CN113935802A - Information processing method, device, equipment and storage medium - Google Patents

Information processing method, device, equipment and storage medium Download PDF

Info

Publication number
CN113935802A
CN113935802A CN202111194964.0A CN202111194964A CN113935802A CN 113935802 A CN113935802 A CN 113935802A CN 202111194964 A CN202111194964 A CN 202111194964A CN 113935802 A CN113935802 A CN 113935802A
Authority
CN
China
Prior art keywords
rule
verification
data
statement
executable
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111194964.0A
Other languages
Chinese (zh)
Inventor
佘山
李傲
郑镇宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Xunmeng Information Technology Co Ltd
Original Assignee
Shanghai Xunmeng Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Xunmeng Information Technology Co Ltd filed Critical Shanghai Xunmeng Information Technology Co Ltd
Priority to CN202111194964.0A priority Critical patent/CN113935802A/en
Publication of CN113935802A publication Critical patent/CN113935802A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides an information processing method, an information processing device, information processing equipment and a storage medium, wherein the information processing method comprises the following steps: receiving a verification rule whether the order data is a credit order; converting the check rule from a natural language into an executable rule statement; verifying the executable rule statements by adopting the trained classification model and the verification result of the executable rule statements on the historical order data; and executing the executable rule statement on the order data of the order to be verified, and outputting a verification result of the order to be verified. The invention optimizes the landing of the credit receipt verification rule, thereby automatically executing the verification of the credit receipt verification rule without manual participation and improving the landing efficiency of the rule and the identification accuracy of the credit receipt.

Description

Information processing method, device, equipment and storage medium
Technical Field
The present invention relates to the field of computer applications, and in particular, to an information processing method, apparatus, system, device, and storage medium.
Background
With the development of the e-commerce industry, the living mode of online shopping has become more and more popular. When a consumer purchases online, the consumer focuses on store parameters such as the commodity sales volume, the store evaluation, the store reputation and the like of a merchant. Meanwhile, the e-commerce platform also provides the consumers with intelligently sorted store/store commodities according to store parameters such as commodity sales volume of merchants, store evaluation, store reputation and the like. Therefore, the sales of the store, the evaluation of the store, the reputation of the store, and the like are important for the promotion of the store and the improvement of the sales. However, these store parameters all require the store to accumulate over a period of time to effectively increase. In a newly-opened shop, good shop parameters cannot be obtained through a natural sales method. In such a case, part of the merchants are swiped through false transactions in order to promote store parameters such as store reputation. The orders that are swiped may be referred to as reputation orders.
To ensure the actual store parameters, the e-commerce platform identifies these reputation tickets. Since the merchant can have a plurality of different credit receipt refreshing modes, and in order to avoid the identification of the e-commerce platform, the credit receipt refreshing mode can be updated. Therefore, after the e-commerce platform obtains a new credit receipt check rule aiming at the updated credit receipt refreshing mode, the e-commerce platform can be used online only after the validity of the new credit receipt check rule is verified manually. Therefore, the new rules of the existing credit tickets are on the ground by adopting a mode of jointly manually verifying by operators and developers, so that the method is time-consuming, labor-consuming, low in efficiency and easy to miss.
Therefore, how to optimize the credit receipt verification rule landing and automatically execute the verification of the credit receipt verification rule without manual participation is a technical problem to be solved in the field.
Disclosure of Invention
In order to overcome the defects of the related technologies, the invention provides an information processing method, an information processing device, information processing equipment and a storage medium, so that the landing of the credit receipt verification rule is optimized, the verification of the credit receipt verification rule is automatically executed, manual participation is not needed, and the rule landing efficiency and the recognition accuracy of the credit receipt are improved.
According to an aspect of the present invention, there is provided an information processing method including:
receiving a verification rule whether the order data is a credit order;
converting the check rule from a natural language into an executable rule statement;
verifying the executable rule statements by adopting the trained classification model and the verification result of the executable rule statements on the historical order data;
and executing the executable rule statement on the order data of the order to be verified, and outputting a verification result of the order to be verified.
In some embodiments of the invention, the converting the check rule from natural language to an executable rule statement comprises:
extracting a processing object text and an operation text of an executable rule sentence from the check rule;
inquiring a processing object statement field and an operation statement field mapped by the processing object text and the operation text according to an executable rule statement mapping table;
and generating an executable rule statement according to the processing object statement field and the operation statement field.
In some embodiments of the invention, the classification model is trained on after-market tag data, chat tag data, wind control tag data, and reputation ticket tag data of the historical order data.
In some embodiments of the present invention, the after-market tag data is obtained by:
acquiring after-sale data of historical order data;
according to an after-sale state classification algorithm, determining an after-sale classification to which the after-sale data belongs;
the after-market classification is used as the after-market label data for the historical order data.
In some embodiments of the present invention, the chat tag data is obtained by:
obtaining a chat record associated with historical order data;
identifying one or more items of chat intention, credit form key words and chat abnormal information of the chat records according to a natural language identification technology;
and taking one or more items of chat intention, reputation list key words and chat abnormal information of the chat records as the chat label data of the historical order data.
In some embodiments of the present invention, the wind control tag data is obtained by:
acquiring one or more items of transaction data, fund data and logistics data of historical order data;
determining one or more affiliated risk classifications in the transaction data, the fund data and the logistics data according to the trained wind control model;
and classifying the risk as the wind control tag data of the historical order data.
In some embodiments of the invention, the classification model is a decision tree model.
In some embodiments of the present invention, the verifying the executable rule statement using the trained classification model and the result of verifying the historical order data by the executable rule statement includes:
inputting a plurality of historical order data into a trained classification model to obtain a classification result output by the classification model;
inputting the plurality of historical order data into an executable rule statement to obtain a verification result output by the executable rule statement;
and when the ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders is larger than a set verification threshold value, determining that the executable rule statement passes verification.
In some embodiments of the invention, the validation rule comprises a rule threshold, the rule threshold being set via a user.
In some embodiments of the invention, the validation rules include a rule threshold determined from the trained classification model and the validation results of the executable rule statements against historical order data.
In some embodiments of the invention, the determination is made according to the following steps:
inputting a plurality of historical order data into a trained classification model to obtain a classification result output by the classification model;
for each candidate rule threshold, inputting the plurality of historical order data into an executable rule statement to obtain a verification result output by the executable rule statement;
and taking the candidate rule threshold with the maximum ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold.
In some embodiments of the present invention, the candidate rule threshold value with the largest ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders further includes, as the rule threshold value:
judging whether the maximum ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders is larger than a set verification threshold value or not for the candidate rule threshold value;
if so, determining that the executable rule statement passes verification, and taking a candidate rule threshold value with the largest proportion of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold value;
if not, determining that the executable rule statement does not pass the verification.
According to still another aspect of the present invention, there is also provided an information processing apparatus comprising:
the receiving module is configured to receive a check rule whether the order data is a credit order;
a conversion module configured to convert the verification rule from a natural language into an executable rule statement;
the rule checking module is configured to check the executable rule statement by adopting a trained classification model and a checking result of the executable rule statement on historical order data;
and the order checking module is configured to execute the executable rule statement on the order data of the order to be verified and output a checking result of the order to be verified.
According to still another aspect of the present invention, there is also provided an electronic apparatus, including: a processor; a storage medium having stored thereon a computer program which, when executed by the processor, performs the steps as described above.
According to yet another aspect of the present invention, there is also provided a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps as described above.
Compared with the prior art, the invention has the advantages that:
on one hand, the verification rule for judging whether the order data is the credit order is converted into the executable rule statement, so that the natural language of the verification rule is conveniently written, the requirement on the code experience of a writer is low, and meanwhile, the verification rule is automatically executed conveniently through the conversion of the natural language and the executable rule statement without manual coding participation; on the other hand, the trained classification model and the verification result of the executable rule statement on the historical order data are adopted to verify the executable rule statement, so that the verification of the verification rule can be automatically executed, whether the verification rule can be used for identifying and judging the credit receipt or not is judged, manual participation is not needed in the verification process of the verification rule, the verification sum landing efficiency of the verification rule is improved, the verified verification rule can be quickly brought on line, and the verification rule is used for identifying the credit receipt as soon as possible. Therefore, the credit receipt verification rule landing is optimized, the credit receipt verification rule and verification thereof are automatically executed, manual participation is not needed, and the rule landing efficiency and the recognition accuracy of the credit receipt are improved.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
Fig. 1 shows a flowchart of an information processing method according to an embodiment of the present invention.
FIG. 2 shows a flow diagram for converting the check rule from natural language to an executable rule statement, according to an embodiment of the invention.
FIG. 3 illustrates a flow diagram for obtaining after-market label data according to an embodiment of the invention.
Fig. 4 illustrates a flow diagram for obtaining chat tag data in accordance with an embodiment of the invention.
FIG. 5 shows a flowchart for obtaining the wind control tag data according to an embodiment of the invention.
FIG. 6 shows a flowchart for verifying the executable rule statement using the trained classification model and the result of verifying the executable rule statement against historical order data, according to an embodiment of the invention.
Fig. 7 shows a block diagram of an information processing apparatus according to an embodiment of the present invention.
Fig. 8 schematically illustrates a computer-readable storage medium in an exemplary embodiment of the invention.
Fig. 9 schematically illustrates an electronic device in an exemplary embodiment of the invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the steps. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
Fig. 1 shows a flowchart of an information processing method according to an embodiment of the present invention. The information processing method comprises the following steps:
step S110: and receiving a verification rule whether the order data is a credit order.
Specifically, the check rule is used to identify whether the order data is a reputation order.
In this embodiment, the verification rule of the reputation ticket may be obtained by natural language editing. For example, the operator may enter verification rules compiled in natural language, such as actual ship-to site disagreement with ship-to site; the package weight is not consistent with the weight of the goods in the order, etc.
In some variations, multiple candidate natural language fields may also be provided to the operator, so that the operator may splice the multiple candidate natural language fields together by selecting, dragging, and the like. The natural language field may include a processing object text as well as an operation text. The processing object text may include, for example, a receiving place in an order, a receiving place in a sign-in stage in a logistics track, a package weight, a commodity weight, and the like, which is not limited in the present application. The operation text may include, for example, greater than, equal to, less than, plus, true, false, etc., and the present application is not limited thereto. In an embodiment of providing multiple candidate natural language fields for the operator, the candidate natural language fields may be further classified to improve the editing efficiency of the verification rules of the operator. For example, the candidate natural language fields may be divided into order information, user information, logistics information, merchandise information, package information, etc., and the classification may be set as desired. The operator can also manually add candidate natural language fields to expand the generated verification rules and improve the flexibility of the generated verification rules.
Step S120: and converting the check rule from a natural language into an executable rule statement.
Specifically, the conversion between the check rule and the executable rule statement may be implemented in the form of a mapping table, an executable rule statement template, or the like. One way in which the present application may be implemented is described below in conjunction with fig. 2.
Step S130: and verifying the executable rule statement by adopting the trained classification model and the verification result of the executable rule statement on the historical order data.
Specifically, the trained classification model can automatically recognize whether the order data is the credit order, but considering that the algorithm of the classification model is complex and the execution efficiency is relatively low, compared with the method for verifying whether the order data is the credit order by using the classification model in real time, the credit order verification efficiency and the real-time performance can be improved by adopting the executable rule statement. Therefore, the application can adopt the trained classification model for assistance in the verification of the executable rule statement so as to determine whether the executable rule statement can effectively identify the credit statement.
Step S140: and executing the executable rule statement on the order data of the order to be verified, and outputting a verification result of the order to be verified.
Specifically, the executable rule statement may be executed only on order data of the order to be verified, so as to output a verification result of the order to be verified.
In some variations, a validation rule set may be generated from executable rule statements that have been previously validated, and when a new validation rule is validated, the executable rule statements of the new validation rule are added to the validation rule set together, so as to identify whether order data of an order to be validated is a reputation list through the validation rule set. Specifically, for the verification rule set, the manner of use of the verification rule set may be set. For example, when any executable rule statement in the validation rule set is true, the order to be validated may be determined to be a reputation sheet. For another example, when the rule data that verifies the executable rule statement in the rule set as true is greater than the set threshold, the order to be verified may be determined to be a reputation order. For another example, the credit form scoring may be performed on the order to be verified according to the executable rule statements in the verification rule set, and when the score value is greater than the set threshold value, the order to be verified may be determined to be the credit form. In a scoring embodiment, each executable rule statement may have a weight, and the weighted sum of the verification results (converted into numerical values) of each executable rule statement is used as the reputation order score of the order to be verified. The weight of each executable rule statement can be set in the verification process, and when the verification result of the executable rule statement is more consistent with the verification result of the trained classification model, the weight of the executable rule statement is higher.
Further, in the embodiment of verifying the rule set, the re-verification of the executable rule statement may also be performed periodically. Considering the update of the reputation list refresh mode of the merchant, the previous refresh mode may not be used any more, and thus the corresponding executable rule statements are also difficult to identify a new refresh mode, so the verification of step S130 may be performed again on the executable rule statements of the verification rule set periodically, and when the number/proportion of the executable rule statements inconsistent with the verification result of the trained classification model is large, the executable rule statements may be deleted from the verification rule set. Therefore, the rule redundancy of the verification rule set is reduced, and the verification efficiency of the verification rule set is improved.
In the information processing method provided by the invention, on one hand, the verification rule for judging whether the order data is the credit order is converted into the executable rule statement so as to facilitate the writing of the natural language of the verification rule, the requirement on the code experience of a writer is lower, and meanwhile, the automatic execution of the verification rule is facilitated through the conversion of the natural language and the executable rule statement without manual participation in coding; on the other hand, the trained classification model and the verification result of the executable rule statement on the historical order data are adopted to verify the executable rule statement, so that the verification of the verification rule can be automatically executed, whether the verification rule can be used for identifying and judging the credit receipt or not is judged, manual participation is not needed in the verification process of the verification rule, the verification sum landing efficiency of the verification rule is improved, the verified verification rule can be quickly brought on line, and the verification rule is used for identifying the credit receipt as soon as possible. Therefore, the credit receipt verification rule landing is optimized, the credit receipt verification rule and verification thereof are automatically executed, manual participation is not needed, and the rule landing efficiency and the recognition accuracy of the credit receipt are improved.
Referring now to FIG. 2, FIG. 2 illustrates a flow diagram for converting the check rule from a natural language to an executable rule statement, according to an embodiment of the present invention. Fig. 2 shows the following steps together:
step S121: and extracting a processing object text and an operation text of the executable rule sentence from the check rule.
Specifically, step S121 may perform word segmentation and word tagging on the verification rule through a word segmentation algorithm. Thus, the processing target text and the operation text of the executable rule sentence can be extracted by word labeling.
In some variations, when editing of the verification rule is implemented by the candidate natural language field, the processing object text and the operation text in the verification rule may be determined directly according to the category and the label of the candidate natural language field selected by the operator.
Specifically, the processing target text may include, for example, a receiving place in an order, a receiving place in a sign-in stage in a logistics track, a package weight, a product weight, and the like, which is not limited in the present application. The operation text may include, for example, greater than, equal to, less than, plus, true, false, etc., and the present application is not limited thereto.
Step S122: and inquiring a processing object statement field and an operation statement field mapped by the processing object text and the operation text according to the executable rule statement mapping table.
Specifically, in the present embodiment, an executable rule sentence mapping table may be maintained so as to map the processing target text and the operation text in the natural language with the corresponding sentence field, so that the processing target sentence field (of the executable rule sentence) and the operation sentence field may be obtained from the mapping table based on the extracted processing target text and operation text.
Step S123: and generating an executable rule statement according to the processing object statement field and the operation statement field.
In particular, the processing object statement field and the operation statement field may be directly spliced together to form an executable rule statement. In some variations, the processing object statement field and the operation statement field may be concatenated together by the syntax of the executable rule statement (location of different fields, etc.). Furthermore, an executable rule statement template can be provided, and the processing object statement field and the operation statement field are filled in the executable rule statement template, so that the executable rule statement is generated. The present application is not so limited.
Specifically, the classification model is trained according to after-sales tag data, chat tag data, wind control tag data and credit form tag data of historical order data. In particular, the classification model may be a decision tree model to enable training and classification based on multi-labels. Wherein the reputation ticket label data is used to indicate whether the historical order data is a reputation ticket. The after-market tag data, the chat tag data, and the wind control tag data may be described with reference to fig. 3 to 5, respectively. The type of label used in the classification model of the present application is not limited thereto, and other labels are also within the scope of the present application.
Referring now to fig. 3, fig. 3 illustrates a flow diagram for obtaining after-market label data, according to an embodiment of the invention. Fig. 3 shows the following steps in total:
step S101: and acquiring after-sales data of the historical order data.
Specifically, the after-sales data may include, for example, after-sales applications of the consumer, post-sales communication data between the consumer and the merchant, return flow information, post-sales fund flow information, and the like, and the present application is not limited thereto.
Step S102: and determining the after-sale classification of the after-sale data according to an after-sale state classification algorithm.
Specifically, the after-market status classification algorithm may set the classification rules based on the determined after-market classifications (e.g., merchant reason refund only, merchant reason refund and refund, merchant reason shipping cost refund, consumer reason refund and refund, consumer reason shipping cost refund, etc.). And performing after-sale classification according to the set classification rules. The after-market classification is determined, for example, based on the after-market reason selected by the consumer, the type of after-market application selected by the consumer, feedback information from the merchant, and the like.
Step S103: the after-market classification is used as the after-market label data for the historical order data.
Specifically, the relevance of after-market classification to whether an order is a reputation ticket can be learned based on the use of post-market tag data in the training of classification models.
Turning now to fig. 4, fig. 4 illustrates a flow diagram for obtaining chat tab data, in accordance with an embodiment of the present invention. Fig. 4 shows the following steps in total:
step S104: and obtaining a chat record associated with the historical order data.
Step S105: and identifying one or more items of the chat intention, the reputation list keyword and the chat abnormal information of the chat records according to a natural language identification technology.
Specifically, the natural language identification technique may include a word segmentation algorithm, a word segmentation labeling algorithm, an intention prediction algorithm, a keyword mapping, an abnormal information mapping, and the like. Step S105 may process the chat log by using a natural language identification technology, so as to identify one or more items of the chat intention, the reputation list keyword, and the chat abnormal information of the chat log. Specifically, the reputation word keyword may be associated with a stored reputation word table, and when a keyword matching the reputation word table exists in the chat log, the keyword of the chat log may be used as the reputation word keyword. Similarly, the exception information may also be implemented in the form of a mapping table, which is not limited in this application.
Step S106: and taking one or more items of chat intention, reputation list key words and chat abnormal information of the chat records as the chat label data of the historical order data.
Specifically, considering that the chat records intuitively display the communication process between the consumer and the merchant, and the communication process can effectively realize the recognition of the credit form, the relevance of the chat information and the order form can be learned according to the use of the chat label data in the training of the classification model.
Referring now to fig. 5, fig. 5 illustrates a flow chart for obtaining the wind control tag data according to an embodiment of the present invention. Fig. 5 shows the following steps in total:
step S107: one or more of transaction data, fund data and logistics data of the historical order data are obtained.
Step S108: and determining one or more of the transaction data, the fund data and the logistics data according to the trained wind control model.
In particular, the risk classification may be, for example, a risk level. For example, a low risk level, a medium risk level, a high risk level, etc. may be set. In particular, the trained wind control model may effectively determine a risk level to which one or more of transaction data, funding data, logistics data belong.
Step S109: and classifying the risk as the wind control tag data of the historical order data.
Specifically, it can be understood that the higher the risk level, the greater the probability that the order is a reputation list, and therefore, the relevance of the chat information to whether the order is a reputation list can be learned according to the use of the chat tag data in the training of the classification model.
Therefore, by introducing the big data marking technology, a safe and reliable data base is provided for automatic verification. Meanwhile, the functions of classifying and marking found credit notes and integrating the marking are realized, wherein: after-sale domain marking is realized through an after-sale state classification strategy; marking of a chatting-like domain is realized through a natural language identification technology; marking in a wind control domain is realized through a wind control algorithm; and integrating various label data through a decision tree model to realize final two-classification judgment of the credit form. Therefore, the effect that credit form discovery automation, operation and development personnel do not need to intervene can be achieved.
The above description is only illustrative of various tag acquisition modes provided in the present application, and the present application is not limited thereto.
Referring now to fig. 6, fig. 6 is a flow chart illustrating verification of the executable rule statement using a trained classification model and a result of verification of historical order data by the executable rule statement according to an embodiment of the present invention. Fig. 6 shows the following steps in total:
step S131: and inputting a plurality of historical order data into the trained classification model to obtain a classification result output by the classification model.
In particular, the classification results provided by the classification model are used to indicate whether the historical order data is a reputation order.
Step S132: and inputting the plurality of historical order data into an executable rule statement to obtain a verification result output by the executable rule statement.
Specifically, the verification result output by the executable rule statement is used for indicating whether the historical order data is a reputation list.
And step S133, when the ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders is greater than a set verification threshold, determining that the executable rule statement passes verification.
Therefore, the verification threshold is set so as to ensure that the executable rule statement capable of effectively identifying the credit form passes verification and is convenient for online use. Specifically, the set verification threshold may be set by an operator as needed. Further, before verification of the executable rule statement is carried out on the classification model, iteration updating can be carried out through recent historical order data, so that the recognition accuracy of the classification model is improved, and the verification accuracy of the executable rule statement can be improved.
In some embodiments of the present application, the verification rule may include a rule threshold. The rule threshold is a value used in the check rule. For example, the verification rule may be set such that when the difference between the package weight and the product weight (product of the individual product weight and the product quantity) is greater than N, the credit is determined. N may be used as the rule threshold of the check rule. For another example, the verification rule may be set to determine that the order is a credit when the number of the items of the same order having the same delivery address and the same receiving address is greater than M, and M may be used as a rule threshold of the verification rule.
In particular, the rule threshold may be set on demand via a user. In some variations, the validation rules include a rule threshold determined from a trained classification model and validation results of the executable rule statements against historical order data.
In some embodiments, the rule threshold may be determined according to the following steps: inputting a plurality of historical order data into a trained classification model to obtain a classification result output by the classification model; for each candidate rule threshold, inputting the plurality of historical order data into an executable rule statement to obtain a verification result output by the executable rule statement; and taking the candidate rule threshold with the maximum ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold.
For example, in an embodiment where the verification rule may be set such that the difference between the parcel weight and the commodity weight (product of the individual commodity weight and the commodity quantity) is greater than N, the verification rule is determined to be a credit receipt, and N is used as the rule threshold of the verification rule, the candidate rule thresholds of N are set to be N respectively1、N2、N3. Entering the plurality of historical order data into an executable rule statement: the difference between the weight of the package and the weight of the goods (product of the weight of the single goods and the number of the goods) is larger than N1If so, judging the credit form; the difference between the weight of the package and the weight of the goods (product of the weight of the single goods and the number of the goods) is larger than N2If so, judging the credit form; parcel weight and commodity weight (single merchant)Product of product weight and product quantity) is greater than N3And if the historical order data is judged to be the credit list, inputting the historical order data into an executable rule statement, and obtaining a verification result output by the executable rule statement. When the difference between the weight of the package and the weight of the commodity (the product of the weight of the single commodity and the quantity of the commodity) is more than N2Judging that the ratio of the number of the verification results of the credit lists, which are consistent with the classification results, to the total number of the plurality of historical orders is maximum, and adding N to the total number of the plurality of historical orders2As the rule threshold, a complete verification rule can be obtained.
Therefore, a better rule threshold can be obtained through the assistance of the classification model, so that the identification accuracy of the executable rule statement on the reputation list is improved.
Further, in the step of using the candidate rule threshold with the largest ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold, the method may further include: judging whether the maximum ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders is larger than a set verification threshold value or not for the candidate rule threshold value; if so, determining that the executable rule statement passes verification, and taking a candidate rule threshold value with the largest proportion of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold value; if not, determining that the executable rule statement does not pass the verification. Therefore, the selected rule threshold value can be ensured, and higher identification accuracy can be obtained for the verification rule.
In the embodiment of the application, an operator can customize the filtering condition of the credit receipt according to the business requirement of the operator, so that the verification rule is obtained. Then, natural language is converted into executable statements of the code, and developers can take values to check. Then, verification data of the verification rule can be constructed in the big data, when the verification rule passes the verification, the order data to be recognized can be subjected to code executable statement verification, and a result can be output.
The above are merely a plurality of specific implementation manners of the information processing method of the present invention, and each implementation manner may be implemented independently or in combination, and the present invention is not limited thereto. Furthermore, the flow charts of the present invention are merely schematic, the execution sequence between the steps is not limited thereto, and the steps can be split, combined, exchanged sequentially, or executed synchronously or asynchronously in other ways within the protection scope of the present invention.
Referring next to fig. 7, fig. 7 shows a block diagram of an information processing apparatus according to an embodiment of the present invention. The information processing apparatus 200 includes a receiving module 210, a converting module 220, a rule checking module 230, and an order checking module 240.
The receiving module 210 is configured to receive a check rule whether the order data is a reputation order;
the conversion module 220 is configured to convert the verification rule from natural language to an executable rule statement;
the rule checking module 230 is configured to check the executable rule statements using the trained classification model and the checking result of the executable rule statements against the historical order data;
the order verification module 240 is configured to execute the executable rule statement on the order data of the order to be verified, and output a verification result of the order to be verified.
In the information processing apparatus according to the exemplary embodiment of the present invention, on one hand, the check rule for determining whether the order data is the credit order is converted into the executable rule statement, so as to facilitate the writing of the natural language of the check rule, and the requirement on the code experience of a writer is low, and at the same time, the automatic execution of the check rule is facilitated by the conversion of the natural language and the executable rule statement, and no manual coding is required; on the other hand, the trained classification model and the verification result of the executable rule statement on the historical order data are adopted to verify the executable rule statement, so that the verification of the verification rule can be automatically executed, whether the verification rule can be used for identifying and judging the credit receipt or not is judged, manual participation is not needed in the verification process of the verification rule, the verification sum landing efficiency of the verification rule is improved, the verified verification rule can be quickly brought on line, and the verification rule is used for identifying the credit receipt as soon as possible. Therefore, the credit receipt verification rule landing is optimized, the credit receipt verification rule and verification thereof are automatically executed, manual participation is not needed, and the rule landing efficiency and the recognition accuracy of the credit receipt are improved.
Fig. 7 is a schematic diagram of an information processing apparatus 200 provided by the present invention, and the splitting, combining, and adding of modules are within the scope of the present invention without departing from the spirit of the present invention. The information processing apparatus 200 provided in the present invention may be implemented by software, hardware, firmware, plug-in, and any combination thereof, and the present invention is not limited thereto.
In an exemplary embodiment of the present invention, there is also provided a computer-readable storage medium on which a computer program is stored, which, when executed by, for example, a processor, can implement the steps of the information processing method described in any one of the above embodiments. In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the present invention described in the information processing method section above of this description, when said program product is run on the terminal device.
Referring to fig. 8, a program product 700 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the tenant computing device, partly on the tenant device, as a stand-alone software package, partly on the tenant computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing devices may be connected to the tenant computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In an exemplary embodiment of the invention, there is also provided an electronic device that may include a processor and a memory for storing executable instructions of the processor. Wherein the processor is configured to perform the steps of the information processing method in any one of the above embodiments via execution of the executable instructions.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 500 according to this embodiment of the invention is described below with reference to fig. 9. The electronic device 500 shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 9, the electronic device 500 is embodied in the form of a general purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one memory unit 520, a bus 530 that couples various system components including the memory unit 520 and the processing unit 510, a display unit 540, and the like.
Wherein the storage unit stores program code executable by the processing unit 510 to cause the processing unit 510 to perform steps according to various exemplary embodiments of the present invention described in the information processing method section described above in this specification. For example, the processing unit 510 may perform the steps as shown in fig. 1.
The memory unit 520 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM)5201 and/or a cache memory unit 5202, and may further include a read only memory unit (ROM) 5203.
The memory unit 520 may also include a program/utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
Bus 530 may be one or more of any of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 500 may also communicate with one or more external devices 600 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a tenant to interact with the electronic device 500, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 500 to communicate with one or more other computing devices. Such communication may be through input/output (I/O) interfaces 550. Also, the electronic device 500 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 560. The network adapter 560 may communicate with other modules of the electronic device 500 via the bus 530. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned information processing method according to the embodiment of the present invention.
Compared with the prior art, the invention has the advantages that:
on one hand, the verification rule for judging whether the order data is the credit order is converted into the executable rule statement, so that the natural language of the verification rule is conveniently written, the requirement on the code experience of a writer is low, and meanwhile, the verification rule is automatically executed conveniently through the conversion of the natural language and the executable rule statement without manual coding participation; on the other hand, the trained classification model and the verification result of the executable rule statement on the historical order data are adopted to verify the executable rule statement, so that the verification of the verification rule can be automatically executed, whether the verification rule can be used for identifying and judging the credit receipt or not is judged, manual participation is not needed in the verification process of the verification rule, the verification sum landing efficiency of the verification rule is improved, the verified verification rule can be quickly brought on line, and the verification rule is used for identifying the credit receipt as soon as possible. Therefore, the credit receipt verification rule landing is optimized, the credit receipt verification rule and verification thereof are automatically executed, manual participation is not needed, and the rule landing efficiency and the recognition accuracy of the credit receipt are improved.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

Claims (15)

1. An information processing method characterized by comprising:
receiving a verification rule whether the order data is a credit order;
converting the check rule from a natural language into an executable rule statement;
verifying the executable rule statements by adopting the trained classification model and the verification result of the executable rule statements on the historical order data;
and executing the executable rule statement on the order data of the order to be verified, and outputting a verification result of the order to be verified.
2. The information processing method of claim 1, wherein said converting the check rule from a natural language into an executable rule statement comprises:
extracting a processing object text and an operation text of an executable rule sentence from the check rule;
inquiring a processing object statement field and an operation statement field mapped by the processing object text and the operation text according to an executable rule statement mapping table;
and generating an executable rule statement according to the processing object statement field and the operation statement field.
3. The information processing method of claim 1, wherein the classification model is trained based on after-market tag data, chat tag data, wind control tag data, and reputation ticket tag data of historical order data.
4. The information processing method according to claim 3, wherein the after-market label data is acquired by:
acquiring after-sale data of historical order data;
according to an after-sale state classification algorithm, determining an after-sale classification to which the after-sale data belongs;
the after-market classification is used as the after-market label data for the historical order data.
5. The information processing method according to claim 3, wherein the chat label data is acquired by:
obtaining a chat record associated with historical order data;
identifying one or more items of chat intention, credit form key words and chat abnormal information of the chat records according to a natural language identification technology;
and taking one or more items of chat intention, reputation list key words and chat abnormal information of the chat records as the chat label data of the historical order data.
6. The information processing method according to claim 3, wherein the flag data is acquired by:
acquiring one or more items of transaction data, fund data and logistics data of historical order data;
determining one or more affiliated risk classifications in the transaction data, the fund data and the logistics data according to the trained wind control model;
and classifying the risk as the wind control tag data of the historical order data.
7. The information processing method of claim 3, wherein the classification model is a decision tree model.
8. The information processing method of claim 3, wherein the verifying the executable rule statement using the trained classification model and the result of the verification of the historical order data by the executable rule statement comprises:
inputting a plurality of historical order data into a trained classification model to obtain a classification result output by the classification model;
inputting the plurality of historical order data into an executable rule statement to obtain a verification result output by the executable rule statement;
and when the ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders is larger than a set verification threshold value, determining that the executable rule statement passes verification.
9. The information processing method of claim 1, wherein the check rule includes a rule threshold, the rule threshold being set via a user.
10. The information processing method of claim 1, wherein the validation rules include a rule threshold determined from a trained classification model and validation results of the executable rule statements against historical order data.
11. The information processing method of claim 10, wherein the rule threshold is determined according to the steps of:
inputting a plurality of historical order data into a trained classification model to obtain a classification result output by the classification model;
for each candidate rule threshold, inputting the plurality of historical order data into an executable rule statement to obtain a verification result output by the executable rule statement;
and taking the candidate rule threshold with the maximum ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold.
12. The information processing method according to claim 11, wherein the candidate rule threshold value having the largest ratio of the number of the classification results that are consistent with the verification results to the total number of the plurality of historical orders is used as the rule threshold value, and the method further comprises:
judging whether the maximum ratio of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders is larger than a set verification threshold value or not for the candidate rule threshold value;
if so, determining that the executable rule statement passes verification, and taking a candidate rule threshold value with the largest proportion of the number of the classification results consistent with the verification results to the total number of the plurality of historical orders as the rule threshold value;
if not, determining that the executable rule statement does not pass the verification.
13. An information processing apparatus characterized by comprising:
the receiving module is configured to receive a check rule whether the order data is a credit order;
a conversion module configured to convert the verification rule from a natural language into an executable rule statement;
the rule checking module is configured to check the executable rule statement by adopting a trained classification model and a checking result of the executable rule statement on historical order data;
and the order checking module is configured to execute the executable rule statement on the order data of the order to be verified and output a checking result of the order to be verified.
14. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory having stored thereon a computer program that, when executed by the processor, performs:
the information processing method according to any one of claims 1 to 12.
15. A storage medium having a computer program stored thereon, the computer program when executed by a processor performing:
the information processing method according to any one of claims 1 to 12.
CN202111194964.0A 2021-10-12 2021-10-12 Information processing method, device, equipment and storage medium Pending CN113935802A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111194964.0A CN113935802A (en) 2021-10-12 2021-10-12 Information processing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111194964.0A CN113935802A (en) 2021-10-12 2021-10-12 Information processing method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113935802A true CN113935802A (en) 2022-01-14

Family

ID=79279156

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111194964.0A Pending CN113935802A (en) 2021-10-12 2021-10-12 Information processing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113935802A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116739719A (en) * 2023-08-14 2023-09-12 南京大数据集团有限公司 Flow configuration system of transaction platform

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116739719A (en) * 2023-08-14 2023-09-12 南京大数据集团有限公司 Flow configuration system of transaction platform
CN116739719B (en) * 2023-08-14 2023-11-03 南京大数据集团有限公司 Flow configuration system and method of transaction platform

Similar Documents

Publication Publication Date Title
CN109509048B (en) Malicious order identification method and device, electronic equipment and storage medium
CN109598517B (en) Commodity clearance processing, object processing and category prediction method and device thereof
CN104737187A (en) System and process of associating import and/or export data with a corporate identifier
CN109815480B (en) Data processing method and device and storage medium
CN113159355A (en) Data prediction method, data prediction device, logistics cargo quantity prediction method, medium and equipment
CN112417881A (en) Logistics information identification method and device, electronic equipment and storage medium
CN112883990A (en) Data classification method and device, computer storage medium and electronic equipment
CN112990294A (en) Training method and device of behavior discrimination model, electronic equipment and storage medium
CN111754317A (en) Financial investment data evaluation method and system
CN110704803A (en) Target object evaluation value calculation method and device, storage medium and electronic device
CN113935802A (en) Information processing method, device, equipment and storage medium
CN115809930A (en) Anti-fraud analysis method, device, equipment and medium based on data fusion matching
CN115017385A (en) Article searching method, device, equipment and storage medium
CN116010707A (en) Commodity price anomaly identification method, device, equipment and storage medium
CN114637850A (en) Abnormal behavior recognition and model training method, device, equipment and storage medium
CN114219310A (en) Order auditing method, system, electronic equipment and storage medium
CN112465149A (en) Same-city part identification method and device, electronic equipment and storage medium
CN113590484A (en) Algorithm model service testing method, system, equipment and storage medium
CN112686732A (en) Abnormal address data identification method, device, equipment, medium and product
CN113077315A (en) Data processing method and device, computer readable storage medium and electronic equipment
CN112989050A (en) Table classification method, device, equipment and storage medium
CN112418356A (en) Goods name classification method and device, electronic equipment and storage medium
CN112418354B (en) Goods source information classification method and device, electronic equipment and storage medium
CN112613950B (en) Class identification model training method, class identification method and related equipment
CN116629639B (en) Evaluation information determining method and device, medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination