CN115062138A

CN115062138A - Information processing method and device

Info

Publication number: CN115062138A
Application number: CN202210689853.5A
Authority: CN
Inventors: 毛璐; 李长亮
Original assignee: Beijing Kingsoft Digital Entertainment Co Ltd
Current assignee: Beijing Kingsoft Digital Entertainment Co Ltd
Priority date: 2022-06-17
Filing date: 2022-06-17
Publication date: 2022-09-16

Abstract

The application provides an information processing method and an information processing device, wherein the information processing method comprises the following steps: acquiring a project text corresponding to a target project, wherein the project text contains target object information; searching a preset topological structure corresponding to the target project, wherein the preset topological structure is constructed based on an incidence relation formed by target objects in the target project; extracting associated object information and associated relation information which have associated relation with the target object from the project text according to the preset topological structure and the target object information; and integrating the target object information, the associated object information and the association relation information based on the preset topological structure to obtain target project information of the target object. The scheme can improve the information integrity.

Description

Information processing method and device

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information processing method. The application also relates to an information processing apparatus, a computing device, and a computer-readable storage medium.

Background

With the development of computer technology, data sources for recording object information become diversified. The object information may be information describing the object itself, information describing a transaction in which the object participates, and the like. The data source may be a web page, an electronic document, an electronic book, and the like.

In the related art, in order to increase the richness of object information, it is generally necessary to obtain information from a plurality of data sources. However, information from a plurality of data sources often has the problem of complicated and disordered contents. Therefore, there is a need to provide a more sophisticated solution.

Disclosure of Invention

In view of this, embodiments of the present application provide an information processing method to solve technical defects in the prior art. The embodiment of the application also provides an information processing device, a computing device and a computer readable storage medium.

According to a first aspect of embodiments of the present application, there is provided an information processing method, including:

acquiring a project text corresponding to a target project, wherein the project text contains target object information;

searching a preset topological structure corresponding to the target project, wherein the preset topological structure is constructed based on an incidence relation formed by target objects in the target project;

extracting associated object information and associated relation information which have associated relation with the target object from the project text according to the preset topological structure and the target object information;

and integrating the target object information, the associated object information and the association relation information based on the preset topological structure to obtain target project information of the target object.

Optionally, before searching for the preset topological structure corresponding to the target item, the method further includes:

acquiring a history item text corresponding to the target item, wherein the history item text comprises the target object information;

determining historical associated object information corresponding to a target object in the historical item text, and taking the target object information and the historical associated object information as nodes;

determining the incidence relation between the target object information and the historical incidence object information in the historical item text;

and determining and connecting nodes with incidence relations in the target object information and the historical incidence object information according to the incidence relations, and constructing the preset topological structure.

Optionally, the extracting, according to the preset topological structure and the target object information, associated object information and associated relationship information having an associated relationship with the target object from the project text includes:

identifying a target node corresponding to the target object information from the preset topological structure;

respectively obtaining the relationship type of each incidence relationship formed by the target node and the keywords of each node except the target node in the preset topological structure;

determining an extraction rule corresponding to the relationship type according to the relationship type and the key words of the nodes corresponding to the relationship type;

and extracting associated object information and associated relation information which have associated relation with the target object from the project text by using the extraction rule.

Optionally, the obtaining the relationship type of each association relationship formed by the target node respectively includes:

obtaining the node type of each associated node which has an association relation with the target node;

and searching a relation type corresponding to the obtained node type from the pre-established corresponding relation between the node type and the relation type.

Optionally, the determining, according to the relationship type and the keyword of the node corresponding to the relationship type, the extraction rule corresponding to the relationship type includes:

obtaining an extraction rule template corresponding to the relationship type;

and adjusting the extraction rule template by using the key words of the nodes corresponding to the relationship types to obtain the extraction rules corresponding to the relationship types.

Optionally, the integrating the target object information, the associated object information, and the association relationship information based on the preset topology structure to obtain the target item information of the target object includes:

acquiring a first identifier of a target object to which the target object information belongs, a second identifier of an associated object to which the associated object information belongs, and a third identifier of an associated relationship to which the associated relationship information belongs;

identifying a target node with the first identification, an associated node with the second identification and a connecting line with the third identification from the preset topological structure;

and adding the target object information, the associated object information and the association relation information to the preset topological structure according to the target node, the associated node and the connecting line to obtain target project information of the target object.

Optionally, the integrating, based on the preset topology, the target object information, the associated object information, and the association relationship information to obtain the target item information of the target object further includes:

acquiring an update project text of the target project every preset time;

extracting updating associated object information and updating associated relation information which have an associated relation with a target object from the updating project text;

and updating the target item information of the target object according to the updated associated object information and the updated associated relation information to obtain the updated item information of the target object.

Optionally, after the obtaining of the target item information of the target object, the method further includes:

determining an index to be counted, and extracting statistical data corresponding to the index to be counted from the target project information;

and counting the statistical data and displaying the statistical result in the interactive interface.

Optionally, the statistical result includes: time information; after the target item information of the target object is obtained, the method further includes:

determining an due task corresponding to the time information in the statistical result, and displaying the due task under the time information in a preset format on a reminding interface;

and determining a task to be reminded according to the current time and a preset reminding rule, and outputting deadline reminding information aiming at the task to be reminded.

receiving retrieval information input by a user on a retrieval interface;

matching the retrieval information with the target project information to obtain a matching result;

and displaying the matching result in a search result display area of a search interface based on a preset display mode.

According to a second aspect of embodiments of the present application, there is provided an information processing apparatus including:

the text acquisition module is configured to acquire a project text corresponding to a target project, wherein the project text contains target object information;

the topology obtaining module is configured to search a preset topology structure corresponding to the target project, wherein the preset topology structure is constructed based on an incidence relation formed by target objects in the target project;

the information extraction module is configured to extract associated object information and associated relation information which have an associated relation with the target object from the project text according to the preset topological structure and the target object information;

and the information integration module is configured to integrate the target object information, the associated object information and the association relation information based on the preset topological structure to obtain target project information of the target object.

Optionally, the apparatus further comprises: a build module configured to:

Optionally, the information extraction module is further configured to:

obtaining the node type of each association node which has an association relation with the target node;

Optionally, the information extraction module is further configured to:

obtaining an extraction rule template corresponding to the relationship type;

Optionally, the information integration module is further configured to:

Optionally, the apparatus further comprises: an update module configured to:

acquiring an update project text of the target project every preset time;

Optionally, the apparatus further comprises: a first application module configured to:

Optionally, the statistical result includes: time information; the first application module further configured to:

Optionally, the apparatus further comprises: a second application module configured to:

receiving retrieval information input by a user on a retrieval interface;

According to a third aspect of embodiments herein, there is provided a computing device comprising:

a memory and a processor;

the memory is used for storing computer-executable instructions, and the steps of the information processing method are realized when the processor executes the computer-executable instructions.

According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the information processing method.

According to the scheme provided by the application, the project text corresponding to the target project is obtained, and the project text contains target object information; searching a preset topological structure corresponding to the target item, and extracting associated object information and associated relation information which have an associated relation with the target object from the item text according to the preset topological structure and the target object information; and integrating the target object information, the associated object information and the association relation information based on a preset topological structure to obtain target project information of the target object. The preset topological structure is constructed based on an incidence relation formed by target objects in the target project. Therefore, the preset topology structure includes a rule for determining the target object, the associated object and the association relationship. Therefore, according to the preset topological structure, the associated object and the associated information of the target object can be obtained from the target data source. On the basis, the preset topological structure has the characteristics of clearness and orderliness. Therefore, the target object information, the associated object information and the associated relation information are integrated based on the preset topological structure to obtain the target item information of the target object, and the target object, the associated object and the associated information can be recorded in a clear and ordered form, so that the obtained information of the target object is clear, ordered and more complete. Therefore, the scheme can improve the information acquisition integrity.

Drawings

Fig. 1 is a flowchart of an information processing method according to an embodiment of the present application;

fig. 2 is a flowchart illustrating a process of constructing a preset topology structure in an information processing method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a default topology provided by an embodiment of the present application;

fig. 4 is a flowchart illustrating extraction of associated object information and associated relationship information in an information processing method according to an embodiment of the present application;

fig. 5 is a flowchart illustrating a determination of a relationship type of an association relationship in an information processing method according to an embodiment of the present application;

fig. 6 is a flowchart illustrating a determination process of an extraction rule corresponding to a relationship type in an information processing method according to an embodiment of the present application;

fig. 7 is a flowchart illustrating determination of target item information in an information processing method according to an embodiment of the present application;

fig. 8 is a flowchart illustrating an update of target item information in an information processing method according to an embodiment of the present application;

FIG. 9 is a flowchart illustrating an example of an information processing method applied to an enterprise financial management project according to an embodiment of the present application;

fig. 10 is a flowchart illustrating a statistical method for item information in an information processing method according to an embodiment of the present application;

fig. 11 is an exemplary diagram of a statistical result display scenario applied to an information processing method of an enterprise financial management project according to an embodiment of the present application;

fig. 12 is a flowchart of a method for reminding an expired item in an information processing method according to an embodiment of the present application;

fig. 13 is an exemplary diagram of a prompt message output scenario in an information processing method applied to an enterprise financial management project according to an embodiment of the present application;

fig. 14 is a flowchart illustrating a method for retrieving project information in an information processing method according to an embodiment of the present application;

fig. 15 is an exemplary diagram of a search result display scenario in an information processing method applied to an enterprise financial management project according to an embodiment of the present application;

fig. 16 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application;

fig. 17 is a block diagram of a computing device according to an embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.

The terminology used in the one or more embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the present application. As used in one or more embodiments of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present application refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first aspect may be termed a second aspect, and, similarly, a second aspect may be termed a first aspect, without departing from the scope of one or more embodiments of the present application.

First, the noun terms to which one or more embodiments of the present invention relate are explained.

Structuring the document: the system is composed of a title, a chapter, a paragraph and other logic structures. Also referred to as a "document tree," the backbone is a parent element, such as < my document >, and the branches and pages are child elements, such as < chapter > and < paragraph >.

Robotic Process Automation (RPA): an application program that provides another way to automate the end user's manual process by mimicking the end user's manual process at a computer.

Knowledge Graph (Knowledge Graph): the map is a series of different graphs for displaying the relation between the knowledge development process and the structure, and the knowledge resources and the carriers thereof are described by using the visualization technology, and the knowledge and the interrelation among the knowledge resources, the knowledge construction, the knowledge drawing and the knowledge display are mined, analyzed, constructed, drawn and displayed. The modern theory is that the theory and method of applying mathematics, graphics, information visualization technology, information science and other disciplines are combined with the method of metrology citation analysis, co-occurrence analysis and the like, and the core structure, development history, frontier field and overall knowledge framework of the disciplines are vividly displayed by utilizing a visual map to achieve the aim of multi-discipline fusion. The construction process of the knowledge graph mainly comprises 6 links: knowledge modeling, knowledge storage, knowledge extraction, knowledge fusion, knowledge calculation and knowledge application are structured semantic knowledge bases which are used for rapidly describing contents and mutual relations in a physical world, and a large amount of knowledge is aggregated by reducing data granularity from a file (document) level to a data (data) level, so that rapid response and reasoning of knowledge are realized, and practical and valuable references can be provided for subject research.

It should be noted that when the staff needs to query the bulletin information related to the project, the staff often needs to manually query the bulletin web page of the project at regular time through the web page, and manually extract the related information of the enterprise purchase project, including the project name, the issuer, the product type, the income type, the annual income rate, the purchase amount, the purchase deadline, the start date, the due date, and the like. In addition, in order to better understand the enterprise, basic information of the enterprise, including enterprise full names, enterprise codes, enterprise representatives, concepts affiliated, industries affiliated, territories affiliated, major products, enterprise profiles, and the like, needs to be manually queried. The staff needs to inquire the condition of the due project or set a reminder of the due project.

However, the above method has low working efficiency, and in the process of following up the item information purchased by the enterprise, the staff usually needs to look up a large number of unstructured documents from websites or other channels in a scattered manner, which is time-consuming and labor-consuming.

Secondly, after the project information and the basic information of the enterprise purchased by the enterprise are obtained, errors are prone to occur in the extraction and recording process. Most of the bulletin documents of the item information purchased by the enterprise are unstructured, and the format and the structure of the documents are flexible and changeable and are not fixed. The staff extracts information such as: the method has the advantages that when key structural information such as an entrusting party, an entrusted party, a product type, a product deadline, a predicted yield and the like is obtained, manual searching and manual record arrangement are needed, the whole process is low in efficiency and easy to make mistakes, and the relevance of purchasing project events in a dimension time axis interval of the same enterprise cannot be effectively established.

In addition, after the item information fields purchased by the structured enterprises are acquired, the manual layer cannot perform rapid, comprehensive, accurate and objective analysis on the structured information, and cognitive deviation which is first-in-first and one-sided often exists, so that the speed and quality of business marketing decision are finally influenced.

Moreover, in a scene of searching enterprise project information, traditional engineering software often only supports a keyword and strong matching search mode, and cannot quickly and comprehensively find all information to be searched.

Therefore, the embodiment of the application provides an information processing method, an enterprise project intelligent marketing RPA assistant based on a knowledge graph and a natural language processing technology can automatically complete extraction of semi-structured and unstructured project knowledge, perform knowledge fusion and real-time updating with an existing project graph, realize functions of intelligent question answering, retrieval and the like on the basis of the graph, and assist enterprises in completing efficient management and decision of project behavior information.

In the present application, an information processing method is provided. The present application relates to an information processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

Fig. 1 shows a flowchart of an information processing method according to an embodiment of the present application, which specifically includes the following steps:

s102, acquiring a project text corresponding to the target project, wherein the project text contains target object information.

Specifically, the target item is an item that needs to be managed in an actual application scenario, for example, the target item may be a financial item, a research and development item, a bid item, and the like. The project text refers to a data text related to the target project, the project text may include a project information text acquired by the target object and a basic information text of the target object, and in a scenario where the target project is a financial project, the project text may refer to a financial information text purchased by an enterprise, a basic information text of the enterprise, and the like; in the case where the target project is a development project, the project text may be a development progress information text, a project basic information text, and the like.

In addition, the target object is a main object of the target project, that is, a main object which needs to integrate project information, for example, in a scenario where the target project is a financial project, the target object may be an enterprise, and then, each piece of financial project information of the enterprise may be integrated to obtain corresponding target project information; in a scenario where the target project is a research and development project, the target object may be a research and development department of an enterprise, and then information of each research and development project of the research and development department may be integrated to obtain corresponding target project information. The target object information refers to related information of the target object, for example, the target object information may be information of an identifier, a name, a legal representative, an industry, a region, and the like of the target object, and specific target object information may be set according to an application scenario and a requirement, which is exemplified herein. For example, the target object information may be "XX enterprise", "XX company", "XX department", "enterprise code", "XX representative", "XX industry", and/or "XX territory", and the like.

In a specific application, the manner of obtaining the item text corresponding to the target item may be various. For example, a text containing target object information may be searched from a data source of a text type to obtain an item text corresponding to a target item. Or, for example, data containing target object information may be searched from a data source; if the searched data is of an image type, converting the searched data into text data; if the searched data is of a text type, determining the searched data as text data; if the searched data is of an audio type, converting the searched data into text data; and determining each obtained text data as a project text corresponding to the target project. Any method capable of obtaining the project text corresponding to the target project can be used in the present application, and this embodiment does not limit this.

In addition, the project text corresponding to the target project may be at least one text, and when the project text is multiple, the data content of each project text may be different types of content, for example, in a scenario where the target project is a financial project, the project text may include two types of texts, one type is a financial information text purchased by an enterprise, and the other type is a basic information text of the enterprise, and subsequently, the various types of project texts may be fused to obtain the target project information of the target object, so that a rich data base is provided for obtaining the target project information, thereby improving the data richness and integrity of the obtained target project information.

S104, searching a preset topological structure corresponding to the target project, wherein the preset topological structure is constructed based on an incidence relation formed by target objects in the target project.

Specifically, the "topology" is a method of abstracting an entity into "nodes" irrespective of the size and shape thereof, abstracting lines connecting the entities into "lines", and expressing the association between the nodes and the lines in the form of a graph.

In practical application, the preset topological structure can be a knowledge map, the knowledge map is called a knowledge domain visualization map or a knowledge domain mapping map, and is a series of different graphs for displaying the relation between the knowledge development process and the structure, the knowledge resources and the carriers thereof are described by using a visualization technology, and the knowledge and the interrelation thereof are mined, analyzed, constructed, drawn and displayed. In addition, any preset topological structure constructed based on the incidence relation formed by the target objects in the target project can be used in the present application, and the present embodiment does not limit this.

It should be noted that, because various item texts of the target item of the target object are integrated to obtain corresponding target item information, in order to make the target item information of the target object more orderly, entities and corresponding relationships between the entities in the various item texts of the target item of the target object may be represented by a topological structure. Therefore, a preset topological structure can be constructed in advance based on the incidence relation formed by the target object in the target project, namely, a topological frame is constructed based on the incidence relation formed by the target object, and then specific information in the project text corresponding to the target project is extracted and added to the preset topological structure, so that final target project information is obtained.

In an optional implementation manner of this embodiment, before searching for the preset topological structure corresponding to the target item, the preset topological structure may be further pre-constructed, fig. 2 is a flowchart of a construction process of the preset topological structure in the information processing method according to an embodiment of the present application, and as shown in fig. 2, before searching for the preset topological structure corresponding to the target item, the following steps may be further included:

step S202: and acquiring a history item text corresponding to the target item, wherein the history item text comprises target object information.

Step S204: and determining history associated object information corresponding to the target object in the history item text, and taking the target object information and the history associated object information as nodes.

Step S206: and determining the association relationship between the target object information and the historical associated object information in the historical item text.

Step S208: and determining and connecting nodes with the incidence relation in the target object information and the historical incidence object information according to the incidence relation, and constructing a preset topological structure.

In a specific application, the preset topological structure comprises nodes and connecting lines, and target object information in a target project can be used as an entity, namely, each target object information can be a node in the preset topological structure; the history associated object information is an entity having an association relationship with the target object information, for example, the history associated object information may include at least one of attribute information of the target object, another entity associated with the target object, and attribute information of another entity. The association relationship may be an association relationship between the target object information and the associated object information.

It should be noted that, the target object information and the history associated object information may be used as nodes, and then the nodes having an association relationship in the target object information and the history associated object information are connected to construct the preset topology structure. Therefore, the preset topological structure is constructed based on the incidence relation formed by the target object, the two nodes with the connecting line show that the incidence relation exists, the incidence relation between the target object information and the historical incidence object information in the target item can be simply and orderly shown through the preset topological structure, and various information included in the item text corresponding to the target item can be integrated based on the preset topological structure subsequently.

For example, fig. 3 is a schematic view of a preset topology structure provided in an embodiment of the present application, and as shown in fig. 3, a mode that an enterprise financial knowledge graph can be established according to historical financial information and basic information of an enterprise is described by taking a target item as a financial item as an example. Specifically, three nodes of a consignor (target object information), a trusteeship (historical associated object information) and a financing product (historical associated object information) and three associated relations of entrusting, issuing and purchasing and the like can be extracted around the historical financing announcement information of enterprise purchase to jointly form a purchase event, wherein the consignor, the financing product nodes and the entrusting and purchasing relations have attribute characteristics, the consignor can correspondingly have information such as a true date, registered capital, market date and total stock, the financing product can be divided according to a product type, a profit type and a yield, the consignment relation can correspondingly have announcement time, and the purchasing relation can correspondingly have information such as money amount, term, announcement time and the like. Around the basic information of an enterprise, the entrusting party can be classified into different nodes such as legal representatives, listed exchanges, concepts, industries, regions and the like. The concept represents a set of financial products purchased by enterprises and having common characteristics, and the set of financial products can comprise geographical classification, time-to-market classification, economic hotspot classification and the like.

In the embodiment of the application, historical associated object information corresponding to a target object can be determined based on a historical project text of the target object, the target object information and the historical associated object information are used as nodes, the nodes with the association relation are connected through a connecting line, a preset topological structure is constructed, the association relation between the target object information and the historical associated object information in the target project can be simply and orderly shown through the preset topological structure, various information included in the project text corresponding to the target project can be integrated subsequently based on the preset topological structure, and the ordering of the target project information is improved.

And S106, extracting associated object information and associated relation information which have associated relation with the target object from the project text according to the preset topological structure and the target object information.

Specifically, the associated object information is information of an associated object having an associated relationship with the target object in the project text, and the associated relationship information is a specific relationship existing between the target object and the associated object, for example, if the target object is a client and the associated object is an authorized party, the associated object information is information of the authorized party, and the associated relationship information is an authorized relationship.

It should be noted that after the preset topology is determined, the target object information, the associated object information related to the target object, and the association relationship information between the target object and the associated object may be extracted from the project text, where the target object information and the associated object information are nodes in the preset topology, and the connected nodes indicate that an association relationship exists, and a specific relationship may be extracted from the project text as the association relationship information. The related object information may be related information of an entity having a relationship with the target object, and the related object information may also be attribute feature information of the target object, such as an industry to which the related object information belongs, a region to which the related object information belongs, and the like.

In an optional implementation manner of this embodiment, association object information and association relationship information having an association relationship with a target object may be extracted from a project text based on a relationship type of each association relationship in a preset topology structure. Fig. 4 is a flowchart illustrating an extraction process of associated object information and associated relationship information in an information processing method according to an embodiment of the present application, and as shown in fig. 4, the extracting, from a project text, associated object information and associated relationship information that have an associated relationship with a target object according to a preset topology and target object information may specifically include the following steps:

step S402: and identifying a target node corresponding to the target object information from the preset topological structure.

Step S404: and respectively obtaining the relationship type of each incidence relationship formed by the target node and the keywords of each node except the target node in the preset topological structure.

Step S406: and determining an extraction rule corresponding to the relationship type according to the relationship type and the key words of the nodes corresponding to the relationship type.

Step S408: and extracting associated object information and associated relation information which have associated relation with the target object from the project text by using the extraction rule.

Specifically, the preset topological structure is constructed by taking target object information and associated object information as nodes and connecting the nodes with an associated relationship through connecting lines, wherein the target node is a node corresponding to the target object information in the preset topological structure, and if the target object information is a consignor, the target node is a node in the preset topological structure for representing the consignor.

In addition, nodes connected through connecting lines in the preset topological structure indicate that an association relationship exists, and therefore the relationship type of each association relationship formed by the target node refers to the relationship type of each connecting line of the target node in the preset topological structure.

It should be noted that, the extraction rule corresponding to the relationship type may be determined according to the relationship type of each association relationship formed by the target node and the keyword of the node corresponding to the relationship type, and then, based on the corresponding extraction rule, the association object information and the association relationship information having an association relationship with the target object may be extracted from the project text. Therefore, different relation types and different keywords can correspond to different extraction rules, so that associated object information and associated relation information which are associated with a target object in a project text can be extracted more pertinently, and the accuracy of extracting the associated object information and the associated relation information is high.

In an optional implementation manner of this embodiment, the associated node may be searched first, and then the corresponding relationship type may be determined based on the node type of the associated node. Fig. 5 is a flowchart for determining a relationship type of an association relationship in an information processing method according to an embodiment of the present application, and as shown in fig. 5, the obtaining relationship types of each association relationship formed by a target node respectively may specifically include the following steps:

step S502: and obtaining the node type of each association node which has association relation with the target node.

Step S504: and searching a relation type corresponding to the obtained node type from the pre-established corresponding relation between the node type and the relation type.

Specifically, the associated node is a node having an association relationship with the target node, that is, a node connected to the target node in the preset topology structure.

It should be noted that two nodes connected in the preset topology structure indicate that there is an association relationship, so that a node connected to the target node can be determined from the preset topology structure as an association node. In the embodiment of the application, the corresponding relation between the node type and the relation type can be preset, so that after the node type of each associated node is obtained, the relation type corresponding to the obtained node type can be searched from the corresponding relation between the node type and the relation type which is established in advance, and the relation type of each associated relation formed by the target node is determined.

In an optional implementation manner of this embodiment, the relationship type at least includes: the target object is of a first type formed by action logic in the item and the first object; the relationship types further include at least one of the following types: a second type formed between the target object and the attribute information of the target object, a third type formed by the action logic of the first object, and a fourth type formed between the first object and the attribute information of the first object. Fig. 6 is a flowchart of determining an extraction rule corresponding to a relationship type in an information processing method according to an embodiment of the present application, and as shown in fig. 6, the determining an extraction rule corresponding to a relationship type according to a relationship type and a keyword of a node corresponding to the relationship type may specifically include the following steps:

step S602: and obtaining an extraction rule template corresponding to the relationship type.

Step S604: and adjusting the extraction rule template by using the keywords of the nodes corresponding to the relationship types to obtain the extraction rules corresponding to the relationship types.

Specifically, the action logic means that there is an action relationship between the target object and the first object in the target item, such as purchase and commission, that is, the first type formed by the target object and the first object through the action logic in the item means that there is an action type relationship between the target object and the first object, as shown in fig. 3, the target object is a commission party, the first object may be an authorized party (i.e., a trusted party), and at this time, the action logic is commission; the target object is the principal and the first object may be a financial product, with the action logic being a purchase.

As shown in fig. 3, when the target object is the client, the target object information may be information of the client, a legal representative, a listed exchange, an industry, a region, a concept, and the like, each of the target object information is a node in a preset topology, and the information has an association relationship with each other, and the nodes such as the legal representative, the listed exchange, the industry, the region, the concept, and the like are attribute information of the client (the target object), so that the second type formed between the target object and the attribute information of the target object (i.e., the target object information) indicates that the node corresponding to the target object and the node corresponding to the attribute information of the target object have an associated association relationship, that is, the node corresponding to the attribute information of the target object belongs to the node corresponding to the target object.

Secondly, there may be an action association relationship between the first object and the target object, and there may also be an action association relationship between the first object and other objects (such as other first objects) except the target object, that is, a third type formed by the action logic of the first object means that there is an action association relationship between the first object and other objects except the target object, as shown in fig. 3, the first object is an authorized party (i.e., a trusted party), and there is an issue relationship between the authorized party and the financial product.

Furthermore, the first object may also include multiple types of attribute information, such as legal representatives, industries, regions, and the like, each of the attribute information of the first object may also be a node in a preset topology structure, and the information has a dependent association relationship, so that the fourth type formed between the attribute information of the first object and the first object means that a dependent association relationship exists between the node corresponding to the first object and the node corresponding to the attribute information of the first object, that is, the node corresponding to the attribute information of the first object belongs to the node corresponding to the first object.

The extraction rule template may be a plurality of templates. Illustratively, the input of the extraction rule is text and the output is the corresponding entity. In a possible implementation manner, the extraction rule may be an entity recognition method based on sequence labeling, for example, the extraction rule is an entity recognition model in the natural language processing field, text is input into the entity recognition model, and a corresponding entity may be output, and the entity recognition model may be composed of a BERT model and a CRF model, or the entity recognition model may be further composed of a BERT model, a BiLSTM model and a CRF model, and so on. In another possible implementation manner, the extraction rule may also be a regular expression, and thus, the corresponding extraction rules may be different because the keywords are different, so that the extraction rule template needs to be adjusted by using the keywords of the nodes corresponding to the relationship types to obtain the extraction rules corresponding to the relationship types.

For example, for the entity identification method based on sequence labeling, a keyword may be used as labeling data, and a sample text containing the keyword is used for training to obtain an extraction rule (i.e., an entity identification model). For the regular expression, the keywords in the expression can be replaced by the keywords of the nodes corresponding to the relationship types, so as to obtain the extraction rule corresponding to the relationship types.

In the embodiment of the application, a method for automatically extracting key information is provided for unstructured enterprise purchase financing information documents acquired from the whole network, meanwhile, the custom configuration of business fields can be supported through a background system configuration module on the later engineering design level, different extraction rules can be configured for different relation types, and subsequently, the extraction rules corresponding to different relation types can be determined, so that more accurate information extraction is performed.

And S108, integrating the target object information, the associated object information and the associated relation information based on a preset topological structure to obtain target project information of the target object.

In a specific application, the target object information, the associated object information, and the association relationship information are integrated based on the preset topology structure, and various ways of obtaining the target item information of the target object are available. For example, the target object information, the associated object information, and the association relationship information may be added to corresponding nodes in the preset topology structure to obtain target item information of the target object. Or, for example, the target object information, the associated object information, and the association relationship information may be recorded correspondingly according to a preset topology structure to obtain a correspondence table as target item information of the target object. The first example is described in detail below in the form of alternative embodiments for ease of understanding and reasonable layout.

In an optional implementation manner of this embodiment, an example is described in which the target object information, the associated object information, and the association relationship information are added to corresponding nodes in the preset topology structure to obtain target item information of the target object, that is, the obtained target item information of the target object is in a form of a knowledge graph. Fig. 7 is a flowchart for determining target item information in an information processing method according to an embodiment of the present application, and as shown in fig. 7, the target item information of a target object is obtained by integrating target object information, associated object information, and association relation information based on a preset topology structure, where the method specifically includes the following steps:

step S702: and acquiring a first identifier of a target object to which the target object information belongs, a second identifier of an associated object to which the associated object information belongs, and a third identifier of an associated relation to which the associated relation information belongs.

Step S704: and identifying a target node with a first identification, an associated node with a second identification and a connecting line with a third identification from the preset topological structure.

Step S706: and adding the target object information, the associated object information and the association relation information to a preset topological structure according to the target node, the associated node and the connecting line to obtain target project information of the target object.

Specifically, the target object information is information related to the target object, the first identifier is an identifier of the target object to which the target object information belongs, and the target object can be found from the preset topological structure based on the first identifier. In addition, the associated object information is information of an associated object related to the target object, the second identifier is an identifier of the associated object to which the associated object information belongs, and the associated object can be found from the preset topological structure based on the second identifier. Furthermore, two nodes in the preset topological structure are connected through a connecting line, which indicates that an association relationship exists between the two nodes, and the association relationship information refers to a specific relationship between the nodes, so that the third identifier refers to an identifier of the association relationship to which the association relationship information belongs, and the corresponding connecting line can be found from the preset topological structure based on the third identifier.

It should be noted that after the first identifier of the target object to which the target object information belongs, the second identifier of the associated object to which the associated object information belongs, and the third identifier of the associated relationship to which the associated relationship information belongs are obtained, the target node having the first identifier, the associated node having the second identifier, and the connection line having the third identifier may be identified from the preset topology, then the target object information may be added to the target object, the associated object information is added to the associated object, and the associated relationship information is added to the corresponding connection line, so as to obtain the target item information of the target object.

Following the above example, the model of the enterprise finance knowledge map is determined as an example, wherein the enterprise purchase finance bulletin data is unstructured data, and the enterprise basic information is semi-structured data. And carrying out knowledge fusion such as alignment, combination and the like on knowledge from different sources to form globally unified knowledge identification and association. In the embodiment of the application, the enterprise financial knowledge extracted from the unstructured data and the enterprise basic information extracted from the semi-structured data can be fused through enterprise entities, the information of the affiliated concept, the affiliated industry, the area and the like of the enterprise is fused into the knowledge graph, and the application value of purchasing the financial knowledge graph of the enterprise is improved.

According to the scheme, the preset topological structure is constructed based on the incidence relation formed by the target objects in the target project. Therefore, the preset topology structure includes a rule for determining the target object, the associated object and the association relationship. Therefore, according to the preset topological structure, the associated object and the associated information of the target object can be obtained from the target data source. On the basis, the preset topological structure has the characteristics of clearness and orderliness. Therefore, the target object information, the associated object information and the associated relation information are integrated based on the preset topological structure to obtain the target item information of the target object, and the target object, the associated object and the associated information can be recorded in a clear and ordered form, so that the obtained information of the target object is clear, ordered and more complete. Therefore, the scheme can improve the information acquisition integrity.

In an optional implementation manner of this embodiment, in order to ensure timeliness of the target item information, an update item text of the target item may be obtained at regular time afterwards, and the target item information of the target object is updated. Fig. 8 is a flowchart of updating target item information in an information processing method according to an embodiment of the present application, and as shown in fig. 8, after target item information of a target object is obtained by integrating target object information, associated object information, and association relation information based on a preset topology structure, the method may further include the following steps:

step S802: and acquiring an updated project text of the target project at intervals of preset duration.

Step S804: and extracting the updated associated object information and the updated associated relation information which have the associated relation with the target object from the updated project text.

Step S806: and updating the target item information of the target object according to the updated associated object information and the updated associated relation information to obtain the updated item information of the target object.

Specifically, the preset time period is a preset time period, and represents a time interval for updating the target item information of the target object, such as 7 days, 15 days, one month, and the like. The updated project text refers to updated data text related to the target project, such as updated enterprise purchase financing information and the like.

It should be noted that, a specific implementation process of extracting, from the update project text, the update associated object information and the update associated relationship information that have an associated relationship with the target object is similar to the above specific implementation process of extracting, from the update project text, the associated object information and the associated relationship information that have an associated relationship with the target object, and is not described herein again.

In practical application, according to the updated associated object information and the updated associated relationship information, the target item information of the target object is updated, and when the updated item information is obtained, if the target item information is in a knowledge graph form, the updated associated object information and the updated associated relationship information can be added to corresponding nodes in the target item information to obtain the updated item information of the target object; if the target item information is the corresponding relation table, the updated associated object information and the updated associated relation information may be added to corresponding positions in the corresponding relation table to obtain updated item information of the target object.

In the embodiment of the application, the updated project text of the target project can be obtained at regular time, effective project information is extracted from the updated project text, and the newly added project information is updated to the target project information of the target object through entity alignment and combination, so that the scale, the real-time performance and the effectiveness of the target project information of the target object are ensured.

Fig. 9 is a processing flow diagram of an information processing method applied to an enterprise financing project according to an embodiment of the present application, and as shown in fig. 9, the overall architecture of the present solution mainly includes two parts, namely, construction and application of an enterprise financing knowledge graph: (1) constructing an enterprise financing knowledge map; (2) and (4) applying enterprise financing knowledge maps. The construction of the enterprise financing knowledge graph is equivalent to the process of obtaining the target project information, and comprises the steps of carrying out knowledge modeling based on unstructured data 'enterprise purchase financing information' and semi-structured data 'enterprise basic information', carrying out knowledge extraction and mining on the unstructured data 'enterprise purchase financing information' based on the knowledge modeling, then carrying out knowledge fusion, and constructing the knowledge graph. The application of the enterprise financial knowledge map may specifically include performing at least one of index statistics (i.e., an insight assistant), reminding display (i.e., a reminding assistant), and retrieval (i.e., a retrieval assistant) based on the enterprise financial knowledge map. For ease of understanding and proper layout, the second case (the enterprise financing knowledge-graph application) is described in detail below in the form of an alternative embodiment.

According to the embodiment, the target object information, the associated object information and the association relation information are added to the preset topological structure, so that the structural effect and the visual effect of the target project information can be improved. Compared with the method for sorting the target project information through the relational data table, the ordering of the target project information and the convenience of application can be further improved.

In an optional implementation manner of this embodiment, after the target item information of the target object is obtained, a statistical function of the item information may also be provided. Fig. 10 is a flowchart of a statistical method for item information in an information processing method according to an embodiment of the present application, and as shown in fig. 10, after obtaining target item information of a target object, the method may further include the following steps:

step S1002: and determining the indexes to be counted, and extracting statistical data corresponding to the indexes to be counted from the target project information.

Step S1004: and counting the statistical data, and displaying the statistical result in the interactive interface.

Specifically, the target project information is constructed and obtained based on the project text of the target project, so that the target project information includes multiple dimensions of data related to the target project, such as enterprise, industry, concept, due time, and the like, and the target index to be counted refers to a data dimension that needs to be counted, for example, the target index may refer to project information due within 30 days.

In addition, the interactive interface is an interface providing a statistical function of the project information, and the interactive interface can receive a retrieval request of a user and can also display a corresponding statistical result to the user.

In practical application, the to-be-counted index may be an index corresponding to a statistical result to be displayed in the interactive interface, for example, the interactive interface includes an expiration data statistical area of an enterprise financial purchase event, and the to-be-counted index corresponding to the expiration data statistical area may be item information expired within 30 days. In addition, the index to be counted may also be an index carried in a query request triggered by a user, and if the user wants to query the project information of the "XX enterprise", the "XX enterprise" may be input in the retrieval area of the interactive interface for retrieval, where the index to be counted is the project information corresponding to the "XX enterprise".

It should be noted that after the indexes to be counted are determined, the statistical data corresponding to the indexes to be counted can be extracted from the target project information, then the statistical data is counted, and the statistical result is displayed in the interactive interface. Specifically, the statistical data are counted, and the statistical results are displayed in the interactive interface, which may be displayed as the statistical results by determining the number, proportion, and the like of the statistical data, or may be displayed in the interactive interface in sequence by arranging the statistical data as the statistical results.

Fig. 11 is an exemplary diagram of a statistical result display scenario in an information processing method applied to an enterprise financial project according to an embodiment of the present application, where, as shown in fig. 11, an interactive interface is a data statistics large screen, and an interface partition includes an enterprise purchase financial event expiration data statistics area, an enterprise purchase financial expiration information list area, and an intelligent analysis area based on a financial information map (which may support intelligent analysis in 3 dimensions of enterprise, industry, and concept).

A data statistics area: the statistical data viewing of a visual layer is supported, and the function switching of regions, industries, concepts, time and product types is supported, for example: according to the actual business needs of the user, the regions can be selected: a, industry: manufacturing, concept: winning summary, expiration time: and in the last 30 days, the data statistics such as the number of enterprises, the product type proportion and the like under the selected condition group are checked in real time.

Information list area: the method supports the list viewing of all the structured purchasing financing information data extracted based on the data source, and key field information of consignor, consignee, product name, money amount, term, product type, expected profitability, income type, product origin date, product due date and the like of the financing product to be due is clear at a glance.

An intelligent analysis area: the method supports intelligent analysis of enterprise, industry and concept dimensions, and supports entity retrieval based on a financing information map, such as: clicking a tab (enterprise analysis), inputting an XX enterprise, and executing retrieval, wherein all structured basic information of the current retrieval enterprise and time axis information of the current enterprise purchasing financing product events in the past can be displayed in the interface area on the right side, so that the user of the product can master the target comprehensively and in multiple dimensions to follow up the overall situation and purchasing behavior of the enterprise conveniently.

In the embodiment of the application, a knowledge graph of the enterprise purchasing and financing products is constructed aiming at the extracted key information of the enterprise purchasing and financing and a knowledge base covering the enterprise and industry information, and based on the knowledge graph and natural language processing technology, full-scene and multi-dimensional intelligent analysis such as time behavior sequence analysis of the enterprise purchasing and financing products, ranking analysis of inter-industry enterprise financing investment sum, analysis of intra-industry enterprise investment preference for different product types financing products, ranking analysis of inter-concept enterprise financing investment sum, analysis of intra-concept enterprise investment preference for different product types financing products, and the like is provided.

In an optional implementation manner of this embodiment, after the target item information of the target object is obtained, the due item may be reminded based on the target item information of the target object. Fig. 12 is a flowchart of a method for reminding an expired item in an information processing method according to an embodiment of the present application, where as shown in fig. 12, a statistical result includes: the time information, after obtaining the target item information of the target object, may further include the following steps:

step 1202: and determining an due task corresponding to the time information in the statistical result, and displaying the due task under the time information in a preset format on a reminding interface.

Step 1204: and determining the task to be reminded according to the current time and a preset reminding rule, and outputting deadline prompt information aiming at the task to be reminded.

Specifically, the time information is an expiration time of the project, the time information may be in units of days, that is, the time information is a date. The expired task refers to a task which expires at the time information, that is, a task which needs to be processed before the corresponding expiration time.

In addition, the reminding interface refers to an interface for displaying the tasks due under each time information, and the reminding interface can be triggered and displayed by a user. The preset format refers to a preset format for displaying the due tasks under each time information, for example, the preset format may be a schedule format or a list format.

In practical application, besides the due tasks under the time information are displayed in a preset format on the reminding interface, the brief information of the due tasks can be displayed, and the brief information of the due tasks can comprise brief information of the name, the amount and the like of the due tasks.

In addition, after the reminding interface displays the due tasks under the time information in a preset format, the displayed due tasks can also provide a skip function, namely, after a user clicks a certain due task, the user can skip to a detailed content interface corresponding to the due task so as to allow the user to view the detailed content of the due task, and thus the due task is processed.

It should be noted that each task in the target project generally has a deadline requirement and needs to be processed before due, so that due tasks corresponding to each time information in the target project information can be counted, and due tasks under the time information are displayed in a preset format, so that a user can know the due time of each task at a glance, and thus, the processing is performed in time.

In addition, the preset reminding rule may be a preset rule for reminding due tasks, and the preset reminding rule includes reminding time, reminding mode and the like, for example, the preset reminding rule may show the reminding information through the prompt box 3 days before due, and the preset reminding rule may also show the reminding information through the prompt box 1 day before due.

In practical application, the task to be reminded which needs to be reminded at present can be determined according to the current time and the preset reminding rule, and then the deadline prompting information for the task to be reminded is output in the reminding mode defined in the preset reminding rule.

Exemplarily, fig. 13 is an exemplary diagram of a prompt information output scene in an information processing method applied to an enterprise financing project according to an embodiment of the present application, and as shown in fig. 13, a reminding interface displays financing due events corresponding to date grids in a calendar form, for example, a 4-month 9-day due task 1 exists, a 4-month 14-day due task 2 exists, and a 4-month 28-day due task 3 exists, and simultaneously supports a setting center under the reminding interface to perform custom setting of preference behaviors such as reminding time and the like.

During specific implementation, a user can directly click a reminding button to anchor and jump to a corresponding pane area of a schedule after checking the information of the financing expiration and follow-up intention following of a target enterprise in an interactive interface; the user can also set the reminding time to be three days before expiration, and then the system can execute the timed message pushing according to the reminding condition set by the user so as to realize the instant follow-up of the target enterprise and maximize the ductility and smoothness of the business process through the product.

In an optional implementation manner of this embodiment, after obtaining the target item information of the target object, a function of retrieving the item information may also be provided. Fig. 14 is a flowchart of a method for retrieving project information in an information processing method according to an embodiment of the present application, and as shown in fig. 14, after obtaining target project information of a target object, the information processing method according to the embodiment of the present application may further include the following steps:

step 1402: and receiving retrieval information input by a user on a retrieval interface.

Step 1404: and matching the retrieval information with the target project information to obtain a matching result.

Step 1406: and displaying the matching result in a retrieval result display area of the retrieval interface based on a preset display mode.

Specifically, the retrieval interface is an interface for providing retrieval functions for a user, and the retrieval interface can be triggered and displayed by the user. And the retrieval interface comprises a retrieval frame and a retrieval result display area, a user can input retrieval information in the retrieval frame, and a matching result retrieved based on the retrieval information is displayed in the retrieval result display area for the user to view.

In practical application, when a user wants to retrieve information of a certain dimension, corresponding retrieval information can be input in a retrieval interface, and the retrieval information can be sentences and/or words related to target item information. That is, the retrieval information input by the user in the retrieval interface may be at least one sentence, or may also be at least one keyword, or a combination of a sentence and a keyword, and the like.

It should be noted that information of each dimension in the target project information can be semantically retrieved by inputting related retrieval information, that is, the embodiment of the present application supports multidimensional semantic retrieval of industry, concept, enterprise name, field, amount, time, product type, income type, expected income rate, product origin date, product expiration date, product name, and the like. In addition, the user can input a plurality of search information at the same time, thereby not limiting the number of search conditions input by the user in a single sentence.

In specific implementation, the retrieval information is matched with the target item information, and when a matching result is obtained, data related to the retrieval information can be searched from the target item information, and the related data is used as the matching result. In addition, synonym linkage can be supported, for example, when a company is queried, entity linkage can be performed by using whether the company full name or short name contains a keyword besides using the security number full matching. Therefore, synonym linkage is supported, flexible, quick and accurate semantic retrieval experience is provided for users, and the efficiency and quality of the user positioning target follow-up enterprise are improved to the maximum degree.

In the embodiment of the application, based on the preset display mode, before the matching result is displayed in the search result display area of the search interface, a preset display mode may be obtained, and the preset display mode may be at least one display method, such as text display and picture display. In actual implementation, if the target item information is in a knowledge spectrogram form, a sub-graph corresponding to the matching result can be determined, and the sub-graph is displayed in a search result display area of the search interface, so that the search result can be displayed in the sub-graph form, and a user can be helped to better know the relationship between entities and entity information.

Fig. 15 is an exemplary diagram of a retrieval result display scenario in an information processing method applied to an enterprise financial management project according to an embodiment of the present application, where as shown in fig. 15, an interface partition of a retrieval interface includes: a semantic retrieval area and a retrieval answer subgraph visualization operation area.

And a semantic retrieval area: the method supports multi-dimensional semantic retrieval of industries, concepts, enterprise names, fields, amounts, time, product types, income types, expected income rates, product information dates, product expiration dates, product names and the like, can realize the number of retrieval conditions which are not limited by single sentence input of users, supports synonym linkage, provides flexible, quick and accurate semantic retrieval experience for the users, and improves the efficiency and quality of the users for positioning targets and following the enterprises to the maximum extent.

And (3) searching an answer subgraph visualization operation area: answer subgraph return and visual display of graph combined query are carried out after search question and sentence intent recognition processing is supported, structured field information of a current node can be displayed in a suspension mode when a cursor moves into a node area, and a user is helped to better know relationships among entities and entity information.

It should be noted that fig. 11, fig. 13, and fig. 15 respectively show exemplary diagrams of three application scenarios, namely, a statistics function of project information, a reminder for an expired project, and a search function of project information, which function is required in an actual application may enter a corresponding interface, that is, the required function may be implemented.

In the embodiment of the application, semantic search and multi-degree reasoning are carried out. Based on a financial information knowledge map, a deep semantic retrieval solution of knowledge bases of industry enterprises and the like for automatic learning acquisition is integrated, mature experiences of a team on intention recognition and map construction in a plurality of floor projects are integrated, and quick, comprehensive, accurate and fine-grained flexible retrieval and positioning are really realized.

According to the scheme provided by the embodiment of the application, the project text corresponding to the target project is obtained, and the project text contains target object information; searching a preset topological structure corresponding to the target item, and extracting associated object information and associated relation information which have an associated relation with the target object from the item text according to the preset topological structure and the target object information; and integrating the target object information, the associated object information and the association relation information based on a preset topological structure to obtain target project information of the target object. The preset topological structure is constructed based on an incidence relation formed by target objects in the target project. Therefore, the preset topology structure includes a rule for determining the target object, the associated object and the association relationship. Therefore, according to the preset topological structure, the associated object and the associated information of the target object can be obtained from the target data source. On the basis, the preset topological structure has the characteristics of clearness and orderliness. Therefore, the target object information, the associated object information and the associated relation information are integrated based on the preset topological structure to obtain the target item information of the target object, and the target object, the associated object and the associated information can be recorded in a clear and ordered form, so that the obtained information of the target object is clear, ordered and more complete. Therefore, the scheme can improve the information acquisition perfection.

In addition, the intelligent statistics, analysis and retrieval and due reminding functions based on full scenes and multiple dimensions are provided, quick, comprehensive, accurate and fine-grained flexible retrieval and positioning are achieved, timed prompt information pushing can be executed according to reminding conditions set by a user, instant follow-up of target enterprises is achieved, and the ductility and smoothness of a business process are improved through products to the maximum extent.

Corresponding to the above method embodiment, the present application also provides an information processing apparatus embodiment, and fig. 16 shows a schematic structural diagram of an information processing apparatus provided in an embodiment of the present application. As shown in fig. 16, the apparatus includes:

a text obtaining module 1602, configured to obtain a project text corresponding to a target project, where the project text includes target object information;

the topology obtaining module 1604 is configured to find a preset topology structure corresponding to the target item, where the preset topology structure is constructed based on an association relationship formed by target objects in the target item;

an information extraction module 1606 configured to extract, according to the preset topology and the target object information, associated object information and associated relationship information that have an associated relationship with the target object from the project text;

an information integration module 1608 configured to integrate the target object information, the associated object information, and the association relation information based on the preset topological structure, so as to obtain target item information of the target object.

According to the scheme, the preset topological structure is constructed based on the incidence relation formed by the target objects in the target project. Therefore, the preset topology structure includes a rule for determining the target object, the associated object and the association relationship. Therefore, according to the preset topological structure, the associated object and the associated information of the target object can be obtained from the target data source. On the basis, the preset topological structure has the characteristics of clearness and orderliness. Therefore, the target object information, the associated object information and the associated relation information are integrated based on the preset topological structure to obtain the target item information of the target object, and the target object, the associated object and the associated information can be recorded in a clear and ordered form, so that the obtained information of the target object is clear, ordered and more complete. Therefore, the scheme can improve the information acquisition perfection.

In an alternative embodiment, the apparatus further comprises: a build module configured to:

determining an association relation between the target object information and the historical associated object information in the historical item text;

In an optional implementation, the information extraction module 1606 is further configured to:

obtaining an extraction rule template corresponding to the relationship type;

In an alternative embodiment, the information integration module 1608 is further configured to:

In an alternative embodiment, the apparatus further comprises: an update module configured to:

acquiring an update project text of the target project every preset time;

In an alternative embodiment, the apparatus further comprises: a first application module configured to:

In an alternative embodiment, the statistical result comprises: time information; the first application module further configured to:

In an alternative embodiment, the apparatus further comprises: a second application module configured to:

receiving retrieval information input by a user on a retrieval interface;

The information processing device provided in the embodiment of the application provides full-scene and multi-dimensional intelligent statistics, analysis and retrieval and expiration reminding functions, realizes quick, comprehensive, accurate and fine-grained flexible retrieval and positioning, can execute timed prompt information pushing according to reminding conditions set by a user, realizes instant follow-up to a target enterprise, and realizes the improvement of the ductility and the smoothness of a business process through products to the maximum extent.

The above is a schematic configuration of an information processing apparatus of the present embodiment. It should be noted that the technical solution of the information processing apparatus belongs to the same concept as the technical solution of the information processing method described above, and for details that are not described in detail in the technical solution of the information processing apparatus, reference may be made to the description of the technical solution of the information processing method described above. Further, the components in the device embodiment should be understood as functional blocks that must be created to implement the steps of the program flow or the steps of the method, and each functional block is not actually divided or separately defined. The device claims defined by such a set of functional modules are to be understood as a functional module framework for implementing the solution mainly by means of a computer program as described in the specification, and not as a physical device for implementing the solution mainly by means of hardware.

FIG. 17 shows a block diagram of a computing device provided in accordance with an embodiment of the present application. Components of the computing device 1700 include, but are not limited to, memory 1710 and a processor 1720. Processor 1720 is coupled to memory 1710 via bus 1730, and database 1750 is used to store data.

Computing device 1700 also includes access device 1740, access device 1740 enabling computing device 1700 to communicate via one or more networks 1760. Examples of such networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The Access device 1740 may include one or more of any type of Network Interface (e.g., a Network Interface Controller (NIC)) whether wired or Wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) Wireless Interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) Interface, an ethernet Interface, a Universal Serial Bus (USB) Interface, a cellular Network Interface, a bluetooth Interface, a Near Field Communication (NFC) Interface, and so forth.

In one embodiment of the application, the above components of computing device 1700 and other components not shown in FIG. 17 may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 17 is for purposes of example only and is not limiting as to the scope of the present application. Those skilled in the art may add or replace other components as desired.

Computing device 1700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 1700 can also be a mobile or stationary server.

Wherein processor 1720 is configured to execute the computer-executable instructions of the information processing method.

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the information processing method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the information processing method.

An embodiment of the present application also provides a computer-readable storage medium storing computer instructions, which when executed by a processor, are used for an information processing method.

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the information processing method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the information processing method.

The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in source code form, object code form, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer-readable medium may contain suitable additions or subtractions depending on the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer-readable media may not include electrical carrier signals or telecommunication signals in accordance with legislation and patent practice.

It should be noted that for simplicity and convenience of description, the above-described method embodiments are described as a series of combinations of acts, but those skilled in the art will appreciate that the present application is not limited by the order of acts, as some steps may, in accordance with the present application, occur in other orders and/or concurrently. Further, those skilled in the art will appreciate that the embodiments described in this specification are presently considered to be preferred embodiments and that acts and modules are not required in the present application.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The preferred embodiments of the present application disclosed above are intended only to aid in the explanation of the application. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and its practical applications, to thereby enable others skilled in the art to best understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims

1. An information processing method characterized by comprising:

acquiring a project text corresponding to a target project, wherein the project text comprises target object information;

2. The method according to claim 1, wherein before searching for the preset topology corresponding to the target item, the method further comprises:

3. The method according to claim 1, wherein the extracting, from the project text, associated object information and associated relationship information associated with the target object according to the preset topology and the target object information includes:

and extracting the associated object information and the associated relation information which have the associated relation with the target object from the project text by using the extraction rule.

4. The method according to claim 3, wherein the obtaining the relationship type of each association relationship formed by the target node respectively comprises:

5. The method according to claim 3 or 4, wherein the determining, according to the relationship type and the keyword of the node corresponding to the relationship type, the extraction rule corresponding to the relationship type comprises:

obtaining an extraction rule template corresponding to the relationship type;

6. The method according to any one of claims 1 to 4, wherein the integrating the target object information, the associated object information, and the association relation information based on the preset topology structure to obtain the target item information of the target object includes:

7. The method according to any one of claims 1 to 4, wherein the integrating the target object information, the associated object information, and the association relation information based on the preset topology structure to obtain target item information of the target object further includes:

acquiring an update project text of the target project every preset time;

8. The method according to any one of claims 1 to 4, further comprising, after the obtaining target item information of the target object:

9. The method of claim 8, wherein the statistical result comprises: time information; after the target item information of the target object is obtained, the method further includes:

10. The method according to any one of claims 1 to 4, further comprising, after the obtaining target item information of the target object:

receiving retrieval information input by a user on a retrieval interface;

11. An information processing apparatus characterized by comprising:

12. A computing device, comprising:

a memory and a processor;

the memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions to implement the steps of the information processing method according to any one of claims 1 to 10.

13. A computer-readable storage medium storing computer instructions, which when executed by a processor implement the steps of the information processing method of any one of claims 1 to 10.