CN111160847A - Method and device for processing flow information - Google Patents

Abstract

The invention discloses a method and a device for processing flow information, and relates to the technical field of computers. One embodiment of the method comprises: acquiring a plurality of pieces of process information, and constructing a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node; storing the knowledge-graph in a database. The method and the device can solve the technical problem of lack of reliable evaluation of the flow based on historical data.

Description

Method and device for processing flow information

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for processing flow information.

Background

At present, in the banking industry, due to the fact that products are various and service processes are complex, process optimization often depends on experience of service experts, and support of actual process operation data is lacked.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:

the business process model of the banking industry cannot be mapped, and the static knowledge of the process and the relationship among a plurality of processes are inconvenient to display. The relation between the processes depends on the expert knowledge of the business, and the relation between the processes cannot be analyzed from the perspective of big data; the process optimization depends on the experience of a service expert, and the mining analysis of actual operation data is lacked; the effectiveness of process optimization relies on human evaluation and lacks reliable evaluation based on historical data.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for processing flow information, so as to solve the technical problem of lack of reliable evaluation of a flow based on historical data.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method of processing flow information, including:

acquiring a plurality of pieces of process information, and constructing a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node;

storing the knowledge-graph in a database;

and training based on the knowledge graph to obtain a relation prediction model, and calculating index data of the flow to be measured by adopting the relation prediction model.

Optionally, constructing a knowledge graph according to the pieces of process information includes:

calculating the similarity among the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity more than or equal to a first similarity threshold into a flow group; wherein each process group comprises at least one process;

and for each process group, fusing the processes in the process group so as to construct a knowledge graph.

Optionally, calculating a similarity between the processes according to each process node of each piece of process information and attribute data of each process node, including:

respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node;

and respectively calculating the similarity between vectors corresponding to any two pieces of flow information.

Optionally, fusing the processes in the process group to construct a knowledge graph, including:

and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node.

Optionally, training based on the knowledge graph to obtain a relationship prediction model, including:

taking the entities and the relations in the knowledge graph as items to carry out dimension reduction to obtain a graph structure consisting of the items;

performing shorthand walking on the graph structure by using a Deepwalk algorithm to obtain an item sequence;

inputting the item sequence into a word vector calculation tool to obtain word vector characteristics corresponding to the item sequence;

and inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model.

In addition, according to another aspect of the embodiments of the present invention, there is provided an apparatus for processing flow information, including:

the construction module is used for acquiring a plurality of pieces of process information and constructing a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node;

the storage module is used for storing the knowledge graph into a database;

and the calculation module is used for training based on the knowledge graph to obtain a relation prediction model, and calculating index data of the process to be measured by adopting the relation prediction model.

Optionally, the building module is further configured to:

calculating the similarity among the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity more than or equal to a first similarity threshold into a flow group; wherein each process group comprises at least one process;

and for each process group, fusing the processes in the process group so as to construct a knowledge graph.

Optionally, the building module is further configured to:

respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node;

and respectively calculating the similarity between vectors corresponding to any two pieces of flow information.

Optionally, the building module is further configured to:

and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node.

Optionally, the computing module is further configured to:

taking the entities and the relations in the knowledge graph as items to carry out dimension reduction to obtain a graph structure consisting of the items;

performing shorthand walking on the graph structure by using a Deepwalk algorithm to obtain an item sequence;

inputting the item sequence into a word vector calculation tool to obtain word vector characteristics corresponding to the item sequence;

and inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any of the embodiments described above.

According to another aspect of the embodiments of the present invention, there is also provided a computer readable medium, on which a computer program is stored, which when executed by a processor implements the method of any of the above embodiments.

One embodiment of the above invention has the following advantages or benefits: because the technical means of constructing the knowledge graph according to a plurality of pieces of process information, training on the basis of the knowledge graph to obtain the relation prediction model and calculating the index data of the process to be tested by adopting the relation prediction model is adopted, the technical problem that the process is not reliably evaluated on the basis of historical data in the prior art is solved. According to the embodiment of the invention, the knowledge graph is constructed according to the process information, so that the relationship between the processes can be displayed in the form of the graph, the propagation and sharing of business process knowledge are facilitated, the relationship between the processes is analyzed from the data perspective, the process optimization points are excavated, and the process quality and efficiency are improved; the method adopts a graph convolution neural network algorithm and a graph calculation mining algorithm, combines the operation data of the business process, and trains a process quality model, a cost model, an efficiency model and a heat model, thereby predicting each index data of the process, providing decision basis for resource allocation, realizing resource optimal configuration and improving the customer experience.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

FIG. 1 is a schematic diagram of a main flow of a method of processing flow information according to an embodiment of the invention;

FIG. 2 is a schematic diagram of a process flow according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a knowledge-graph according to an embodiment of the invention;

FIG. 4 is a schematic view of a main flow of a method of processing flow information according to a referential embodiment of the present invention;

FIG. 5 is a schematic diagram of the main blocks of an apparatus for processing flow information according to an embodiment of the present invention;

FIG. 6 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 7 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic diagram of a main flow of a method of processing flow information according to an embodiment of the present invention. As an embodiment of the present invention, as shown in fig. 1, the method for processing flow information may include:

step 101, acquiring a plurality of pieces of process information, and constructing a knowledge graph according to the plurality of pieces of process information.

Optionally, in an embodiment of the present invention, an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node. Optionally, the process used for constructing the knowledge graph may be each business process in the banking system, as shown in fig. 2, each process node in the process includes automatic entry, primary entry, secondary entry, manual entry, accounting, and the like. Each flow node has corresponding attribute data. Specifically, the node information collector may collect operation-state flow information (including structured information and unstructured information) as source data of a flow knowledge graph, and then, the SQL knowledge extraction method and the NLP knowledge extraction method may process the source data to obtain entities, relationships, attribute data, and the like, where an entity refers to a flow link and information of an attribute data flow link, and a relationship is a time sequence, a dependency, and the like between the flow links, so as to construct the flow knowledge graph, as shown in fig. 3.

Optionally, constructing a knowledge graph according to the pieces of process information includes: calculating the similarity among the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity more than or equal to a first similarity threshold into a flow group; wherein each process group comprises at least one process; and for each process group, fusing the processes in the process group so as to construct a knowledge graph. In the embodiment of the present invention, for each process, similarity between each process is first calculated, the processes with the similarity greater than or equal to a preset first similarity threshold are divided into a process group, the similarity of each process in each process group is higher, and each process in the group may be constructed as a knowledge graph, as shown in fig. 3.

Optionally, calculating a similarity between the processes according to each process node of each piece of process information and attribute data of each process node, including: respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node; and respectively calculating the similarity between vectors corresponding to any two pieces of flow information. The similarity between each process can be calculated from two angles of process nodes and attribute data respectively, the process node angle is mainly used for constructing onehot vectors, the calculation method of the attribute data angle is similar, and only the actual attribute value is adopted during vector construction. The similarity between vectors can be calculated by cosine similarity or the like.

For example: now, assume that the private bank card opening process includes: the method comprises six process nodes of customer information acquisition, customer information verification, signing, card making, mailing, feedback and the like, wherein the credit card opening process comprises the following steps: the system comprises six nodes, namely client information acquisition, client information verification, limit verification, signing, card making, mailing and the like. These two processes involve 7 nodes in total: the method comprises the steps of customer information acquisition, customer information verification, limit verification, signing, card making, mailing and feedback, wherein an onehot vector is determined to be 7-dimensional, a private bank card onehot vector is (1,1,0,1,1,1,1), a credit card onehot vector is (1,1,1,1,1,1,0), and the cosine similarity is calculated to obtain 0.83.

Optionally, fusing the processes in the process group to construct a knowledge graph, including: and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node. In the embodiment of the invention, the similarity among the process nodes can adopt a calculation method of attribute data angles in similar process similarities, and the similarity can be combined after reaching a specified threshold. In addition, the nodes can combine the map information of the preposed nodes, the subsequent nodes, the node in degree, the node out degree and the like, enrich attribute data and bring the attribute data into similarity calculation.

For example: the method is characterized in that a private bank card making and a credit card making are assumed to be two different nodes defined, the attributes of the two nodes comprise an execution mechanism, average time consumption, key technical components and the like, only one node is connected before and after the two nodes, the front node of the credit card making carries out excessive credit check, and the rear node of the private bank card making carries out excessive feedback. In conclusion, the similarity between the two is calculated to be high and can be combined.

Step 102, storing the knowledge-graph in a database.

After the knowledge graph is constructed through step 101, the knowledge graph is stored in a database. The node IDs in the knowledge graph can be stored in a relational database, the relational IDs in the knowledge graph can be stored in a non-relational database, and the node IDs and the relational IDs are associated so as to relieve the storage and calculation pressure of a graph database. Optionally, the number defined by each process is stored as a common attribute or a tag of all process nodes in the process map, which facilitates fast retrieval of the entire process map.

And 103, training based on the knowledge graph to obtain a relation prediction model, and calculating index data of the to-be-measured process by using the relation prediction model.

In this step, the flow data may be processed and trained based on graph computation mining and graph deep learning to obtain a relational prediction model. Specifically, nodes, node relations and attributes required by model training are extracted from the knowledge graph to serve as source data, valuable information for flow optimization is mined from the source data, and the source data are provided for the model to be trained after flows such as data cleaning, feature derivation and format conversion. Graph computation mining is used for relation mining among the processes, and graph deep learning is used for prediction of process indexes such as process completion time, calling times and the like.

Optionally, training based on the knowledge graph to obtain a relationship prediction model, including: taking the entities and the relations in the knowledge graph as items to carry out dimension reduction to obtain a graph structure consisting of the items; performing shorthand walking on the graph structure by using a Deepwalk algorithm to obtain an item sequence; inputting the item sequence into a word vector calculation tool to obtain word vector characteristics corresponding to the item sequence; and inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model. Alternatively, the word vector computation tool may be word2vec, by which the embedding of the item sequence may be obtained. Alternatively, the convolutional neural network may be a graph convolutional neural network (GCN) or a graph attention neural network (GAT), etc.

The staff can continuously optimize the existing flow, the optimized flow is used as the flow to be tested and is input into the relation prediction model to obtain various index data of the flow to be tested, and therefore a basis is provided for flow optimization.

In the step, various index data of the process to be tested can be calculated based on the relation prediction model obtained by training, so that the purposes of process association analysis, relation mining, process prediction and the like are achieved. Alternatively, the index data may be an average elapsed time, the number of required persons, a failure rate, an evaluation score, or other dimensions. Therefore, these index data are also provided for each process as a training sample, and it should be noted that the training samples are different and the models obtained by training are also different due to the difference in predicted index data. For example, the quality, efficiency, cost, heat, completion time, etc. of the process can be predicted, and a basis is provided for resource optimization configuration.

According to the various embodiments, the technical means that the knowledge graph is constructed according to the plurality of pieces of process information, the relation prediction model is obtained based on the knowledge graph training, and the index data of the process to be tested is calculated by adopting the relation prediction model solves the technical problem that the process is not reliably evaluated based on historical data in the prior art. According to the embodiment of the invention, the knowledge graph is constructed according to the process information, so that the relationship between the processes can be displayed in the form of the graph, the propagation and sharing of business process knowledge are facilitated, the relationship between the processes is analyzed from the data perspective, the process optimization points are excavated, and the process quality and efficiency are improved; the method adopts a graph convolution neural network algorithm and a graph calculation mining algorithm, combines the operation data of the business process, and trains a process quality model, a cost model, an efficiency model and a heat model, thereby predicting each index data of the process, providing decision basis for resource allocation, realizing resource optimal configuration and improving the customer experience.

Fig. 4 is a schematic diagram of a main flow of a method of processing flow information according to a referential embodiment of the present invention. As another embodiment of the present invention, as shown in fig. 4, the method for processing flow information may include:

step 401, calculating the similarity between the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity greater than or equal to the first similarity threshold into a flow group. Wherein each flow group comprises at least one flow.

Optionally, step 401 may comprise: respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node; and respectively calculating the similarity between vectors corresponding to any two pieces of flow information. In the embodiment of the invention, for each process, the similarity between the processes is respectively calculated, the processes with the similarity greater than or equal to the preset first similarity threshold are divided into a process group, the similarity of each process in each process group is higher, and each process in the group can be constructed into a knowledge graph.

Optionally, calculating a similarity between the processes according to each process node of each piece of process information and attribute data of each process node, including: respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node; and respectively calculating the similarity between vectors corresponding to any two pieces of flow information. The similarity between each process can be calculated from two angles of process nodes and attribute data respectively, the process node angle is mainly used for constructing onehot vectors, the calculation method of the attribute data angle is similar, and only the actual attribute value is adopted during vector construction. The similarity between vectors can be calculated by cosine similarity or the like.

And 402, fusing the flows in the flow groups for each flow group, so as to construct a knowledge graph.

Optionally, step 402 may include: and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node. And calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node. In the embodiment of the invention, the similarity among the process nodes can adopt a calculation method of attribute data angles in similar process similarities, and the similarity can be combined after reaching a specified threshold. In addition, the nodes can combine the map information of the preposed nodes, the subsequent nodes, the node in degree, the node out degree and the like, enrich attribute data and bring the attribute data into similarity calculation.

Step 403, storing the knowledge graph in a database.

The node IDs in the knowledge graph can be stored in a relational database, the relational IDs in the knowledge graph can be stored in a non-relational database, and the node IDs and the relational IDs are associated to relieve the storage and calculation pressure of a graph database.

And step 404, using the entities and the relations in the knowledge graph as items to perform dimension reduction, and obtaining a graph structure consisting of the items.

And 405, performing shorthand walk on the graph structure by using a Deepwalk algorithm to obtain an item sequence.

Step 406, inputting the item sequence into a word vector calculation tool to obtain a word vector feature corresponding to the item sequence.

And 407, inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model.

And step 408, calculating index data of the process to be measured by using the relation prediction model.

The staff can continuously optimize the existing flow, the optimized flow is used as the flow to be tested and is input into the relation prediction model to obtain various index data of the flow to be tested, and therefore a basis is provided for flow optimization. The index data can be dimensions such as average time consumption, number of required personnel, failure rate, heat, cost, completion time, evaluation score and the like.

In addition, in one embodiment of the present invention, the detailed implementation of the method for processing flow information is described in detail in the above-mentioned method for processing flow information, and therefore the repeated content is not described again.

Fig. 5 is a schematic diagram of main blocks of an apparatus for processing flow information according to an embodiment of the present invention, and as shown in fig. 5, theapparatus 500 for processing flow information includes aconstruction module 501, astorage module 502, and acalculation module 503. Theconstruction module 501 is configured to obtain a plurality of pieces of process information, and construct a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node; thestorage module 502 is used for storing the knowledge graph into a database; thecalculation module 503 is configured to obtain a relationship prediction model based on the knowledge graph training, and calculate index data of the process to be measured by using the relationship prediction model.

Optionally, thebuilding module 501 is further configured to:

calculating the similarity among the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity more than or equal to a first similarity threshold into a flow group; wherein each process group comprises at least one process;

and for each process group, fusing the processes in the process group so as to construct a knowledge graph.

Optionally, thebuilding module 501 is further configured to:

respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node;

and respectively calculating the similarity between vectors corresponding to any two pieces of flow information.

Optionally, thebuilding module 501 is further configured to:

and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node.

Optionally, the calculatingmodule 503 is further configured to:

taking the entities and the relations in the knowledge graph as items to carry out dimension reduction to obtain a graph structure consisting of the items;

performing shorthand walking on the graph structure by using a Deepwalk algorithm to obtain an item sequence;

inputting the item sequence into a word vector calculation tool to obtain word vector characteristics corresponding to the item sequence;

and inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model.

According to the various embodiments, the technical means that the knowledge graph is constructed according to the plurality of pieces of process information, the relation prediction model is obtained based on the knowledge graph training, and the index data of the process to be tested is calculated by adopting the relation prediction model solves the technical problem that the process is not reliably evaluated based on historical data in the prior art. According to the embodiment of the invention, the knowledge graph is constructed according to the process information, so that the relationship between the processes can be displayed in the form of the graph, the propagation and sharing of business process knowledge are facilitated, the relationship between the processes is analyzed from the data perspective, the process optimization points are excavated, and the process quality and efficiency are improved; the method adopts a graph convolution neural network algorithm and a graph calculation mining algorithm, combines the operation data of the business process, and trains a process quality model, a cost model, an efficiency model and a heat model, thereby predicting each index data of the process, providing decision basis for resource allocation, realizing resource optimal configuration and improving the customer experience.

It should be noted that, in the implementation of the apparatus for processing flow information according to the present invention, the above method for processing flow information has been described in detail, and therefore, the repeated description is omitted here.

Fig. 6 illustrates anexemplary system architecture 600 of a method of processing flow information or an apparatus for processing flow information to which embodiments of the present invention may be applied.

As shown in fig. 6, thesystem architecture 600 may includeterminal devices 601, 602, 603, anetwork 604, and aserver 605. Thenetwork 604 serves to provide a medium for communication links between theterminal devices 601, 602, 603 and theserver 605.Network 604 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

A user may use theterminal devices 601, 602, 603 to interact with theserver 605 via thenetwork 604 to receive or send messages or the like. Theterminal devices 601, 602, 603 may have installed thereon various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

Theterminal devices 601, 602, 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

Theserver 605 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using theterminal devices 601, 602, 603. The background management server may analyze and otherwise process the received data such as the item information query request, and feed back a processing result (for example, target push information, item information — just an example) to the terminal device.

It should be noted that the method for processing the flow information provided by the embodiment of the present invention is generally executed by theserver 605, and accordingly, the apparatus for processing the flow information is generally disposed in theserver 605. The method for processing the flow information provided by the embodiment of the present invention may also be executed by theterminal devices 601, 602, and 603, and accordingly, the apparatus for processing the flow information may be disposed in theterminal devices 601, 602, and 603.

It should be understood that the number of terminal devices, networks, and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 7, shown is a block diagram of acomputer system 700 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 7, thecomputer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from astorage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data necessary for the operation of thesystem 700 are also stored. TheCPU 701, theROM 702, and the RAM703 are connected to each other via abus 704. An input/output (I/O)interface 705 is also connected tobus 704.

The following components are connected to the I/O interface 705: aninput portion 706 including a keyboard, a mouse, and the like; anoutput section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; astorage section 708 including a hard disk and the like; and acommunication section 709 including a network interface card such as a LAN card, a modem, or the like. Thecommunication section 709 performs communication processing via a network such as the internet. Adrive 710 is also connected to the I/O interface 705 as needed. Aremovable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on thedrive 710 as necessary, so that a computer program read out therefrom is mounted into thestorage section 708 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through thecommunication section 709, and/or installed from theremovable medium 711. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 701.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer programs according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a building module, a storage module, and a computing module, where the names of the modules do not in some way constitute a limitation on the modules themselves.

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring a plurality of pieces of process information, and constructing a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node; storing the knowledge-graph in a database; and training based on the knowledge graph to obtain a relation prediction model, and calculating index data of the flow to be measured by adopting the relation prediction model.

According to the technical scheme of the embodiment of the invention, because the technical means of constructing the knowledge graph according to a plurality of pieces of process information, training based on the knowledge graph to obtain the relation prediction model and calculating the index data of the process to be tested by adopting the relation prediction model is adopted, the technical problem that the process is lack of reliable evaluation based on historical data in the prior art is solved. According to the embodiment of the invention, the knowledge graph is constructed according to the process information, so that the relationship between the processes can be displayed in the form of the graph, the propagation and sharing of business process knowledge are facilitated, the relationship between the processes is analyzed from the data perspective, the process optimization points are excavated, and the process quality and efficiency are improved; the method adopts a graph convolution neural network algorithm and a graph calculation mining algorithm, combines the operation data of the business process, and trains a process quality model, a cost model, an efficiency model and a heat model, thereby predicting each index data of the process, providing decision basis for resource allocation, realizing resource optimal configuration and improving the customer experience.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (12)

1. A method for processing flow information, comprising:

acquiring a plurality of pieces of process information, and constructing a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node;

storing the knowledge-graph in a database;

and training based on the knowledge graph to obtain a relation prediction model, and calculating index data of the flow to be measured by adopting the relation prediction model.

2. The method of claim 1, wherein constructing a knowledge graph from the plurality of pieces of process information comprises:

calculating the similarity among the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity more than or equal to a first similarity threshold into a flow group; wherein each process group comprises at least one process;

and for each process group, fusing the processes in the process group so as to construct a knowledge graph.

3. The method of claim 2, wherein calculating the similarity between the processes according to the process nodes of each piece of process information and the attribute data of the process nodes comprises:

respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node;

and respectively calculating the similarity between vectors corresponding to any two pieces of flow information.

4. The method of claim 2, wherein fusing the processes in the process group to construct a knowledge graph comprises:

and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node.

5. The method of claim 1, wherein training based on the knowledge-graph results in a relational prediction model comprising:

taking the entities and the relations in the knowledge graph as items to carry out dimension reduction to obtain a graph structure consisting of the items;

performing shorthand walking on the graph structure by using a Deepwalk algorithm to obtain an item sequence;

inputting the item sequence into a word vector calculation tool to obtain word vector characteristics corresponding to the item sequence;

and inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model.

6. An apparatus for processing flow information, comprising:

the construction module is used for acquiring a plurality of pieces of process information and constructing a knowledge graph according to the plurality of pieces of process information; wherein an entity in the knowledge graph represents a process node, and an attribute of the entity represents attribute data of the process node;

the storage module is used for storing the knowledge graph into a database;

and the calculation module is used for training based on the knowledge graph to obtain a relation prediction model, and calculating index data of the process to be measured by adopting the relation prediction model.

7. The apparatus of claim 6, wherein the build module is further configured to:

calculating the similarity among the flows according to each flow node of each piece of flow information and the attribute data of each flow node, and dividing the flows with the similarity more than or equal to a first similarity threshold into a flow group; wherein each process group comprises at least one process;

and for each process group, fusing the processes in the process group so as to construct a knowledge graph.

8. The apparatus of claim 7, wherein the build module is further configured to:

respectively constructing a vector corresponding to each piece of process information according to each process node of each piece of process information and attribute data of each process node;

and respectively calculating the similarity between vectors corresponding to any two pieces of flow information.

9. The apparatus of claim 7, wherein the build module is further configured to:

and calculating the similarity between the attribute data of any two process nodes, and if the similarity is greater than a second similarity threshold, fusing the two process nodes into one process node.

10. The apparatus of claim 6, wherein the computing module is further configured to:

taking the entities and the relations in the knowledge graph as items to carry out dimension reduction to obtain a graph structure consisting of the items;

performing shorthand walking on the graph structure by using a Deepwalk algorithm to obtain an item sequence;

inputting the item sequence into a word vector calculation tool to obtain word vector characteristics corresponding to the item sequence;

and inputting the word vector characteristics into a convolutional neural network, and training to obtain a relation prediction model.

11. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.

12. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-5.

Images