Document association method and device, electronic device and storage medium

Through automated document association methods, identifying key fields and mapping relationships and selecting associated documents, the problem of difficult improvement in document association analysis efficiency and quality in the existing technology is solved, and an efficient and accurate document association process is achieved.

CN113971207BActive Publication Date: 2024-11-01ANHUI IFLYTEK INTELLIGENT SYST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111308278.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-05
Publication Date
2024-11-01
Estimated Expiration
2041-11-05

AI Technical Summary

Technical Problem

In the prior art, the correlation analysis between documents mainly relies on manual reading, which makes it difficult to improve efficiency and quality, especially in complex scenarios such as file reading. As the number and complexity of documents increase, the efficiency and quality of correlation analysis are difficult to improve. ensure.

Method used

By obtaining the document collection, identifying the key fields and their properties in the target document, searching for candidate documents in the document to be associated based on the mapping relationship between the field type and the document type, and selecting the associated documents through the verification results to achieve automated Document association process.

Benefits of technology

No manual reading and analysis is required, which improves the efficiency of document association, and reduces the error rate through layer-by-layer screening, improving the quality and quality efficiency of document association.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113971207B_ABST
    Figure CN113971207B_ABST
Patent Text Reader

Abstract

The present application discloses a document association method and device, an electronic device and a storage medium, wherein the document association method comprises: obtaining a document collection, the document collection comprises a plurality of documents, the plurality of documents comprises a target document and at least one document to be associated; identifying a first key field and its first field attribute in the target document; wherein the first field attribute comprises a first field type to which the first key field belongs; based on a mapping relationship between a field type and a document type, searching for candidate documents related to the first key field in at least one document to be associated; and selecting a candidate document as an associated document based on the verification results of each candidate document. The above scheme can improve the quality and efficiency of document association.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of document processing, and in particular to a document association method and device, an electronic device and a storage medium. Background Art

[0002] In many scenarios, the correlation between documents is extremely important for sorting out information and improving document reading efficiency. For example, in the file reading scenario, analyzing the correlation between documents can help relevant personnel quickly understand the events involved in the file; or in the historical research scenario, analyzing the correlation between documents can help relevant personnel quickly grasp the historical background and other relevant knowledge involved in the historical materials, and so on.

[0003] At present, the correlation between documents is generally sorted out by manual reading. Taking the file reading scenario as an example, relevant personnel need to read the documents in the file one by one to find related evidence documents in a large amount of documents. With the increase in the number of documents in the file and the increase in the complexity of the events involved in the file, the efficiency and quality of the correlation analysis conducted by relevant personnel will inevitably decrease. In view of this, how to improve the quality and efficiency of document correlation has become an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a document association method and device, electronic device and storage medium, which can improve the quality and efficiency of document association.

[0005] In order to solve the above technical problems, the first aspect of the present application provides a document association method, including: obtaining a document collection, the document collection includes a plurality of documents, the plurality of documents include a target document and at least one document to be associated; identifying a first key field and its first field attribute in the target document; wherein the first field attribute includes a first field type to which the first key field belongs; based on a mapping relationship between a field type and a document type, searching for candidate documents related to the first key field in at least one document to be associated; and based on the verification results of each candidate document, selecting the candidate document as an associated document.

[0006] In order to solve the above-mentioned technical problems, the second aspect of the present application provides a document association device, including a document acquisition module, a document identification module, a document search module and a document selection module, wherein the document acquisition module is used to acquire a document collection; wherein the document collection includes a main document, and the plurality of documents include a target document and at least one document to be associated; the document identification module is used to identify a first key field and its first field attribute in the target document; wherein the first field attribute includes a first field type to which the first key field belongs; the document search module is used to search for candidate documents related to the first key field in at least one document to be associated based on a mapping relationship between a field type and a document type; and the document selection module is used to select a candidate document as an associated document based on the verification results of each candidate document.

[0007] In order to solve the above technical problems, the third aspect of the present application provides an electronic device, including a memory and a processor coupled to each other, the memory storing program instructions, and the processor being used to execute the program instructions to implement the document association method in the above first aspect.

[0008] In order to solve the above technical problem, the fourth aspect of the present application provides a computer-readable storage medium storing program instructions that can be executed by a processor, wherein the program instructions are used to implement the document association method in the above first aspect.

[0009] The above scheme obtains a document set, and the document set includes several documents, and the several documents include a target document and at least one document to be associated, and identifies the first key field and the first field attribute in the target document, and the first field attribute includes the first field type to which the first field belongs, and then searches for candidate documents related to the first key field in at least one document to be associated based on the mapping relationship between the field type and the document type, and selects the candidate documents as associated documents based on the verification results of each candidate document. On the one hand, since there is no need to analyze the correlation between documents through manual reading, it helps to improve the efficiency of document association. On the other hand, in the process of document association, the associated documents are finally obtained through layer-by-layer screening such as field identification, document mapping and document verification, which can reduce the error rate of document association as much as possible and improve the quality of document association. Therefore, the quality and efficiency of document association can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of an embodiment of the document association method of the present application;

[0011] Figure 2 yes Figure 1 A schematic diagram of a flow chart of an embodiment of step S14;

[0012] Figure 3 yes Figure 1A flowchart of another embodiment of selecting an associated document;

[0013] Figure 4 It is a schematic diagram of a framework of an embodiment of a document association device of the present application;

[0014] Figure 5 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application;

[0015] Figure 6 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0016] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0017] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0018] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0019] See also Figure 1 , Figure 1 It is a flowchart of an embodiment of the document association method of the present application.

[0020] Specifically, the following steps may be included:

[0021] Step S11: Obtain a document collection.

[0022] In the embodiment of the present disclosure, the document set includes a plurality of documents, and the plurality of documents include a target document and at least one document to be associated.

[0023] In an implementation scenario, the document collection can be set according to the actual application scenario. Taking the scenario of historical research as an example, the document collection can include historical materials related to a certain event; or, taking the scenario of case handling as an example, the document collection can be a file related to a certain case. Other situations can be deduced by analogy, and no examples are given here one by one.

[0024] In an implementation scenario, the target document and the document to be associated can be set according to the actual application scenario. Taking the scenario of textual research as an example, the target document can be the textual research material to be investigated (such as silk books, bronze inscriptions, etc.), and the document to be associated can be the verified textual research material (such as the published bronze inscriptions compilation, history books, etc.); or, taking the case handling scenario as an example, the target document can be a litigation document (such as a prosecution opinion, an indictment, etc.), and the document to be associated can be an evidence document (such as a detention warrant, an arrest warrant, etc.), and other situations can be deduced by analogy, and examples are not given one by one here.

[0025] In an implementation scenario, a document collection may correspond to a case (or event), and several documents contained in the document collection may be related to at least one target person, that is, the target person involved in the document collection may be one or more, which is not limited here. Still taking the case handling scenario as an example, the document collection may correspond to the case of "Zhang San driving under the influence of alcohol causing disability", that is, several documents contained in the document collection may be related to only one target person (namely Zhang San); or, the document collection may also correspond to the case of "Zhang San and Li Si conspiring to steal", that is, several documents contained in the document collection may be related to two target persons (namely Zhang San and Li Si). It should be noted that the examples of the above document collections are only a few situations that may be involved in real scenarios, and the document collection is not limited thereto.

[0026] In an implementation scenario, the document formats of the target document and the document to be associated may not be limited, for example: word, PDF, picture, etc. In order to obtain the document text in formats such as PDF, picture, etc., recognition technologies such as OCR (Optical Character Recognition) may be used to perform text recognition to obtain the document text. The specific process of text recognition can refer to the technical details of text recognition methods such as OCR, which will not be repeated here.

[0027] Step S12: Identify the first key field and its first field attribute in the target document.

[0028] In the embodiment of the present disclosure, the first field attribute includes the first field type to which the first key field belongs.

[0029] In an implementation scenario, the first key field and the first field type to which it belongs can be set according to the actual application. Still taking the case handling scenario as an example, the first field type may include but is not limited to: "name" (the corresponding first key field is such as Zhang San, Li Si, etc.), "alcohol content" (the corresponding first key field is such as 20mg / 100ml, 80mg / 100ml, etc.), "stolen items" (the corresponding first key field is such as "electric vehicle", "cash", etc.), which are not limited here. In general, in the case handling scenario, the first field type can be divided into two major categories, which can be named as the first type and the second type respectively for the convenience of distinction. Among them, the first type is the field type related to the suspect, such as including but not limited to: name, ID number, age, gender, household registration, residence, education, etc., and the second type is the field type related to the case, such as including but not limited to: criminal record, alcohol content, course of the incident, confession and acceptance of guilt, etc., and the specific situation is not limited here.

[0030] In an implementation scenario, the first key field and its first field attribute can be obtained by identifying the target document based on at least one of a semantic recognition model and preset business rules. It should be noted that in real scenarios, the semantic recognition model and the preset business rules can be combined to jointly identify the key fields and their field attributes to improve the recognition accuracy, and the preset business rules can be used as a supplement to the semantic recognition model to reduce the training difficulty of the semantic recognition model. Of course, it is also possible to identify the key fields and their field attributes based only on the semantic recognition model or the preset business rules according to actual needs, without limitation here. For example, when the target document follows certain writing specifications, it can be identified based on preset business rules; or, when the target document does not follow certain writing specifications, it can be identified based on the semantic recognition model, and in order to improve the recognition accuracy, the semantic recognition model can be trained through a large number of sample documents. For details, please refer to the following related descriptions, which will not be repeated here.

[0031] In a specific implementation scenario, during the training process of the semantic recognition model, each sample key field and its sample field attribute (such as, including but not limited to the sample field type) can be marked in advance in the sample document, and then the sample document can be identified using the semantic recognition model to obtain the predicted key field and its predicted field attribute, and then the network parameters of the semantic recognition model can be adjusted based on the difference between the sample key field and the predicted key field, and the difference between the sample field attribute and the predicted field attribute. After the training converges, the semantic recognition model can be used to identify the target document to extract the first key field and its first field attribute. The semantic recognition model can specifically include but is not limited to: BERT (Bidirectional Encoder Representation from Transformers), RNN (Recurrent Neural Network), etc., and the network structure of the semantic recognition model is not limited here. For the specific recognition process, please refer to the technical details of network models such as BERT and RNN, which will not be repeated here. Taking the case handling scenario as an example, the semantic recognition model can be used to identify the target document (such as a litigation document) to obtain the first key field belonging to the aforementioned first type and the second key field belonging to the aforementioned second type. Specifically, the second type may include but is not limited to: document number, document date, incident process, verified facts, and the first type may include but is not limited to: name, ID number, age, registered residence, place of residence, education status, etc., and penalty information (such as type of compulsory measures, date of execution of compulsory measures, location of compulsory measures, and executing agency), etc. Other situations can be deduced by analogy, and no examples are given here one by one.

[0032] In a specific implementation scenario, the preset business rules may include a description of business definitions and constraints, which are used to maintain the business structure or control and influence the behavior of the business. In essence, it is to identify the key fields in the target document and the field types to which they belong. It should be noted that in the case of identification based on preset business rules, the target document must follow certain writing specifications. For example, paragraphs involving some specific field types in the target document generally appear mainly in specific positions of the document (such as the beginning, the end, etc.). Considering that the training cost of the semantic recognition model itself is also relatively high, business rules can be used to extract these regular field types. For example, for situations such as "the first field is the name field, the second field is the time field, ..., and the last field is the event field", where the paragraphs are clear and the description method is relatively fixed, it can be identified through preset business rules to obtain key fields such as "name", "time", "events" and their field attributes. Other situations can be deduced by analogy, and no examples are given here.

[0033] Step S13: Based on the mapping relationship between the field type and the document type, search for a candidate document related to the first key field in at least one document to be associated.

[0034] Table 1 Schematic diagram of an embodiment of the mapping relationship between field types and document types

[0035]

[0036] In an implementation scenario, there is a certain mapping relationship between the field type and the document type, and the mapping relationship between the field type and the document type can be a one-to-one relationship or a one-to-many relationship. That is to say, for each field type, there is a sub-mapping relationship of the field type in the mapping relationship, and the sub-mapping relationship includes the field type and at least one document type related to the field type. Still taking the case handling scenario as an example, please refer to Table 1, which is a schematic table of an embodiment of the mapping relationship between the field type and the document type. As shown in Table 1, the document types that have a mapping relationship with the field type "criminal record" include: "detention certificate", "notice of extension of detention period", "arrest warrant", "notice of bail pending trial", and the mapping relationship between the field type and the document type is a one-to-many relationship; or, the document types that have a mapping relationship with the field type "alcohol content" include: "forensic appraisal opinion", and the mapping relationship between the field type and the document type is a one-to-one relationship. For other field types and document types that have a mapping relationship with them, please refer to Table 1, and no examples will be given one by one here. It should be noted that the mapping relationship shown in Table 1 is only a mapping relationship that may exist in the actual application process, and does not limit the actual setting method of the mapping relationship.

[0037] In an implementation scenario, the type of document to be associated can be determined based on the mapping relationship between the pre-built field type and the document type, so that each name of the document to be associated that has a mapping relationship with the current field type can be matched and selected. Specifically, based on the mapping relationship, the document type related to the first field type to which the first key field belongs can be selected as the candidate type, and then based on the similarity between the candidate type and the document title of each document to be associated, the document to be associated is selected as the candidate document. Still taking the case handling scenario as an example, as shown in Table 1, for example, if the first field type to which the first key field belongs is "confession and acceptance of punishment", then from Table 1, the document type "confession and acceptance of punishment agreement" can be selected as the candidate type, and on this basis, the document title of each document to be associated can be matched with the candidate type "confession and acceptance of punishment agreement" for similarity. For example, a text similarity matching algorithm can be used for the association matching of documents, and a threshold can be set. If the threshold is reached, the document to be associated can be retained as a candidate document, otherwise the document to be associated will be screened out, and the screened out document to be associated will be returned to the list of documents to be associated. Still taking the first field type "Plea and Acceptance of Punishment" as an example, the candidate type is "Plea and Acceptance of Punishment Agreement", and the threshold can be set to 0.8. That is, when the text similarity between the document title of the document to be associated and the candidate type "Plea and Acceptance of Punishment Agreement" exceeds 0.8, the document to be associated can be used as a candidate document.

[0038] In one implementation scenario, the text similarity matching algorithm is mainly used in search engines and is matched based on strings. Strings are composed of characters. As long as each character in two strings is compared to see whether they are equal, it can be known whether the two strings are equal, or each string is mapped to a hash value through a hash function, and then compared to obtain a matching result. The specific process of similarity matching can be referred to the relevant technical details of text matching, which will not be repeated here.

[0039] In an implementation scenario, after the associated documents are screened according to the similarity matching algorithm, a series of candidate documents can be obtained, and the candidate documents can be arranged in a certain priority order. As shown in Table 1, taking the first field type "criminal record" as an example, multiple candidate documents of document types such as "detention certificate", "notice of extension of detention period", "arrest warrant", "notice of bail pending trial" can be searched, and multiple candidate documents can be sorted in order of priority, with candidate documents with high priority before candidate documents with low priority. Therefore, in the process of document review, the user's needs for reviewing documents of different types can be met, greatly improving the user experience. Specifically, the above priority order can be automatically generated or obtained by user configuration. For example, the priority order can be obtained according to the number of times different document types are read during the case handling process. As shown in Table 1, the priority order of "document type" corresponding to the field type of "criminal record" is: "detention certificate", "arrest certificate", "bail pending trial notice", "notice of extension of detention period", but the case handlers believe that the priority order needs to be adjusted during use. The case handlers can also set the priority order. The reset priority order can be: "detention certificate", "notice of extension of detention period", "arrest certificate", "bail pending trial notice", and the modified priority order is more practical in work.

[0040] Step S14: Based on the verification results of each candidate document, select the candidate document as the associated document.

[0041] See also Figure 2 , Figure 2 yes Figure 1 The flowchart of step S14 in the embodiment of FIG. 1 includes the following steps:

[0042] Step S21: Obtain candidate documents.

[0043] In an implementation scenario, it is necessary to verify all documents in the candidate documents, and verify the candidate documents according to the arrangement order of the candidate documents. Therefore, when verifying the documents, it is necessary to obtain the candidate documents first.

[0044] Step S22: Acquire the first data of the candidate document at the first preset position.

[0045] The first data of the candidate document at the first preset position is obtained, and the obtained first data is used to verify the target person. The first preset position can be set to a preset position (such as the last 50 words, etc.), a preset page number (such as the first page, the last page, etc.), etc., which is not limited here.

[0046] Step S23: Acquire the second data of the candidate document at the second preset position.

[0047] The second data of the candidate document at the second preset position is obtained, and the obtained second data is used to verify the legality of the document. Similar to the first preset position, the second preset position can also be set to a preset position (such as the last 50 words, etc.), a preset page number (such as the first page, the last page, etc.), which is not limited here.

[0048] It should be noted that step S22 and step S23 can be executed simultaneously, that is, the first data at the first preset position and the second data at the second preset position of the candidate document can be obtained simultaneously. Of course, step S22 and step S23 can also be executed in a sequential order, such as step S22 can be executed first and then step S23, or step S23 can be executed first and then step S22, which is not limited here. In addition, in the process of verifying the candidate documents, only the verification related to the target person can be performed, or only the verification related to the legality can be performed. Of course, in order to improve the verification accuracy, both the verification related to the target person and the verification related to the legality can be implemented, which is not limited here.

[0049] Step S24: Determine whether the first data involves the target person, if not, execute step S27, otherwise obtain the final verification result according to the second sub-result of step S25.

[0050] In one implementation scenario, the first data obtained is used to verify the target person to determine whether the first data involves the target person. For example, it is possible to check whether the first data at a preset position of the candidate document (e.g., the last 50 words, the first page, etc.) contains the target person, etc., which is not limited here. If the target person is involved, the first sub-result is yes (i.e., the verification related to the target person is passed), and the second sub-result needs to be obtained and based on the two sub-results, the final verification result of the candidate document is obtained.

[0051] Step S25: Determine whether the second data is compliant and legal. If not, execute step S27; otherwise, obtain the final verification result in combination with the first sub-result of step S24.

[0052] In one implementation scenario, the acquired second data is used to verify compliance and legality to determine whether the second data is compliant and legal. For example, it is possible to check whether the second data at a preset position of the candidate document (e.g., the last 50 words, the first page, etc.) contains seal information (e.g., a fingerprint, a stamp, a signature, etc.), which is not limited here. If it is compliant and legal, the second sub-result is yes (i.e., it passes the compliance and legality related verification).

[0053] It should be noted that, when the second data is compliant and legal, if the first sub-result of step S24 is yes, it can be considered that the final verification result of the candidate document is yes (i.e., passed the verification), and step S26 can be executed. If the first sub-result of step S24 is no, it can be considered that the final verification result of the candidate document is no (i.e., failed the verification), and step S27 can be executed.

[0054] Step S26: Keep the candidate document in the candidate document list.

[0055] In one implementation scenario, based on the first sub-result and the second sub-result, if the first sub-result is yes and the second sub-result is also yes, the selected candidate document is retained in the candidate document list.

[0056] Step S27: Delete the candidate document from the candidate document list.

[0057] Based on the first sub-result and the second sub-result, if the judgment result in the first sub-result or the second sub-result is negative, it means that the candidate document may not involve the target person or does not meet the compliance and legal requirements. The content of such candidate documents is not used as a reference, so this candidate document is deleted from the candidate document list, and the deleted candidate document will be returned to the documents to be associated.

[0058] In an implementation scenario, the first field attribute includes the target person involved in the first key field, and the verification result includes at least one of the first sub-result and the second sub-result. The first sub-result includes whether the candidate document involves the target person, and the second sub-result includes whether the candidate document is compliant and legal. Among them, the verification of the target person involved in the candidate document is to ensure that there is a corresponding relationship between the target person and the candidate document. Taking the case handling scenario as an example, a case may involve multiple suspects, that is, there are multiple target persons at this time, but they may not correspond to each other in the candidate documents. Therefore, the candidate documents need to be screened to ensure that the candidate documents corresponding to the target person correspond to each other.

[0059] In an implementation scenario, the verification result includes a first sub-result, and the first sub-result includes obtaining the first data of the candidate document at the first preset position, and obtaining the first sub-result based on whether the first data contains the target person. As shown in Table 2, Table 2 is a schematic table of an embodiment of a mapping relationship between field types and associated documents. If the target person is not unique, whether the corresponding relationship between the target person and the candidate document is correct becomes a key issue. Still taking the case handling scenario as an example, if there are two target persons, one is "Zhang San" and the other is "Li Si", the field type of the target person "Zhang San" is associated with the document, and the recommended document types to be associated include "detention certificate", "arrest certificate", "judgment", etc. For these documents to be associated, it is necessary to further determine which of these documents belong to the target person "Zhang San" to ensure that there is a corresponding relationship between the target person and the document. The target person is verified by the first data at the first preset position of the document to be associated. For example, the first page of the document contains the name of the target person, the last fifty characters of the document contain the name of the suspect, the first page of the document contains the name of the target person, the ID number of the target person, etc.

[0060] Table 2 Schematic diagram of an embodiment of the mapping relationship between field types and associated document judgment

[0061]

[0062] In one implementation scenario, the verification result includes a second sub-result, and the step of obtaining the second sub-result includes obtaining second data of the candidate document at a second preset position; and obtaining the second sub-result based on whether the second data contains seal information. As shown in Table 2, there will be a specific document identifier at a fixed position in the document file. The signature, seal, and seal information in the document are identified by the image and text recognition engine. In combination with relevant regulations, the compliance and legality of the document are further judged. Only documents that pass the compliance and legality verification can be used as candidate documents to output relevant data and results. For example: the last page of the interrogation record contains the target person's seal, and the target person is the person being interrogated; the detention certificate has the signature and seal of the target person, and the target person is the detainee.

[0063] The above scheme obtains a document set, and the document set includes several documents, and the several documents include a target document and at least one document to be associated, and identifies the first key field and the first field attribute in the target document, and the first field attribute includes the first field type to which the first field belongs, and then searches for candidate documents related to the first key field in at least one document to be associated based on the mapping relationship between the field type and the document type, and selects the candidate documents as associated documents based on the verification results of each candidate document. On the one hand, since there is no need to analyze the correlation between documents through manual reading, it helps to improve the efficiency of document association. On the other hand, in the process of document association, the associated documents are finally obtained through layer-by-layer screening such as field identification, document mapping and document verification, which can reduce the error rate of document association as much as possible and improve the quality of document association. Therefore, the quality and efficiency of document association can be improved.

[0064] See also Figure 3 , Figure 3 yes Figure 1 Specifically, the target document may also involve multiple target persons, in which case the following steps may be included:

[0065] Step S31: Identify the first key field and its first field attribute in the target document.

[0066] The first field attribute includes the first field type to which the first key field belongs. If there is more than one first field type in the target document, for example, the first field types are "name" and "ID number", the correspondence between the field type and the document type needs to be ensured for the first field types "name" and "ID number" to reduce mistakes in work and other behaviors that affect work progress.

[0067] Step S32: Matching search to obtain candidate documents.

[0068] In an implementation scenario, based on the mapping relationship between field type and document type, candidate documents related to the first key field are searched in at least one document to be associated, and based on the mapping relationship, the document type related to the first field type to which the first key field belongs is selected as the candidate type; based on the similarity between the candidate type and the document title of each document to be associated, the document to be associated is selected as the candidate document. Among them, the documents related to the first field type to which the first key field belongs are selected as the candidate type. If the first field type is divided into two major categories, the first type is the field type related to the suspect, such as including but not limited to name, ID number, education, etc., and the second type is the field type related to the case, such as including but not limited to: previous record, alcohol content, course of the incident, confession and acceptance of guilt, etc. At this time, the document type is screened, and all documents with a mapping relationship with the first field type are listed as candidate documents. However, in practice, there may be a large number of documents in the candidate document sequence, so the candidate documents need to be screened. In this application, a threshold is set for the similarity of the document title, and the candidate documents are screened. Based on the similarity between the candidate type and each document title to be associated, a threshold is set for the similarity of the document title, and the document to be associated is selected as the candidate document. Still taking the case handling scenario as an example, the threshold can be set to 0.8, that is, when the text similarity between the document title and the candidate type exceeds 0.8, the screening is successful. Taking the candidate type "Notice of Extension of Detention Period" as an example, the document title is "Forensic Appraisal Opinion", then the document is not screened through; if the candidate type is "Notice of Extension of Detention Period" and the document title is "Notice of Extension of Detention Period", then the document is screened through. Specifically, the threshold range set when screening documents is not limited here, and can be set according to actual conditions.

[0069] Step S33: Determine whether the match is successful, if so, execute step S34, otherwise execute step S38.

[0070] In an implementation scenario, candidate types are screened by comparing the title similarity with the document titles of each document to be associated. The purpose of screening is to classify the candidate documents, retain documents with higher relevance, and filter out documents with lower relevance, thereby reducing the workload of reading documents and increasing work speed.

[0071] Step S34: Verify the target person.

[0072] In an implementation scenario, after the candidate documents are screened, the remaining candidate documents include all documents related to the target person, but there is more than one target person. If there is more than one target person, the candidate documents include all the relevant candidate documents of the target person. If the documents in the candidate documents are not selected, not only will the number of candidate documents be large, but they will also be difficult to distinguish during the process of associating documents. Still taking the case handling scenario as an example, if there are two target persons, namely "Zhang San" and "Li Si", the candidate documents include all documents related to "Zhang San" and "Li Si", and the candidate documents include "Detention Certificate", "Notice of Extension of Detention Period", "Arrest Certificate", "Notice of Bail Pending Trial", "Call Record Form", and "Confession and Acceptance of Punishment". In fact, only the "Call Record Form" among the candidate documents belongs to the target person "Zhang San", and the other candidate documents all belong to the target person "Li Si". However, if the candidate documents are not screened, when the documents are associated and consulted, all candidate documents need to be consulted for the target person "Zhang San", and all candidate documents also need to be consulted for the target person "Li Si". Therefore, verifying the candidate documents for the target persons can further reduce the workload and improve work efficiency.

[0073] Step S35: Check whether it passes. If so, execute step S36, otherwise execute step S38.

[0074] In an implementation scenario, if the verification is passed, it indicates that the candidate documents for the target person are mutually corresponding, and if the verification is not passed, it indicates that the candidate document does not belong to the corresponding target person.

[0075] Step S36: Verify the legality.

[0076] In an implementation scenario, all candidate documents should be legal. The content of candidate documents directly affects the content of the work. When the document association method is used in a lawsuit, the candidate documents will be directly used as evidence documents, so the compliance and legality of the documents need to be verified. For example: if the candidate document is a "case filing and execution document", the seal of the relevant government agency must be included in the full evidence document of the candidate document; if the candidate document is a personal "application", the application must be signed with a personal signature, date, etc. Only when the candidate document is legal, the candidate document is meaningful for reference.

[0077] Step S37: Check whether it passes. If so, execute step S39, otherwise execute step S38.

[0078] If the validity check passes, it means that the candidate document is legal. Otherwise, the candidate document cannot be used as an associated document.

[0079] Step S38: Delete the candidate document.

[0080] In an implementation scenario, the deleted candidate documents will be returned to the list of documents to be associated to ensure that when the next first field type has a mapping relationship with it, no document will be missed when searching for the documents to be associated. For example, if there are two target persons, namely "Zhang San" and "Li Si", the candidate documents include all documents related to "Zhang San" and "Li Si", and the candidate documents include "Detention Certificate", "Notice of Extension of Detention Period", "Arrest Certificate", "Notice of Bail Pending Trial", "Call Record Form", and "Confession and Acceptance of Punishment". In practice, only "Call Record Form" belongs to the target person "Zhang San" in the candidate documents. After screening the target person "Zhang San", "Detention Certificate", "Notice of Extension of Detention Period", "Arrest Certificate", "Notice of Bail Pending Trial", and "Confession and Acceptance of Punishment" will be deleted. These documents will be returned to the list of documents to be associated. When screening the target person "Li Si", the relevant candidate documents will not be missed, ensuring the normal operation of the work.

[0081] Step S39: retain the candidate document.

[0082] In an implementation scenario, when a candidate document is retained after screening, it indicates that the candidate document is a candidate document related to the target person, and the candidate document is arranged in a candidate document list according to the priority order in the candidate document.

[0083] The above scheme identifies the first key field and the first field attribute in the target document, wherein the first field attribute includes the first field type to which the first field belongs; based on the mapping relationship between the field type and the document type, a candidate document related to the first key field is searched in at least one document to be associated; based on the verification results of each candidate document, the candidate document is selected as the associated document. Therefore, the accuracy of the search is improved in the process of searching for associated documents. In addition, since the verification is performed in the process of screening the associated documents, the error rate in the process of searching for associated documents can be reduced as much as possible.

[0084] In some disclosed embodiments, after determining the associated documents of the target document, it is also possible to respond to the first key field selected by the user in the target document by using the selected first key field as the target key field, and display the target document and the associated documents corresponding to the target key field on the same screen on the document display interface, and the document display interface includes a first display area and a second display area, the first display area is used to display the target document, and the second display area is used to display the associated documents.

[0085] In an implementation scenario, still taking the case handling scenario as an example, the target document may be "Zhang San entered a jewelry store in a certain year and month and stole a number of jewelry...", etc. When the user selects "Zhang San" as the first field in the target document, and the first field type is "criminal record", the corresponding associated document display interface will appear with "Zhang San's" "detention certificate", "arrest certificate", "bail pending trial notice" and other associated documents, and the associated documents are arranged in order of priority. Among them, the document display interface has two display areas, the first display area displays the target document content, and the second display area displays the associated document content. The first display area and the second display area can be distributed up and down, or left and right, which is not limited here.

[0086] In one implementation scenario, different types of associated documents have different priorities, and the second display area displays the associated documents in order of priority. Still taking the case handling scenario as an example, when "detention warrant", "arrest warrant", and "notice of extension of detention period" appear in the associated documents, their priority order can be configured according to business needs. The configurable priority order is "detention warrant", "notice of extension of detention period", and "arrest warrant". Business personnel need to investigate the reasons for the extension of the period in the notice of extension of detention period to see if there is a connection between the cases, or other reasons. The specific priority order can be configured according to the actual situation and is not limited here. After the priority order is configured, it can be viewed in the second display area. The second display area can also be set with an up or down button. The user can click the up or down button to switch the display between the associated documents. Upward can display associated documents with higher priority, and downward can display associated documents with lower priority. The page switching method can also be set, for example, it can be set to page turning or sliding. The specific setting method is not limited here and can be set according to the actual situation.

[0087] In one implementation scenario, before the target document and the associated document corresponding to the target key field are displayed on the same screen in the document display interface, the second key field and its second field attribute in the associated document can be identified, and the second field attribute includes the second field type to which the second key field belongs, and then the second key field of the second field type related to the first field type is selected as the associated key field of the target key field, and the second display area highlights the associated key field in the associated document in a preset format. In the above manner, highlighting the preset format can enable the user to quickly locate and read the main content of the displayed associated document when viewing the associated document.

[0088] In one implementation scenario, still taking the case handling scenario as an example, the field type "name" can be associated with "household registration information", and the location of the field type "name" in the "household registration information" is highlighted, and the associated document content is recommended more intelligently, which is convenient for users to quickly read and compare. In addition, the method for obtaining the second key field and its second field attribute can refer to the relevant description of the first key field and its first field attribute in the aforementioned public embodiment, which will not be repeated here.

[0089] In an implementation scenario, still taking case handling as an example, the location of the "name" in the "household registration information" can be highlighted. If the household registration information registration form is already defined, and the content filled in the first paragraph of the text area of ​​the household registration information registration form is "name", then the field type can be directly identified according to the business rules, and the first paragraph of the text area of ​​the document content can be directly located; if the household registration information registration form is not defined, it is necessary to identify it according to the element extraction field type. Through identification, the second display area highlights the associated key fields in the associated document in a preset format. Among them, the highlighting method can be highlighting, and the color of the highlighted area can be set by itself, which is not limited here.

[0090] In one implementation scenario, the mapping relationship can be adjusted based on the user's viewing of the associated documents corresponding to each first key field, and the viewing situation includes at least one of the viewing duration and the viewing frequency. In the above manner, the target document and the associated documents corresponding to the target key field are displayed on the same screen on the document display interface, and the associated key fields in the associated documents are highlighted in a preset format, which can maximize the speed of searching for the key fields of the document at work and improve work efficiency.

[0091] In a specific implementation scenario, the viewing situation is based on the associated documents displayed in the second display area, and can be adjusted according to the user's usage habits or the closeness of the user's viewing of the document association. Still taking case handling as an example, when the user has worked for a period of time, the mapping relationship needs to be adjusted. If the field type is "criminal record", the document types include "detention certificate", "notice of extension of detention period", "arrest certificate", "notice of bail pending trial", but the user's probability of using "notice of bail pending trial" in actual application is less than 5%, but when the field type is "criminal record", the probability of consulting "alarm record table" is about 70%. The user can adjust its mapping relationship, delete the mapping relationship between "notice of bail pending trial" and "criminal record situation", and can add the mapping relationship between "alarm record table" and "criminal record situation". The specific mapping relationship can be set according to the actual use of the user, and is not limited here.

[0092] In another specific implementation scenario, based on the user's viewing of the associated documents corresponding to each first key field, if the display time of the associated document in the second display area can be counted in the background, and the number of views is also counted, when the user reads any associated document, the background can record the user's reading time. When the user needs to adjust the priority order in the candidate documents, the user can refer to the background statistical data for adjustment. For example: there are "Detention Certificate", "Notice of Extension of Detention Period", "Arrest Warrant" and "Notice of Bail Pending Trial" in the candidate documents. The user can refer to the viewing time and the number of views in the background. The viewing time and the number of views can be referred to alone or in combination. There is no specific limitation and it can be set according to the actual application scenario.

[0093] See also Figure 4 , Figure 4 It is a framework diagram of an embodiment of the document association device of the present application. The document association device 40 includes a document acquisition module 41, a document identification module 42, a document search module 43 and a document selection module 44. Among them, the document acquisition module 41 is used to acquire a document collection, the document collection includes a plurality of documents, and the plurality of documents include a target document and at least one document to be associated; the document identification module 42 is used to identify the first key field and its first field attribute in the target document; the first field attribute includes the first field type to which the first key field belongs; the document search module 43 is used to search for candidate documents related to the first key field in at least one document to be associated based on the mapping relationship between the field type and the document type; the document selection module 44 is used to select candidate documents as associated documents based on the verification results of each candidate document.

[0094] The above scheme obtains a document set, and the document set includes several documents, and the several documents include a target document and at least one document to be associated, and identifies the first key field and the first field attribute in the target document, and the first field attribute includes the first field type to which the first field belongs, and then searches for candidate documents related to the first key field in at least one document to be associated based on the mapping relationship between the field type and the document type, and selects the candidate documents as associated documents based on the verification results of each candidate document. On the one hand, since there is no need to analyze the correlation between documents through manual reading, it helps to improve the efficiency of document association. On the other hand, in the process of document association, the associated documents are finally obtained through layer-by-layer screening such as field identification, document mapping and document verification, which can reduce the error rate of document association as much as possible and improve the quality of document association. Therefore, the quality and efficiency of document association can be improved.

[0095] In some disclosed embodiments, the mapping relationship includes a sub-mapping relationship for each field type, and the sub-mapping relationship includes the field type and at least one document type related to the field type.

[0096] Therefore, the mapping relationship can improve the accuracy of document association, thereby increasing the speed of document association and further improving work efficiency.

[0097] In some disclosed embodiments, the document search module 43 includes a candidate type determination submodule for selecting, based on a mapping relationship, a document type related to the first field type to which the first key field belongs as a candidate type, and the document search module 43 includes a candidate document determination submodule for selecting a document to be associated as a candidate document based on the similarity between the candidate type and the document title of each document to be associated.

[0098] Therefore, by selecting the document to be associated as the candidate document through the similarity between the candidate type and the document title of each document to be associated, the accuracy of document association can be improved as much as possible, and the error rate of document association can be reduced as much as possible.

[0099] In some disclosed embodiments, the first field attribute includes a target person involved in the first key field. The verification result includes at least one of a first sub-result and a second sub-result, the first sub-result including whether the candidate document involves the target person, and the second sub-result including whether the candidate document is compliant and legal.

[0100] Therefore, the first verification sub-result is used to determine whether the candidate document involves the target person, and the second judgment sub-result is used to determine whether the candidate document is compliant and legal. The selected candidate document improves the accuracy of document association as much as possible, which is conducive to reducing the number of invalid documents read during the work process and improving work efficiency.

[0101] In some disclosed embodiments, the verification result includes a first sub-result, the document selection module 44 includes a first verification sub-module, the first verification sub-module includes a first data acquisition unit for acquiring first data of the candidate document at a first preset position, and the first verification sub-module includes a first result acquisition unit for acquiring the first sub-result based on whether the first data contains a target person.

[0102] Therefore, by acquiring the first data at the first preset position, the time for searching the first data in the document can be reduced, thereby improving work efficiency as much as possible.

[0103] In some disclosed embodiments, the verification result includes a second sub-result, the document selection module 44 includes a second verification sub-module, the second verification sub-module includes a second data acquisition unit for acquiring second data of the candidate document at a second preset position, and the second verification sub-module includes a second result acquisition unit for acquiring the second sub-result based on whether the second data contains seal information.

[0104] Therefore, by obtaining the second data at the preset position, judging whether the candidate document is compliant and legal is helpful to determine the legality of the candidate document.

[0105] In some disclosed embodiments, the document association device 40 also includes a field selection module for responding to a first key field selected by a user in a target document and using the selected first key field as a target key field; the document association device 40 also includes a document display module for displaying the target document and the associated documents corresponding to the target key field on the same screen on a document display interface, the document display interface including a first display area and a second display area, the first display area being used to display the target document, and the second display area being used to display the associated documents.

[0106] Therefore, by displaying the target document and the associated documents on the same screen, the key attributes of the two can be compared, thereby increasing reading speed and improving work efficiency.

[0107] In some disclosed embodiments, different document types have different priorities, and the second display area displays associated documents in order of priority.

[0108] Therefore, displaying related documents in order of priority helps the staff to classify the related documents, so that the content of the related documents can be viewed more quickly and accurately.

[0109] In some disclosed embodiments, the document identification module 42 is also used to identify a second key field and its second field attributes in the associated document, wherein the second field attributes include a second field type described by the second key field, and the document association device 40 also includes a field association module for selecting a second key field related to the first field type as an associated key field of the target key field, and the second display area highlights the associated key field in the associated document in a preset format.

[0110] Therefore, by highlighting the associated key fields, it is possible to quickly locate the key field content, increase the speed of consulting the associated documents, and further improve work efficiency.

[0111] In some disclosed embodiments, the first key field and its first field attribute are obtained by identifying the target document based on at least one of a semantic recognition model and a preset business rule.

[0112] Therefore, by identifying the target document through a semantic recognition model or a preset business rule, the first key field and the first field attribute can be determined more accurately, thereby quickly and accurately completing the identification of the target document.

[0113] In some disclosed embodiments, the document association device 40 also includes a relationship adjustment module for adjusting the mapping relationship based on the user's viewing of the associated documents corresponding to each first key field, wherein the viewing status includes at least one of viewing duration and viewing frequency.

[0114] Therefore, by adjusting the mapping relationship, it is more convenient to consult the associated documents when associating documents, which reduces the staff's screening of associated documents, can save time and improve work efficiency.

[0115] See also Figure 5 , Figure 5 1 is a schematic diagram of a framework of an embodiment of an electronic device of the present application. The electronic device 50 includes a memory 51 and a processor 52 coupled to each other, the memory 51 stores program instructions, and the processor 52 is used to execute the program instructions to implement the steps in any of the above document association method embodiments. Specifically, the electronic device 50 may include but is not limited to: a desktop computer, a laptop computer, a server, a mobile phone, a tablet computer, etc., which are not limited here.

[0116] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps in any of the above document association method embodiments. The processor 52 can also be called a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 52 can be implemented by an integrated circuit chip.

[0117] The above scheme obtains a document set, and the document set includes several documents, and the several documents include a target document and at least one document to be associated, and identifies the first key field and the first field attribute in the target document, and the first field attribute includes the first field type to which the first field belongs, and then searches for candidate documents related to the first key field in at least one document to be associated based on the mapping relationship between the field type and the document type, and selects the candidate documents as associated documents based on the verification results of each candidate document. On the one hand, since there is no need to analyze the correlation between documents through manual reading, it helps to improve the efficiency of document association. On the other hand, in the process of document association, the associated documents are finally obtained through layer-by-layer screening such as field identification, document mapping and document verification, which can reduce the error rate of document association as much as possible and improve the quality of document association. Therefore, the quality and efficiency of document association can be improved.

[0118] See also Figure 6 , Figure 6 The computer-readable storage medium 60 stores program instructions 61 that can be executed by a processor, and the program instructions 61 are used to implement the steps in any of the above document association method embodiments.

[0119] The above scheme obtains a document set, and the document set includes several documents, and the several documents include a target document and at least one document to be associated, and identifies the first key field and the first field attribute in the target document, and the first field attribute includes the first field type to which the first field belongs, and then searches for candidate documents related to the first key field in at least one document to be associated based on the mapping relationship between the field type and the document type, and selects the candidate documents as associated documents based on the verification results of each candidate document. On the one hand, since there is no need to analyze the correlation between documents through manual reading, it helps to improve the efficiency of document association. On the other hand, in the process of document association, the associated documents are finally obtained through layer-by-layer screening such as field identification, document mapping and document verification, which can reduce the error rate of document association as much as possible and improve the quality of document association. Therefore, the quality and efficiency of document association can be improved.

[0120] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0121] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0124] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A document association method, characterized in that: include: Acquire a document set; wherein the document set includes a plurality of documents, and the plurality of documents include a target document and at least one document to be associated; Identify a first key field and a first field attribute in the target document; wherein the first field attribute includes a first field type to which the first key field belongs; Based on the mapping relationship between the field type and the document type, searching for a candidate document related to the first key field in the at least one document to be associated; Based on the verification results of each of the candidate documents, the candidate document with the verification result of passing the verification is selected as the associated document; wherein, the several documents are related to at least one target person, the first field attribute also includes the target person involved in the first key field, the verification result includes a first sub-result and a second sub-result, the first sub-result includes whether the candidate document involves the target person, the second sub-result includes whether the candidate document is compliant and legal, and the verification result of passing the verification includes that the first sub-result involves the target person and the second sub-result is compliant and legal.

2. The method according to claim 1, characterized in that: The mapping relationship includes a sub-mapping relationship of each of the field types, and the sub-mapping relationship includes the field type and at least one of the document types related to the field type.

3. The method according to claim 1, characterized in that: The step of searching the at least one document to be associated to obtain a candidate document related to the first key field based on the mapping relationship between the field type and the document type includes: Based on the mapping relationship, select a document type related to a first field type to which the first key field belongs as a candidate type; Based on the similarity between the candidate type and the document title of each of the documents to be associated, the document to be associated is selected as the candidate document.

4. The method according to claim 1, characterized in that: The step of obtaining the first sub-result comprises: Acquire first data of the candidate document at a first preset position; The first sub-result is obtained based on whether the first data includes the target person.

5. The method according to claim 1, characterized in that The step of obtaining the second sub-result comprises: Acquire second data of the candidate document at a second preset position; The second sub-result is obtained based on whether the second data includes seal information.

6. The method according to claim 1, characterized in that After selecting the candidate document with the verification result of passing the verification as the associated document based on the verification result of each candidate document, the method further includes: In response to a first key field selected by a user in the target document, taking the selected first key field as a target key field; Displaying the target document and the associated documents corresponding to the target key fields on the same screen on the document display interface; The document display interface includes a first display area and a second display area, the first display area is used to display the target document, and the second display area is used to display associated documents.

7. The method according to claim 6, characterized in that Different document types have different priorities, and the second display area displays the associated documents in order according to the priorities.

8. The method according to claim 6, characterized in that Before displaying the target document and the associated documents corresponding to the target key field on the document display interface on the same screen, the method further includes: Identify a second key field and a second field attribute thereof in the associated document; wherein the second field attribute includes a second field type to which the second key field belongs; Selecting a second key field of the second field type that is related to the first field type as an associated key field of the target key field; The second display area highlights the associated key fields in the associated document in a preset format.

9. The method according to claim 1, characterized in that: The first key field and the first field attribute thereof are obtained by identifying the target document based on at least one of a semantic recognition model and a preset business rule.

10. The method according to claim 1, characterized in that After selecting the candidate document with the verification result of passing the verification as the associated document based on the verification result of each candidate document, the method further includes: Adjusting the mapping relationship based on the viewing status of the associated documents corresponding to each of the first key fields by the user; The viewing situation includes at least one of viewing duration and viewing frequency.

11. A document association device, characterized in that: include: A document acquisition module, used to acquire a document set; wherein the document set includes a plurality of documents, and the plurality of documents include a target document and at least one document to be associated; A document identification module, used for identifying a first key field and a first field attribute in the target document; wherein the first field attribute includes a first field type to which the first key field belongs; A document search module, configured to search for candidate documents related to the first key field in the at least one document to be associated based on a mapping relationship between field types and document types; A document selection module is used to select the candidate document with the verification result of passing the verification as an associated document based on the verification results of each of the candidate documents; wherein the several documents are related to at least one target person, the first field attribute also includes the target person involved in the first key field, the verification result includes a first sub-result and a second sub-result, the first sub-result includes whether the candidate document involves the target person, the second sub-result includes whether the candidate document is compliant and legal, and the verification result of passing the verification includes that the first sub-result involves the target person and the second sub-result is compliant and legal.

12. An electronic device, characterized in that: It comprises a memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the document association method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: Program instructions that can be executed by a processor are stored, and the program instructions are used to implement the document association method according to any one of claims 1 to 10.