User portrait-based property fee collection strategy generation method and system

Abstract

The invention provides a property fee collection strategy generation method and system based on a user portrait, and the method comprises the steps: obtaining multiple types of first behavior data of a target user, generating a user portrait comprising multiple types of first feature values, and carrying out the matching of a first strategy set based on the user portrait; obtaining first arrearage information representing an arrearage scene, updating each first feature value to a second feature value by using a plurality of first weight values associated with the first arrearage information, and matching a second strategy set from a plurality of preset collection strategies based on the plurality of second feature values; and determining a first target strategy based on the intersection of the first strategy set and the second strategy set. According to the technical scheme of the embodiment of the invention, the first characteristic value and the second characteristic value can be utilized to carry out secondary matching of the collection strategy, the intersection is taken from the strategies matched twice to obtain the target payment strategy, the target payment strategy is more suitable for the payment ability, intention and scene of the target user, the reliability of the target payment strategy is improved, and the user experience is improved. And the collection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for generating a property fee collection strategy based on user portraits. Background Art

[0002] The collection of property fees is an important part of property management. After collecting the property fees, the property management personnel need to compile statistics on the payment situation and screen out the users who are in arrears, and then carry out relevant collection work on the users who are in arrears. Traditional manual collection not only relies on the communication skills and management experience of the property management personnel, but also has low collection efficiency.

[0003] In related technologies, user profiles are constructed by collecting user behavior data, and appropriate collection strategies are automatically matched through user profiles. The collection strategies guide property management personnel to adopt appropriate collection measures for collection. Although the efficiency of collection has been improved to a certain extent, the behavior data can only reflect the user's payment habits and ability, and cannot reflect the objective factors of the user's arrears, such as the customer's temporary capital turnover leading to arrears, or the relevant property being a foreclosed property that cannot be paid. Therefore, the collection strategies matched by the existing user profiles cannot fully reflect the user's intentions, the reliability of the collection strategies cannot be guaranteed, and the efficiency of property fee collection is low. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method and system for generating a property fee collection strategy based on user portraits, which can improve the reliability of the collection strategy and improve the collection efficiency.

[0005] In a first aspect, an embodiment of the present invention provides a method for generating a property fee collection strategy based on a user profile, comprising:

[0006] Selecting a target user from multiple delinquent users, determining a first delinquency period based on a first delinquent bill of the target user, and acquiring multiple types of first behavior data generated by the target user in the first delinquent period;

[0007] Generate a user profile based on multiple categories of the first behavior data, and match a first strategy set from multiple preset confiscation strategies based on the user profile, wherein the user profile includes multiple first feature values, each of which corresponds to a category of the first behavior data, and the preset confiscation strategy is associated with multiple feature value intervals, each of which corresponds to a category of the first behavior data;

[0008] Acquire first arrears information pre-associated with the target user, and determine multiple preset weight values ​​associated with the first arrears information as a first weight value, wherein the first arrears information is used to characterize an arrears scenario of the first arrears period, and each of the preset weight values ​​corresponds to one of the first feature values;

[0009] updating each of the first characteristic values ​​to a second characteristic value based on the corresponding first weight value, and matching a second strategy set from a plurality of preset collection strategies based on a plurality of the second characteristic values;

[0010] A first target policy is determined based on an intersection of the first policy set and the second policy set.

[0011] According to some embodiments of the present invention, generating a user portrait based on multiple types of the first behavior data includes:

[0012] Determine one of the first behavior data as second behavior data, determine multiple of the first behavior data as third behavior data, and determine the corresponding magnification coefficients based on the numbers of the third behavior data, wherein the magnification coefficients are greater than 1;

[0013] Input all of the first behavior data into the preset model to obtain the first eigenvalues ​​corresponding to each of them, and generate the user portrait based on the first eigenvalues, wherein the first eigenvalue of the second behavior data is the initial eigenvalue output by the preset model, and the first eigenvalue of the third behavior data is the product of the initial eigenvalue and the amplification factor.

[0014] According to some embodiments of the present invention, obtaining first arrears information pre-associated with the target user includes:

[0015] Constructing a first visualization interface, and displaying the first overdue bill on the first visualization interface;

[0016] In response to any of the first overdue bills being clicked, a second visualization interface is constructed, and a first list and a second list are displayed on the second visualization interface, wherein the first list records the first behavior data, and the second list records a plurality of preset overdue information, each of the preset overdue information represents a different overdue scenario, and each of the preset overdue information is associated with its own first weight value;

[0017] Determining at least one optional arrears information in the second list, wherein each of the first behavior data is associated with at least one of the preset arrears information;

[0018] The optional arrears information selected from the second list is determined as the first arrears information.

[0019] According to some embodiments of the present invention, determining a first target policy based on an intersection of the first policy set and the second policy set includes:

[0020] Determine the intersection of the first policy set and the second policy set as a target policy set;

[0021] When the target strategy set is an empty set, determining each of the preset collection strategies of the second strategy set as a candidate collection strategy;

[0022] Alternatively, when the target strategy set is not an empty set, determining the preset collection strategy of the target strategy set as the candidate collection strategy;

[0023] When there are multiple candidate collection strategies, the second characteristic value with the largest value is determined as the first reference value, the characteristic value interval with the smallest value range corresponding to the first reference value is determined as the first reference interval, and the candidate collection strategy corresponding to the first reference interval is determined as the first target strategy.

[0024] According to some embodiments of the present invention, after determining the first target policy based on the intersection of the first policy set and the second policy set, the method further includes:

[0025] Acquire first feedback information generated based on the first target strategy;

[0026] When the first feedback information is used to indicate that all the first overdue bills have been paid, maintaining the current first weight value of the first overdue bill information;

[0027] When the first feedback information is used to indicate that at least one of the first overdue bills has not been paid, a second target strategy is determined from the target strategy set.

[0028] According to some embodiments of the present invention, when the first feedback information is used to indicate that at least one of the first overdue bills has not been paid, and at least one of the first overdue bills has been paid, determining a second target strategy from the target strategy set includes:

[0029] Determine the first outstanding bill that has not been paid as a second outstanding bill, and determine a second outstanding period based on the second outstanding bill;

[0030] Acquire second arrears information based on the input of the target user, wherein the second arrears information is used to characterize an arrears scenario of the second arrears period, and determine the plurality of preset weight values ​​associated with the second arrears information as a second weight value;

[0031] Each of the first feature values ​​is updated to a third feature value based on the corresponding second weight value, and the second target strategy is determined based on the plurality of the third feature values.

[0032] According to some embodiments of the present invention, when the first feedback information is used to represent that all of the first overdue bills have not been paid, determining a second target strategy from the target strategy set includes:

[0033] removing the first target policy from the target policy set;

[0034] When there are multiple candidate collection strategies remaining in the target strategy set, the second characteristic value that is only smaller than the first reference value is determined as the second reference value, the characteristic value interval with the smallest value range among the characteristic value intervals corresponding to the second reference value is determined as the second reference interval, and the candidate collection strategy corresponding to the second reference interval is determined as the second target strategy;

[0035] Acquire second feedback information generated based on the second target strategy;

[0036] When the second feedback information is used to represent that all the first overdue bills have been paid, the preset weight value corresponding to the second reference value in the first overdue information is increased based on the preset step value, and the preset weight value corresponding to the first reference value in the first overdue information is reduced based on the step value.

[0037] In the second aspect, an embodiment of the present invention provides a system for generating a property fee collection strategy based on user portrait, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the method for generating a property fee collection strategy based on user portrait as described in the first aspect above.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a property fee collection strategy generation system based on user portrait as described in the second aspect above.

[0039] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method for generating a property fee collection strategy based on user portrait as described in the first aspect above.

[0040] The method for generating a property fee collection strategy based on user portrait according to an embodiment of the present invention has at least the following beneficial effects: selecting a target user from a plurality of arrears users, determining a first arrears period based on a first arrears bill of the target user, and obtaining a plurality of first behavior data generated by the target user in the first arrears period; generating a user portrait based on the plurality of first behavior data, matching a first strategy set from a plurality of preset collection strategies based on the user portrait, wherein the user portrait includes a plurality of first feature values, each of which corresponds to a type of the first behavior data, and the preset collection strategy is associated with a plurality of feature value intervals, each of which corresponds to a type of the first behavior data; obtaining first arrears information pre-associated with the target user, determining a plurality of preset weight values ​​associated with the first arrears information as a first weight value, wherein the first arrears information is used to characterize an arrears scenario of the first arrears period, and each of which corresponds to a first feature value; updating each of the first feature values ​​to a second feature value based on the corresponding first weight value, matching a second strategy set from a plurality of preset collection strategies based on a plurality of the second feature values; and determining a first target strategy based on the intersection of the first strategy set and the second strategy set. According to the technical solution of the embodiment of the present invention, it is possible to predict the user's payment ability and payment intention through the user portrait, characterize the user's arrears scenario through the first arrears information, use the first eigenvalue and the second eigenvalue to perform secondary matching of the collection strategy, and take the intersection of the two matched strategies to obtain the target payment strategy. The target payment strategy is more suitable for the target user's payment ability, intention and scenario, thereby improving the reliability of the target payment strategy and improving the collection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of a method for generating a property fee collection strategy based on user portraits provided by an embodiment of the present invention;

[0042] Figure 2 It is a schematic diagram of a method for generating a property fee collection strategy based on user portraits provided by an embodiment of the present invention;

[0043] Figure 3 It is a complete flow chart of a method for generating a property fee collection strategy based on user portraits provided by another embodiment of the present invention;

[0044] Figure 4 It is a structural diagram of a system for generating a property fee collection strategy based on user portraits provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0045] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0046] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0047] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0048] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0049] An embodiment of the present invention provides a method and system for generating a property fee collection strategy based on user portraits, wherein the method comprises: selecting a target user from a plurality of users in arrears, determining a first arrears period based on a first arrears bill of the target user, and obtaining a plurality of categories of first behavior data generated by the target user during the first arrears period; generating a user portrait based on the plurality of categories of the first behavior data, and matching a first strategy set from a plurality of preset collection strategies based on the user portrait, wherein the user portrait comprises a plurality of first feature values, each of the first feature values ​​corresponds to a category of the first behavior data, and the preset collection strategy is related to There are multiple feature value intervals, each of which corresponds to a type of the first behavior data; obtain the first arrears information pre-associated with the target user, and determine the multiple preset weight values ​​associated with the first arrears information as the first weight value, wherein the first arrears information is used to characterize the arrears scenario of the first arrears period, and each of the preset weight values ​​corresponds to one of the first feature values; update each of the first feature values ​​to a second feature value based on the corresponding first weight value, match a second strategy set from multiple preset collection strategies based on multiple second feature values; determine the first target strategy based on the intersection of the first strategy set and the second strategy set. According to the technical solution of the embodiment of the present invention, it is possible to predict the user's payment ability and payment intention through user portraits, characterize the user's arrears scenario through the first arrears information, perform secondary matching of the collection strategy using the first feature value and the second feature value, and obtain the target payment strategy by taking the intersection of the two matched strategies. The target payment strategy is more suitable for the payment ability, intention and scenario of the target user, thereby improving the reliability of the target payment strategy and the collection efficiency.

[0050] The technical solution of the embodiment of the present invention is further described below based on the accompanying drawings.

[0051] Reference Figure 1 , Figure 1 A flowchart of a method for generating a property fee collection strategy based on a user portrait is provided in an embodiment of the present invention. The method for generating a property fee collection strategy based on a user portrait includes but is not limited to the following steps:

[0052] S10, selecting a target user from multiple delinquent users, determining a first delinquency period based on a first delinquent bill of the target user, and obtaining multiple types of first behavior data generated by the target user in the first delinquent period;

[0053] S20, generating a user profile based on the multiple types of first behavior data, and matching a first strategy set from multiple preset confiscation strategies based on the user profile, wherein the user profile includes multiple first feature values, each first feature value corresponds to a type of first behavior data, and the preset confiscation strategy is associated with multiple feature value intervals, each feature value interval corresponds to a type of first behavior data;

[0054] S30, obtaining first arrears information pre-associated with the target user, and determining multiple preset weight values ​​associated with the first arrears information as a first weight value, wherein the first arrears information is used to characterize an arrears scenario of a first arrears cycle, and each preset weight value corresponds to a first characteristic value;

[0055] S40, updating each first characteristic value to a second characteristic value based on the corresponding first weight value, and matching a second strategy set from a plurality of preset collection strategies based on the plurality of second characteristic values;

[0056] S50: Determine a first target policy based on the intersection of the first policy set and the second policy set.

[0057] It should be noted that the technical solution of this embodiment is to determine a first target strategy for a user in arrears. In the case of multiple users in arrears, each user can be determined as a target user and the technical solution of this embodiment can be executed once, which will not be repeated later.

[0058] It should be noted that the target user is a user in arrears, and the first arrears bill is the arrears bill corresponding to the target user. Since property management fees are usually collected periodically, such as one month or one quarter, the billing cycle of each first arrears bill is fixed. After selecting the target user, all the first arrears bills are automatically read, and the first arrears cycle is determined based on the billing cycles corresponding to all the first arrears bills.

[0059] It should be noted that the technical solution of this embodiment can be applied to property systems, such as property APPs. Each user can log in to the property APP to perform various operations such as logging in, paying, complaining, viewing bills, and using services. The property system records each user's operations as user behavior data. The first behavior data is the user behavior data generated by the target user during the first arrears period.

[0060] It should be noted that after obtaining the first behavior data, constructing a user profile based on the user behavior is an existing technology, and the specific principle will not be elaborated here. The user portrait technology can convert each type of first behavior data into a first feature value, determine the user label through the first feature value, and thus obtain a user portrait. The user portrait includes the first feature value corresponding to each first behavior data, such as Figure 2As shown, the target user includes n first behavior data, where n is a positive integer. The first behavior data 1 is used to generate the first feature value 1 in the user portrait, the first behavior data 2 is used to generate the first feature value 2, and so on.

[0061] For example, Figure 2 As shown, the user portraits of this embodiment include three categories. Category A users are used to represent users with higher satisfaction, including two portraits: hardcore fans and satisfied users; Category B users are used to represent low-frequency users of property APPs, including three portraits: indifferent users, silent users, and wavering users; Category C users are used to represent users who are less cooperative with property management, including three user portraits: opposing, dissatisfied but convertible, and dissatisfied but unconvertible.

[0062] It should be noted that constructing user portraits is a prior art. This embodiment pre-sets multiple preset collection strategies. Each preset collection strategy is associated with multiple feature value intervals. Each feature value interval corresponds to a type of first behavior data. Therefore, each feature value interval can be used to compare a first feature value. When all the first feature values ​​included in the user portrait fall into each feature value interval of a preset collection strategy, the preset collection strategy can be placed in the first strategy set.

[0063] It should be noted that the preset collection strategy can be set according to actual needs, for example Figure 2 As shown, the preset collection strategies include installment payment, preferential incentives, automatic deductions, door-to-door collection or reminder of late payment fees, etc. This embodiment does not limit the specific strategy content.

[0064] It is worth noting that since the types of user behavior data generated by each user are not necessarily all the same, for example, the user behavior data of some users in arrears include complained properties, while the user behavior data of some users in arrears do not include complained properties. Therefore, the characteristic value interval associated with each preset collection strategy corresponds to all optional user behavior data. When the target user has only several types of first behavior data, only the characteristic value interval corresponding to the first behavior data is required to be compared, and the remaining characteristic value intervals are not considered. For example, if the first behavior data of the target user does not include complained properties, then when matching the preset collection strategy, the characteristic value interval corresponding to the complained property of the preset collection strategy is not considered, and no further details will be given later. In addition, the user behavior data corresponding to each characteristic value interval is different, so the values ​​of multiple characteristic value intervals of the same preset collection strategy are independent of each other and can be set according to actual needs. The characteristic value intervals of the same type of user behavior data for different preset collection strategies can be repeated. This embodiment does not limit the numerical values ​​of the same type of characteristic value intervals of different preset collection strategies to be staggered, and can be set according to actual needs.

[0065] Exemplarily, Strategy 1, Strategy 2, Strategy 3 and Strategy 4 respectively include characteristic value intervals corresponding to n first behavior data. After constructing the user portrait, the first characteristic value 1 falls into the characteristic value interval 1 of each strategy, the first characteristic value 2 falls into the characteristic value interval 2 of Strategy 1, Strategy 2 and Strategy 3, and does not fall into the characteristic value interval 2 of Strategy 4. In this way, Strategy 4 is excluded, and so on. The strategies whose n first characteristic values ​​all fall into the corresponding characteristic value intervals are put into the first strategy set.

[0066] It should be noted that the first behavior data is generated based on user behavior, so the user portrait is based on user behavior and can characterize the user's payment ability and payment intention to a certain extent. However, the scenario in which the user generates a first behavior data may be different. For example, if the property management personnel prevent the user from making illegal renovations and the property management personnel provide unreasonable services, the user may file a complaint in the property APP, thereby generating the first behavior data of complaining about the property. When constructing the user portrait, it can only be considered that the user has filed a complaint once, and the reason and scenario for filing the complaint cannot be determined. On this basis, this embodiment introduces the first arrears information. The first arrears information can be the reason for the user's arrears set by the property management personnel in the property APP. The first arrears information is added by the property management personnel for the target user, and the arrears reason can be used to characterize the arrears scenario. The first arrears information includes multiple first weight values, which are similar to the above-mentioned preset collection strategy. This embodiment only applies the first weight value corresponding to the first characteristic value.

[0067] It should be noted that the first characteristic value of the user portrait can characterize the user behavior. In this embodiment, the first characteristic value is updated to the second characteristic value according to the first weight value, so that the second strategy set matched by multiple second characteristic values ​​can characterize the user's payment intention in the arrears scenario. The method of matching the characteristic value interval based on the second characteristic value will not be repeated here.

[0068] It should be noted that the first weight value can correct the user portrait in the scenario of arrears. For instance, in the above example, the property management personnel preventing users from making illegal renovations and the property management personnel providing unreasonable services will both generate the first behavior data of complaining about the property. Based on the first behavior data, when the first arrears information is about illegal renovations, the corresponding first weight value is lower, and the first feature value corresponding to the complained property is reduced to obtain the second feature value, thereby weakening the consideration of the first behavior data when matching the second strategy set. Similarly, when the first arrears information is about unsatisfactory service, the first weight value is higher, and the consideration of the first behavior data is strengthened when matching the second strategy set.

[0069] It should be noted that the first policy set is the preset collection strategy corresponding to the user portrait, and the second policy set is the preset collection strategy corresponding to the user behavior in a specific scenario. This embodiment further determines the first target strategy in the intersection of the first policy set and the second policy set, so that the first target strategy can not only reflect the user portrait, but also meet the arrears scenario, thereby improving the reliability of the collection strategy.

[0070] For example, Figure 2 As shown, the first strategy set includes strategy 1, strategy 2 and strategy 3, the second strategy set includes strategy 2, strategy 3 and strategy 4, and the intersection of the first strategy set and the second strategy set includes strategy 2 and strategy 3. If strategy 1 is adopted, it does not meet the user scenario represented by the second characteristic value. For example, the first arrears information is an unsatisfactory service, and even if installment payment is provided, it will not improve user satisfaction. If strategy 4 is adopted, although it meets the user scenario, door-to-door collection does not meet the user portrait, so strategy 4 is not applicable. Strategy 2 and strategy 3 can meet both the user portrait and the user scenario, so you can choose one of strategy 2 and strategy 3 as the first target strategy.

[0071] In addition, in one embodiment, referring to Figure 3 Step S20 includes but is not limited to the following steps:

[0072] S21, determining one first behavior data as second behavior data, determining a plurality of first behavior data as third behavior data, and determining a corresponding magnification factor based on the number of each third behavior data, wherein the magnification factor is greater than 1;

[0073] S22, input all the first behavior data into the preset model to obtain the corresponding first eigenvalues, and generate a user portrait based on the first eigenvalues, wherein the first eigenvalue of the second behavior data is the initial eigenvalue output by the preset model, and the first eigenvalue of the third behavior data is the product of the initial eigenvalue and the amplification factor.

[0074] It should be noted that, according to the description of the above embodiment, the first behavior data may appear multiple times. For example, a user may initiate multiple complaints and deliberately default on payments if the complaints are not resolved. Therefore, the same first behavior data may appear multiple times in the first default period. In this embodiment, the repeated first behavior data is determined as the third behavior data, and the remaining data is determined as the second behavior data. Since the third behavior data appears multiple times, the amplification factor is used to amplify the first eigenvalue corresponding to the third behavior data when calculating the third behavior data, thereby enhancing the proportion of the third behavior data and making the user portrait more accurate.

[0075] It should be noted that the magnification factor can be determined according to the number of data in the third behavior, for example, the number of data 1 in the third behavior is 2, and the magnification factor is 1.1; for another example, the number of data 2 in the third behavior is 10, and the magnification factor is 2. The magnification factor can be proportional to the number of data in the third behavior, and the specific ratio is not limited here.

[0076] It should be noted that the preset model of this embodiment is an artificial intelligence model for constructing a user portrait. The specific model is not limited here, and the existing technology can be used. After the preset model outputs the initial eigenvalues ​​corresponding to each first behavior data, since the multiple first behavior data include second behavior data and third behavior data, for the initial eigenvalue corresponding to the third behavior data, the product of the initial eigenvalue and the amplification factor is used as the first eigenvalue, and for the second behavior data, the initial eigenvalue is directly applied as the first eigenvalue.

[0077] For example, Figure 2 As shown, among the n first behavior data, the number of first behavior data 1 is 3, corresponding to the amplification factor 1, the number of first behavior data 2 is 4, corresponding to the amplification factor 2, and the number of first behavior data 3 is 1, then the first behavior data 1 and the first behavior data 2 are the third behavior data, and the first behavior data 3 is the second behavior data. After all of them are input into the preset model, the initial eigenvalue 1 of the first behavior data 1, the initial eigenvalue 2 of the first behavior data 2, and the initial eigenvalue 3 of the first behavior data 3 are obtained. The first eigenvalue 1 corresponding to the first behavior data 1 is the product of the initial eigenvalue 1 and the amplification factor 1, the first eigenvalue 2 corresponding to the first behavior data 2 is the product of the initial eigenvalue 2 and the amplification factor 2, and the first eigenvalue 3 corresponding to the first behavior data 3 is the initial eigenvalue 3.

[0078] In addition, in one embodiment, referring to Figure 3 Step S30 includes but is not limited to the following steps:

[0079] S31, constructing a first visualization interface, and displaying a first overdue bill on the first visualization interface;

[0080] S32, in response to any first overdue bill being clicked, constructing a second visualization interface, displaying a first list and a second list on the second visualization interface, wherein the first list records the first behavior data, and the second list records a plurality of preset overdue information, each preset overdue information represents a different overdue scenario, and each preset overdue information is associated with its own first weight value;

[0081] S33, determining at least one optional arrears information in the second list, wherein each first behavior data is associated with at least one preset arrears information;

[0082] S34: Determine the optional arrears information selected in the second list as the first arrears information.

[0083] It should be noted that, according to the description of the above embodiment, the first arrears information is obtained by the property management personnel based on the target user selection. This embodiment constructs a first visual interface to display the first arrears bill, so that the property management personnel can check whether each user has any arrears. If the first arrears bill is displayed on the first visual interface, the user is the target user. If there is no first arrears bill, the current user is not an arrears user.

[0084] It should be noted that, although a target user can be associated with multiple first arrears bills, for example, one first arrears bill per month, and the property management fee has not been paid for multiple consecutive months, multiple first arrears bills are displayed in the first visualization interface. However, the first arrears information of the same target user is the same. If multiple first target strategies are generated based on the same target user, it will not improve the collection efficiency too much. In order to improve the collection efficiency of property management personnel, this embodiment generates only one first target strategy for each target user each time. Based on this, you can click on any first arrears bill in the first visualization interface to enter the second visualization interface, and configure the first arrears information in the second visualization interface.

[0085] It should be noted that the first list and the second list are displayed simultaneously in the second visualization interface. The property management personnel can use the first behavior data displayed in the first list as a basis for judgment and select the first arrears information from multiple preset arrears information displayed in the second list, thereby improving the reliability of the first arrears information.

[0086] It should be noted that the preset arrears information can be set according to actual needs, and this embodiment does not limit the specific options. For example Figure 2 As shown, the preset arrears information may include illegal renovation, unsatisfactory service, foreclosed property, lost contact with customers, and financial problems of the owner, etc. The arrears scenarios of each preset arrears information are different.

[0087] It should be noted that, in this embodiment, at least one preset arrears information is associated with each type of first behavior data. After reading all the first behavior data of the target user, the preset arrears information associated with the first behavior data is determined as optional arrears information. The optional arrears information can be set as optional items in the second list, and the remaining preset arrears information is not selectable. When there are many preset arrears information, it can eliminate unmatched options for property management personnel, thereby improving the accuracy of selecting the first arrears information.

[0088] For example, refer to Figure 2The first behavior data includes complaints about power outages, frequent power outages, window damage, and property management. Each first behavior data is associated with the preset arrears information of unsatisfactory service. Complaints about power outages and frequent power outages are also associated with illegal renovations. Therefore, unsatisfactory service and illegal renovations are identified as optional arrears information in the second list, and property management personnel can select the first arrears information from them. The remaining foreclosed houses, lost contact customers, and owners' economic problems are not identified as optional arrears information, and property management personnel cannot select the above options from the second list, effectively avoiding the mistaken selection of the first arrears information.

[0089] In addition, in one embodiment, referring to Figure 3 Step S50 includes but is not limited to the following steps:

[0090] S51, determining the intersection of the first policy set and the second policy set as a target policy set;

[0091] S52, when the target strategy set is an empty set, determining each preset collection strategy of the second strategy set as a candidate collection strategy;

[0092] S53, when the target policy set is not an empty set, determining the preset collection policy of the target policy set as the candidate collection policy;

[0093] S54, when there are multiple candidate collection strategies, the second characteristic value with the largest value is determined as the first reference value, the characteristic value interval with the smallest value range corresponding to the first reference value is determined as the first reference interval, and the candidate collection strategy corresponding to the first reference interval is determined as the first target strategy.

[0094] It should be noted that, since the second eigenvalue is obtained by correcting the first weight value based on the first eigenvalue, the second policy set can reflect the user profile to a certain extent. After determining the target policy set, when the target policy set is an empty set, no preset collection policy can simultaneously meet the user profile and the arrears scenario. In this embodiment, each preset collection policy of the second policy set is determined as a candidate collection policy. When the target policy set is not an empty set, all preset collection policies in the target policy set are determined as candidate collection policies.

[0095] It should be noted that after determining the candidate collection strategies, if there is only one, it will be directly determined as the first target strategy, and no further details will be given here.

[0096] It should be noted that, in the present embodiment, each preset collection strategy corresponds to a plurality of characteristic value intervals, each characteristic value interval corresponds to a first characteristic value or a second characteristic value, and the characteristic value interval of the candidate collection strategy can satisfy the first characteristic value and the second characteristic value at the same time. According to the above description, the second characteristic value is obtained based on the correction of the first characteristic value. In the present embodiment, the second characteristic value with the largest value is used as the first reference value, and the first reference value is used to characterize the feature with the highest weight in the arrears scenario. The first reference value corresponds to a class of first behavior data. If there are m candidate collection strategies (m is a positive integer greater than 1), the first reference value corresponds to m characteristic value intervals. The smaller the characteristic value interval hit by the first reference value, the higher the possibility of accurate matching. The larger the numerical range of the characteristic value interval, the more likely it is that the match is successful due to a large numerical value. Therefore, in the present embodiment, the characteristic value interval with the smallest numerical range is used as the first reference interval, and the candidate collection strategy corresponding to the first reference interval is determined as the first target strategy, thereby effectively improving the reliability of the first target strategy.

[0097] In addition, in one embodiment, referring to Figure 3 After executing step S50, the method further includes but is not limited to the following steps:

[0098] S61, obtaining first feedback information generated based on the first target strategy;

[0099] S62, when the first feedback information is used to indicate that all first overdue bills have been paid, maintaining the current first weight value of the first overdue bill information;

[0100] S63: When the first feedback information is used to indicate that at least one first overdue bill has not been paid, determine a second target strategy from the target strategy set.

[0101] It should be noted that after determining the first target strategy, the present embodiment obtains the first feedback information generated based on the first target strategy, and the first feedback information is used to characterize the collection effect of the first target strategy. The first feedback information can be set by the property management personnel in the property APP. For example, each first arrears bill and a submit button are displayed in the property APP. The property management personnel can directly click the submit button to generate the first feedback information. At this time, the first feedback information does not carry the first arrears bill, so it can be determined that no first arrears bill has been paid. It is also possible to select at least one first arrears bill and click the submit button, so that the first feedback information carries at least one first arrears bill to characterize that some or all of the first arrears bills have been paid. Of course, the payment status of the first arrears bill can also be automatically refreshed within a preset period, and the first feedback information can be automatically constructed according to the payment status. It is sufficient to determine the payment status of each first arrears bill through the first feedback information.

[0102] It should be noted that, in step S62, if all the first outstanding bills have been paid, it can be determined that the collection effect of the first target strategy is good, and the first target strategy generated this time is correct, and the first weight value currently corresponding to the first outstanding information is maintained, so that the next time it is applied, an accurate target strategy can still be generated. In step S63, when at least one first outstanding bill has not been paid, based on the fact that the first target strategy failed to make the target user pay all the first outstanding bills, it is necessary to further determine the second target strategy to continue collecting.

[0103] For example, when determining the second target strategy, the first arrears period can be reconstructed based on the first arrears bill that has not been paid, and the technical solution of the above embodiment is re-executed in the new first arrears period to determine the second target strategy. At this time, the second target strategy can be the same as the first target strategy. For example, the first target strategy is Figure 2 In the strategy 2 "discount incentive" shown, the target user determines that paying part of the first overdue bill can maximize the discount, so part of the first overdue bill is not paid. After the same strategy 2 is adopted again, the user completes the payment of the remaining bill.

[0104] It should be noted that when determining the second target strategy, if there are remaining candidate confiscation strategies in the target strategy set, the remaining candidate confiscation strategies can also be used as the second target strategy to improve the confiscation efficiency by changing the strategy. For example, the first target strategy is strategy 2, and the second target strategy is strategy 3, and different methods are used to execute confiscation.

[0105] In addition, in one embodiment, referring to Figure 3 When the first feedback information is used to indicate that at least one first overdue bill has not been paid, and at least one first overdue bill has been paid, step S63 includes but is not limited to the following steps:

[0106] S631, determining the first outstanding bill that has not been paid as a second outstanding bill, and determining a second outstanding period based on the second outstanding bill;

[0107] S632, obtaining second arrears information based on the input of the target user, wherein the second arrears information is used to characterize an arrears scenario of a second arrears period, and determining a plurality of preset weight values ​​associated with the second arrears information as a second weight value;

[0108] S633: Update each first feature value to a third feature value based on the corresponding second weight value, and determine a second target strategy based on the plurality of third feature values.

[0109] It should be noted that, in the case where part of the first outstanding bill is paid, the construction and application of the first target strategy is used as the first collection event of the target user, the first outstanding bill that has not been paid is determined as the second outstanding bill, and the second collection event of the target user is constructed based on the second outstanding bill. The method of re-determining the second target strategy based on the second outstanding bill, the second outstanding period and the second outstanding information can refer to the description of the first target strategy in the above embodiment, which will not be repeated here. Referring to the description of the above step S63, the second target strategy and the first target strategy can be the same or different, which will not be repeated here.

[0110] It should be noted that the root causes of different first arrears bills generated by the target user may be different. For example, the first few first arrears bills were due to insufficient balance, and the latter few bills were due to foreclosure and could not be paid. This embodiment divides the collection operation of the target user into at least two times. Of course, when the second target strategy has not completed all collections, the third target strategy can be further determined in the same way. Through the technical solution of this embodiment, different preset collection strategies can be used to collect progressively from the target user, and the strategy can be flexibly adjusted according to the actual arrears scenario of the target user to improve the collection strategy.

[0111] It should be noted that the second arrears information may be different from the first arrears information, for example Figure 2 As shown, the first arrears information is unsatisfactory service, and the second arrears information may be the owner's economic problem. The target user can only pay a number of first arrears bills under the preferential incentive of strategy 2, and the remaining second arrears bills cannot be paid due to insufficient balance. Since the user portrait is unchanged, this embodiment does not regenerate the user portrait when generating the strategy in a progressive manner, but based on the first eigenvalue of the user portrait, a new correction is made to the first eigenvalue through a new second weight value. For example, if the second arrears information selects the owner's economic problem, the second weight value corresponding to the same type of first behavior data is different from the first weight value, so that the third eigenvalue is different from the second eigenvalue, thereby matching different third strategy sets, and determining the second target strategy using the intersection of the first strategy set and the third strategy set.

[0112] For example, Figure 2 As shown, the first target strategy is preferential incentives. Taking the second overdue payment information as the owner's economic problem as an example, the third strategy set calculated based on the second weight value includes strategy 1 and strategy 4. After taking the intersection with the first strategy set, the second target strategy is strategy 1 "installment payment", which processes the remaining first overdue bills of the same target user in installments, so that the second target strategy can solve the owner's economic problem in the overdue payment scenario.

[0113] It is worth noting that after determining the second target strategy, the same judgment operation can be performed after obtaining new first feedback information until all first overdue bills are paid, which will not be repeated later.

[0114] In addition, in one embodiment, referring to Figure 3 When the first feedback information is used to indicate that all first overdue bills have not been paid, step S63 includes but is not limited to the following steps:

[0115] S634, removing the first target policy from the target policy set;

[0116] S635, when there are multiple candidate collection strategies remaining in the target strategy set, determine the second characteristic value that is only smaller than the first reference value as the second reference value, determine the characteristic value interval with the smallest value range among the characteristic value intervals corresponding to the second reference value as the second reference interval, and determine the candidate collection strategy corresponding to the second reference interval as the second target strategy;

[0117] S636, obtaining second feedback information generated based on the second target strategy;

[0118] S637, when the second feedback information is used to indicate that all first overdue bills have been paid, the preset weight value corresponding to the first overdue bill information of the second reference value is increased based on the preset step value, and the preset weight value corresponding to the first overdue bill information of the first reference value is reduced based on the step value.

[0119] It should be noted that the first target strategy is determined from multiple candidate collection strategies based on the first reference value. Therefore, the first target strategy is not absolutely applicable. When the first feedback information indicates that all first overdue bills have not been paid, it can be determined that the first target strategy is not applicable to the target user, and the second target strategy needs to be determined from the target strategy set. Since no first overdue bills have been paid, there is no need to rebuild the user portrait and the second strategy set. The first target strategy can be directly removed from the target strategy set, and the second target strategy can be determined from the remaining candidate collection strategies.

[0120] It should be noted that when there is one candidate collection strategy left in the target strategy set, such as Figure 2 As shown, after removing strategy 2, strategy 3 remains, and strategy 3 can be directly used as the second target strategy.

[0121] It should be noted that when there are multiple candidate collection strategies remaining in the target strategy set, this embodiment further determines a second reference value from multiple second characteristic values, and the second reference value is the second characteristic value with the second largest value, that is, the second reference value is only smaller than the first reference value. If the values ​​of multiple second characteristic values ​​are relatively close, it is very likely that any one of them is the main root cause of the arrears. This embodiment determines the second characteristic values ​​from large to small as reference values ​​to determine the target strategy, which can realize the traversal of candidate collection strategies. For example, after determining the second target strategy according to the second reference value, when the second target strategy is still not applicable, the second target strategy is removed from the target strategy set, and the third reference value is determined by the same principle to determine the third target strategy, and so on until the target strategy set is cleared or the first arrears information is fully paid. If the second feedback information based on the second target strategy feedback indicates that part of the first arrears information has been paid, the next target strategy can also be determined by the method of steps S631 to S633, which will not be repeated here.

[0122] It should be noted that when the second feedback information indicates that all first overdue bills have been paid, it can be determined that the first target strategy is inaccurate and the second target strategy is an accurate strategy. The difference between the first target strategy and the second target strategy lies in the corresponding second characteristic value. Each second characteristic value corresponds to a preset weight value associated with a first characteristic value and the first overdue information. Therefore, in the scenario corresponding to the first overdue information, the preset weight value corresponding to the first reference value is too large, and the preset weight value corresponding to the second reference value is small. This embodiment reduces the preset weight value corresponding to the first reference value based on the preset step value, and increases the preset weight value corresponding to the second reference value, thereby realizing the adjustment of the preset model, and the first weight value corresponding to the first overdue information is automatically iteratively updated to improve the accuracy of strategy generation. The value of the step value can be set according to actual needs, and no further restrictions are made here.

[0123] For example, Figure 2 As shown, the first reference value corresponds to the second characteristic value 1, and the second reference value corresponds to the second characteristic value 2. The first reference value corresponds to the first characteristic value 1 and the first weight value 1, and the second reference value corresponds to the first characteristic value 2 and the first weight value 2. When the first arrears information is "unsatisfactory service", the first weight value 2 is increased based on the step value, and the first weight value 1 is decreased. When determining the first target strategy for the next target user based on the first arrears information, the updated first weight value 1 and first weight value 2 are used.

[0124] like Figure 4 As shown, Figure 4 The present invention also provides a system for generating a property fee collection strategy based on user portraits, including:

[0125] The processor 401 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0126] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the method for generating a property fee collection strategy based on user portraits in the embodiment of this application;

[0127] Input / output interface 403, used to implement information input and output;

[0128] Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0129] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0130] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0131] An embodiment of the present application also provides an electronic device, including the property fee collection strategy generation system based on user portrait as described above.

[0132] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for generating a property fee collection strategy based on user portrait is implemented.

[0133] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are implemented to be located in one place, or may also be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0134] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media generally include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0135] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions under the shared conditions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for generating a property fee collection strategy based on user portrait, characterized in that: include: Selecting a target user from multiple delinquent users, determining a first delinquency period based on a first delinquent bill of the target user, and acquiring multiple types of first behavior data generated by the target user in the first delinquent period; Generate a user profile based on multiple categories of the first behavior data, and match a first strategy set from multiple preset confiscation strategies based on the user profile, wherein the user profile includes multiple first feature values, each of which corresponds to a category of the first behavior data, and the preset confiscation strategy is associated with multiple feature value intervals, each of which corresponds to a category of the first behavior data; Acquire first arrears information pre-associated with the target user, and determine multiple preset weight values ​​associated with the first arrears information as a first weight value, wherein the first arrears information is used to characterize an arrears scenario of the first arrears period, and each of the preset weight values ​​corresponds to one of the first feature values; updating each of the first characteristic values ​​to a second characteristic value based on the corresponding first weight value, and matching a second strategy set from a plurality of preset collection strategies based on a plurality of the second characteristic values; A first target policy is determined based on an intersection of the first policy set and the second policy set.

2. The method for generating a property fee collection strategy based on user portrait according to claim 1, characterized in that: Generating a user profile based on multiple types of the first behavior data includes: Determine one of the first behavior data as second behavior data, determine multiple of the first behavior data as third behavior data, and determine the corresponding magnification coefficients based on the numbers of the third behavior data, wherein the magnification coefficients are greater than 1; Input all of the first behavior data into the preset model to obtain the first eigenvalues ​​corresponding to each of them, and generate the user portrait based on the first eigenvalues, wherein the first eigenvalue of the second behavior data is the initial eigenvalue output by the preset model, and the first eigenvalue of the third behavior data is the product of the initial eigenvalue and the amplification factor.

3. The method for generating a property fee collection strategy based on user portrait according to claim 1 is characterized in that: Acquiring first arrears information pre-associated with the target user, including: Constructing a first visualization interface, and displaying the first overdue bill on the first visualization interface; In response to any of the first overdue bills being clicked, a second visualization interface is constructed, and a first list and a second list are displayed on the second visualization interface, wherein the first list records the first behavior data, and the second list records a plurality of preset overdue information, each of the preset overdue information represents a different overdue scenario, and each of the preset overdue information is associated with its own first weight value; Determining at least one optional arrears information in the second list, wherein each of the first behavior data is associated with at least one of the preset arrears information; The optional arrears information selected from the second list is determined as the first arrears information.

4. The method for generating a property fee collection strategy based on user portrait according to claim 1, characterized in that: Determining a first target policy based on an intersection of the first policy set and the second policy set includes: Determine the intersection of the first policy set and the second policy set as a target policy set; When the target strategy set is an empty set, determining each of the preset collection strategies of the second strategy set as a candidate collection strategy; Alternatively, when the target strategy set is not an empty set, determining the preset collection strategy of the target strategy set as the candidate collection strategy; When there are multiple candidate collection strategies, the second characteristic value with the largest value is determined as the first reference value, the characteristic value interval with the smallest value range corresponding to the first reference value is determined as the first reference interval, and the candidate collection strategy corresponding to the first reference interval is determined as the first target strategy.

5. The method for generating a property fee collection strategy based on user portrait according to claim 4 is characterized in that: After determining a first target policy based on an intersection of the first policy set and the second policy set, the method further includes: Acquire first feedback information generated based on the first target strategy; When the first feedback information is used to indicate that all the first overdue bills have been paid, maintaining the current first weight value of the first overdue bill information; When the first feedback information is used to indicate that at least one of the first overdue bills has not been paid, a second target strategy is determined from the target strategy set.

6. The method for generating a property fee collection strategy based on user portrait according to claim 5, characterized in that: When the first feedback information is used to indicate that at least one of the first overdue bills has not been paid, and at least one of the first overdue bills has been paid, determining a second target strategy from the target strategy set includes: determining the first outstanding bill that has not been paid as a second outstanding bill, and determining a second outstanding period based on the second outstanding bill; Acquire second arrears information based on the input of the target user, wherein the second arrears information is used to characterize an arrears scenario of the second arrears period, and determine the plurality of preset weight values ​​associated with the second arrears information as a second weight value; Each of the first feature values ​​is updated to a third feature value based on the corresponding second weight value, and the second target strategy is determined based on the plurality of the third feature values.

7. The method for generating a property fee collection strategy based on user portrait according to claim 5, characterized in that: When the first feedback information is used to indicate that all the first overdue bills have not been paid, determining a second target strategy from the target strategy set includes: removing the first target policy from the target policy set; When there are multiple candidate collection strategies remaining in the target strategy set, the second characteristic value that is only smaller than the first reference value is determined as the second reference value, the characteristic value interval with the smallest value range among the characteristic value intervals corresponding to the second reference value is determined as the second reference interval, and the candidate collection strategy corresponding to the second reference interval is determined as the second target strategy; Acquire second feedback information generated based on the second target strategy; When the second feedback information is used to represent that all the first overdue bills have been paid, the preset weight value corresponding to the second reference value in the first overdue information is increased based on the preset step value, and the preset weight value corresponding to the first reference value in the first overdue information is reduced based on the step value.

8. A property fee collection strategy generation system based on user portrait, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the method for generating a property fee collection strategy based on user portrait as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: Including the property fee collection strategy generation system based on user portrait as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method for generating a property fee collection strategy based on user portraits as described in any one of claims 1 to 7.

Images