Automatic case pushing system

Abstract

The invention provides an automatic case pushing system, and the system comprises a property management system which is used for recording data related to property management and uploading property sheet information to a mediation platform according to the needs, so as to generate a mediation case; the proprietor platform is used for logging in a community proprietor account and confirming property arrearage, and providing a platform for uploading a money return voucher photo for the proprietor; the mediation platform is used for receiving and processing the mediation cases, automatically classifying the cases of the same type, receiving money return voucher photos uploaded by owners, carrying out image-text recognition verification and debt calculation according to the money return voucher photos, confirming case mediation states, and automatically pushing the cases which are successfully mediated to a property management system in the early morning every day; according to the invention, the arrearage information is automatically captured from the property management system according to the property management order information uploaded to the mediation platform by the property management system, and the mediation case is automatically generated, so that errors and workload of manual input are reduced, and the cases of the same type are automatically classified according to the property management order information, so that the case processing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of case pushing, and in particular to an automatic case pushing system. Background Art

[0002] The property management company accepts the entrustment of the owner and implements professional management of the property within a specific area in accordance with the relevant laws and regulations or the agreement of the contract and obtains corresponding remuneration.

[0003] In the traditional property case handling process, especially when it comes to mediation of arrears, property companies face many challenges. On the one hand, due to the lack of effective information technology, at present, property fees are usually collected by owners in person. Before the owner pays, the property company usually informs the owner of the payment of property fees by posting notices or visiting the owner to urge payment. Many key links such as case generation, classification, mediation progress tracking and final mediation confirmation require a lot of manual operations. On the other hand, with the growth of business volume, relying solely on manpower has become difficult to meet the growing service needs, and it also increases management costs and the risk of errors.

[0004] Therefore, it is necessary to provide a new automatic case push system to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides an automatic case pushing system.

[0006] The case automatic push system provided by the present invention includes a property system, which is responsible for recording data related to property management and uploading property list information to the mediation platform as needed to generate mediation cases;

[0007] The owner platform is used for community owner account login and property arrears confirmation, providing a platform for owners to upload photos of payment receipts;

[0008] The mediation platform is used to receive and process mediation cases, automatically classify cases of the same type, and receive photos of payment receipts uploaded by owners. It performs image and text recognition verification and calculates the amount owed based on the photos of payment receipts, confirms the mediation status of the case, and automatically pushes successfully mediated cases to the property system in the early hours of each day.

[0009] Furthermore, the mediation case handling steps include the following steps:

[0010] S1. Case generation: automatically generate mediation cases based on the property list information uploaded to the mediation platform by the property system;

[0011] S2. Case classification: Classify the cases of the same type according to the property list information;

[0012] S3. Case mediation: The mediator will contact the owner of the property management bill who owes money for mediation;

[0013] S4. Case progress identification: Receive the property owner who owes the property bill and upload the photo of the payment receipt with the signature and seal to the owner platform, and perform image and text recognition verification of the signature and seal and calculate the outstanding amount;

[0014] S5. Case mediation confirmation: The mediation platform identifies the repayment amount based on the repayment voucher. When the case has been written off, the outstanding fees have been settled and the mediation document information exists at the same time, the mediation platform automatically pushes the case to the property system in the early morning every day for the property system to confirm whether the mediation is successful. If the mediation is successful, the case will be withdrawn; if the mediation fails, prosecution will be initiated.

[0015] Furthermore, the image and text recognition verification utilizes optical character recognition, which specifically includes the following steps:

[0016] S1. Pre-process the payment receipt photo;

[0017] S2, feature extraction and positioning: Use Canny edge detection to find the edges of the signature strokes, further refine the signature area, and use the known seal template to match the area in the image to locate the seal position;

[0018] S3. Training OCR model: Collect a large number of signature and seal samples as training data sets;

[0019] S4, multi-stage verification: set rules to check whether the recognition results conform to the preset format, and the OCR model preliminarily recognizes the text content of the signature and seal;

[0020] S5. User interactive confirmation: When the system cannot accurately recognize the signature or seal, the mediator is required to confirm on the mediation platform.

[0021] Furthermore, the formats preset in the multi-stage verification include the date format of the seal, the length format of the signature, and the position format of the signature and seal.

[0022] Furthermore, the mediator may contact the owner of the property bill who is in arrears by telephone or text message notification.

[0023] Furthermore, the property list information includes the name of the property company, the name of the community, and the amount of the property fee case.

[0024] Furthermore, the classification of cases of the same type includes the following steps: according to the community name, case status and case channel, all uploaded cases are automatically scanned on the mediation platform to find eligible cases. When cases in the same batch are identified and classified, the mediation platform automatically pushes these cases to the corresponding batches on the mediation platform.

[0025] Furthermore, the arrears calculation is to compare the case amount with the repayment amount: the arrears amount Q m = Case amount W m - Refund amount H m .

[0026] Compared with the related art, the automatic case pushing system provided by the present invention has the following beneficial effects:

[0027] 1. The present invention automatically captures arrears information from the property system according to the property list information uploaded by the property system to the mediation platform, and automatically generates mediation cases to reduce errors and workload in manual entry, and automatically classifies and processes cases of the same type according to the property list information to improve the efficiency of case handling.

[0028] 2. The present invention performs graphic recognition and verification of signatures and seals and calculation of outstanding debts based on photos of payment receipts, thereby improving recognition accuracy and efficiency. When a case meets certain conditions (such as outstanding debts have been settled, mediation document information is complete, etc.), the system can automatically update the case status, synchronize it to the property management system, and automatically push the case, reducing the number of manual confirmation steps.

[0029] 3. The present invention automatically matches the batch name of the target system according to the rules, and intelligently and automatically identifies whether the case has been paid back and whether the case has met the filing standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A structural block diagram of the automatic case push system provided by the present invention;

[0031] Figure 2 A flowchart of the mediation case processing provided by the present invention;

[0032] Figure 3 This is a flowchart of the image and text recognition verification provided by the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0034] Please refer to Figure 1 , Figure 2 , Figure 3 ,in, Figure 1 A structural block diagram of the automatic case push system provided by the present invention; Figure 2 A flowchart of the mediation case processing provided by the present invention; Figure 3 This is a flowchart of the image and text recognition verification provided by the present invention.

[0035] In the specific implementation process, Figure 1As shown, the case automatic push system includes a property system, which is responsible for recording data related to property management and uploading property list information to the mediation platform as needed to generate mediation cases, wherein the property system includes community information, owner information, administrator information, property amount management, property company information, and property fee list, and the property list information includes property company information, community information, and the amount of property fee case entrusted;

[0036] The owner platform is used for the login management of the community owner account and confirmation of property arrears, providing a platform for owners to upload photos of payment receipts;

[0037] The mediation platform is used to receive and process mediation cases, automatically classify cases of the same type, and receive photos of payment receipts uploaded by owners. It performs image recognition and verification and calculates the amount owed based on the photos of payment receipts, confirms the mediation status of the case, and automatically pushes the successfully mediated cases to the property management system at dawn every day. The amount owed is calculated by comparing the case amount with the payment amount: the amount owed Q m = Case amount W m - Refund amount H m .

[0038] Furthermore, refer to Figure 2 As shown, the mediation case processing steps include the following steps:

[0039] S1. Case generation: automatically generate mediation cases based on the property list information uploaded to the mediation platform by the property system;

[0040] S2. Case classification: All uploaded cases are automatically scanned on the mediation platform according to the community name, case status and case channel. When a case reaches a certain status (such as the status before mediation), the mediation platform automatically scans all cases in the database to find cases that meet the conditions. When cases in the same batch are identified and classified, the mediation platform automatically pushes these cases to the corresponding batches on the mediation platform;

[0041] In order to show the case classification process more clearly: the following steps are adopted:

[0042] 1. Define the case data structure: Each case can be represented as a triple containing the community name, case status, and case channel. For example, a case can be represented as (N, S, C), where N represents the community name, S represents the case status, and C represents the case channel;

[0043] 2. Define rules: The conditions for cases to belong to the same batch are (N i , S i , C i ) and (N j , S j , C j) must satisfy N i =N j , S i =S j And C i =Cx;

[0044] 3. Define a judgment function: Define a function F to determine whether two cases belong to the same batch. If the two cases meet the above conditions, the function returns a true value (True), otherwise it returns a false value (False).

[0045] There are three sample data as follows:

[0046] Case A: Community X, Status: Under mediation, Channel: Channel A;

[0047] Case B: Community X, Status: Under mediation, Channel: Channel A;

[0048] Case C: Community X, Status: Under mediation, Channel: Channel A;

[0049] 1. Data representation: Each case is represented as a triple:

[0050] Case A: (X, under mediation, A);

[0051] Case B: (X, under mediation, A);

[0052] Case C: (X, under mediation, A);

[0053] 2. Determination function: Define a function F to determine whether two cases belong to the same batch:

[0054] F((N i , S i , C i ), (N j , S j , C j ))=N i =N j ∧S i =S j ∧C i =C j

[0055] 3. Determine whether case A and case B belong to the same batch: F((X, mediation in progress, A), (X, mediation in progress, A)) = (X = X) ∧ (mediation in progress = mediation in progress) ∧ A = A. Since all conditions are met, F((X, mediation in progress, A), (X, mediation in progress, A)) = True.

[0056] Determine whether case A and case C belong to the same batch: F((X, mediation processing, A), (X, mediation processing, A)) = (X = X) ∧ (mediation processing = mediation processing) ∧ A = A. Similarly, all conditions are met, so F((X, mediation processing, A), (X, mediation processing, A)) = True;

[0057] Determine whether case B and case C belong to the same batch: F((X, mediation processing, A), (X, mediation processing, A)) = (X = X) ∧ (mediation processing = mediation processing) ∧ A = A. Again, all conditions are met, so F((X, mediation processing, A), (X, mediation processing, A)) = True;

[0058] Through the above determination, it is concluded that cases A, B, and C all belong to the same batch;

[0059] S3. Case mediation: The mediator will contact the owner of the property bill who is in arrears for mediation. The mediator can contact the owner of the property bill who is in arrears by phone or text message.

[0060] S4. Case progress identification: Receive the property owner who owes the property bill and upload the photo of the payment receipt with the signature and seal to the owner platform, and perform image and text recognition verification of the signature and seal and calculate the outstanding amount;

[0061] S5. Case mediation confirmation: The mediation platform identifies the repayment amount based on the repayment voucher. When the case has been written off, the outstanding fees have been settled and the mediation document information exists at the same time, the mediation platform automatically pushes the case to the property system in the early morning every day for the property system to confirm whether the mediation is successful. If the mediation is successful, the case will be withdrawn; if the mediation fails, prosecution will be initiated.

[0062] In a specific embodiment, reference Figure 3 As shown, the image and text recognition verification uses optical character recognition, which specifically includes the following steps:

[0063] S1. Pre-process the payment receipt photo;

[0064] Preprocessing includes denoising: using a median filter or a bilateral filter to remove noise from the image; grayscale: converting a color image into a grayscale image to reduce the color space dimension; binarization: using the Otsu threshold segmentation algorithm to convert the image into a black and white image to highlight the text and seal;

[0065] S2, feature extraction and positioning: Use Canny edge detection to find the edges of the signature strokes, further refine the signature area, and use the known seal template to match the area in the image to locate the seal position;

[0066] S3. Training OCR model: Collect a large number of signature and seal samples as training data sets, use convolutional layers to extract image features, pooling layers to reduce the size of feature maps, fully connected layers for classification, and finally output recognition results through softmax function. For example, assuming that the input image size is 28×2828×28, the first convolutional layer has 3232 filters, each filter size is 5×55×5, the step size is 11, and the padding is 22, then the output feature map size is 28×2828×28; then through the maximum pooling layer, the pooling window size is 2×22×2, the step size is 22, and the output feature map size is 14×1414×14; the next fully connected layer flattens the feature map and outputs the probability distribution through the softmax classifier;

[0067] S4, multi-stage verification: set rules to check whether the recognition results conform to the preset format, and the OCR model preliminarily recognizes the text content of the signature and seal;

[0068] S5. User interactive confirmation: When the system cannot accurately recognize the signature or seal, the mediator is required to confirm on the mediation platform.

[0069] It should be noted that the preset formats in the multi-stage verification include the date format of the seal, the length format of the signature, and the position of the signature and seal format.

[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0071] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention, and any figure mark in the claims should not be regarded as limiting the claims involved.

[0072] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. Automatic case push system, It is characterized in that Including a property management system, which is responsible for recording data related to property management and uploading property list information to the mediation platform as needed to generate mediation cases; The owner platform is used for community owner account login and property arrears confirmation, providing a platform for owners to upload photos of payment receipts; The mediation platform is used to receive and process mediation cases, automatically classify cases of the same type, and receive photos of payment receipts uploaded by owners. It performs image and text recognition verification and calculates the amount owed based on the photos of payment receipts, confirms the mediation status of the case, and automatically pushes successfully mediated cases to the property system in the early hours of each day.

2. The automatic case push system according to claim 1, It is characterized in that The mediation case handling steps include the following steps: S1. Case generation: automatically generate mediation cases based on the property list information uploaded to the mediation platform by the property system; S2. Case classification: Classify the cases of the same type according to the property list information; S3. Case mediation: The mediator will contact the owner of the property management bill who owes money for mediation; S4. Case progress identification: Receive the property owner who owes the property bill and upload the photo of the payment receipt with the signature and seal to the owner platform, and perform image and text recognition verification of the signature and seal and calculate the outstanding amount; S5. Case mediation confirmation: The mediation platform identifies the repayment amount based on the repayment voucher. When the case has been written off, the outstanding fees have been settled and the mediation document information exists at the same time, the mediation platform automatically pushes the case to the property system in the early morning every day for the property system to confirm whether the mediation is successful. If the mediation is successful, the case will be withdrawn; if the mediation fails, prosecution will be initiated.

3. The automatic case push system according to claim 1, It is characterized in that The image and text recognition verification uses optical character recognition, which specifically includes the following steps: S1. Pre-process the payment receipt photo; S2, feature extraction and positioning: Use Canny edge detection to find the edges of the signature strokes, further refine the signature area, and use the known seal template to match the area in the image to locate the seal position; S3. Training OCR model: Collect a large number of signature and seal samples as training data sets; S4, multi-stage verification: set rules to check whether the recognition results conform to the preset format, and the OCR model preliminarily recognizes the text content of the signature and seal; S5. User interactive confirmation: When the system cannot accurately recognize the signature or seal, the mediator is required to confirm on the mediation platform.

4. The automatic case push system according to claim 3, It is characterized in that The formats preset in the multi-stage verification include the date format of the seal, the length format of the signature, and the position of the signature and seal format.

5. The automatic case push system according to claim 4, It is characterized in that The mediator may contact the owner of the property bill who is in arrears by phone or text message notification.

6. The automatic case push system according to claim 5, It is characterized in that The property bill information includes the name of the property company, the name of the community, and the amount of property fee entrusted.

7. The automatic case push system according to claim 6, It is characterized in that The classification and processing of cases of the same type includes the following steps: according to the community name, case status and case channel, all uploaded cases are automatically scanned on the mediation platform to find eligible cases. When cases in the same batch are identified and classified, the mediation platform automatically pushes these cases to the corresponding batches on the mediation platform.

8. The automatic case pushing system according to claim 7, It is characterized in that The calculation of the outstanding amount is to compare the case amount with the amount of repayment: the outstanding amount Q m = = Case amount W m - Refund amount H m .

Images