Population screening methods, devices, equipment and storage media

By obtaining and calculating the portrait data of the objects to be screened, and filtering according to preset filter rules and indicators, the problem of changes in screening rules in complex business systems is solved, and a group screening scheme with strong adaptability and scalability is realized, which improves the system's Maintainability.

CN111753186BActive Publication Date: 2024-11-15HANGZHOU SHUPAO TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010387855.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-05-09
Publication Date
2024-11-15
Estimated Expiration
2040-11-15

AI Technical Summary

Technical Problem

The prior art is difficult to adapt to the changes in the screening rules of dynamically changing data in complex business systems, cannot meet the needs of multi-level nested complex screening, and the system is poor maintainability.

Method used

A group filtering method is proposed. By obtaining the portrait data of the objects to be screened, calculating according to preset filtering rules and indicators, the acquisition of target filtering groups is achieved, the changes in topic indicators and dimension attributes are supported, and the user can modify the filtering rules are supported in real time. Send the calculation engine to perform calculations.

Benefits of technology

It realizes a general big data group screening solution, has good scalability, meets the needs of complex screening and computing, and improves the maintainability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111753186B_ABST
    Figure CN111753186B_ABST
Patent Text Reader

Abstract

The present application proposes a group screening method, device, equipment and storage medium, wherein the method includes: obtaining the portrait data of the object to be screened; obtaining the target portrait data matching the preset screening rules from the portrait data; performing calculations based on the target portrait data and the preset screening indicators, and obtaining the target screening group from the object to be screened based on the calculation results. Thus, a general big data group screening solution is provided, which can adapt to the changes of subject indicators and dimensional attributes, has good scalability, and can meet complex screening calculation requirements.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a population screening method, device, equipment and storage medium. Background Art

[0002] Recommending suitable items to users based on historical behavior information such as user access records and access frequency and item attributes can effectively improve user experience. However, user-item recommendation systems usually have the problem of cold start, that is, the problem of inaccurate recommendation results. Rule-based item recommendation is a method that can solve the cold start problem, and the core of rule-based recommendation is group definition and screening.

[0003] At present, in response to the dynamically changing data generated by complex business systems, a group screening solution is needed that can adapt to changes in screening rules and meet the multi-level nested complex screening needs of the business. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a group screening method to implement a universal big data group screening solution that can adapt to changes in screening rules and meet complex screening calculation requirements.

[0006] The second object of the present application is to provide a group screening device.

[0007] The third objective of the present application is to provide a computer device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] The first embodiment of the present application proposes a population screening method, comprising:

[0010] Obtain the portrait data of the object to be screened;

[0011] Acquire target portrait data matching a preset screening rule from the portrait data;

[0012] Calculation is performed based on the target portrait data and preset screening indicators, and a target screening group is obtained from the object to be screened based on the calculation result.

[0013] The group screening method of the embodiment of the present application obtains the portrait data of the object to be screened; obtains the target portrait data that matches the preset screening rules from the portrait data; performs calculations based on the target portrait data and the preset screening indicators, and obtains the target screening group from the object to be screened based on the calculation results. Thus, a general big data group screening solution is realized, which can adapt to the changes in subject indicators and dimensional attributes and has good scalability. For example, it can support the addition of user / item attributes / indicators, or support users to modify screening rules. If the screening rules change, the calculation engine can be sent to perform calculations in real time, which can meet complex screening calculation requirements and improve system maintainability.

[0014] In addition, the population screening method according to the above embodiment of the present application may also have the following additional technical features:

[0015] Optionally, obtaining target portrait data that matches preset screening rules from the portrait data includes: obtaining preset object dimensions and object attributes; determining object attribute values ​​that match the object dimensions and object attributes from the portrait data, so as to determine the object attribute values ​​as target portrait data.

[0016] Optionally, obtaining target portrait data that matches preset screening rules from the portrait data includes: obtaining preset model topics and model indicators; determining a model indicator value that matches the model topic and model indicators from the portrait data, so as to determine the model indicator value as the target portrait data, wherein the model indicator value is calculated based on the factual data of the object according to preset rules.

[0017] Optionally, the calculation based on the target portrait data and the preset filtering indicators includes: calculating the target portrait data and the preset filtering indicators through a user-defined function; if the target portrait data meets the preset filtering indicators, the return value is true; if the target portrait data does not meet the preset filtering indicators, the return value is false; wherein the user-defined function is Z=UDF(X, Y), X is the preset filtering indicator, Y is the target portrait data, and Z is the return value.

[0018] Optionally, there are multiple screening indicators, and obtaining a target screening group from the objects to be screened based on the calculation results includes: obtaining multiple calculation results corresponding to each object in the objects to be screened, the multiple calculation results corresponding to multiple screening indicators; if the multiple calculation results corresponding to the current object are all true, it is determined that the current object belongs to the target screening group.

[0019] The second embodiment of the present application provides a group screening device, comprising:

[0020] An acquisition module is used to obtain the portrait data of the object to be screened;

[0021] A matching module, used to obtain target portrait data matching a preset screening rule from the portrait data;

[0022] The screening module is used to perform calculations based on the target portrait data and preset screening indicators, and obtain a target screening group from the object to be screened based on the calculation results.

[0023] The group screening device of the embodiment of the present application obtains the portrait data of the object to be screened; obtains the target portrait data that matches the preset screening rules from the portrait data; performs calculations based on the target portrait data and the preset screening indicators, and obtains the target screening group from the object to be screened based on the calculation results. Thus, a general big data group screening solution is realized, which can adapt to the changes in subject indicators and dimensional attributes, and has good scalability. For example, it can support the addition of user / item attributes / indicators, or support users to modify screening rules. If the screening rules are changed, the calculation engine can be sent to perform calculations in real time, which can meet complex screening calculation requirements and improve system maintainability.

[0024] In addition, the group screening device according to the above embodiment of the present application may also have the following additional technical features:

[0025] Optionally, the matching module is specifically used to: obtain preset object dimensions and object attributes; determine object attribute values ​​that match the object dimensions and object attributes from the portrait data, so as to determine the object attribute values ​​as target portrait data.

[0026] Optionally, the matching module is specifically used to: obtain preset model topics and model indicators; determine a model indicator value that matches the model topic and model indicators from the portrait data, so as to determine the model indicator value as the target portrait data, wherein the model indicator value is calculated based on the factual data of the object according to preset rules.

[0027] Optionally, the screening module includes: a calculation unit, used to calculate the target portrait data and the preset screening index through a user-defined function; if the target portrait data meets the preset screening index, the return value is true; if the target portrait data does not meet the preset screening index, the return value is false; wherein the custom function is Z=UDF(X, Y), X is the preset screening index, Y is the target portrait data, and Z is the return value.

[0028] Optionally, the screening module also includes: a screening unit, used to obtain multiple calculation results corresponding to each object in the objects to be screened, and the multiple calculation results correspond to multiple screening indicators; if the multiple calculation results corresponding to the current object are all true, it is determined that the current object belongs to the target screening group.

[0029] The third aspect embodiment of the present application proposes a computer device, including a processor and a memory; wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the population screening method as described in the first aspect embodiment.

[0030] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the population screening method as described in the first aspect of the application.

[0031] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a population screening method provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of the structure of a group screening device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] Embodiments of the present application are described in detail below, and examples of the embodiments 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 intended to be used to explain the present application, and should not be construed as limiting the present application.

[0035] The population screening method, device and equipment of the embodiments of the present application are described below with reference to the accompanying drawings.

[0036] Figure 1 A schematic diagram of a population screening method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0037] Step 101, obtaining the portrait data of the object to be screened.

[0038] The group screening method of the embodiment of the present application can be applied to a data warehouse. In this embodiment, when performing group screening, the portrait data of the object to be screened is first obtained. Optionally, the portrait data of the object to be screened is stored in the data warehouse.

[0039] As an example, the object to be screened may be a user, and the portrait data may include the user's name, age, gender, etc.

[0040] As another example, the object to be screened may be an object, and the portrait data may include the name, type, etc. of the object.

[0041] For example, an example of a user portrait data set P is as follows:

[0042] P=((0,USER,USER.AGE,28),

[0043] (1,USER,BEHAVIOR,PV,200),

[0044] (2, USER, USER.ACTIVITY, 'Participated in the Shanghai Auto Show'))

[0045] Among them, the user portrait data subset P contains three data. The first data corresponds to the serial number 0, indicating that the user's object attribute value under the object dimension USER and the object attribute AGE is 20, that is, the user's age is 20. The second data corresponds to the serial number 1, indicating that the user's model indicator value under the model theme BEHAVIOR and the model indicator PV is 200. The third data corresponds to the serial number 2, indicating that the user's object attribute value under the object dimension USER and the object attribute ACTIVITY is "participated in the Shanghai Auto Show event."

[0046] It should be noted that the above-mentioned portrait data is only an example. In actual applications, the portrait data usually includes all object attribute values ​​and model indicator values ​​of the user / item.

[0047] Step 102, obtaining target portrait data matching the preset screening rules from the portrait data.

[0048] In this embodiment, a screening rule for group screening can be pre-set, and the target portrait data participating in the calculation can be obtained from the portrait data according to the screening rule. For example, the screening rule corresponds to filtering out users older than 20 from all users, and it is known that the user age matches the screening rule, and the user age data is obtained from the portrait data of all users according to the screening rule as the target portrait data.

[0049] In order to explain the present application more clearly, the screening rules are explained below. The screening rules may include multiple sub-conditions, as shown below: R = COND op COND, where R represents the screening rule and COND is the sub-condition of the rule. For each sub-condition, as shown below: COND = [] op VALUE, ORDER, where [] represents a position parameter, and the position parameter is used to use the target portrait data as input in the group screening calculation process. op represents an operator, and examples are as follows: op = {&&,||,==,>,<,≥,≤}. It should be noted that op includes but is not limited to logical operations, arithmetic operations, and custom operations. VALUE represents a value, and ORDER is a sequence value used for sorting, for example, increasing from 0.

[0050] As an example, the filtering rule is: (USER.AGE>20,0)&&(USER.ACTIVITY='Participated in the Shanghai Auto Show',1), where (USER.AGE>20,0) and (USER.ACTIVITY='Participated in the Shanghai Auto Show',1) are two sub-conditions. The filtering rule means filtering users who are older than 20 and have participated in the Shanghai Auto Show.

[0051] As another example, the filtering rule is: (ITEM.TYPE = 'fine', 0) && (ITEM.NAME = 'car cigarette lighter', 1), where (ITEM.TYPE = 'fine', 0) and (ITEM.NAME = 'car cigarette lighter', 1) are two sub-conditions, and the filtering rule means filtering items with the type of "fine" and the name of "car cigarette lighter".

[0052] In one embodiment of the present application, portrait data involving object dimensions and object attributes may be stored in a data warehouse, and target portrait data matching preset screening rules may be obtained from the portrait data, including: obtaining preset object dimensions and object attributes, and determining object attribute values ​​matching the object dimensions and object attributes from the portrait data, so as to determine the object attribute values ​​as target portrait data.

[0053] As an example, the preset filtering rule includes a sub-condition (USER.AGE>20,0), the object dimension corresponding to the sub-condition is USER, and the object attribute is AGE, then the object attribute value 20 that matches the object dimension USER and the object attribute AGE is determined from the aforementioned set P as the target portrait data. It should be noted that if the filtering rule includes multiple sub-conditions, the corresponding object dimension and object attribute are determined for each sub-condition, and the object attribute value that matches the object dimension and object attribute corresponding to the current sub-condition is determined from the portrait data. Among them, the object dimension refers to a series of data entities related to the factual data, and the fact is used to describe the measurable values ​​generated by operational events in the real world.

[0054] In one embodiment of the present application, portrait data involving model themes and model indicators may be stored in a data warehouse, and target portrait data matching preset screening rules may be obtained from the portrait data, including: obtaining preset model themes and model indicators, determining model indicator values ​​matching the model themes and model indicators from the portrait data, and determining the model indicator values ​​as the target portrait data, wherein the model indicator values ​​are calculated based on the factual data of the object according to preset rules.

[0055] As an example, the preset screening rule includes sub-conditions (BEHAVIOR, PV>100, 0), then the model indicator value 200 matching the model subject BEHAVIOR and the model indicator PV is determined from the aforementioned set P as the target profile data. The model subject refers to a series of business-related data models designed according to the dimensional modeling method, and the model indicator is calculated from the fact data according to the preset rules.

[0056] Step 103, performing calculations based on the target portrait data and preset screening indicators, and obtaining a target screening group from the objects to be screened based on the calculation results.

[0057] In this embodiment, the screening index corresponding to the screening rule can be obtained according to the pre-set screening rule, and then, after obtaining the target portrait data matching the screening rule, the target portrait data and the screening index are calculated to obtain the calculation result. Optionally, if the screening rule includes multiple sub-conditions, there are multiple screening indicators corresponding to the screening rule, wherein each sub-condition corresponds to a screening indicator.

[0058] In one embodiment of the present application, the target portrait data and the preset screening index are calculated by a user-defined function, and if the target portrait data meets the preset screening index, the return value is true; if the target portrait data does not meet the preset screening index, the return value is false. The user-defined function is developed based on the expression calculation engine.

[0059] As a possible implementation method, the custom function is Z=UDF(X, Y), where X is the preset screening index, Y is the target portrait data, and Z is the return value. For example, the return value of UDF(USER.AGE>20,

[28] ) is true, and the return value of (USER.AGE>20,

[10] ) is false.

[0060] It should be noted that user-defined functions can return logical values, such as True or False, or they can return any expression, and the returned calculation result will be recorded as 0. There is no restriction here.

[0061] In one embodiment of the present application, there are multiple screening indicators, and a target screening group is obtained from the objects to be screened according to the calculation results, including: obtaining multiple calculation results corresponding to each object in the objects to be screened, the multiple calculation results corresponding to multiple screening indicators, if the multiple calculation results corresponding to the current object are all true, then it is determined that the current object meets the screening rules, that is, it belongs to the target screening group; otherwise, it is determined that the current object does not meet the screening rules, that is, it does not belong to the target screening group.

[0062] For example, if the filter object is a user, after obtaining the calculation results of all sub-conditions under the filter rule, the user groups are aggregated and sorted according to the sequence values ​​of the sub-conditions. For each user, the final result of the filter rule is calculated based on the return value of the custom function, and the user is identified based on the final result to determine whether the user belongs to the target filter group. For example, the filter rule is (USER.AGE>20,0)&&(USER.ACTIVITY='Participated in the Shanghai Auto Show',1), for user A, the calculation result obtained by the custom function is [True, True], then it is determined that user A belongs to the target filter group.

[0063] In the related art, vector matrix is ​​used to store user and item attributes, and the vector must have a fixed structure and clear values. For example, the user vector U and the item vector I are as follows: U = (USER, AGE, HEIGHT, ACTIVITY), I = (ITEM, TYPE, PRICE, NAME). When performing group screening, for example, for users who are over 20 years old and have participated in the Shanghai Auto Show, the recommended items are high-quality car cigarette lighters. The corresponding screening rules are (U.AGE>20&&U.ACTIVITY='Participated in the Shanghai Auto Show', I.TYPE='High-quality'&&I.NAME='Car cigarette lighter'). The above group screening solution has a fixed calculation method, which is difficult to adapt to the situation where the screening rules change during the application process, and cannot meet the needs of multi-level nested complex screening calculations in the business. Moreover, more than 50% of the logic is based on non-SQL (Structured Query Language) implementation, which has poor maintainability and high application threshold.

[0064] The group screening method of the embodiment of the present application obtains the portrait data of the object to be screened; obtains the target portrait data that matches the preset screening rules from the portrait data; performs calculations based on the target portrait data and the preset screening indicators, and obtains the target screening group from the object to be screened based on the calculation results. Thus, a general big data group screening solution is realized, which can adapt to the changes in subject indicators and dimensional attributes and has good scalability. For example, it can support the addition of user / item attributes / indicators, or support users to modify screening rules. If the screening rules change, the calculation engine can be sent to perform calculations in real time, which can meet complex screening calculation requirements and improve system maintainability.

[0065] The group screening method of the embodiment of the present application is described below in conjunction with the user-item recommendation scenario.

[0066] For users who are over 20 years old and have participated in the Shanghai Auto Show, when recommending high-quality car cigarette lighters, the filtering rules include (USER.AGE>20,0)&&(USER.ACTIVITY='Participated in the Shanghai Auto Show',1) and (ITEM.TYPE='High-quality',0)&&(ITEM.NAME='Car cigarette lighter',1). The portrait data of user USER is as follows: P=((0,USER,USER.AGE,28),(1,USER,BEHAVIOR,PV,200),(2,USER,USER.ACTIVITY,'Participated in the Shanghai Auto Show')), and the data partition involved in the calculation is determined according to the filtering rules P'=((0,USER,USER.AGE,28),(2,USER,USER.ACTIVITY,'Participated in the Shanghai Auto Show')).

[0067] The screening calculation process is as follows:

[0068] (0,UDF(USER.AGE>20,

[28] ))

[0069] (1,UDF(USER.ACTIVITY='Participated in Shanghai Auto Show',['Participated in Shanghai Auto Show']))

[0070] (A[0]&&A[1],[True,True])

[0071] If the expression returns a true result, it means that the user USER meets the group definition, thereby achieving the goal of obtaining the target user that meets the screening rules. Then, based on the same method, item screening is achieved to obtain the target items that meet the screening rules, and then the target items are recommended to the screened target users, thus achieving rule-based item recommendation.

[0072] In order to implement the above embodiments, the present application also proposes a group screening device.

[0073] Figure 2 A schematic diagram of the structure of a population screening device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the device includes: an acquisition module 10, a matching module 20, and a screening module 30.

[0074] Among them, the acquisition module 10 is used to obtain the portrait data of the object to be screened.

[0075] The matching module 20 is used to obtain target portrait data matching the preset screening rules from the portrait data.

[0076] The screening module 30 is used to perform calculations based on the target portrait data and preset screening indicators, and obtain a target screening group from the object to be screened based on the calculation results.

[0077] In one embodiment of the present application, the matching module 20 is specifically used to: obtain preset object dimensions and object attributes; determine object attribute values ​​that match the object dimensions and object attributes from the portrait data, so as to determine the object attribute values ​​as target portrait data.

[0078] In one embodiment of the present application, the matching module 20 is specifically used to: obtain preset model topics and model indicators; determine a model indicator value that matches the model topic and model indicators from the portrait data to determine the model indicator value as the target portrait data, and the model indicator value is calculated based on the factual data of the object according to preset rules.

[0079] In one embodiment of the present application, the screening module 30 includes: a calculation unit, used to calculate the target portrait data and the preset screening index through a user-defined function; if the target portrait data meets the preset screening index, the return value is true; if the target portrait data does not meet the preset screening index, the return value is false; wherein the custom function is Z=UDF(X, Y), X is the preset screening index, Y is the target portrait data, and Z is the return value.

[0080] Furthermore, the screening module 30 also includes: a screening unit, used to obtain multiple calculation results corresponding to each object in the objects to be screened, and the multiple calculation results correspond to multiple screening indicators; if the multiple calculation results corresponding to the current object are all true, it is determined that the current object belongs to the target screening group.

[0081] It should be noted that the explanation of the population screening method in the aforementioned embodiment is also applicable to the population screening device of this embodiment and will not be repeated here.

[0082] The group screening device of the embodiment of the present application obtains the portrait data of the object to be screened; obtains the target portrait data that matches the preset screening rules from the portrait data; performs calculations based on the target portrait data and the preset screening indicators, and obtains the target screening group from the object to be screened based on the calculation results. Thus, a general big data group screening solution is realized, which can adapt to the changes in subject indicators and dimensional attributes, and has good scalability. For example, it can support the addition of user / item attributes / indicators, or support users to modify screening rules. If the screening rules are changed, the calculation engine can be sent to perform calculations in real time, which can meet complex screening calculation requirements and improve system maintainability.

[0083] In order to implement the above embodiments, the present application also proposes a computer device, including a processor and a memory; wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the population screening method as described in any of the above embodiments.

[0084] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the population screening method as described in any of the above embodiments is implemented.

[0085] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0086] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0087] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0088] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0089] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0090] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0091] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0092] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for population screening, It is characterized in that include: Obtain the portrait data of the object to be screened; Acquire target portrait data matching a preset screening rule from the portrait data; Calculation is performed based on the target portrait data and preset screening indicators, and a target screening group is obtained from the object to be screened based on the calculation result; Wherein, obtaining target portrait data matching a preset screening rule from the portrait data includes: Get preset object dimensions and object properties; Determining an object attribute value matching the object dimension and the object attribute from the portrait data, so as to determine the object attribute value as target portrait data; If the screening rule includes multiple sub-conditions, the corresponding object dimension and object attribute are determined for each sub-condition, and the object attribute value matching the object dimension and object attribute corresponding to the current sub-condition is determined from the portrait data, and there are multiple screening indicators corresponding to the screening rule, wherein each sub-condition corresponds to one screening indicator, wherein the object dimension refers to a series of data entities related to factual data, and facts are used to describe measurable values ​​generated by operational events in the real world; The calculation according to the target portrait data and the preset screening index includes: Calculating the target portrait data and the preset screening index through a user-defined function; If the target portrait data meets the preset screening index, the return value is true; If the target portrait data does not meet the preset screening index, the return value is false; Among them, the custom function is Z=UDF(X, Y), X is the preset screening index, Y is the target portrait data, and Z is the return value.

2. The method according to claim 1, It is characterized in that The step of acquiring target portrait data matching a preset screening rule from the portrait data further includes: Get the preset model topics and model indicators; Determining a model indicator value that matches the model subject and the model indicator from the portrait data, so as to determine the model indicator value as the target portrait data; The model indicator value is calculated based on the actual data of the object according to preset rules.

3. The method according to claim 1, It is characterized in that There are multiple screening indicators, and obtaining a target screening group from the object to be screened according to the calculation results includes: Acquire multiple calculation results corresponding to each object in the objects to be screened, wherein the multiple calculation results correspond to multiple screening indicators; If the multiple calculation results corresponding to the current object are all true, it is determined that the current object belongs to the target screening group.

4. A group screening device, It is characterized in that include: An acquisition module is used to obtain the portrait data of the object to be screened; A matching module, used to obtain target portrait data matching a preset screening rule from the portrait data; A screening module, used to perform calculations based on the target portrait data and preset screening indicators, and obtain a target screening group from the object to be screened based on the calculation results; Wherein, the matching module is specifically used for: Get preset object dimensions and object properties; Determining an object attribute value matching the object dimension and the object attribute from the portrait data, so as to determine the object attribute value as target portrait data; If the screening rule includes multiple sub-conditions, the corresponding object dimension and object attribute are determined for each sub-condition, and the object attribute value matching the object dimension and object attribute corresponding to the current sub-condition is determined from the portrait data, and there are multiple screening indicators corresponding to the screening rule, wherein each sub-condition corresponds to one screening indicator, wherein the object dimension refers to a series of data entities related to factual data, and facts are used to describe measurable values ​​generated by operational events in the real world; The screening module comprises: A calculation unit, used for calculating the target portrait data and the preset screening index through a user-defined function; If the target portrait data meets the preset screening index, the return value is true; If the target portrait data does not meet the preset screening index, the return value is false; Among them, the custom function is Z=UDF(X, Y), X is the preset screening index, Y is the target portrait data, and Z is the return value.

5. The device as claimed in claim 4, It is characterized in that The matching module is specifically used for: Get the preset model topics and model indicators; A model indicator value matching the model subject and the model indicator is determined from the portrait data to determine the model indicator value as the target portrait data, wherein the model indicator value is calculated based on the factual data of the object according to preset rules.

6. The device according to claim 4, It is characterized in that The screening module also includes: A screening unit, used to obtain a plurality of calculation results corresponding to each object in the objects to be screened, wherein the plurality of calculation results correspond to a plurality of screening indicators; If the multiple calculation results corresponding to the current object are all true, it is determined that the current object belongs to the target screening group.

7. A computer device, It is characterized in that include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the population screening method as described in any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the population screening method as described in any one of claims 1 to 3 is implemented.