Document Search Platform, Search Method, Device, Electronic Device and Storage Medium

Abstract

The present disclosure provides a document search platform, a search method, a device, an electronic device, and a storage medium. The method includes: obtaining a document to be processed, where the document to be processed has a corresponding document type, and obtaining tag information corresponding to the document to be processed. Then, according to the tag information and the document to be processed, a target document library corresponding to the document type is constructed, and according to the target document library, a target document search platform is formed. Since the target document search platform is formed according to the target document library corresponding to the document type, the constructed target document platform can provide document search services of the corresponding document type for different business scenarios based on the target document library of the corresponding document type, thereby effectively improving the reusability of the document search platform and enabling the constructed document search platform to effectively meet the document search needs of different business scenarios. The present disclosure can also combine RPA and AI to implement the construction of the IA document search platform, further reducing labor costs.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a document search platform, a search method, a device, an electronic device, and a storage medium. Background Art

[0002] Robotic Process Automation (RPA) refers to the use of specific "robot software" to simulate human operations on a computer and automatically execute process tasks according to rules. Artificial Intelligence (AI) is a technical science that studies, develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence.

[0003] In the related art, in order to meet the document search requirements of corresponding business scenarios, a document search platform is usually constructed based on all documents in the corresponding business scenario. For different business scenarios, multiple different document search platforms usually need to be constructed.

[0004] In this way, the constructed document search platform cannot meet the document search requirements in different business scenarios, resulting in the constructed document search platform not being reusable in different business scenarios. Summary of the Invention

[0005] Embodiments of the present disclosure provide a method for constructing a document search platform, a document search method, a device, an electronic device, and a storage medium to solve the problems in the related art. The technical solutions are as follows:

[0006] In a first aspect, a method for constructing a document search platform proposed by an embodiment of the present disclosure includes: obtaining a document to be processed, where the document to be processed has a corresponding document type; obtaining tag information corresponding to the document to be processed; constructing a target document library corresponding to the document type according to the tag information and the document to be processed; and forming a target document search platform according to the target document library.

[0007] In an implementation manner, obtaining tag information corresponding to the document to be processed includes: determining a parent tag corresponding to the document to be processed; parsing a sub-tag corresponding to the parent tag from the document to be processed; and using the parent tag and the sub-tag together as the tag information.

[0008] In one embodiment, parsing sub - tags corresponding to a parent tag from a document to be processed includes: invoking a natural language processing (NLP) service in the field of artificial intelligence (AI) to identify a document general index corresponding to the parent tag from the document to be processed, and using the document general index as the sub - tag; and / or invoking the NLP service to identify an associated entity value corresponding to the parent tag from the document to be processed, and using the associated entity value as the sub - tag.

[0009] In one embodiment, constructing a target document library corresponding to a document type according to tag information and a document to be processed includes: invoking a robotic process automation (RPA) robot to determine an initial document library corresponding to the document type; storing the tag information and the document to be processed in the initial document library to form a target document library.

[0010] In one embodiment, storing tag information and a document to be processed in an initial document library includes: obtaining a target loading type corresponding to the document to be processed; using a target document storage method corresponding to the target loading type to store the tag information and the document to be processed in the initial document library.

[0011] In one embodiment, using a target document storage method corresponding to a target loading type to store tag information and a document to be processed in an initial document library includes: if the target loading type is a document loading type, storing the document to be processed and the corresponding document tag information in the target document library; and / or if the target loading type is a link loading type, storing the access link corresponding to the document to be processed and the corresponding tag information in the target document library; and / or if the target loading type is a rich - text loading type, editing the document to be processed via a rich - text editor and storing the editing result and the corresponding tag information in the target document library.

[0012] In one embodiment, after determining a parent tag corresponding to a document to be processed, it further includes: configuring an attribute for the parent tag and using the configured attribute as tag information, where the attribute is used to identify whether the parent tag participates in document search.

[0013] In a second aspect, a document search method proposed by an embodiment of the present disclosure is applied to a document search platform, and the document search platform is constructed by the construction method of the document search platform in the first aspect above. The document search method includes: receiving a document search request, parsing a required document type and required tag information from the document search request, and then determining a target document library corresponding to the required document type from multiple document libraries, where the multiple document libraries belong to the document search platform and the document libraries are used to store documents of corresponding document types; searching for a target document corresponding to the required tag information from the target document library.

[0014] In one embodiment, the requirement tag information includes: requirement attributes and requirement sub-tags. There are multiple corresponding parent tags in the target document library, and each parent tag has corresponding sub-tags, where the corresponding sub-tags are used to describe the documents. Among them, searching for the target document corresponding to the requirement tag information in the target document library includes: invoking the natural language processing (NLP) service in the field of artificial intelligence (AI) to process the requirement attributes, so as to determine the target parent tag from the multiple parent tags, where the target parent tag has corresponding target sub-tags; searching for the target document in the target document library according to the requirement attributes, requirement sub-tags, and target sub-tags.

[0015] In one embodiment, the target document library includes: multiple documents. Among them, searching for the target document in the target document library according to the requirement attributes, requirement sub-tags, and target sub-tags includes: invoking a robotic process automation (RPA) robot to search for the documents to be screened from the multiple documents according to the requirement sub-tags and the target sub-tags; screening the target document from the multiple documents to be screened according to the requirement attributes.

[0016] In one embodiment, searching for multiple documents to be screened from the target document library according to the requirement sub-tags and the target sub-tags includes: determining the similarity value between the requirement sub-tags and the target sub-tags of each document; if the similarity value meets the set condition, then taking the document corresponding to the corresponding target sub-tag as the document to be screened.

[0017] In a third aspect, an apparatus for constructing a document search platform proposed by an embodiment of the present disclosure includes: a first acquisition module, configured to acquire a document to be processed, where the document to be processed has a corresponding document type; a second acquisition module, configured to acquire tag information corresponding to the document to be processed; a construction module, configured to construct a target document library corresponding to the document type according to the tag information and the document to be processed; and a formation module, configured to form a target document search platform according to the target document library.

[0018] In one embodiment, the second acquisition module includes: a first determination sub-module, configured to determine the parent tag corresponding to the document to be processed; a parsing sub-module, configured to parse the sub-tag corresponding to the parent tag from the document to be processed; and a processing sub-module, configured to use the parent tag and the sub-tag together as the tag information.

[0019] In one embodiment, the parsing sub-module is further configured to: invoke the natural language processing (NLP) service in the field of artificial intelligence (AI) to identify the document general index corresponding to the parent tag from the document to be processed, and use the document general index as the sub-tag; and / or invoke the NLP service to identify the associated entity value corresponding to the parent tag from the document to be processed, and use the associated entity value as the sub-tag.

[0020] In one embodiment, the building module includes: a second determination sub-module, configured to call a robotic process automation (RPA) robot to determine an initial document library corresponding to a document type; and a storage sub-module, configured to store tag information and a document to be processed in the initial document library to form a target document library.

[0021] In one embodiment, the storage sub-module is further configured to: obtain a target loading type corresponding to the document to be processed; and store the tag information and the document to be processed in the initial document library by using a target document storage method corresponding to the target loading type.

[0022] In one embodiment, the storage sub-module is further configured to: if the target loading type is a document loading type, store the document to be processed and corresponding document tag information in the target document library; and / or if the target loading type is a link loading type, store an access link corresponding to the document to be processed and corresponding tag information in the target document library; and / or if the target loading type is a rich text loading type, perform an editing process on the document to be processed via a rich text editor, and store the editing result and corresponding tag information in the target document library.

[0023] In one embodiment, the second obtaining module further includes: a configuration sub-module, configured to configure attributes for a parent tag and use the configured attributes as tag information, where the attributes are used to identify whether the parent tag participates in document search.

[0024] In one embodiment, the method for building a document search platform is implemented by using artificial intelligence (AI) and robotic process automation (RPA).

[0025] In a fourth aspect, a document search device according to an embodiment of the present disclosure is built by the building device including a document search platform in the third aspect above. The document search device includes: a receiving module, configured to receive a document search request; a parsing module, configured to parse a required document type and required tag information from the document search request; a determination module, configured to determine a target document library corresponding to the required document type from multiple document libraries, where the multiple document libraries belong to the document search platform and the document libraries are used to store documents of corresponding document types; and a search module, configured to search for a target document corresponding to the required tag information from the target document library.

[0026] In one embodiment, the requirement tag information includes: requirement attributes and requirement sub-tags. There are corresponding multiple parent tags in the target document library, and each parent tag has corresponding sub-tags, and the corresponding sub-tags are used to describe documents. Among them, the search module includes: a third determination sub-module, configured to call a natural language processing (NLP) service in the field of artificial intelligence (AI) to process the requirement attributes, so as to determine a target parent tag from the multiple parent tags, where the target parent tag has corresponding target sub-tags; a search sub-module, configured to search for a target document from the target document library according to the requirement attributes, requirement sub-tags, and target sub-tags.

[0027] In one embodiment, the target document library includes: multiple documents. Among them, the search sub-module is further configured to: call a robotic process automation (RPA) robot to search for documents to be screened from the multiple documents according to the requirement sub-tags and the target sub-tags; screen the target document from the multiple documents to be screened according to the requirement attributes.

[0028] In one embodiment, the search sub-module is further configured to: determine a similarity value between the requirement sub-tags and the target sub-tags of each document; if the similarity value meets a set condition, use the document corresponding to the corresponding target sub-tag as the document to be screened.

[0029] In a fifth aspect, an electronic device provided by an embodiment of the present disclosure includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the program, it implements a method for constructing a document search platform provided in the embodiment of the first aspect, or implements a document search method provided in the embodiment of the second aspect.

[0030] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements a method for constructing a document search platform provided in the embodiment of the first aspect, or implements a document search method provided in the embodiment of the second aspect.

[0031] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present disclosure will be readily apparent by reference to the drawings and the following detailed description. Description of the Drawings

[0032] In the drawings, unless otherwise specified, the same reference numerals throughout the several views denote the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments proposed according to the present disclosure and should not be regarded as limiting the scope of the present disclosure.

[0033] Figure 1 It is a schematic flowchart of a method for constructing a document search platform proposed in an embodiment of the present disclosure;

[0034] Figure 2 It is a schematic flowchart of a method for constructing a document search platform proposed in another embodiment of the present disclosure;

[0035] Figure 3 It is a schematic flowchart of a method for constructing a document search platform proposed in another embodiment of the present disclosure;

[0036] Figure 4 It is a schematic diagram of a document library construction interface proposed in an embodiment of the present disclosure;

[0037] Figure 5 It is a schematic diagram of a document storage management interface proposed in an embodiment of the present disclosure;

[0038] Figure 6A It is a schematic diagram of a document storage interface of the document loading type proposed in an embodiment of the present disclosure;

[0039] Figure 6B It is a schematic diagram of a document storage interface of the link loading type proposed in an embodiment of the present disclosure;

[0040] Figure 6C It is a schematic diagram of a document storage interface of the rich text loading type proposed in an embodiment of the present disclosure;

[0041] Figure 7 It is a schematic diagram of a tag information configuration interface proposed in an embodiment of the present disclosure;

[0042] Figure 8 It is a schematic diagram of an attribute configuration interface proposed in an embodiment of the present disclosure;

[0043] Figure 9 It is a schematic flowchart of a document search method proposed in an embodiment of the present disclosure;

[0044] Figure 10 It is a schematic flowchart of a document search method proposed in another embodiment of the present disclosure;

[0045] Figure 11 It is a schematic diagram of a document attribute editing interface proposed in an embodiment of the present disclosure;

[0046] Figure 12 It is a schematic diagram of a document search interface proposed in an embodiment of the present disclosure;

[0047] Figure 13 It is a schematic diagram of a document screening interface proposed in an embodiment of the present disclosure;

[0048] Figure 14It is a schematic structural diagram of a device for constructing a document search platform proposed in an embodiment of the present disclosure;

[0049] Figure 15 It is a schematic structural diagram of a device for constructing a document search platform proposed in another embodiment of the present disclosure;

[0050] Figure 16 It is a schematic structural diagram of a document search device proposed in an embodiment of the present disclosure;

[0051] Figure 17 It is a schematic structural diagram of a document search device proposed in another embodiment of the present disclosure;

[0052] Figure 18 It is a schematic hardware structure diagram of an electronic device provided in an embodiment of the present disclosure. Detailed implementation manners

[0053] The embodiments of the present disclosure will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary only for explaining the present disclosure and should not be construed as limiting the present disclosure.

[0054] In the description of the embodiments of the present disclosure, the term "a plurality" means two or more.

[0055] In the description of the embodiments of the present disclosure, the term "document to be processed" refers to a document that is currently to be processed, for example, a professional knowledge document, an enterprise information document, etc.

[0056] In the description of the embodiments of the present disclosure, the term "document type" means that the document to be processed can be divided into multiple document types according to different classification bases, for example, a medical document type, a legal document type, etc.

[0057] In the description of the embodiments of the present disclosure, the term "tag information" refers to information used to describe the tags of the document to be processed, for example, the feature information of the tag, the content information of the tag, etc.

[0058] In the description of the embodiments of the present disclosure, the term "parent tag" refers to a tag preset for the document to be processed, that is, it can be called a parent tag, and this parent tag can be, for example, an associated entity reused from other platforms.

[0059] In the description of the embodiments of the present disclosure, the term "document general index" refers to a document index that can be applied to all documents to be processed, for example, document type, document size, document name, document storage address, document update time, etc.

[0060] In the description of the embodiments of the present disclosure, the term "attribute" refers to information used to describe the attributes of a parent tag. For example, information such as the tag name, the tag data format, the description of whether the tag is allowed to be modified, and the description of whether the tag participates in the search, etc.

[0061] In the description of the embodiments of the present disclosure, the term "sub-tag" refers to the specific document content corresponding to the parent tag.

[0062] In the description of the embodiments of the present disclosure, the term "associated entity value" refers to relevant information used to specifically describe the corresponding parent tag. For example, the characteristic information of the associated entity, the content information of the associated entity, etc.

[0063] In the description of the embodiments of the present disclosure, the term "initial document library" refers to the document library corresponding to the document type of the document to be processed from multiple document libraries in the initial stage of the execution of the method for constructing a document search platform.

[0064] In the description of the embodiments of the present disclosure, the term "document search request" refers to a request made by the user-side electronic device for triggering a document search in the document search platform. [[ID=!3]]

[0065] In the description of the embodiments of the present disclosure, the term "required document type" refers to the document type that a user can have when performing a document search. This document type can be referred to as the required document type, and this required document search type can be used to represent the document search requirements in the business scenario where the user is located.

[0066] In the description of the embodiments of the present disclosure, the term "required tag information" refers to the tag information that a user can have when performing a document search. For example, the document name that the user needs to search for, the document content keywords, etc.

[0067] Referring to the following description and the accompanying drawings, these and other aspects of the embodiments of the present disclosure will become clear. In these descriptions and drawings, some specific implementation manners in the embodiments of the present disclosure are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present disclosure. However, it should be understood that the scope of the embodiments of the present disclosure is not limited thereto. On the contrary, the embodiments of the present disclosure include all variations, modifications, and equivalents that fall within the spirit and connotation of the appended claims.

[0068] Figure 1 It is a schematic flowchart of a method for constructing a document search platform proposed by an embodiment of the present disclosure.

[0069] In this embodiment, the method for constructing a document search platform is configured in a device for constructing a document search platform for illustration. In this embodiment, the method for constructing a document search platform can be configured in a device for constructing a document search platform. The device for constructing a document search platform can be set in a server or in an electronic device. The embodiments of the present disclosure do not limit this.

[0070] See Figure 1 , the method for constructing the document search platform includes:

[0071] S101: Obtain a document to be processed, where the document to be processed has a corresponding document type.

[0072] Among them, the document currently to be processed, that is, can be referred to as the document to be processed. This document to be processed can be used to assist in constructing a document search platform during the execution of the method for constructing a document search platform. The document to be processed can be specifically, for example, a professional knowledge document, an enterprise information document, etc., and this is not limited.

[0073] It can be understood that the document to be processed can be divided into multiple document types according to different classification bases. For example, it can be divided according to different application scenarios to which the document to be processed belongs as the classification basis, and the document type can be specifically, for example, a medical document type, a legal document type, etc., and this is not limited.

[0074] In the embodiments of the present disclosure, the document search platform can pre-provide a corresponding data transmission interface, and obtain documents published in different offline business scenarios via this data transmission interface, and use this document as the document to be processed, and this is not limited.

[0075] In some embodiments, it can also be to pre-establish a data transmission link between different offline business scenario platforms and the document search platform, and when there is a new document published in different offline business scenario platforms, generate a corresponding document transmission instruction, and trigger the offline business scenario platform to transmit the newly published document to the document search platform via this document transmission instruction. Or, any possible method can also be used to obtain the document to be processed, and this is not limited.

[0076] After the embodiments of the present disclosure obtain the document to be processed from different offline business scenarios, they can perform annotation processing of the corresponding business scenario on the corresponding document to be processed according to the business scenario to which the document to be processed belongs. For example, when the document to be processed is obtained from a medical scenario, the document to be processed can be marked as a medical document type, and this is not limited.

[0077] S102: Obtain tag information corresponding to the document to be processed.

[0078] Among them, the tags can be used to describe the basic attributes and features of the document. The tags can be used to index and manage the structured field information of the document. The tags can be specifically, for example, the document name, the document update time, etc., and there is no limitation thereto.

[0079] Among them, the information used to describe the tags of the document to be processed can be referred to as tag information. The tag information can be specifically, for example, the feature information of the tags, the content information of the tags, etc., and there is no limitation thereto.

[0080] In the embodiments of the present disclosure, after obtaining the document to be processed, the tag information of the document to be processed can be identified to obtain the tag information corresponding to the document to be processed.

[0081] For example, identifying the tag information of the document to be processed can be entity recognition of the document to be processed. For example, after obtaining the document to be processed, the document to be processed can be input into a pre-trained artificial intelligence (AI) model (the artificial intelligence model can support entity recognition of the document to be processed), and the artificial intelligence model performs entity recognition on the document to be processed to obtain a plurality of entity information corresponding to the document to be processed, and the entity information is used as the tag information corresponding to the document to be processed, and there is no limitation thereto.

[0082] Alternatively, identifying the tag information of the document to be processed can also be feature parsing of the document to be processed after obtaining the document to be processed. For example, the document to be processed can be subjected to feature parsing processing via a feature parsing algorithm to obtain a plurality of feature information corresponding to the document to be processed, and the feature information is used as the tag information corresponding to the document to be processed, and there is no limitation thereto.

[0083] S103: Construct a target document library corresponding to the document type according to the tag information and the document to be processed.

[0084] In the embodiments of the present disclosure, after obtaining the document to be processed and determining the tag information corresponding to the document to be processed, a document library corresponding to the document type can be constructed according to the tag information and the document to be processed, and the document library can be referred to as a target document library.

[0085] In some embodiments, constructing a target document library corresponding to the document type according to the tag information and the document to be processed can also be constructing a document library of the corresponding document type in the document search platform in advance, and performing labeling processing on the corresponding document library using the document type. Then, after obtaining the document to be processed, the document to be processed of the corresponding document type can be stored in the document library of the corresponding document type, and the tag information can be configured on the side of the corresponding document to be processed, so as to construct a target document library, and there is no limitation thereto.

[0086] In the embodiments of the present disclosure, the target document library can be used to store the to-be-processed documents of the corresponding document type and the label information corresponding to the to-be-processed documents. That is to say, according to the label information and the to-be-processed documents, constructing a target document library corresponding to the document type can be storing the obtained to-be-processed documents with the same document type and the corresponding label information into a document library to construct the target document library, and there is no limitation on this.

[0087] In the embodiments of the present disclosure, since the constructed target document library is only used to correspondingly store the to-be-processed documents and label information of one document type, after forming a target document search platform according to the target document library subsequently, the target document library corresponding to the document type corresponding to the actual business scenario can be called in the target document search platform according to the actual business scenario. Furthermore, when searching for documents in the target document library, the searched documents can effectively meet the document search requirements of the actual business scenario.

[0088] S104: Form a target document search platform according to the target document library.

[0089] In the embodiments of the present disclosure, after constructing a target document library corresponding to the document type according to the label information and the to-be-processed documents, the document search platform can be processed according to the target document library, and the obtained document search platform after the aforementioned processing is used as the target document search platform.

[0090] In the embodiments of the present disclosure, processing the document search platform according to the target document library can be, after constructing the target document library, deploying the target document library in the document search platform, and performing annotation processing on the target document library according to the business scenario corresponding to the to-be-processed documents in the target document library (for example, according to the business scenario corresponding to the to-be-processed documents in the target document library, the target document library can be annotated as a medical document library, a legal document library, etc., and there is no limitation on this), and using the obtained document search platform after the aforementioned annotation processing as the target document search platform.

[0091] Alternatively, any other possible method can also be adopted to realize forming a target document search platform according to the target document library, and there is no limitation on this.

[0092] In the embodiments of the present disclosure, since the target document library corresponding to the document type is constructed according to the tag information and the document to be processed, when the target document library is deployed in the document search platform, the constructed target document search platform can provide document search services for different business scenarios based on multiple target document libraries with different business scenarios. Therefore, when different business scenarios perform corresponding document searches, there is no need to reconstruct the document search platform for the corresponding business scenarios, that is, the target document search platform can be directly called, which can effectively improve the reusability of the document search platform and enable the constructed target document search platform to effectively meet the document search requirements of different business scenarios.

[0093] In the embodiments of the present disclosure, the embodiments of the present disclosure can effectively combine RPA and AI to realize the intelligent automation (IA) of the document search platform construction process, thereby effectively improving the automation degree of the document search platform construction and reducing the labor cost.

[0094] In this embodiment, by obtaining the document to be processed, where the document to be processed has a corresponding document type, and obtaining the tag information corresponding to the document to be processed, then constructing a target document library corresponding to the document type according to the tag information and the document to be processed, and forming a target document search platform according to the target document library. Since the target document platform is formed according to the target document library corresponding to the document type, the constructed target document platform can provide document search services of the corresponding document type for different business scenarios based on the target document library of the corresponding document type, thereby effectively improving the reusability of the document search platform and enabling the constructed document search platform to effectively meet the document search requirements of different business scenarios.

[0095] Figure 2 It is a schematic flowchart of the construction method of the document search platform proposed in another embodiment of the present disclosure.

[0096] See Figure 2 , the construction method of the document search platform includes:

[0097] S201: Obtain the document to be processed, where the document to be processed has a corresponding document type.

[0098] For the description of S201, please refer to the above embodiments specifically, and details will not be repeated here.

[0099] S202: Determine the parent tag corresponding to the document to be processed.

[0100] Among them, the tags preset for the document to be processed, which can be called parent tags, can be associated entities reused from other platforms, can also be tags pre-obtained from a tag library, or can also be index information applicable to all documents to be processed, and there is no limitation in this regard.

[0101] Among them, the document to be processed can specifically be a text containing entities. For example: "In the research on the influenza situation among children in 2021, it was found that the occurrence of influenza has a certain seasonality."

[0102] The entities can include diseases, research objects, research times, etc., and there is no limitation in this regard.

[0103] Among them, the associated entity refers to an entity obtained from other platforms that can be reused by the document to be processed. For example, the associated entity can be an associated entity reused from the corresponding medical business platform.

[0104] That is to say, in the embodiments of the present disclosure, obtaining the associated entity corresponding to the document to be processed can be to obtain, via the data transmission interface of the document search platform, the associated entity that can be reused by the document to be processed in other platforms, and using the aforementioned reused associated entity as the parent tag corresponding to the document to be processed, and there is no limitation in this regard.

[0105] Among them, the index information refers to the structured information related to all documents participating in the search. The index information can specifically be, for example, document type, document size, document name, document storage address, document update time, etc., and there is no limitation in this regard.

[0106] In some embodiments, determining the parent tag corresponding to the document to be processed can be, after determining the document to be processed, obtaining, via the data transmission interface of the document search platform, the associated entity that can be reused by other corresponding business platforms, and using this tag as the parent tag. Or, determining the tag corresponding to the document to be processed can also be, after obtaining the document to be processed, obtaining, by the data transmission interface of the document search platform, the tags in the tag library, and using the aforementioned obtained tags as the parent tags corresponding to the document to be processed, and there is no limitation in this regard.

[0107] S203: Configure attributes for the parent tag and use the configured attributes as tag information.

[0108] Among them, the information used to describe the attributes of the parent tag can be called attributes. The attributes can specifically be, for example, tag name, tag data format, description of whether the tag is allowed to be modified, description of whether the tag participates in the search, etc. There is no limitation in this regard. The attributes are used to determine whether the parent tag participates in document search.

[0109] That is to say, after obtaining the parent tag in the embodiments of the present disclosure, various attributes of the parent tag can be configured to meet the document search requirements of different business scenarios. The attribute configuration can specifically be, for example, tag classification, tag name, tag type, whether the tag is required, value type, whether to participate in indexing, visibility filtering, etc., and there is no limitation thereto.

[0110] In the embodiments of the present disclosure, by configuring corresponding attributes for the parent tag and using the attributes as tag information, the parent tag can be flexibly configured and modified based on the attributes, so that the document tag information in the document search platform can effectively meet the document search requirements of different business scenarios.

[0111] S204: Parse the child tag corresponding to the parent tag from the document to be processed.

[0112] Among them, assume that the document to be processed is: "In the influenza situation research for children in 2021, it is found that the occurrence of influenza has a certain seasonality", and the parent tags are: "disease, research object, research time, etc.", and the child tags can be the specific document content corresponding to the parent tags. The child tags corresponding to the parent tags can be, for example: "disease - influenza, research object - children, research time - 2021", and there is no limitation thereto.

[0113] In some embodiments, to parse the child tag corresponding to the parent tag from the document to be processed, after obtaining the document to be processed and determining the corresponding parent tag, the document to be processed and the parent tag can be input into a pre-trained Global Pointer model to obtain the child tag corresponding to the parent tag output by the Global Pointer model, and there is no limitation thereto.

[0114] Among them, the Global Pointer model is an artificial intelligence model based on rotary position encoding (a relative position encoding). This model can support information extraction from documents, or this model can also be configured as any other possible artificial intelligence model that can support extracting corresponding child tags from documents, and there is no limitation thereto.

[0115] Optionally, in some embodiments, to parse the child tag corresponding to the parent tag from the document to be processed, it can be to call the natural language processing (NLP) service in the field of artificial intelligence (AI) to identify the document general index corresponding to the parent tag from the document to be processed, and use the document general index as the child tag. Thus, it can be realized that the document general index corresponding to the parent tag is accurately parsed from the document to be processed as the child tag, so that the parsed document general index can be adapted to the parent tag, and when the document general index is used as the child tag, the determination effect of the child tag can be effectively improved.

[0116] Among them, the document general index refers to the relevant information used to specifically describe the corresponding parent tag. The document general index can specifically be, for example, the feature information of the corresponding parent tag, the content information of the corresponding parent tag, etc., and there is no limitation on this.

[0117] Among them, when the parent tag is "document update time", the corresponding document general index can specifically be, for example, "April 20, 2022", and there is no limitation on this.

[0118] That is to say, in the embodiments of the present disclosure, after determining the parent tag, the document to be processed can be parsed according to the parent tag (wherein, the parsing method can specifically be, for example, semantic parsing, model parsing, etc., and there is no limitation on this), so as to parse and obtain the document general index corresponding to the parent tag from the document to be processed, and use this document general index as the sub-tag, and there is no limitation on this.

[0119] In the embodiments of the present disclosure, to parse and obtain the sub-tag corresponding to the parent tag from the document to be processed, it can also be to call a Natural Language Processing (NLP) service to process the document to be processed, so as to parse and obtain the sub-tag corresponding to the parent tag from the document to be processed, and there is no limitation on this.

[0120] In some embodiments, to extract the associated entity value corresponding to the parent tag (for example, the associated entity) from the document to be processed, it can be to use an entity recognition model to extract the associated entity value corresponding to the parent tag (for example, the associated entity) from the document to be processed, that is, the document to be processed and the corresponding parent tag (for example, the associated entity) can be input into the entity recognition model to obtain the associated entity value corresponding to the parent tag (for example, the associated entity) output by the entity recognition model, and there is no limitation on this.

[0121] Optionally, in some other embodiments, to parse and obtain the sub-tag corresponding to the parent tag from the document to be processed, it can also be to call the NLP service to identify the associated entity value corresponding to the parent tag from the document to be processed, and use the associated entity value as the sub-tag. Thus, it can be realized to accurately parse and obtain the associated entity value corresponding to the parent tag as the sub-tag from the document to be processed, so that the parsed associated entity value can be adapted to the parent tag, and thus when the associated entity value is used as the sub-tag, the determination effect of the sub-tag can be effectively improved.

[0122] Among them, the associated entity value refers to the relevant information used to specifically describe the corresponding parent tag (for example, the associated entity). The associated entity value can specifically be, for example, the feature information of the associated entity, the content information of the associated entity, etc., and there is no limitation on this.

[0123] Among them, when the associated entity is a "disease", the corresponding associated entity value can be, for example, "influenza, cold", and there is no limitation on this.

[0124] In the embodiments of the present disclosure, parsing the sub-tags corresponding to the parent tag from the document to be processed may also be to call a Natural Language Processing (NLP) service to process the document to be processed, so as to identify the associated entity value corresponding to the parent tag from the document to be processed, and use the associated entity value as the sub-tag, and there is no limitation on this.

[0125] S205: Use the parent tag and the sub-tag together as tag information.

[0126] In this embodiment, by determining the parent tag corresponding to the document to be processed and parsing the sub-tags corresponding to the parent tag from the document to be processed, when using the parent tag and the sub-tag together as tag information, the tag information can accurately represent the parent tag and the corresponding sub-tags, so as to effectively improve the comprehensiveness and reference of the tag information, and when providing the tag information to the document search platform, the document search platform can assist the execution of the user's document search work based on the two dimensions of the parent tag and the sub-tag.

[0127] After determining the parent tag corresponding to the document to be processed and parsing the sub-tags corresponding to the parent tag from the document to be processed in the embodiments of the present disclosure, the parent tag and the sub-tag can be used together as tag information, and then, the subsequent construction method of the document search platform can be executed in combination with the tag information. For specific details, reference can be made to the subsequent embodiments.

[0128] S206: Construct a target document library corresponding to the document type according to the tag information and the document to be processed.

[0129] S207: Form a target document search platform according to the target document library.

[0130] For the description of S206 - S207, reference can be specifically made to the above embodiments, and details will not be repeated here.

[0131] In this embodiment, by obtaining a document to be processed, where the document to be processed has a corresponding document type, and determining a parent tag corresponding to the document to be processed, determining the parent tag corresponding to the document to be processed, and parsing a sub-tag corresponding to the parent tag from the document to be processed, it is possible to make the tag information accurately represent the parent tag and the corresponding sub-tags when the parent tag and the sub-tag are used as tag information together, thereby effectively improving the comprehensiveness and reference of the tag information, and when providing the tag information to the document search platform, enabling the document search platform to assist in the execution of the user's document search work based on two dimensions of the parent tag and the sub-tag. Then, configure corresponding attributes for the parent tag and use the attributes as tag information, so that the parent tag can be flexibly configured and modified based on the attributes, and thus the document label information in the document search platform can effectively meet the document search requirements of different business scenarios. Then, according to the tag information and the document to be processed, construct a target document library corresponding to the document type, and form a target document search platform according to the target document library, thereby effectively improving the reusability of the document search platform, and enabling the constructed document search platform to effectively meet the document search requirements of different business scenarios

[0132] Figure 3 It is a schematic flowchart of a method for constructing a document search platform proposed in another embodiment of the present disclosure.

[0133] See Figure 3 , the method for constructing the document search platform includes:

[0134] S301: Obtain a document to be processed, where the document to be processed has a corresponding document type.

[0135] S302: Obtain tag information corresponding to the document to be processed.

[0136] The descriptions of S301 - S302 can be specifically referred to the above embodiments and will not be elaborated here.

[0137] S303: Invoke a robotic process automation (RPA) robot to determine an initial document library corresponding to the document type.

[0138] Among them, in the initial stage of the execution of the method for constructing the document search platform, the document library corresponding to the document type of the document to be processed among multiple document libraries can be referred to as the initial document library, and this initial document library can be used to assist in constructing the target document library during the subsequent execution of the method for constructing the document search platform. Specifically, refer to the subsequent embodiments.

[0139] In the embodiments of the present disclosure, to determine an initial document library corresponding to a document type, a robotic process automation (RPA) robot may be called to automatically label a certain document library according to the document type. After the labeling process of the document library, the document library can only be used to store documents of the corresponding document type. The labeled document library can be referred to as the initial document library.

[0140] S304: Store the label information and the document to be processed in the initial document library to form a target document library.

[0141] After determining the initial document library corresponding to the document type in the embodiments of the present disclosure, the label information and the document to be processed can be stored in the initial document library to form a target document library.

[0142] Optionally, in some embodiments, storing the label information and the document to be processed in the initial document library to form a target document library may be to obtain a target loading type corresponding to the document to be processed and adopt a target document storage method corresponding to the target loading type to store the label information and the document to be processed in the initial document library. Thus, it is possible to adaptively store the corresponding document to be processed based on the target document storage method adapted to the document to be processed, effectively meeting the document storage requirements of the documents to be processed with different target loading types. In addition, by storing the label information and the document to be processed using the target document storage method corresponding to the target loading type, the target loading type of the documents in the initial document library does not need to be limited to a single format, thus enabling effective expansion of the documents in the document search platform to a large extent.

[0143] Among them, the document to be processed can be loaded in different types, and this type can be referred to as the target loading type. The target loading type can be specifically, for example, a document loading type, a link loading type, a rich text loading type, etc., and there is no limitation thereto.

[0144] Among them, different target loading types can have corresponding document storage methods, and this document storage method can be referred to as the target document storage method.

[0145] For example, storing the label information and the document to be processed in the initial document library using the target document storage method corresponding to the document format may be to directly store the document to be processed in the initial document library when the document to be processed is of the text loading type, or alternatively, when the document to be processed is of the image loading type, perform optical character recognition (OCR) on the image and store the recognized text in the initial document library, and there is no limitation thereto.

[0146] Optionally, in some embodiments, a target document storage method corresponding to the document format is adopted to store the tag information and the document to be processed in the initial document library. When the target loading type is the document loading type, the document to be processed and the corresponding document tag information can be stored in the target document library, and / or when the target loading type is the link loading type, the access link corresponding to the document to be processed and the corresponding tag information can be stored in the target document library, and / or when the target loading type is the rich text loading type, the document to be processed is edited through a rich text editor, and the editing result and the corresponding tag information are stored in the target document library.

[0147] In the embodiments of the present disclosure, the document loading type means that the document to be processed supports being directly loaded from the local device of the target document library to the target document library. At this time, the document to be processed and the corresponding tag information can be stored from the local device of the target document library to the target document library.

[0148] In the embodiments of the present disclosure, the link loading type is an external link (for example, a Uniform Resource Locator (URL)), that is, the original file of the document to be processed does not exist locally on the device of the target document library, and this external link supports jumping to the document to be processed corresponding to the external link. At this time, the external link and the corresponding tag information can be stored in the target document library.

[0149] In the embodiments of the present disclosure, the rich text loading type means that the document to be processed is loaded in types such as picture type, audio type, video type, etc. At this time, a rich text editor can be used to edit the document to be processed to obtain the corresponding editing result, and the editing result and the corresponding tag information are stored in the target document library.

[0150] In the embodiments of the present disclosure, since the initial document library corresponding to the document type is determined first, the tag information and the document to be processed of the corresponding document type can be accurately stored in the initial document library of the corresponding document type, so that the document type of the formed target document library can be adapted to the document type of the document to be processed, thereby effectively improving the construction effect of the target document library.

[0151] S305: Form a target document search platform according to the target document library.

[0152] For the description of S305, reference can be specifically made to the above embodiments, and details are not described herein again.

[0153] In the embodiments of the present disclosure, the method for constructing a document search platform described in the embodiments of the present disclosure can be specifically illustrated in combination with specific schematic diagrams. In the initial stage of the method for constructing a document search platform, the document to be processed and the initial document library corresponding to the document type of the document to be processed can be obtained (the initial document library can be constructed in advance in the document library construction interface of the document search platform (the document library construction interface can be seen in ​ , ​ which is a schematic diagram of the document library construction interface proposed in an embodiment of the present disclosure)), and the tag information corresponding to the document to be processed can be obtained. Then, the target loading type corresponding to the document to be processed can be determined, and in the document upload management interface of the document search platform (the document upload management interface can be seen in ​ , ​ which is a schematic diagram of the document storage management interface proposed in an embodiment of the present disclosure), the configuration item of the corresponding document loading type can be selected to enter the document storage interface of different document loading types (the document storage interface of different document loading types can be seen in ​ , ​ , ​ , ​ which is a schematic diagram of the document storage interface of the document loading type proposed in an embodiment of the present disclosure, ​ which is a schematic diagram of the document storage interface of the link loading type proposed in an embodiment of the present disclosure, ​ which is a schematic diagram of the document storage interface of the rich text loading type proposed in an embodiment of the present disclosure), and the corresponding document to be processed can be stored in the corresponding document storage interface.

[0154] After the document to be processed is stored in the initial document library in the embodiments of the present disclosure, corresponding tag information can be configured for the document to be processed on the side of the document to be processed in the initial document library (for example, see ​ , ​ which is a schematic diagram of the tag information configuration interface proposed in an embodiment of the present disclosure, that is, the edit item can be clicked on this interface, and the corresponding tag information configuration operation can be performed under the edit item to realize the configuration of the corresponding tag information for the document to be processed). In addition, the corresponding attributes can also be configured for the parent tag in the attribute configuration interface of the corresponding tag (see ​ , ​ which is a schematic diagram of the attribute configuration interface proposed in an embodiment of the present disclosure). Thus, the construction of the target document library is completed, and the target document search platform is formed.

[0155] In this embodiment, by obtaining a document to be processed, where the document to be processed has a corresponding document type, and obtaining the tag information corresponding to the document to be processed, and then determining the initial document library corresponding to the document type, it is possible to accurately store the tag information and the document to be processed with the corresponding document type into the initial document library of the corresponding document type, so that the corresponding document type of the formed target document library can be adapted to the document type of the document to be processed, thereby effectively improving the construction effect of the target document library. Therefore, when forming a target document search platform based on the target document library, the constructed document search platform can effectively meet the document search requirements of different business scenarios.

[0156] ​ It is a schematic flowchart of a document search method proposed in an embodiment of the present disclosure.

[0157] In this embodiment, the document search method is exemplified by being configured in a document search device. In this embodiment, the document search method can be configured in a document search device, and the document search device can be set in a server or can also be set in an electronic device. The embodiments of the present disclosure do not limit this.

[0158] See ​ , the document search method includes:

[0159] S901: Receive a document search request.

[0160] In this embodiment, the meanings and descriptions of the same terms as those in the above embodiment can be specifically referred to in the above embodiment and will not be repeated here.

[0161] Among them, a request made by a user-side electronic device for triggering document search in a document search platform can be referred to as a document search request.

[0162] In the embodiments of the present disclosure, receiving a document search request can be that the target document search platform provides a corresponding data transmission interface in advance, and receives the document search request made by the user-side device via the data transmission interface, and this is not limited.

[0163] Or, receiving a document search request can also be that a corresponding monitoring device is preset in the target document search platform, and the user-side device is monitored via the monitoring device, and when it is monitored that the user-side device generates a corresponding document search request, the document search request is received, and this is not limited.

[0164] S902: Parse the required document type and required tag information from the document search request.

[0165] In the embodiments of the present disclosure, after receiving the document search request, the required document type and required tag information can be parsed from the document search request.

[0166] Among them, when a user conducts a document search, the user may have the document types required for the search. Such document types can be referred to as required document types. The required document search types can be used to represent the document search requirements in the business scenarios where the user is located. For example, when the business scenario where the user is located is a medical business scenario, it can be determined that when the user conducts a document search, the required document type is a medical document type, and there is no limitation in this regard.

[0167] Among them, when a user conducts a document search, the user may have the tag information required for the search. Such tag information can be referred to as required tag information. The required tag information can specifically be, for example, the document name that the user needs to search for, keywords in the document content, etc., and there is no limitation in this regard.

[0168] For example, if the received document search request is: "Investigation on the causes of influenza in children in 2021", then the required document type can be, for example, a medical document type, and the required tag information can be the keyword information in the document search request, such as: "influenza, children, 2021", etc., and there is no limitation in this regard.

[0169] In the embodiments of the present disclosure, parsing the required document type and the required tag information from the document search request may be to perform semantic parsing processing on the document search request to obtain the required document type and the required tag information.

[0170] S903: Determine a target document library corresponding to the required document type from multiple document libraries. Among them, the multiple document libraries belong to the document search platform, and the document libraries are used to store documents of corresponding document types.

[0171] In the embodiments of the present disclosure, after receiving a document search request, the document library corresponding to the required document type in the document search request may be determined from multiple document libraries as the target document library.

[0172] In the embodiments of the present disclosure, multiple document libraries in the target document search platform can be used to store the to-be-processed documents of corresponding document types. Determining the target document library corresponding to the required document type from multiple document libraries may be to first determine multiple document types corresponding to the multiple document libraries respectively, and after determining the required document type, compare the required document type with the previously determined multiple document types, and when the required document type is the same as the document type, use the document library corresponding to this document type as the target document library, and there is no limitation in this regard.

[0173] For example, determining a target document library corresponding to the requirement document type from multiple document libraries may be, for example, when determining that the requirement document type is a medical document type, determining the document library for storing medical documents as the target document library, and then supporting document search in the medical document library, so that the obtained target documents can effectively meet the medical document requirements in the corresponding medical business scenarios.

[0174] In some embodiments, when constructing a target document search platform, it may support labeling multiple document libraries according to the document type. Correspondingly, determining a target document library corresponding to the requirement document type from multiple document libraries may be determining that when the corresponding identifier of the document library is the requirement document type, using this document library as the target document library, and there is no limitation on this.

[0175] In the embodiments of the present disclosure, since the target document library stores the to-be-processed documents adapted to the document type of the business scenario where the user is located, it can support document search from the target document library adapted to the business type of the business scenario where the user is located, so as to effectively narrow the scope of document search based on the target document library, while effectively improving the document search efficiency and enabling the obtained documents to effectively meet the document search requirements of different business scenarios.

[0176] S904: Search for target documents corresponding to the requirement tag information from the target document library.

[0177] In the embodiments of the present disclosure, after determining a target document library corresponding to the requirement document type from multiple document libraries, search for the to-be-processed document corresponding to the requirement tag information from the multiple to-be-processed documents in the target document library as the target document.

[0178] In the embodiments of the present disclosure, the target document library stores tag information associated with the documents. Correspondingly, searching for target documents corresponding to the requirement tag information from the target document library may be to find the tag information that matches the requirement tag information in the target document library, and use the document corresponding to this tag information as the target document.

[0179] For example, if the requirement tag information is: "2021, influenza, children", it may be to check whether the documents stored in the target document library have the document tag information of: "2021, influenza, children", and when determining that a certain document has the document tag information of: "2021, influenza, children", using this document as the target document, and there is no limitation on this.

[0180] In some embodiments, to search for tag information that matches the requirement tag information in the target document library, a pre-trained information matching model can be used to perform a matching process on the requirement tag information and the tag information. That is, the requirement tag information and the tag information can be input into the pre-trained information matching model, and the information matching model performs a matching process on the requirement tag information and the tag information to obtain a corresponding matching result. When the matching result indicates that the requirement tag information and the tag information match, the document to be processed corresponding to the tag information is used as the target document, and there is no limitation on this.

[0181] Alternatively, to search for tag information that matches the requirement tag information in the target document library, it can also be to determine the matching degree value of the requirement tag information and the tag information, and when the matching degree value is greater than a pre-determined matching degree threshold, the document to be processed corresponding to the tag information is used as the target document, and there is no limitation on this.

[0182] In the embodiments of the present disclosure, the embodiments of the present disclosure can effectively combine RPA and AI to achieve intelligent automation (IA) in the document search process, thereby effectively improving the degree of automation of document search and reducing labor costs.

[0183] In this embodiment, by receiving a document search request, parsing the required document type and requirement tag information from the document search request, and determining the target document library corresponding to the required document type from multiple document libraries, where the multiple document libraries belong to a document search platform and the document library is used to store documents of the corresponding document type, and then searching for the target document corresponding to the requirement tag information from the target document library. Thus, it is possible to support document search in the target document library adapted to the business type of the business scenario where the user is located, thereby effectively narrowing the scope of document search based on the target document library, while effectively improving the document search efficiency and enabling the searched target document to effectively meet the document search requirements of different business scenarios.

[0184] ​ It is a schematic flowchart of a document search method proposed in another embodiment of the present disclosure.

[0185] See ​ , the document search method includes:

[0186] S1001: Receive a document search request.

[0187] S1002: Parse the required document type and requirement tag information from the document search request.

[0188] S1003: Determine a target document library corresponding to the requirement document type from multiple document libraries. Among them, the multiple document libraries belong to a document search platform, and each document library is used to store documents of the corresponding document type.

[0189] For the descriptions of S1001 - S1003, please refer to the above embodiments for details and will not be elaborated here.

[0190] S1004: Invoke the natural language processing (NLP) service in the field of artificial intelligence (AI) to process the requirement attributes, so as to determine a target parent tag from multiple parent tags. Among them, the target parent tag has corresponding target child tags.

[0191] Among them, the parent tags participating in the current document search among the multiple parent tags can be called target parent tags. Correspondingly, the child tags corresponding to the target parent tags can be called target child tags.

[0192] For example, the multiple parent tags and their corresponding child tags can be, for example: "document format - text format, disease - influenza, document update time - April 2021, research object - children, cause of onset - spontaneously caused". The target parent tag can be, for example, the parent tags participating in the current document search, such as: "disease, research object, cause of onset". Correspondingly, the target child tags can be the child tags corresponding to the target parent tags, such as: "children, spontaneously caused, influenza", etc., and there is no limitation on this.

[0193] In the embodiments of the present disclosure, attributes can be used to determine whether the parent tags and the child tags corresponding to the parent tags participate in the document search. Among them, the tags among the parent tags participating in the subsequent document search can be called target parent tags. Correspondingly, the child tags corresponding to the target parent tags can be called target child tags.

[0194] Among them, the attributes for requirements can be called requirement attributes, and these requirement attributes can support the configuration adjustment of the parent tags in the target document library according to the user's document search requirements.

[0195] That is to say, after determining the target document library corresponding to the requirement document type from multiple document libraries in the embodiments of the present disclosure, the natural language processing (NLP) service in the field of artificial intelligence (AI) can be invoked to process the requirement attributes, adjust the attributes corresponding to the parent tags in the target document library, so as to determine whether the parent tags and the child tags corresponding to the parent tags participate in the subsequent document search, use the parent tags participating in the subsequent document search as target parent tags, and use the child tags corresponding to the target parent tags as target child tags. Then, the subsequent document search method can be executed based on the target child tags. For details, please refer to the subsequent embodiments.

[0196] For example, multiple parent tags can be, for example: document format, disease, research time, research object. The documents that the user needs to search for can be specifically, for example, documents with children as the research object. At this time, during the document search process, according to the demand attributes, two tags such as disease and research time can be hidden, so that the two parent tags such as disease and research time and their corresponding child tags do not participate in the subsequent document search, and the parent tags such as document format and research object except the parent tags are used as target parent tags, and the child tags corresponding to the target parent tags are used as target child tags. Thus, based on the demand attributes, the target parent tags that can effectively meet the subsequent document search can be determined from multiple parent tags, thereby further narrowing the tag search scope, and thus during the subsequent document search process, the data volume of tag processing can be effectively reduced, and thus while effectively ensuring the document search effect, the document search efficiency can be effectively improved.

[0197] S1005: Search for target documents from the target document library according to the demand attributes, demand sub-tags, and target sub-tags.

[0198] After determining the target parent tags from multiple parent tags according to the demand attributes in the embodiments of the present disclosure, target documents can be searched from the target document library according to the demand attributes, demand sub-tags, and target sub-tags.

[0199] In some embodiments, searching for target documents from the target document library according to the demand attributes, demand sub-tags, and target sub-tags can be to perform a matching process on the demand sub-tags and the target sub-tags (wherein, the matching process method can be specifically, for example, model matching, feature matching, etc., and there is no limitation on this), to obtain the corresponding matching process result, and further screen the foregoing matching process result according to the demand attributes to obtain the target document, and there is no limitation on this.

[0200] Optionally, in some embodiments, searching for target documents from the target document library according to the demand attributes, demand sub-tags, and target sub-tags can be to call a robotic process automation (RPA) robot to automatically search for documents to be screened from multiple documents according to the demand sub-tags and the target sub-tags.

[0201] That is to say, in the embodiments of the present disclosure, it is possible to support determining multiple documents to be screened from multiple documents in the target document library according to the demand sub-tags and the target sub-tags, and then, it is possible to support further screening the multiple documents to be screened according to the demand attributes to obtain the target document.

[0202] In some embodiments, searching for target documents from a target document library according to a requirement sub-tag and a target sub-tag may involve performing a matching process on the requirement sub-tag and the target sub-tag, and when the requirement sub-tag and the target sub-tag match, taking the document corresponding to the target sub-tag in the target document library as a document to be screened, and there is no limitation on this.

[0203] Alternatively, searching for multiple documents to be screened from a target document library according to a requirement sub-tag and a target sub-tag may also involve searching in the target document library for the target sub-tag that is the same as the requirement sub-tag, and when the requirement sub-tag and the target sub-tag are the same, taking the document corresponding to the target sub-tag in the target document library as a document to be screened, and there is no limitation on this.

[0204] Optionally, in some embodiments, searching for multiple documents to be screened from a target document library according to a requirement sub-tag and a target sub-tag may involve determining the similarity value between the requirement sub-tag and the target sub-tag of each document, and when the similarity value meets a set condition, taking the document corresponding to the corresponding target sub-tag as a document to be screened.

[0205] Among them, the similarity value can be used to represent the similarity degree between the requirement sub-tag and the target sub-tag. The larger the similarity value, the more it can represent that the requirement sub-tag and the target sub-tag are closer to being the same. On the contrary, the smaller the similarity value, the more it can represent that the gap between the requirement sub-tag and the target sub-tag is larger, and there is no limitation on this.

[0206] That is to say, in the embodiments of the present disclosure, it may involve determining the Euclidean distance between the requirement sub-tag and the target sub-tag, taking this Euclidean distance as the similarity value between the requirement sub-tag and the target sub-tag, comparing the similarity value with a preset set condition (wherein, this set condition can be adaptively configured in combination with the document search requirements in the actual business scenario, and there is no limitation on this), and when the similarity value meets the set condition, taking the document corresponding to the corresponding target sub-tag as a document to be screened.

[0207] In the embodiments of the present disclosure, the multiple documents to be screened obtained by searching from a target document library according to a requirement sub-tag and a target sub-tag can be sorted according to the magnitude of their corresponding similarity values. At this time, the target document can be screened from the multiple documents to be screened according to the requirement attributes.

[0208] It can be understood that in the embodiments of the present disclosure, the documents in the target document library can have multiple target sub-tags, and there may be a situation where some target sub-tags of multiple documents to be processed overlap. In this case, when performing a matching search for target documents based on the requirement sub-tag, there may be a situation where the number of documents obtained by the search is multiple. At this time, the multiple documents to be screened obtained by the foregoing search can be further configured and screened according to the requirement attributes to determine the target document from the multiple documents to be screened, and there is no limitation on this.

[0209] For example, in the embodiments of the present disclosure, the document search method described in the embodiments of the present disclosure can be specifically illustrated in combination with specific schematic diagrams. In the initial stage of the document search method, the document search platform can receive a document search request, and then, according to the demand attributes in the document search request, in the document attribute editing interface of the target document library (see ​ , ​ which is a schematic diagram of the document attribute editing interface proposed in an embodiment of the present disclosure), edit the attributes of the tags in the target document library, so as to determine the target parent tag and the target sub-tag from the parent tags in the target document library to participate in the document search to obtain the corresponding target document.

[0210] Then, the demand sub-tags in the document search request can be entered into the document search interface of the target document search platform (see ​ , ​ which is a schematic diagram of the document search interface proposed in an embodiment of the present disclosure). The target document search platform can search for the target document according to the similarity value between the demand sub-tags and the target sub-tags, and present one or more documents to be screened obtained by the search in the document search interface in the order of the similarity value from large to small. It can also support entering the document screening interface through the screening configuration item of the document search interface as shown in ​ (see ​ , ​ which is a schematic diagram of the document screening interface proposed in an embodiment of the present disclosure), and configure the screening conditions for the parent tags of the documents to be screened according to the demand attributes, so as to screen out the target document from multiple documents to be screened.

[0211] In this embodiment, by receiving the document search request, parsing the demand document type and demand tag information from the document search request, and determining the target document library corresponding to the demand document type from multiple document libraries, where the multiple document libraries belong to the document search platform and are used to store the documents to be processed of the corresponding document types, and determining the target document library corresponding to the demand document type from multiple document libraries, where the multiple document libraries belong to the document search platform and are used to store the documents of the corresponding document types, and then, according to the demand attributes, determining the target parent tag from multiple parent tags, where the target parent tag has a corresponding target sub-tag, and searching for the target document from the target document library according to the demand attributes, demand sub-tags, and target sub-tags. Thus, based on the demand attributes, the target parent tag that can effectively meet the subsequent document search can be determined from multiple parent tags, thereby further narrowing the tag search range, and thus, in the subsequent document search process, the data volume of tag processing can be effectively reduced, and thus, while effectively ensuring the document search effect, the document search efficiency can be effectively improved.

[0212] ​ It is a schematic structural diagram of a device for constructing a document search platform proposed in an embodiment of the present disclosure.

[0213] Refer to ​ , the device 140 for constructing a document search platform includes: a first acquisition module 1401 for acquiring a document to be processed, where the document to be processed has a corresponding document type; a second acquisition module 1402 for acquiring tag information corresponding to the document to be processed; a construction module 1403 for constructing a target document library corresponding to the document type according to the tag information and the document to be processed; and a formation module 1404 for forming a target document search platform according to the target document library.

[0214] Optionally, in some embodiments, refer to ​ , ​ It is a schematic structural diagram of a device for constructing a document search platform proposed in another embodiment of the present disclosure, where the second acquisition module 1402 includes: a first determination sub-module 14021 for determining a parent tag corresponding to the document to be processed; a parsing sub-module 14022 for parsing a sub-tag corresponding to the parent tag from the document to be processed; and a processing sub-module 14023 for using the parent tag and the sub-tag together as tag information.

[0215] Optionally, in some embodiments, the parsing sub-module 14022 is further configured to: call a natural language processing (NLP) service in the field of artificial intelligence (AI) to identify a document general index corresponding to the parent tag from the document to be processed, and use the document general index as the sub-tag; and / or call the NLP service to identify an associated entity value corresponding to the parent tag from the document to be processed, and use the associated entity value as the sub-tag.

[0216] Optionally, in some embodiments, the construction module 1403 includes: a second determination sub-module 14031 for calling a robotic process automation (RPA) robot to determine an initial document library corresponding to the document type; a storage sub-module 14032 for storing the tag information and the document to be processed in the initial document library to form a target document library.

[0217] Optionally, in some embodiments, the storage sub-module 14032 is further configured to: acquire a target loading type corresponding to the document to be processed; and store the tag information and the document to be processed in the initial document library by using a target document storage method corresponding to the target loading type.

[0218] Optionally, in some embodiments, the storage sub-module 14032 is further configured to: if the target loading type is a document loading type, store the document to be processed and the corresponding document tag information in the target document library; and / or if the target loading type is a link loading type, store the access link corresponding to the document to be processed and the corresponding tag information in the target document library; and / or if the target loading type is a rich text loading type, edit the document to be processed via a rich text editor, and store the editing result and the corresponding tag information in the target document library.

[0219] Optionally, in some embodiments, the second acquisition module 1402 further includes: a configuration sub-module 14024, configured to, after determining the parent tag corresponding to the document to be processed, configure an attribute for the parent tag, and use the configured attribute as tag information, where the attribute is used to identify whether the parent tag participates in document search.

[0220] Optionally, in some embodiments, the method for constructing a document search platform is implemented by using artificial intelligence AI and robotic process automation RPA.

[0221] It should be noted that for the functions and specific implementation principles of the above-mentioned modules in the embodiments of the present disclosure, reference may be made to the above-mentioned method embodiments, and details are not described herein again.

[0222] In this embodiment, by obtaining a document to be processed, where the document to be processed has a corresponding document type, and obtaining the tag information corresponding to the document to be processed, then constructing a target document library corresponding to the document type according to the tag information and the document to be processed, and forming a target document search platform according to the target document library. Since the target document search platform is formed according to the target document library corresponding to the document type, the constructed target document platform can provide document search services of the corresponding document type for different business scenarios based on the target document library of the corresponding document type, thereby effectively improving the reusability of the document search platform and enabling the constructed document search platform to effectively meet the document search requirements of different business scenarios.

[0223] ​ It is a schematic structural diagram of a document search device proposed in an embodiment of the present disclosure.

[0224] See ​, the document search device 160 includes: a receiving module 1601 for receiving a document search request; a parsing module 1602 for parsing the required document type and required tag information from the document search request; a determining module 1603 for determining a target document library corresponding to the required document type from multiple document libraries, where the multiple document libraries belong to a document search platform, and the document library is used to store documents of the corresponding document type; a search module 1604 for searching for a target document corresponding to the required tag information from the target document library.

[0225] Optionally, in some embodiments, refer to ​ , ​ is a schematic structural diagram of a document search device proposed in another embodiment of the present disclosure. The required tag information includes: required attributes and required sub-tags. There are corresponding multiple parent tags in the target document library, and the parent tags have corresponding sub-tags, and the corresponding sub-tags are used to describe documents;

[0226] Among them, the search module 1604 includes: a third determining sub-module 16041 for calling the natural language processing (NLP) service in the field of artificial intelligence (AI) to process the required attributes, so as to determine a target parent tag from multiple parent tags, where the target parent tag has a corresponding target sub-tag; a search sub-module 16042 for searching for a target document from the target document library according to the required attributes, required sub-tags, and target sub-tags.

[0227] Optionally, in some embodiments, the target document library includes: multiple documents; among them, the search sub-module 16042 is further configured to: call a robotic process automation (RPA) robot to search for documents to be screened from the multiple documents according to the required sub-tags and target sub-tags; screen the target document from the multiple documents to be screened according to the required attributes.

[0228] Optionally, in some embodiments, the search sub-module 16042 is further configured to: determine the similarity value between the required sub-tags and the target sub-tags of each document; if the similarity value meets the set conditions, then use the document corresponding to the corresponding target sub-tag as the document to be screened.

[0229] It should be noted that for the functions and specific implementation principles of the above-mentioned modules in the embodiments of the present disclosure, reference may be made to the above-mentioned method embodiments, and details are not described herein again.

[0230] In this embodiment, by receiving a document search request, parsing the requirement document type and requirement tag information from the document search request, and determining a target document library corresponding to the requirement document type from multiple document libraries, where the multiple document libraries belong to a document search platform and each document library is used to store documents of a corresponding document type, and then searching for a target document corresponding to the requirement tag information from the target document library. Thus, it is possible to support document search in a target document library adapted to the business type of the business scenario where the user is located, so as to effectively narrow the scope of document search based on the target document library, effectively improve the document search efficiency while enabling the searched target document to effectively meet the document search requirements of different business scenarios.

[0231] To implement the above embodiment, the present disclosure also provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method for constructing a document search platform proposed in the foregoing embodiment of the present disclosure, or implements the document search method proposed in the foregoing embodiment of the present disclosure.

[0232] ​ It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. As ​ shown, the electronic device 180 includes: a memory 1810 and a processor 1820, and a computer program executable on the processor 1820 is stored in the memory 1810. When the processor 1820 executes the computer program, it implements the method for constructing a document search platform in the above embodiment, or implements the document search method in the above embodiment. The number of the memory 1810 and the processor 1820 can be one or more.

[0233] The electronic device further includes: a communication interface 1830, configured to communicate with external devices and perform data interaction and transmission. If the memory 1810, the processor 1820, and the communication interface 1830 are implemented independently, the memory 1810, the processor 1820, and the communication interface 1830 can be interconnected through a bus and complete communication with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, ​ only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0234] Optionally, in a specific implementation, if the memory 1810, the processor 1820, and the communication interface 1830 are integrated on a single chip, the memory 1810, the processor 1820, and the communication interface 1830 can communicate with each other through an internal interface.

[0235] The present disclosure also provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the method for constructing a document search platform as proposed in the foregoing embodiments of the present disclosure, or implements the document search method in the above embodiments.

[0236] The present disclosure also provides a computer program product, which when the instruction processor in the computer program product executes, implements the method for constructing a document search platform as proposed in the foregoing embodiments of the present disclosure, or implements the document search method in the above embodiments.

[0237] It should be understood that the above processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced risc machines (ARM) architecture.

[0238] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), and direct access random access memory (DR RAM).

[0239] In addition, in each embodiment of the present disclosure, each functional unit may be integrated in a processing module, or each unit may exist physically alone, or two or more units may be integrated in a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, or an optical disc, etc.

[0240] As described above, the above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various changes or substitutions, and these should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for constructing a document search platform, characterized in that, Including: Obtain a document to be processed, where the document to be processed has a corresponding document type; Obtain label information corresponding to the document to be processed; Construct a target document library corresponding to the document type according to the label information and the document to be processed; and Form a target document search platform according to the target document library; Wherein, the method further includes: Receive a document search request; Parse a required document type and required label information from the document search request; Determine a target document library corresponding to the required document type from multiple document libraries, where the multiple document libraries belong to the document search platform, and the document libraries are used to store documents of corresponding document types; Search for a target document corresponding to the required label information from the target document library; The required label information includes: a required attribute and required sub - labels. There are corresponding multiple parent labels in the target document library, and the parent labels have corresponding sub - labels, and the corresponding sub - labels are used to describe the documents; Wherein, the searching for a target document corresponding to the required label information from the target document library includes: Call a natural language processing (NLP) service in the field of artificial intelligence (AI) to process the required attribute, so as to determine a target parent label from the multiple parent labels, where the target parent label has corresponding target sub - labels; Search for the target document from the target document library according to the required attribute, the required sub - labels, and the target sub - labels.

2. The method according to claim 1, wherein The obtaining of the label information corresponding to the document to be processed includes: Determine a parent label corresponding to the document to be processed; Parse sub - labels corresponding to the parent label from the document to be processed; and Use the parent label and the sub - labels together as the label information.

3. The method according to claim 2, characterized in that The parsing of the sub - labels corresponding to the parent label from the document to be processed includes: Call a natural language processing (NLP) service in the field of artificial intelligence (AI) to identify a document general index corresponding to the parent label from the document to be processed, and use the document general index as the sub - label; and / or Call the NLP service to identify an associated entity value corresponding to the parent label from the document to be processed, and use the associated entity value as the sub - label.

4. The method according to claim 1, characterized in that The constructing of the target document library corresponding to the document type according to the label information and the document to be processed includes: Call a robotic process automation (RPA) robot to determine an initial document library corresponding to the document type; Store the label information and the document to be processed into the initial document library to form the target document library.

5. The method according to claim 4, wherein The storing of the label information and the document to be processed into the initial document library includes: Obtain a target loading type corresponding to the document to be processed; Use a target document storage method corresponding to the target loading type to store the label information and the document to be processed into the initial document library.

6. The method according to claim 5, wherein The using of the target document storage method corresponding to the target loading type to store the label information and the document to be processed into the initial document library includes: If the target loading type is a document loading type, store the to-be-processed document and the corresponding document tag information in the target document library; and / or If the target loading type is a link loading type, store the access link corresponding to the to-be-processed document and the corresponding tag information in the target document library; and / or If the target loading type is a rich text loading type, edit the to-be-processed document via a rich text editor, and store the editing result and the corresponding tag information in the target document library.

7. The method according to claim 2, wherein After determining the parent tag corresponding to the to-be-processed document, it further includes:[[]] Configure an attribute for the parent tag, and use the configured attribute as the tag information, where the attribute is used to identify whether the parent tag participates in document search.

8. A document search method applied to a document search platform, where the document search platform is constructed by the method for constructing a document search platform according to any one of the above claims 1-7, and is characterized in that The method includes:[[]] Receive a document search request; Parse the required document type and required tag information from the document search request; Determine a target document library corresponding to the required document type from multiple document libraries, where the multiple document libraries belong to the document search platform, and the document library is used to store documents of the corresponding document type; Search for a target document corresponding to the required tag information from the target document library; The required tag information includes: a required attribute and required sub-tags. There are multiple corresponding parent tags in the target document library, and the parent tag has corresponding sub-tags, and the corresponding sub-tags are used to describe the document; Among them, the searching for a target document corresponding to the required tag information from the target document library includes:[[]] Call the natural language processing NLP service in the field of artificial intelligence AI to process the required attribute, so as to determine a target parent tag from the multiple parent tags, where the target parent tag has corresponding target sub-tags; Search for the target document from the target document library according to the required attribute, the required sub-tags, and the target sub-tags.

9. The method according to claim 8, wherein The target document library includes: multiple of the documents; Among them, the searching for the target document from the target document library according to the required attribute, the required sub-tags, and the target sub-tags includes:[[]] Call a robotic process automation RPA robot to search for documents to be screened from multiple of the documents according to the required sub-tags and the target sub-tags; Screen the target document from multiple of the documents to be screened according to the required attribute.

10. The method according to claim 9, characterized in that, Among them, The searching for documents to be screened from multiple of the documents according to the required sub-tags and the target sub-tags includes:[[]] Determine the similarity value between the required sub-tags and the target sub-tags of each of the documents; If the similarity value meets the set conditions, use the document corresponding to the corresponding target sub-tags as the document to be screened.

11. An apparatus for constructing a document search platform, characterized in that, It includes:[[]] A first acquisition module, configured to acquire a to-be-processed document, where the to-be-processed document has a corresponding document type; A second acquisition module, configured to acquire tag information corresponding to the document to be processed; A construction module, configured to construct a target document library corresponding to the document type according to the tag information and the document to be processed; and A formation module, configured to form a target document search platform according to the target document library; Wherein, it further includes: Receiving a document search request; Parsing a required document type and required tag information from the document search request; Determining a target document library corresponding to the required document type from multiple document libraries, wherein the multiple document libraries belong to the document search platform, and the document libraries are used to store documents of corresponding document types; Searching for a target document corresponding to the required tag information from the target document library; The required tag information includes: a required attribute and required sub-tags, the target document library has corresponding multiple parent tags, and the parent tags have corresponding sub-tags, and the corresponding sub-tags are used to describe the document; Wherein, the searching for a target document corresponding to the required tag information from the target document library includes: Invoking a natural language processing (NLP) service in the field of artificial intelligence (AI) to process the required attribute, so as to determine a target parent tag from the multiple parent tags, wherein the target parent tag has corresponding target sub-tags; Searching for the target document from the target document library according to the required attribute, the required sub-tags, and the target sub-tags.

12. A document search device, characterized in that, Applied to a document search platform, the document search platform is constructed by the document search platform construction device described in claim 11 above; Wherein, the device includes: A receiving module, configured to receive a document search request; A parsing module, configured to parse a required document type and required tag information from the document search request; A determining module, configured to determine a target document library corresponding to the required document type from multiple document libraries, wherein the multiple document libraries belong to the document search platform, and the document libraries are used to store documents of corresponding document types; A searching module, configured to search for a target document corresponding to the required tag information from the target document library; The required tag information includes: a required attribute and required sub-tags, the target document library has corresponding multiple parent tags, and the parent tags have corresponding sub-tags, and the corresponding sub-tags are used to describe the document; Wherein, the searching for a target document corresponding to the required tag information from the target document library includes: Invoking a natural language processing (NLP) service in the field of artificial intelligence (AI) to process the required attribute, so as to determine a target parent tag from the multiple parent tags, wherein the target parent tag has corresponding target sub-tags; Searching for the target document from the target document library according to the required attribute, the required sub-tags, and the target sub-tags.

13. An electronic device, characterized in that, It includes: A processor and a memory, wherein instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the document search platform construction method described in any one of claims 1 to 7, or to implement the document search method described in any one of claims 8 to 10.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the method for constructing a document search platform as described in any one of claims 1-7, or implements the document search method as described in any one of claims 8 to 10.

Images