Business Object Extraction Method, Server, Business Terminal, and Storage Medium

Abstract

This specification relates to the field of artificial intelligence technology, and specifically discloses a business object extraction method, a server, a business terminal, and a storage medium. The method includes: receiving a business object extraction request sent by a business terminal, where the business object extraction request at least includes an object identifier set and extraction constraint conditions; based on the extraction constraint conditions, obtaining a specified business data subset corresponding to the corresponding object identifier from the business data set of any object identifier, so as to extract the specified object features of the corresponding object identifier based on the specified business data subset; using the business object extraction algorithm corresponding to the business type in the extraction constraint conditions to process the specified object features under each object identifier in the object identifier set, so as to screen out the potential object identifiers targeted by the corresponding business type; and feeding back the potential object identifiers to the business terminal, so that the business terminal performs resource allocation on the business objects corresponding to the potential object identifiers, thereby improving the efficiency and accuracy of resource allocation.

Description

Technical Field

[0001] This specification relates to the field of artificial intelligence technology, and in particular, to a method for extracting business objects, a server, a business terminal, and a storage medium. Background Art

[0002] At present, the types of online services that a business system can provide to users are increasing, and the volume of business data processed by the business system is extremely large. If the allocation of business resources is unreasonable, there may be a risk of a large amount of loss of business resources, which will cause greater losses to the enterprise. At present, the allocation of business resources mostly adopts the method of manual allocation, which consumes a high amount of labor costs. Therefore, how to more accurately and efficiently achieve the configuration of business resources has become a technical problem to be solved urgently in this field. Summary of the Invention

[0003] The purpose of the embodiments of this specification is to provide a method for extracting business objects, a server, a business terminal, and a storage medium, which can greatly improve the accuracy and efficiency of business resource allocation and reduce the risk of resource loss.

[0004] The method for extracting business objects, the server, the business terminal, and the storage medium provided in this specification are implemented in the following ways:

[0005] A method for extracting business objects, applied to a server, the method includes: receiving a business object extraction request sent by a business terminal, the business object extraction request at least including an object identifier set and an extraction constraint condition; wherein, the object identifier set refers to a set composed of multiple object identifiers, and the object identifier refers to information for identifying a business object; the extraction constraint condition at least includes the business type targeted by the business object extraction; based on the extraction constraint condition, obtaining a specified business data subset corresponding to the corresponding object identifier from the business data set of any one of the object identifiers, so as to extract a specified object feature of the corresponding object identifier based on the specified business data subset; using the business object extraction algorithm corresponding to the business type to process the specified object features under each object identifier in the object identifier set, so as to screen out potential object identifiers targeted by the business type; and feeding back the screened potential object identifiers to the business terminal, so that the business terminal performs resource allocation on the business objects corresponding to the potential object identifiers.

[0006] In other embodiments of the method provided in this specification, when the business type is the transfer out of business resources, the feature types of the specified object features at least include the business resource requirement feature and the business resource repayment feature of the business object.

[0007] In some other embodiments of the method provided in this specification, when obtaining the specified business data subset corresponding to the corresponding object identifier from the business data set of any of the object identifiers, it includes: for any object identifier in the object identifier set, obtaining the first specified business data subset of the corresponding object identifier under the business resource requirement characteristics from the business data set of the object identifier; and obtaining the second specified business data subset of the corresponding object identifier under the business resource repayment characteristics from the business data set of the object identifier.

[0008] In some other embodiments of the method provided in this specification, when extracting the specified object characteristics of the corresponding business object based on the specified business data subset, it includes: obtaining the first preset weight corresponding to each business data type in the first specified business data subset, where the first preset weight is used to represent the importance of the corresponding business data type when extracting the business resource requirement characteristics; and using the C5 decision tree algorithm to perform feature extraction on the first specified business data subset associated with the first preset weight to obtain the business resource requirement characteristics of the corresponding object identifier.

[0009] In some other embodiments of the method provided in this specification, when extracting the specified object characteristics of the corresponding business object based on the specified business data subset, it includes: obtaining the second preset weight corresponding to each business data type in the second specified business data subset, where the second preset weight is used to represent the importance of the corresponding business data type when extracting the business resource repayment characteristics; and using the C5 decision tree algorithm to perform feature extraction on the second specified business data subset associated with the second preset weight to obtain the business resource repayment characteristics of the corresponding object identifier.

[0010] In some other embodiments of the method provided in this specification, when processing the specified object characteristics under each object identifier in the object identifier set by using the business object extraction algorithm corresponding to the business type, it includes: using the C5 decision tree algorithm to process the specified object characteristics under each object identifier in the object identifier set.

[0011] On the other hand, this specification also provides a server, including: a request receiving module, configured to receive a service object extraction request sent by a service terminal, where the service object extraction request at least includes an object identifier set and an extraction constraint condition; wherein, the object identifier set refers to a set composed of multiple object identifiers, and the object identifier refers to information for identifying a service object; the extraction constraint condition at least includes the service type for which the service object extraction is targeted; a feature extraction module, configured to obtain a specified service data subset corresponding to a corresponding object identifier from the service data set of any one of the object identifiers based on the extraction constraint condition, so as to extract a specified object feature corresponding to the corresponding object identifier based on the specified service data subset; an object screening module, configured to process the specified object features under each object identifier in the object identifier set by using the service object extraction algorithm corresponding to the service type, so as to screen out potential object identifiers targeted by the service type; an information feedback module, configured to feedback the screened potential object identifiers to the service terminal, so that the service terminal performs service processing on the service objects corresponding to the potential object identifiers.

[0012] On the other hand, this specification also provides a service object extraction method, which is applied to a service terminal. The method includes: receiving an object identifier and an extraction constraint condition input on an object extraction configuration interface; wherein, the object identifier refers to information for identifying a service object; the extraction constraint condition at least includes the service type for which the service object extraction is targeted; when receiving an object extraction trigger instruction, sending a service object extraction request to a server, where the service object extraction request at least includes an object identifier set and the extraction constraint condition; wherein, the object identifier set refers to a set composed of the input object identifiers; so that the server obtains a specified service data subset corresponding to a corresponding object identifier from the service data set of any one of the object identifiers based on the extraction constraint condition, so as to extract a specified object feature corresponding to the corresponding object identifier based on the specified service data subset; processing the specified object features under each object identifier in the object identifier set by using the service object extraction algorithm corresponding to the service type, so as to screen out potential object identifiers targeted by the service type; and feedbacking the screened potential object identifiers to the service terminal; receiving the potential object identifiers feedbacked by the server, so as to perform resource allocation on the service objects corresponding to the potential object identifiers.

[0013] On the other hand, this specification also provides a service terminal, including: an input information receiving module, configured to receive an object identifier and extraction constraint conditions input in an object extraction configuration interface; wherein, the object identifier refers to information for identifying a service object; the extraction constraint conditions at least include the service type targeted by the service object extraction; a request sending module, configured to send a service object extraction request to a server when receiving an object extraction trigger instruction, the service object extraction request at least including an object identifier set and the extraction constraint conditions; wherein, the object identifier set refers to a set composed of the input object identifiers; so that the server, based on the extraction constraint conditions, obtains a specified service data subset corresponding to the corresponding object identifier from the service data set of any of the object identifiers, and extracts a specified object feature corresponding to the corresponding object identifier based on the specified service data subset; processes the specified object features under each object identifier in the object identifier set by using a service object extraction algorithm corresponding to the service type to filter out potential object identifiers targeted by the service type; and feeds back the filtered potential object identifiers to the service terminal; a service object receiving module, configured to receive the potential object identifiers fed back by the server to perform resource allocation on the service objects corresponding to the potential object identifiers.

[0014] On the other hand, this specification also provides a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed, the steps of the method described in any one or more of the above embodiments are implemented.

[0015] The service object extraction method, server, service terminal, and storage medium provided by one or more embodiments of this specification can, for the service type corresponding to a service scenario, based on pre-configured service data extraction requirements, object extraction algorithms, etc., filter out potential service objects corresponding to the corresponding service type, and then perform resource allocation in the corresponding service scenario for the potential service objects, thereby improving the efficiency and accuracy of service resource allocation and reducing the probability of resource loss in the service system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts. In the drawings:

[0017] Figure 1 It is a schematic diagram of an implementation process of a service object extraction provided by this specification;

[0018] Figure 2Schematic diagram of the processing flow for a scenario example of business object extraction provided in this specification;

[0019] Figure 3 Schematic diagram of the module structure of the user feature extraction device provided in this specification;

[0020] Figure 4 Schematic diagram of the module structure of the server in an embodiment provided in this specification. Detailed implementation manners

[0021] In order to enable those skilled in the art of this technology to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in one or more embodiments of this specification with reference to the accompanying drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of the specification, rather than all the embodiments. Based on one or more embodiments of the specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the embodiment solutions of this specification.

[0022] In a scenario example of this specification, the method can be applied to a business object extraction system, and the system can include a business terminal and at least one server. The business terminal may refer to a terminal device used by business personnel or an intelligent business terminal (such as a service robot, an intelligent counter, etc.). Based on the above scenario example, this specification also provides a business object extraction method. Figure 1 It is a schematic diagram of the process of the embodiment of the business object extraction method provided in this specification. As Figure 1 shown, the business object extraction method can be applied to the server. The method can include the following steps.

[0023] S20: Receive a business object extraction request sent by the business terminal. The business object extraction request includes at least an object identifier set and extraction constraint conditions; wherein, the object identifier set refers to a set composed of multiple object identifiers, and the object identifier refers to information for identifying a business object; the extraction constraint conditions include at least the business type for which the business object extraction is targeted.

[0024] The business object may refer to a user account targeted by the business. Of course, it may also be a user terminal used by the user, etc. The business object can be identified by an object identifier within the business system, and the object identifier can be, for example, a user account number, a user terminal identifier, etc.

[0025] The business terminal can receive the object identifier and extraction constraint conditions input by the business personnel on the object extraction request configuration interface. The extraction constraint conditions can at least include the business type targeted by the business object extraction, etc. And based on the extraction request of the business personnel, an operation is triggered to send a business object extraction request to the server. Correspondingly, the business object extraction request can at least include an object identifier set composed of the object identifiers input by the business personnel and the extraction constraint conditions. The extraction constraint conditions can also include the business data extraction requirements, object extraction algorithms, etc. based on which the business personnel configure the object extraction on the business terminal. Among them, the business data extraction requirements can, for example, include the business type, business data extraction method, business data extraction range, etc. When performing business object extraction for different business scenarios, the required business data and the object extraction algorithms used may vary greatly. By pre-configuring the above information, while reducing the data extraction volume, the accuracy of business object extraction corresponding to the corresponding business type can be greatly improved.

[0026] Alternatively, extraction parameters can also be pre-configured in the business terminal. The extraction parameters can, for example, include extraction constraint conditions, object identifier range requirements targeted by the object extraction, time period, etc. The extraction constraint conditions can include the business data extraction requirements, algorithms used for extraction, etc. corresponding to each business type pre-configured in the business terminal. The business terminal can regularly extract the corresponding object identifiers from the business system based on the pre-configured extraction parameters and send a business object extraction request to the server. Correspondingly, the business object extraction request can at least include an object identifier set composed of the object identifiers extracted by the business terminal and the extraction constraint conditions in the extraction parameters.

[0027] After receiving the business object extraction request, the server can parse the extraction request to parse out the object identifier set and extraction constraint conditions therein.

[0028] S22: Based on the extraction constraint conditions, obtain the specified business data subset corresponding to the corresponding object identifier from the business data set of any one of the object identifiers, so as to extract the specified object features of the corresponding object identifier based on the specified business data subset.

[0029] The business data corresponding to each object identifier in the business system is usually associated with the object identifier. The business data corresponding to any object identifier can be used as a business data set. The server can extract a specified business data subset of the corresponding object identifier from the business data set according to the extraction constraint conditions. The specified business data subset can include the business data types, business data ranges, or business data extracted by the business data extraction method defined in the extraction constraint conditions. Of course, if the extraction constraint conditions do not define the business data extraction requirements, the entire business data set corresponding to the object identifier can be used as the specified business data subset.

[0030] S24: Process the specified object features under each object identifier in the object identifier set by using the business object extraction algorithm corresponding to the business type, so as to screen out the potential object identifiers targeted by the business type.

[0031] The server can further extract the specified business features corresponding to the object identifier based on the specified business data subset of the object identifier. And process the specified business features of each object identifier by using the object extraction algorithm corresponding to the business type, so as to screen out the potential object identifiers of the business type. The object extraction algorithm can be pre-configured in the extraction constraint conditions or pre-configured in the server.

[0032] S26: Feed back the screened potential object identifiers to the business terminal, so that the business terminal performs resource allocation on the business objects corresponding to the potential object identifiers.

[0033] The server can feed back the screened potential object identifiers to the business terminal, so that the business terminal performs resource allocation on the business objects corresponding to the potential object identifiers. For example, the business terminal can allocate resources to the business objects corresponding to the potential object identifiers.

[0034] The solution provided in the above embodiments can screen out the potential business objects corresponding to the corresponding business type based on the pre-configured business data extraction requirements, object extraction algorithms, etc. for the business type corresponding to the business scenario. Then, perform resource allocation in the corresponding business scenario for the potential business object, thereby improving the efficiency and accuracy of business resource allocation and reducing the probability of resource loss in the business system.

[0035] In some embodiments, the business type can be the transfer of business resources. The business resources can be, for example, the digital form of physical currency, digital currency, virtual currency, etc. The transfer of business resources can be, for example, loans, investments, etc. When the business type is the transfer of business resources, the feature types of the specified object features preferably can at least include the business resource demand feature and the business resource repayment feature of the business object.

[0036] Based on the basic features extracted using these two types of features as objects, it can comprehensively reflect the resource requirements, urgency, etc. of business objects, as well as the repayment ability of business objects within a certain time interval. Screening potential business objects for the transfer of business resources based on these features can make resource allocation more balanced and reasonable, improve the user experience, and at the same time, can also minimize the possible losses caused by the transfer of business resources.

[0037] Correspondingly, for any object identifier in the object identifier set, the server can obtain a first specified business data subset of the corresponding object identifier under the business resource demand feature from the business dataset of the object identifier; and obtain a second specified business data subset of the corresponding object identifier under the business resource repayment feature from the business dataset of the object identifier. By extracting the corresponding business data for different feature types respectively, the accuracy of feature extraction can be further improved.

[0038] In some embodiments, the server can also obtain a first preset weight corresponding to each business data type in the first specified business data subset, where the first preset weight is used to represent the importance of the corresponding business data type when extracting the business resource demand feature; and use the C5 decision tree algorithm to perform feature extraction on the first specified business data subset associated with the first preset weight to obtain the business resource demand feature of the corresponding object identifier. And obtain a second preset weight corresponding to each business data type in the second specified business data subset, where the second preset weight is used to represent the importance of the corresponding business data type when extracting the business resource repayment feature; use the C5 decision tree algorithm to perform feature extraction on the second specified business data subset associated with the second preset weight to obtain the business resource repayment feature of the corresponding object identifier. The C5 decision tree algorithm can further adaptively adjust the importance of each business data type. Based on the C5 decision tree algorithm for extracting the business resource demand feature and the business resource repayment feature, the accuracy and efficiency of feature extraction can be further improved.

[0039] In some embodiments, the business resource demand feature and the business resource repayment feature can also be used as model input features for object screening, and the C5 decision tree algorithm is used to process the business resource demand feature and the business resource repayment feature under each object identifier in the object identifier set to obtain the screening result of potential object identifiers, further screening out potential high-quality customers with capital needs and repayment ability, thereby improving the rationality of resource allocation.

[0040] In a scenario example, Logstash can be used for data collection and processing. And elasticsearch can be used as a "database" to store the extracted specified business datasets.

[0041] Such asFigure 2 As shown in the figure, the server may include a data collection device 1, a log processing device 2, a public opinion data processing device 3, a user feature extraction device 4, a fund demand discrimination device 5, a repayment ability discrimination device 6, and a potential user screening device 7.

[0042] The data collection device 1 may be connected to the log processing device 2, the public opinion processing device 3, and the user feature extraction device 4. It uses logstash to collect user logs, public opinion data, user basic information, user account movement information, user collateral information, etc., and stores the collected data in elasticsearch.

[0043] The log processing device 2 may use the user logs collected by the data collection device 1 to extract feature data such as the user browsing credit products (such as Rong E Jie), querying credit reports, viewing credit card limit increase information, and performing credit card limit increase operations.

[0044] The public opinion processing device 3 may use information such as enterprise public opinion and social public opinion collected by the data collection device 1 to extract feature data such as enterprise positive public opinion (such as listing) and social public opinion (such as the warming of the housing market).

[0045] The user feature extraction device 4 may combine the user basic information, user account movement information, and user collateral information collected by the data collection device 1 to generate user feature data, and perform annotation processing on the user in combination with the feature public opinion data generated by the public opinion processing device 3. As Figure 3 shown in the figure, the user feature extraction device 4 may include a fund demand feature annotation unit 41 and a repayment ability feature annotation unit 42. The fund demand feature annotation unit 41 may generate a wide table of user fund demand features by combining dimensions such as user browsing credit product information, credit report query, credit card limit increase, and social public opinion. The repayment ability feature annotation unit 42 may generate a wide table of user repayment ability features by combining dimensions such as user basic situation, credit granting situation, bad situation, and collateral situation.

[0046] The fund requirement discrimination device 5 can use the C5 decision tree to construct a fund requirement feature model. Since the wide table of user fund requirement features generated by the user feature extraction device 4 usually cannot reflect the importance of each feature, before modeling, the features can be sorted according to their importance, and feature weights can be assigned according to the sorting results. The higher the sorting result, the greater the weight value. For example, if the features of fund requirement include three features: credit card limit increase, browsing credit products, and checking credit reports, and the sorting is: credit card limit increase > browsing credit products > checking credit reports, then the weights of these three features are 3, 2, and 1 respectively. For the data comparison before and after weight processing, please refer to Table 1 and Table 2. Among them, Table 1 is the user fund requirement feature data before weight processing. Table 2 is the user fund requirement feature data after weight processing. After weight processing, use the C5 decision tree to construct a fund requirement feature model and output the fund requirement discrimination result.

[0047] Table 1

[0048] Username Credit card limit increase Browse credit products Check credit report User A 1 0 1

[0049] Table 2

[0050] Username Credit card limit increase Browse credit products Check credit report User A 3 0 1

[0051] The repayment ability discrimination device 6 can use the C5 decision tree to construct a repayment ability feature model. Similar to the fund requirement discrimination device, before constructing the repayment ability feature model, weight processing is required according to the feature importance. After the processing is completed, use the C5 decision tree to construct a repayment ability feature model and output the repayment ability discrimination result.

[0052] The potential user screening device 7 can combine the output results of the fund requirement discrimination device 5 and the repayment ability discrimination device 6; regard the user's fund requirement and repayment ability as two new features, and use the C5 decision tree to construct a potential user feature model again, and finally screen out potential high-quality users who have fund requirements and repayment ability.

[0053] The solution provided by the above scenario example can automatically implement data collection, analysis, and potential user mining, greatly improving the efficiency of potential user mining. Using the C5 decision tree for potential user determination, the AUC value of the determination model is 0.7. Compared with the traditional method that relies on the experience of business personnel for determination, the screening accuracy is higher, which can further improve the rationality of loan resource allocation and reduce loan losses.

[0054] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key points of each embodiment are the differences from other embodiments. Specifically, reference can be made to the description of the relevant processing related embodiments above, and details will not be repeated here.

[0055] The above description has been made for specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0056] As Figure 4 shown, based on the business object extraction method described above, one or more embodiments of this specification further provide a server, including: a request receiving module 102, configured to receive a business object extraction request sent by a service terminal, where the business object extraction request at least includes an object identifier set and extraction constraint conditions; wherein, the object identifier set refers to a set composed of multiple object identifiers, and the object identifier refers to information for identifying a business object; the extraction constraint conditions at least include the business type for which the business object extraction is targeted. A feature extraction module 104, configured to obtain a specified business data subset corresponding to a corresponding object identifier from the business data set of any object identifier in the object identifier set based on the extraction constraint conditions, so as to extract a specified object feature corresponding to the corresponding object identifier based on the specified business data subset. An object screening module 106, configured to process the specified object features under each object identifier in the object identifier set by using the business object extraction algorithm corresponding to the business type, so as to screen out potential object identifiers targeted by the business type. An information feedback module 108, configured to feedback the screened potential object identifiers to the service terminal, so that the service terminal performs business processing on the business objects corresponding to the potential object identifiers.

[0057] Based on the business object extraction method described above, an embodiment of this specification further provides a business object extraction method, which is applied to a service terminal, and the method includes:

[0058] Receiving the object identifier and extraction constraint conditions input in the object extraction configuration interface; wherein, the object identifier refers to information for identifying a business object; the extraction constraint conditions at least include the business type for which the business object extraction is targeted;

[0059] Upon receiving an object extraction trigger instruction, send a service object extraction request to the server, where the service object extraction request includes at least an object identifier set and the extraction constraint conditions; wherein, the object identifier set refers to a set composed of the input object identifiers; so that the server, based on the extraction constraint conditions, obtains a corresponding specified service data subset of the corresponding object identifier from the service data set of any object identifier in the object identifier set, and extracts the specified object features of the corresponding object identifier based on the specified service data subset; use the service object extraction algorithm corresponding to the service type to process the specified object features under each object identifier in the object identifier set to filter out potential object identifiers targeted by the service type; and feedback the filtered potential object identifiers to the service terminal;

[0060] Receive the potential object identifiers fed back by the server to perform resource allocation on the service objects corresponding to the potential object identifiers.

[0061] Based on the above service object extraction method, an embodiment of this specification further provides a service terminal, including: an input information receiving module, configured to receive the object identifier and extraction constraint conditions input on the object extraction configuration interface; wherein, the object identifier refers to information for identifying a service object; the extraction constraint conditions include at least the service type targeted by the service object extraction. A request sending module, configured to send a service object extraction request to the server upon receiving an object extraction trigger instruction, where the service object extraction request includes at least an object identifier set and the extraction constraint conditions; wherein, the object identifier set refers to a set composed of the input object identifiers; so that the server, based on the extraction constraint conditions, obtains a corresponding specified service data subset of the corresponding object identifier from the service data set of any object identifier in the object identifier set, and extracts the specified object features of the corresponding object identifier based on the specified service data subset; use the service object extraction algorithm corresponding to the service type to process the specified object features under each object identifier in the object identifier set to filter out potential object identifiers targeted by the service type; and feedback the filtered potential object identifiers to the service terminal. A service object receiving module, configured to receive the potential object identifiers fed back by the server to perform resource allocation on the service objects corresponding to the potential object identifiers.

[0062] This specification also provides a computer-readable storage medium. When the instructions are executed, the steps of the method described in any one or more of the above embodiments are implemented. The storage medium may include a physical device for storing information, usually by digitizing the information and then storing it in a medium using electrical, magnetic, or optical means. The storage medium may include: devices that store information using electrical energy, such as various memories, such as RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memories, bubble memories, USB flash drives; devices that store information using optical means, such as CDs or DVDs. Of course, there are also other types of readable storage media, such as quantum memories, graphene memories, and so on.

[0063] It should be noted that the above-described device may also include other embodiments according to the description of the method or device embodiments. The specific implementation manner may refer to the description of the relevant method embodiments and will not be elaborated here one by one.

[0064] The embodiments of this specification are not limited to those that must conform to the standard data model / template or the situations described in the embodiments of this specification. Some industry standards or implementation schemes slightly modified on the basis of the implementation described by using custom methods or embodiments can also achieve the same, equivalent, or similar, or predictable implementation effects after deformation as the above embodiments. The embodiments obtained by applying these modified or deformed data acquisition, storage, determination, processing methods, etc. still fall within the scope of the optional implementation schemes of this specification.

[0065] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments. In the description of this specification, the description of reference terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0066] The above are only examples of this specification and are not intended to limit this specification. For those skilled in the art, various modifications and changes can be made to this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included within the scope of the claims of this specification.

Claims

1. A method for extracting business objects, characterized in that, Applied to a server, the method includes: Receiving a service object extraction request sent by a service terminal, where the service object extraction request includes at least an object identifier set and extraction constraint conditions; wherein, the object identifier set refers to a set composed of multiple object identifiers, and the object identifier refers to information for identifying a service object; the extraction constraint conditions include at least the service type for which the service object extraction is targeted; the extraction constraint conditions further include the service data extraction requirements and service object extraction algorithms based on which the service personnel configure on the service terminal during object extraction. Based on the extraction constraint conditions, obtaining a specified service data subset corresponding to the corresponding object identifier from the service data set of any one of the object identifiers, so as to extract the specified object features of the corresponding object identifier based on the specified service data subset. Using the service object extraction algorithm corresponding to the service type to process the specified object features under each object identifier in the object identifier set, so as to filter out the potential object identifiers targeted by the service type. Feeding back the filtered potential object identifiers to the service terminal, so that the service terminal performs resource allocation on the service objects corresponding to the potential object identifiers. Wherein, obtaining a specified service data subset corresponding to the corresponding object identifier from the service data set of any one of the object identifiers includes: For any object identifier in the object identifier set, obtaining a first specified service data subset corresponding to the corresponding object identifier under the service resource demand feature from the service data set of the object identifier; and obtaining a second specified service data subset corresponding to the corresponding object identifier under the service resource repayment feature from the service data set of the object identifier.

2. The method according to claim 1, characterized in that, In the case where the service type is service resource transfer out, the feature types of the specified object features include at least the service resource demand feature and service resource repayment feature of the service object.

3. The method according to claim 1, characterized in that, The extracting the specified object features of the corresponding service object based on the specified service data subset includes: Obtaining the first preset weight corresponding to each service data type in the first specified service data subset, where the first preset weight is used to represent the importance of the corresponding service data type when extracting the service resource demand feature. Using the C5 decision tree algorithm to perform feature extraction on the first specified service data subset associated with the first preset weight, to obtain the service resource demand feature of the corresponding object identifier.

4. The method according to claim 1, characterized in that, The extracting the specified object features of the corresponding service object based on the specified service data subset includes: Obtaining the second preset weight corresponding to each service data type in the second specified service data subset, where the second preset weight is used to represent the importance of the corresponding service data type when extracting the service resource repayment feature. Using the C5 decision tree algorithm to perform feature extraction on the second specified service data subset associated with the second preset weight, to obtain the service resource repayment feature of the corresponding object identifier.

5. The method according to claim 2, characterized in that, The using the service object extraction algorithm corresponding to the service type to process the specified object features under each object identifier in the object identifier set includes: Using the C5 decision tree algorithm to process the specified object features under each object identifier in the object identifier set.

6. A server, characterized in that, Including: A request receiving module, configured to receive a service object extraction request sent by a service terminal, where the service object extraction request at least includes an object identifier set and extraction constraint conditions; wherein, the object identifier set refers to a set composed of multiple object identifiers, and the object identifier refers to information for identifying a service object; the extraction constraint conditions at least include the service type for which the service object extraction is targeted; the extraction constraint conditions further include the service data extraction requirements and service object extraction algorithms configured by a service personnel on the service terminal when performing object extraction; A feature extraction module, configured to obtain a specified service data subset corresponding to a corresponding object identifier from the service data set of any one of the object identifiers based on the extraction constraint conditions, so as to extract specified object features corresponding to the corresponding object identifier based on the specified service data subset; An object screening module, configured to process the specified object features under each object identifier in the object identifier set by using the service object extraction algorithm corresponding to the service type, so as to screen out potential object identifiers targeted by the service type; An information feedback module, configured to feedback the screened potential object identifiers to the service terminal, so that the service terminal performs service processing on the service objects corresponding to the potential object identifiers; Wherein, the feature extraction module is specifically configured to: for any object identifier in the object identifier set, obtain a first specified service data subset corresponding to the corresponding object identifier under the service resource demand feature from the service data set of the object identifier; and obtain a second specified service data subset corresponding to the corresponding object identifier under the service resource repayment feature from the service data set of the object identifier.

7. A method for extracting business objects, characterized in that, Applied to a service terminal, the method includes: Receiving the object identifier and extraction constraint conditions input on an object extraction configuration interface; wherein, the object identifier refers to information for identifying a service object; the extraction constraint conditions at least include the service type for which the service object extraction is targeted; the extraction constraint conditions further include the service data extraction requirements and service object extraction algorithms configured by a service personnel on the service terminal when performing object extraction; When receiving an object extraction trigger instruction, send a service object extraction request to the server, where the service object extraction request includes at least an object identifier set and the extraction constraint conditions; wherein, the object identifier set refers to a set composed of the input object identifiers; so that the server, based on the extraction constraint conditions, obtains a specified service data subset corresponding to the corresponding object identifier from the service data set of any of the object identifiers, and extracts the specified object features of the corresponding object identifier based on the specified service data subset; use the service object extraction algorithm corresponding to the service type to process the specified object features under each object identifier in the object identifier set to screen out the potential object identifiers targeted by the service type; and feedback the screened potential object identifiers to the service terminal; wherein, obtaining the specified service data subset corresponding to the corresponding object identifier from the service data set of any of the object identifiers includes: for any object identifier in the object identifier set, obtaining a first specified service data subset corresponding to the object identifier in the service data set under the service resource requirement feature; and obtaining a second specified service data subset corresponding to the object identifier in the service data set under the service resource repayment feature; Receive the potential object identifiers fed back by the server to perform resource allocation on the service objects corresponding to the potential object identifiers.

8. A business terminal, characterized in that, Including: An information input receiving module, configured to receive the object identifiers and extraction constraint conditions input on the object extraction configuration interface; wherein, the object identifier refers to the information for identifying the service object; the extraction constraint conditions at least include the service type targeted by the service object extraction; the extraction constraint conditions further include the service data extraction requirements and service object extraction algorithms configured by the service personnel on the service terminal when performing object extraction; A request sending module, configured to send a service object extraction request to a server when receiving an object extraction trigger instruction, where the service object extraction request at least includes an object identifier set and the extraction constraint condition; wherein, the object identifier set refers to a set composed of the input object identifiers; so that the server, based on the extraction constraint condition, obtains a specified service data subset corresponding to the corresponding object identifier from the service data set of any of the object identifiers, and extracts a specified object feature corresponding to the corresponding object identifier based on the specified service data subset; processes the specified object features under each object identifier in the object identifier set by using a service object extraction algorithm corresponding to the service type, so as to screen out potential object identifiers targeted by the service type; and feeds back the screened potential object identifiers to the service terminal; wherein, obtaining a specified service data subset corresponding to the corresponding object identifier from the service data set of any of the object identifiers includes: for any object identifier in the object identifier set, obtaining a first specified service data subset corresponding to the object identifier in the service data set of the object identifier under the service resource requirement feature; and obtaining a second specified service data subset corresponding to the object identifier in the service data set of the object identifier under the service resource repayment feature; A service object receiving module, configured to receive the potential object identifiers fed back by the server, so as to perform resource allocation on the service objects corresponding to the potential object identifiers.

9. A computer-readable storage medium, on which computer instructions are stored, characterized in that, When the instruction is executed, it implements the steps of the method according to any one of claims 1 to 5 and 7.

Images