Dynamic configuration algorithm-based participation mobilization method, medium and equipment

Abstract

The invention relates to the technical field of information processing, in particular to a method, medium and equipment for mobilizing attendants based on a dynamic configuration algorithm, and the method comprises the following steps: obtaining mobilizing task information, and calculating the score of each mobilizing means according to the mobilizing task information; implementing participation mobilization according to the score of each mobilization means, and dynamically updating the score of each mobilization means to obtain the updated score of each mobilization means; implementing participation mobilization according to the updated scores of all mobilization means; repeating the steps S2 and S3 until the corresponding personnel give clear feedback information, and ending the mobilization; by means of the algorithm, all mobilization means are scored according to element information in multiple aspects such as space, time, personnel and relation of uninsured persons, the uninsured persons are mobilized according to scores, the scores are continuously updated according to quantitative information of the implementation effects of the mobilization means, and the mobilization efficiency and success rate are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly to a method, medium and device for mobilizing insurance participation based on a dynamic configuration algorithm. Background Art

[0002] In order to better promote the legal coverage of the residents' medical insurance for all people, it is necessary to mobilize the uninsured people based on the collected information. The traditional mobilization method is to push the information of the uninsured people to the corresponding community workers, and then the community workers conduct telephone mobilization or home mobilization one by one according to the personnel information.

[0003] However, the efficiency of this traditional mobilization method is relatively low, and the workload for community workers is extremely large. For example, there is a need to conduct multiple telephone mobilizations or home mobilizations for a single household, or there is no corresponding contact information for minors or newborns and it is necessary to contact the corresponding guardians. Therefore, a more convenient, fast and accurate mobilization method is needed to assist community workers in mobilizing insurance participation.

[0004] It should be noted that the information disclosed in this background art section is only intended to enhance the overall understanding of the present invention, and should not be regarded as an admission or any form of implication that this information constitutes prior art already known to those of ordinary skill in the art. Summary of the Invention

[0005] To solve the technical problems of the traditional mobilization method being cumbersome and inefficient, the present invention provides a method for mobilizing insurance participation based on a dynamic configuration algorithm. The method for mobilizing insurance participation based on a dynamic configuration algorithm includes the following steps: S1 Obtain mobilization task information, and calculate the scores of each mobilization means according to the mobilization task information; S2 Implement insurance participation mobilization according to the scores of each mobilization means, and dynamically update the scores of each mobilization means to obtain the updated scores of each mobilization means; S3 Implement insurance participation mobilization according to the updated scores of each mobilization means; S4 Repeat the steps of S2 and S3 until the corresponding person gives clear feedback information, then the mobilization ends.

[0006] Further, the calculation of the scores of each mobilization means includes the following steps: Obtain mobilization task information, and define the element scores of each element information in the mobilization task information; Define the weights of each mobilization means to obtain the initial weight matrix of each mobilization means; Calculate the scores of each mobilization means by combining the element scores and the initial weight matrix.

[0007] Furthermore, the element information at least includes spatial elements, temporal elements, relational elements, and personnel elements; Among them, the spatial elements at least include unit address, household register address, insurance participation address, and residential address; The temporal elements at least include the centralized payment period, the centralized insurance participation period, and the period of insurance suspension; The relational elements at least include household register relationship, family relationship, school relationship, and unit relationship; The personnel elements at least include whether it is a newborn, whether it is a minor, whether it is a student, whether it is an employed person, and whether it is an unemployed person.

[0008] Furthermore, each of the mobilization means at least includes SMS mobilization, digital grid workers, intelligent outbound calls, and manual visits.

[0009] Furthermore, the scoring of each mobilization means is expressed as:

[0010] Among them, is the score of each element, is the initial weight matrix, is the total number of element information.

[0011] Furthermore, the dynamic update of the scoring of each mobilization means includes the following steps: Record the quantized information of the effect of insurance participation mobilization, and obtain a feedback matrix according to the historical quantized information of the effect; Update the initial weight matrix according to the feedback matrix to obtain an updated weight matrix; Calculate the updated scoring of each mobilization means by combining the element score and the updated weight matrix.

[0012] Furthermore, the quantized information of the effect at least includes mobilization success rate score, mobilization time efficiency score, and mobilization cost score.

[0013] Furthermore, the updated weight matrix The update formula is expressed as:

[0014] Among them, is the initial weight matrix, is the learning rate, is the latest feedback matrix, is the historical feedback matrix, is the mask matrix.

[0015] Further, the present invention also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the method for mobilizing insurance participation based on the dynamic configuration algorithm described in any one of the above.

[0016] Further, the present invention also provides an electronic device, including at least one processor and a memory communicatively connected to the processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the processor to execute the method for mobilizing insurance participation based on the dynamic configuration algorithm described in any one of the above.

[0017] Based on the above, a method, medium, and device for mobilizing insurance participation based on a dynamic configuration algorithm provided by the present invention, compared with the prior art, score various mobilization means according to multi-faceted element information such as space, time, personnel, and relationships of uninsured persons through this algorithm, mobilize the uninsured persons according to the scores, and continuously update the scores according to the quantification information of the implementation effects of the mobilization means, thereby improving the mobilization efficiency and success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the following description of the positional relationship of the drawings, unless otherwise specified, it is based on the direction in which the components are shown in the drawings.

[0019] Figure 1 It is a schematic flowchart of a method for mobilizing insurance participation based on a dynamic configuration algorithm provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0021] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more. Additionally, the term "comprising" and any variations thereof mean "at least including".

[0022] To solve the above problems, the R & D personnel found that the traditional mobilization method lacks a dynamic decision-making mechanism and cannot automatically select the optimal mobilization means according to individual characteristics. Through analysis, it is found that the effects of different mobilization means are affected by multi-dimensional factors such as spatio-temporal elements and personnel attributes. Based on this, an attempt is made to construct a dynamic scoring model, quantify the task elements into computable parameters, and continuously optimize the mobilization strategy in combination with historical feedback data.

[0023] Therefore, the present application proposes an insured mobilization method based on a dynamic configuration algorithm, as Figure 1 shown, the insured mobilization method based on the dynamic configuration algorithm includes the following steps: S1 Obtain mobilization task information and calculate the scores of each mobilization means according to the mobilization task information; S2 Implement insured mobilization according to the scores of each mobilization means, and dynamically update the scores of each mobilization means to obtain the updated scores of each mobilization means; S3 Implement insured mobilization according to the updated scores of each mobilization means; S4 Repeat the steps of S2 and S3 until the corresponding person gives clear feedback information and then the mobilization ends.

[0024] By collecting the quantified information on the effect of insured mobilization and dynamically updating the scores of each mobilization means in real time, a closed-loop optimization mechanism is formed, and finally the process is automatically terminated when clear feedback is obtained, which can significantly improve the mobilization efficiency and success rate.

[0025] Among them, calculating the scores of each mobilization means includes the following steps: Obtain mobilization task information and define the element scores of each element information in the mobilization task information; Define the weights of each mobilization means to obtain the initial weight matrix of each mobilization means; Calculate the scores of each mobilization means by combining the element scores and the initial weight matrix.

[0026] The mobilization task information contains at least element information such as spatial elements, temporal elements, relational elements, and personnel elements. Specifically, it can be obtained by calling a data interface or reading a configuration file. Scores are assigned by defining the scoring criteria for each element information.

[0027] Among them, the spatial element mainly involves the matching and distance between addresses. The spatial element includes at least the unit address, household register address, insured address, and residential address.

[0028] Unit address: If the unit address matches other addresses (such as household register, place of residence), a higher score can be given; if there are multiple associated unit addresses, scores can be assigned according to distance or convenience.

[0029] Household register address: The matching degree between the household register and the insured address, whether in the same city or region, or whether it belongs to an area that is easy to contact.

[0030] Insured address: The stability of the insured address, whether it matches other information such as the unit address and the residential address.

[0031] Residential address: Whether the residential address has a high degree of connection or intersection with other addresses.

[0032] For example, the scoring criteria for a certain spatial element can be as shown in Table 1: Table 1

[0033] Among them, the temporal element is mainly based on the matching degree of the insurance participation period and the payment time. The temporal element includes at least the centralized payment period, the centralized insurance participation period, and the uninsured period.

[0034] Centralized payment period: The insurance participation situation of the insured during the centralized payment period. If the time is close to or has passed the payment period, a higher score is obtained.

[0035] Centralized insurance participation period: Associated with the centralized insurance participation period, evaluating the urgency of the insurance participation behavior.

[0036] Uninsured period: If the current is in the uninsured period, it means that urgent handling is required, and a higher score is given.

[0037] For example, the scoring criteria for a certain temporal element can be as shown in Table 2: Table 2

[0038] Among them, the relationship factors mainly focus on the social relationships related to individuals. The relationship factors at least include household registration relationship, family relationship, school relationship, and work unit relationship.

[0039] Household registration relationship: If the household registration relationship is stable or easy to access (such as in the same family or the same region), the score is relatively high.

[0040] Family relationship: The relationship among family members. If there is an intimate relationship (such as spouse, parents, etc.), the score is relatively high.

[0041] School relationship: If the insured is a student or related to the school (such as a student at school), points are assigned according to the educational background and needs.

[0042] Work unit relationship: If employed, the stability and contact information of the work unit can also affect the score.

[0043] For example, the scoring criteria for a certain relationship factor can be as shown in Table 3: Table 3

[0044] Among them, the personnel factors mainly consider the mobilization needs and urgency of the personnel types. The personnel factors at least include newborns, minors, students, employed persons, and unemployed persons.

[0045] Newborns: Newborns usually have relatively high demands in terms of medical care and insurance, and are given a relatively high score.

[0046] Minors: The needs of minors are related to their parents or guardians, so they also require a relatively high score.

[0047] Students: The mobilization of the student group may rely on family and school connections, and a certain score needs to be assigned.

[0048] Employed persons: Employed persons can usually be mobilized through their work units, so they are given a medium score.

[0049] Unemployed persons: Unemployed persons may rely more on external services during mobilization, and the score is relatively high.

[0050] For example, the scoring criteria for a certain personnel factor can be as shown in Table 4: Table 4

[0051] Each mobilization method at least includes different mobilization methods such as SMS mobilization, digital grid workers, intelligent outbound calls, and manual visits. Different mobilization methods have different cost weights. For example, the cost proportion of SMS mobilization is 1, the cost proportion of digital grid workers is 2, the cost proportion of intelligent outbound calls is 3, and the cost proportion of manual visits is 4.

[0052] Associate each mobilization means with each element information respectively to form a preset matrix, and assign weight values to form an initial weight matrix. Preferably, the weight values can be initialized through historical mobilization data or expert experience.

[0053] Calculate the scores of each mobilization means by combining the element scores and the initial weight matrix. The specific calculation method can adopt matrix multiplication operation, so that the final score of each mobilization means is a linear combination of the element scores and the corresponding weights. Multiply the element score matrix by the initial weight matrix to obtain the scores of each mobilization means, and select the mobilization means to implement the insurance participation mobilization according to the scores of each mobilization means. Then the scores of each mobilization means Are expressed as:

[0054] Where Is the score of each element, Is the initial weight matrix, Is the total number of element information.

[0055] Through the above technical solution, the present application realizes the accurate calculation of the scores of mobilization means. By defining the scores of each element information and the initial weights of each mobilization means, and combining the matrix calculation method, more accurate scores of mobilization means can be obtained. This scoring method takes into account the influence of multiple elements and mobilization means, improves the pertinence and effectiveness of the insurance participation mobilization. At the same time, due to the adoption of matrix calculation, the scoring process is more efficient, can quickly process a large amount of data, and provides a reliable basis for the subsequent mobilization work.

[0056] Furthermore, the dynamic update of the scores of each mobilization means includes the following steps: Record the quantitative information of the effect of the insurance participation mobilization, and obtain a feedback matrix according to the quantitative information of the effect of the historical insurance participation mobilization; Update the initial weight matrix according to the feedback matrix to obtain an updated weight matrix; Calculate the updated scores of each mobilization means by combining the element scores and the updated weight matrix.

[0057] The quantitative information of the effect at least includes the mobilization success rate score, the mobilization time efficiency score, and the mobilization cost score. Then

[0058]

[0059]

[0060] Among them, the "number of successful tasks" is counted as the number of successful tasks when the user gives feedback after being notified by the corresponding mobilization means, regardless of whether the user feedbacks to participate in insurance or not. If no user feedback is received, it is not counted as the number of successful tasks.

[0061] Respectively assign different weight ratios to the success rate score, mobilization time efficiency score, and mobilization cost score to calculate the mobilization means effectiveness score.

[0062] Since the recommended mobilization means obtained from the initial weight matrix for a single mobilization task is a single one, but there are multiple recommended mobilization means calculated from the initial weight matrices that combine different mobilization means based on different element scores in many historical mobilization tasks, it is necessary to combine the mobilization means effectiveness scores calculated from multiple historical mobilization tasks and convert the historical mobilization means effectiveness scores into a feedback matrix.

[0063] Combined with the feedback matrix, the initial weight matrix is updated using the Bayesian update method, and the updated weight matrix The update formula is expressed as: .

[0064] Among them, is the initial weight matrix, is the learning rate, is the latest feedback matrix, is the historical feedback matrix.

[0065] is the normalization term, which can limit the influence of the feedback matrix on the initial weight matrix, prevent the update amplitude from being too large, and can be adjusted according to the difference between the new and old feedbacks to ensure that the update is targeted.

[0066] Furthermore, in order to achieve local dynamic update, a mask matrix needs to be added and defined as:

[0067] Ensure that only the positions with values in participate in the update. Then the final updated weight matrix The update formula is expressed as:

[0068] Calculate the updated scores of each mobilization means by combining the element scores and the updated weight matrix, and implement the insurance mobilization again. Continuously loop through the mobilization implementation and weight matrix update steps until the corresponding person gives clear feedback information, then the mobilization ends. For example, if a mobilized person clearly states that they have already participated in insurance or are willing to participate in insurance, or are not willing to participate in insurance, then the mobilization ends.

[0069] To fully describe the technical solution of this application, this embodiment provides an example mobilization task: Calculate the scores of each element according to the element information in the mobilization task, as shown in Table 5 below: Table 5

[0070] Define the cost weights of each mobilization method, and generate a correlation weight matrix in combination with the above-mentioned element scores, as shown in Table 6 below: Table 6

[0071] Then the scores of each mobilization method Are expressed as:

[0072] That is, the score of the intelligent outbound call mobilization method is 13.7, the score of the SMS mobilization method is 16.0, the score of the digital grid member mobilization method is 16.9, and the score of the manual visit mobilization method is 14.3. Among them, the score of the digital grid member mobilization method is the highest, and it is recommended to use the digital grid member mobilization method to implement the insurance participation mobilization.

[0073] The quantified information on the historical insurance participation mobilization effect is shown in Table 7: Table 7

[0074] Given that the success rate score weight ratio is 0.5, the mobilization time efficiency score weight ratio is 0.3, and the mobilization cost score weight ratio is 0.2. Then the historical effect scores of each mobilization method: SMS mobilization (unit address): 0.5 * 0.3 + 0.3 * 0.0 + 0.2 * 0.0 = 0.15 Manual visit (household registration address): 0.5 * 0.7 + 0.3 * 0.25 + 0.2 * 0.5 = 0.525 Intelligent outbound call (active employees): 0.5 * 0.8 + 0.3 * 0.5 + 0.2 * 0.6 = 0.67 Digital grid member (minors): 0.5 * 0.9 + 0.3 * 0.75 + 0.2 * 0.4 = 0.765 Convert to a feedback matrix Is:

[0075] Assume the historical feedback matrix :

[0076] Use the mask matrix Screening the position, then

[0077] As described above, the initial weight matrix is

[0078] where the learning rate , then -[[-END]] :

[0079] Use the mask matrix to perform screening: *

[0080]

[0081] then :

[0082] then :

[0083] Then the updated weight matrix is:

[0084]

[0085] Combine the factor scores and the updated weight matrix to calculate the updated scores of each mobilization method, and implement the insurance participation mobilization again. Continuously loop through the mobilization implementation and weight matrix update steps until the corresponding person gives clear feedback information, then the mobilization ends. For example, if a mobilized person clearly states that they are already insured, willing to be insured, or not willing to be insured, then the mobilization ends.

[0086] In some preferred embodiments, the present invention also provides a computer-readable storage medium storing computer instructions, and when the computer is executed by a processor, it implements the above-mentioned insurance participation mobilization method based on a dynamic configuration algorithm.

[0087] In some preferred embodiments, the present invention also provides an electronic device, including at least one processor and a memory communicatively connected to the processor, wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the processor implements the above-mentioned insurance participation mobilization method based on a dynamic configuration algorithm.

[0088] In summary, a method, medium, and device for mobilizing insurance participation based on a dynamic configuration algorithm provided by the present invention, compared with the prior art, scores various mobilization means according to the information of multiple elements such as space, time, personnel, and relationships of uninsured personnel through this algorithm, mobilizes the uninsured personnel according to the scores, and continuously updates the scores according to the quantitative information of the implementation effects of the mobilization means, improving the mobilization efficiency and success rate.

[0089] Although terms such as spatial element, time element, relationship element, and personnel element are used more frequently in this article, the possibility of using other terms is not excluded. These terms are only used to more conveniently describe and explain the essence of the present invention; interpreting them as any additional limitation is contrary to the spirit of the present invention.

[0090] In addition, those skilled in the art should understand that although there are many problems in the prior art, each embodiment or technical solution of the present invention can be improved only in one or several aspects, and it is not necessary to solve all the technical problems listed in the prior art or the background art at the same time. Those skilled in the art should understand that the content not mentioned in a claim should not be regarded as a limitation to that claim.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for mobilizing insurance participation based on a dynamic configuration algorithm, characterized in that: It includes the following steps S1 Obtain mobilization task information, and calculate the scores of each mobilization means according to the mobilization task information; S2 Implement insurance participation mobilization according to the scores of each mobilization means, and dynamically update the scores of each mobilization means to obtain the updated scores of each mobilization means; S3 Implement insurance participation mobilization according to the updated scores of each mobilization means; S4 Repeat the steps of S2 and S3 until clear feedback information is given by the corresponding person, then the mobilization ends.

2. The method for mobilizing insurance participation based on a dynamic configuration algorithm according to claim 1, wherein: The calculation of the scores of each mobilization means includes the following steps: Obtain mobilization task information, and define the element scores of each element information in the mobilization task information; Define the weights of each mobilization means to obtain the initial weight matrix of each mobilization means; Calculate the scores of each mobilization means by combining the element scores and the initial weight matrix.

3. The method for mobilizing insurance participation based on the dynamic configuration algorithm according to claim 2, wherein: The element information at least includes spatial elements, time elements, relationship elements, and personnel elements; Among them, the spatial elements at least include unit address, household registration address, insurance participation address, and residential address; The time elements at least include the centralized payment period, the centralized insurance participation period, and the period of insurance suspension; The relationship elements at least include household registration relationship, family relationship, school relationship, and unit relationship; The personnel elements at least include whether it is a newborn, whether it is a minor, whether it is a student, whether it is an in-service person, and whether it is an unemployed person.

4. The method for mobilizing insurance participation based on a dynamic configuration algorithm according to claim 1, wherein: Each mobilization means at least includes SMS mobilization, digital grid clerks, intelligent outbound calls, and manual visits.

5. The method for mobilizing insurance participation based on a dynamic configuration algorithm according to claim 2, wherein: The scores of the respective mobilization means are expressed as: Among them, is the score for each element, is the initial weight matrix, is the total number of element information.

6. The method for mobilizing insurance participation based on a dynamic configuration algorithm according to claim 2, wherein: The dynamic update of the scores of each mobilization means includes the following steps: Record the quantized information on the effect of insurance participation mobilization, and obtain a feedback matrix according to the historical quantized information on the effect; Update the initial weight matrix according to the feedback matrix to obtain the updated weight matrix; Calculate the updated scores of each mobilization means by combining the element scores and the updated weight matrix.

7. The method for mobilizing insurance participation based on a dynamic configuration algorithm according to claim 6, characterized in that: The quantized information on the effect at least includes mobilization success rate score, mobilization time efficiency score, and mobilization cost score.

8. The method for mobilizing insurance participation based on a dynamic configuration algorithm according to claim 6, characterized in that: The updated weight matrix is expressed by the following update formula: Among them, is the initial weight matrix, is the learning rate, is the latest feedback matrix, is the historical feedback matrix, is the mask matrix.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer is executed by a processor, it implements the insurance participation mobilization method based on a dynamic configuration algorithm described in any one of claims 1-8.

10. An electronic device, characterized in that: It includes at least one processor and a memory communicatively connected to the processor, wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the processor executes the insurance participation mobilization method based on a dynamic configuration algorithm described in any one of claims 1-8.

Images