Data invalidation processing method and device, equipment, medium and product

Abstract

The invention provides a data invalidation processing method, device and equipment, a medium and product quality, relates to the technical field of artificial intelligence, in particular to the technical field of large models and deep learning, and can be used for cloud computing and cloud services. According to the specific implementation scheme, in response to an invalidation processing request initiated by an invalidation initiator, to-be-invalidated information of to-be-invalidated data is obtained; and based on an invalidation processing period, performing invalidation processing on the to-be-invalidated data according to the to-be-invalidated information to obtain target invalidation data. Through the technical scheme, the processing efficiency of data invalidation processing can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of large models and deep learning technology, and can be used for cloud computing and cloud services. Background Art

[0002] With the rapid advancement of artificial intelligence technology, some useless or erroneous data needs to be invalidated. The traditional process may require manual operation, which is inefficient and has low accuracy. Therefore, an efficient method of invalid data processing is continued.

[0003] In particular, traditional industries are also accelerating their transformation. For example, paper invoices of various enterprises have been fully upgraded to digital invoices to facilitate statistics and management, and accelerate digital transformation. Currently, there are the following complexity and efficiency issues in the process of red-checking digital invoices: 1) The process of red-checking digital invoices may involve multiple links and manual approval; 2) Errors are prone to occur during the manual red-checking process, such as selecting the wrong red-checking reason, filling in the wrong amount, etc.; 3) Red-checking requires a lot of information, and multiple systems need to jump to each other for verification. Summary of the invention

[0004] The present invention provides a method, device, equipment, medium and product for processing invalid data.

[0005] According to one aspect of the present disclosure, a method for processing invalid data is provided, the method comprising:

[0006] In response to an invalidation processing request initiated by an invalidation initiator, obtaining information on the data to be invalidated;

[0007] Based on the invalidation processing cycle, the data to be invalidated is invalidated according to the information to be invalidated to obtain target invalid data.

[0008] According to another aspect of the present disclosure, a method for processing invalid data is provided, which is applied to a third-party platform, and the method includes:

[0009] Get the invalid intent of the invalid initiator;

[0010] The application program interface API service of the data invalidation plug-in is remotely called to perform invalidation processing according to the invalidation intention; the data invalidation plug-in is used to implement the data invalidation processing method described in any embodiment of the present disclosure.

[0011] According to another aspect of the present disclosure, a data invalidation processing device is provided, the device comprising:

[0012] The module for acquiring information to be invalidated is used to acquire information of data to be invalidated in response to an invalidation processing request initiated by an invalidation initiator;

[0013] The invalidation processing module is used to perform invalidation processing on the data to be invalidated based on the invalidation processing cycle and the information to be invalidated to obtain target invalid data.

[0014] According to another aspect of the present disclosure, a data invalidation processing device is provided, which is configured on a third-party platform, and includes:

[0015] The valid intention acquisition module is used to acquire the invalid intention of the invalid initiator;

[0016] The invalidation processing module is used to remotely call the application program interface API service of the data invalidation plug-in to perform invalidation processing according to the invalidation intention; the data invalidation plug-in is used to implement the data invalidation processing method described in any embodiment of the present disclosure.

[0017] According to another aspect of the present disclosure, there is provided an electronic device, the electronic device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data invalidation processing method described in any embodiment of the present disclosure.

[0021] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the data invalidation processing method described in any embodiment of the present disclosure.

[0022] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the data invalidation processing method described in any embodiment of the present disclosure is implemented.

[0023] According to the technology disclosed in the present invention, the efficiency of data invalidation processing can be improved.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0026] Figure 1 is a flow chart of a method for processing invalid data provided according to an embodiment of the present disclosure;

[0027] Figure 2 It is a flow chart of a red-charge cycle of a digital electronic ticket provided according to an embodiment of the present disclosure;

[0028] Figure 3 is a flowchart of another method for processing invalid data provided according to an embodiment of the present disclosure;

[0029] Figure 4 is a flowchart of another method for processing invalid data provided according to an embodiment of the present disclosure;

[0030] Figure 5 is a flow chart of a method for processing invalid data provided according to an embodiment of the present disclosure;

[0031] Figure 6 This is a system block diagram of a digital electronic ticket redemption system provided according to an embodiment of the present disclosure;

[0032] Figure 7 It is a structural schematic diagram of a data invalidation processing device provided according to an embodiment of the present disclosure;

[0033] Figure 8 is a structural diagram of another data invalidation processing device provided according to an embodiment of the present disclosure

[0034] Fig. 9 It is a block diagram of an electronic device used to implement the data invalidation processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] In addition, it should be noted that in the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of data to be invalidated, digital invoice-related data, etc. are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0038] Figure 1 This is a flow chart of a data invalidation processing method provided according to an embodiment of the present disclosure. This method is applicable to situations where data invalidation processing is performed, and is particularly applicable to situations where digital electronic tickets are red-checked. This method can be performed by a data invalidation processing device, which can be implemented in software and / or hardware, and can be integrated into an electronic device that carries the data invalidation processing function, such as a data invalidation processing system on a PC, specifically a digital electronic ticket red-checking system. Figure 1 As shown, the data invalidation processing method of this embodiment may include:

[0039] S101, in response to an invalidation processing request initiated by an invalidation initiator, obtaining information of data to be invalidated.

[0040] In this embodiment, the invalidation initiator refers to the party that initiates the invalidation processing request, for example, it can be the red reversal initiator, where the red reversal initiator refers to the party that initiates the red reversal of the digital invoice, for example, it can be operations, sales, etc. The so-called invalidation processing request refers to a request for triggering or instructing non-invalidation processing of invalid data; optionally, the invalidation processing request can be a red reversal request, where the red reversal request refers to a request for triggering the system to perform a red reversal of the digital invoice; optionally, the red reversal request includes the digital invoice to be red reversal. The so-called data to be invalidated refers to data that needs to be invalidated; optionally, the data to be invalidated can be a digital invoice to be red reversal; where the digital invoice to be red reversal refers to a fully digitized electronic invoice that needs to be red reversal. The so-called information to be invalidated refers to information related to invalidation processing in the data to be invalidated; optionally, the information to be invalidated can be information to be red reversal, where the information to be red reversal refers to information related to the red reversal of the digital invoice to be red reversal, including but not limited to invoice type, invoice number, invoice date, purchaser information, etc.

[0041] Optionally, the system can obtain the waiting redemption information of the number of electronic bills to be redempted in response to the redemption request initiated by the redemption initiator. Specifically, when the redemption initiator has a redemption demand for a number of electronic bills, it initiates a redemption request; accordingly, the system obtains the waiting redemption information of the number of electronic bills to be redempted in the redemption request.

[0042] S102, based on the invalidation processing cycle, invalidation processing is performed on the invalid data according to the invalidation information to obtain target invalid data.

[0043] In this embodiment, the invalid processing cycle refers to the entire life cycle of invalid data, that is, the process of invalid data invalid processing; including invalid status and invalid events, wherein the invalid status covers the entire process from the initiation to the delivery of invalid data; invalid events include various invalid initiator intention classification results and system operation event process data cache objects, event condition verification methods, event post-processing methods, and event business logic processing methods for various situations. Optionally, in the digital electricity invoice red check scenario, the invalid processing cycle can be the digital electricity invoice red check cycle; wherein, the digital electricity invoice red check cycle refers to the entire life cycle of the digital electricity invoice red check; optionally, the digital electricity invoice red check cycle includes the digital electricity invoice red check process, including invoice status and red check events; wherein, the invoice status covers the entire process from the initiation to the delivery of the digital electricity red check; red check events include various red check initiator intention classification results and system operation event process data cache objects, event condition verification methods, event post-processing methods, and event business logic processing methods for various situations; exemplarily, such as Figure 2 As shown in the figure, the red-reversal cycle of digital invoices specifically includes 10 types of invoice status and 10 types of red-reversal events; among them, the invoice status includes 0 digital blue invoice issued, 1 digital blue invoice sent, 2 refund review in progress, 3 refund review passed, 4 refund rejected, 5 red invoice issued, 6 refund pending confirmation, 7 digital red-reversal, 8 digital red invoice issued, and 9 digital red invoice sent; red-reversal events include machine review, refund review passed, refund review rejected, user updates refund information, user confirms refund, user cancellation, unconfirmed for more than 72 hours, red invoice issued, red-reversal initiated to the tax control platform, and blue invoice red-reversal and red invoice creation. It should be noted that LR in the figure indicates that the arrow points from left to right.

[0044] The so-called target invalid data refers to the invalid data obtained after invalid processing is performed on the invalid data; optionally, the target invalid data can be a target number of electric red tickets, wherein the target number of electric red tickets refers to the number of electric red tickets after the red-punch number of electric tickets is red-punch.

[0045] Optionally, in conjunction with an external system, based on the red-reversal cycle of digital electricity invoices, the digital electricity invoices to be red-reversed are automatically red-reversed according to the red-reversal information to be received, and the target digital electricity red-reversal invoices are obtained. Specifically, based on the big model, the digital electricity invoices to be red-reversed are automatically red-reversed according to the red-reversal information to be received and the red-reversal cycle of digital electricity invoices, and the target digital electricity red-reversal invoices are obtained.

[0046] The technical solution provided by the embodiment of the present disclosure obtains the to-be-invalidated information of the data to be invalidated by responding to the invalidation processing request initiated by the invalidation initiator, and then performs invalidation processing on the invalid data based on the to-be-invalidated information based on the invalidation processing cycle to obtain the target invalid data. The above technical solution, the present disclosure performs automatic processing on the invalid data based on the invalidation processing cycle, reduces manual operations, and improves the efficiency of invalidation processing, especially in the scenario of red-checking of digital electronic invoices. Compared with the cumbersome process of red-checking of traditional digital electronic invoices, the present disclosure designs a red-checking cycle of digital electronic invoices, automates the red-checking process, and automatically performs red-checking on digital electronic invoices, which reduces manual operations and improves the efficiency of red-checking.

[0047] Based on the above embodiment, as an optional method of the present disclosure, after obtaining the target invalid data, it also includes: generating an invalid query instruction; the invalid query instruction includes an invalid result query instruction and an invalid information query instruction; and sending the invalid query instruction to an external system.

[0048] Among them, the invalid query instruction refers to the instruction involved in the invalid data invalid processing process, including but not limited to the invalid result query instruction and the invalid information query instruction; wherein the invalid result query instruction refers to the instruction used to indicate the feedback of invalid results; the invalid information query instruction refers to the instruction used to query invalid information. Optionally, the invalid query instruction can be a red check query instruction; wherein the red check query instruction refers to the instruction involved in the red check process of electronic invoices, including but not limited to the red check result query instruction and the red invoice information query instruction; wherein the red check result query instruction is used to indicate the instruction to feedback the red check result; the red invoice information query instruction refers to the instruction used to query the red invoice information.

[0049] Among them, the so-called external system refers to other systems that are relied on for invalidation processing of the data to be invalidated; optionally, in the scenario of digital invoice red cancellation, the external system refers to other systems that are relied on for digital invoice red cancellation, including but not limited to financial systems, order systems, billing systems, contract systems, commodity systems, BOS cloud storage systems, tax Leqi platforms, tax systems, etc.

[0050] Optionally, after obtaining the target number of electronic red invoices, a red-refund query instruction is generated; the red-refund query instruction includes a red-refund result query instruction and a red-invoice information query instruction; and the red-refund query instruction is sent to an external system. Specifically, after obtaining the target number of electronic red invoices, a red-refund query instruction is generated, and the red-refund query instruction is sent to an external system such as tax information for further processing.

[0051] It is understandable that by seamlessly connecting the data invalidation processing system with other systems, data sharing and process collaboration can be achieved, thereby improving the overall processing efficiency. Especially in the scenario of digital invoice red-check, by seamlessly connecting the digital invoice red-check system with other systems, data sharing and process collaboration can be achieved, thereby improving the overall operational efficiency of the enterprise.

[0052] On the basis of the above embodiment, as another optional method of the present disclosure, after obtaining the target invalid data, it also includes: updating the fund data associated with the invalid data.

[0053] Optionally, in the scenario of digital invoice red-check, after obtaining the target digital invoice red-check, the fund data associated with the digital invoice to be red-checked is updated. Specifically, after obtaining the target digital invoice red-check, that is, after the red-check is completed, the digital invoice red-check system will synchronize and update various fund data associated with the digital invoice to be red-checked in real time, such as updating the amount of the digital invoice, that is, the amount of the original blue invoice is returned - the rollback of the invoice detail record - the invoiceable amount record - the rollback of the invoiced amount; another example is to perform a reverse transfer of the invoice pool, that is, from the invoice consumption pool to the balance pool, and update the balance of each fund pool of the red-check initiator; another example is to update the status information of the red and blue invoices, and update the amount of the ticket; another example is to create a new red invoice record, various operation records and other information for storage in the warehouse.

[0054] It can be understood that by updating the financial data associated with invalid data, the real-time accuracy of the financial data can be ensured, especially in the scenario of red-check digital invoices, by updating the financial data associated with red-check digital invoices, the real-time accuracy of the invoicing data can be ensured.

[0055] On the basis of the above embodiment, as another optional method of the present disclosure, after obtaining the target invalid data, it also includes: encrypting and storing the target invalid data on the cloud.

[0056] Optionally, in the scenario of digital electricity invoice redemption, the target digital electricity invoice is encrypted and stored in the cloud. Specifically, after obtaining the target digital electricity invoice, the encrypted address information BosBucket is configured for the multi-format file corresponding to the target digital electricity invoice, and uploaded to the cloud storage service; accordingly, the cloud storage service feeds back the storage address information BosBucketKey of the multi-format file to the digital electricity invoice redemption system.

[0057] It can be understood that by encrypting and storing the target invalid data after invalidation processing on the cloud, the number of interactions between systems is reduced while ensuring data security. Especially in the scenario of red-checking digital electricity invoices, by encrypting and storing the target digital electricity red invoices obtained by red-checking on the cloud, the number of interactions between systems is reduced while ensuring data security. Only one interaction is required to ensure that the red invoices can be permanently downloaded.

[0058] Based on the above embodiment, as another optional method of the present disclosure, after obtaining the target invalid data, the method further includes: pushing the target invalid data in real time through a multi-format file.

[0059] Optionally, in the scenario of digital invoice redemption, the target digital invoice redemption is pushed in real time through multi-format files. Specifically, after obtaining the target digital invoice redemption, the digital invoice redemption system automatically triggers the real-time push of multi-format files, i.e., automatic delivery by the electronic tax bureau, automatic push by SMS|email, and query and download on the platform side.

[0060] It is understandable that the target invalid data can be pushed in real time, providing multi-channel file delivery, especially in the scenario of red-check of digital invoices, the red invoices after the red-check can be pushed in real time, providing multi-channel delivery.

[0061] On the basis of the above embodiment, as another optional manner of the present disclosure, it further includes: during the invalidation process, the invalidation processing progress is fed back to the invalidation initiator in real time.

[0062] Among them, the invalid processing progress refers to which invalid node the invalid data flows to in the invalid processing cycle; optionally, in the digital electricity invoice red-refund scenario, the invalid processing progress can be the red-refund processing progress, wherein the red-refund processing progress refers to which red-refund node the red-refund flows to in the digital electricity invoice red-refund cycle.

[0063] Optionally, in the scenario of red-reversal of digital invoices, during the red-reversal process of digital invoices, the progress of the red-reversal processing is fed back to the red-reversal initiator in real time.

[0064] It is understandable that real-time invalidation progress feedback can be provided to the invalidation initiator in real time, so that the invalidation initiator can understand the invalidation processing progress in real time, especially in the red-reversal scenario of digital invoices, real-time red-reversal progress feedback can be provided to the red-reversal initiator in real time, so that the red-reversal initiator can understand the red-reversal processing situation at any time.

[0065] Based on the above embodiments, as another optional method of the present disclosure, after obtaining the invalid information of the data to be invalidated, it also includes: performing data processing on the invalid information; the data processing includes at least one of data cleaning, data verification and data pre-storage.

[0066] Optionally, in the scenario of red-checking of digital invoices, data processing can be performed on the red-checking information; data processing includes at least one of data cleaning, data verification and data pre-storage. Specifically, data cleaning is performed on the red-checking information, such as filtering out useless or erroneous data. Data verification is performed on the red-checking information, such as verifying whether the invoice number is correct, whether the invoice amount is correct, etc.; data pre-storage is performed on the verified red-checking information.

[0067] It can be understood that data processing of invalid information can ensure the accuracy of data in the subsequent invalid processing process, especially in the scenario of red-check of digital invoices, data processing of red-check information can ensure the accuracy of data in the subsequent red-check process.

[0068] Figure 3 1 is a flowchart of another data invalidation processing method provided according to an embodiment of the present disclosure; based on the above embodiment, this embodiment further optimizes "based on the invalidation processing cycle, invalidation processing of invalid data according to the invalidation information" to provide an optional implementation scheme. Figure 3 As shown, the data invalidation processing method of this embodiment may include:

[0069] S201, in response to an invalidation processing request initiated by an invalidation initiator, obtaining information on data to be invalidated.

[0070] S202, obtaining condition verification data, and determining whether the data to be invalidated meets the invalidation condition according to the condition verification data and the information to be invalidated.

[0071] In this embodiment, conditional verification data refers to the correct data used to verify the invalid condition of invalid information. The so-called invalid condition refers to the condition used to verify invalid processing; optionally, the invalid condition can be a red-check condition in the digital invoice red-check scenario, wherein the red-check condition includes identity authentication, red-check condition on the invoice side and red-check condition on the tax side; optionally, the rules and algorithms corresponding to the traditional red-check conditions are integrated to obtain the red-check conditions; wherein, identity authentication refers to the identity authentication of the role of the red-check initiator, whether the identity of the red-check initiator is consistent with the identity of the account to which the digital invoice belongs, and whether the red-check initiator is an operational authority with an organizational structure relationship; the red-check condition on the invoice side refers to whether the original blue ticket data information is correct, the digital invoice status is in a red-checkable state, consumption data (such as orders or bills) verification, contract|goods|red-check amount verification, etc.; the red-check condition on the tax side refers to whether the invoice has been deducted, whether the red-letter confirmation form information is normal, etc.

[0072] Optionally, conditional verification data can be obtained from an external system, and the conditional verification data can be compared with the information to be invalidated to determine whether the data to be invalidated meets the invalidation condition. Specifically, in the digital invoice red-check scenario, conditional verification data for identity authentication is obtained from an external system, such as determining whether the identity of the red-check initiator is consistent with the account to which the digital invoice belongs, and whether the red-check initiator is an authorized person with an organizational structure relationship; conditional verification data corresponding to the red-check conditions on the invoice side is obtained from an external system, such as whether the original blue invoice data information is correct, whether the digital invoice status is in a red-checkable state, consumption data (such as orders or bills) verification, contract|goods|red-check amount verification, etc.; conditional verification data corresponding to the red-check conditions on the tax side is obtained from an external system, such as whether the invoice has been deducted, whether the red-letter confirmation form information is normal, etc.

[0073] S203: If the invalidation condition is met, the machine verification data is obtained, and the invalid data is subjected to machine verification based on the machine verification data and the invalidation information.

[0074] In this embodiment, the machine review verification data refers to verification data used for automatic machine review of invalid information, such as approval rules.

[0075] An optional method is to obtain machine review verification data from an external system if the invalidation condition is met, and perform machine review on the invalid data based on the machine review verification data; if the invalidation condition is not met, the invalid data is not invalidated.

[0076] Optionally, in the scenario of a red-check for digital invoices, if the red-check conditions are met, the machine review verification data is obtained from the external system, and the invalid data is subject to machine review based on the machine review verification data and the information to be red-checked; if the red-check conditions are not met, the red-check digital invoice will not be processed.

[0077] S204, after passing the machine review, based on the invalid processing cycle, the invalid data is invalidated according to the invalid information to obtain the target invalid data.

[0078] The technical solution provided by the embodiment of the present disclosure obtains the information to be invalidated of the data to be invalidated by responding to the invalidation processing request initiated by the invalidation initiator, and then obtains the conditional verification data, and determines whether the data to be invalidated meets the invalidation condition according to the conditional verification data and the information to be invalidated. If the invalidation condition is met, the machine review verification data is obtained, and the invalid data is machine reviewed according to the machine review verification data and the information to be invalidated. After the machine review passes, the invalid data is invalidated according to the information to be invalidated based on the invalidation processing cycle. The above technical solution can ensure the compliance of subsequent invalid operations by judging the invalidation conditions of the invalid data, especially in the scenario of red-checking digital invoices, by judging the red-checking conditions of the red-checked digital invoices, understanding and applying the red-checking rules, and ensuring the compliance of the red-checking operation.

[0079] On the basis of the above embodiments, as an optional method of the present disclosure, based on the invalid processing cycle, invalid processing is performed on the invalid data according to the information to be invalidated, including: determining the current invalid node of the data to be invalidated in the invalid processing cycle; based on the invalid processing logic corresponding to the current invalid node, processing the invalid data according to the information to be invalidated to obtain the current invalid event; in response to the processing operation of the current invalid event by the invalidation initiator, obtaining the current invalid state of the data to be invalidated; according to the current invalid state, determining the next invalid node of the data to be invalidated in the invalid processing cycle, and transferring the data to be invalidated to the next invalid node.

[0080] Among them, invalid nodes refer to nodes in the invalid processing process in the invalid processing cycle; usually, invalid processing of invalid data requires multiple invalid nodes. The so-called invalid processing logic refers to the data processing logic corresponding to the invalid processing node for related processing of invalid data, such as the logic related to the issuance of red tickets in the red-check of digital invoices.

[0081] Optionally, in the scenario of red-checking digital invoices, determine the current red-check node of the digital invoice to be red-checked in the red-check cycle of the digital invoices, process the digital invoice to be red-checked according to the red-checking information based on the red-checking processing logic corresponding to the current red-checking node, obtain the current invalid event, respond to the red-check initiator's processing operation on the current invalid event, such as confirmation operation, etc., obtain the current red-check state of the digital invoice to be red-checked, and then determine the next invalid node of the digital invoice to be red-checked in the red-check cycle of the digital invoice according to the current red-checking state, and transfer the digital invoice to be red-checked to the next red-checking node, for example Figure 2 As shown in , if the current red refund status is that the refund has been approved, the next red refund node will be entered to issue a red ticket.

[0082] It can be understood that by processing the invalid data based on the relevant specific circumstances of the invalid status and invalid events in the invalid processing cycle, the invalid processing process is made more automated and the efficiency of invalid processing is improved, especially in the scenario of red-cancellation of digital invoices, the efficiency of red-cancellation can be improved.

[0083] Figure 4 1 is a flowchart of another data invalidation processing method provided according to an embodiment of the present disclosure; based on the above embodiment, this embodiment further optimizes "obtaining invalidation information of data to be invalidated" and provides an optional implementation scheme. Figure 4 As shown, the data invalidation processing method of this embodiment may include:

[0084] S301, in response to an invalidation processing request initiated by an invalidation initiator, obtaining an image to be invalidated of data to be invalidated.

[0085] In this embodiment, the image to be invalidated refers to an image of data to be invalidated that needs to be invalidated; optionally, the image to be invalidated may be an image of an invoice to be red-coordinated, wherein the invoice image to be red-coordinated refers to an image of a digital invoice that needs to be red-coordinated, such as a scanned copy of a project invoice.

[0086] Optionally, in a scenario of red-reversal of digital electronic invoices, in response to a red-reversal request from the initiator of the red-reversal, an invoice image of the digital electronic invoice to be red-reversed in the red-reversal request is obtained.

[0087] S302, using a data recognition model to recognize the image to be invalidated, and obtaining invalidation information of the data to be invalidated.

[0088] Among them, the data recognition model is used to identify the information to be invalidated of the data to be invalidated in the image to be invalidated; optionally, the data recognition model can be an invoice recognition model, wherein the invoice recognition model is used to identify the information to be red-checked of the electronic invoice to be red-checked, and can be a model composed of a neural network.

[0089] In an optional manner, the image to be invalidated can be input into a data recognition model, and after model recognition, the invalidation information of the data to be invalidated can be obtained. Optionally, in the scenario of a red-check of a digital invoice, the image of the invoice to be red-checked can be input into a data recognition model, and after model recognition, the red-check information of the digital invoice to be red-checked can be obtained.

[0090] Furthermore, the data recognition model may include a text detection model, a direction classifier and a text recognition model; wherein the text detection model is used to detect text in images to be invalidated, and in the digital invoice red-check scenario, it is used to detect text in invoices to be red-checked; the direction classifier is used to perform angle correction on detected text blocks or text lines; and the text recognition model is used to perform text recognition.

[0091] Correspondingly, a data recognition model is used to identify the invalid data to obtain the invalid information of the invalid data, including: using a text detection model to perform field recognition on the invalid image to obtain the key field text line; using a direction classifier to perform angle correction on the key field text line; using a text recognition model to perform text recognition on the corrected key field text line to obtain the invalid information of the invalid data.

[0092] The key field text line refers to the text line image to which a specific field belongs.

[0093] Optionally, a text detection model is used to perform field recognition on the image of the invoice to be redeemed to obtain text lines of key fields; a direction classifier is used to perform angle correction on the text lines of key fields; a text recognition model is used to perform text recognition on the corrected text lines of key fields to obtain the pending redeemed information of the invoice to be redeemed. Specifically, a text detection model can be used to perform specific field recognition on the image of the invoice to be redeemed to obtain text lines of key fields, and then, in scenes where the image is not 0 degrees, a direction classifier is used to perform angle correction on the text lines of key fields, that is, an affine transformation is performed on the text lines of key fields, and then a text recognition model is used to perform character-level text recognition on the corrected text lines of key fields to obtain the pending redeemed information of the invoice to be redeemed.

[0094] It can be understood that the recognition accuracy can be improved by determining the information to be invalidated, such as the information to be redacted, through the text detection model, the direction classifier and the text recognition model.

[0095] S303, based on the invalidation processing cycle, invalidation processing is performed on the invalid data according to the invalidation information to obtain target invalid data.

[0096] The technical solution provided by the embodiment of the present disclosure, in response to the red-check request initiated by the red-check initiator, obtains the to-be-invalidated image of the data to be invalidated, then uses the data recognition model to recognize the to-be-invalidated image, obtains the to-be-invalidated information of the data to be invalidated, and then based on the invalidation processing cycle, performs invalidation processing on the invalid data according to the to-be-invalidated information, and obtains the target invalid data. The above technical solution, through the invoice recognition model to perform image recognition of the invoice to be red-checked, can accurately obtain the to-be-invalidated information of the electronic invoice to be red-checked, and reduce the probability of red-check errors.

[0097] On the basis of the above embodiments, as an optional method of the present disclosure, obtaining the information to be invalidated of the data to be invalidated includes: obtaining the original information of the data to be invalidated input or uploaded by the invalidation initiator; performing multiple rounds of dialogue extraction on the original information based on the big model to obtain the information to be invalidated of the data to be invalidated.

[0098] Among them, the original information refers to the specific information in the data to be invalidated. Optionally, the original information in the digital invoice redemption scenario can be the digital invoice information, wherein the digital invoice information refers to the specific invoice information on the digital invoice to be redemption.

[0099] Optionally, in the scenario of red-checking digital invoices, obtain the digital invoice information of the digital invoice to be red-checked input or uploaded by the initiator of the red-check; extract the digital invoice information through multiple rounds of dialogue based on the big model to obtain the red-check information of the digital invoice to be red-checked. Specifically, the initiator of the red-check can input or upload the digital invoice information of the digital invoice to be red-checked in the digital invoice red-check system, and then the digital invoice red-check system can call the big model to conduct multiple rounds of dialogue on the digital invoice information to extract the red-check information of the digital invoice to be red-checked.

[0100] It can be understood that by providing a system for the invalidation initiator to upload or input the data to be invalidated based on his own needs, and obtaining the invalidation information of the data to be invalidated based on multiple rounds of dialogues based on a large model, the acquired invalidation information can be made more accurate, especially in the scenario of red-checking of several electronic invoices, by providing a system for the red-check initiator to upload or input the data to be invalidated based on his own needs, and obtaining the invalidation information of the data to be invalidated based on multiple rounds of dialogues based on a large model, the acquired invalidation information can be made more accurate.

[0101] Based on the above embodiment, as another optional method of the present disclosure, obtaining the information of the data to be invalidated includes: obtaining the invalidation intention of the invalidation initiator; based on the Prompt generator, generating the information of the data to be invalidated according to the invalidation intention.

[0102] Among them, invalid intention refers to the invalid data related information that the invalid initiator needs to invalidate in a specific scenario; optionally, the invalid intention can be a red-refund intention, wherein the red-refund intention refers to the digital invoice related information that the red-refund initiator needs to red-refund in a specific scenario. The prompt generator can customize the output data format of different invalid scenarios, such as the red-refund scenario of invoices.

[0103] Optionally, in the scenario of red-reversal of digital invoices, the red-reversal intention of the red-reversal initiator can be obtained; based on the Prompt generator, the red-reversal information of the digital invoices to be red-reversed is generated according to the red-reversal intention.

[0104] Specifically, the red-reversal intention of the red-reversal initiator can be obtained through voice or text input, and then based on the prompt generator, the red-reversal information of the number of electronic invoices to be red-reversed is generated according to the red-reversal intention. For example, 1 Help me to red-reversal a certain invoice, specify the invoice number; 2 The user directly uploads the blue invoice information for red-reversal; 3 Help me check which invoices can be red-reversed at present, and the system needs to further provide a list of the number of electronic blue invoices that can be red-reversed by the specified red-reversal initiator, etc.

[0105] It can be understood that based on the Prompt generator, the structured output data format of each scenario can be customized, and the method of obtaining the invalidation information of the data to be invalidated is more flexible and rich, especially in the scenario of red-check of digital invoices, which makes the method of obtaining the red-check information of digital invoices to be red-checked more flexible and rich.

[0106] Figure 5 This is a flow chart of a data invalidation processing method provided according to an embodiment of the present disclosure. This embodiment is applicable to the case of how to perform data invalidation processing, and is particularly applicable to the case of how to perform red-checking on digital electronic tickets. The device can be implemented in software and / or hardware, and can be integrated into an electronic device that carries the data invalidation processing function, such as a third-party platform, such as an enterprise office software terminal. Figure 5 As shown, the data invalidation processing method of this embodiment may include:

[0107] S401, obtaining the invalidation intention of the invalidation initiator.

[0108] Among them, the invalid intention can be the red-check intention in the electronic ticket counting scenario.

[0109] Optionally, in the scenario of red-reversal of digital invoices, the red-reversal intention of the red-reversal initiator can be obtained. Specifically, the red-reversal intention of the red-reversal initiator can be obtained by triggering the red-reversal application of digital invoices in the third-party platform, such as clicking the red-reversal function button.

[0110] S402, remotely call the application program interface API service of the data invalidation plug-in, and perform invalidation processing according to the invalidation intention.

[0111] Optionally, in the scenario of red-reversal of digital invoices, the application program interface API service of the red-reversal plug-in of digital invoices can be remotely called to perform red-reversal of digital invoices according to the red-reversal intention.

[0112] Among them, the data invalidation plug-in is used to implement the data invalidation processing method provided by any embodiment of the present disclosure; optionally, the data invalidation plug-in can be a digital electric invoice red check plug-in, wherein the implementation of the digital electric invoice red check plug-in includes plug-in registration, plug-in parsing and plug-in triggering, wherein, plug-in registration: the invoice business side, that is, the side where the digital electric invoice red check system is located, registers the openAPI configuration file of the plug-in into the plug-in library, and after the review is passed and put on the shelf, the super assistant can use the specified plug-in to process the red check intention query of the red check initiator; plug-in parsing: identify the red check intention query, select the corresponding plug-in according to the natural language description of the plug-in API interface and parameters in the openAPI configuration file, and generate an API for calling the plug-in service, recorded as the calling API; plug-in triggering: use the calling API to remotely call the application program interface API service of the digital electric invoice red check plug-in, and perform the digital electric invoice red check according to the red check intention. After the digital electric invoice red check system completes the red check, the red check result and other related data are returned to the third-party platform in JSON format for display.

[0113] The technical solution provided by the embodiment of the present disclosure obtains the invalidation intention of the invalidation initiator, remotely calls the application program interface API service of the data invalidation plug-in, and performs invalidation processing according to the invalidation intention. The above technical solution directly enters the data invalidation processing system in the form of a plug-in to perform data invalidation processing, making data invalidation processing more efficient and flexible and convenient, especially in the scenario of digital electricity ticket red reversal, directly enters the digital electricity ticket red reversal system in the form of a plug-in to perform digital electricity ticket red reversal, making digital electricity ticket red reversal more efficient and flexible and convenient.

[0114] A specific example, such as Figure 6As shown in the figure, the digital invoice red-check system is a system block diagram of the digital invoice intelligent red-check system. The red-check initiator Actor initiates the red-check. After the plug-in registration and configuration, the intelligent application is released, the plug-in service corresponding to the digital invoice red-check system is remotely called, and data is interacted with the external system to realize the red-check of the digital invoice. Among them, the Qianfan large model EB4.0 realizes the acquisition of the red-check information of the digital invoice to be red-checked. The core model of the system combines multi-system integration and performs intelligent circulation of digital invoices based on the digital invoice red-check life cycle (i.e., the digital invoice red-check cycle). Among them, the data processing module is used to process the red-check information, such as cleaning, verification and pre-storage; the rule judgment module is used to judge the red-check conditions of the digital invoice to be red-checked; the intelligent approval module is used to conduct machine review of the digital invoice to be red-checked; the instruction generation module is used to generate various query instructions during or after the red-check is completed; the fund processing module is used to update the fund data associated with the digital invoice to be red-checked in real time after the red-check is completed; the intelligent delivery module is used to perform cloud encrypted storage and multi-format intelligent push of the digital invoice after the red-check is completed.

[0115] This disclosure can save a lot of time and human resources by automating the red-check business, thereby improving financial management efficiency and reducing operating costs. The digital invoice red-check system can seamlessly connect with other enterprise systems to achieve data sharing and process collaboration, improving the overall operational efficiency of the enterprise. The red-check rules for digital invoices are relatively complex, including partial red-check, full red-check, and red-check restrictions in different scenarios. The digital invoice red-check system can accurately understand and apply these rules to ensure the compliance of red-check operations.

[0116] Figure 7 This is a schematic diagram of the structure of a data invalidation processing device provided according to an embodiment of the present disclosure. This embodiment is applicable to situations where data invalidation is handled, and in particular, to situations where digital electronic tickets are red-checked. The device can be implemented in software and / or hardware, and can be integrated into an electronic device that carries the data invalidation processing function, such as a data invalidation processing system on a PC, specifically a digital electronic ticket red-checking system. Figure 7 As shown, the data invalidation processing device 500 of this embodiment may include:

[0117] The to-be-invalidated information acquisition module 501 is used to obtain the to-be-invalidated information of the to-be-invalidated data in response to the invalidation processing request initiated by the invalidation initiator;

[0118] The invalidation processing module 502 is used to perform invalidation processing on the invalid data according to the invalidation information based on the invalidation processing cycle to obtain target invalid data.

[0119] The technical solution provided by the embodiment of the present disclosure obtains the to-be-invalidated information of the data to be invalidated by responding to the invalidation processing request initiated by the invalidation initiator, and then performs invalidation processing on the invalid data based on the to-be-invalidated information based on the invalidation processing cycle to obtain the target invalid data. The above technical solution, the present disclosure performs automatic processing on the invalid data based on the invalidation processing cycle, reduces manual operations, and improves the efficiency of invalidation processing, especially in the scenario of red-checking of digital electronic invoices. Compared with the cumbersome process of red-checking of traditional digital electronic invoices, the present disclosure designs a red-checking cycle of digital electronic invoices, automates the red-checking process, and automatically performs red-checking on digital electronic invoices, which reduces manual operations and improves the efficiency of red-checking.

[0120] Furthermore, the invalid processing module 502 is used to:

[0121] Acquire conditional verification data, and determine whether the data to be invalidated meets the invalidation condition based on the conditional verification data and the information to be invalidated;

[0122] If the invalidation condition is met, the machine verification data is obtained, and the invalid data is machine-verified based on the machine verification data and the invalidation information;

[0123] After passing the machine review, based on the invalid processing cycle, the invalid data will be invalidated according to the information to be invalidated.

[0124] Furthermore, the invalid processing module 502 is used to:

[0125] Determine the current invalid node of the data to be invalidated in the invalidation processing cycle;

[0126] Based on the invalid processing logic corresponding to the current invalid node, the invalid data is processed according to the invalid information to obtain the current invalid event;

[0127] In response to the invalidation initiator's processing operation on the current invalidation event, obtaining the current invalidation state of the data to be invalidated;

[0128] According to the current invalid state, the next invalid node of the data to be invalidated in the invalid processing cycle is determined, and the data to be invalidated is transferred to the next invalid node.

[0129] Furthermore, the module 501 for obtaining invalid information is specifically used for:

[0130] Obtaining the original information of the data to be invalidated input or uploaded by the invalidation initiator;

[0131] Based on the large model, multiple rounds of dialogue extraction are performed on the original information to obtain the invalid information of the invalid data.

[0132] Furthermore, the module 501 for obtaining invalid information is specifically used for:

[0133] Get the invalid intent of the invalid initiator;

[0134] Based on the Prompt generator, the invalidation information of the data to be invalidated is generated according to the invalidation intention.

[0135] Furthermore, the module 501 for obtaining invalid information includes:

[0136] An image to be invalidated acquiring unit, used for acquiring an image to be invalidated of data to be invalidated;

[0137] The unit for determining the information to be invalidated is used to use a data recognition model to identify the image to be invalidated and obtain the information to be invalidated of the data to be invalidated; wherein the data recognition model includes a text detection model, a direction classifier and a text recognition model.

[0138] Furthermore, the unit for determining the information to be invalid is specifically used for:

[0139] Use the text detection model to identify the fields of invalid images and obtain the key field text lines;

[0140] Use the direction classifier to correct the angle of the key field text line;

[0141] A text recognition model is used to perform text recognition on the corrected key field text lines to obtain the invalidation information of the invalidation data.

[0142] Furthermore, the device also includes an instruction generation module, which is used to:

[0143] After obtaining the target invalid data, an invalid query instruction is generated; the invalid query instruction includes an invalid result query instruction and an invalid information query instruction;

[0144] An invalid query command was sent to an external system.

[0145] Furthermore, the device also includes a funds updating module, which is used to:

[0146] After obtaining the target invalid data, the fund data associated with the invalid data is updated.

[0147] Furthermore, the device also includes an encryption storage module, which is used to:

[0148] After obtaining the target invalid data, the target invalid data is encrypted and stored in the cloud.

[0149] Furthermore, the device also includes an invalid push module, which is used to:

[0150] After obtaining the target invalid data, the target invalid data is pushed in real time through multi-format files.

[0151] Furthermore, the device also includes a progress feedback module, which is used to:

[0152] During the invalidation process, the progress of the invalidation process is fed back to the invalidation initiator in real time.

[0153] Furthermore, the device also includes a data processing module, which is used to:

[0154] After obtaining the information of the data to be invalidated, data processing is performed on the information to be invalidated; the data processing includes at least one of data cleaning, data verification and data pre-storage.

[0155] Figure 8 1 is a schematic diagram of the structure of another device for redemption of digital electronic invoices provided according to an embodiment of the present disclosure. This embodiment is applicable to the case of how to perform data invalidation processing, and is particularly applicable to the case of how to redemption of digital electronic invoices. The device can be implemented in software and / or hardware, and can be integrated into an electronic device that carries the data invalidation processing function, such as a third-party platform, such as an enterprise office software terminal. Figure 8 As shown, the data invalidation processing device 600 of this embodiment may include:

[0156] The invalid intention acquisition module 601 is used to acquire the invalid intention of the invalid initiator;

[0157] The invalidation processing module 602 is used to remotely call the application program interface API service of the data invalidation plug-in to perform invalidation processing according to the invalidation intention; the data invalidation plug-in is used to implement the data invalidation processing method of any embodiment of the present disclosure.

[0158] The technical solution provided by the embodiment of the present disclosure obtains the invalidation intention of the invalidation initiator, remotely calls the application program interface API service of the data invalidation plug-in, and performs invalidation processing according to the invalidation intention. The above technical solution directly enters the data invalidation processing system in the form of a plug-in to perform data invalidation processing, making data invalidation processing more efficient and flexible and convenient, especially in the scenario of digital electricity ticket red reversal, directly enters the digital electricity ticket red reversal system in the form of a plug-in to perform digital electricity ticket red reversal, making digital electricity ticket red reversal more efficient and flexible and convenient.

[0159] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0160] Fig. 9 It is a block diagram of an electronic device used to implement the data invalidation processing method of the embodiment of the present disclosure. Fig. 9A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0161] like Fig. 9 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0162] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0163] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as data invalidation processing methods. For example, in some embodiments, the data invalidation processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the data invalidation processing method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the data invalidation processing method in any other appropriate manner (e.g., by means of firmware).

[0164] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0166] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0168] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0169] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0170] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning technology, big data processing technology, knowledge graph technology, and other major directions.

[0171] Cloud computing refers to a technology system that uses network access to elastically scalable shared physical or virtual resource pools. Resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on demand and in a self-service manner. Cloud computing technology can provide efficient and powerful data processing capabilities for technical applications such as artificial intelligence and blockchain, as well as model training.

[0172] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0173] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for processing invalid data, the method comprising: In response to an invalidation processing request initiated by an invalidation initiator, obtaining information on the data to be invalidated; Based on the invalidation processing cycle, the data to be invalidated is invalidated according to the information to be invalidated to obtain target invalid data.

2. The method according to claim 1, wherein: Based on the invalidation processing cycle, invalidation processing is performed on the data to be invalidated according to the information to be invalidated, including: Acquire condition verification data, and determine whether the data to be invalidated meets the invalidation condition according to the condition verification data and the information to be invalidated; If the invalidation condition is met, obtaining machine review verification data, and performing machine review on the data to be invalidated according to the machine review verification data and the information to be invalidated; After passing the machine review, based on the invalidation processing cycle, the data to be invalidated is invalidated according to the information to be invalidated.

3. The method according to claim 1 or 2, wherein: Based on the invalidation processing cycle, invalidation processing is performed on the data to be invalidated according to the information to be invalidated, including: Determine the current invalid node of the data to be invalidated in the invalidation processing cycle; Based on the invalidation processing logic corresponding to the current invalid node, the data to be invalidated is processed according to the invalidation information to obtain a current invalidation event; In response to the invalidation initiator's processing operation on the current invalidation event, obtaining the current invalidation state of the data to be invalidated; According to the current invalid state, the next invalid node of the data to be invalidated in the invalidation processing cycle is determined, and the data to be invalidated is transferred to the next invalid node.

4. The method according to claim 1, wherein: The obtaining of information about data to be invalidated includes: Obtaining the original information of the data to be invalidated input or uploaded by the invalidation initiator; Based on the large model, multiple rounds of dialogue extraction are performed on the original information to obtain the invalid information of the data to be invalidated.

5. The method according to claim 1, wherein: The obtaining of information about data to be invalidated includes: Get the invalid intent of the invalid initiator; Based on the Prompt generator, the to-be-invalidated information of the to-be-invalidated data is generated according to the invalidation intention.

6. The method according to claim 1, wherein: The obtaining of information about data to be invalidated includes: Obtain an image to be invalidated of the data to be invalidated; A data recognition model is used to recognize the image to be invalidated, and invalidation information of the data to be invalidated is obtained; wherein the data recognition model includes a text detection model, a direction classifier and a text recognition model.

7. The method according to claim 6, wherein: The method of using a data recognition model to recognize invalid data and obtaining invalid information of the invalid data includes: Using the text detection model to perform field recognition on the image to be invalidated to obtain key field text lines; Using the direction classifier to perform angle correction on the key field text line; The text recognition model is used to perform text recognition on the corrected key field text line to obtain the invalidation information of the invalidation data.

8. The method according to claim 1, wherein: After getting the target invalid data, it also includes: Generate an invalid query instruction; the invalid query instruction includes an invalid result query instruction and an invalid information query instruction; The invalid query instruction is sent to an external system.

9. The method according to claim 1, wherein: After getting the target invalid data, it also includes: The fund data associated with the data to be invalidated is updated.

10. The method according to claim 1, wherein: After getting the target invalid data, it also includes: The target invalid data is encrypted and stored in the cloud.

11. The method according to claim 1, wherein: After getting the target invalid data, it also includes: The target invalid data is pushed in real time through multi-format files.

12. The method according to claim 1, wherein: Also includes: During the invalidation process, the progress of the invalidation process is fed back to the invalidation initiator in real time.

13. The method according to claim 1, wherein: After obtaining the invalidation information of the data to be invalidated, it also includes: Data processing is performed on the information to be invalidated; the data processing includes at least one of data cleaning, data verification and data pre-storage.

14. A method for processing invalid data, applied to a third-party platform, the method comprising: Get the invalid intent of the invalid initiator; Remotely call the API service of the data invalidation plug-in to perform invalidation processing according to the invalidation intention; The data invalidation plug-in is used to implement the data invalidation processing method described in any one of claims 1-13.

15. A data invalidation processing device, the device comprising: The module for acquiring information to be invalidated is used to acquire information of data to be invalidated in response to an invalidation processing request initiated by an invalidation initiator; The invalidation processing module is used to perform invalidation processing on the data to be invalidated based on the invalidation processing cycle and the information to be invalidated to obtain target invalid data.

16. The device according to claim 15, wherein: The invalid processing module is used to: Acquire condition verification data, and determine whether the data to be invalidated meets the invalidation condition according to the condition verification data and the information to be invalidated; If the invalidation condition is met, obtaining machine review verification data, and performing machine review on the data to be invalidated according to the machine review verification data and the information to be invalidated; After passing the machine review, based on the invalidation processing cycle, the data to be invalidated is invalidated according to the information to be invalidated.

17. The device according to claim 15 or 16, wherein: The invalid processing module is used for: Determine the current invalid node of the data to be invalidated in the invalidation processing cycle; Based on the invalidation processing logic corresponding to the current invalid node, the data to be invalidated is processed according to the invalidation information to obtain a current invalidation event; In response to the invalidation initiator's processing operation on the current invalidation event, obtaining the current invalidation state of the data to be invalidated; According to the current invalid state, the next invalid node of the data to be invalidated in the invalidation processing cycle is determined, and the data to be invalidated is transferred to the next invalid node.

18. The device according to claim 15, wherein: The module for obtaining information to be invalidated is specifically used for: Obtaining the original information of the data to be invalidated input or uploaded by the invalidation initiator; Based on the large model, multiple rounds of dialogue extraction are performed on the original information to obtain the invalid information of the data to be invalidated.

19. The device according to claim 15, wherein: The module for obtaining information to be invalidated is specifically used for: Get the invalid intent of the invalid initiator; Based on the Prompt generator, the to-be-invalidated information of the to-be-invalidated data is generated according to the invalidation intention.

20. The device according to claim 15, wherein: The module for obtaining information to be invalidated includes: An image to be invalidated acquiring unit, used for acquiring an image to be invalidated of data to be invalidated; The unit for determining the information to be invalidated is used to use a data recognition model to identify the image to be invalidated to obtain the information to be invalidated of the data to be invalidated; wherein the data recognition model includes a text detection model, a direction classifier and a text recognition model.

21. The device according to claim 20, wherein: The unit for determining the information to be invalidated is specifically used to: Using the text detection model to perform field recognition on the image to be invalidated to obtain key field text lines; Using the direction classifier to perform angle correction on the key field text line; The text recognition model is used to perform text recognition on the corrected key field text line to obtain the invalidation information of the invalidation data.

22. The device according to claim 15, wherein: The device also includes an instruction generation module, which is used to: After obtaining the target invalid data, an invalid query instruction is generated; the invalid query instruction includes an invalid result query instruction and an invalid information query instruction; The invalid query instruction is sent to an external system.

23. The device according to claim 15, wherein: The device also includes a funds updating module, which is used to: After obtaining the target invalid data, the fund data associated with the invalid data is updated.

24. The device according to claim 15, wherein: The device also includes an encryption storage module, which is used to: After the target invalid data is obtained, the target invalid data is encrypted and stored in the cloud.

25. The device according to claim 15, wherein: The device also includes an invalid push module, which is used to: After the target invalid data is obtained, the target invalid data is pushed in real time through a multi-format file.

26. The device according to claim 15, wherein: The device also includes a progress feedback module, which is used to: During the invalidation process, the progress of the invalidation process is fed back to the invalidation initiator in real time.

27. The device according to claim 15, wherein: The device also includes a data processing module, which is used to: After obtaining the information to be invalidated of the data to be invalidated, data processing is performed on the information to be invalidated; the data processing includes at least one of data cleaning, data verification and data pre-storage.

28. A data invalidation processing device, configured on a third-party platform, comprising: An invalid intention acquisition module, used to acquire the invalid intention of the invalid initiator; An invalidation processing module is used to remotely call the application program interface API service of the data invalidation plug-in to perform invalidation processing according to the invalidation intention; the data invalidation plug-in is used to implement the data invalidation processing method described in any one of claims 1-13.

29. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the data invalidation processing method according to any one of claims 1 to 14.

30. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the data invalidation processing method according to any one of claims 1 to 14.

31. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the data invalidation processing method according to any one of claims 1 to 14.

Images