Knowledge graph construction method and device, and knowledge graph construction system

Abstract

The application provides a knowledge graph construction method and device and a knowledge graph construction system. The method comprises: acquiring node information, which is information of a business node handling a business; acquiring content information, which is information of a business content handled by the business node handling the business; acquiring process information, which is information of an approval sequence of the business node handling the business; constructing a knowledge graph according to the node information, the content information and the process information, and displaying the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph. By constructing the knowledge graph, the process of handling the business is displayed, the process of handling the business can be visually displayed, and thus a user can see the process of handling the business through the displayed knowledge graph, thereby improving the experience effect of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of knowledge graph, in particular to a knowledge graph construction method and device, a computer readable storage medium and a knowledge graph construction system. BACKGROUND

[0002] Currently, various process information of handling services is invisible. After submitting a service order, the submitter does not know the handling process of the service order, and only handles it through forms or files. The user experience of handling services is poor. SUMMARY

[0003] The main purpose of the present application is to provide a knowledge graph construction method, device, computer readable storage medium and knowledge graph construction system to at least solve the problem of poor user experience in handling services in the prior art.

[0004] In order to achieve the above purpose, according to one aspect of the present application, a knowledge graph construction method is provided, comprising: acquiring node information, wherein the node information is the information of a service node of handling services; acquiring content information, wherein the content information is the information of a service content handled by the service node of handling services; acquiring process information, wherein the process information is the information of an approval sequence of the service node of handling services; constructing a knowledge graph according to the node information, the content information and the process information, and displaying the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0005] Optionally, after constructing the knowledge graph, the method further comprises: extracting, from all the process information, common information with the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of handled services, wherein the common information includes a common name, common node information, common content information and common process information, the common name and the common information correspond one by one, and the common information is suitable for all services; in the case of new service handling, finding the corresponding common information according to the common name, and generating the process information corresponding to the new service according to at least the common information.

[0006] Optionally, the obtaining the process information comprises: obtaining first process information, wherein the approval sequence of the first process information is that the first business node is approved first, then the second business node is approved, and then the first business node is approved again; obtaining second process information, wherein the approval sequence of the second process information is that the first business node is approved first, then the second business node and the third business node are approved simultaneously, and then the fourth business node is approved; obtaining third process information, wherein the approval sequence of the third process information is that the first business node is approved first, then the second business node and the third business node are approved simultaneously, and then the fourth business node is approved after the second business node is approved or the third business node is approved; and obtaining fourth process information, wherein the approval sequence of the fourth process information is that the first business node is approved first, then the second business node is approved, and then the third business node is approved.

[0007] Optionally, after the knowledge graph is constructed, the method further comprises: receiving a first predetermined operation, wherein the first predetermined operation is an operation of modifying the knowledge graph; and in response to the first predetermined operation, at least updating the node information and the approval sequence of the process information, and updating the knowledge graph to obtain an updated knowledge graph.

[0008] Optionally, after the knowledge graph is constructed, the method further comprises: in a case where a new business is to be added to the knowledge graph, performing semantic analysis on the content of the new business, determining target business content corresponding to the new business, and calculating the similarity between the target business content of the new business and a plurality of content information; determining the content information with the highest similarity to the new business as target content information, and highlighting the process information and the node information corresponding to the target content information in the knowledge graph.

[0009] Optionally, before the content of the new business is analyzed semantically to determine the target business content corresponding to the new business, the method further comprises: obtaining pre-stored question and answer pairs, wherein each question and answer pair comprises one question and one answer; and performing a filtering step at least once, wherein the filtering step comprises: displaying a question in the display interface, obtaining a reply answer, wherein the reply answer is an answer input into a display box, searching for a target question and answer pair with a similarity greater than a similarity threshold from a plurality of question and answer pairs according to the reply answer, and determining the answer in the target question and answer pair as first target process information.

[0010] Optionally, after highlighting the process information and the node information corresponding to the target content information in the knowledge graph, the method further includes: receiving a second predetermined operation, wherein the second predetermined operation is an operation of selecting the highlighted process information and node information; in response to the second predetermined operation, determining that the selected process information is first initial process information and the selected node information is first initial node information; receiving a third predetermined operation, wherein the third predetermined operation is an operation of selecting the process information and node information that are not highlighted; in response to the third predetermined operation, determining that the selected process information is second initial process information and the selected node information is second initial node information; receiving a fourth predetermined operation, wherein the fourth predetermined operation is an operation of fusing the first initial process information, the second initial process information, the first initial node information, and the second initial node information; and in response to the fourth predetermined operation, generating second target process information, wherein the second target process information includes the first initial process information, the second initial process information, the first initial node information, and the second initial node information.

[0011] According to another aspect of the present application, a knowledge graph construction device is provided, which includes: a first acquisition unit configured to acquire node information, wherein the node information is information of a business node that handles a business; a second acquisition unit configured to acquire content information, wherein the content information is information of a business content handled by the business node that handles the business; a third acquisition unit configured to acquire process information, wherein the process information is information of an approval sequence of the business node that handles the business; and a first processing unit configured to construct a knowledge graph according to the node information, the content information, and the process information, and display the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0012] According to still another aspect of the present application, a computer readable storage medium is provided, which includes a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform any of the knowledge graph construction methods.

[0013] According to yet another aspect of the present application, a knowledge graph construction system is provided, which includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the knowledge graph construction methods.

[0014] By means of constructing the knowledge graph, the process of handling the business is displayed, the process of handling the business can be visually displayed, so that the user can see the process of handling the business through the displayed knowledge graph, and the experience effect of the user is improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings constituting a part of the specification provide further understanding of the present application, the illustrative embodiments of the present application and the description thereof serve to explain the present application, and do not constitute improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a construction method of a knowledge graph is shown according to an embodiment of the present application;

[0017] Figure 2 A flowchart of a construction method of a knowledge graph is shown according to an embodiment of the present application;

[0018] Figure 3 A structure block diagram of a construction device of a knowledge graph is shown according to an embodiment of the present application.

[0019] Among them, the above-mentioned drawings include the following reference signs:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input and output device. DETAILED DESCRIPTION

[0021] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background, the various process information for handling business in the prior art is invisible, after submitting a business form, the submitter does not know the handling process of the business form, and only handles it through forms or files, and the experience effect of the user handling business is poor. To solve the problem that the experience effect of the user handling business is poor, the embodiments of the present application provide a knowledge graph construction method, device, computer readable storage medium and knowledge graph construction system.

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking the case of running on a mobile terminal, Figure 1 is a hardware structure block diagram of a mobile terminal of a knowledge graph construction method of the embodiments of the present application. As shown in Figure 1 , the mobile terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned mobile terminal can further include a transmission device 106 for communication function and an input and output device 108. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal can further include more or less components than those shown in Figure 1 , or have a different configuration from Figure 1 .

[0027] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the device information display method of the embodiments of the present application. The processor 102 executes various functional applications and data processing, i.e., implements the above method, by running the computer programs stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include memories disposed remotely with respect to the processor 102, which can be connected to the mobile terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The specific examples of the above network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.

[0028] In the embodiments, a method for constructing a knowledge graph running on a mobile terminal, a computer terminal or the like is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown herein.

[0029] Figure 2 is a flowchart of a method for constructing a knowledge graph according to an embodiment of the present application. As shown in Figure 2 , the method comprises the following steps:

[0030] In step S201, node information is acquired, wherein the node information is information of a service node handling a service;

[0031] Specifically, when a user handles a service, multiple service nodes are often required for approval. For example, for a leave application of an enterprise, the personnel required for approval include the person himself / herself, a superior leader, and human resources. For a purchase order, the personnel required for approval include the person himself / herself, a superior leader, sales, and finance. For a leave application of a school, the personnel required for approval include the person himself / herself, a class teacher, and a student councilor. Therefore, different services correspond to different service nodes required.

[0032] Specifically, all the business nodes required for handling a service can be input in advance, the business nodes required for handling the service are determined, and then the node information of the business nodes is obtained.

[0033] In step S202, content information is obtained, wherein the content information is information of a service content handled by the business node handling the service.

[0034] Specifically, the service content handled by different business nodes is different when a user handles a service. For example, for a leave slip of an enterprise, the person in charge is responsible for filling in the leave slip, the superior leader is responsible for approving the leave slip, and the human resources department is responsible for recording the attendance.

[0035] For example, for a purchase order, the person in charge is responsible for filling in the purchase order and purchase information, the superior leader is responsible for approving the purchase order, the sales department is responsible for making an amount budget, and the finance department is responsible for making a payment.

[0036] For example, for a leave slip of a school, the person in charge is responsible for filling in the leave slip, the class teacher is responsible for approving the leave slip, and the student committee is responsible for recording the number of people on leave and the names of the people on leave, so as to make a roll call in class.

[0037] Specifically, the service content that each business node can handle can be input in advance, it is determined what the service content that each business node can handle is, and then the information of the service content handled by the business node, i.e., the content information, is obtained.

[0038] In step S203, process information is obtained, wherein the process information is information of an approval sequence of the business node handling the service.

[0039] Specifically, the approval sequence of different services is different when a user handles a service. For example, for a leave slip of an enterprise, after the person in charge submits the leave slip, the leave slip is submitted to the superior leader, after the superior leader approves it, the leave slip is submitted to the human resources department, and after the human resources department records the attendance, the process ends.

[0040] For example, for a purchase order, after the person in charge submits the purchase order, the purchase order is submitted to the superior leader, after the superior leader approves it, the purchase order is submitted to the sales department, after the sales department makes an amount budget for the purchase, the purchase order is submitted to the finance department, after the finance department makes a payment, the purchase order is submitted to the sales department, and the sales department is responsible for purchasing the goods.

[0041] For example, for a leave slip of a school, after the person in charge submits the leave slip, the leave slip is submitted to the class teacher, after the class teacher approves it, the leave slip is submitted to the student committee and the person in charge, the student committee records the number of people who should be present and the number of people who are actually present according to the leave slip, and the person in charge goes out of the school according to the leave slip approved by the class teacher.

[0042] Specifically, the approval sequence of the plurality of service nodes when handling the service can be input in advance, so that the service handling process can be determined, and the process information can be obtained.

[0043] In step S204, a knowledge graph is constructed according to the node information, the content information, and the process information, the node information corresponds to entities of the knowledge graph, the content information corresponds to attributes of the knowledge graph, and the process information corresponds to relationships of the knowledge graph, and the knowledge graph is displayed on a display interface of a display device.

[0044] Specifically, the entire process of handling the service can be displayed in the form of a knowledge graph, so that the process of handling the service can be visually displayed, the user can see the current process, the previous process, and the next process of handling the service, and even the entire process, and the user can click the knowledge graph to display information of a node and information of a service content.

[0045] In this embodiment, the process of handling the service is displayed by constructing a knowledge graph, the process of handling the service can be visually displayed, so that the user can see the process of handling the service through the displayed knowledge graph, and the user experience is improved.

[0046] In the case where all the service handling has common characteristics (the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the service handled), the same part can be extracted, and in the specific implementation process, after the knowledge graph is constructed, the method further includes the following steps: extracting, from all the process information, the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the service handled as general information, wherein the general information includes a general name, general node information, general content information, and general process information, the general name and the general information correspond to each other, and the general information is applicable to all services; in the case where a new service is handled, the corresponding general information is found according to the general name, and the process information corresponding to the new service is generated at least according to the general information.

[0047] In this scheme, the part of the knowledge graph with the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the service handled can be extracted as general information, and the general information can be named as a general name, so that if a new service needs to be added, the general name can be directly searched to search the general information, and it is not necessary to select one by one, and the user experience is further improved.

[0048] Specifically, if there are multiple approved businesses, the specific approval process is as follows:

[0049] Business one: A-B-C-D;

[0050] Business two: A-B-C;

[0051] Business three: B-C-D;

[0052] Business four: B-C-B-A-B;

[0053] The four businesses above are all leave handling businesses, and the same process in the four businesses is B-C, so B-C is taken as general information and stored as a general name "leave business". Subsequently, the general information is searched out through the general name, and then other nodes and businesses are set based on the general information.

[0054] Of course, the stored general information can not be limited to one, but also multiple, for example, the leave business stores one general information, the procurement business stores one general information, and the call package can also store one general information.

[0055] The process information can be various, for the approval order, it can be sequential approval, series approval, parallel approval, etc. In the specific implementation process, the process information can be obtained through the following steps: obtaining first process information, wherein the approval order of the above first process information is that the first business node is approved, then the second business node is approved, and then the first business node is approved again; obtaining second process information, wherein the approval order of the above second process information is that the above first business node is approved, then the above second business node and the third business node are approved at the same time, and then the fourth business node starts to approve the information; obtaining third process information, wherein the approval order of the above third process information is that the above first business node is approved, then the above second business node and the above third business node are approved at the same time, and then the above fourth business node starts to approve the information after the above second business node is approved or the above third business node is approved; obtaining fourth process information, wherein the approval order of the above fourth process information is that the above first business node is approved, then the above second business node is approved, and then the above third business node is approved.

[0056] In the scheme, the first flow information actually refers to a business requiring a certain business node to repeat the approval, and other business nodes will also be passed through in the middle. The second flow information actually refers to a business requiring two parallel business nodes to approve. The third flow information actually refers to a business requiring any one of the two parallel business nodes to approve. The fourth flow information actually refers to the order of the serial approval. In the embodiment, multiple approval orders are defined, and the flow information corresponding to different approval orders is different. In this way, with multiple flow information, a knowledge graph can be further constructed efficiently and accurately.

[0057] Specifically, in the case of multiple business nodes for approval, the approval result can be determined as passed only after multiple business nodes are approved. Of course, it is not limited to this way, and the approval result can be determined as passed only after a predetermined number of business nodes are approved. The predetermined number can be 1 / 2, 2 / 3, etc. Of course, different ways can be defined for different approved businesses, for example, according to the type of business, to determine the approval process and the approval result. If the business type is leave type, the corresponding approval process must pass the class teacher, and the approval result is determined as passed only if the class teacher agrees. If the business type is to purchase stationery, and the amount is less than the predetermined amount, the approval process is defined as being able to pass the superior leader or not, and the approval result is passed regardless of whether the superior leader agrees or not. Of course, for leave type, different leave types have different approval processes, for example, if the number of leave days is less than or equal to two days, the approval of the class teacher is required. If the number of leave days is greater than two days and less than or equal to five days, the approval of the class teacher and the age director is required. If the number of leave days is greater than five days, the approval of the class teacher, the age director, and the school principal is required.

[0058] Of course, for defining flow information, the priority of specific parameters can also be defined, for example, determining the level of business content. If the business content is the highest level, the flow of the highest level business content is processed first. If the business content is ordinary level, the flow of the ordinary level business content is processed after the highest level is processed.

[0059] Of course, for different types of businesses, the priority of the flow can also be defined, for example, for enterprise users, if the business type is to entertain clients, the corresponding flow information is the first level, and the approval process should be sales-department leader-department manager. If the business type is bidding, the corresponding flow information is the second level, and the approval process should be sales-department leader-department manager-supervisor. If the department leader is subject to both approval processes, the business of entertaining clients will be displayed as the highest priority on the display interface, which can be highlighted.

[0060] In order to update the knowledge graph in the case of adding new business to the knowledge graph, the application further comprises the following steps after constructing the knowledge graph: receiving a first predetermined operation, wherein the first predetermined operation is an operation for modifying the knowledge graph; in response to the first predetermined operation, at least updating the node information and the approval order of the flow information, and updating the knowledge graph to obtain an updated knowledge graph.

[0061] In this scheme, the knowledge graph can also be updated, and operations can be directly performed on the knowledge graph. This is a visual operation, for example, a new business node can be created, so that the entity, attribute and relationship of the knowledge graph can be directly changed, and the user can directly see the change process, thereby further improving the user experience effect.

[0062] Specifically, if the knowledge graph is updated, it is actually equivalent to handling a business. After the user himself / herself submits an update business form and the superior and the superior's superior approve, the user is allowed to update the knowledge graph. The updated knowledge graph can be used normally.

[0063] In order to facilitate the user to update the knowledge graph, the application further comprises the following steps after constructing the knowledge graph: in the case of adding new business to the knowledge graph, performing semantic analysis on the content of the new business, determining the target business content corresponding to the new business, and calculating the similarity between the target business content of the new business and a plurality of content information; determining the content information with the highest similarity to the new business as the target content information, and highlighting the flow information and the node information corresponding to the target content information in the knowledge graph.

[0064] In this scheme, in the case of adding new business to the knowledge graph, since the original business in the knowledge graph has been defined in advance, the similarity between the new business and the original business can be analyzed, the original business with the highest similarity to the new business is taken as the target business, and the corresponding target content information and flow information are highlighted on the display interface, thereby facilitating the user to refer to, and facilitating the user to update the knowledge graph based on the highlighted nodes and flow.

[0065] Specifically, in the case of adding new business to the knowledge graph, whether to go through the A node or the B node first can be determined by manual operation, or can be determined by automatic operation through semantic analysis, so that the closest one can be found from the stored content information, and it can be determined whether to go through the A node or the B node first according to the stored flow.

[0066] Specifically, the process information, business node and business content of handling a certain business in the knowledge graph can be highlighted, so that the process of handling a certain business can be directly seen on a graph. Only a part of the knowledge graph is displayed. Of course, for the general part, it can also be directly highlighted and named, so that it can be directly queried using the knowledge graph. For example, the name is the senior handling department, and the corresponding business nodes are the chairman and general manager. This general part can also be stored as a single knowledge graph and named.

[0067] If the user wants to newly input a business to the knowledge graph, but the user does not know the specific process sequence and the content that can be approved by the business node, the user can be guided to select the business node and the process through the question and answer pair. In some embodiments, before the semantic analysis of the content of the new business is performed to determine the target business content corresponding to the new business, the above method further includes the following steps: obtaining a pre-stored question and answer pair, wherein the question and answer pair is a combination of a question corresponding to an answer; performing a filtering step at least once, the filtering step being: displaying a question in the display interface and obtaining a reply answer, wherein the reply answer is an answer input into the display box, and according to the reply answer, searching for a target question and answer pair from a plurality of question and answer pairs that has a similarity greater than a similarity threshold with the reply answer, and determining that the answer in the target question and answer pair corresponds to the first target process information.

[0068] In this scheme, a plurality of question and answer pairs are pre-stored. By successively asking the user and obtaining the user's reply, the user can be guided to select the business node and the process of handling the business. Even if the user does not know how to fill in the business process, the user can be guided to set the business node and the process through the question and answer pair, thereby ensuring that the user experience is good.

[0069] For example, there are a plurality of question and answer pairs. First, ask the user "do you want to fill in a leave application form?", if the user replies "yes", then continue to ask the user "are you an enterprise user or a school user?", if the user replies "enterprise user", then determine that the corresponding first target process information is self-superior leader-human resources. If the user replies "no, it is a purchase order" when the user is asked for the first time, then continue to ask the user "do you want to purchase product A?", if the user replies "yes", then determine that the corresponding first target process information is self-administration, if the user replies "no, want to purchase product B", then the corresponding first target process information is self-superior leader-sales-finance-sales-self.

[0070] Of course, there are also some pre-set reverse rules when guiding the user to input the question, which can be set according to the priority of the parameters, or according to the importance of the parameters, specifically, a plurality of reverse rules can be set, and the customer can set (or other user), for example: 1, according to the number of established process weight to reverse, 2, according to the number of processes used by the current user department weight to reverse, 3, give priority to general processes, supplemented by specific processes, and then according to their usage frequency to reverse, 4, according to the importance priority of the established process to reverse.

[0071] Specifically, for the knowledge graph, the text stored in the knowledge graph can also be processed by text alignment. A database can be introduced and put into the whole graph. The text feature vector in the text can be extracted, and the text feature vector can be scored. The AHP algorithm can be used to score, so that a text scoring result can be obtained, and the evaluation coefficient of each text can be determined.

[0072] The knowledge graph can be displayed on the display interface, and the user can directly perform addition, deletion, modification and query processing on the knowledge graph through clicking operation. In some embodiments, after highlighting the process information and node information corresponding to the target content information in the above knowledge graph, the method further includes the following steps: receiving a second predetermined operation, wherein the second predetermined operation is a selected operation on the highlighted process information and node information; in response to the second predetermined operation, determining that the selected process information is first initial process information, and determining that the selected node information is first initial node information; receiving a third predetermined operation, wherein the third predetermined operation is a selected operation on the process information and node information that are not highlighted; in response to the third predetermined operation, determining that the selected process information is second initial process information, and determining that the selected node information is second initial node information; receiving a fourth predetermined operation, wherein the fourth predetermined operation is an operation for fusing the first initial process information, the second initial process information, the first initial node information and the second initial node information; in response to the fourth predetermined operation, generating second target process information, wherein the second target process information includes the first initial process information, the second initial process information, the first initial node information and the second initial node information.

[0073] In the scheme, in the case that the knowledge graph has been displayed in the display interface, part of the content in the knowledge graph is highlighted, and part of the content is not highlighted. The highlighting is for the convenience of the user to view. The user can refer to the highlighted part to process the business. The user can splice a new second target process information by selecting the highlighted part and selecting the part that is not highlighted. The spliced second target process information is the new business processing process defined by the user this time, which can be stored and processed. In this way, the processing process of the business can be operated in the manner of directly operating on the knowledge graph, which greatly facilitates the operation of the user.

[0074] In the scheme, after the knowledge graph is generated, the knowledge graph can be converted back to the original node information, content information and process information through a conversion process. The conversion process is entity-node information, attribute-content information and relationship-process information. After obtaining the node information, content information and process information, these information can be stored in a document, such as WORD.

[0075] In order to enable those skilled in the art to more clearly understand the technical solutions of the present application, the implementation process of the knowledge graph construction method of the present application will be described in detail below in conjunction with specific embodiments.

[0076] The present embodiment relates to a specific knowledge graph construction method, comprising the following steps:

[0077] Step S1: obtaining process information, which includes a plurality of business nodes related to the process business and a plurality of business content corresponding to the business nodes;

[0078] Step S2: determining a general business theme corresponding to the process according to the plurality of business content, wherein the general theme can be applied to different processes;

[0079] Step S3: determining the connection relationship of the plurality of business themes and the general theme;

[0080] Step S4: constructing a knowledge graph related to the process according to the determined connection relationship;

[0081] Step S5: the construction method is built in the form of "business node->entity, connection relationship->edge, business content->attribute";

[0082] Step S6: the general business theme can be extracted to quickly adapt to different process applications;

[0083] Step S7: the knowledge graph can be converted back to the process information in the form of a graph through "entity->business node, edge->connection relationship, attribute->business content".

[0084] The embodiment of the present application further provides a knowledge graph construction device. It should be noted that the knowledge graph construction device of the embodiment of the present application can be used to execute the method for constructing a knowledge graph provided by the embodiment of the present application. The device is used to realize the above-mentioned embodiment and preferred embodiment, and details are not repeated. As used below, the term "module" can be a combination of software and / or hardware that realizes a predetermined function. Although the device described in the following embodiment is preferably realized in software, realization in hardware or a combination of software and hardware is also possible and contemplated.

[0085] The knowledge graph construction device provided by the embodiment of the present application is introduced below.

[0086] Figure 3 FIG. 1 is a structural block diagram of a knowledge graph construction device according to the embodiment of the present application. As shown in FIG. 1, the device comprises: Figure 3

[0087] A first acquisition unit 10 is configured to acquire node information, wherein the node information is information of a service node for handling a service;

[0088] Specifically, when a user handles a service, multiple service nodes are often required for approval. For example, for a leave application of an enterprise, the personnel required for approval include the person himself / herself, a superior leader, and human resources. For a purchase order, the personnel required for approval include the person himself / herself, a superior leader, a salesperson, and a financial officer. For a leave application of a school, the personnel required for approval include the person himself / herself, a class teacher, and a student committee member. Therefore, different services correspond to different service nodes required.

[0089] Specifically, all service nodes required for handling a service can be input in advance to determine the service nodes required for handling the service, and then the node information of the service nodes is acquired.

[0090] A second acquisition unit 20 is configured to acquire content information, wherein the content information is information of a service content handled by the service node for handling the service;

[0091] Specifically, when a user handles a service, the service content handled by different service nodes is different. For example, for a leave application of an enterprise, the person himself / herself is responsible for filling out the leave application, a superior leader is responsible for approving the leave application, and human resources is responsible for recording attendance.

[0092] For example, for a purchase order, the person himself / herself is responsible for filling out the purchase order and purchase information, a superior leader is responsible for approving the purchase order, a salesperson is responsible for making an amount budget, and a financial officer is responsible for making a payment.

[0093] ​For example, for the school leave application, the person is responsible for filling out the leave application, the class teacher is responsible for approving the leave application, and the student representative is responsible for recording the number of absentees and the names of the absentees for the class roll call.

[0094] Specifically, the business content that each business node can handle can be input in advance to determine what business content each business node can handle, and then the information of the business content handled by the business node, i.e., the content information, is obtained.

[0095] The third obtaining unit 30 is configured to obtain process information, wherein the process information is information of an approval sequence of the business node for handling the business.

[0096] Specifically, the approval sequence of different businesses is different when a user handles the business. For example, for the leave application of an enterprise, after the person submits the leave application, the leave application is submitted to the superior leader, and after the superior leader approves it, the leave application is submitted to the human resources department. After the human resources department records the attendance, the process ends.

[0097] For example, for the purchase order, after the person submits the purchase order, the purchase order is submitted to the superior leader, and after the superior leader approves it, the purchase order is submitted to the sales department. After the sales department makes the budget for the purchase amount, the purchase order is submitted to the finance department. After the finance department makes the payment, the purchase order is submitted to the sales department, and the sales department is responsible for purchasing the goods.

[0098] For example, for the leave application of a school, after the person submits the leave application, the leave application is submitted to the class teacher, and after the class teacher approves it, the leave application is submitted to the student representative and the person. The student representative records the number of absentees and the actual number of absentees according to the leave application, and the person leaves the school according to the leave application approved by the class teacher.

[0099] Specifically, the approval sequence of multiple business nodes when handling the business can be input in advance, so that the process of handling the business can be determined, and then the process information is obtained.

[0100] The first processing unit 40 is configured to construct a knowledge graph according to the node information, the content information, and the process information, and display the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0101] Specifically, the entire process that needs to be gone through when handling the business can be displayed in the form of a knowledge graph, so that the process of handling the business can be visually displayed. The user can see the current process, the previous process, and the next process of handling the business, and even the entire process. Moreover, the user can click the knowledge graph to display the information of a certain node and the information of a certain business content.

[0102] Through the embodiment, the process of handling a service is displayed in the form of constructing a knowledge graph, and the process of handling a service can be visually displayed, so that a user can see the process of handling a service through the displayed knowledge graph, and the user experience is improved.

[0103] In the case that all the service handling has common features (the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the handled service), the same part can be extracted, and in the specific implementation process, the device further includes an extraction unit and a second processing unit. The extraction unit is configured to extract, from all the above process information, the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the handled service as general information after constructing the knowledge graph, wherein the general information includes a general name, general node information, general content information, and general process information, the general name and the general information are one-to-one corresponding, and the general information is suitable for all services. The second processing unit is configured to find the corresponding general information according to the general name in the case of adding a new service, and generate the process information of the new service according to at least the general information.

[0104] In the scheme, the part of the knowledge graph with the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the handled service can be extracted as general information, and the general information can be named as a general name. In this way, if a new service needs to be added, the general name can be directly searched to search for the general information, and there is no need to repeatedly select one by one, and the user experience is further improved.

[0105] Specifically, if there are multiple approved services, the specific approval process is as follows:

[0106] Service 1: A-B-C-D;

[0107] Service 2: A-B-C;

[0108] Service 3: B-C-D;

[0109] Service 4: B-C-B-A-B;

[0110] The above four services are all leave handling services, and the same process in the four services is B-C, so B-C is taken as general information and stored as a general name “leave handling service”. The general information can be searched directly through the general name, and then other nodes and services can be set based on the general information.

[0111] Of course, the stored general information can not be limited to one, but also multiple, for example, the leave business stores a general information, the procurement business stores a general information, and the cost package can also store a general information.

[0112] The flow information can be various, for the approval sequence, it can be sequential approval, series approval, parallel approval and the like, in the specific implementation process, the third acquisition unit includes a first acquisition module, a second acquisition module, a third acquisition module and a fourth acquisition module, the first acquisition module is used for acquiring first flow information, wherein the approval sequence of the first flow information is that the first business node is approved first, then the second business node is approved, and then the first business node is approved again; the second acquisition module is used for acquiring second flow information, wherein the approval sequence of the second flow information is that the first business node is approved first, then the second business node and the third business node are approved simultaneously, and then the fourth business node is approved; the third acquisition module is used for acquiring third flow information, wherein the approval sequence of the third flow information is that the first business node is approved first, then the second business node and the third business node are approved simultaneously, and then the fourth business node is approved; the fourth acquisition module is used for acquiring fourth flow information, wherein the approval sequence of the fourth flow information is that the first business node is approved first, then the second business node is approved, and then the third business node is approved.

[0113] In the scheme, the first flow information actually refers to a business that needs a certain business node to repeat the approval, and in the middle, it will also pass through other business nodes for approval, the second flow information actually refers to a business that needs two business nodes to be approved in parallel, the third flow information actually refers to a business that needs any one of the two parallel business nodes to be approved, and the fourth flow information actually refers to a series approval sequence. In this embodiment, multiple approval sequences are defined, and different approval sequences correspond to different flow information. In this way, with multiple flow information, the knowledge graph can be further constructed efficiently and accurately.

[0114] Specifically, in the case of multiple business nodes, the approval result can be determined as passed only after all the business nodes are approved. Of course, it is not limited to this way, and the approval result can be determined as passed only after a predetermined number of business nodes are approved. The predetermined number can be 1 / 2, 2 / 3, etc. Of course, different ways can be defined for different approved businesses. For example, according to the type of business, the approval process and the approval result are determined. If the business type is leave type, the corresponding approval process must pass the class teacher, and the approval result is determined as passed only if the class teacher agrees. If the business type is to purchase stationery, and the amount is less than the predetermined amount, the approval process is defined as being able to pass the superior leader or not, and the approval result is passed regardless of whether the superior leader agrees or not. Of course, for leave type, the approval process for different leave types is different. For example, if the number of leave days is less than or equal to two days, the approval of the class teacher is required. If the number of leave days is greater than two days and less than or equal to five days, the approval of the class teacher and the age director is required. If the number of leave days is greater than five days, the approval of the class teacher, the age director, and the school principal is required.

[0115] Of course, for defining the process information, the priority of the specific parameters can also be defined. For example, the level of business content is determined. If the business content is the highest level, the process of the highest level business content is processed first. If the business content is the ordinary level, the process of the ordinary level business content is processed after the highest level is processed.

[0116] Of course, for different types of businesses, the priority of the process can also be defined. For example, for enterprise users, if the business type is to entertain clients, the corresponding process information is the first level, and the approval process should be sales-department leader-department manager. If the business type is bidding, the corresponding process information is the second level, and the approval process should be sales-department leader-department manager-supervisor. If the department leader is subject to both approval processes, the business of entertaining clients will be displayed as the highest priority on the display interface and can be highlighted.

[0117] In order to update the knowledge graph when a new business needs to be added to the knowledge graph, the above-mentioned device of the present application further comprises a first receiving unit and a third processing unit. The first receiving unit is used to receive a first predetermined operation after the knowledge graph is constructed, wherein the first predetermined operation is an operation of modifying the knowledge graph. The third processing unit is used to update at least the node information and the approval order of the process information in response to the first predetermined operation, and update the knowledge graph to obtain an updated knowledge graph.

[0118] In the scheme, the knowledge graph can also be updated, and operation can be directly performed on the knowledge graph. This is a visual operation, for example, a new business node is created, so that the entity, attribute and relationship of the knowledge graph can be directly changed, and the user can directly see the change process, thereby further improving the user experience effect.

[0119] Specifically, if the knowledge graph is updated, it is actually equivalent to handling a business. After the user himself / herself submits an update business form and is approved by the superior and the superior superior, the user is allowed to update the knowledge graph. The updated knowledge graph can be normally used.

[0120] In order to facilitate the user to update the knowledge graph, the above-mentioned device of the present application further comprises a fourth processing unit and a fifth processing unit. The fourth processing unit is used to perform semantic analysis on the content of the new business when a new business is pre-added to the knowledge graph after the knowledge graph is constructed, determine the target business content corresponding to the new business, and calculate the similarity between the target business content of the new business and a plurality of content information. The fifth processing unit is used to determine that the content information with the highest similarity to the new business is the target content information, and highlight the process information and node information corresponding to the target content information in the knowledge graph.

[0121] In the scheme, when a new business needs to be added to the knowledge graph, the similarity between the new business and the original business can be analyzed since the original business has been pre-defined in the knowledge graph. The original business with the highest similarity to the new business is taken as the target business, and the corresponding target content information and process information are highlighted on the display interface, thereby facilitating the user to refer to and update the knowledge graph based on the highlighted nodes and processes.

[0122] Specifically, when a new business is pre-added to the knowledge graph, whether to go through the A node or the B node can be determined by manual operation, or the content can be determined by semantic analysis through an automatic manner, so that the closest one can be found from the stored content information, and it is determined whether to go through the A node or the B node according to the stored process.

[0123] Specifically, the process information, business node and business content of handling a certain business in the knowledge graph can be highlighted, so that the process of handling a certain business can be directly seen on a graph. Only a part of the knowledge graph is displayed. Of course, for the general part, it can also be directly highlighted and named, so that the knowledge graph can be directly queried. For example, the name is high-level handling department, and the corresponding business nodes are chairman and general manager. This general part can also be stored as a single knowledge graph and named.

[0124] If the user wants to newly input a business to the knowledge graph, but the user does not know the specific process sequence and the content that can be approved by the business node, the user can be guided to select the business node and the process through the question and answer pair. In some embodiments, the above device further includes a fourth acquisition unit and an execution unit. The fourth acquisition unit is configured to acquire a pre-stored question and answer pair before performing semantic analysis on the content of the new business to determine the target business content corresponding to the new business. The question and answer pair is a combination of one question corresponding to one answer. The execution unit is configured to execute the screening step at least once. The screening step is to display a question in the display interface and acquire a reply answer. The reply answer is an answer input into the display box. According to the reply answer, a target question and answer pair with a similarity greater than a similarity threshold is searched from a plurality of question and answer pairs, and the answer in the target question and answer pair is determined as the first target process information.

[0125] In this scheme, a plurality of question and answer pairs are pre-stored. By successively asking the user and acquiring the user's reply, the user can be guided to select the business node and the process of handling the business. Even if the user does not know how to fill in the business process, the user can be guided to set the business node and the process through the question and answer pair, thereby ensuring that the user experience is good.

[0126] For example, there are a plurality of question and answer pairs. First, ask the user "do you want to fill in a leave application form?" If the user replies "yes", continue to ask the user "are you an enterprise user or a school user?" If the user replies "enterprise user", the corresponding first target process information is determined as self-supervisor-human resources. If the user replies "no, it is a purchase order" when asking the user for the first time, continue to ask the user "do you want to purchase product A?" If the user replies "yes", the corresponding first target process information is determined as self-administration. If the user replies "no, want to purchase product B", the corresponding first target process information is self-supervisor-sales-finance-sales-self.

[0127] Of course, there are also some preset reverse rules when guiding the user to input the question, which can be set according to the priority of the parameter, or according to the importance of the parameter, specifically, a plurality of reverse rules can be set, and the customer can set (or other user), for example: 1, according to the number of established process weight to reverse, 2, according to the number of current user department process weight reverse, 3, give priority to general process, supplemented by specific process, and then according to their usage frequency reverse, 4, according to the importance priority of the established process reverse.

[0128] Specifically, for the knowledge graph, the text stored in the knowledge graph can also be processed by text alignment. A database can be introduced and put into the whole graph. The text feature vector in the text can be extracted, and the text feature vector can be scored. The scoring can be performed by using the AHP algorithm. In this way, a text scoring result can be obtained to determine the evaluation coefficient of each text.

[0129] The knowledge graph can be displayed on the display interface, and the user can directly perform addition, deletion, modification and query processing on the knowledge graph through clicking operation. In some embodiments, the above device further includes a second receiving unit, a sixth processing unit, a third receiving unit, a seventh processing unit, a fourth receiving unit and an eighth processing unit. The second receiving unit is used to highlight the process information and the node information corresponding to the target content information in the above knowledge graph, and then receive a second predetermined operation. The second predetermined operation is a selected operation on the highlighted process information and node information. The sixth processing unit is used to determine the selected process information as first initial process information and the selected node information as first initial node information in response to the second predetermined operation. The third receiving unit is used to receive a third predetermined operation. The third predetermined operation is a selected operation on the process information and node information without highlighting. The seventh processing unit is used to determine the selected process information as second initial process information and the selected node information as second initial node information in response to the third predetermined operation. The fourth receiving unit is used to receive a fourth predetermined operation. The fourth predetermined operation is used to represent the operation of fusing the first initial process information, the second initial process information, the first initial node information and the second initial node information. The eighth processing unit is used to generate second target process information in response to the fourth predetermined operation. The second target process information includes the first initial process information, the second initial process information, the first initial node information and the second initial node information.

[0130] In the scheme, in the case that the knowledge graph has been displayed in the display interface, part of the content in the knowledge graph is highlighted, and part of the content is not highlighted. The highlighting is for the convenience of the user to view, and the user can refer to the highlighted part to process the business. The user can splice a new second target process information by selecting the highlighted part and the part without highlighting. The spliced second target process information is the new business processing process defined by the user this time, and can be stored and processed. In this way, the processing process of the business can be operated in the manner of directly operating on the knowledge graph, which greatly facilitates the operation of the user.

[0131] In the scheme, after the knowledge graph is generated, the knowledge graph can be turned back to the original node information, content information and process information through a turning back process. The turning back process is entity-node information, attribute-content information and relationship-process information. After the node information, content information and process information are obtained, the information can be stored in a document, such as WORD.

[0132] The knowledge graph construction device includes a processor and a memory. The first acquisition unit, the second acquisition unit, the third acquisition unit and the first processing unit are stored in the memory as program units. The corresponding functions are realized by the processor executing the program units stored in the memory. The modules are located in the same processor. Alternatively, the modules are located in different processors in any combination.

[0133] The processor includes a core, and the core retrieves the corresponding program unit from the memory. The core can be set to one or more, and the experience effect of the user in processing the business in the prior art can be improved by adjusting the core parameters.

[0134] The memory can include a non-persistent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM). The memory includes at least one memory chip.

[0135] The embodiment of the application provides a computer readable storage medium. The computer readable storage medium includes a stored program. When the program runs, the device where the computer readable storage medium is located performs the knowledge graph construction method.

[0136] Specifically, the knowledge graph construction method includes:

[0137] In step S201, node information is acquired. The node information is the information of a business node of the business.

[0138] In step S202, content information is acquired, wherein the content information is information of a service content of the service node.

[0139] In step S203, process information is acquired, wherein the process information is information of an approval sequence of the service node.

[0140] In step S204, a knowledge graph is constructed according to the node information, the content information and the process information, and the knowledge graph is displayed on a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0141] The embodiment of the present application provides a processor, which is used for running a program, wherein the processor implements the construction method of the knowledge graph when the program is running.

[0142] Specifically, the construction method of the knowledge graph comprises:

[0143] In step S201, node information is acquired, wherein the node information is information of a service node.

[0144] In step S202, content information is acquired, wherein the content information is information of a service content of the service node.

[0145] In step S203, process information is acquired, wherein the process information is information of an approval sequence of the service node.

[0146] In step S204, a knowledge graph is constructed according to the node information, the content information and the process information, and the knowledge graph is displayed on a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0147] The present application also provides a construction system of a knowledge graph, comprising one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a construction method of the knowledge graph.

[0148] The embodiment of the present application provides a device, which comprises a processor, a memory and a program stored in the memory and capable of running on the processor, and the processor implements at least the following steps when the program is executed:

[0149] Step S201, acquiring node information, wherein the node information is information of a service node for handling a service;

[0150] Step S202, acquiring content information, wherein the content information is information of a service content handled by the service node for handling the service;

[0151] Step S203, acquiring process information, wherein the process information is information of an approval sequence of the service node for handling the service;

[0152] Step S204, constructing a knowledge graph according to the node information, the content information, and the process information, and displaying the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0153] The device herein can be a server, a PC, a PAD, a mobile phone, or the like.

[0154] The application further provides a computer program product adapted to execute a program comprising at least the following method steps when executed on a data processing device:

[0155] Step S201, acquiring node information, wherein the node information is information of a service node for handling a service;

[0156] Step S202, acquiring content information, wherein the content information is information of a service content handled by the service node for handling the service;

[0157] Step S203, acquiring process information, wherein the process information is information of an approval sequence of the service node for handling the service;

[0158] Step S204, constructing a knowledge graph according to the node information, the content information, and the process information, and displaying the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph.

[0159] It should be apparent to those skilled in the art that the modules or steps of the application described above can be implemented with a general purpose computer, and can be centralized in a single computer or distributed among a network of computers, and can be implemented with program code executable by a computer, and thus can be stored in a storage device and executed by a computer, and in some cases, the steps shown or described can be executed in a different order than shown or described, or can be implemented as separate integrated circuit modules or as a single integrated circuit module, and thus the application is not limited to any particular combination of hardware and software.

[0160] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) embodying computer readable program code.

[0161] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams.

[0162] The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams.

[0163] The flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products described herein can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams.Figure 1 one or more processes and / or functions specified in one or more blocks Figure 1 one or more processes and / or functions specified in one or more blocks

[0164] In one typical arrangement, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0165] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer readable media.

[0166] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0167] It should also be noted that the terms "comprising", "containing", or any other variant thereof, are intended to cover non-exclusive inclusion, so that processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device that includes the element.

[0168] From the above description, it can be seen that the above-mentioned embodiments of the present application achieve the following technical effects:

[0169] 1) The knowledge graph construction method of this application displays the business process by constructing a knowledge graph, which can visualize the business process. In this way, users can see the business process through the displayed knowledge graph, thereby improving the user experience.

[0170] 2) The knowledge graph construction device of this application displays the business process by constructing a knowledge graph, which can visualize the business process. In this way, users can see the business process through the displayed knowledge graph, thereby improving the user experience.

[0171] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for constructing a knowledge graph, characterized in that, The method comprises: acquiring node information, wherein the node information is information of a service node for handling a service; acquiring content information, wherein the content information is information of a service content handled by the service node for handling the service; acquiring process information, wherein the process information is information of an approval sequence of the service node for handling the service; constructing a knowledge graph according to the node information, the content information, and the process information, and displaying the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph, after the knowledge graph is constructed, the method further comprises: extracting, from all the process information, common information having the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of a handled service, wherein the common information comprises a common name, common node information, common content information, and common process information, the common name and the common information correspond to each other one by one, and the common information is suitable for all services; in the case of new service handling, the corresponding common information is found according to the common name, and the process information corresponding to the new service is generated at least according to the common information.

2. The method of claim 1, wherein, acquiring process information, comprising: acquiring first process information, wherein the approval sequence of the first process information is that the first service node is approved, then the second service node is approved, and then the first service node is approved again; acquiring second process information, wherein the approval sequence of the second process information is that the first service node is approved, then the second service node and the third service node are simultaneously approved, and then the fourth service node starts to be approved; acquiring third process information, wherein the approval sequence of the third process information is that the first service node is approved, then the second service node and the third service node are simultaneously approved, and then the fourth service node starts to be approved after the second service node is approved or the third service node is approved; acquiring fourth process information, wherein the approval sequence of the fourth process information is that the first service node is approved, then the second service node is approved, and then the third service node is approved.

3. The method of claim 1, wherein, after the knowledge graph is constructed, the method further comprises: receiving a first predetermined operation, wherein the first predetermined operation is an operation of modifying the knowledge graph; in response to the first predetermined operation, at least updating the node information and the approval sequence of the process information, and updating the knowledge graph to obtain an updated knowledge graph.

4. The method of claim 1, wherein, after the knowledge graph is constructed, the method further comprises: in the case of new service pre-added to the knowledge graph, performing semantic analysis on the content of the new service, determining target service content corresponding to the new service, and calculating the similarity between the target service content of the new service and a plurality of content information; determine the content information most similar to the new business as target content information, and highlight the process information and the node information corresponding to the target content information in the knowledge graph.

5. The method of claim 4, wherein, Before performing semantic analysis on the content of the new business to determine the target business content corresponding to the new business, the method further comprises: obtaining a pre-stored question and answer pair, wherein the question and answer pair is a combination of one question corresponding to one answer; performing a filtering step at least once, the filtering step being: displaying a question in the display interface and obtaining a reply answer, wherein the reply answer is an answer input into a display box, finding a target question and answer pair from a plurality of question and answer pairs according to the reply answer, the target question and answer pair having a similarity greater than a similarity threshold with the reply answer, and determining the answer in the target question and answer pair as first target process information.

6. The method of claim 4, wherein, After highlighting the process information and the node information corresponding to the target content information in the knowledge graph, the method further comprises: receiving a second predetermined operation, wherein the second predetermined operation is a selection operation on the highlighted process information and node information; in response to the second predetermined operation, determining the selected process information as first initial process information and the selected node information as first initial node information; receiving a third predetermined operation, wherein the third predetermined operation is a selection operation on the process information and node information that are not highlighted; in response to the third predetermined operation, determining the selected process information as second initial process information and the selected node information as second initial node information; receiving a fourth predetermined operation, wherein the fourth predetermined operation represents an operation of fusing the first initial process information, the second initial process information, the first initial node information, and the second initial node information; in response to the fourth predetermined operation, generating second target process information, wherein the second target process information includes the first initial process information, the second initial process information, the first initial node information, and the second initial node information. 7.A device for constructing a knowledge graph, characterized in that, comprises: a first obtaining unit configured to obtain node information, wherein the node information is information of a business node for handling a business; a second obtaining unit configured to obtain content information, wherein the content information is information of a business content handled by the business node for handling a business; a third obtaining unit configured to obtain process information, wherein the process information is information of an approval sequence of the business node for handling a business; a first processing unit configured to construct a knowledge graph according to the node information, the content information, and the process information, and display the knowledge graph in a display interface of a display device, wherein the node information corresponds to an entity of the knowledge graph, the content information corresponds to an attribute of the knowledge graph, and the process information corresponds to a relationship of the knowledge graph, The device also comprises an extraction unit and a second processing unit, the extraction unit is used for extracting, from all the process information, common information which has the same approval sequence, the same node information corresponding to the approval sequence, and the same content information of the business handled, wherein the common information comprises a common name, common node information, common content information, and common process information, the common name and the common information correspond one by one, and the common information is suitable for all businesses; the second processing unit is used for, in the case of new business handling, finding the corresponding common information according to the common name, and generating the process information corresponding to the new business according to at least the common information.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls the device where the computer readable storage medium is located to execute the knowledge graph construction method in any one of claims 1 to 6 when the program is running. 9.A system for constructing a knowledge graph, characterized in that, comprise: one or more processors, memories, and one or more programs, wherein the one or more programs are stored in the memories and configured to be executed by the one or more processors, and the one or more programs comprise a program for executing the knowledge graph construction method in any one of claims 1 to 6.

Images