermore, a Brownian motion model combines workers' real-time movement speed and direction to predict their future range of movement, thereby improving the prediction of workers' accessibility. The demand information posted by the demander is extracted through a text processing unit, with key parameters such as job type, skill level, working hours, and urgency being extracted and structured and labeled. The matching module performs precise matching based on urgency and the worker's range of movement, ensuring that urgent needs are met first and that common needs are optimally matched within a reasonable timeframe. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of the system proposed by the present invention;

[0039] Figure 2 A schematic diagram of the method proposed in the present invention;

[0040] Figure 3 This is a schematic diagram of the worker terminal module proposed by the present invention;

[0041] Figure 4 This is a schematic diagram of the geographic location update module proposed in the present invention;

[0042] Figure 5 This is a schematic diagram of the demand analysis division module proposed in the present invention;

[0043] Figure 6 This is a schematic diagram of the dynamic matching module proposed by the present invention;

[0044] Figure 7 This is a diagram of the architecture of the electronic equipment in this solution;

[0045] Figure 8 This is a schematic diagram of the computer-readable storage medium structure in this solution. DETAILED DESCRIPTION

[0046] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0047] See Figure 1 As shown, a project employment matching service platform based on geographic location updates includes:

[0048] Worker terminal module: The worker terminal module is mainly used to obtain the real-time geographic location data and job skill tags of workers and employers in real time, and push matching information to workers;

[0049] Geographic location update module: The geographic location update module integrates BDS, base station positioning and inertial navigation data. It is mainly used to dynamically correct positioning errors through a multi-source fusion algorithm, trigger a location update every 10 seconds, and predict the worker's activity range in real time based on the worker's activity parameters;

[0050] Demand analysis and classification module: The demand analysis and classification module is mainly used to classify the employer's needs into preset engineering work type labels and extract structured parameters such as skill level, working hours, and urgency;

[0051] Dynamic matching module: The dynamic matching module is mainly used to obtain the worker with the highest matching degree based on the obtained structured parameters, and calculate the optimal path time from the worker's current location to the employment location in combination with the Dijkstra path planning algorithm to obtain the optimal solution worker for the current employment demand.

[0052] See Figure 2 As shown, a method for providing engineering employment matching services based on geographic location updates includes:

[0053] The worker terminal module collects BDS, base station positioning and inertial navigation data to obtain the worker's current geographic location, and uses the Kalman filter algorithm to correct the worker's geographic location;

[0054] Based on the workers' real-time movement speed and direction, the Brownian motion model is used to predict the workers' activity radius and range in the future time period;

[0055] Receive demand information from employers, perform text structured processing to extract job types, skill levels, duration, and urgency, and label the demand by job type and skill level;

[0056] The matching logic is divided based on the urgency of the demand, and workers are screened with different priorities. Urgent needs are screened based on real-time geographic location, while ordinary needs are finely matched based on the activity range of candidate workers within the remaining available time.

[0057] The matching results are pushed to the worker side, who then accepts the order, confirms it, and updates the matching status and location data in real time.

[0058] See Figure 3 As shown, the worker terminal module specifically includes:

[0059] Multi-source positioning data acquisition unit: The multi-source positioning data acquisition unit integrates BDS, base station positioning and inertial navigation unit to obtain the real-time location of workers:

[0060] Work type skill label management unit: The work type skill label management unit uploads the worker's skill certificate data to the database and supports blockchain evidence verification;

[0061] Matching information push unit: The matching information push unit is mainly used to push the matching results to the worker end, and the worker accepts the order and confirms it, and updates the matching status and location data in real time.

[0062] Specifically, the satellite pseudorange observation value is obtained through the Beidou satellite navigation system. The formula is:

[0063] ρ i =||x sat,i -x u ||+c·δt+∈ i

[0064] Among them, ρ i is the satellite pseudorange observation value, x sat,i is the satellite coordinate, x u is the user coordinate, δt is the clock difference, ∈ i is the error term;

[0065] When positioning through base stations, the distance difference between the worker and multiple base stations is calculated based on the cellular network signal strength or arrival time difference to solve the position;

[0066] When managing job skill tags, skill certificates are collected and entered. The data format includes: name, certificate number, issuing agency, validity period, and job classification.

[0067] Upload the collected data to the central database and blockchain for evidence storage to ensure that it cannot be tampered with and is traceable;

[0068] When transmitting the matching results, the matching data includes the type of work, skills, location, and time requirements.

[0069] See Figure 4 As shown, the geographic location update module specifically includes:

[0070] Worker geographic location correction unit: This unit performs unified data source timestamp processing based on the acquired multi-source positioning data, fuses the unified multi-source data using the extended Kalman filter algorithm, and dynamically adjusts the data source weights based on the confidence level of each data source to correct the worker's geographic location.

[0071] Worker activity range prediction unit: The worker activity range prediction unit calculates the worker's activity radius based on the worker's real-time movement speed and movement direction obtained by the worker terminal module and the Brownian motion model calculation theory. The worker's activity range is obtained based on the activity radius prediction, and the deviation between the predicted and measured positions is compared every 5 minutes to dynamically correct the prediction result;

[0072] The worker's activity range is a circular range.

[0073] Specifically, obtain location information and timestamps from different data sources (BDS, base station positioning, inertial navigation, etc.), perform unified timestamp processing on all data sources, and ensure that all data are integrated at the same time node;

[0074] Data fusion is performed through Kalman filtering to define the state vector and the observation vector

[0075]

[0076] in, is the worker's motion state vector, x(t) and y(t) are the position coordinate data, v x (t) and v y (t) is the velocity component;

[0077] Based on the workers' movement behavior, the system dynamic model is defined as follows:

[0078]

[0079] in, is the position coordinate data at time t+1, is the state transition matrix, is the process noise;

[0080] Observe the positioning data obtained from each data source and obtain the observation model. The formula is:

[0081]

[0082] in, is the observation vector, is the observation matrix, is the observation noise;

[0083] Update the state vector by calculating the Kalman gain;

[0084] Dynamically evaluate the confidence of each data source and adjust the Kalman filter weights based on the confidence level. The confidence level is calculated by comparing the error of each data source with its historical performance.

[0085] When predicting the worker's activity range, based on the Brownian motion model, the worker's activity range can be regarded as a random process, and the activity radius calculation formula is:

[0086]

[0087] Where r(t) is the activity radius, D(t) is the worker's diffusion coefficient, which is usually related to the worker's speed and direction, and Δt is the time step;

[0088] Based on the worker's speed and direction, predict its possible position in the future. Assuming that the worker moves at a constant speed, the predicted position is:

[0089]

[0090] in, To predict the location, The speed at which workers move;

[0091] Every 5 minutes, the predicted position is compared with the actual measured position, the deviation is calculated, and the diffusion coefficient D(t) is corrected according to the deviation to update the prediction of the activity range. If the deviation is large, the diffusion coefficient is adjusted to reflect a more accurate prediction.

[0092] See Figure 5 As shown in the figure, the demand analysis division module specifically includes:

[0093] Work type division unit: The work type division unit adopts a multi-level classification strategy based on the engineering field to divide the work types, and divides the technical levels based on the skills of the work types;

[0094] The first-level classification of the types of work includes major categories such as construction engineering, decoration engineering, and mechanical and electrical engineering. The second-level classification is further subdivided into types of work, such as electricians include strong current electricians and weak current electricians;

[0095] The technical level includes: junior, intermediate, senior or professional level certificate name;

[0096] Text processing unit: The text processing unit is mainly used to normalize the original text data of the project's employment requirements, identify and process the implicit expressions in the requirements description, and extract the workers required for the project.

[0097] Specifically, the first-level classification of work types mainly divides work types into major categories according to engineering fields (such as construction engineering, decoration engineering, mechanical and electrical engineering, etc.). This level of classification usually does not involve details and mainly provides a rough classification based on the type of project requirements;

[0098] The second-level classification of jobs provides a more detailed division of each major type of job. The second-level classification is further refined according to the different tasks and responsibilities of the job, for example:

[0099] Construction work may include: carpentry, plastering, reinforcement work, etc.;

[0100] Decoration work may include: painters, tilers, decorative designers, etc.;

[0101] Mechanical and electrical engineering may include: electricians (further subdivided into high-voltage electricians and low-voltage electricians), plumbers, etc.

[0102] When classifying technical levels, each type of work needs to be classified according to its skill requirements. Common technical levels include: junior, intermediate, senior or professional levels;

[0103] When the text processing unit identifies implicit expressions, many engineering requirements texts may contain implicit or ambiguous statements. For example, "We need someone with electrician experience" implicitly means "We need an electrician with at least some experience." For these implicit expressions, dependency parsing is used to identify the core information and conditional constraints within the sentence.

[0104] See Figure 6 As shown, the dynamic matching module specifically includes:

[0105] Labor allocation unit: The labor allocation unit divides labor demands into urgent demands and ordinary demands based on the urgency of labor demands;

[0106] Worker matching unit: The worker matching unit matches urgent needs with general needs based on the types of needs of the labor allocation unit;

[0107] The urgent demand matching specifically includes: obtaining all workers who match the skills of the urgently needed jobs, obtaining their real-time geographic locations, and matching the workers who are the shortest distance from the project location;

[0108] The common requirements specifically include: obtaining the remaining time required for workers to arrive, predicting and obtaining the activity range of the workers within the remaining time based on the specific locations of all workers in the geographic location update module, and obtaining the worker with the shortest distance to the project location based on the activity range of all workers;

[0109] Path screening calculation unit: The path screening calculation unit is mainly implemented through the Dijkstra algorithm, which takes the worker's current position as the starting point and the project location as the target node, iteratively calculates the shortest time path, and calculates the shortest time path.

[0110] Specifically, according to the urgency of the labor demand, the demand is divided into emergency demand and ordinary demand;

[0111] When matching urgent needs, obtain a list of workers whose job types and skill levels match the urgent needs, obtain workers who meet the required job types and skill requirements from the worker database, obtain the real-time geographic location of the matched workers, calculate the distance from each worker to the project location, and select the worker closest to the project location as the matching result;

[0112] During normal demand matching, the remaining time until a worker arrives is obtained, and the locations of all workers in the module are updated based on their geographic locations. Based on the worker's current location and the remaining time, the worker's future activity range is predicted. The activity range is usually assumed to be a circular area with a radius equal to the product of the worker's movement speed and the remaining time. Based on the activity ranges of all workers, the worker closest to the project location is selected.

[0113] In the above path screening calculation process, the Dijkstra algorithm is used to calculate the shortest time path from the worker's current location to the project location. The worker's current location and the project location are regarded as nodes of the graph, with the worker's current location as the starting point and the project location as the end point. Each edge in the graph represents a road or path, and the edge weight represents the travel time.

[0114] Initialize the distance matrix D, where D[i] represents the shortest time from the worker's current location to node i. Initialize the starting point D[starting point] = 0, and the initial values of other nodes are infinite. For each node i, select the path with the minimum time D[current node] and update the shortest path of the adjacent nodes. The formula is:

[0115] D[j]=min(D[j],D[i]+t ij )

[0116] Where D[j] is the current estimated shortest time from the starting point to node j, D[i] is the determined shortest time from the starting point to node i, and t ij is the path time from node i to node j;

[0117] When the shortest time paths of all nodes are calculated, the shortest time path from the worker's current location to the project location is obtained.

[0118] Furthermore, the method according to the embodiment of the present application can also be used with the aid of Figure 7 The electronic device architecture shown in FIG. Figure 7 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a project employment matching service platform and method based on geographic location updates provided in this application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 7 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 7 One or more components of an electronic device are shown.

[0119] Figure 8 This is a schematic diagram of the computer-readable storage medium structure provided by an embodiment of the present application. Figure 8 As shown, a computer-readable storage medium 600 according to one embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a project employment matching service platform and method based on geographic location updates according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0120] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0121] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0122] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A project employment matching service platform based on geographic location updates, characterized by: include: Worker terminal module: The worker terminal module is mainly used to obtain the real-time geographic location data and job skill tags of workers and employers in real time, and push matching information to workers; Geographic location update module: The geographic location update module integrates BDS, base station positioning and inertial navigation data. It is mainly used to dynamically correct positioning errors through a multi-source fusion algorithm, trigger a location update every 10 seconds, and predict the worker's activity range in real time based on the worker's activity parameters; Demand analysis and classification module: The demand analysis and classification module is mainly used to classify the employer's needs into preset engineering work type labels and extract structured parameters such as skill level, working hours, and urgency; Dynamic matching module: The dynamic matching module is mainly used to obtain the worker with the highest matching degree based on the obtained structured parameters, and calculate the optimal path time from the worker's current location to the employment location in combination with the Dijkstra path planning algorithm to obtain the optimal solution worker for the current employment demand.

2. The engineering employment matching service platform based on geographic location update according to claim 1, characterized in that: The worker terminal module specifically includes: Multi-source positioning data acquisition unit: The multi-source positioning data acquisition unit integrates BDS, base station positioning and inertial navigation unit to obtain the real-time location of workers: Work type skill label management unit: The work type skill label management unit uploads the worker's skill certificate data to the database and supports blockchain evidence verification; Matching information push unit: The matching information push unit is mainly used to push the matching results to the worker end, and the worker accepts the order and confirms it, and updates the matching status and location data in real time.

3. The engineering employment matching service platform based on geographic location update according to claim 1, characterized in that: The geographic location update module specifically includes: Worker geographic location correction unit: This unit performs unified data source timestamp processing based on the acquired multi-source positioning data, fuses the unified multi-source data using the extended Kalman filter algorithm, and dynamically adjusts the data source weights based on the confidence level of each data source to correct the worker's geographic location. Worker activity range prediction unit: The worker activity range prediction unit calculates the worker's activity radius based on the worker's real-time movement speed and movement direction obtained by the worker terminal module and the Brownian motion model calculation theory. The worker's activity range is obtained based on the activity radius prediction, and the deviation between the predicted and measured positions is compared every 5 minutes to dynamically correct the prediction result; The worker's activity range is a circular range.

4. The engineering employment matching service platform based on geographic location update according to claim 1, characterized in that: The demand analysis and division module specifically includes: Work type division unit: The work type division unit adopts a multi-level classification strategy based on the engineering field to divide the work types, and divides the technical levels based on the skills of the work types; The first-level classification of the types of work includes major categories such as construction engineering, decoration engineering, and mechanical and electrical engineering. The second-level classification is further subdivided into types of work, such as electricians include strong current electricians and weak current electricians; The technical level includes: junior, intermediate, senior or professional level certificate name; Text processing unit: The text processing unit is mainly used to normalize the original text data of the project's employment requirements, identify and process the implicit expressions in the requirements description, and extract the workers required for the project.

5. The engineering employment matching service platform based on geographic location update according to claim 1, characterized in that: The dynamic matching module specifically includes: Labor allocation unit: The labor allocation unit divides labor demands into urgent demands and ordinary demands based on the urgency of labor demands; Worker matching unit: The worker matching unit matches urgent needs with general needs based on the types of needs of the labor allocation unit; The urgent demand matching specifically includes: obtaining all workers who match the skills of the urgently needed jobs, obtaining their real-time geographic locations, and matching the workers who are the shortest distance from the project location; The common requirements specifically include: obtaining the remaining time required for workers to arrive, predicting and obtaining the activity range of the workers within the remaining time based on the specific locations of all workers in the geographic location update module, and obtaining the worker with the shortest distance to the project location based on the activity range of all workers; Path screening calculation unit: The path screening calculation unit is mainly implemented through the Dijkstra algorithm, taking the current position of the worker as the seven points and the project location as the target node, iteratively calculating to obtain the shortest time path and calculate the shortest time path.

6. A project employment matching service method based on geographic location update, characterized in that: include: The worker terminal module collects BDS, base station positioning and inertial navigation data to obtain the worker's current geographic location, and uses the Kalman filter algorithm to correct the worker's geographic location; Based on the workers' real-time movement speed and direction, the Brownian motion model is used to predict the workers' activity radius and range in the future time period; Receive demand information from employers, perform text structured processing to extract job types, skill levels, duration, and urgency, and label the demand by job type and skill level; The matching logic is divided based on the urgency of the demand, and workers are screened with different priorities. Urgent needs are screened based on real-time geographic location, while ordinary needs are finely matched based on the activity range of candidate workers within the remaining available time. The matching results are pushed to the worker side, who then accepts the order, confirms it, and updates the matching status and location data in real time.

7. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the engineering employment matching service method based on geographic location update as described in any one of claims 1-5.

8. A computer-readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the method for providing engineering employment matching services based on geographic location updates according to any one of claims 1 to 5 is implemented.

Images