Non-repayment blood donation recruitment method and system based on big data processing

Abstract

The invention discloses a big data processing-based non-repayment blood donation recruitment method and system, and the method comprises the steps: obtaining blood station blood type inventory data, clinical blood use prediction data and regional blood type distribution data, and generating target blood donation amount sets of different blood types; collecting historical blood donor data; on the basis of the target blood donation amount set and historical blood donor data, an adaptive value of each blood donor is calculated through a blood donor priority scoring model, and the adaptive values are used for screening a target blood donor group; screening out a target blood donation point set based on a traffic time minimization principle according to the residential address distribution information of the target blood donor group and the plurality of candidate blood donation points; and generating a blood donation recruitment scheme based on the target blood donation point set and the historical recruitment mode response data of the target blood donor group. According to the invention, the problems of low blood donor screening efficiency, unreasonable blood donation point layout, homogenization of recruitment modes and the like in a traditional system are effectively solved, and the intelligent level and resource matching precision of blood recruitment are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for recruiting voluntary blood donors based on big data processing. Background Technology

[0002] In recent years, the number of voluntary whole blood donors has been declining. Meanwhile, the aging population and the expansion of medical treatment have led to a continuous increase in clinical blood demand, exacerbating the blood supply-demand imbalance. Current blood resource management technologies, lacking scientifically quantifiable evaluation models, struggle to comprehensively consider factors such as donor blood type compatibility, donation habits, and response enthusiasm. This makes it difficult to accurately reach high-value donor groups, resulting in low utilization of recruitment resources and poor response efficiency. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this invention provides a method and system for recruiting voluntary blood donors based on big data processing.

[0004] In a first aspect, the present invention provides a method for recruiting voluntary blood donors based on big data processing, the method comprising: Obtain blood type inventory data from blood banks, clinical blood use prediction data, and regional blood type distribution data to generate target blood donation volumes for different blood types; Collect historical blood donor data, which includes blood type, number of blood donations, amount of blood donated per donation, time of most recent blood donation, residential address, historical response recruitment methods and corresponding response time limits; Based on the target blood donation volume set and the historical blood donor data, the fit value of each blood donor is calculated through a preset blood donor priority scoring model. The fit value is used to screen the target blood donor group. Based on the residential address distribution information of the target blood donor group and multiple candidate blood donation points, a set of target blood donation points was selected based on the principle of minimizing travel time; Based on the target blood donation site set and the historical recruitment response data of the target blood donor group, a blood donation recruitment plan is generated.

[0005] Preferably, the blood donor priority scoring model is represented as follows: , , , In the formula, For the blood donor's fit value, This is a weighting coefficient for the amount of blood donated in a single instance. For the compliance coefficient of blood donation interval, This is based on historical recruitment response rates. This is the decay factor based on the time elapsed since the most recent blood donation. This refers to the actual interval between blood donations. The minimum legally allowed blood donation interval, where k is the attenuation coefficient. Minimum blood donation cycle protection factor , , The weighting adjustment coefficient satisfies .

[0006] Preferably, the step of selecting a set of target blood donation points based on the residential address distribution information of the target blood donor group and multiple candidate blood donation points, and on the principle of minimizing travel time, includes: Obtain residential address distribution data and corresponding transportation mode preference data for the target blood donor group; Based on time cost models for different modes of transportation, the weighted comprehensive transportation time between each candidate blood donation point and each residential address is calculated separately. The objective function is to minimize the maximum weighted combined travel time for all target blood donors. The solution is obtained iteratively through a location optimization algorithm, and the final output is the set of blood donation points that minimizes the objective function value.

[0007] Preferably, the recruitment methods include SMS, in-app push notifications, email, private messages on social media platforms, and telephone communication.

[0008] Preferably, the step of generating a blood donation recruitment plan based on the target blood donation site set and the historical recruitment method response data of the target blood donor group includes: For each target blood donor, based on their associated target blood donation point and according to the target blood donor's historical recruitment response data, the expected response efficiency of the blood donor for different recruitment methods is calculated; Select at least one recruitment method with the highest expected response efficiency as the current preferred recruitment channel for the corresponding blood donor; For any target blood donor recruited through the current preferred recruitment channel, customized recruitment information is generated by integrating the necessary information of the corresponding blood donor and its associated target blood donation point information according to the preset recruitment information template. By integrating multiple recruitment information sources, a blood donation recruitment plan was obtained.

[0009] Secondly, the present invention also provides a blood donation recruitment system based on big data processing, the system comprising: The data acquisition and analysis module is used to acquire blood type inventory data from blood banks, clinical blood use prediction data, and regional blood type distribution data, and generate target blood donation sets for different blood types. The blood donor data collection module is used to collect historical blood donor data, which includes blood type, number of blood donations, amount of blood donated per donation, time of most recent blood donation, residential address, historical response recruitment methods and corresponding response time. The priority assessment module is used to calculate the fit value of each blood donor based on the target blood donation volume set and the historical blood donor data, using a preset blood donor priority scoring model. The fit value is used to screen the target blood donor group. The blood donation point optimization module is used to select a set of target blood donation points based on the distribution information of the residential addresses of the target blood donor group and multiple candidate blood donation points, and on the principle of minimizing travel time. The recruitment plan generation module is used to generate blood donation recruitment plans based on the target blood donation point set and the historical recruitment method response data of the target blood donor group.

[0010] Preferably, the blood donor priority scoring model is represented as follows: , , , In the formula, For the blood donor's fit value, This is a weighting coefficient for the amount of blood donated in a single instance. For the compliance coefficient of blood donation interval, This is based on historical recruitment response rates. This is the decay factor based on the time elapsed since the most recent blood donation. This refers to the actual interval between blood donations. The minimum legally allowed blood donation interval, where k is the attenuation coefficient. Minimum blood donation cycle protection factor , , The weighting adjustment coefficient satisfies .

[0011] Preferably, the blood donation point optimization module is further used for: Obtain residential address distribution data and corresponding transportation mode preference data for the target blood donor group; Based on time cost models for different modes of transportation, the weighted comprehensive transportation time between each candidate blood donation point and each residential address is calculated separately. The objective function is to minimize the maximum weighted combined travel time for all target blood donors. The solution is obtained iteratively through a location optimization algorithm, and the final output is the set of blood donation points that minimizes the objective function value.

[0012] Thirdly, the present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the method as described in the first aspect above and any possible implementation thereof.

[0013] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in the first aspect above and any possible implementation thereof.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1) This invention accurately generates the target blood donation volume by integrating blood bank blood type inventory, clinical blood use prediction, and regional blood type distribution data. It scientifically selects suitable groups by constructing a priority scoring model based on historical blood donor data, optimizes blood donation site selection based on the principle of minimizing travel time, and dynamically matches and optimizes recruitment channels and generates customized recruitment information based on historical blood donor response data. This achieves the technical effects of low error rate in target blood donation volume calculation, significantly improved blood donor response rate, greatly shortened average commuting time, and precise allocation of recruitment resources. At the same time, it adapts to different blood type needs through dynamic weight adjustment, strengthens privacy protection and emergency response capabilities, and upgrades blood recruitment from experience-driven to data-driven, effectively improving the efficiency of blood resource utilization and the level of intelligent management of blood banks.

[0015] 2) This invention quantifies the suitability value of blood donors by comprehensively considering the weight of single blood donation volume, compliance coefficient of blood donation interval, historical recruitment response rate, and time decay coefficient of most recent blood donation. It can prioritize the screening of high-value blood donors with a high number of blood donations, compliant intervals, and positive responses, thereby improving the recruitment response rate. It can also protect the health of blood donors through legal interval constraints and time decay mechanisms. Furthermore, it can adapt to different blood type inventory needs by dynamically adjusting the weight coefficients, thereby achieving a balance between efficient blood resource collection and protection of blood donor rights, significantly reducing blood station management costs and improving emergency blood use response efficiency.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of the present invention or the background art will be described below.

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0019] Figure 1 A flowchart illustrating a method for recruiting voluntary blood donors based on big data processing, provided as an embodiment of the present invention; Figure 2 This is a schematic diagram of a blood donation recruitment system based on big data processing, provided as an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] The current blood donation recruitment management system suffers from several problems, including a lack of scientific quantitative assessment in donor screening, failure to consider transportation costs in blood donation site selection, and homogenization of recruitment methods. These issues make it impossible to accurately match suitable blood donors and blood donation sites.

[0023] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for recruiting voluntary blood donors based on big data processing, provided as an embodiment of the present invention. Figure 1 As shown, the method includes: S100: Obtain blood type inventory data from blood banks, clinical blood use prediction data, and regional blood type distribution data to generate target blood donation sets for different blood types; Real-time blood type inventory data (including current inventory, safety stock threshold, and consumption trend over the past 30 days) is obtained from the blood bank's information system interface. An LSTM neural network is used to construct a clinical blood usage prediction model. Input parameters include historical blood usage data and blood bank department scheduling plans. The model outputs predicted blood demand for each blood type over the next 7 days. Based on regional demographic databases and historical blood donation data from the blood bank, and using regional blood type distribution data (ABO and Rh blood type ratio heatmaps divided by administrative regions), the above data is input into the objective function: Target blood donation volume = Predicted blood usage volume × 1.2 (safety factor) - Current inventory + Expected non-conforming products. This generates target blood donation volume sets for A, B, O, and AB blood types. For example, the target volume for O blood is 5000ml, and for A blood is 3800ml.

[0024] S200, collect historical blood donor data, which includes blood type, number of blood donations, amount of blood donated per donation, time of most recent blood donation, residential address, historical response recruitment methods and corresponding response time limits; In this embodiment, an ETL tool is used to incrementally synchronize the historical blood donor data of the past 5 years from the distributed databases of the blood bank management system, the regional health information platform, and the blood donor service APP in real time. The synchronization frequency is set to once per hour to ensure data timeliness. During the data cleaning process, regular expressions are used to validate the blood type field (e.g., using the regular expression ^[A|B|O|AB](\+|-)?$ to validate ABO and Rh blood type formats). For missing blood type data, a filling strategy based on the K-nearest neighbor algorithm is used (using the blood type distribution of 10 blood donors with neighboring residential addresses as the filling basis). For numerical data such as the number of blood donations and the amount of blood donated per donation, outliers are identified using the 3σ principle (e.g., a single blood donation exceeding 500ml is considered an anomaly and marked), and corrections are made using linear interpolation. The residential address field is converted to latitude and longitude coordinates in the WGS84 coordinate system by an address parsing engine. Simultaneously, city-level, district-level, and street-level administrative hierarchy information is extracted for spatial clustering analysis. For fuzzy addresses (such as "near XX Road"), semantic analysis combined with historical blood donation point distribution is used for probability matching (addresses with a matching probability below 70% trigger a manual review process). In historical recruitment response data, the response time of each channel is calculated using timestamp differences (e.g., the time difference between SMS sending time and appointment success time). Data spanning multiple days is standardized using a 24-hour format. Unresponsive records are marked as -1, and a dynamic response rate is calculated using a sliding window algorithm (window size equal to 3 recruitment times). Data storage uses an HBase distributed database, with the blood donor's ID number as the RowKey to create a primary key index, along with column-based secondary indexes (e.g., bitmap indexes by blood type, residential address latitude and longitude, and most recent blood donation time). Real-time verification during data writing is achieved through HBase's coprocessor mechanism (e.g., automatic comparison with the legal minimum blood donation interval) to ensure data integrity and consistency. In one possible embodiment, data involving personal privacy (such as residential address and contact information) is stored in encrypted form using an algorithm, and the encryption key is stored separately from the data in a separate database.

[0025] S300, based on the target blood donation volume set and the historical blood donor data, calculate the fit value of each blood donor through a preset blood donor priority scoring model, and the fit value is used to screen the target blood donor group; Preferably, the blood donor priority scoring model is represented as follows: , , , In the formula, For the blood donor's fit value, This is a weighting coefficient for the amount of blood donated in a single instance. For the compliance coefficient of blood donation interval, This is based on historical recruitment response rates. This is the decay factor based on the time elapsed since the most recent blood donation. This refers to the actual interval between blood donations. The minimum legally allowed blood donation interval, where k is the attenuation coefficient. Minimum blood donation cycle protection factor , , The weighting adjustment coefficient satisfies .

[0026] In this embodiment, a weighting coefficient for the amount of blood donated in a single instance is defined. The weighting of 200ml of blood donation is as follows: =0.3, the weight corresponding to 400ml of blood donation =0.7. Taking a blood donor as an example, their historical blood donation record includes 3 donations of 200ml each and 2 donations of 400ml each. ,in to This refers to the number of days between each blood donation and the previous one. =180 days, k=30 (attenuation coefficient), if the interval between a blood donor's most recent blood donation... =210 days (exceeding the legal minimum interval) =180 days), then ,like =150 days (insufficient interval), then =1.2 (A base coefficient is forcibly assigned to avoid directly excluding potential blood donors).

[0027] Let R be the response rate of the last three recruitments. If a blood donor responds twice in the last three recruitments, then R = 2 / 3 ≈ 0.67. = 0.414. Calculate. The time difference (181 days) between the current date (June 10, 2024) and the most recent blood donation date (e.g., December 10, 2023) is standardized to... =181 / 365≈0.495. (Setting) =0.5、 0.3 =0.2.

[0028] This indicates a weighted average of blood donation contribution and compliance, among which... Prioritize the amount of blood donated in a single donation (400ml has higher weighting, encouraging more contributions). Compliance intervals are calculated using an exponential function. A decay reward is applied, with the coefficient closer to 1 the closer the interval is to the legal minimum interval, to avoid excessive and frequent data collection; for intervals that are insufficient ( A fixed coefficient of 1.2 is assigned to it, which reflects both compliance requirements and the possibility of participation from potential blood donors. This represents the incentive term for historical response positivity. A logarithmic function is used to weaken the marginal effect of high response rates and avoid excessive bias towards blood donors with occasional high responses. This indicates the decay of the most recent blood donation period. The value decreases with increasing time since the most recent blood donation (e.g., after a 1-year interval). =1), when the interval is six months =0.5), penalizing recent blood donors with a negative coefficient aligns with the medical principle of "protecting the health of blood donors." Furthermore, a minimum blood donation cycle protection coefficient is used. Those who do not meet the blood donation cycle Certain blood donors were excluded from this blood donation recruitment plan to ensure that donors had sufficient recovery time, avoid health risks caused by frequent recruitment, and balance inventory needs with the rights and interests of blood donors.

[0029] This embodiment comprehensively considers the weight of a single blood donation, the compliance coefficient of the blood donation interval, the historical recruitment response rate, and the time decay coefficient of the most recent blood donation, and quantifies the suitability value of blood donors through a weighted calculation method. This can not only prioritize the screening of high-value blood donors with a high number of blood donations, compliant intervals, and positive responses, thereby improving the recruitment response rate, but also protect the health of blood donors through legal interval constraints and time decay mechanisms. Furthermore, it can dynamically adjust the weight coefficients to adapt to the different blood type inventory needs, achieving a balance between efficient blood resource collection and protection of blood donor rights, significantly reducing blood station management costs and improving emergency blood use response efficiency.

[0030] S400: Based on the residential address distribution information of the target blood donor group and multiple candidate blood donation points, a set of target blood donation points is selected based on the principle of minimizing travel time. Distributed web crawlers were used to parse residential address text from historical registration data of the target blood donor group. The addresses were then converted to latitude and longitude coordinates in the WGS84 coordinate system using the Baidu Maps API. For ambiguous addresses (such as "near XX community"), a Hidden Markov Model (HMM) was used in conjunction with a heatmap of regional blood donation point distribution for probability matching. Transportation mode preference data was extracted from historical interaction records of the blood bank app, and a probability distribution vector was constructed including five modes of transportation: walking, public transport, subway, driving, and cycling. A transportation network topology graph was constructed based on Dijkstra's algorithm, with candidate blood donation points and residential addresses as nodes, and the time cost of different transportation modes as edge weights. For each blood donor, the weighted comprehensive travel time to each candidate point was calculated (the weights being the transportation mode preference probabilities). The optimization objective function was defined as:

[0031] In the formula, Gathering for target blood donors, According to the mode of transportation, Let m be the probability that blood donor j prefers method m. To optimize the time it takes for blood donor j to reach a candidate blood donation point via method m, a non-dominated sorting genetic algorithm is used iteratively. The population size is set to 100, the crossover probability to 0.85, and the polynomial mutation probability to 0.1. The iteration terminates when the optimal solution has not been updated for 20 consecutive generations. Taking a certain region as an example, 5 target points are selected from 15 candidate blood donation points, reducing the maximum weighted travel time for 95% of blood donors from 42 minutes to 26 minutes. Specifically, the average commute time for drivers is reduced by 38%, and for public transport users by 27%, effectively improving participation convenience.

[0032] S500 generates a blood donation recruitment plan based on the target blood donation point set and the historical recruitment method response data of the target blood donor group.

[0033] Preferably, the step of generating a blood donation recruitment plan based on the target blood donation site set and the historical recruitment method response data of the target blood donor group includes: For each target blood donor, based on their associated target blood donation point and according to the target blood donor's historical recruitment response data, the expected response efficiency of the blood donor for different recruitment methods is calculated; Select at least one recruitment method with the highest expected response efficiency as the current preferred recruitment channel for the corresponding blood donor; For any target blood donor recruited through the current preferred recruitment channel, customized recruitment information is generated by integrating the necessary information of the corresponding blood donor and its associated target blood donation point information according to the preset recruitment information template. By integrating multiple recruitment information sources, a blood donation recruitment plan was obtained.

[0034] By analyzing the historical recruitment interaction records of target blood donors using natural language processing technology, a three-dimensional behavioral model was constructed, including channel preference, response speed, and information feedback patterns. Taking blood donor Wang as an example, his historical data shows that he received recruitment information 4 times in the past 6 months, including 2 phone calls, 1 SMS message, and no response to APP push notifications. Therefore, phone calls were determined to be his preferred recruitment channel.

[0035] A dynamic template engine is invoked to semantically fuse blood donor personal data with target blood donation center information. Taking Mr. Li (blood type A, residing in XX district) as an example, his associated target blood donation center is the XX Building temporary blood donation center (open from 9:00 AM to 4:00 PM on March 15, 2025), and his historical preferred donation method is SMS. Basic template: “

XX Blood Bank

[0036] In one possible implementation, a combined outreach model of "pre-notification by phone + confirmation via app push" is used for high-fit donors (e.g., the top 20% of donors). For those who do not respond to the initial outreach, a secondary recall mechanism based on survival analysis is initiated (e.g., sending a supplementary SMS message 30 minutes later if the call is missed). The number of recruits is dynamically allocated based on the real-time capacity of the target blood donation center (e.g., a center can currently accommodate 10 people / hour) to avoid queuing and overcrowding. The generated recruitment plan includes: a mapping table between target donors and preferred channels; a time-segmented recruitment information delivery plan; a forecast of the expected reception volume for each blood donation center; and an emergency response plan (e.g., automatically prioritizing the recruitment of donors with the corresponding blood type in case of sudden blood demand).

[0037] In one possible embodiment, the blood donation template also includes:

Changsha Blood Center

[0038] In one possible embodiment, the blood donation template also includes: "[Changsha Blood Center] Paying Tribute to Blood Donors! On June 14th, World Blood Donor Day, we sincerely invite you to return to the blood donation center and pass on the relay of life with your blood. Donating blood on that day will earn you an exclusive commemorative badge and a care package, and you'll also have the opportunity to participate in the '100 Blood Donation Stories' collection, letting your kindness be seen! We look forward to celebrating this glory of life with you."

[0039] In one possible embodiment, the blood donation template also includes: "[Changsha Blood Center] 520 is more than just sweet words; it's about expressing love with your blood! This romantic day, invite your loved one to the blood donation center. Couples who donate blood together can receive a customized 'Passionate Couple' souvenir (limited-edition roses + a certificate of love). Let your two heartbeats resonate with the same surge of blood, transforming love into the power to save lives. We await your contribution to writing the story of love!" In one possible embodiment, the blood donation template also includes: Dear Blood Donors: Thank you for your support! To express our gratitude for your long-term dedication and support of the voluntary blood donation cause, the Changsha Blood Center plans to hold a "Dedication to Love, Unity and Cooperation" regular blood donor social event on February 25, 2023 (Saturday). This event is free of charge, and we look forward to warmly welcoming you! Reply with "social event + your name" in the background to register.

[0040] This embodiment accurately generates the target blood donation volume by integrating blood bank blood type inventory, clinical blood use prediction, and regional blood type distribution data. It also constructs a priority scoring model based on historical blood donor data to scientifically screen suitable groups, optimizes blood donation site selection based on the principle of minimizing travel time, and dynamically matches and optimizes recruitment channels and generates customized recruitment information based on historical blood donor response data. This achieves the technical effects of low error rate in target blood donation volume calculation, significantly improved blood donor response rate, greatly shortened average commuting time, and precise allocation of recruitment resources. At the same time, it adapts to different blood type needs through dynamic weight adjustment, strengthens privacy protection and emergency response capabilities, and upgrades blood recruitment from experience-driven to data-driven, effectively improving the efficiency of blood resource utilization and the level of intelligent management of blood banks.

[0041] Preferably, the step of selecting a set of target blood donation points based on the residential address distribution information of the target blood donor group and multiple candidate blood donation points, and on the principle of minimizing travel time, includes: Obtain residential address distribution data and corresponding transportation mode preference data for the target blood donor group; Based on time cost models for different modes of transportation, the weighted comprehensive transportation time between each candidate blood donation point and each residential address is calculated separately. The objective function is to minimize the maximum weighted combined travel time for all target blood donors. The solution is obtained iteratively through a location optimization algorithm, and the final output is the set of blood donation points that minimizes the objective function value.

[0042] In this embodiment, the residential address text of the target blood donor group is parsed into spatial coordinate data. Natural language processing technology is used to perform semantic completion and probability matching on the fuzzy address. At the same time, the transportation mode preference features of blood donors are mined from the historical interaction data of the blood station to construct a behavioral model that includes multiple transportation mode selection tendencies. A time cost assessment model based on spatiotemporal network theory is constructed using multi-source data fusion. Differentiated time calculation logic is designed for different modes of transportation. The actual road distance and travel time of walking routes are obtained through map service interfaces. A dynamic time consumption prediction model is constructed by combining historical bus schedule data and real-time traffic information. Historical trajectory data from vehicle navigation systems is used to optimize the time loss assessment of driving routes. The time calculation for each mode of transportation incorporates real-time traffic conditions and road environment influencing factors. Furthermore, the weighted comprehensive travel time from all target blood donors to candidate blood donation points is used as the optimization objective. A heuristic optimization algorithm is used to iteratively screen the candidate blood donation point set. During the algorithm iteration process, the weight coefficients of each mode of transportation are dynamically adjusted to adapt to the travel characteristics of the blood donor group. By simulating the population evolution operation of the natural selection mechanism, the optimal solution that minimizes the maximum travel time is gradually approximated. Finally, a combination of target blood donation points that matches the residential distribution characteristics of blood donors is output. This combination can effectively balance the transportation convenience of blood donors in different areas and form an efficient blood donation service network covering the main residential areas of the target group.

[0043] Preferably, the recruitment methods include SMS, in-app push notifications, email, private messages on social media platforms, and telephone communication.

[0044] In summary, the method provided in this embodiment can achieve at least the following effects: 1) This invention accurately generates the target blood donation volume by integrating blood bank blood type inventory, clinical blood use prediction, and regional blood type distribution data. It scientifically selects suitable groups by constructing a priority scoring model based on historical blood donor data, optimizes blood donation site selection based on the principle of minimizing travel time, and dynamically matches and optimizes recruitment channels and generates customized recruitment information based on historical blood donor response data. This achieves the technical effects of low error rate in target blood donation volume calculation, significantly improved blood donor response rate, greatly shortened average commuting time, and precise allocation of recruitment resources. At the same time, it adapts to different blood type needs through dynamic weight adjustment, strengthens privacy protection and emergency response capabilities, and upgrades blood recruitment from experience-driven to data-driven, effectively improving the efficiency of blood resource utilization and the level of intelligent management of blood banks.

[0045] 2) This invention quantifies the suitability value of blood donors by comprehensively considering the weight of single blood donation volume, compliance coefficient of blood donation interval, historical recruitment response rate, and time decay coefficient of most recent blood donation. It can prioritize the screening of high-value blood donors with a high number of blood donations, compliant intervals, and positive responses, thereby improving the recruitment response rate. It can also protect the health of blood donors through legal interval constraints and time decay mechanisms. Furthermore, it can adapt to different blood type inventory needs by dynamically adjusting the weight coefficients, thereby achieving a balance between efficient blood resource collection and protection of blood donor rights, significantly reducing blood station management costs and improving emergency blood use response efficiency.

[0046] See Figure 2 In one embodiment, a blood donation recruitment system based on big data processing is also provided, the system comprising: The data acquisition and analysis module 100 is used to acquire blood type inventory data of blood banks, clinical blood use prediction data and regional blood type distribution data, and generate target blood donation volume sets for different blood types. The blood donor data collection module 200 is used to collect historical blood donor data, which includes blood type, number of blood donations, amount of blood donated at one time, time of most recent blood donation, residential address, historical response recruitment methods and corresponding response time limits; The priority assessment module 300 is used to calculate the fit value of each blood donor based on the target blood donation volume set and the historical blood donor data, using a preset blood donor priority scoring model. The fit value is used to screen the target blood donor group. The blood donation point optimization module 400 is used to select a set of target blood donation points based on the distribution information of the residential addresses of the target blood donor group and multiple candidate blood donation points, and on the principle of minimizing travel time. The recruitment plan generation module 500 is used to generate blood donation recruitment plans based on the target blood donation point set and the historical recruitment method response data of the target blood donor group.

[0047] Preferably, the blood donor priority scoring model is represented as follows: , , , In the formula, For the blood donor's fit value, This is a weighting coefficient for the amount of blood donated in a single instance. For the compliance coefficient of blood donation interval, This is based on historical recruitment response rates. This is the decay factor based on the time elapsed since the most recent blood donation. This refers to the actual interval between blood donations. The minimum legally allowed blood donation interval, where k is the attenuation coefficient. Minimum blood donation cycle protection factor , , The weighting adjustment coefficient satisfies .

[0048] Preferably, the blood donation point optimization module 400 is further used for: Obtain residential address distribution data and corresponding transportation mode preference data for the target blood donor group; Based on time cost models for different modes of transportation, the weighted comprehensive transportation time between each candidate blood donation point and each residential address is calculated separately. The objective function is to minimize the maximum weighted combined travel time for all target blood donors. The solution is obtained iteratively through a location optimization algorithm, and the final output is the set of blood donation points that minimizes the objective function value.

[0049] It is understood that the system provided in this embodiment has functions or includes modules that can be used to execute the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0050] The present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs a method as described in any of the above possible implementations.

[0051] The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0052] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0053] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will also readily understand that the various embodiments of the present invention have different focuses, and for the sake of convenience and brevity, the same or similar parts may not be repeated in different embodiments. Therefore, parts not described or not described in detail in one embodiment can be referred to in other embodiments.

Claims

1. A method for recruiting voluntary blood donors based on big data processing, characterized in that, The method includes: Obtain blood type inventory data from blood banks, clinical blood use prediction data, and regional blood type distribution data to generate target blood donation volumes for different blood types; Collect historical blood donor data, which includes blood type, number of blood donations, amount of blood donated per donation, time of most recent blood donation, residential address, historical response recruitment methods and corresponding response time limits; Based on the target blood donation volume set and the historical blood donor data, the fit value of each blood donor is calculated through a preset blood donor priority scoring model. The fit value is used to screen the target blood donor group. Based on the residential address distribution information of the target blood donor group and multiple candidate blood donation points, a set of target blood donation points was selected based on the principle of minimizing travel time; Based on the target blood donation site set and the historical recruitment response data of the target blood donor group, a blood donation recruitment plan is generated.

2. The method for recruiting voluntary blood donors based on big data processing according to claim 1, characterized in that, The donor priority scoring model is represented as follows: ， ， ， In the formula, For the blood donor's fit value, This is a weighting coefficient for the amount of blood donated in a single instance. For the compliance coefficient of blood donation interval, This is based on historical recruitment response rates. This is the decay factor based on the time elapsed since the most recent blood donation. This refers to the actual interval between blood donations. The minimum legally allowed blood donation interval, where k is the attenuation coefficient. Minimum blood donation cycle protection factor , , The weighting adjustment coefficient satisfies .

3. The method for recruiting voluntary blood donors based on big data processing according to claim 2, characterized in that, The process involves selecting a set of target blood donation points based on the residential address distribution information of the target blood donor group and multiple candidate blood donation points, using the principle of minimizing travel time. This set includes: Obtain residential address distribution data and corresponding transportation mode preference data for the target blood donor group; Based on time cost models for different modes of transportation, the weighted comprehensive transportation time between each candidate blood donation point and each residential address is calculated separately. The objective function is to minimize the maximum weighted combined travel time for all target blood donors. The solution is obtained iteratively through a location optimization algorithm, and the final output is the set of blood donation points that minimizes the objective function value.

4. The method for recruiting voluntary blood donors based on big data processing according to claim 1, characterized in that, The recruitment methods include SMS, in-app push notifications, email, private messages on social media platforms, and telephone communications.

5. The method for recruiting voluntary blood donors based on big data processing according to claim 1, characterized in that, The blood donation recruitment plan is generated based on the historical recruitment method response data of the target blood donation point set and the target blood donor group, including: For each target blood donor, based on their associated target blood donation point and according to the target blood donor's historical recruitment response data, the expected response efficiency of the blood donor for different recruitment methods is calculated; Select at least one recruitment method with the highest expected response efficiency as the current preferred recruitment channel for the corresponding blood donor; For any target blood donor recruited through the current preferred recruitment channel, customized recruitment information is generated by integrating the necessary information of the corresponding blood donor and its associated target blood donation point information according to the preset recruitment information template. By integrating multiple recruitment information sources, a blood donation recruitment plan was obtained.

6. A blood donation recruitment system based on big data processing, characterized in that, The system includes: The data acquisition and analysis module is used to acquire blood type inventory data from blood banks, clinical blood use prediction data, and regional blood type distribution data, and generate target blood donation sets for different blood types. The blood donor data collection module is used to collect historical blood donor data, which includes blood type, number of blood donations, amount of blood donated per donation, time of most recent blood donation, residential address, historical response recruitment methods and corresponding response time. The priority assessment module is used to calculate the fit value of each blood donor based on the target blood donation volume set and the historical blood donor data, using a preset blood donor priority scoring model. The fit value is used to screen the target blood donor group. The blood donation point optimization module is used to select a set of target blood donation points based on the distribution information of the residential addresses of the target blood donor group and multiple candidate blood donation points, and on the principle of minimizing travel time. The recruitment plan generation module is used to generate blood donation recruitment plans based on the target blood donation point set and the historical recruitment method response data of the target blood donor group.

7. The voluntary blood donation recruitment system based on big data processing according to claim 6, characterized in that, The donor priority scoring model is represented as follows: ， ， ， In the formula, For the blood donor's fit value, This is a weighting coefficient for the amount of blood donated in a single instance. For the compliance coefficient of blood donation interval, This is based on historical recruitment response rates. This is the decay factor based on the time elapsed since the most recent blood donation. This refers to the actual interval between blood donations. The minimum legally allowed blood donation interval, where k is the attenuation coefficient. Minimum blood donation cycle protection factor , , The weighting adjustment coefficient satisfies .

8. The voluntary blood donation recruitment system based on big data processing according to claim 6, characterized in that, The blood donation point optimization module is also used for: Obtain residential address distribution data and corresponding transportation mode preference data for the target blood donor group; Based on time cost models for different modes of transportation, the weighted comprehensive transportation time between each candidate blood donation point and each residential address is calculated separately. The objective function is to minimize the maximum weighted combined travel time for all target blood donors. The solution is obtained iteratively through a location optimization algorithm, and the final output is the set of blood donation points that minimizes the objective function value.

9. An electronic device, characterized in that, include: The electronic device includes a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the voluntary blood donation recruitment method based on big data processing as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform the blood donation recruitment method based on big data processing as described in any one of claims 1 to 5.

Images