CN113609271A

CN113609271A - Service processing method, device and equipment based on knowledge graph and storage medium

Info

Publication number: CN113609271A
Application number: CN202110920537.XA
Authority: CN
Inventors: 吴辰侣
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-08-11
Filing date: 2021-08-11
Publication date: 2021-11-05
Anticipated expiration: 2041-08-11
Also published as: CN113609271B

Abstract

The embodiment of the application discloses a service processing method, a device, equipment and a storage medium based on a knowledge graph, which comprises the following steps: acquiring business consultation data input by a user, and determining a target consultation business and a target consultation dimension of the business consultation data; acquiring a knowledge graph associated with the target consulting service, and determining primary associated information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension; determining secondary associated information of the target consultation service in the knowledge graph based on the target consultation service and the associated service; and determining the primary associated information and the secondary associated information as associated client service information of the target consultation service, and outputting the associated client service information to a user operation interface of a client service system. By adopting the embodiment of the application, the service efficiency of the customer service system can be improved, and the user experience is optimized.

Description

Service processing method, device and equipment based on knowledge graph and storage medium

Technical Field

The present application relates to the field of artificial intelligence, and in particular, to a service processing method, apparatus, device, and storage medium based on a knowledge graph.

Background

With the development of the technology in the field of artificial intelligence, more and more enterprises provide information for users through an online customer service system, including the customer service explaining the business consulted by the users, and provide associated information on the basis of the business consulted by the users so as to continuously introduce the users. The related information is usually provided by depending on the experience of the staff, and the experienced staff can quickly explain the service consulted by the user and introduce the related information more relevant to the service for the client. However, the method too depends on the experience of the workers, and for the workers with insufficient experience, the method also has certain limitations, low efficiency and poor applicability.

Disclosure of Invention

The embodiment of the application provides a service processing method, a service processing device, service processing equipment and a storage medium based on a knowledge graph, which can improve the service efficiency of a customer service system and optimize user experience.

In a first aspect, an embodiment of the present application provides a service processing method based on a knowledge graph, where the method includes:

acquiring business consultation data input by a user, and determining target consultation business and target consultation dimensionality of the business consultation data, wherein the target consultation dimensionality corresponds to the target consultation business one to one;

acquiring a knowledge graph associated with the target consulting service, and determining primary associated information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension, wherein the primary associated information of the target consulting service comprises a target consulting dimension characteristic corresponding to the target consulting dimension of the target consulting service, an associated consulting dimension characteristic corresponding to the associated consulting dimension of the target consulting service, and an associated service of the target consulting service, and the dimension characteristic corresponding to the target consulting dimension of the associated service is the same as the target consulting dimension characteristic corresponding to the target consulting dimension of the target consulting service;

determining a difference dimension of the target consulting service and the associated service in the knowledge graph based on the target consulting service and the associated service, and determining a difference dimension characteristic corresponding to the difference dimension of the target consulting service and a difference dimension characteristic corresponding to the associated service in the difference dimension as secondary associated information of the target consulting service;

and determining the primary associated information and the secondary associated information as associated client service information of the target consultation service, and outputting the associated client service information to a user operation interface of the client service system.

In the embodiment of the application, the terminal device may obtain the service consultation data input by the user, and determine the target consultation service and the target consultation dimension of the service consultation data, that is, determine which aspect of the service information the user wants to query. The terminal device may obtain a knowledge graph associated with the target counseling service (i.e., a knowledge graph in the field of the target counseling service), and determine primary associated information and secondary associated information corresponding to the target counseling service in the knowledge graph based on the target counseling service. Here, the primary associated information of the target counseling service may be a set of information that the user may consult after consulting the target counseling service in the user question-answering habit (i.e., dimensional characteristics of the target counseling service in other dimensions and associated services of the target counseling service). Here, the secondary associated information of the target counseling service is used to explain the difference between the target counseling service and the related service. The terminal equipment can obtain the associated client service information of the target consultation service according to the primary associated information of the target consultation service and the secondary associated information of the target consultation service, and output the associated client service information of the target consultation service to a user operation interface of the client service system, so that the user experience is optimized, and the service efficiency of the client service system is improved.

With reference to the first aspect, in a possible implementation manner, before the determining, in the knowledge graph, primary association information of the target consulting service based on the target consulting service and the target consulting dimension, the method further includes:

acquiring a plurality of training corpora to be labeled from a service consultation database of the customer service system;

performing semantic annotation on the plurality of training corpuses to be annotated to obtain a plurality of annotated training corpuses, wherein the annotated training corpuses comprise training service information and associated training service information associated with the training service information;

and constructing the knowledge graph based on each training service information and the associated training service information of each training service information.

With reference to the first aspect, in a possible implementation manner, the constructing the knowledge graph based on the training service information and the associated training service information of the training service information includes:

dividing each training service information and the associated training service information of each training service information according to a format of service-dimension characteristics to obtain a training triple corresponding to each training service information and an associated training triple corresponding to each associated training service information, wherein the training triples and the associated training triples are triples, and one triple comprises a service, a dimension and dimension characteristics of the service in the dimension;

and constructing the knowledge graph based on each training triplet and the associated training triplet of each training triplet.

With reference to the first aspect, in a possible implementation manner, the constructing the knowledge graph based on the respective training triples and the associated training triples of the respective training triples includes:

determining the service and dimension characteristics in each training triplet and the service and dimension characteristics in the associated training triples of each training triplet as nodes in the knowledge graph;

determining the dimensions in the training triples and the dimensions in the associated training triples of the training triples as the node connection relation in the knowledge graph;

and connecting the nodes of the knowledge graph according to the node connection relation of the knowledge graph to obtain the knowledge graph.

In this embodiment of the application, the terminal device may obtain a plurality of training corpora to be labeled from a service consulting database of the customer service system, divide each training service information and associated training service information associated with the training service information according to a format of service-dimension characteristics to obtain a training triplet corresponding to each training service information and an associated training triplet corresponding to each associated training service information, and further construct a knowledge graph based on the training triplet corresponding to each training service information and the associated training triplet corresponding to each associated training service information. Here, the terminal device may determine the service and the dimension characteristics in each training triplet, and the service and the dimension characteristics in the associated training triplet of each training triplet as nodes in the knowledge graph, and may also determine the dimensions in each training triplet, and the dimensions in the associated training triplet of each training triplet as node connection relationships in the knowledge graph, and connect the nodes of the knowledge graph according to the node connection relationships of the knowledge graph to obtain the knowledge graph, so that the knowledge graph better fits the use habits of users, optimizes the user experience, and improves the question-answering efficiency of the customer service system.

With reference to the first aspect, in one possible implementation, the method further includes:

respectively counting the occurrence times of the training triples and the associated training triples of the training triples in the training corpus to obtain the weight of the nodes in the knowledge graph;

respectively counting the times of the training triples and the times of the associated training triples of the training triples appearing in the same training corpus to obtain the weight of the node connection relation in the knowledge graph;

and constructing the knowledge graph based on the weight of the nodes in the knowledge graph and the weight of the connection relation of the nodes in the knowledge graph.

In the embodiment of the application, the terminal device may count the occurrence times of each training triplet and the associated training triplet of each training triplet in the training corpus to obtain the weight of the node in the knowledge graph, and may also count the occurrence times of each training triplet and the associated training triplet of each training triplet in the plurality of labeled training corpora in the same training corpus to obtain the weight of the node connection relationship in the knowledge graph, and construct the knowledge graph based on the weight of the node in the knowledge graph and the weight of the node connection relationship in the knowledge graph, so that the knowledge graph better fits the use habit of the user, optimizes the user experience, and improves the question-answer efficiency of the customer service system.

With reference to the first aspect, in a possible implementation manner, the acquiring business consultation data input by a user and determining a target consultation service of the business consultation data and a target consultation dimension of the target consultation service includes:

acquiring business consultation data input by a user, and judging the data type of the business consultation data, wherein the data type comprises at least one of audio data, video data, picture data or character data;

when the data type of the business consultation data is audio data or video data, converting the business consultation data into the business consultation data of a text data type through voice to text conversion;

when the data type of the business consultation data is picture data, converting the business consultation data into the business consultation data of a character data type through character recognition;

and performing semantic analysis on the service consultation data of the text data type to obtain a target consultation service corresponding to the service consultation data of the text data type and a target consultation dimension of the target consultation service.

In the embodiment of the application, the terminal device can convert the service consultation data of different data types into the service consultation data of the text data type, and performs semantic analysis on the service consultation data of the text data type to obtain the target consultation service corresponding to the service consultation data of the text data type and the target consultation dimension of the target consultation service, so that the type of the service consultation data applicable to the customer service system is increased, and the applicability of the system is improved.

With reference to the first aspect, in a possible implementation manner, the determining, in the knowledge graph, primary association information of the target consulting service based on the target consulting service and the target consulting dimension includes:

determining a target triple corresponding to the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension of the target consulting service, and determining the dimension characteristic in the target triple as the target consulting dimension characteristic corresponding to the target consulting service in the target consulting dimension;

determining a service association triple associated with the target consulting service in the knowledge graph based on the target consulting service, and determining an associated consulting dimension characteristic of the target consulting service in an associated consulting dimension associated with the target consulting service based on the dimension and the dimension characteristic in the service association triple;

and determining a feature association triple associated with the target consulting dimension characteristic in the knowledge graph based on the target consulting dimension of the target consulting service and the target consulting dimension characteristic, and determining an associated service of the target consulting service based on the service in the feature association triple.

In the embodiment of the application, the terminal device can determine a target triple corresponding to the target consultation service, an associated triple associated with the target consultation service and a feature associated triple associated with the target consultation dimension characteristic in the knowledge map, so as to obtain the target consultation dimension characteristic corresponding to the target consultation dimension of the target consultation service, the associated consultation dimension characteristic of the target consultation service in the associated consultation dimension and the associated service of the target consultation service, and further obtain primary associated information of the target consultation service, so that the primary associated information of the target consultation service obtained by the terminal device is more comprehensive, the user experience is optimized, and the service efficiency of the client service system is improved.

In a second aspect, an embodiment of the present application provides a service processing apparatus based on a knowledge graph, where the apparatus includes:

the service determining module is used for acquiring service consultation data input by a user and determining target consultation service and target consultation dimension of the service consultation data, wherein the target consultation dimension corresponds to the target consultation service one to one;

a primary information association module, configured to obtain a knowledge graph associated with the target consulting service, and determine primary association information of the target consulting service in the knowledge graph based on the target consulting service and a target consulting dimension of the target consulting service, where the primary association information of the target consulting service includes a target consulting dimension feature corresponding to the target consulting service in the target consulting dimension, an associated consulting dimension feature corresponding to the associated consulting dimension associated with the target consulting service, and an associated service of the target consulting service, and a dimension feature corresponding to the associated service in the target consulting dimension is the same as a target consulting dimension feature corresponding to the target consulting service in the target consulting dimension;

a secondary information correlation module, configured to determine, based on the target consulting service and the associated service, a difference dimension between the target consulting service and the associated service in the knowledge graph, and determine a difference dimension feature corresponding to the difference dimension of the target consulting service and a difference dimension feature corresponding to the associated service in the difference dimension, so as to serve as secondary correlation information of the target consulting service;

and the association display module is used for determining the primary association information and the secondary association information as the associated client service information of the target consultation service and outputting the associated client service information to a user operation interface of a client service system.

In a third aspect, an embodiment of the present application provides a terminal device, where the terminal device includes a processor and a memory, and the processor and the memory are connected to each other. The memory is configured to store a computer program that supports the terminal device to execute the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect, where the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a service processing method according to an embodiment of the present application;

FIG. 2 is a schematic flow chart for constructing a knowledge graph according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a knowledge-graph structure provided by an embodiment of the present application;

fig. 4 is another schematic flow chart of a service processing method provided in an embodiment of the present application;

fig. 5 is a schematic structural diagram of a service processing apparatus according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

At present, the artificial intelligence technology is utilized to construct a customer service system for information in a certain field, so that the technical development in the field can be better promoted. For example, in the financial field, a customer service system is constructed for financial business information, so that people can quickly know information such as applicable groups, business ranges, income types and the like of certain financial products. The application range of the customer service system is very wide, the construction of the customer service system for financial business information in the financial field is only used as an application scene for explanation, and the construction of the customer service system for other information in other fields or in the financial field is essentially the same as the embodiment provided by the application, and is not repeated here. Taking a customer service system in the financial field as a specific application scenario as an example, when a user performs operations such as voice-form consultation or text-form conversation with a customer service on a user operation interface of the customer service system in the terminal device, the terminal device may acquire data input by the user as service consultation data. When the terminal device obtains that the user session or the question contains 'how do you want to consult the income of the fund a' through the user operation interface of the customer service system, 'the fund a' in 'how do the income of the fund a' can be used as the target consultation service, 'the income' can be used as the target consultation dimension, and the target consultation service and the target consultation dimension correspond to the knowledge graph to obtain the target triple (the fund-the income-the annual percentage of interest is 10%). The terminal device can determine the target node "a fund" and "annual percentage 10%" contained in the target triple and determine the associated node according to the target node respectively. For example, the association node "B fund" connected by earnings to "annual percentage 10%", the association node "medical fund" connected by fund type to "a fund", the association node "zhang san" connected by fund manager to "a fund", and the like. And the terminal equipment can obtain primary associated triples (annual percentage 10% -income-B fund, A fund-fund type-medical fund, A fund-fund manager-Zhang III and the like) associated with the target triples (A fund-income-annual percentage 10%) so as to determine primary associated information of the target consultation service. The terminal device may further determine a connection relationship between the target node and the associated node through a knowledge graph, for example, the connection relationship "semiannual percentage rate" between the target node "a fund" and the associated node "B fund" is different, so as to obtain an associated node "semiannual percentage rate 8%" connected with the target node "a fund" through the "semiannual percentage rate", and an associated node "semiannual percentage rate 5%" connected with the associated node "B fund" through the "semiannual percentage rate. And the customer service system can obtain secondary associated triples (different from each other, namely A fund-half annual percentage-B fund, 8% of A fund-half annual percentage, 5% of B fund-half annual percentage, and the like) associated with the target triples (A fund-income-annual percentage), and further determine secondary associated information of the target consultation service.

Further, the customer service system can determine the primary associated information and the secondary associated information as associated customer service information of the target consultation service, and output the associated customer service information to a user operation interface of the customer service system to be directly displayed to the user, or display the associated customer service information to the customer service system for the customer service to reply to the user until the user quits the customer service system. In the embodiment of the present application, for convenience of description, a customer service system of a financial system is taken as a customer service system, and a terminal device is taken as an execution subject of the present application, so as to exemplify the business processing method and apparatus provided in the embodiment of the present application.

Referring to fig. 1, fig. 1 is a flow chart illustrating a service processing method according to an embodiment of the present application. As shown in fig. 1, the service processing method provided in the embodiment of the present application may include the following steps:

s101: and acquiring the business consultation data input by the user, and determining the target consultation business and the target consultation dimension of the business consultation data.

In some possible embodiments, when a user performs operations such as a voice-type consultation or a text-type conversation with a customer service on a user operation interface of a customer service system in the terminal device, the terminal device may acquire data input by the user as service consultation data. When the terminal equipment acquires that the user session or the question contains 'how do you want to consult the income of the A fund' through the user operation interface of the customer service system, the service consultation data can be subjected to semantic recognition to obtain the 'how do the income of the A fund', the 'A fund' in the 'how do the income of the A fund' can be used as a target consultation service, and the 'income' is used as a target consultation dimension.

In some possible embodiments, before performing step S102, the terminal device may construct a knowledge graph, please refer to fig. 2 together, and fig. 2 is a schematic flow chart of constructing a knowledge graph according to an embodiment of the present application. The above-described method of constructing a knowledge graph may include the implementation provided by each of the following steps S201 to S206.

S201: and acquiring a plurality of training corpora to be labeled from a service consultation database of the customer service system.

In some possible embodiments, the terminal device may obtain the corpus by consulting the service database of the customer service system. The terminal device can acquire data in databases such as application data, knowledge base text data, platform marketing activity data, platform product data, and find product library, or extract a plurality of dialogue information from user logs of the customer service system as training corpora. The terminal device may input the corpus of different sources into the distributed processor, and process the corpus according to the data format of the corpus (for example, access the HDFS file by using spark sql, clean the data by using sql according to the rule, remove special symbols, etc.), thereby converting the corpus of different data formats into the corpus to be labeled with a uniform format.

S202: and semantically labeling the training corpuses to be labeled to obtain a plurality of labeled training corpuses, wherein the labeled training corpuses comprise training service information and associated training service information associated with the training service information.

S203: and dividing each training service information and the associated training service information of each training service information according to a format of service-service dimension-dimension characteristics to obtain a training triple corresponding to each training service information and an associated training triple corresponding to each associated training service information.

In some possible embodiments, the terminal device may label and divide the corpus to be labeled (for example, label and divide the corpus according to the format of the service-dimension feature by using the haymaltp open source packet), so as to obtain the divided corpus. Any divided training corpus comprises: training triples corresponding to the training service information and associated training triples corresponding to the associated training service information of the training service information.

In some possible embodiments, the terminal device may label the training corpus 1 (client: how profit of a fund is 10%, customer care, three times of fund manager mainly responsible for a fund, and the like) and the training corpus 2 (client: which kind of fund with 10% of profit rate is client care, 10% of fund has a fund and B fund, which have different half-year profit rates, 8% of half-year profit rate of a fund and 5% of B fund), to obtain labeled dialogue information 1 (training business information: how profit of a fund is triple training: a fund-profit-10% of annual profit rate, three times of training business information 1: a fund belonging to medical care fund type 2: three times of training fund-1-three times of training fund-medical care fund-type of mutual training business information. Associating training triplets 2: fund-fund manager-zhang san. ) And labeled training corpus 2 (training service information: what is a fund with a 10% annual rate? Training the triples: fund-income-annual percentage of change 10%. Associated training service information 1: the fund having an annual percentage of 10% has fund a. Associated training service information 1: the fund with the annual percentage of 10% has B fund. Associated training service information 3: the half-annual profit rates of the A fund and the B fund are different. Associated training service information 4: the half-annual percentage benefit of the A fund is 8%. Associated training service information 5: the half-annual percentage benefit of B-fund is 5%. Associating training triplets 1: annual percentage 10% -income-A fund. Associating training triplets 2: annual percentage 10% -income-B fund. And (3) associating the training triplets: fund a-half annual percentage difference-fund B. And (4) associating the training triplets: the A fund is half-annualized, and is 8 percent of half-annualized. And (3) associating the training triplets 5: b fund-half annual percentage of conversion-5% of conversion. ).

S204: and determining the service and dimension characteristics in each training triple and the service and dimension characteristics in the associated training triples of each training triple as nodes in the knowledge graph.

It can be understood that, in the knowledge graph, when a node corresponding to the service and the dimensional feature of the training triplet is a target node, a node corresponding to the service and the dimensional feature in the associated training triplet corresponding to the training triplet is an associated node of the target node.

S205: and determining the service dimension in each training triple and the service dimension in the associated training triple of each training triple as the node connection relation in the knowledge graph.

It can be understood that, in the knowledge graph, when the node connection relationship corresponding to the service dimension of the training triplet is the target consulting dimension, the node connection relationship corresponding to the service dimension in the associated training triplet corresponding to the training triplet is the associated consulting dimension.

S206: and connecting the nodes of the knowledge graph according to the node connection relation of the knowledge graph to obtain the knowledge graph.

In some possible implementations, please refer to fig. 3 together, and fig. 3 is a schematic structural diagram of a knowledge graph provided in the embodiment of the present application. As shown in fig. 3, the terminal device may determine a node in the knowledge graph through each training triplet (a black dashed line region in fig. 3) in the plurality of labeled training corpora and a node in an associated training triplet (a gray dashed line region in fig. 3) of each training triplet, and determine a node connection relationship in the knowledge graph through each training triplet and a node connection relationship in each associated training triplet. For example, the terminal device may determine, as nodes of the knowledge graph, a node a1(a fund), a node a2 (annual percentage of 10%), an associated node B1 (medical fund), and an associated node B2 (zhang san) in each triplet through a training triplet (a fund-profit-annual percentage of 10%), an associated training triplet 1(a fund-fund type-medical fund), and an associated training triplet 2(a fund-fund manager-zhang) in the labeled training corpus 1. Further, a node connection relationship C1 (benefit) of the node a1(a fund) and the node a2 (annual percentage 10%), a node connection relationship C2 (fund type) of the node a1(a fund) and the associated node B1 (medical fund), and a node connection relationship C3 (fund manager) of the node a1(a fund) and the associated node B2 (zhang) were determined as node connection relationships in the knowledge graph. The terminal device may also determine the nodes and the node connection relationships in the knowledge graph through the nodes and the node connection relationships included in the labeled corpus 2, which is not described herein again.

In some possible embodiments, the terminal device may count the occurrence times of each training triplet and the associated training triplet of each training triplet in the training corpus, respectively, to obtain the weight of the node in the knowledge graph. It can be understood that the terminal device may also count the times that each training triplet and the associated training triplet of each training triplet appear in the same training corpus, respectively, to obtain the weight of the node connection relationship in the knowledge graph. Further, the terminal equipment can construct the knowledge graph based on the weight of the node in the knowledge graph and the weight of the connection relation of the nodes in the knowledge graph, so that the knowledge graph is more suitable for the use habit of a user, the user experience is optimized, and the question and answer efficiency of the customer service system is improved.

In some possible embodiments, step S102 may be performed after the terminal device completes building the knowledge-graph.

S102: acquiring a knowledge graph associated with the target consulting service, and determining primary associated information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension of the target consulting service.

In some possible embodiments, the knowledge graph associated with the target counseling service is a knowledge graph of a field of the target counseling service, for example, when the target counseling service is determined to be "a fund", the terminal device may determine that the field to which the target counseling service belongs is "fund", and then the terminal device may acquire the knowledge graph of the fund field to determine primary associated information of the target counseling service.

In some possible embodiments, the primary association information includes: the system comprises a target consultation dimension characteristic (annual percentage of change is 10%) corresponding to a target consultation dimension (income) of the target consultation service (A fund), an associated consultation dimension characteristic (medical fund) corresponding to an associated consultation dimension (fund type) associated with the target consultation service (A fund) and an associated service (B fund) of the target consultation service. Here, the dimensional characteristic (annual percentage of 10%) of the related business (B fund) in the target consulting dimension (benefit) is the same as the target consulting dimensional characteristic (annual percentage of 10%) of the target consulting business (a fund) in the target consulting dimension (benefit). Here, the primary associated information of the target counseling service may be a set of information that the user may consult after consulting the target counseling service in the user question-answering habit (i.e., dimensional characteristics of the target counseling service in other dimensions and associated services of the target counseling service).

In some possible embodiments, after determining that the target consulting service is "a fund" and the target consulting dimension is "income", the terminal device may obtain a knowledge graph in the fund field, determine a target triple (a fund-income-annual percentage of 10%) corresponding to the target consulting service based on the target consulting service (a fund) and the target consulting dimension (income) of the target consulting service in the knowledge graph, and further obtain a target consulting dimension characteristic (annual percentage of 10%) corresponding to the target consulting dimension of the target consulting service.

In some possible embodiments, the terminal device may use the nodes included in the target triple as target nodes (i.e., "a fund" and "annual percentage of 10%"), and determine the associated nodes of the target nodes in the knowledge graph according to the target nodes, respectively. For example, the terminal device may determine, in the knowledge graph, the associated node "B fund" connected with "annual percentage 10%", the associated node "medical fund" connected with "a fund" through a fund type, the associated node "zhang san" connected with "a fund" through a fund manager, and the like. And the terminal equipment can further obtain a primary associated triple (annual percentage 10% -income-B fund, A fund-fund type-medical fund, A fund-fund manager-Zhang III and the like) associated with the target triple (A fund-income-annual percentage 10%) through the target node and the associated node, and further determine primary associated information of the target consultation service. That is, the related consultation dimension characteristic (medical fund) corresponding to the target consultation service in the related consultation dimension (fund type), the related consultation dimension characteristic (Zhang III) corresponding to the target consultation service in the related consultation dimension (fund manager), and the related service (B fund) of the target consultation service.

S103: and determining the distinguishing dimension of the target consulting service and the relevant service in the knowledge graph based on the target consulting service and the relevant service, and determining the distinguishing dimension characteristics corresponding to the distinguishing dimension of the target consulting service and the distinguishing dimension characteristics corresponding to the relevant service in the distinguishing dimension as secondary relevant information of the target consulting service.

In some possible embodiments, the secondary association information includes: the difference dimension characteristic (semiannual percentage rate 8%) corresponding to the difference dimension (semiannual percentage rate) of the target consulting business (A fund) and the difference dimension characteristic (semiannual percentage rate 5%) corresponding to the difference dimension (semiannual percentage rate) of the associated business (B fund). Here, the secondary associated information of the target counseling service is used to explain the difference between the target counseling service and the related service.

In some possible embodiments, the terminal device may further determine secondary association information of the target counseling service in the knowledge graph through the target counseling service and the association service. For example, the terminal device may use the "half-annual profit rate" as a distinguishing dimension between the target consultation service and the associated service according to the difference between the service dimensions "half-annual profit rate" of the target consultation service "a fund and the associated service" B fund ", and further obtain an associated node" half-annual profit rate 8% "connected to the target node" a fund by the "half-annual profit rate" in the knowledge graph, and obtain an associated node "half-annual profit rate 5%" connected to the node "B fund by the" half-annual profit rate "in the knowledge graph. Therefore, the terminal equipment can determine secondary associated triples (different from each other, namely, A fund-half annual percentage-B fund, 8% of A fund-half annual percentage, 5% of B fund-half annual percentage, and the like) of the target triples (A fund-income-annual percentage), and further determine secondary associated information of the target consultation service. That is, the terminal device may determine the secondary associated information of the target counseling service: the difference dimension characteristic (semiannual percentage rate 8%) corresponding to the difference dimension (semiannual percentage rate) of the target consulting business (A fund) and the difference dimension characteristic (semiannual percentage rate 5%) corresponding to the difference dimension (semiannual percentage rate) of the associated business (B fund).

In some feasible embodiments, if a certain target advisory service is a cold service, the cold service does not conform to the existing triple rule, that is, the terminal device cannot determine the target triple corresponding to the target advisory service in the knowledge graph through the existing identification rule, the terminal device may feed the target advisory service back to the background maintenance personnel and/or enter the target advisory service into the knowledge graph, and update the associated identification rule, so as to obtain the target triple corresponding to the target advisory service and the associated triple (the primary associated triple and the secondary associated triple). The terminal equipment can associate the cold business to the knowledge graph in such a way, so that the applicability of the customer service system is improved.

S104: and determining the primary associated information and the secondary associated information as associated client service information of the target consultation service, and outputting the associated client service information to a user operation interface of a client service system.

In some possible embodiments, after determining the primary associated information and the secondary associated information of the target consulting service according to the target triplet and the primary associated triplet and the secondary associated triplet associated with the target triplet, the customer service system may obtain the associated customer service information of the target consulting service according to the primary associated information and the secondary associated triplet (for example, taking the primary associated triplet and the secondary associated triplet associated with the target triplet as a keyword, retrieving the keyword in a service consulting database of the customer service system to obtain the extended information corresponding to the keyword as the associated customer service information of the target consulting service), and output the associated customer service information of the target consulting service to a user operation interface of the customer service system to be directly displayed to the user, or to be displayed to the customer service for the customer service to reply to the user, until the user logs off the customer service system.

Referring to fig. 4, fig. 4 is another schematic flow chart of a service processing method according to an embodiment of the present application.

S301: and acquiring the business consultation data input by the user and judging the data type of the business consultation data.

S302: and when the data type of the business consultation data is audio data or video data, converting the business consultation data into the business consultation data of a text data type through voice to text conversion.

S303: and when the data type of the business consultation data is picture data, converting the business consultation data into the business consultation data of the character data type through character recognition.

S304: and performing semantic analysis on the business consultation data of the text data type to obtain a target consultation service corresponding to the business consultation data of the text data type and a target consultation dimension of the target consultation service.

In some possible embodiments, when a user performs operations such as a voice-type consultation or a text-type conversation with a customer service on a user operation interface of a customer service system in the terminal device, the terminal device may acquire data input by the user as service consultation data. The terminal equipment can convert the business consultation data of different data types into the business consultation data of the character data type, and carries out semantic analysis on the business consultation data of the character data type so as to obtain a target consultation service corresponding to the business consultation data of the character data type and a target consultation dimension of the target consultation service. For example, when the terminal device obtains that "how do you want to consult the income of the a fund" is included in the user session or the question obtained through the user operation interface of the customer service system, semantic recognition can be performed on the service consultation data to obtain "how do the income of the a fund", the "a fund" in "how do the income of the a fund" can be used as the target consultation service, and "income" is used as the target consultation dimension. The types of the service consultation data applicable to the customer service system are increased, and the applicability of the system is improved.

S305: acquiring a knowledge graph associated with the target consulting service, and determining primary associated information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension of the target consulting service.

In some feasible embodiments, the terminal device may further obtain, through the knowledge graph, the association degree between each associated node and the target node (or the association degree between the primary associated triple and the target triple), so as to screen the associated nodes (or the primary associated triples) to obtain the screened primary associated triples, thereby improving the association degree between the primary associated triples and the target triple (i.e., the target consultation service), avoiding excessive association, and improving the working efficiency of the customer service system.

S306: and determining the distinguishing dimension of the target consulting service and the relevant service in the knowledge graph based on the target consulting service and the relevant service, and determining the distinguishing dimension characteristics corresponding to the distinguishing dimension of the target consulting service and the distinguishing dimension characteristics corresponding to the relevant service in the distinguishing dimension as secondary relevant information of the target consulting service.

In some feasible embodiments, the terminal device may further determine the association degree of the secondary association triple with the target triple according to the association degree of the node connection relationship in the knowledge graph and the target node, so as to screen the secondary association triple, thereby improving the association degree of the secondary association triple with the target triple (i.e., the target advisory service), avoiding excessive association, and improving the working efficiency of the customer service system.

S307: and determining the primary associated information and the secondary associated information as associated client service information of the target consultation service, and outputting the associated client service information to a user operation interface of a client service system.

Referring to fig. 5, fig. 5 is a schematic structural diagram of a service processing apparatus according to an embodiment of the present application, where the apparatus includes:

the service determination module 401 is configured to obtain service consulting data input by a user, and determine a target consulting service of the service consulting data and a target consulting dimension of the target consulting service.

In some possible embodiments, when the user performs operations such as a voice-type consultation or a text-type conversation with the customer service on the user operation interface of the customer service system in the terminal device, the service determination module 401 may obtain data input by the user as service consultation data. When the service determination module 401 obtains that the user session or the question includes "how do you want to consult the benefit of the a fund" through the user operation interface of the customer service system, it may perform semantic recognition on the service consultation data to obtain "how do the benefit of the a fund", and may use "the a fund" in "how do the benefit of the a fund" as the target consultation service and "the benefit" as the target consultation dimension.

The primary information association module 402 is configured to obtain a knowledge graph associated with the target consulting service, and determine primary association information of the target consulting service in the knowledge graph based on the target consulting service and a target consulting dimension of the target consulting service, where the primary association information of the target consulting service includes a target consulting dimension feature corresponding to the target consulting service in the target consulting dimension, an associated consulting dimension feature corresponding to the target consulting service in the associated consulting dimension, and an associated service of the target consulting service. Here, the dimension characteristic of the associated service in the target consulting dimension is the same as the target consulting dimension characteristic of the target consulting service in the target consulting dimension.

In some possible embodiments, after determining that the target consulting service is "a fund" and the target consulting dimension is "income", the primary information associating module 402 may obtain a knowledge graph of the fund field, determine a target triple (a fund-income-annual percentage of 10%) corresponding to the target consulting service in the knowledge graph based on the target consulting service (a fund) and the target consulting dimension (income) of the target consulting service, and further obtain a target consulting dimension characteristic (annual percentage of 10%) corresponding to the target consulting dimension of the target consulting service.

In some possible embodiments, the primary information association module 402 may use the nodes included in the target triple as target nodes (i.e., "a fund" and "annual percentage of 10%"), and determine the associated nodes of the target nodes in the knowledge graph according to the target nodes, respectively. For example, the preliminary information association module 402 may determine, in the knowledge-graph, association nodes "B-fund" associated with "annual percentage 10%" connected through revenue, "medical fund" associated with "a-fund" connected through fund type, "zhang san" associated with "a-fund" connected through fund manager, and so on. Further, the primary information association module 402 may obtain, through the target node and the association node, a primary association triple (annual percentage 10% -income-B fund, a fund-fund type-medical fund, a fund-fund manager-zhang san, etc.) associated with the target triple (a fund-income-annual percentage 10%), and further determine primary association information of the target consulting service. That is, the related consultation dimension characteristic (medical fund) corresponding to the target consultation service in the related consultation dimension (fund type), the related consultation dimension characteristic (Zhang III) corresponding to the target consultation service in the related consultation dimension (fund manager), and the related service (B fund) of the target consultation service.

The secondary information association module 403 is configured to determine, in the knowledge graph, a difference dimension between the target consulting service and the associated service based on the target consulting service and the associated service, and determine a difference dimension feature corresponding to the difference dimension of the target consulting service and a difference dimension feature corresponding to the difference dimension of the associated service, so as to serve as secondary associated information of the target consulting service.

In some possible embodiments, the secondary information association module 403 may also determine secondary association information of the target counseling service in the knowledge graph through the target counseling service and the association service. For example, the secondary information association module 403 may obtain, in the knowledge graph, an association node "semiannual percentage rate 8%" connected to the target node "a fund by the" semiannual percentage rate "and obtain, in the knowledge graph, an association node" semiannual percentage rate 5% "connected to the node" B fund by the "semiannual percentage rate", according to the difference between the service dimensions "semiannual percentage rate" of the target consulting service "a fund and the association service" B fund. The secondary information correlation module 403 may determine secondary correlation triples (a fund-semiannual percentage is different-B fund, a fund-semiannual percentage is 8%, B fund-semiannual percentage is 5%, etc.) of the target triples (a fund-income-annual percentage is 10%), thereby determining secondary correlation information of the target consulting service. That is, the secondary information association module 403 may obtain the difference dimension (semiannual percentage) of the target consulting service (a fund) and the related service (B fund), the difference dimension characteristic (semiannual percentage 8%) of the target consulting service (a fund) in the difference dimension (semiannual percentage) and the difference dimension characteristic (semiannual percentage 5%) of the related service (B fund) in the difference dimension (semiannual percentage).

And the association display module 404 is configured to determine the primary association information and the secondary association information as association client service information of the target consulting service, and output the association client service information to a user operation interface of the client service system.

In some possible embodiments, the association displaying module 404 may obtain the associated client service information of the target consulting service according to the primary associated triplet and the secondary associated triplet associated with the target triplet after determining the primary associated information and the secondary associated information of the target consulting service according to the primary associated triplet and the secondary associated triplet associated with the target triplet, and the associated client service information of the target consulting service (for example, the primary associated triplet and the secondary associated triplet associated with the target triplet and the target triplet are used as keywords and retrieved from a service consulting database of the client service system to obtain the extended information corresponding to the keywords and used as the associated client service information of the target consulting service), and output the associated client service information of the target consulting service to a user operation interface of the client service system to be directly displayed to the user, or to be displayed to the client service for the client service to reply to the user, until the user logs off the customer service system.

Referring to fig. 6, fig. 6 is a schematic structural diagram of a terminal device provided in an embodiment of the present application. As shown in fig. 6, the terminal device in this embodiment may include: one or more processors 501 and memory 502. The processor 501 and the memory 502 are connected by a bus 503. The memory 502 is used for storing a computer program comprising program instructions, and the processor 501 is used for executing the program instructions stored in the memory 502 to perform the following operations:

acquiring business consultation data input by a user, and determining a target consultation service of the business consultation data and a target consultation dimension of the target consultation service, wherein the target consultation dimension corresponds to the target consultation service one to one;

acquiring a knowledge graph associated with the target consulting service, and determining primary associated information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension, wherein the primary associated information of the target consulting service comprises target consulting dimension characteristics of the target consulting service in the target consulting dimension, associated consulting dimension characteristics of the target consulting service in the associated consulting dimension associated with the target consulting service, and associated services of the target consulting service, and the dimension characteristics of the associated services in the target consulting dimension are the same as the target consulting dimension characteristics of the target consulting service in the target consulting dimension;

determining the distinguishing dimension of the target consulting service and the related service in the knowledge graph based on the target consulting service and the related service, and determining the distinguishing dimension characteristics corresponding to the distinguishing dimension of the target consulting service and the distinguishing dimension characteristics corresponding to the related service in the distinguishing dimension as secondary related information of the target consulting service;

and determining the primary associated information and the secondary associated information as associated client service information of the target consultation service, and outputting the associated client service information to a user operation interface of a client service system.

In some possible embodiments, the processor 501 is further configured to:

acquiring a plurality of training corpora to be labeled from a service consultation database of a customer service system;

performing semantic annotation on a plurality of training corpuses to be annotated to obtain a plurality of annotated training corpuses, wherein the annotated training corpuses comprise training service information and associated training service information associated with the training service information;

and constructing a knowledge graph based on each training service information and the associated training service information of each training service information.

In some possible embodiments, the processor 501 is configured to:

dividing each training service information and associated training service information of each training service information according to a format of service-service dimension-dimension characteristics to obtain a training triple corresponding to each training service information and an associated training triple corresponding to each associated training service information, wherein the training triples and the associated training triples are triples, and one triple comprises a service, a service dimension and dimension characteristics of the service in the service dimension;

and constructing a knowledge graph based on each training triplet and the associated training triplets of each training triplet.

In some possible embodiments, the processor 501 is configured to:

determining the service and dimension characteristics in each training triple and the service and dimension characteristics in the associated training triples of each training triple as nodes in the knowledge graph;

determining the service dimension in each training triplet and the service dimension in the associated training triplet of each training triplet as the node connection relation in the knowledge graph;

In some possible embodiments, the processor 501 is configured to:

respectively counting the occurrence times of each training triplet and the associated training triplet of each training triplet in the training corpus to obtain the weight of the node in the knowledge graph;

respectively counting the times of the training triples and the associated training triples of the training triples appearing in the same training corpus to obtain the weight of the node connection relation in the knowledge graph;

In some possible embodiments, the processor 501 is configured to:

acquiring business consultation data input by a user, and judging the data type of the business consultation data, wherein the data type comprises at least one of audio data, video data, picture data or text data;

when the data type of the business consultation data is picture data, converting the business consultation data into the business consultation data of the character data type through character recognition;

and performing semantic analysis on the business consultation data of the text data type to obtain a target consultation service corresponding to the business consultation data of the text data type and a target consultation dimension of the target consultation service.

With reference to the first aspect, in a possible implementation manner, the processor 501 is configured to:

determining a target triple corresponding to the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension, and determining the dimension characteristics in the target triple as target consulting dimension characteristics corresponding to the target consulting service in the target consulting dimension;

determining a business association triple associated with the target consulting business in the knowledge graph based on the target consulting business, and determining an associated consulting dimension characteristic of the associated consulting dimension associated with the target consulting business based on the business dimension and the dimension characteristic in the business association triple;

and determining a feature association triple associated with the target consultation dimension characteristic in the knowledge graph based on the target consultation dimension and the target consultation dimension characteristic of the target consultation service, and determining the associated service of the target consultation service based on the service in the feature association triple.

In some possible embodiments, the processor 501 may be a Central Processing Unit (CPU), and the processor may be other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 502 may include both read-only memory and random access memory, and provides instructions and data to the processor 501. A portion of the memory 502 may also include non-volatile random access memory. For example, the memory 502 may also store device type information.

In a specific implementation, the terminal device may execute, through each built-in functional module, the implementation manners provided in the steps in fig. 1, fig. 2, and fig. 4, which may be referred to specifically for the implementation manners provided in the steps, and are not described herein again.

An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a processor, the method provided in each step in fig. 1, fig. 2, and fig. 4 is implemented.

The computer-readable storage medium may be the terminal device provided in any of the foregoing embodiments or an internal storage unit of the terminal device, such as a hard disk or a memory of an electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) card, a flash card (flash card), and the like, which are provided on the electronic device. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the electronic device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the electronic device. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.

The terms "first", "second", "third", "fourth", and the like in the claims and in the description and drawings of the present application are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments. The term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The method and the associated apparatus provided in the embodiments of the present application are described with reference to the flowchart and/or the structural diagram of the method provided in the embodiments of the present application, and each flow and/or block of the flowchart and/or the structural diagram of the method and/or the combination of the flows and/or blocks in the flowchart and/or the block diagram can be specifically implemented by computer program instructions. These computer program instructions may 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 flow or flows and/or block or blocks of the block diagram. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block or blocks of the block diagram. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block or blocks.

Claims

1. A service processing method based on knowledge graph is characterized in that the method comprises the following steps:

acquiring a knowledge graph associated with the target consulting service, and determining primary associated information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension, wherein the primary associated information of the target consulting service comprises a target consulting dimension characteristic corresponding to the target consulting dimension of the target consulting service, an associated consulting dimension characteristic corresponding to an associated consulting dimension associated with the target consulting service, and an associated service of the target service, and the dimension characteristic corresponding to the associated service in the target consulting dimension is the same as the target consulting dimension characteristic corresponding to the target consulting dimension of the target consulting service;

determining the difference dimension of the target consulting service and the associated service in the knowledge graph based on the target consulting service and the associated service, and determining the difference dimension characteristics of the target consulting service in the difference dimension and the difference dimension characteristics of the associated service in the difference dimension as secondary associated information of the target consulting service;

and determining the primary associated information and the secondary associated information as associated customer service information of the target consultation service, and outputting the associated customer service information to a user operation interface of a customer service system.

2. The method of claim 1, wherein before the determining primary relevance information of the target consulting service in the knowledge-graph based on the target consulting service and the target consulting dimension, the method further comprises:

3. The method of claim 2, wherein the constructing the knowledge-graph based on the respective training service information and the associated training service information of the respective training service information comprises:

dividing each training service information and associated training service information of each training service information according to a format of service-dimension characteristics to obtain a training triple corresponding to each training service information and an associated training triple corresponding to each associated training service information, wherein the training triples and the associated training triples are triples, and one triple comprises a service, a dimension and dimension characteristics of the service in the dimension;

constructing the knowledge-graph based on each training triplet and the associated training triplet of each training triplet.

4. The method of claim 3, wherein the constructing the knowledge-graph based on the respective training triples and the associated training triples of the respective training triples comprises:

determining dimensions in each training triplet and dimensions in the associated training triplets of each training triplet as node connection relations in the knowledge graph;

5. The method of claim 4, further comprising:

6. The method as claimed in any one of claims 1 to 5, wherein the acquiring business advisory data input by the user and determining a target advisory business and a target advisory dimension of the business advisory data comprises:

7. The method of any one of claims 1-6, wherein the determining primary relevance information of the target consulting service in the knowledge-graph based on the target consulting service and the target consulting dimension comprises:

determining a target triple corresponding to the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension, and determining a dimension characteristic in the target triple as a target consulting dimension characteristic corresponding to the target consulting service in the target consulting dimension;

determining a service association triple associated with the target consulting service in the knowledge graph based on the target consulting service, and determining an associated consulting dimension characteristic of the associated consulting dimension associated with the target consulting service based on the dimension and the dimension characteristic in the service association triple;

and determining a feature association triple associated with the target consulting dimension feature in the knowledge graph based on the target consulting dimension of the target consulting service and the target consulting dimension feature, and determining an associated service of the target consulting service based on the service in the feature association triple.

8. A knowledge-graph based business process apparatus, the apparatus comprising:

a primary information association module, configured to obtain a knowledge graph associated with the target consulting service, and determine primary association information of the target consulting service in the knowledge graph based on the target consulting service and the target consulting dimension, where the primary association information of the target consulting service includes a target consulting dimension feature corresponding to the target consulting service in the target consulting dimension, an associated consulting dimension feature corresponding to an associated consulting dimension associated with the target consulting service, and an associated service of the target consulting service, and a dimension feature corresponding to the associated service in the target consulting dimension is the same as a target consulting dimension feature corresponding to the target consulting service in the target consulting dimension;

and the association display module is used for determining the primary association information and the secondary association information as the associated customer service information of the target consultation service and outputting the associated customer service information to a user operation interface of a customer service system.

9. A terminal device, characterized in that it comprises a processor and a memory, said processor and memory being interconnected, wherein said memory is adapted to store a computer program comprising program instructions, said processor being configured to invoke said program instructions to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method according to any of claims 1-7.