Location privacy protection and trust-based worker recruitment method and system

Abstract

The invention discloses a worker recruitment method based on location privacy protection and trust, which comprises the following steps: a worker recruitment side uploads recruitment information and worker information to a server in an encryption mode; the server calculates the distance between the worker position and the task point and encrypts and transmits the distance to the worker recruiter; the worker recruiter obtains a worker set through data reconstruction; obtaining a recruitment worker set in the obtained worker set; the worker recruiter updates worker weight calculation data; and the worker recruiter classifies worker weights and completes worker recruitment based on location privacy protection and trust. The invention also discloses a system for realizing the worker recruitment method based on location privacy protection and trust. According to the method, protection of worker position privacy and employment demand data can be realized, the reliability of worker recruitment and the feasibility of subsequent recruitment work are ensured, and the reliability, the accuracy and the safety are higher.

Description

Technical Field

[0001] The present invention belongs to the field of crowd intelligence perception, and specifically relates to a worker recruitment method and system based on location privacy protection and trust. Background Art

[0002] Crowd sensing uses the massive sensing devices carried by people to sense and utilize data, and realizes data processing in the physical world through data collection and sharing. In crowd sensing applications, workers' willingness to participate and the quality of submitted sensing data are key factors for the successful execution of tasks. As more sensing users participate in tasks, the contributed data becomes richer, but the risk of privacy leakage also increases. In order to motivate users to submit high-quality data and increase their willingness to participate, privacy protection becomes crucial.

[0003] During the interaction between the perception platform and workers, the worker recruitment problem becomes complex and challenging: protecting workers' privacy and ensuring data reliability are crucial to the successful execution of crowd perception tasks.

[0004] In terms of location privacy protection, there are currently two main methods: one is a location obfuscation-based scheme that protects the location of workers and task points by blurring the location information and hiding the area; the other is a perturbation-based scheme that distorts the location information by adding artificial noise, which is an extension of the traditional concept of differential privacy. However, when using these methods for location privacy protection, there may be risks of inaccurate task allocation, high overhead, and information leakage.

[0005] In response to data quality issues, some researchers have proposed a class of solutions called true value discovery methods, including the average method, weighted average method, median method, etc. These methods aim to make the calculated value as close to the true value as possible, thereby ensuring the reliability of the calculated value as much as possible. However, in the specific implementation process, the reliability and accuracy of such solutions cannot be guaranteed in extreme cases. Summary of the invention

[0006] One of the purposes of the present invention is to provide a worker recruitment method based on location privacy protection and trust with high reliability, good accuracy and good security.

[0007] A second objective of the present invention is to provide a system for implementing the worker recruitment method based on location privacy protection and trust.

[0008] The worker recruitment method based on location privacy protection and trust provided by the present invention comprises the following steps: S1. The worker recruiter uploads the recruitment information and the worker uploads his / her own information to the server in an encrypted manner; S2. The server calculates the distance between the worker's location and the task point based on the received data information, and transmits it to the worker recruiter in encrypted form; the worker recruiter obtains the worker set through data reconstruction; S3. From the obtained set of workers, the worker recruiter obtains a set of recruited workers based on a greedy algorithm; S4. The worker recruiter updates the worker weight calculation data based on the data information in the recruited worker set and the accuracy and timeliness of the worker data; S5. The worker recruiter classifies the workers by weight based on the updated worker weight calculation data to complete the worker recruitment based on location privacy protection and trust.

[0009] The step S1 specifically includes the following steps: The worker recruiter will send the location information of the task point and the recruitment range threshold R, and obtain two sets of secret shares through secret sharing and , and Shared with the first server ,Will Share to the second server ;in, The x-axis position information shared with the first server The secret share, Y-axis position information shared with the first server The secret share, is the secret share of the recruitment range threshold R shared with the first server, The x-axis position information shared with the second server The secret share, Y-axis position information shared with the second server The secret share, is the secret share of the recruitment range threshold R shared with the second server; The worker sends his position information at time t , two sets of secret shares are obtained through secret sharing and , and Shared with the first server ,Will Share to the second server ;in, The x-axis position information shared with the first server The secret share, Y-axis position information shared with the first server The secret share, The x-axis position information shared with the second server The secret share, Y-axis position information shared with the second server The secret share.

[0010] The step S2 specifically includes the following steps: server , c takes the value of 0 or 1. Based on the received data information, the sum of the squares of the distances between the worker and the task point is calculated. for ; server According to the calculated , calculate the first variable of each for and exchanged with each other; Randomly generated additional value for worker recruiters; server The first variable of the interaction exchange , reconstructed to obtain the second variable for ; The second variable Encryption generates the first key And send it to the first server , the second variable Encryption generates the second key And send it to the second server ; First Server and the second server , decrypt the encrypted data received by each party, and send the decrypted result to the worker recruiter; The worker recruiter will receive the data and reconstruct it to obtain the location information. The workers within the recruitment range threshold R and the corresponding data information constitute the worker set .

[0011] The step S3 comprises the following steps: In the obtained worker set, workers whose worker weight data is lower than a second set value are removed; If after removing workers whose weight data is lower than the second set value, the number of remaining workers is less than or equal to the number of workers to be recruited, then all remaining workers are recruited; If after removing the workers whose weight data is lower than the second set value, the number of remaining workers is greater than the number of workers to be recruited, the worker benefits of the remaining workers are calculated based on the distance between the remaining workers and the task point and the weight values ​​of the remaining workers, and the corresponding workers are recruited using a greedy algorithm.

[0012] The step S3 specifically includes the following steps: In the obtained worker set, workers whose worker weight data is lower than the second set value are removed to obtain the remaining worker set ; For the remaining workers Make a judgment: If the remaining workers If the number of workers in is less than or equal to the number of workers to be recruited, the remaining workers will be recruited directly. All workers in and constitute the set of recruited workers ; If the remaining workers The number of workers in is greater than the number of workers to be recruited, then the following formula is used to expand the remaining worker set The confidence upper bound for the i-th worker in : In the formula is the weight value; Aggregate for the remaining workers The weight of the i-th worker in; K is the number of workers to be recruited; The total number of times workers were recruited; Aggregate for the remaining workers The number of times the i-th worker is recruited; Based on the distance between the remaining workers and the task point and the confidence upper limit of the remaining workers, the remaining workers set is calculated using the following formula: The worker benefit of the i-th worker in : In the formula Gathering for the remaining workers The cost required for the i-th worker in; Based on the greedy algorithm, in the remaining worker set Recruiting workers benefits The top K workers constitute the set of recruited workers , and update the corresponding and .

[0013] The step S4 comprises the following steps: If there is no worker whose worker weight data is greater than or equal to the first set value in the set of recruited workers, return to step S1 to recruit workers for the next task point; In the set of recruited workers, if there is a worker whose worker weight data is greater than or equal to the first set value, the truth data and accuracy data corresponding to the worker are calculated based on the worker's weight data, and the worker weight calculation data of all workers in the set of recruited workers are updated in combination with the timeliness of the corresponding data.

[0014] The step S4 specifically comprises the following steps: If there is no worker whose worker weight data is greater than or equal to the first set value in the set of recruited workers, return to step S1 to recruit workers for the next task point; In the set of recruited workers, if there is a worker whose weight data is greater than or equal to the first set value, then based on the worker's weight data, the truth value of the task point at time t is calculated using the following formula: , initial time t=1, task point j=0: In the formula Data submitted for the iith worker; is a binary function, and if but ,otherwise , is the first set value; Calculate the accuracy of the data of the iith worker for ; The historical weight value of the ii-th worker up to time t is calculated using the following formula: : In the formula is the normalized weight value, and , is the weight value before normalization and , is the coefficient calculated for the weight value before normalization, is the weight value before normalization at time j, and n is the current time; is the weight value of worker ii at time tt; according to and , calculate the updated weight calculation data for the ii-th worker in the recruited worker set : In the formula To sum the weights; is the data accuracy threshold.

[0015] The worker recruiter in step S5 classifies the workers by weight according to the updated worker weight calculation data, which specifically includes the following steps: Use the following formula to update the weight value of the iith worker :According to the information obtained by the platform, workers whose known worker weight data is greater than or equal to the set value are Initialized to 1, the remaining workers Initialized to 0.5: In the formula is the set of tasks that the ii-th worker participates in at time t; is the number of tasks that the ii-th worker participates in at time t; According to the updated weight values ​​of each worker, the workers are classified by weight: If the weight of the mth worker is If the weight of the worker is greater than or equal to the first set value, the mth worker is classified as a worker whose weight data is greater than or equal to the set value, and this type of worker is recruited first in the next worker recruitment process; If the weight of the mth worker is If the weight of the worker is less than the second set value, the mth worker is classified as a worker whose weight data is lower than the set value, and such worker is recruited normally in the next worker recruitment process; The first setting value is greater than the second setting value.

[0016] The present invention also provides a system for implementing the worker recruitment method based on location privacy protection and trust, including a data upload module, a worker reconstruction module, a worker recruitment module, a data update module and a worker division module; the data upload module, the worker reconstruction module, the worker recruitment module, the data update module and the worker division module are connected in series in sequence; the data upload module is used for the worker recruiter to upload the recruitment information and the workers' own information to the server in an encrypted manner, and upload the data information to the worker reconstruction module; the worker reconstruction module is used for the server to calculate the distance between the worker's position and the task point based on the received data information, and encrypt and transmit it to the worker recruiter; the worker recruiter reconstructs the data A worker set is obtained, and the data information is uploaded to the worker recruitment module; the worker recruitment module is used to obtain a set of recruited workers based on a greedy algorithm in the obtained worker set according to the received data information, and upload the data information to the data update module; the data update module is used to update the worker weight calculation data based on the accuracy and timeliness of the worker data according to the received data information, and upload the data information to the worker classification module; the worker classification module is used to classify the workers by weight according to the received data information, and the worker recruiter calculates the data according to the updated worker weights, so as to complete the worker recruitment based on location privacy protection and trust.

[0017] Beneficial effects: The worker recruitment method and system based on location privacy protection and trust provided by the present invention adopts a lightweight encryption-secret sharing scheme and a trusted server to protect location privacy, thereby realizing the protection of worker information and task point location information; at the same time, the scheme of the present invention also realizes the reconstruction of the worker set, the updating of the worker weight data and the classification of the worker weight categories through the distance information between the worker location and the task point, thereby further improving the reliability and accuracy of the data; therefore, the present invention has higher reliability, better accuracy and better security. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The figure is a schematic diagram of the method flow of the present invention.

[0019] Figure 2 Schematic diagram of data accuracy comparison of comparative examples of the method of the present invention.

[0020] Figure 3 Schematic diagram of the worker recognition rate update change of the comparative example of the method of the present invention.

[0021] Figure 4 Schematic diagram of the functional modules of the system of the present invention. DETAILED DESCRIPTION

[0022] like Figure 1 The method flow diagram of the method of the present invention is shown as follows: The worker recruitment method based on location privacy protection and trust disclosed in the present invention comprises the following steps: S1. The worker recruiter uploads the recruitment information and the worker uploads his / her own information to the server in an encrypted manner; the specific steps include the following: The worker recruiter will send the location information of the task point and the recruitment range threshold R, and obtain two sets of secret shares through secret sharing and , and Shared with the first server ,Will Share to the second server ;in, The x-axis position information shared with the first server The secret share, Y-axis position information shared with the first server The secret share, is the secret share of the recruitment range threshold R shared with the first server, The x-axis position information shared with the second server The secret share, Y-axis position information shared with the second server The secret share, is the secret share of the recruitment range threshold R shared with the second server; The worker sends his position information at time t , two sets of secret shares are obtained through secret sharing and , and Shared with the first server ,Will Share to the second server ;in, The x-axis position information shared with the first server The secret share, Y-axis position information shared with the first server The secret share, The x-axis position information shared with the second server The secret share, Y-axis position information shared with the second server The secret share.

[0023] S2. The server calculates the distance between the worker's location and the task point based on the received data information, and transmits it to the worker recruiter in encrypted form; the worker recruiter obtains the worker set through data reconstruction; specifically, the steps are as follows: server , c takes the value of 0 or 1. Based on the received data information, the sum of the squares of the distances between the worker and the task point is calculated. for ; server According to the calculated , calculate the first variable of each for and exchanged with each other; Randomly generated additional value for worker recruiters; server The first variable of the interaction exchange , reconstructed to obtain the second variable for ; The second variable Encryption generates the first key And send it to the first server , the second variable Encryption generates the second key And send it to the second server ; First Server and the second server , decrypt the encrypted data received by each party, and send the decrypted result to the worker recruiter; The worker recruiter will receive the data and reconstruct it to obtain the location information. The workers within the recruitment range threshold R and the corresponding data information constitute the worker set .

[0024] S3. In the obtained worker set, the worker recruiter obtains a set of recruited workers based on a greedy algorithm; the steps include: In the obtained worker set, workers whose worker weight data is lower than a second set value are removed; If after removing workers whose weight data is lower than the second set value, the number of remaining workers is less than or equal to the number of workers to be recruited, then all remaining workers are recruited; If after removing the workers whose weight data is lower than the second set value, the number of remaining workers is greater than the number of workers to be recruited, the worker benefits of the remaining workers are calculated according to the distance between the remaining workers and the task point and the weight values ​​of the remaining workers, and the corresponding workers are recruited using the greedy algorithm; When implementing it, you can take the following steps: In the obtained worker set, workers whose worker weight data is lower than the second set value are removed to obtain the remaining worker set ; For the remaining workers Make a judgment: If the remaining workers If the number of workers in is less than or equal to the number of workers to be recruited, the remaining workers will be recruited directly. All workers in and constitute the set of recruited workers ; If the remaining workers The number of workers in is greater than the number of workers to be recruited, then the following formula is used to expand the remaining worker set The confidence upper bound for the i-th worker in : In the formula is the weight value; Aggregate for the remaining workers The weight of the i-th worker in; K is the number of workers to be recruited; The total number of times workers were recruited; Aggregate for the remaining workers The number of times the i-th worker is recruited; Based on the distance between the remaining workers and the task point and the confidence upper limit of the remaining workers, the remaining workers set is calculated using the following formula: The worker benefit of the i-th worker in : In the formula Gathering for the remaining workers The cost required for the i-th worker in; Based on the greedy algorithm, in the remaining worker set Recruiting workers benefits The top K workers constitute the set of recruited workers , and update the corresponding and .

[0025] S4. The worker recruiter updates the worker weight calculation data based on the data information in the recruited worker set and the accuracy and timeliness of the worker data; including the following steps: If there is no worker whose worker weight data is greater than or equal to the first set value in the set of recruited workers, return to step S1 to recruit workers for the next task point; In the set of recruited workers, if there is a worker whose worker weight data is greater than or equal to the first set value, the truth data and accuracy data corresponding to the worker are calculated based on the worker weight data, and the worker weight calculation data of all workers in the set of recruited workers are updated in combination with the timeliness of the corresponding data; When implementing it, you can take the following steps: If there is no worker whose worker weight data is greater than or equal to the first set value in the set of recruited workers, return to step S1 to recruit workers for the next task point; In the set of recruited workers, if there is a worker whose weight data is greater than or equal to the first set value, then based on the worker's weight data, the truth value of the task point at time t is calculated using the following formula: , initial time t=1, task point j=0: In the formula Data submitted for the iith worker; is a binary function, and if but ,otherwise , is the first set value; Calculate the accuracy of the data of the iith worker for ; The historical weight value of the ii-th worker up to time t is calculated using the following formula: : In the formula is the normalized weight value, and , is the weight value before normalization and , is the coefficient calculated for the weight value before normalization, is the weight value before normalization at time j, and n is the current time; is the weight value of worker ii at time tt; weight The significance of is to ensure that the worker weights at moments closer to the current moment account for a higher proportion, and the workers at moments farther from the current moment account for a lower proportion; according to and , calculate the updated weight calculation data for the ii-th worker in the recruited worker set : In the formula To sum the weights; is the data accuracy threshold.

[0026] S5. The worker recruiter classifies the workers by weight according to the updated worker weight calculation data to complete the worker recruitment based on location privacy protection and trust. The specific steps include: Use the following formula to update the weight value of the iith worker :According to the information obtained by the platform, workers whose known worker weight data is greater than or equal to the set value are Initialized to 1, the remaining workers Initialized to 0.5: In the formula is the set of tasks that the ii-th worker participates in at time t; is the number of tasks that the ii-th worker participates in at time t; According to the updated weight values ​​of each worker, the workers are classified by weight: If the weight of the mth worker is If the weight of the worker is greater than or equal to the first set value, the mth worker is classified as a worker whose weight data is greater than or equal to the set value, and this type of worker is recruited first in the next worker recruitment process; If the weight of the mth worker is If the weight of the worker is less than the second set value, the mth worker is classified as a worker whose weight data is lower than the set value, and such worker is recruited normally in the next worker recruitment process; The first setting value is greater than the second setting value.

[0027] The solution of the present invention is aimed at such situations. It adopts a lightweight encryption-secret sharing scheme and a trusted server to protect location privacy, thereby realizing the protection of real worker information and task point location information. At the same time, the solution of the present invention also realizes the reconstruction of the worker set through the distance information between the worker location and the task point, as well as the update of the worker weight data and the classification of the worker weight categories, further improving the reliability and accuracy of the data and ensuring the legitimate interests of normal workers.

[0028] The following is a collection of embodiments to further illustrate the method of the present invention: The object of this embodiment is the T-Driver dataset; the dataset contains the GPS tracks of 10,357 taxis in a certain city from February 2 to February 8, 2008.

[0029] Since the positions of workers in a crowd intelligence network environment are random and mobile, and there is currently no such public data set for worker recruitment; therefore, an embodiment of the present invention uses the taxi trajectories in the T-Driver data set to simulate the worker trajectories, uses the location data of the taxi as the location data of the worker, and sets the location information of the task point, so as to realize a simulation experiment of the worker recruitment process.

[0030] Then, the method of the present invention is compared with the prior art (Random method, CRH method) on the data set. The comparison results are as follows: Figure 2 and Figure 3 As shown; Among them, the Random method: At a task point determined at a certain time, the Random algorithm randomly selects workers within a range threshold. Since different randomly selected workers will affect the overall effect of the system of the present invention, the Random algorithm is repeatedly run independently for multiple times, and the average value of the perception data submitted by the workers in the iteration is used as the final truth value of the operation.

[0031] Similar to the Random method, for the overall effect of the system of the present invention, the CRH algorithm is repeatedly run independently for multiple times, and the average value of the truth values ​​calculated from all iterative operations is calculated as the final calculated truth value.

[0032] Figure 2 A schematic diagram comparing the truth value and the true value GTD error for multiple periodic task executions; Figure 2 It can be seen that the data error obtained by the method of the present invention is lower than that of the Random method and the CRH method, and has better robustness; Figure 3 A schematic diagram showing the changing trend of worker recognition rate updates for different numbers of worker sets; Figure 3It can be seen that with the increase of the operating cycle, the worker recognition rate of the method of the present invention shows an upward trend, indicating that while recruiting workers to perform tasks, the method of the present invention continuously identifies more workers whose weight data is greater than or equal to the set value.

[0033] In addition, the solution of the present invention is also applicable to scenarios such as air quality monitoring, network coverage map construction, noise level monitoring, traffic monitoring and street view collection.

[0034] like Figure 4 The figure shows a schematic diagram of the functional modules of the system of the present invention: the system disclosed in the present invention for implementing the worker recruitment method based on location privacy protection and trust comprises a data upload module, a worker reconstruction module, a worker recruitment module, a data update module and a worker division module; the data upload module, the worker reconstruction module, the worker recruitment module, the data update module and the worker division module are connected in series in sequence; the data upload module is used for the worker recruiter to upload the recruitment information and the worker's own information to the server in an encrypted manner, and to upload the data information to the worker reconstruction module; the worker reconstruction module is used for the server to calculate the distance between the worker's position and the task point according to the received data information, and encrypt and transmit it to the worker recruiter; the worker recruiter The recruiter obtains the worker set through data reconstruction and uploads the data information to the worker recruitment module; the worker recruitment module is used to obtain the set of recruited workers based on the greedy algorithm in the obtained worker set according to the received data information, and upload the data information to the data update module; the data update module is used to update the worker weight calculation data based on the accuracy and timeliness of the worker data according to the received data information, and upload the data information to the worker classification module; the worker classification module is used to classify the workers by weight according to the received data information, and the worker recruiter calculates the data according to the updated worker weights, so as to complete the worker recruitment based on location privacy protection and trust.

Claims

1. A worker recruitment method based on location privacy protection and trust, characterized in that: The steps include: S1. The worker recruiter uploads the recruitment information and the worker uploads his / her own information to the server in an encrypted manner; S2. The server calculates the distance between the worker's location and the task point based on the received data information, and transmits it to the worker recruiter in encrypted form; the worker recruiter obtains the worker set through data reconstruction; S3. From the obtained set of workers, the worker recruiter obtains a set of recruited workers based on a greedy algorithm; S4. The worker recruiter updates the worker weight calculation data based on the data information in the recruited worker set and the accuracy and timeliness of the worker data; S5. The worker recruiter classifies the workers by weight based on the updated worker weight calculation data to complete the worker recruitment based on location privacy protection and trust.

2. The worker recruitment method based on location privacy protection and trust according to claim 1, characterized in that: The step S1 specifically includes the following steps: The worker recruiter will send the location information of the task point and the recruitment range threshold R, and obtain two sets of secret shares through secret sharing and , and Shared with the first server ,Will Share to the second server ;in, The x-axis position information shared with the first server The secret share, Y-axis position information shared with the first server The secret share, is the secret share of the recruitment range threshold R shared with the first server, The x-axis position information shared with the second server The secret share, Y-axis position information shared with the second server The secret share, is the secret share of the recruitment range threshold R shared with the second server; The worker sends his position information at time t , two sets of secret shares are obtained through secret sharing and , and Shared with the first server ,Will Share to the second server ;in, The x-axis position information shared with the first server The secret share, Y-axis position information shared with the first server The secret share, The x-axis position information shared with the second server The secret share, Y-axis position information shared with the second server The secret share.

3. The worker recruitment method based on location privacy protection and trust according to claim 2, characterized in that: The step S2 specifically includes the following steps: server , c takes the value of 0 or 1. Based on the received data information, the sum of the squares of the distances between the worker and the task point is calculated. for ; server According to the calculated , calculate the first variable of each for and exchanged with each other; Randomly generated additional value for worker recruiters; server The first variable of the interaction exchange , reconstructed to obtain the second variable for ; The second variable Encryption generates the first key And send it to the first server , the second variable Encryption generates the second key And send it to the second server ; First Server and the second server , decrypt the encrypted data received by each party, and send the decrypted result to the worker recruiter; The worker recruiter will receive the data and reconstruct it to obtain the location information. The workers within the recruitment range threshold R and the corresponding data information constitute the worker set .

4. The worker recruitment method based on location privacy protection and trust according to claim 3, characterized in that: The step S3 comprises the following steps: In the obtained worker set, workers whose worker weight data is lower than a second set value are removed; If after removing workers whose weight data is lower than the second set value, the number of remaining workers is less than or equal to the number of workers to be recruited, then all remaining workers are recruited; If after removing the workers whose weight data is lower than the second set value, the number of remaining workers is greater than the number of workers to be recruited, the worker benefits of the remaining workers are calculated based on the distance between the remaining workers and the task point and the weight values ​​of the remaining workers, and the corresponding workers are recruited using a greedy algorithm.

5. The worker recruitment method based on location privacy protection and trust according to claim 4, characterized in that: The step S3 specifically includes the following steps: In the obtained worker set, workers whose worker weight data is lower than the second set value are removed to obtain the remaining worker set ; For the remaining workers Make a judgment: If the remaining workers If the number of workers in is less than or equal to the number of workers to be recruited, the remaining workers will be recruited directly. All workers in and constitute the set of recruited workers ; If the remaining workers The number of workers in is greater than the number of workers to be recruited, then the following formula is used to expand the remaining worker set The confidence upper bound for the i-th worker in : In the formula is the weight value; Set for the remaining workers The weight of the i-th worker in; K is the number of workers to be recruited; The total number of times workers were recruited; Set for the remaining workers The number of times the i-th worker is recruited; Based on the distance between the remaining workers and the task point and the confidence upper limit of the remaining workers, the remaining workers set is calculated using the following formula: The worker benefit of the i-th worker in : In the formula Gathering for the remaining workers The cost required for the i-th worker in; Based on the greedy algorithm, in the remaining worker set Recruiting workers benefits The top K workers constitute the set of recruited workers , and update the corresponding and .

6. The worker recruitment method based on location privacy protection and trust according to claim 5, characterized in that: The step S4 comprises the following steps: If there is no worker whose worker weight data is greater than or equal to the first set value in the set of recruited workers, return to step S1 to recruit workers for the next task point; In the set of recruited workers, if there is a worker whose worker weight data is greater than or equal to the first set value, the truth data and accuracy data corresponding to the worker are calculated based on the worker's weight data, and the worker weight calculation data of all workers in the set of recruited workers are updated in combination with the timeliness of the corresponding data.

7. The worker recruitment method based on location privacy protection and trust according to claim 6, characterized in that: The step S4 specifically comprises the following steps: If there is no worker whose worker weight data is greater than or equal to the first set value in the set of recruited workers, return to step S1 to recruit workers for the next task point; In the set of recruited workers, if there is a worker whose weight data is greater than or equal to the first set value, then based on the worker's weight data, the truth value of the task point at time t is calculated using the following formula: , initial time t=1, task point j=0: In the formula Data submitted for the iith worker; is a binary function, and if but ,otherwise , is the first set value; Calculate the accuracy of the data of the iith worker for ; The historical weight value of the ii-th worker up to time t is calculated using the following formula: : In the formula is the normalized weight value, and , is the weight value before normalization and , is the coefficient calculated for the weight value before normalization, is the weight value before normalization at time j, and n is the current time; is the weight value of worker ii at time tt; according to and , calculate the updated weight calculation data for the ii-th worker in the recruited worker set : In the formula To sum the weights; is the data accuracy threshold.

8. The worker recruitment method based on location privacy protection and trust according to claim 7, characterized in that: The worker recruiting party in step S5 divides the workers according to the updated worker quality data, which specifically includes the following steps: Use the following formula to update the weight value of the iith worker :According to the information obtained by the platform, workers whose known worker weight data is greater than or equal to the set value are Initialized to 1, the remaining workers Initialized to 0.5: In the formula is the set of tasks that the ii-th worker participates in at time t; is the number of tasks that the ii-th worker participates in at time t; According to the updated weight values ​​of each worker, the workers are classified by weight: If the weight of the mth worker is If the weight of the worker is greater than or equal to the first set value, the mth worker is classified as a worker whose weight data is greater than or equal to the set value, and this type of worker is recruited first in the next worker recruitment process; If the weight of the mth worker is If the weight of the worker is less than the second set value, the mth worker is classified as a worker whose weight data is lower than the set value, and such worker is recruited normally in the next worker recruitment process; The first setting value is greater than the second setting value.

9. A system for implementing the worker recruitment method based on location privacy protection and trust as described in any one of claims 1 to 8, characterized in that: It includes a data upload module, a worker reconstruction module, a worker recruitment module, a data update module and a worker division module; the data upload module, the worker reconstruction module, the worker recruitment module, the data update module and the worker division module are connected in series in sequence; the data upload module is used for the worker recruiter to upload the recruitment information and the worker's own information to the server in an encrypted manner, and upload the data information to the worker reconstruction module; the worker reconstruction module is used for the server to calculate the distance between the worker's position and the task point according to the received data information, and encrypt and transmit it to the worker recruiter; the worker recruiter obtains a set of workers through data reconstruction, and uploads the data information to the worker recruitment module; the worker recruitment module is used for the worker recruiter to obtain a set of recruited workers based on a greedy algorithm in the obtained set of workers according to the received data information, and upload the data information to the data update module; The data update module is used to update the worker weight calculation data based on the received data information and the data information in the recruited worker set, based on the accuracy and timeliness of the worker data, and upload the data information to the worker classification module; the worker classification module is used to classify the workers by weight based on the received data information and the worker recruiter according to the updated worker weight calculation data, so as to complete the worker recruitment based on location privacy protection and trust.

Images