Object Determination Method, Device, Equipment, Storage Medium, and Program Product

Abstract

The present disclosure provides an object determination method, apparatus, device, storage medium, and program product, which relate to the field of computer technologies, and particularly to the fields of big data and knowledge graph technologies. The specific implementation solution is as follows: obtaining tree-structured data and a matching value for each node in the tree-structured data according to the business scope information of an entity and an industry knowledge graph; and determining at least one candidate object according to the tree-structured data and the matching value.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to the fields of big data and knowledge graph technologies. More specifically, the present disclosure relates to an object determination method, apparatus, device, storage medium, and program product. Background Art

[0002] There is a large amount of information on the business scope of enterprise entities. Determining the main business of an enterprise entity is of great significance for, for example, attracting investment. How to efficiently determine the main business of an enterprise entity is a major challenge currently faced. Summary of the Invention

[0003] The present disclosure provides an object determination method, apparatus, device, storage medium, and program product.

[0004] According to one aspect of the present disclosure, there is provided an object determination method, including: obtaining tree structure data and a matching value for each node in the tree structure data according to the business scope information of an entity and an industry knowledge graph; and determining at least one candidate object according to the tree structure data and the matching value.

[0005] According to another aspect of the present disclosure, there is provided an object determination apparatus, including: a tree structure data determination module and a candidate object determination module. The tree structure data determination module is configured to obtain tree structure data and a matching value for each node in the tree structure data according to the business scope information of an entity and an industry knowledge graph; the candidate object determination module is configured to determine at least one candidate object according to the tree structure data and the matching value.

[0006] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor and a memory communicatively connected to the at least one processor. Wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method of the embodiments of the present disclosure.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method of the embodiments of the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, where the computer program implements the method of the embodiments of the present disclosure when executed by a processor.

[0009] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings are used to better understand the present solution and do not constitute a limitation to the present disclosure. Among them:

[0011] Figure 1 Schematically shows the system architecture diagram of the object determination method and device according to an embodiment of the present disclosure;

[0012] Figure 2 Schematically shows the flowchart of the object determination method according to an embodiment of the present disclosure;

[0013] Figure 3 Schematically shows the schematic diagram of the object determination method according to an embodiment of the present disclosure;

[0014] Figure 4 Schematically shows the schematic diagram of the object determination method according to another embodiment of the present disclosure;

[0015] Figure 5 Schematically shows the schematic diagram of the tree structure data according to an embodiment of the present disclosure;

[0016] Figure 6 Schematically shows the block diagram of the object determination device according to an embodiment of the present disclosure; and

[0017] Figure 7 Schematically shows the block diagram of the electronic device that can implement the object determination method according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following makes an explanation of the exemplary embodiments of the present disclosure in conjunction with the drawings. Among them, various details of the embodiments of the present disclosure are included to help understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0019] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0020] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0021] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning that a person skilled in the art would usually understand this expression (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0022] For example, in the process of attracting investment for construction, how to accurately select the enterprise entities that really need to be attracted from a large number of enterprise entities is a challenging problem. Because the business scope of most current enterprise entities is relatively wide, if only the business scope information of enterprise entities is used to find suitable enterprise entities, it will lead to the situation that the introduced enterprise entities do not meet the business requirements, wasting manpower and material resources.

[0023] For example: If there are already several textile enterprise entities in an industrial park and now it wants to introduce several clothing manufacturing enterprise entities to make up for the lack of the industrial chain. If the business scope information of an enterprise entity is "production and sales of textiles and clothing, production and sales of clothing raw materials, production of cotton and linen textiles", by extracting keywords, "clothing production" can be matched from the business scope information, and this enterprise entity that actually mainly engages in textiles is added to the list of enterprise entities for attracting investment. It may be found that this enterprise entity cannot meet the requirements and waste manpower and material resources after the later connection.

[0024] In some embodiments, keywords are used to select the business scope information of all relevant enterprise entities, and at least one more selection is made manually to determine the enterprise entities for attracting investment. It has defects such as high labor cost, time-consuming and laborious, and low accuracy in determining the main business.

[0025] Figure 1 Schematically shows the system architecture of an object determination method and device according to an embodiment of the present disclosure. It should be noted that Figure 1 The shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help a person skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0026] As Figure 1 shown, the system architecture 100 according to this embodiment may include clients 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the clients 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0027] Users can use clients 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on clients 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0028] Clients 101, 102, and 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop portable computers, and desktop computers, etc. Clients 101, 102, and 103 of the embodiments of the present disclosure can, for example, run application programs.

[0029] Server 105 can be a server providing various services, such as a background management server that supports the websites browsed by users using clients 101, 102, and 103 (for example only). The background management server can analyze and process data such as user requests received, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the client. In addition, server 105 can also be a cloud server, that is, server 105 has cloud computing capabilities.

[0030] It should be noted that the object determination method provided by the embodiments of the present disclosure can be executed by server 105. Correspondingly, the object determination device provided by the embodiments of the present disclosure can be set in server 105. The object determination method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from server 105 and capable of communicating with clients 101, 102, and 103 and / or server 105. Correspondingly, the object determination device provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from server 105 and capable of communicating with clients 101, 102, and 103 and / or server 105.

[0031] In one example, server 105 can obtain the business scope information and industry knowledge graph of entities from clients 101, 102, and 103 via network 104.

[0032] It should be understood that Figure 1 the number of clients, networks, and servers in

[0033] is merely illustrative. According to the implementation requirements, there can be any number of clients, networks, and servers.

[0034] In the technical solution of the present disclosure, the authorization or consent of the user is obtained before obtaining or collecting the user's personal information.

[0035] The embodiments of the present disclosure provide an object determination method. The following will be combined with Figure 1 the system architecture of Figures 2 to 5 to describe the object determination method according to the exemplary embodiments of the present disclosure. The object determination method of the embodiments of the present disclosure can be executed, for example, by Figure 1 the server 105 shown.

[0036] Figure 2 FIG. schematically shows a flowchart of the object determination method according to an embodiment of the present disclosure.

[0037] As Figure 2 shown, the object determination method 200 of the embodiments of the present disclosure may include, for example, operation S210 to operation S220.

[0038] In operation S210, according to the business scope information of the entity and the industry knowledge graph, tree structure data and the matching value of each node in the tree structure data are obtained.

[0039] The entity may include, for example, a company, an enterprise, etc. The industry knowledge graph can represent the hierarchical relationship, association relationship, etc. of the industry. The tree structure data can be understood as a tree structure representation method of the industry knowledge graph related to a specific entity. Each node of the tree structure data represents a specific industry name. The matching value can be understood as the number of times the business scope information of the entity matches the node of the tree structure data.

[0040] In operation S220, at least one candidate object is determined according to the tree structure data and the matching value.

[0041] The business scope of the entity includes the main business. The candidate object can be understood as the candidate main business information of the entity selected from the business scope information of the entity. The candidate main business information of the entity actually has a relatively high probability of being the main business.

[0042] The business scope information of an entity has a node matching relationship with an industry knowledge graph. That is, a certain business scope information of an entity can be matched with a certain node in the industry knowledge graph. The object determination method of the embodiments of the present disclosure can clearly and intuitively represent the hierarchical relationship and association relationship of specific industry names related to the business scope information of the entity according to the business scope of the entity and the tree structure data determined by the industry knowledge graph. The object determination method of the embodiments of the present disclosure also converts the selection of candidate objects (such as candidate main businesses) according to the business scope information of the entity into the selection of candidate main businesses according to the matching values of each node in the tree structure data. The tree structure data is based on the industry knowledge graph and has high accuracy. At the same time, the form of the tree structure is convenient for determining the matching values of the nodes. Therefore, the object determination method of the embodiments of the present disclosure can automatically, accurately and efficiently determine candidate objects according to the business scope information of the entity.

[0043] Figure 3 FIG. schematically shows a schematic diagram of an object determination method 300 according to an embodiment of the present disclosure.

[0044] As Figure 3 shown, in operation S310, according to the business scope information 301 of the entity and the industry knowledge graph 302, tree structure data 303 and the matching value 304 of each node in the tree structure data 303 are obtained. In operation S320, at least one candidate object 305 is determined according to the tree structure data 303 and the matching value 304.

[0045] Exemplarily, the business scope information of the entity and the industry knowledge graph can both be determined in advance.

[0046] Figure 4 FIG. schematically shows a schematic diagram of an object determination method 400 according to another embodiment of the present disclosure.

[0047] As Figure 4 shown, the object determination method 400 according to the embodiment of the present disclosure may further include: operations S410 to S440.

[0048] In operation S410, keywords of the business scope information 401 are extracted to obtain a first keyword data set 402.

[0049] In operation S420, keywords of the name 403 of the entity are extracted to obtain a second keyword data set 404.

[0050] In operation S430, a target keyword data set 405 is obtained according to at least one of the first keyword data set 402 and the second keyword data set 404.

[0051] In operation S440 , at least one target object 407 is determined based on a similarity value between the at least one candidate object 406 and the target keyword dataset 405 .

[0052] The object determination method 400 of the embodiment of the present disclosure includes the following specific implementation schemes.

[0053] 1) extracting keywords from the business scope information to obtain a first keyword dataset; determining the first keyword dataset as a target keyword dataset; and determining at least one target object based on a similarity value between at least one candidate object and the target keyword dataset.

[0054] 2) extracting keywords from the entity name to obtain a second keyword dataset; determining the second keyword dataset as a target keyword dataset; and determining at least one target object based on a similarity value between at least one candidate object and the target keyword dataset.

[0055] 3) extracting keywords from the business scope information to obtain a first keyword dataset, extracting keywords from the entity name to obtain a second keyword dataset; determining a target keyword dataset based on the first keyword dataset and the second keyword dataset; and determining at least one target object based on a similarity value between at least one candidate object and the target keyword dataset.

[0056] Exemplarily, “determining a target keyword dataset based on the first keyword dataset and the second keyword dataset” may include: removing duplicates and merging elements of the first keyword dataset and the second keyword dataset to obtain the target keyword dataset.

[0057] In some cases, an entity's business scope is very broad, and therefore its business scope information is relatively complex. The above operation still results in a large number of candidate objects, which cannot accurately select the primary business. Since the keywords in the entity's name and the keywords in its business scope information are highly correlated with the primary business, according to embodiments of the present disclosure, at least one of the keywords in the entity's name or the keywords in its business scope information can be used as the basis for secondary selection to accurately determine the target object from the candidate objects.

[0058] like Figure 4 As shown, according to an object determination method 400 according to an embodiment of the present disclosure, extracting keywords from business scope information to obtain a first keyword data set may include, for example, operations S411 to S413.

[0059] In operation S411 , text preprocessing is performed on the entity's business scope information 401 .

[0060] Text preprocessing can, for example, include denoising, stop word removal, and the above-mentioned word segmentation. Denoising can, for example, include removing legal statements included in the business scope information and removing noisy texts such as non-compliant punctuation. Stop words can, for example, include words such as "ah" and "is". Word segmentation can be performed, for example, according to the part of speech of the business scope information.

[0061] In operation S412, determine the TF-IDF values of the word segmentation of the business scope information.

[0062] In operation S413, according to the TF-IDF values, extract the keywords of the business scope information to obtain the first keyword dataset.

[0063] TF-IDF (Term Frequency-Inverse Document Frequency). TF-IDF values can be used to characterize the importance of a word for a document set or a document in a corpus. The importance of the word is positively correlated with the number of times the word appears in the document and negatively correlated with the frequency of the word in the corpus.

[0064] Combined with the embodiments of the present disclosure, a certain number of business scope information can be determined in advance as business scope information samples. The TF-IDF values of the business scope word segmentation obtained by word segmentation in the business scope information samples are used to determine the importance of the business scope word segmentation for the current business scope information. This importance can also characterize the degree of correlation between the business scope word segmentation and the main business.

[0065] As Figure 4 shown, in operation S420, the keywords of the entity name 403 can be extracted through a keyword extraction model to obtain the second keyword dataset 404.

[0066] Exemplarily, the keyword extraction model can, for example, include: TextRank model, LDA model (Latent Dirichlet Allocation model, LDA for short).

[0067] In operation S440, according to the similarity calculation model, determine the similarity values between at least one candidate object 406 and the target keyword dataset 405 to determine at least one target object 407.

[0068] Exemplarily, the similarity calculation model can, for example, include: Pearson similarity calculation model.

[0069] Exemplarily, in the object determination method according to an embodiment of the present disclosure, the industry knowledge graph may include four levels; obtaining the tree structure data and the matching value of each node in the tree structure data according to the business scope information of the entity and the industry knowledge graph may include: matching the business scope information of the entity with the third-level nodes and the fourth-level nodes of the industry knowledge graph to obtain the matching nodes of the business scope information; obtaining the tree structure data according to the matching nodes and the first-level nodes and the second-level nodes of the industry knowledge graph; and determining the matching value of each node in the tree structure data according to the number of times of matching between the business scope information and the nodes in the tree structure data.

[0070] Exemplarily, the industry knowledge graph may be consistent with the "Classification of National Economic Industries" released by the National Bureau of Statistics, and the classification of industries in the "Classification of National Economic Industries" includes four levels. Among them, in the order of the first level, the second level, the third level, and the fourth level, the industry scope represented by the nodes at the corresponding levels is smaller.

[0071] The granularity of the business scope information of the entity is closer to that of the third-level nodes and the fourth-level nodes. Therefore, in the object determination method according to an embodiment of the present disclosure, the business scope information of the entity can be matched with the third-level nodes and the fourth-level nodes of the industry knowledge graph to improve the accuracy of matching.

[0072] Exemplarily, "obtaining the tree structure data according to the matching nodes and the first-level nodes and the second-level nodes of the industry knowledge graph" can be understood as: after determining the matching nodes at the third level or the fourth level, the tree structure data can be obtained according to the first-level nodes and the second-level nodes of the industry knowledge graph corresponding to the matching nodes.

[0073] In the industry knowledge graph, for some industries, there are only first-level to third-level nodes and no corresponding fourth-level nodes. "Matching the business scope information of the entity with the third-level nodes and the fourth-level nodes of the industry knowledge graph to obtain the matching nodes of the business scope information" can be understood as: when the relevant industry does not include the fourth-level nodes, matching the business scope information of the entity with the third-level nodes of the industry knowledge graph to obtain the matching nodes of the business scope information; when the relevant industry includes the fourth-level nodes, matching the business scope information of the entity with the fourth-level nodes of the industry knowledge graph to obtain the matching nodes of the business scope information. That is, for a certain determined business scope information, only one matching node will be obtained, and the matching node is a node at the third level or a node at the fourth level.

[0074] Exemplarily, for the object determination method according to an embodiment of the present disclosure, determining at least one candidate object according to tree structure data and a matching value may include: determining at least one candidate object according to the maximum value of the matching values of the nodes at each level, or the comparison result between the matching value and a comparison threshold, in the order from the root node to the leaf node of the tree structure data.

[0075] Since the order from the root node to the leaf node of the tree structure data corresponds to the order from the largest to the smallest in the industry scope, the method for determining an object according to an embodiment of the present disclosure, by determining at least one candidate object in the order from the root node to the leaf node of the tree structure data, can accurately and comprehensively determine the candidate object.

[0076] Specifically, there is the following situation:

[0077] For example, for the same level, there are two leaf nodes Nx and Ny, and their matching values are the largest and the same in this level. The matching value of the parent node of leaf node Nx is greater than the matching value of the parent node of leaf node Ny. When only using the matching values of the leaf nodes as the basis for determining candidate objects, both leaf node Nx and leaf node Ny will be used as candidate objects. In fact, the matching value of the parent node of leaf node Nx is larger, and the subtree of the parent node of leaf node Nx - leaf node Nx is more important. Therefore, leaf node Nx is a more accurate candidate object.

[0078] Figure 5 FIG. 500 schematically shows a schematic diagram of tree structure data according to an embodiment. Among them, the root node is N0. The nodes at the first level include node N11 and node N12, the nodes at the second level include node N21, node N22, and node N23. The nodes at the third level include node N31, node N32, node N33, and node N34. The nodes at the fourth level include node N41, node N42, and node N43.

[0079] The following will be combined with Figure 5 for illustration to describe the object determination method according to an embodiment of the present disclosure.

[0080] As Figure 5 shown in the example, except for the root node N0, there are a total of 4 levels. The order of these four levels from the root node to the leaf node respectively represents the first level to the fourth level in the industry knowledge graph related to a certain entity. Figure 5 Each circle in represents a node in the industry knowledge graph, and the number in the node represents the number of times the business scope information matches the node, that is, the matching value. As Figure 5 shown, the business scope information of this entity matches leaf node N31 2 times, matches leaf node N32 1 time, matches leaf node N41 1 time, matches leaf node N42 1 time, and matches leaf node N43 1 time.

[0081] The matching value of the parent node N21 is obtained by aggregating the matching values of its two child nodes N31 and N32 (i.e., by adding the two). The matching value of the parent node N33 is the same as the matching value of its only child node N41. Similarly, the matching value of the parent node N22 is the same as the matching value of its only child node N33. The matching value of the parent node N11 is obtained by aggregating the matching values of its two child nodes N21 and N22. Thus, the matching values of each node in the left subtree of the tree structure data 500 are determined. The matching value of the parent node N34 is obtained by aggregating the matching values of its two child nodes N42 and N43. The matching value of the parent node N23 is the same as the matching value of its only child node N34. Similarly, the matching value of the parent node N12 is the same as the matching value of its only child node B23. Thus, the matching values of each node in the right subtree of the tree structure data 500 are determined.

[0082] Since the industry knowledge graph is hierarchical and high-level industries contain low-level industries, the parent node of any child node represents that the industry of this parent node is the upper level of the industry of this child node. For example: The node representing "textile industry" is the upper level of the node representing "cotton textile and printing and finishing" and the node representing "ramie textile and printing and finishing", so the node representing "textile industry" is the parent node. The matching value of the parent node aggregates the matching values of all its corresponding child nodes, and the matching value of this parent node represents the business scope information of this entity and the number of times of matching with this parent node. Thus, it is possible to continuously aggregate from the leaf nodes up to the root node of this tree, thereby obtaining the tree structure data. Each node of the tree structure data contains two values: the specific industry name and the matching value.

[0083] In the object determination method of the present disclosure embodiment, when determining a candidate object, starting from the root node, find the node with the largest matching value among the child nodes of the root node as the first-level candidate node (if there are multiple child nodes with the largest and same matching values, they can all be used as candidate nodes at the corresponding level), and then along the subtree with this first-level candidate node as the root node, find the child node with the largest matching value among the child nodes of this first-level candidate node as the second-level candidate node. Until all the third-level nodes and fourth-level nodes with the most matching values are used as candidate objects.

[0084] For example, as Figure 5As shown in the example, starting from the root node N0, the matching values of the two first-level child nodes N11 and N12 of the root node N0 are 4 and 2 respectively. Among the first-level nodes, the node with the largest matching value is the node N11, that is, the node N11 is determined as the first-level candidate node. Then, search downward along the subtree with the node N11 as the root node. The matching values of the two second-level child nodes N21 and N22 of the node N11 are 3 and 1 respectively. Among the second-level nodes, the node with the largest matching value is the node N21, that is, the node N21 is determined as the second-level candidate node. Next, search downward along the subtree with the node N21 as the root node. Among the third-level nodes, the node with the largest matching value is the node N31. Since the node N31 is a leaf node of this subtree, the candidate object of this entity is determined as the specific industry name represented by the leaf node N31.

[0085] Figure 6 FIG. schematically shows a block diagram of an object determination device according to an embodiment of the present disclosure.

[0086] As Figure 6 shown, the object determination device 600 according to an embodiment of the present disclosure may include, for example, a tree structure data determination module 610 and a candidate object determination module 620.

[0087] The tree structure data determination module 610 is configured to obtain tree structure data and the matching value of each node in the tree structure data according to the business scope information of the entity and the industry knowledge graph.

[0088] The candidate object determination module 620 is configured to determine at least one candidate object according to the tree structure data and the matching value.

[0089] The object determination device according to an embodiment of the present disclosure may further include: a first keyword dataset determination module, a second keyword dataset determination module, a target keyword dataset determination module, and a target object determination module.

[0090] The first keyword dataset determination module may be configured to extract keywords of the business scope information to obtain a first keyword dataset.

[0091] The second keyword dataset determination module may be configured to extract keywords of the name of the entity to obtain a second keyword dataset.

[0092] The target keyword dataset determination module may be configured to obtain a target keyword dataset according to at least one of the first keyword dataset and the second keyword dataset.

[0093] The target object determination module may be configured to determine at least one target object according to the similarity value between at least one candidate object and the target keyword dataset.

[0094] An object determination device according to an embodiment of the present disclosure, the industry knowledge graph includes four levels; the tree structure data determination module may include: a matching node determination sub-module, a tree structure data determination sub-module, and a matching value determination sub-module.

[0095] The matching node determination sub-module can be used to match the business scope information of the entity with the nodes of the third level and the fourth level of the industry knowledge graph to obtain the matching nodes of the business scope information;

[0096] The tree structure data determination sub-module can be used to obtain tree structure data according to the matching nodes and the nodes of the first level and the second level of the industry knowledge graph; and

[0097] The matching value determination sub-module can be used to determine the matching value of each node of the tree structure data according to the number of times the business scope information matches the nodes of the tree structure data.

[0098] An object determination device according to an embodiment of the present disclosure, the candidate object determination module may include: a candidate object determination sub-module.

[0099] The candidate object determination sub-module can be used to determine at least one candidate object in the order from the root node to the leaf node of the tree structure data according to the maximum value of the matching values of the nodes at each level, or the comparison result of the matching value and the comparison threshold.

[0100] An object determination device according to an embodiment of the present disclosure, the first keyword dataset determination module may include: a TF-IDF value determination sub-module, a first keyword dataset determination sub-module.

[0101] The TF-IDF value determination sub-module can be used to determine the TF-IDF values of the segmented business scope information, and the segmented business scope information is obtained by segmenting the business scope information.

[0102] The first keyword dataset determination sub-module can be used to extract keywords of the business scope information according to the TF-IDF values to obtain the first keyword dataset.

[0103] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0104] Figure 7FIG. shows a schematic block diagram of an exemplary electronic device 700 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementations of the present disclosure described and / or claimed herein.

[0105] As Figure 7 shown, the device 700 includes a computing unit 701 that can perform various appropriate actions and processes in accordance with a computer program stored in a read only memory (ROM) 702 or a computer program loaded from a storage unit 707 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0106] A plurality of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0107] The computing unit 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 executes the various methods and processes described above, such as the object determination method. For example, in some embodiments, the object determination method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the object determination method described above can be executed. Alternatively, in other embodiments, the computing unit 701 can be configured to execute the object determination method in any other suitable manner (e.g., by means of firmware).

[0108] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0110] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of a communication network include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0113] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0114] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0115] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. An object determination method, comprising: Obtaining tree structure data and a matching value for each node in the tree structure data according to the business scope information of an entity and an industry knowledge graph; And Determining at least one candidate object according to the tree structure data and the matching value; Extracting keywords of the business scope information to obtain a first keyword data set; Extracting keywords of the name of the entity to obtain a second keyword data set; Obtaining a target keyword data set according to at least one of the first keyword data set and the second keyword data set; And Determining at least one target object according to the similarity value between at least one of the candidate objects and the target keyword data set; Wherein, the industry knowledge graph includes four levels; the obtaining tree structure data and a matching value for each node in the tree structure data according to the business scope information of an entity and an industry knowledge graph includes: Matching the business scope information of the entity with the nodes of the third level and the fourth level of the industry knowledge graph to obtain the matching nodes of the business scope information; Obtaining the tree structure data according to the matching nodes and the nodes of the first level and the second level of the industry knowledge graph; and Determining the matching value of each node in the tree structure data according to the number of times of matching between the business scope information and the nodes of the tree structure data.

2. The method according to claim 1, wherein, The determining at least one candidate object according to the tree structure data and the matching value includes: Determining at least one of the candidate objects in the order from the root node to the leaf node of the tree structure data according to the maximum value of the matching values of the nodes at each level, or the comparison result between the matching value and a comparison threshold.

3. The method according to claim 1, wherein, The extracting keywords of the business scope information to obtain a first keyword data set includes: Determining the TF-IDF value of the word segmentation of the business scope information, where the word segmentation of the business scope information is obtained by performing word segmentation on the business scope information; and Extracting keywords of the business scope information according to the TF-IDF value to obtain the first keyword data set.

4. An object determination device, comprising: A tree structure data determination module, configured to obtain tree structure data and a matching value for each node in the tree structure data according to the business scope information of an entity and an industry knowledge graph; A candidate object determination module, configured to determine at least one candidate object according to the tree structure data and the matching value; And A first keyword data set determination module, configured to extract keywords of the business scope information to obtain a first keyword data set; A second keyword data set determination module, configured to extract keywords of the name of the entity to obtain a second keyword data set; A target keyword data set determination module, configured to obtain a target keyword data set according to at least one of the first keyword data set and the second keyword data set; And A target object determination module, configured to determine at least one target object according to the similarity values between at least one of the candidate objects and the target keyword dataset; wherein, the industry knowledge graph includes four levels; the tree structure data determination module includes: A matching node determination sub-module, configured to match the business scope information of the entity with the nodes of the third level and the fourth level of the industry knowledge graph to obtain the matching nodes of the business scope information; A tree structure data determination sub-module, configured to obtain the tree structure data according to the matching nodes and the nodes of the first level and the second level of the industry knowledge graph; and A matching value determination sub-module, configured to determine the matching value of each node of the tree structure data according to the number of times the business scope information matches the nodes of the tree structure data.

5. The apparatus according to claim 4, wherein The candidate object determination module includes: A candidate object determination sub-module, configured to determine at least one of the candidate objects in the order from the root node to the leaf node of the tree structure data according to the maximum value of the matching values of the nodes at each level, or the comparison result between the matching value and a comparison threshold.

6. The device according to claim 4, wherein The first keyword dataset determination module includes: A TF-IDF value determination sub-module, configured to determine the TF-IDF values of the business scope information after word segmentation, where the business scope information after word segmentation is obtained by performing word segmentation on the business scope information; and A first keyword dataset determination sub-module, configured to extract the keywords of the business scope information according to the TF-IDF values to obtain the first keyword dataset.

7. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-3.

9. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-3.

Images