A method, device, medium and equipment for acquiring target users

Abstract

The present invention is a method, device, medium and equipment for acquiring a target user, and relates to the field of data processing technology, including: acquiring a determination threshold of at least one relationship determination feature corresponding to a target relationship, acquiring target feature data of a candidate user within a preset historical time period, and when any record data in the target feature data fails to meet the determination threshold of the corresponding relationship determination feature, confirming that the candidate user is not the target user, and when all record data in the target feature data meet the determination threshold of the corresponding relationship determination feature, acquiring a target priority corresponding to the candidate user, and confirming the candidate user as the target user based on the target priority. It can be seen that feature data of different dimensions are analyzed, and target users are determined in different ways. At the same time, based on different feature information of the user and data related to the disease, comparison is performed, and the user's score is confirmed from different angles, so that the accuracy of acquiring the target user is high.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, medium and equipment for acquiring a target user. Background Art

[0002] At present, in the medical field, establishing a certain relationship can provide a guarantee for different users facing uncertain risks, reduce the pressure of users, reduce social contradictions and conflicts caused by risk events, and play an important role in maintaining social stability. However, not all users are qualified to establish relationships with organizations. Organizations should evaluate and screen users. Only users who meet the conditions are qualified to establish relationships. Traditional user screening often adopts manual review, which consumes a lot of manpower and resources, making the efficiency of screening target users slow and difficult to meet the growing review needs. With the rapid development of artificial intelligence technology, big data technology provides rich data support for screening target users. Deep mining and analysis of user feature information data to screen target users has become a popular research direction. The method of screening target users in the existing technology is to obtain the user's application materials, automatically read the key information in the application materials through scanning and recognition technology, match the key information with the information in the database, and thus determine the target user. This method does not analyze the feature data from different dimensions, which reduces the efficiency of screening target users. When scoring users, it does not consider comparing the different feature information of users with disease-related data, which makes the accuracy of obtaining target users low. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is a method for acquiring target users, and the method comprises the following steps:

[0004] A determination threshold of at least one relationship determination feature corresponding to a target relationship is obtained, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease, and the relationship determination feature is used to determine whether an association relationship can be established between a candidate user and a target object.

[0005] Obtain target feature data of the candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating the target disease obtained from the initial feature data, each record data includes a numerical value corresponding to the relationship determination feature, and the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user seeks medical treatment due to physical abnormalities within the preset historical time period.

[0006] When there is any record data in the target feature data that fails to meet the determination threshold of the corresponding relationship determination feature, it is determined that the candidate user is not the target user.

[0007] When all record data in the target feature data meet the judgment threshold of the corresponding relationship judgment feature, the target priority corresponding to the candidate user is obtained, wherein the target priority is a value obtained by processing the numerical value corresponding to the target feature obtained from the initial feature data and is used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened relationship judgment feature.

[0008] When the target priority is greater than the specified priority, it is determined that the candidate user is not the target user, wherein the specified priority is the cost required for the candidate user to establish a target relationship with the target object.

[0009] When the target priority is not greater than the specified priority, the candidate user is confirmed as the target user.

[0010] The present invention also provides a device for acquiring a target user, the device comprising:

[0011] A designated feature information acquisition module is used to obtain a determination threshold of at least one relationship determination feature corresponding to a target relationship, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease, and the relationship determination feature is used to determine whether an association relationship can be established between a candidate user and a target object.

[0012] A target feature data acquisition module is used to obtain the target feature data of a candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating a target disease obtained from the initial feature data, each record data includes a numerical value corresponding to a relationship determination feature, and the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user has a physical abnormality and seeks medical treatment within the preset historical time period.

[0013] The target determination module is used to confirm that the candidate user is not the target user when there is any record data in the target feature data that cannot meet the determination threshold of the corresponding relationship determination feature.

[0014] A target priority acquisition module is used to obtain the target priority corresponding to the candidate user when all record data in the target feature data meet the judgment threshold of the corresponding relationship judgment feature, wherein the target priority is a value obtained by processing the value corresponding to the target feature obtained from the initial feature data and used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened out relationship judgment feature.

[0015] The first target user acquisition module is used to confirm that the candidate user is not the target user when the target priority is greater than the specified priority, wherein the specified priority is the cost required for the candidate user to establish a target relationship with the target object.

[0016] The second target user acquisition module is used to confirm the candidate user as the target user when the target priority is not greater than the specified priority.

[0017] The present invention also provides a non-transitory computer-readable storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned method of acquiring a target user.

[0018] The present invention also provides an electronic device, comprising a processor and the above-mentioned non-transitory computer-readable storage medium.

[0019] The present invention has at least the following beneficial effects: obtaining a determination threshold of at least one relationship determination feature corresponding to a target relationship, obtaining target feature data of a candidate user within a preset historical time period, confirming that the candidate user is not a target user when any record data in the target feature data fails to meet the determination threshold of the corresponding relationship determination feature, obtaining a target priority corresponding to the candidate user when all record data in the target feature data meet the determination threshold of the corresponding relationship determination feature, confirming that the candidate user is not a target user when the target priority is greater than a specified priority, and confirming that the candidate user is a target user when the target priority is not greater than a specified priority. It can be seen that by analyzing feature data of different dimensions and determining target users in different ways, the efficiency of screening target users is improved, and when scoring users, comparison is made based on different feature information of users and data related to diseases, and the scores of users are confirmed from different angles, so that the accuracy of obtaining target users is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of a method for acquiring a target user provided in the first embodiment of the present invention;

[0022] Figure 2 This is a flow chart of S400 provided in the first embodiment of the present invention;

[0023] Figure 3 This is a flowchart of S1 provided in Embodiment 1 of the present invention;

[0024] Figure 4 This is a flow chart of S14 provided in the first embodiment of the present invention;

[0025] Figure 5 A flowchart of S2 provided in Embodiment 1 of the present invention;

[0026] Figure 6 A schematic diagram of the structure of a device for acquiring a target user provided in Embodiment 2 of the present invention;

[0027] Figure 7 A schematic diagram of the structure of a target priority acquisition module 400 provided in Embodiment 2 of the present invention;

[0028] Figure 8 A schematic diagram of the structure of a first execution module 1 provided in Embodiment 2 of the present invention;

[0029] Fig. 9 A schematic diagram of the structure of the fourth acquisition module 14 provided in the second embodiment of the present invention;

[0030] Fig.10 This is a schematic diagram of the structure of the second execution module 2 provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] This embodiment provides a method for acquiring a target user, the method comprising the following steps: Figure 1 As shown:

[0035] S100, obtaining a determination threshold of at least one relationship determination feature corresponding to a target relationship, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease.

[0036] Specifically, the target object is an organization that can provide protection for the user when the user's physical condition is abnormal.

[0037] Specifically, the target disease is the disease corresponding to the target relationship.

[0038] Specifically, the relationship determination features are used to determine whether an association relationship can be established between the candidate user and the target object, for example: gender, age, number of diagnoses, disease name, number of hospitalizations and the number of days of hospitalization corresponding to each hospitalization, the usage of various types of drugs, the type of lifestyle intervention, the cost required to treat the disease, etc. The relationship determination features can be understood as: when the target disease is diabetes, the age is set within a certain range, the gender is set to male or female, the usage of drugs for diabetes is set within a certain range, the number of days of hospitalization due to diabetes attacks is set within a certain range, and so on.

[0039] Specifically, those skilled in the art know that the determination threshold can be selected according to actual needs, all of which fall within the protection scope of the present invention and will not be described in detail here.

[0040] Specifically, the candidate user is a user who wants to establish a target relationship with the target object.

[0041] S200, obtaining target feature data of the candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating the target disease obtained from the initial feature data, and each record data includes a numerical value corresponding to the relationship determination feature.

[0042] Specifically, the end time of the preset historical time period is the current time, and the time span of the preset historical time period is consistent with the relationship establishment time span corresponding to the target relationship.

[0043] Specifically, the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user has physical abnormalities and seeks medical treatment within the preset historical time period, wherein each disease corresponds to a group of record data, each group of record data includes several record data, and each record data includes a numerical value corresponding to the relationship judgment feature.

[0044] S300: When there is any record data in the target feature data that fails to meet the determination threshold of the corresponding relationship determination feature, it is determined that the candidate user is not the target user.

[0045] Specifically, for example: when the target disease is diabetes, there will be several feature data related to the treatment of diabetes in the target feature data. In order to establish the association relationship of the target disease, it is necessary to meet the conditions that the number of diagnoses does not exceed 5 times, the insulin dosage does not exceed 50 units, and the metformin dosage does not exceed 100 units. If a certain record data in the target feature data, such as the insulin dosage is 80, it means that this candidate user is not the target user.

[0046] S400, when all record data in the target feature data meet the judgment threshold of the corresponding relationship judgment feature, obtain the target priority corresponding to the candidate user, wherein the target priority is a value obtained by processing the value corresponding to the target feature obtained from the initial feature data and used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened relationship judgment feature.

[0047] Specifically, in S400, the target priority is obtained through the following steps: Figure 2 As shown:

[0048] S1, obtaining a target score corresponding to the candidate user, wherein the target score is a value obtained by adding values ​​obtained by normalizing values ​​corresponding to target features corresponding to the candidate user.

[0049] Specifically, S1 also includes the following steps: Figure 3 As shown:

[0050] S11, obtaining a first score according to the initial feature data, wherein the first score is a value obtained by normalizing the number of hospitalizations recorded in the initial feature data, that is, obtaining a first score A1 according to the target feature data, wherein A1 meets the following conditions:

[0051] A1=1 / e -a , a is the number of hospitalizations in a preset historical time period obtained based on the initial feature data corresponding to the candidate user.

[0052] S12, obtaining a second score based on the initial feature data, wherein the second score is a value obtained based on the multiple disease names recorded in the initial feature data and the cost required to treat the diseases corresponding to the disease names, that is, obtaining a second score A2 based on the initial feature data, wherein A2 meets the following conditions:

[0053] A2=P 0 +∑ ni=1 β i ×(B i -B min ) / (B max -B min ), B i is the target cost corresponding to the i-th key disease, i ranges from 1 to n, n is the number of key diseases, B min is the minimum target cost among the target costs corresponding to n key diseases, B max is the maximum target cost among the target costs corresponding to n key diseases, β i is the target probability corresponding to the i-th key disease, P 0 is the probability of the 1st to the nth key diseases occurring simultaneously.

[0054] Specifically, n≥2, where when n=1, P 0 =0.

[0055] Specifically, the key disease is a disease recorded in the initial feature data that the candidate user was diagnosed with within a preset historical time period.

[0056] Specifically, the target cost is the cost required for treating the key disease for the candidate user recorded in the initial feature data within a preset historical time period.

[0057] Specifically, the target probability is the ratio between the number of sample users suffering from the key disease and the total number of sample users, wherein the sample users are patients who have been treated within a preset historical time period.

[0058] Specifically, P 0 is obtained in the same way as the target probability based on the number of sample users who suffer from n key diseases at the same time.

[0059] S13, based on preset rules, obtaining a third score, wherein the preset rules are scoring rules corresponding to different age groups based on gender settings, and the third score is a score obtained by comparing the gender and age corresponding to the candidate user with the gender and age group in the preset rules.

[0060] Specifically, the value range of the score corresponding to each age group in the preset rule is 0 to 1, wherein the sum of the scores corresponding to all age groups in the preset rule is 1.

[0061] Furthermore, those skilled in the art know that preset rules can be set according to actual needs, which all fall within the protection scope of the present invention and will not be described in detail herein.

[0062] S14, obtaining a first candidate score according to the initial feature data, wherein the first candidate score is a value obtained based on the first score, the second score, the third score, and the lifestyle intervention type recorded in the initial feature data.

[0063] Specifically, S14 also includes the following steps: Figure 4 As shown:

[0064] S141, when the target exercise amount is not greater than the average exercise amount, the first candidate score is the average of the first score, the second score, the third score and a preset priority threshold, wherein the target exercise amount is the exercise amount of the candidate user within a preset historical time period, and the average exercise amount is the average of the exercise amounts of all sample users with critical diseases within a preset historical time period.

[0065] Specifically, the amount of exercise is measured by the number of exercises.

[0066] Specifically, the value range of the preset priority threshold is 0.4 to 1. Those skilled in the art know that the preset priority threshold can be selected according to actual needs, which falls within the protection scope of the present invention and will not be repeated here.

[0067] S142: When the target movement amount is greater than the average movement amount, the first candidate score is a value obtained by subtracting a preset priority threshold from the sum of the first score, the second score and the third score and dividing the value by four.

[0068] S15, obtaining a second candidate score according to the initial feature data, wherein the second candidate score is a value obtained by multiplying the data related to the target operation type recorded in the initial feature data and the weight corresponding to the target operation type, that is, obtaining a second candidate score M according to the initial feature data, wherein M meets the following conditions:

[0069] M=(∑ p x=1 α x ×P x ) / 100, P x is the value corresponding to the xth target operation type obtained from the initial feature data, α x is the weight corresponding to the x-th target operation type, where x ranges from 1 to p, and p is the number of target operation types.

[0070] Specifically, the target operation type is the type of lifestyle intervention for the target disease. For example, when the target disease is diabetes, the target operation type includes target operation types such as insulin intervention, diet control intervention, and exercise intervention.

[0071] Specifically, α x The value range of is 0 to 1. Those skilled in the art know that α can be adjusted according to actual needs. x The configurations all fall within the protection scope of the present invention and will not be described in detail here.

[0072] S16: When the first candidate score is greater than the second candidate score, the first candidate score is obtained as the target priority.

[0073] S17: When the first candidate score is not greater than the second candidate score, the second candidate score is obtained as the target priority.

[0074] S2. Based on the initial feature data, obtain the candidate priority, wherein the candidate priority is a numerical value obtained based on the information included in the initial feature data and included in the process nodes involved in the processing of the candidate user due to physical abnormalities of the candidate user within a preset historical time period.

[0075] Specifically, S2 also includes the following steps: Figure 5 As shown:

[0076] S21, obtaining a critical priority, wherein the critical priority is a set positive real number.

[0077] Specifically, those skilled in the art know that the key priority can be selected according to actual needs, all of which fall within the protection scope of the present invention and will not be described in detail here.

[0078] S22, obtaining a final priority, wherein the final priority is the ratio of the difference between the largest target cost among the target costs corresponding to n key diseases and the smallest target cost among the target costs corresponding to the n key diseases to the smallest target cost among the target costs corresponding to the n key diseases.

[0079] S23, when the final priority is not greater than the preset final priority threshold, obtaining the candidate priority as the critical priority.

[0080] Specifically, the preset final priority threshold value ranges from 100% to 120%.

[0081] S24, when the final priority is greater than the preset final priority threshold, the candidate priority is obtained as the key priority plus the target multiple of the key priority, wherein the target multiple is the ratio of the largest target cost among the target costs corresponding to n key diseases to the smallest target cost among the target costs corresponding to the n key diseases.

[0082] From the above, we can see that based on the cost of candidate users corresponding to key diseases, candidate users are judged to obtain the final priority. Based on the comparison between the final priority and the threshold, different methods are used to obtain the user's score. When scoring the user, the user's different feature information and disease-related data are compared to confirm the user's score from different angles, so that the accuracy of obtaining the target user is higher.

[0083] S3, obtaining a target priority of the candidate user according to the target score and the candidate priority, wherein the target priority is the product of the target score and the candidate priority.

[0084] S500: When the target priority is greater than the specified priority, confirm that the candidate user is not the target user, wherein the specified priority is the cost required for the candidate user to establish a target relationship with the target object.

[0085] S600: When the target priority is not greater than the specified priority, confirming the candidate user as the target user.

[0086] From the above content, we can see that analyzing the characteristic data of different dimensions and using different methods to determine the target users improves the efficiency of screening the target users. When scoring the users, the users' scores are confirmed from different angles based on their different characteristic information and disease-related data, which makes it more accurate to obtain the target users.

[0087] The first embodiment of the present invention can obtain the determination threshold of at least one relationship determination feature corresponding to the target relationship, obtain the target feature data of the candidate user within a preset historical time period, and when there is any record data in the target feature data that cannot meet the determination threshold of the corresponding relationship determination feature, confirm that the candidate user is not the target user. When all record data in the target feature data meet the determination threshold of the corresponding relationship determination feature, obtain the target priority corresponding to the candidate user. When the target priority is greater than the specified priority, confirm that the candidate user is not the target user. When the target priority is not greater than the specified priority, confirm that the candidate user is the target user. It can be seen that by analyzing feature data of different dimensions and determining the target user in different ways, the efficiency of screening the target user is improved. When scoring the user, the user's score is confirmed from different angles based on the user's different feature information and disease-related data, so that the accuracy of obtaining the target user is higher.

[0088] Embodiment 2

[0089] like Figure 6 As shown, this embodiment provides a device for acquiring a target user, the device comprising:

[0090] A designated feature information acquisition module 100 is used to obtain a determination threshold of at least one relationship determination feature corresponding to a target relationship, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease, and the relationship determination feature is used to determine whether an association relationship can be established between a candidate user and a target object.

[0091] Specifically, the target object is an organization that can provide protection for the user when the user's physical condition is abnormal.

[0092] Specifically, the target disease is the disease corresponding to the target relationship.

[0093] Specifically, for example, relationship determination features such as gender, age, number of diagnoses, disease name, number of hospitalizations and the number of days of hospitalization for each hospitalization, the use of various types of drugs, the type of lifestyle intervention, the cost of treating the disease, etc. can be understood as: when the target disease is diabetes, the age is set within a certain range, the gender is set to male or female, the use of drugs for diabetes is set within a certain range, the number of days of hospitalization due to diabetes attacks is set within a certain range, and so on.

[0094] Specifically, those skilled in the art know that the determination threshold can be selected according to actual needs, all of which fall within the protection scope of the present invention and will not be described in detail here.

[0095] Specifically, the candidate user is a user who wants to establish a target relationship with the target object.

[0096] The target feature data acquisition module 200 is used to obtain the target feature data of the candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating the target disease obtained from the initial feature data, and each record data includes a numerical value corresponding to the relationship judgment feature.

[0097] Specifically, the end time of the preset historical time period is the current time, and the time span of the preset historical time period is consistent with the relationship establishment time span corresponding to the target relationship.

[0098] Specifically, the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user has physical abnormalities and seeks medical treatment within the preset historical time period, wherein each disease corresponds to a group of record data, each group of record data includes several record data, and each record data includes a numerical value corresponding to the relationship judgment feature.

[0099] The target determination module 300 is used to determine that the candidate user is not the target user when there is any record data in the target feature data that fails to meet the determination threshold of the corresponding relationship determination feature.

[0100] Specifically, for example: when the target disease is diabetes, there will be several feature data related to the treatment of diabetes in the target feature data. In order to establish the association relationship of the target disease, it is necessary to meet the conditions that the number of diagnoses does not exceed 5 times, the insulin dosage does not exceed 50 units, and the metformin dosage does not exceed 100 units. If a certain record data in the target feature data, such as the insulin dosage is 80, it means that this candidate user is not the target user.

[0101] The target priority acquisition module 400 is used to obtain the target priority corresponding to the candidate user when all record data in the target feature data meet the judgment threshold of the corresponding relationship judgment feature, wherein the target priority is a value obtained by processing the value corresponding to the target feature obtained from the initial feature data and used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened out relationship judgment feature.

[0102] Specifically, Figure 7 As shown, the target priority acquisition module 400 also includes:

[0103] The first execution module 1 is used to obtain a target score corresponding to the candidate user, wherein the target score is a value obtained by adding the values ​​corresponding to the target features corresponding to the candidate user which are normalized respectively.

[0104] Specifically, Figure 8 As shown, the first execution module 1 also includes:

[0105] The first acquisition module 11 is used to acquire a first score according to the initial feature data, wherein the first score is a value obtained by normalizing the number of hospitalizations recorded in the initial feature data, that is, to acquire a first score A1 according to the target feature data, wherein A1 meets the following conditions:

[0106] A1=1 / e -a , a is the number of hospitalizations in a preset historical time period obtained based on the initial feature data corresponding to the candidate user.

[0107] The second acquisition module 12 is used to acquire a second score according to the initial feature data, wherein the second score is a value acquired based on a plurality of disease names recorded in the initial feature data and the cost required to treat the diseases corresponding to the disease names, that is, to acquire a second score A2 according to the initial feature data, wherein A2 meets the following conditions:

[0108] A2=P 0 +∑ n i=1 β i ×(Bi -B min ) / (B max -B min ), B i is the target cost corresponding to the ith key disease, i ranges from 1 to n, n is the number of key diseases, B min is the minimum target cost among the target costs corresponding to n key diseases, B max is the largest target cost among the target costs corresponding to n key diseases, β i is the target probability corresponding to the i-th key disease, P 0 is the probability of the 1st to the nth key diseases occurring simultaneously.

[0109] Specifically, n≥2, where when n=1, P 0 =0.

[0110] Specifically, the key disease is a disease recorded in the initial feature data that the candidate user was diagnosed with within a preset historical time period.

[0111] Specifically, the target cost is the cost required for treating the key disease for the candidate user recorded in the initial feature data within a preset historical time period.

[0112] Specifically, the target probability is the ratio between the number of sample users suffering from the key disease and the total number of sample users, wherein the sample users are patients who have been treated within a preset historical time period.

[0113] Specifically, P 0 is obtained in the same way as the target probability based on the number of sample users who suffer from n key diseases at the same time.

[0114] The third acquisition module 13 is used to obtain a third score based on preset rules, wherein the preset rules are scoring rules corresponding to different age groups based on gender settings, and the third score is a score obtained by comparing the gender and age corresponding to the candidate user with the gender and age group in the preset rules.

[0115] Specifically, the value range of the score corresponding to each age group in the preset rule is 0 to 1, wherein the sum of the scores corresponding to all age groups in the preset rule is 1.

[0116] Furthermore, those skilled in the art know that preset rules can be set according to actual needs, which all fall within the protection scope of the present invention and will not be described in detail herein.

[0117] The fourth acquisition module 14 is used to acquire a first candidate score according to the initial feature data, wherein the first candidate score is a value acquired based on the first score, the second score, the third score and the lifestyle intervention type recorded in the initial feature data.

[0118] Specifically, Fig. 9 As shown, the fourth acquisition module 14 also includes:

[0119] The first target module 141 is used for when the target exercise amount is not greater than the average exercise amount, the first candidate score is the average of the first score, the second score, the third score and the preset priority threshold, wherein the target exercise amount is the exercise amount of the candidate user within a preset historical time period, and the average exercise amount is the average of the exercise amounts of all sample users with key diseases within a preset historical time period.

[0120] Specifically, the value range of the preset priority threshold is 0.4 to 1. Those skilled in the art know that the preset priority threshold can be selected according to actual needs, which falls within the protection scope of the present invention and will not be repeated here.

[0121] The second target module 142 is used for, when the target movement amount is greater than the average movement amount, the first candidate score is the value obtained by subtracting the value of the sum of the first score, the second score and the third score from the preset priority threshold and dividing it by four.

[0122] The fifth acquisition module 15 is used to acquire a second candidate score according to the initial feature data, wherein the second candidate score is a value obtained by multiplying the data related to the target operation type recorded in the initial feature data and the weight corresponding to the target operation type, that is, the second candidate score M is acquired according to the initial feature data, wherein M meets the following conditions:

[0123] M=(∑ p x=1 α x ×P x ) / 100, P x is the value corresponding to the xth target operation type obtained from the initial feature data, α x is the weight corresponding to the x-th target operation type, where x ranges from 1 to p, and p is the number of target operation types.

[0124] Specifically, the target operation type is the type of lifestyle intervention for the target disease. For example, when the target disease is diabetes, the target operation type includes target operation types such as insulin intervention, diet control intervention, and exercise intervention.

[0125] Specifically, α xThe value range of is 0 to 1. Those skilled in the art know that α can be adjusted according to actual needs. x The configurations all fall within the protection scope of the present invention and will not be described in detail here.

[0126] The sixth acquisition module 16 is configured to acquire the first candidate score as the target priority when the first candidate score is greater than the second candidate score.

[0127] The seventh acquisition module 17 is configured to acquire the second candidate score as the target priority when the first candidate score is not greater than the second candidate score.

[0128] The second execution module 2 is used to obtain the candidate priority based on the initial feature data, wherein the candidate priority is a numerical value obtained based on the information included in the process nodes involved in the processing of the candidate user due to physical abnormalities of the candidate user within a preset historical time period included in the initial feature data.

[0129] Specifically, Fig.10 As shown, the second execution module 2 also includes:

[0130] The critical priority acquisition module 21 is used to acquire the critical priority, wherein the critical priority is a set positive real number.

[0131] Specifically, those skilled in the art know that the key priority can be selected according to actual needs, all of which fall within the protection scope of the present invention and will not be described in detail here.

[0132] The final priority acquisition module 22 is used to obtain the final priority, wherein the final priority is the ratio of the difference between the largest target cost among the target costs corresponding to n key diseases and the smallest target cost among the target costs corresponding to the n key diseases to the smallest target cost among the target costs corresponding to the n key diseases.

[0133] The first candidate priority obtaining module 23 is used to obtain the candidate priority as a critical priority when the final priority is not greater than a preset final priority threshold.

[0134] Specifically, the preset final priority threshold value ranges from 100% to 120%.

[0135] The second candidate priority acquisition module 24 is used to obtain a candidate priority that is a key priority plus a target multiple of the key priority when the final priority is greater than a preset final priority threshold, wherein the target multiple is a ratio of the largest target cost among the target costs corresponding to n key diseases to the smallest target cost among the target costs corresponding to the n key diseases.

[0136] From the above, we can see that based on the cost of candidate users corresponding to key diseases, candidate users are judged to obtain the final priority. Based on the comparison between the final priority and the threshold, different methods are used to obtain the user's score. When scoring the user, the user's different feature information and disease-related data are compared to confirm the user's score from different angles, so that the accuracy of obtaining the target user is higher.

[0137] The third execution module 3 is used to obtain the target priority of the candidate user according to the target score and the candidate priority, wherein the target priority is the product of the target score and the candidate priority.

[0138] The first target user acquisition module 500 is used to confirm that the candidate user is not the target user when the target priority is greater than the specified priority, wherein the specified priority is the cost required for the candidate user to establish a target relationship with the target object.

[0139] The second target user acquisition module 600 is used to confirm that the candidate user is the target user when the target priority is not greater than the specified priority.

[0140] Embodiment 3

[0141] An embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to implement the steps:

[0142] A determination threshold of at least one relationship determination feature corresponding to a target relationship is obtained, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease, and the relationship determination feature is used to determine whether an association relationship can be established between a candidate user and a target object.

[0143] Obtain target feature data of the candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating the target disease obtained from the initial feature data, each record data includes a numerical value corresponding to the relationship determination feature, and the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user seeks medical treatment due to physical abnormalities within the preset historical time period.

[0144] When there is any record data in the target feature data that fails to meet the determination threshold of the corresponding relationship determination feature, it is determined that the candidate user is not the target user.

[0145] When all record data in the target feature data meet the judgment threshold of the corresponding relationship judgment feature, the target priority corresponding to the candidate user is obtained, wherein the target priority is a value obtained by processing the numerical value corresponding to the target feature obtained from the initial feature data and is used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened relationship judgment feature.

[0146] When the target priority is greater than the specified priority, it is determined that the candidate user is not the target user, wherein the specified priority is the cost required for the candidate user to establish a target relationship with the target object.

[0147] When the target priority is not greater than the specified priority, the candidate user is confirmed as the target user.

[0148] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0149] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0150] Embodiment 4

[0151] An embodiment of the present invention provides an electronic device, which includes a processor and the non-transitory computer-readable storage medium in Embodiment 3 of the present invention.

[0152] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technician familiar with this profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for acquiring a target user, characterized in that: The method comprises the following steps: Acquiring a determination threshold of at least one relationship determination feature corresponding to a target relationship, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease, and the relationship determination feature is used to determine whether an association relationship can be established between a candidate user and a target object; Obtain target feature data of the candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating the target disease obtained from the initial feature data, each record data includes a value corresponding to the relationship determination feature, and the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user has physical abnormality and seeks medical treatment within the preset historical time period; When any record data in the target feature data fails to meet the determination threshold of the corresponding relationship determination feature, it is determined that the candidate user is not the target user; When all the record data in the target feature data meet the determination threshold of the corresponding relationship determination feature, the target priority corresponding to the candidate user is obtained, wherein the target priority is a value obtained by processing the value corresponding to the target feature obtained from the initial feature data and used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened relationship determination feature, wherein obtaining the target priority corresponding to the candidate user includes the following steps: Obtaining a target score corresponding to the candidate user, wherein the target score is a value obtained by adding values ​​obtained by normalizing values ​​corresponding to target features corresponding to the candidate user, wherein obtaining the target score corresponding to the candidate user comprises the following steps: According to the initial characteristic data, a first score is obtained, wherein the first score is a value obtained by normalizing the number of hospitalizations recorded in the initial characteristic data, that is, according to the target characteristic data, a first score A1 is obtained, wherein A1 meets the following conditions: A1=1 / e -a , a is the number of hospitalizations in a preset historical time period obtained based on the initial feature data corresponding to the candidate user; According to the initial feature data, a second score is obtained, wherein the second score is a value obtained based on the multiple disease names recorded in the initial feature data and the cost required to treat the diseases corresponding to the disease names, that is, according to the initial feature data, a second score A2 is obtained, wherein A2 meets the following conditions: A2=P 0 +∑ n i=1 β i ×(B i -B min ) / (B max -B min ), B i is the target cost corresponding to the ith key disease, i ranges from 1 to n, n is the number of key diseases, B min is the minimum target cost among the target costs corresponding to n key diseases, B max is the largest target cost among the target costs corresponding to n key diseases, β i is the target probability corresponding to the i-th key disease, P 0 is the probability of the 1st to nth key diseases occurring simultaneously; Based on a preset rule, a third score is obtained, wherein the preset rule is a scoring rule corresponding to different age groups set based on gender, and the third score is a score obtained by comparing the gender and age corresponding to the candidate user with the gender and age group in the preset rule; According to the initial feature data, a first candidate score is obtained, wherein the first candidate score is a value obtained based on the first score, the second score, the third score and the lifestyle intervention type recorded in the initial feature data, wherein according to the initial feature data, obtaining the first candidate score comprises the following steps: When the target exercise amount is not greater than the average exercise amount, the first candidate score is the average of the first score, the second score, the third score and the preset priority threshold, wherein the target exercise amount is the exercise amount of the candidate user in a preset historical time period, and the average exercise amount is the average of the exercise amounts of all sample users with key diseases in a preset historical time period; When the target movement amount is greater than the average movement amount, the first candidate score is a value obtained by subtracting a preset priority threshold from the sum of the first score, the second score and the third score and dividing it by four; According to the initial feature data, a second candidate score is obtained, wherein the second candidate score is a value obtained by multiplying the data related to the target operation type recorded in the initial feature data and the weight corresponding to the target operation type, that is, according to the initial feature data, a second candidate score M is obtained, wherein M meets the following conditions: M=(∑ p x=1 α x ×P x ) / 100, P x is the value corresponding to the xth target operation type obtained from the initial feature data, α x is the weight corresponding to the x-th target operation type, where x ranges from 1 to p, and p is the number of target operation types; When the first candidate score is greater than the second candidate score, the first candidate score is obtained as the target score; When the first candidate score is not greater than the second candidate score, the second candidate score is obtained as the target score; Based on the initial feature data, a candidate priority is obtained, wherein the candidate priority is a value obtained based on information included in a process node involved in processing the candidate user due to physical abnormalities of the candidate user within a preset historical time period included in the initial feature data, wherein obtaining the candidate priority includes the following steps: Obtain a critical priority, wherein the critical priority is a set positive real number; Obtaining a final priority, wherein the final priority is a ratio of a difference between a maximum target cost among the target costs corresponding to the n key diseases and a minimum target cost among the target costs corresponding to the n key diseases to the minimum target cost among the target costs corresponding to the n key diseases; When the final priority is not greater than the preset final priority threshold, the candidate priority is obtained as the critical priority; When the final priority is greater than the preset final priority threshold, the candidate priority is obtained as the key priority plus the target multiple of the key priority, wherein the target multiple is the ratio of the largest target cost among the target costs corresponding to the n key diseases to the smallest target cost among the target costs corresponding to the n key diseases; Obtaining a target priority of the candidate user according to the target score and the candidate priority, wherein the target priority is the product of the target score and the candidate priority; When the target priority is greater than the specified priority, confirming that the candidate user is not the target user, wherein the specified priority is the cost required for the candidate user to establish a target relationship with the target object; When the target priority is not greater than the specified priority, the candidate user is confirmed as the target user.

2. The method for acquiring target users according to claim 1, characterized in that: The end time of the preset historical time period is the current time, and the time span of the preset historical time period is consistent with the relationship establishment time span corresponding to the target relationship.

3. A device for acquiring a target user, characterized in that: The device comprises: A designated feature information acquisition module is used to obtain a determination threshold of at least one relationship determination feature corresponding to a target relationship, wherein the target relationship is an association relationship established between a target user and a target object based on reducing the cost of treating a target disease, and the relationship determination feature is used to determine whether an association relationship can be established between a candidate user and a target object; A target feature data acquisition module is used to acquire target feature data of a candidate user within a preset historical time period, wherein the target feature data is at least one treatment record data generated for treating a target disease acquired from the initial feature data, each record data includes a numerical value corresponding to a relationship determination feature, and the initial feature data is at least one treatment record data corresponding to at least one disease generated when the candidate user has physical abnormalities and seeks medical treatment within the preset historical time period; A target determination module, used to determine that a candidate user is not a target user when any record data in the target feature data fails to meet the determination threshold of the corresponding relationship determination feature; A target priority acquisition module is used to acquire the target priority corresponding to the candidate user when all record data in the target feature data meet the determination threshold of the corresponding relationship determination feature, wherein the target priority is a value obtained by processing the value corresponding to the target feature obtained from the initial feature data and used to determine whether an association relationship can be established between the candidate user and the target object, and the target feature is a screened relationship determination feature, wherein the target priority acquisition module includes: A first execution module is used to obtain a target score corresponding to the candidate user, wherein the target score is a value obtained by adding values ​​corresponding to the target features corresponding to the candidate user after normalization processing is performed respectively, and the first execution module also includes: The first acquisition module is used to acquire a first score according to the initial feature data, wherein the first score is a value obtained by normalizing the number of hospitalizations recorded in the initial feature data, that is, to acquire a first score A1 according to the target feature data, wherein A1 meets the following conditions: A1=1 / e -a , a is the number of hospitalizations in a preset historical time period obtained based on the initial feature data corresponding to the candidate user; The second acquisition module is used to acquire a second score according to the initial feature data, wherein the second score is a value acquired based on a plurality of disease names recorded in the initial feature data and the cost required to treat the diseases corresponding to the disease names, that is, to acquire a second score A2 according to the initial feature data, wherein A2 meets the following conditions: A2=P 0 +∑ n i=1 β i ×(B i -B min ) / (B max -B min ), B i is the target cost corresponding to the ith key disease, i ranges from 1 to n, n is the number of key diseases, B min is the minimum target cost among the target costs corresponding to n key diseases, B max is the largest target cost among the target costs corresponding to n key diseases, β i is the target probability corresponding to the i-th key disease, P 0 is the probability of the 1st to nth key diseases occurring simultaneously; A third acquisition module, configured to acquire a third score based on a preset rule, wherein the preset rule is a score rule corresponding to different age groups set based on gender, and the third score is a score obtained by comparing the gender and age corresponding to the candidate user with the gender and age group in the preset rule; A fourth acquisition module, configured to acquire a first candidate score according to the initial feature data, wherein the first candidate score is a value acquired based on the first score, the second score, the third score, and the lifestyle intervention type recorded in the initial feature data, wherein the fourth acquisition module further comprises; A first target module, for when the target exercise amount is not greater than the average exercise amount, the first candidate score is the average of the first score, the second score, the third score and a preset priority threshold, wherein the target exercise amount is the exercise amount of the candidate user in a preset historical time period, and the average exercise amount is the average of the exercise amounts of all sample users with key diseases in a preset historical time period; A second target module, for when the target movement amount is greater than the average movement amount, the first candidate score is a value obtained by dividing the sum of the first score, the second score and the third score minus the preset priority threshold by four; A fifth acquisition module is used to acquire a second candidate score according to the initial feature data, wherein the second candidate score is a value obtained by multiplying the data related to the target operation type recorded in the initial feature data and the weight corresponding to the target operation type, that is, to acquire a second candidate score M according to the initial feature data, wherein M meets the following conditions: M=(∑ p x=1 α x ×P x ) / 100, P x is the value corresponding to the xth target operation type obtained from the initial feature data, α x is the weight corresponding to the x-th target operation type, where x ranges from 1 to p, and p is the number of target operation types; A sixth acquisition module, configured to acquire the first candidate score as a target score when the first candidate score is greater than the second candidate score; A seventh acquisition module, configured to acquire the second candidate score as the target score when the first candidate score is not greater than the second candidate score; The second execution module is used to obtain a candidate priority based on the initial feature data, wherein the candidate priority is a value obtained based on information included in the process node involved in the process of processing the candidate user due to physical abnormalities of the candidate user within a preset historical time period included in the initial feature data, and the second execution module also includes: A key priority acquisition module, used to acquire a key priority, wherein the key priority is a set positive real number; A final priority acquisition module, used to acquire a final priority, wherein the final priority is a ratio of a difference between a maximum target cost among the target costs corresponding to n key diseases and a minimum target cost among the target costs corresponding to n key diseases to the minimum target cost among the target costs corresponding to n key diseases; A first candidate priority acquisition module, configured to acquire the candidate priority as a critical priority when the final priority is not greater than a preset final priority threshold; A second candidate priority acquisition module is used to acquire a candidate priority that is a key priority plus a target multiple of the key priority when the final priority is greater than a preset final priority threshold, wherein the target multiple is a ratio of the largest target cost among the target costs corresponding to the n key diseases to the smallest target cost among the target costs corresponding to the n key diseases; A third execution module is used to obtain a target priority of the candidate user according to the target score and the candidate priority, wherein the target priority is the product of the target score and the candidate priority; A first target user acquisition module, configured to confirm that the candidate user is not the target user when the target priority is greater than a specified priority, wherein the specified priority is a cost required for the candidate user to establish a target relationship with the target object; The second target user acquisition module is used to confirm the candidate user as the target user when the target priority is not greater than the specified priority.

4. The device for acquiring target users according to claim 3, characterized in that: The end time of the preset historical time period is the current time, and the time span of the preset historical time period is consistent with the relationship establishment time span corresponding to the target relationship.

5. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the method for acquiring a target user as described in any one of claims 1-2.

6. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 5.

Images