CN113065940B - Method, device, equipment and storage medium for reimbursement of invoice based on artificial intelligence - Google Patents
Method, device, equipment and storage medium for reimbursement of invoice based on artificial intelligence Download PDFInfo
- Publication number
- CN113065940B CN113065940B CN202110460755.XA CN202110460755A CN113065940B CN 113065940 B CN113065940 B CN 113065940B CN 202110460755 A CN202110460755 A CN 202110460755A CN 113065940 B CN113065940 B CN 113065940B
- Authority
- CN
- China
- Prior art keywords
- invoice
- information
- reimbursement
- vector
- specified
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 230000003068 static effect Effects 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 101
- 238000003062 neural network model Methods 0.000 claims description 24
- 125000004122 cyclic group Chemical group 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 14
- 238000012015 optical character recognition Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012550 audit Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 5
- 230000000306 recurrent effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000000977 initiatory effect Effects 0.000 claims 1
- 238000012552 review Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 6
- 239000000123 paper Substances 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000003999 initiator Substances 0.000 description 1
- 210000003061 neural cell Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000011087 paperboard Substances 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/128—Check-book balancing, updating or printing arrangements
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of financial science and technology, and discloses an invoice reimbursement method based on artificial intelligence, which comprises the following steps: acquiring information types of reimbursement invoices selected by a user, wherein the information types comprise picture invoices and text invoices; invoking a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and invoking a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice; checking the background database, and judging whether a history reimbursement record corresponding to the specified information exists or not; if not, the appointed information is assigned to be a dynamic variable of the page through an appointed function; combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill; and starting invoice examination and invoice reimbursement according to the invoice reimbursement bill. The key information of the invoice is used as a dynamic parameter, other information is used as a static parameter, and the invoice reimbursement bill is formed rapidly by combining the key information of the invoice with the static information, so that the electronization of invoice reimbursement data is realized.
Description
Technical Field
The application relates to the field of financial science and technology, in particular to an invoice reimbursement method, device, equipment and storage medium based on artificial intelligence.
Background
In daily management of companies, various kinds of objective invoices need to be checked and reimbursed in a level, corresponding invoice details and invoice list documents are manually filled in by staff according to actual conditions of the invoices in the existing invoice reimbursement flow, financial staff check and establish an invoice document library, but due to the fact that the number of staff needing reimbursement is large, the number of the invoices is various, the form is also various, manual reimbursement tasks of the invoices are heavy, and the invoices cannot be operated by multiple persons in a coordinated manner, so that the reimbursement of the invoices is time-consuming and labor-consuming, errors are easy, and the summarization and management of invoice data are not facilitated.
Disclosure of Invention
The application mainly aims to provide an invoice reimbursement method based on artificial intelligence, which aims to solve the technical problems that the existing invoice reimbursement cannot be processed as electronic data, so that time and labor are wasted, mistakes are easy to occur and summarizing statistics is inconvenient.
The application provides an invoice reimbursement method based on artificial intelligence, which comprises the following steps:
acquiring information types of reimbursement invoices selected by a user, wherein the information types comprise picture invoices and text invoices;
invoking a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and invoking a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice;
checking the background database, and judging whether a history reimbursement record corresponding to the specified information exists in the background database;
if not, the appointed information is assigned to be a dynamic variable of the page through an appointed function;
combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill;
and starting invoice auditing and invoice reimbursement according to the invoice reimbursement bill.
The application also provides an invoice reimbursement device based on the artificial intelligence, which comprises:
the acquisition module is used for acquiring the information type of the reimbursement invoice selected by the user, wherein the information type comprises a picture invoice and a text invoice;
the calling module is used for calling a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and calling a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice;
the judging module is used for checking the background database and judging whether a history reimbursement record corresponding to the specified information exists in the background database;
the assignment module is used for assigning the specified information into the dynamic variable of the page through a specified function if the historical reimbursement record corresponding to the specified information does not exist;
the combination module is used for combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill;
and the starting module is used for starting invoice verification and invoice reimbursement according to the invoice reimbursement list.
The application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method described above.
According to the application, the key information of the newly uploaded invoice is used as a dynamic parameter, the information except the key information of the invoice reimbursement bill is used as a static parameter, then the key information of the invoice is accurately acquired through the invoice type, and the invoice reimbursement bill is combined with the static information to quickly form the invoice reimbursement bill, so that the electronization of invoice reimbursement data is realized, the invoice reimbursement can be quickly completed, the error probability is reduced, the time is saved, and the processing efficiency is improved.
Drawings
FIG. 1 is a schematic flow diagram of a method for artificial intelligence based invoice reimbursement in accordance with an embodiment of the present application;
FIG. 2 is a schematic flow diagram of an artificial intelligence based invoice reimbursement system in accordance with an embodiment of the application;
FIG. 3 is a schematic diagram showing an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Referring to FIG. 1, a method for artificial intelligence based invoice reimbursement in accordance with an embodiment of the application includes:
s1: acquiring information types of reimbursement invoices selected by a user, wherein the information types comprise picture invoices and text invoices;
s2: invoking a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and invoking a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice;
s3: checking the background database, and judging whether a history reimbursement record corresponding to the specified information exists in the background database;
s4: if not, the appointed information is assigned to be a dynamic variable of the page through an appointed function;
s5: combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill;
s6: and starting invoice auditing and invoice reimbursement according to the invoice reimbursement bill.
The invoice reimbursement system provided by the application is composed of the HTML page, can support multiple persons to submit invoices at the same time, and can store invoice information submitted by different users at the same time. And when the user updates invoice information each time, the loading page is dynamically refreshed and loaded through a javascript technology, so that the page loading speed is increased. For example, when only the invoice information content of the invoice reported this time in the HTML page is refreshed, other contents of the HTML page are not changed and serve as static variables, and the static variables are assigned once only when the system is started initially. For the part to be refreshed, the jquery framework of the javascript library is used, and is imported into the current code through tag matching as a dynamic variable. When a user clicks a submit button to submit an invoice, data of the client are transmitted to the background through a location.load () function to refresh the data, after an invoice reimbursement bill is formed, the user terminal submitting the invoice can confirm whether the invoice amount is wrong or not to the invoice reimbursement system after receiving the related amount, and if the invoice amount is wrong, the user terminal clicks the confirmation, and then starts subsequent auditing and reimbursement. If the invoice amount is wrong, describing specific problem content, and feeding back to an invoice reimbursement system to serve as an optimization basis of a model algorithm in the follow-up information identification and acquisition of the invoice reimbursement system.
The specified information includes, but is not limited to, invoice date, invoice code, invoice head, invoice tax number, invoice type, invoice amount, and the like. And the picture invoice and the text invoice are different in acquisition mode, the picture invoice refers to a paperboard invoice, a user is required to scan the picture invoice and then upload a scanned picture to obtain the picture invoice, and the text invoice refers to an electronic invoice and can be acquired by linking with the website of the electronic invoice. The above-mentioned picture invoice specification information is obtained by a combination of OCR (Optical Character Recognition ) and deep neural network. The specified information of the text invoice is obtained through a python crawler mode. The picture invoice and the text invoice are distinguished by reading the file suffix of the invoice uploaded by the user. According to the application, the repeated data check is performed in the background database, so that repeated invoices are prevented from being found in time, the follow-up auditing and calculating processes are borrowed, and the invoice reimbursement accuracy is improved.
According to the application, key information of the newly uploaded invoice is used as a dynamic parameter, information except the key information of the invoice reimbursement bill is used as a static parameter, then the key information of the invoice is accurately acquired as the dynamic parameter by an information acquisition mode corresponding to different invoice types corresponding to the picture invoice and the text invoice, and the key information is combined with the static information to quickly form the invoice reimbursement bill, so that the invoice reimbursement bill can be quickly completed, the error probability is reduced, the time is saved, and the processing efficiency is improved.
Further, the step S6 of starting invoice verification and invoice reimbursement according to the invoice reimbursement ticket includes:
s61: acquiring a designated department to which the user belongs;
s62: selecting a designated audit path corresponding to the designated department;
s63: judging whether the auditing result of the appointed auditing path passes auditing;
s64: if yes, linking a national tax official network, and judging whether invoice information of the invoice reimbursement bill is effective or not;
s65: if yes, the invoice amount of the invoice reimbursement bill is distributed to the bank account corresponding to the user.
The user of the application is a registered user of the system, and the user fills in the information of the department during registration, including but not limited to name, telephone, mailbox, bank card number, etc., and clicks a save button, and the information of the department is stored in a background database. The appointed auditing path and the department information of the appointed department are stored in the background database in an associated mode, and a preset auditing path corresponding to the department information is conveniently and timely selected according to the department information. The appointed auditing path is composed of a plurality of auditing nodes, and the auditing nodes are sequentially arranged according to the auditing grade from low to high.
After each node in the auditing path passes the auditing, the node can automatically request to access the national tax officer network, and determine whether the information of the current invoice is accurate or not from the national tax officer network so as to verify the validity of the invoice. For example, judging that when the page loading is completed, requesting the database in the code to inquire invoice information, comparing the invoice information with the invoice information in the national tax officer web page, and if the invoice information is consistent, the invoice is valid, otherwise, invalidating the invoice. The invoice reimbursement system is bound with the financial system, after invoice filling and checking are completed, the financial system enters a unified check account, after the amount is confirmed to be correct, the amount of reimbursement invoice is automatically billed to a bank account corresponding to the user through the financial system, and personal account billing operation is carried out according to the actual reimbursement amount of the user counted by a background database through bank authorization service. Compared with the existing manual auditing process, the method has the advantages that the digital circulation of information is realized, the auditing process time is saved, the fixation, the storage and the analysis of data are realized through the digitization of the information, the data checking and the global analysis are facilitated, and the accuracy of the information is improved.
Further, after the step S65 of distributing the invoice amount of the invoice slip to the bank account corresponding to the user, the method includes:
s66: acquiring label information selected by an summarized invoice initiated by a request end;
s67: performing multi-table association inquiry in the background database according to the tag information to acquire all invoice reimbursement sheets associated with the tag information;
s68: and displaying all invoice reimbursement sheets on the display page of the request end according to a preset summary table.
In the embodiment of the application, the label information comprises an initiator label, a department label, a time label and the like, and summarized data with different requirements can be realized according to the label information. In the summarizing process, contents conforming to the tag information in multiple tables are copied into a summarizing table in a centralized manner in a multi-table association query mode, all invoice reimbursement bill data corresponding to the tag information are formed, data summarizing display is realized, an invoice total list and a personal list are automatically generated, and paper invoices and electronic invoices are distinguished through source marks. Before writing data into the database, a link is established with the database in the written code, and a link field is established in a database table. And when the electronic invoice information is written into the database, the obtained electronic invoice information is stored into the mark field of the database by using the sql language to form the label information. In order to distinguish paper invoices from electronic invoices, source tags are arranged, for example, the tag flag of the electronic invoice is silently written as 1, and the tag flag of the paper invoice is 0 so as to mark different sources, thereby being beneficial to information summarization according to different tag information, realizing that corresponding data are quickly and conveniently acquired as required and are displayed in a centralized manner, and improving the convenience of data processing and data application.
Further, the step S2 of calling the first information obtaining manner corresponding to the picture invoice to obtain the specified information in the picture invoice includes:
s21: starting a designated optical character recognition algorithm;
s22: scanning the picture invoice through the optical character recognition process to obtain scanning data;
s23: inputting the scanning data into a preset cyclic neural network model to obtain a recognition result;
s24: and taking the identification result as the appointed information in the picture invoice.
In the application, aiming at the paper invoice, in the process of translating the paper invoice into computer characters after scanning the invoice through an OCR character recognition technology, the accuracy of recognition is improved through an RNN (RNN cyclic neural network) model algorithm, and the accuracy of information recognition in the paper invoice is improved through training the model weight with the highest accuracy of training by a training set.
Further, the step S23 of inputting the scan data into a preset recurrent neural network model to obtain a recognition result includes:
s231: converting the scan data into a specified vector;
s232: classifying and identifying the specified vector through a preset clustering algorithm to obtain the clustering probability of the specified vector corresponding to each cluster;
s233: and inputting the clustering probability and the specified vector into the preset cyclic neural network model to obtain a recognition result corresponding to the scanning data.
The application discloses a method for realizing circulation by using a cyclic neural network model, which is characterized in that a preset cyclic neural network model is an RNN cyclic neural network model, a weighting value closest to an actual result is confirmed through a result of a function action by weighting a current input and a previous input, and the last calculated output of the RNN cyclic neural network model is taken as an input. Training according to a time sequence, taking the output of the upper hidden layer as the input of the lower hidden layer, combining the weights of the hidden layers to obtain an output result, recording the training loss of each step of the RNN neural network model through a loss function, and adjusting the weight value of each step until a precise identification result is obtained. Hidden layer at time t: h (t) =z (ux+wh (t-1+b)), Z () is a tanh activation function, Z (x) = (e (x) -e (-x))/(e (x) +e (-x)), and the output layer at time t: o (t) =g (Vh (t) +c), G () is a softmax function, G (x) =1/(1+e (-x)), where x represents input, h represents hidden layer unit, o is output, b and c are preset correction parameters, and U/V/W/is weight.
In order to improve the recognition accuracy of the RNN circulating neural network model on the scanning data, the RNN circulating neural network model is subjected to guiding intervention through an LSTM long-short term gating technology and a K-means clustering algorithm, namely, the data is input through a double-input gate, and meanwhile, the sigmoid activation function of the K-means clustering algorithm and the tanh function of the LSTM long-short term gating technology act on the neural cell state update of the RNN circulating neural network model, so that the similarity of an invoice and each cluster is obtained according to the classification information of the invoice vector, and the recognition character accuracy of the RNN circulating neural network model is improved. The trained RNN cyclic neural network model can lock the recognition range of the input information according to the classification information of the input data, and the recognition accuracy of invoice information is improved.
Further, the step S2 of calling a second information obtaining manner corresponding to the text invoice to obtain the specified information in the text invoice includes:
s201: starting a python crawler to download webpage information corresponding to the text invoice from an electronic invoice website set to be crawled;
s202: storing the webpage information in a temporary database;
s203: and cleaning the data in the temporary data to obtain the specified information corresponding to the text invoice.
In the embodiment of the application, the electronic version text invoice actively captures the invoice information of the electronic version text invoice by the python crawler, and pops up the invoice core information after identifying the invoice information, wherein the invoice core information comprises invoice date, invoice code, invoice number, head-up, tax number and the like, and a user submitting the invoice only needs to input the actual reimbursement amount click confirmation. The URL manager manages the electronic invoice website set to be crawled, downloads the webpage content to the local by using the webpage downloading device, sends a request to the target site server through an HTTP request, obtains webpage link information of all electronic invoices, and stores the webpage link information into a temporary database, so that the webpage link information is convenient for subsequent calling. The obtained webpage link information is stored in a csv file or a database, invoice information content in the webpage link information is cleaned, irrelevant content is removed, main invoice information can be directly obtained, and accuracy of obtaining information in an electronic version text invoice is ensured.
Further, the step S3 of checking the background database to determine whether there is a history reimbursement record corresponding to the specified information in the background database includes:
s31: acquiring a first vector corresponding to the specified information and a second vector corresponding to an invoice specified in the background database, wherein the specified invoice is any invoice in the background database;
s32: calculating a vector similarity value of the first vector and the second vector by a specified formula, wherein the specified formula is thatX represents a vector similarity value, M is the first vector, N is the second vector, mi is a component corresponding to the ith information dimension of the first vector, ni is a component corresponding to the ith information dimension of the second vector, and the first vector and the second vector are provided with p information dimensions with the same arrangement times;
s33: judging whether the vector similarity value is larger than a preset threshold value or not;
s34: if yes, judging that the historical reimbursement records corresponding to the specified information exist in the background database, otherwise, judging that the historical reimbursement records do not exist.
According to the application, invoice information is processed into multi-dimensional vectors according to different information types, and then the similarity among the multi-dimensional vectors is compared for duplicate checking. And the duplicate checking accuracy is improved by referring to all invoice main information.
Referring to FIG. 2, an artificial intelligence based invoice reimbursement device of an embodiment of the application includes:
the acquisition module 1 is used for acquiring the information type of the reimbursement invoice selected by the user, wherein the information type comprises a picture invoice and a text invoice;
the calling module 2 is used for calling a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and calling a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice;
the judging module 3 is used for checking the background database and judging whether a history reimbursement record corresponding to the specified information exists in the background database;
the assignment module 4 is used for assigning the specified information into the dynamic variable of the page through a specified function if the historical reimbursement record corresponding to the specified information does not exist;
the combination module 5 is used for combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill;
and the starting module 6 is used for starting invoice verification and invoice reimbursement according to the invoice reimbursement list.
The explanation of the relevant portions of the corresponding portions of the applicable methods in the embodiments of the present application is not repeated.
Further, the starting module 6 includes:
a first acquiring unit configured to acquire a designated department to which the user belongs;
a selection unit for selecting a specified audit path corresponding to the specified department;
the first judging unit is used for judging whether the auditing result of the appointed auditing path passes the auditing;
the link unit is used for linking the national tax official network if the verification is passed, and judging whether the invoice information of the invoice reimbursement bill is valid or not;
and the distributing unit is used for distributing the invoice amount of the invoice reimbursement bill to the bank account corresponding to the user if the invoice amount is effective.
Further, the starting module 6 includes:
the second acquisition unit is used for acquiring label information selected by the summarized invoice initiated by the request end;
the third acquisition unit is used for carrying out multi-table association inquiry in the background database according to the label information to acquire all invoice reimbursement sheets associated with the label information;
and the display unit is used for displaying all invoice reimbursement sheets on the request end display page according to a preset summary table.
Further, the calling module 2 includes:
a first starting unit for starting a specified optical character recognition algorithm;
the scanning unit is used for scanning the picture invoice through the optical character recognition flow to obtain scanning data;
the input unit is used for inputting the scanning data into a preset cyclic neural network model to obtain an identification result;
and the unit is used for taking the identification result as the specified information in the picture invoice.
Further, the input unit includes:
a conversion subunit for converting the scan data into a specified vector;
the identification subunit is used for carrying out classification identification on the specified vector through a preset clustering algorithm to obtain the clustering probability of the specified vector corresponding to each cluster;
and the input subunit is used for inputting the clustering probability and the specified vector into the preset cyclic neural network model to obtain the identification result corresponding to the scanning data.
Further, the calling module 2 includes:
the second starting unit is used for starting the python crawler to download the webpage information corresponding to the text invoice from the electronic invoice website set to be crawled;
the storage unit is used for storing the webpage information in a temporary database;
and the cleaning unit is used for cleaning the data in the temporary data to obtain the specified information corresponding to the text invoice.
Further, the judging module 3 includes:
a fourth obtaining unit, configured to obtain a first vector corresponding to the specified information and a second vector corresponding to a specified invoice in the background database, where the specified invoice is any invoice in the background database;
a calculation unit for calculating a vector similarity value between the first vector and the second vector by a specified formula, wherein the specified formula is thatX represents a vector similarity value, M is the first vector, N is the second vector, mi is a component corresponding to the ith information dimension of the first vector, ni is a component corresponding to the ith information dimension of the second vector, and the first vector and the second vector are provided with p information dimensions with the same arrangement times;
the second judging unit is used for judging whether the vector similarity value is larger than a preset threshold value or not;
and the judging unit is used for judging that the historical reimbursement record corresponding to the specified information exists in the background database if the historical reimbursement record is larger than the preset threshold value, or else, the historical reimbursement record does not exist.
Referring to fig. 3, in an embodiment of the present application, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store all the data required for the artificial intelligence based invoice reimbursement process. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method of artificial intelligence based invoice reimbursement.
The processor executes the method for reimbursement of the invoice based on the artificial intelligence, which comprises the following steps: acquiring information types of reimbursement invoices selected by a user, wherein the information types comprise picture invoices and text invoices; invoking a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and invoking a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice; checking the background database, and judging whether a history reimbursement record corresponding to the specified information exists in the background database; if not, the appointed information is assigned to be a dynamic variable of the page through an appointed function; combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill; and starting invoice auditing and invoice reimbursement according to the invoice reimbursement bill.
According to the computer equipment, the key information of the newly uploaded invoice is used as the dynamic parameter, the information except the key information of the invoice reimbursement bill is used as the static parameter, then the key information of the invoice is accurately acquired through the invoice type and combined with the static information, the invoice reimbursement bill is rapidly formed, the electronization of invoice reimbursement data is realized, the invoice reimbursement matters can be rapidly completed, the error probability is reduced, the time is saved, and the processing efficiency is improved.
In one embodiment, the step of enabling the processor to audit and reimburse the invoice according to the invoice reimbursement ticket includes: acquiring a designated department to which the user belongs; selecting a designated audit path corresponding to the designated department; judging whether the auditing result of the appointed auditing path passes auditing; if yes, linking a national tax official network, and judging whether invoice information of the invoice reimbursement bill is effective or not; if yes, the invoice amount of the invoice reimbursement bill is distributed to the bank account corresponding to the user.
In one embodiment, after the step of sending the invoice amount of the invoice slip to the bank account corresponding to the user, the processor includes: acquiring label information selected by an summarized invoice initiated by a request end; performing multi-table association inquiry in the background database according to the tag information to acquire all invoice reimbursement sheets associated with the tag information; and displaying all invoice reimbursement sheets on the display page of the request end according to a preset summary table.
In one embodiment, the step of the processor invoking a first information obtaining manner corresponding to the picture invoice to obtain the specified information in the picture invoice includes: starting a designated optical character recognition algorithm; scanning the picture invoice through the optical character recognition process to obtain scanning data; inputting the scanning data into a preset cyclic neural network model to obtain a recognition result; and taking the identification result as the appointed information in the picture invoice.
In one embodiment, the step of inputting the scan data into a preset recurrent neural network model to obtain the identification result includes: converting the scan data into a specified vector; classifying and identifying the specified vector through a preset clustering algorithm to obtain the clustering probability of the specified vector corresponding to each cluster; and inputting the clustering probability and the specified vector into the preset cyclic neural network model to obtain a recognition result corresponding to the scanning data.
In one embodiment, the step of the processor invoking a second information obtaining manner corresponding to the text invoice to obtain the specified information in the text invoice includes: starting a python crawler to download webpage information corresponding to the text invoice from an electronic invoice website set to be crawled; storing the webpage information in a temporary database; and cleaning the data in the temporary data to obtain the specified information corresponding to the text invoice.
In one embodiment, the step of determining, by the processor, whether a history reimbursement record corresponding to the specified information exists in the background database includes: acquiring a first vector corresponding to the specified information and a second vector corresponding to an invoice specified in the background database, wherein the specified invoice is any invoice in the background database; calculating a vector similarity value of the first vector and the second vector by a specified formula, wherein the specified formula is thatX represents a vector similarity value, M is the first vector, N is the second vector, mi is a component corresponding to the ith information dimension of the first vector, ni is a component corresponding to the ith information dimension of the second vector, and the first vector and the second vector are provided with p information dimensions with the same arrangement times; judging whether the vector similarity value is larger than a preset threshold value or not; if yes, judging that the historical reimbursement records corresponding to the specified information exist in the background database, otherwise, judging that the historical reimbursement records do not exist.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for artificial intelligence based invoice reimbursement, comprising: acquiring information types of reimbursement invoices selected by a user, wherein the information types comprise picture invoices and text invoices; invoking a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and invoking a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice; checking the background database, and judging whether a history reimbursement record corresponding to the specified information exists in the background database; if not, the appointed information is assigned to be a dynamic variable of the page through an appointed function; combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill; and starting invoice auditing and invoice reimbursement according to the invoice reimbursement bill.
According to the computer readable storage medium, the key information of the newly uploaded invoice is used as the dynamic parameter, the information except the key information of the invoice reimbursement bill is used as the static parameter, then the key information of the invoice is accurately acquired through the invoice type, the invoice reimbursement bill is combined with the static information, the invoice reimbursement bill is rapidly formed, the electronization of invoice reimbursement data is realized, the invoice reimbursement event can be rapidly completed, the error probability is reduced, the time is saved, and the processing efficiency is improved.
In one embodiment, the step of enabling the processor to audit and reimburse the invoice according to the invoice reimbursement ticket includes: acquiring a designated department to which the user belongs; selecting a designated audit path corresponding to the designated department; judging whether the auditing result of the appointed auditing path passes auditing; if yes, linking a national tax official network, and judging whether invoice information of the invoice reimbursement bill is effective or not; if yes, the invoice amount of the invoice reimbursement bill is distributed to the bank account corresponding to the user.
In one embodiment, after the step of sending the invoice amount of the invoice slip to the bank account corresponding to the user, the processor includes: acquiring label information selected by an summarized invoice initiated by a request end; performing multi-table association inquiry in the background database according to the tag information to acquire all invoice reimbursement sheets associated with the tag information; and displaying all invoice reimbursement sheets on the display page of the request end according to a preset summary table.
In one embodiment, the step of the processor invoking a first information obtaining manner corresponding to the picture invoice to obtain the specified information in the picture invoice includes: starting a designated optical character recognition algorithm; scanning the picture invoice through the optical character recognition process to obtain scanning data; inputting the scanning data into a preset cyclic neural network model to obtain a recognition result; and taking the identification result as the appointed information in the picture invoice.
In one embodiment, the step of inputting the scan data into a preset recurrent neural network model to obtain the identification result includes: converting the scan data into a specified vector; classifying and identifying the specified vector through a preset clustering algorithm to obtain the clustering probability of the specified vector corresponding to each cluster; and inputting the clustering probability and the specified vector into the preset cyclic neural network model to obtain a recognition result corresponding to the scanning data.
In one embodiment, the step of the processor invoking a second information obtaining manner corresponding to the text invoice to obtain the specified information in the text invoice includes: starting a python crawler to download webpage information corresponding to the text invoice from an electronic invoice website set to be crawled; storing the webpage information in a temporary database; and cleaning the data in the temporary data to obtain the specified information corresponding to the text invoice.
In one embodiment, the step of determining, by the processor, whether a history reimbursement record corresponding to the specified information exists in the background database includes: obtaining a first vector corresponding to the specified information and a second vector corresponding to the invoice in the background database,wherein, the appointed invoice is any invoice in the background database; calculating a vector similarity value of the first vector and the second vector by a specified formula, wherein the specified formula is thatX represents a vector similarity value, M is the first vector, N is the second vector, mi is a component corresponding to the ith information dimension of the first vector, ni is a component corresponding to the ith information dimension of the second vector, and the first vector and the second vector are provided with p information dimensions with the same arrangement times; judging whether the vector similarity value is larger than a preset threshold value or not; if yes, judging that the historical reimbursement records corresponding to the specified information exist in the background database, otherwise, judging that the historical reimbursement records do not exist.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present application and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application or directly or indirectly applied to other related technical fields are included in the scope of the application.
Claims (8)
1. A method of invoice reimbursement based on artificial intelligence, comprising:
acquiring information types of reimbursement invoices selected by a user, wherein the information types comprise picture invoices and text invoices;
invoking a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and invoking a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice;
checking the background database, and judging whether a history reimbursement record corresponding to the specified information exists in the background database;
if not, the appointed information is assigned to be a dynamic variable of the page through an appointed function;
combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill;
starting invoice auditing and invoice reimbursement according to the invoice reimbursement bill;
the step of calling a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice comprises the following steps:
starting a python crawler to download webpage information corresponding to the text invoice from an electronic invoice website set to be crawled;
sending a request to a target site server through an HTTP request to obtain webpage link information of all text invoices, and storing the webpage link information into a temporary database;
the acquired webpage link information is stored in a csv file or a database, invoice information content in the webpage link information is cleaned, and specified information corresponding to the text invoice is obtained;
the step of checking the background database and judging whether the background database has the history reimbursement record corresponding to the specified information comprises the following steps:
acquiring a first vector corresponding to the specified information and a second vector corresponding to an invoice specified in the background database, wherein the specified invoice is any invoice in the background database;
calculating a vector similarity value of the first vector and the second vector by a specified formula, wherein the specified formula is thatX represents a vector similarity value, M is the first vector, N is the second vector, mi is a component corresponding to the ith information dimension of the first vector, ni is a component corresponding to the ith information dimension of the second vector, and the first vector and the second vector are provided with p information dimensions with the same arrangement times;
judging whether the vector similarity value is larger than a preset threshold value or not;
if yes, judging that a history reimbursement record corresponding to the specified information exists in the background database, otherwise, judging that the history reimbursement record does not exist;
the method comprises the steps of using a jquery framework of a javascript library for a part to be refreshed, and importing the jquery framework into a current code through tag matching to serve as the dynamic variable; and when only refreshing invoice information content of the current reported invoice in the HTML page, other contents of the HTML page are unchanged and serve as the static variables.
2. The method of claim 1, wherein the steps of initiating invoice reviews and invoice reimbursements according to the invoice reimbursement ticket comprise:
acquiring a designated department to which the user belongs;
selecting a designated audit path corresponding to the designated department;
judging whether the auditing result of the appointed auditing path passes auditing;
if yes, linking a national tax official network, and judging whether invoice information of the invoice reimbursement bill is effective or not;
if yes, the invoice amount of the invoice reimbursement bill is distributed to the bank account corresponding to the user.
3. The method of claim 2, wherein after the step of distributing the invoice amount of the invoice slip to the bank account corresponding to the user, comprising:
acquiring label information selected by an summarized invoice initiated by a request end;
performing multi-table association inquiry in the background database according to the tag information to acquire all invoice reimbursement sheets associated with the tag information;
and displaying all invoice reimbursement sheets on the display page of the request end according to a preset summary table.
4. The method for reimbursement of an invoice based on artificial intelligence according to claim 1, wherein the step of calling a first information acquisition mode corresponding to the picture invoice to acquire the specified information in the picture invoice comprises the steps of:
starting a designated optical character recognition algorithm;
scanning the picture invoice through the optical character recognition process to obtain scanning data;
inputting the scanning data into a preset cyclic neural network model to obtain a recognition result;
and taking the identification result as the appointed information in the picture invoice.
5. The method for reimbursement of an invoice based on artificial intelligence according to claim 4, wherein the step of inputting the scan data into a preset recurrent neural network model to obtain a recognition result comprises:
converting the scan data into a specified vector;
classifying and identifying the specified vector through a preset clustering algorithm to obtain the clustering probability of the specified vector corresponding to each cluster;
and inputting the clustering probability and the specified vector into the preset cyclic neural network model to obtain a recognition result corresponding to the scanning data.
6. An artificial intelligence based invoice reimbursement device, comprising:
the acquisition module is used for acquiring the information type of the reimbursement invoice selected by the user, wherein the information type comprises a picture invoice and a text invoice;
the calling module is used for calling a first information acquisition mode corresponding to the picture invoice to acquire the appointed information in the picture invoice, and calling a second information acquisition mode corresponding to the text invoice to acquire the appointed information in the text invoice;
the judging module is used for checking the background database and judging whether a history reimbursement record corresponding to the specified information exists in the background database;
the assignment module is used for assigning the specified information into the dynamic variable of the page through a specified function if the historical reimbursement record corresponding to the specified information does not exist;
the combination module is used for combining the assigned dynamic variable and the preset static variable into an invoice reimbursement bill;
the starting module is used for starting invoice verification and invoice reimbursement according to the invoice reimbursement list;
the calling module comprises:
the second starting unit is used for starting the python crawler to download the webpage information corresponding to the text invoice from the electronic invoice website set to be crawled;
the storage unit is used for sending a request to the target site server through an HTTP request, obtaining the webpage link information of all text invoices and storing the webpage link information into a temporary database;
the cleaning unit is used for storing the acquired webpage link information into a csv file or a database, and cleaning invoice information content in the webpage link information to obtain specified information corresponding to the text invoice;
a fourth obtaining unit, configured to obtain a first vector corresponding to the specified information and a second vector corresponding to a specified invoice in the background database, where the specified invoice is any invoice in the background database;
a calculation unit for calculating a vector similarity value between the first vector and the second vector by a specified formula, wherein the specified formula is thatX represents a vector similarity value, M is the first vector, N is the second vector, mi is a component corresponding to the ith information dimension of the first vector, ni is a component corresponding to the ith information dimension of the second vector, and the first vector and the second vector are provided with p information dimensions with the same arrangement times;
the second judging unit is used for judging whether the vector similarity value is larger than a preset threshold value or not;
the judging unit is used for judging that the historical reimbursement record corresponding to the specified information exists in the background database if the historical reimbursement record is larger than a preset threshold value, and if the historical reimbursement record does not exist;
the method comprises the steps of using a jquery framework of a javascript library for a part to be refreshed, and importing the jquery framework into a current code through tag matching to serve as the dynamic variable; and when only refreshing invoice information content of the current reported invoice in the HTML page, other contents of the HTML page are unchanged and serve as the static variables.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460755.XA CN113065940B (en) | 2021-04-27 | 2021-04-27 | Method, device, equipment and storage medium for reimbursement of invoice based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460755.XA CN113065940B (en) | 2021-04-27 | 2021-04-27 | Method, device, equipment and storage medium for reimbursement of invoice based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113065940A CN113065940A (en) | 2021-07-02 |
| CN113065940B true CN113065940B (en) | 2023-11-17 |
Family
ID=76567761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110460755.XA Active CN113065940B (en) | 2021-04-27 | 2021-04-27 | Method, device, equipment and storage medium for reimbursement of invoice based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065940B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7368541B1 (en) | 2022-05-02 | 2023-10-24 | 株式会社ブロードリーフ | Document management device, document management method, and document management program |
| US20240037975A1 (en) * | 2022-07-26 | 2024-02-01 | HighRadius Corp. | Methods and systems for automatic document pattern recognition and analysis |
| CN115935042B (en) * | 2023-01-19 | 2023-09-26 | 蔷薇大树科技有限公司 | Mortgage asset intelligent duplicate checking method and system based on fusion model |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583827A (en) * | 2018-10-15 | 2019-04-05 | 平安科技（深圳）有限公司 | Invoice collation method, apparatus, computer equipment and storage medium |
| CN109726783A (en) * | 2018-12-28 | 2019-05-07 | 大象慧云信息技术有限公司 | A kind of invoice acquisition management system and method based on OCR image recognition technology |
| CN110264288A (en) * | 2019-05-20 | 2019-09-20 | 深圳壹账通智能科技有限公司 | Data processing method and relevant apparatus based on information discriminating technology |
| CN110782329A (en) * | 2019-09-27 | 2020-02-11 | 国信电子票据平台信息服务有限公司 | Financial invoice authentication management method and system |
| CN111192019A (en) * | 2019-12-30 | 2020-05-22 | 武汉佰钧成技术有限责任公司 | Reimbursement processing method of target bill and related equipment |
| CN112017019A (en) * | 2020-07-10 | 2020-12-01 | 苏宁云计算有限公司 | Automatic reimbursement method and device based on PDF semantic extraction analysis, computer equipment and storage medium |
| CN112085578A (en) * | 2020-09-07 | 2020-12-15 | 杭州真内控科技有限公司 | Electronic invoice reimbursement system and electronic invoice holder device |
| CN112183296A (en) * | 2020-09-23 | 2021-01-05 | 北京文思海辉金信软件有限公司 | Simulated bill image generation and bill image recognition method and device |
| CN112232036A (en) * | 2020-09-08 | 2021-01-15 | 用友网络科技股份有限公司 | Reimbursement bill generation method, electronic device and computer-readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10489502B2 (en) * | 2017-06-30 | 2019-11-26 | Accenture Global Solutions Limited | Document processing |
-
2021
- 2021-04-27 CN CN202110460755.XA patent/CN113065940B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583827A (en) * | 2018-10-15 | 2019-04-05 | 平安科技（深圳）有限公司 | Invoice collation method, apparatus, computer equipment and storage medium |
| CN109726783A (en) * | 2018-12-28 | 2019-05-07 | 大象慧云信息技术有限公司 | A kind of invoice acquisition management system and method based on OCR image recognition technology |
| CN110264288A (en) * | 2019-05-20 | 2019-09-20 | 深圳壹账通智能科技有限公司 | Data processing method and relevant apparatus based on information discriminating technology |
| CN110782329A (en) * | 2019-09-27 | 2020-02-11 | 国信电子票据平台信息服务有限公司 | Financial invoice authentication management method and system |
| CN111192019A (en) * | 2019-12-30 | 2020-05-22 | 武汉佰钧成技术有限责任公司 | Reimbursement processing method of target bill and related equipment |
| CN112017019A (en) * | 2020-07-10 | 2020-12-01 | 苏宁云计算有限公司 | Automatic reimbursement method and device based on PDF semantic extraction analysis, computer equipment and storage medium |
| CN112085578A (en) * | 2020-09-07 | 2020-12-15 | 杭州真内控科技有限公司 | Electronic invoice reimbursement system and electronic invoice holder device |
| CN112232036A (en) * | 2020-09-08 | 2021-01-15 | 用友网络科技股份有限公司 | Reimbursement bill generation method, electronic device and computer-readable storage medium |
| CN112183296A (en) * | 2020-09-23 | 2021-01-05 | 北京文思海辉金信软件有限公司 | Simulated bill image generation and bill image recognition method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113065940A (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113065940B (en) | Method, device, equipment and storage medium for reimbursement of invoice based on artificial intelligence | |
| US11816165B2 (en) | Identification of fields in documents with neural networks without templates | |
| WO2020000688A1 (en) | Financial risk verification processing method and apparatus, computer device, and storage medium | |
| CN112631997B (en) | Data processing method, device, terminal and storage medium | |
| CN109508458B (en) | Legal entity identification method and device | |
| CN104285209A (en) | Spreadsheet-based programming language adapted for report generation | |
| CN110334640A (en) | A kind of ticket processing method and system | |
| TW200929040A (en) | Systems and methods for collecting and analyzing business intelligence data | |
| CN112286934A (en) | Database table importing method, device, equipment and medium | |
| US20220139098A1 (en) | Identification of blocks of associated words in documents with complex structures | |
| CN110362798B (en) | Method, apparatus, computer device and storage medium for judging information retrieval analysis | |
| CN110046155B (en) | Method, device and equipment for updating feature database and determining data features | |
| US20220335073A1 (en) | Fuzzy searching using word shapes for big data applications | |
| WO2019192130A1 (en) | Customer classification method and device and storage medium | |
| US11295125B2 (en) | Document fingerprint for fraud detection | |
| US20130132289A1 (en) | Oil and gas interest tracking system | |
| CN111078564B (en) | UI test case management method, device, computer equipment and computer readable storage medium | |
| US20220121881A1 (en) | Systems and methods for enabling relevant data to be extracted from a plurality of documents | |
| CN110321529B (en) | Frame text display method and device, computer equipment and storage medium | |
| EP4141818A1 (en) | Document digitization, transformation and validation | |
| CN115994232A (en) | Online multi-version document identity authentication method, system and computer equipment | |
| CN110442614A (en) | Searching method and device, electronic equipment, the storage medium of metadata | |
| US11593417B2 (en) | Assigning documents to entities of a database | |
| CN115525739A (en) | Supply chain financial intelligent duplicate checking method, device, equipment and medium | |
| US11789903B1 (en) | Tagging tool for managing data |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230908 Address after: Room 612 and 615, Building 1, No. 88 Shishan Road, Suzhou High tech Zone, Suzhou, Jiangsu Province, 215000 Applicant after: Jiangsu huanxun Information Technology Co.,Ltd. Address before: 518000 Room 202, block B, aerospace micromotor building, No.7, Langshan No.2 Road, Xili street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: Shenzhen LIAN intellectual property service center Effective date of registration: 20230908 Address after: 518000 Room 202, block B, aerospace micromotor building, No.7, Langshan No.2 Road, Xili street, Nanshan District, Shenzhen City, Guangdong Province Applicant after: Shenzhen LIAN intellectual property service center Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: PING AN PUHUI ENTERPRISE MANAGEMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |