Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that, in the case where the embodiment of the present application relates to user information, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) related to the embodiment of the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant country and region, and are provided with corresponding operation entries for the user to select authorization or rejection. In addition, the various models (including but not limited to language models or large models) to which the present application relates are compliant with relevant legal and standard regulations.
The technical scheme of the embodiment of the application can be applied to an online system for providing the object for the user to execute the interactive behavior.
As described in the background art, the intelligent service can only identify the target object of the object dimension to be queried from the dialogue message of the user, and give the response of the object dimension, but in practical application, one object often consists of a plurality of object instances, and the user wants to know about a specific object instance, so that the service accuracy of the service resource is not high.
In some online systems that provide objects for users to perform interactive actions, for example, online transaction platforms that provide commodity transactions, in order to provide users with better service experience, the online systems may generally provide communication capabilities, so that an object provider or the online systems provide services for users, a session channel may be established between the users and service resources, and communication may be performed in a message form, for example, in an on-premise service scenario, the users may send a session message to the service resources to query the service resources for relevant information of the target object, and the service resources may refer to manual services or intelligent services.
Aiming at the technical problem of low response accuracy given by the existing service, the embodiment of the application provides a solution, and the basic idea is that a dialogue message sent by a user terminal based on a first dialogue connection is obtained, wherein the first dialogue connection is established based on a service request sent by the user terminal, a target object associated with the dialogue message is identified, a plurality of object instances of the target object are determined, first selection prompt information aiming at the plurality of object instances is provided for the user terminal, the selected target object instance is determined in response to the first selection request triggered by the first selection prompt information, a first response message corresponding to the dialogue message is generated based on the instance information corresponding to the target object instance, and the first response message is sent to the user terminal based on the first dialogue connection.
According to the embodiment of the application, the target object associated with the dialogue message and the multiple object instances of the target object are identified, so that the selection function of the object instance can be provided for the user, the user can accurately select the target object instance, and the server can generate a targeted and accurate response message based on the instance information of the target object instance, thereby providing more accurate intelligent service, improving communication efficiency and ensuring user experience. In the pre-sales service scene, the interaction desire of the user can be improved, and the object conversion rate is improved.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Implementation details of the technical solution of the embodiment of the present application are set forth in detail below.
Fig. 1 is a flowchart of an embodiment of a service providing method provided by the present application, where the technical solution of the present embodiment may be executed by a server, in this embodiment, the server provides an intelligent service, and the server is disposed in an online system, and in practical application, the online system is generally formed by a user side and a server, where a connection is established between the user side and the server through a network. The network provides a medium for a communication link between the client and the server. The network may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user side can be a consumer user or a buyer facing the user, namely in practical application, and the user can perform interactive actions such as object purchase and the like through the user side.
The method may comprise the steps of:
And 101, acquiring a dialogue message sent by the user side based on the first dialogue connection.
Wherein the first session connection is established based on a service request sent by the user terminal.
The service request may be generated by the user side in response to a service triggering operation, may be a service request of a pointer to a customer service, and the service triggering operation may be a triggering operation for service prompt information, where the service prompt information may be displayed in a target page, and the target page may be, for example, a top page or an object detail page.
The first session connection may be a long connection established between the user terminal and the server terminal for communication, for example, a websocket (a full duplex communication protocol) connection, etc., after the first session connection is established, the user terminal may display a service session interface, and the user (such as a consumer) may perform a message input operation in the service session interface, etc., so that the user terminal may detect that a session message is obtained and may send the session message to the server terminal. Alternatively, the user terminal may send a session end request to the server terminal in response to the session end operation, so that the first session connection may be disconnected. The session end operation may be, for example, an exit operation of the service session interface, or the like.
102 Identifying a target object associated with the conversation message and determining a plurality of object instances of the target object.
An object is often an object instance combination of multiple object instances, for example, an object may have attribute parameters such as size, color, shape, etc. of different specifications, and an object instance may correspond to one or more attribute parameters.
In practice, the object may refer to an SPU (Standard Product Unit ), such as representing a class of commodity in an e-commerce scenario, and the object instance may be represented as a SKU (Stock Keeping Unit, stock measure unit), such as representing a specific commodity instance in an e-commerce scenario.
For example, if the target object is a mobile phone, the attribute parameters thereof may include color (white, black), size (5 inches, 7 inches), and storage capacity (16 GB, 32GB, 64 GB), and examples of the object at this time may include, for example, white 5 inches 16GB, black 7 inches 32GB, and the like.
Wherein, the service type of the service request sent by the user terminal can be identified first, for example, the service type comprises pre-sale service, after-sale service or complaint opinion. The target object associated with the conversation message may be identified in the event that the identified service type is an off-the-shelf service. An off-the-shelf service is typically a service that a user desires to obtain from a service resource in the form of a session, for example, in the event that the user wants to further learn about an object or object instance. The embodiment of the application can identify the target object aiming at the before-sales service, thereby providing accurate and targeted before-sales service for the user, improving the interest of the user on the target object and improving the conversion rate of the object. Of course, the identification of the service type may not be performed, and the identification of the target object may be performed for all the service request information, which is not limited in the present application.
And 103, providing first selection prompt information for a plurality of object instances to the user side.
And 104, responding to a first selection request triggered by the first selection prompt information, and determining the selected target object instance.
And determining the instance identifier corresponding to the target object instance at the same time of determining the selected target object instance.
The first selection prompt information of the plurality of object instances may include, for example, selection prompt content, selection confirmation control, object instance prompt information corresponding to each of the plurality of object instances, and the like. The object instance prompt information may include, for example, a picture of the object instance, an attribute parameter value configuration corresponding to the object instance, and the like, which may be implemented in a control form so as to be selected based on a user operation and the like.
For ease of understanding, fig. 2 shows a schematic diagram of the first selection hint in one practical application. As shown in FIG. 2, the first selection hint information 200 can include selection hint content 201, a selection confirmation control 202, and object instance hint information 203. If the target object is a pair of trousers, the corresponding attribute parameters include color (dark blue, black or light blue), style (eighth, ninth or long trousers), trousers (straight, horn, pencil, smoke tube or broad leg), etc., then the object instance prompt information of a certain object instance may be, for example, "dark blue straight trousers", "dark blue eighth pencil trousers", or "black ninth smoke tube trousers", etc., as shown in fig. 2. Object instance hints for all object instances not shown in fig. 2, different object instance hints may be exposed by paging.
The first selection request may be generated by the user side in response to the object instance prompt for the target object instance and a trigger operation of the selection confirmation control.
And 105, generating a first response message corresponding to the dialogue message based on the instance information corresponding to the target object instance.
The instance information corresponding to the target object instance may include at least one question-answer knowledge pair corresponding to the target object instance and/or object attribute information and instance attribute information corresponding to the target object instance. The detailed description can be found below.
And 106, sending the first response message to the user terminal based on the first session connection.
According to the embodiment, the target object associated with the dialogue message and the multiple object instances of the target object are identified, so that a selection function of the object instance can be provided for a user, the user can accurately select the target object instance, and further the server can generate a targeted and accurate response message based on the instance information of the target object instance, so that more accurate intelligent service is provided, communication efficiency is improved, and user experience is guaranteed. In the pre-sales service scene, the interaction desire of the user can be improved, and the object conversion rate is improved.
In some embodiments, identifying the target object associated with the dialogue message and determining the plurality of object instances of the target object may include identifying whether the dialogue message is associated with the target object, if so, determining the plurality of object instances of the target object, if not, determining at least one object according to historical interaction data corresponding to the user terminal, providing second selection prompt information for the at least one object to the user terminal, and determining the selected target object in response to a second selection request triggered by the second selection prompt information.
The historical interaction data corresponding to the user side can comprise interaction data such as historical browsing, searching, purchasing and/or evaluating. For example, an object browsed in a last predetermined period of time may be determined as at least one object from among objects historically browsed by the user.
The second selection prompt information of the at least one object may include, for example, selection prompt content, selection confirmation control, object prompt information corresponding to the at least one object, and the like. The object hint information may include, for example, an object price, an object picture, object description information, and the like. The object description information may include information describing properties, characteristics, and styles of the object, which may be implemented in the form of a control so as to be selected based on user operations, etc.
The second selection request may be generated by the user side in response to the object prompt information for the target object and a trigger operation of the selection confirmation control.
In some embodiments, there are a number of implementations for identifying whether a conversation message is associated with a target object:
As an optional implementation manner, whether the service request carries the object identifier or not may be judged, if yes, a target object corresponding to the object identifier is determined. Wherein the service request may be generated in response to a triggering operation for the service hint information in the target object detail page. Thus, the service request may carry the object identification of the target object.
As another alternative implementation, it may be determined whether the target object is involved in the history of the first session connection.
In some embodiments, determining the plurality of object instances of the target object may include determining whether an acquisition requirement of the target object instance exists based on object information of the target object and a dialogue message, if so, determining the plurality of object instances of the target object, and if not, generating a first response message corresponding to the dialogue message based on the object information of the target object.
The object information of the target object may include at least one question-answer knowledge pair corresponding to the target object, object attribute information and/or instance attribute information corresponding to the target object, and the like.
The object attribute information corresponding to the target object may include attribute information of the target object of the object dimension, and the like. For example, attribute information of the object dimension may include a category, a brand, and the like. The instance attribute information corresponding to the target object may include attribute information of an instance dimension of an object instance included in the target object, and the like. Attribute information such as instance dimensions may include color, size, material, etc. of the object instance.
Where, for example, a conversation message is a query for object dimensions, there is no acquisition requirement for a target object instance even though the target object contains multiple object instances. If the dialogue message is "this applies scissors to kitchen", the plurality of object instances of the target object are only a plurality of scissors of different colors, and thus, there is no need for acquisition of the target object instance.
Alternatively, the recognition model may be used to determine whether there is a need for acquiring the target object instance based on the object information of the target object and the dialogue message. The first prompt instruction can be generated based on the object information and the dialogue message of the target object, and the first prompt instruction is input into the recognition model, so that whether the acquisition requirement of the target object instance exists or not can be judged based on the object information and the dialogue message of the target object by utilizing the recognition model.
In some embodiments, generating the first response message corresponding to the dialogue message based on the object information of the target object includes one or more of the following implementations:
As an alternative implementation manner, at least one question-answer knowledge pair corresponding to the target object can be searched for from the object knowledge base, the target question-answer knowledge pair matched with the dialogue message is identified from the at least one question-answer knowledge pair, and a first answer message corresponding to the dialogue message is generated based on answer data in the target question-answer knowledge pair;
the object knowledge base can correspondingly store the object identification of the object and at least one question-answer knowledge pair corresponding to the object, so that the at least one question-answer knowledge pair corresponding to the target object instance can be searched from the object knowledge base according to the object identification of the target object.
The object identifier of the target object according to the query may be an object identifier carried in the service request, etc.
The question-answer knowledge pair comprises answer data corresponding to the question data. And further, question data matched with the dialogue message can be determined from at least one question-answer knowledge pair, so that the question-answer knowledge pair to which the question data belongs is determined to be a target question-answer knowledge pair matched with the dialogue message, and a first answer message corresponding to the dialogue message is generated based on answer data in the target question-answer knowledge pair.
The method may determine the question data matched with the dialogue message from at least one question-answer knowledge pair by using a text matching manner, for example, the text similarity and/or semantic similarity between the question data in at least one question-answer knowledge pair and the dialogue message may be calculated, and the question data matched with the dialogue message may be determined. The application is not limited to the matching mode.
Wherein, optionally, the answer data in the target question-answer knowledge pair can be used as the first answer message. Alternatively, the question-answer processing model may be utilized to more vividly and naturally generate the answer data in the target question-answer knowledge pair based on the dialogue message, so as to generate the first answer message corresponding to the dialogue message.
The recognition Model or the question-answering processing Model related in the embodiment of the application can be a Language Model (LM) based on artificial intelligence or a multi-modal Model (MultimodalModel, MM) and the like, and the embodiment of the application does not limit the quantity of Model parameters supported by the Model and aims at meeting actual requirements.
The prompt instruction (prompt) referred to in embodiments of the present application is a natural language input, similar to a command or instruction, used to prompt or guide a model to give an output that meets expectations.
As another alternative implementation manner, object attribute information and instance attribute information corresponding to the target object may be searched from the object information library, and the first answer message corresponding to the dialogue message is generated based on the object attribute information and the instance attribute information by using the question-answer processing model.
The object information base can store object attribute information and instance attribute information corresponding to the object, namely, store the instance identifier of the object instance contained in the object and the instance attribute information of the object instance, store the object identifier of the object and the object attribute information, and store the instance identifier of the object instance contained in the object and the object identifier of the object in a correlated manner, so that the object attribute information of the object and the instance attribute information of the object instance contained in the object can be searched from the object information base according to the object identifier of the target object.
The second prompt instruction, such as "combine object attribute information and instance attribute information, may be input to the question-answer processing model to generate a natural and vivid response, for responding to the dialogue message", so as to instruct the question-answer processing model to combine the object attribute information and the instance attribute information to generate the first answer message corresponding to the dialogue message.
As yet another alternative implementation manner, the object attribute information and the instance attribute information corresponding to the target object may be searched from the object information base, whether attribute data matched with the dialogue message exists in the object attribute information and the instance attribute information is determined, and the first response message corresponding to the dialogue message is generated based on the attribute data.
Alternatively, a first answer message corresponding to the vivid and natural dialogue message may be generated based on the attribute data using a question-answer processing model. A third prompting instruction, such as "combine attribute data to generate a natural and vivid response to respond to the dialogue message", may be input to the question-answer processing model to instruct the question-answer processing model to combine the attribute data to generate a first answer message corresponding to the dialogue message.
According to the method and the device, related information of the target object can be quickly searched by querying the object knowledge base or the object information base, and the efficiency of generating the first response message is improved.
In some embodiments, determining the plurality of object instances of the target object may include identifying whether the dialog message is associated with the target object instance, if so, performing an operation of generating a first response message corresponding to the dialog message based on instance information corresponding to the target object instance, and if not, determining the plurality of object instances of the target object.
In some embodiments, there may be various implementations of identifying whether the dialogue message is associated with the target object instance, that is, as an alternative implementation, whether the dialogue message is associated with the target object instance may be determined by determining whether the service request carries an instance identifier, and if so, determining the target object instance corresponding to the instance identifier.
Wherein the service request may be generated in response to a selection operation for an object instance in the target object detail page and a triggering operation of the service hint information. Because the service request is generated when the target object instance is selected, the client request can carry the instance identifier of the target object instance.
For example, the object detail page may provide an attribute selection area in which a plurality of attribute parameter controls may be displayed, each of which may display parameter data for the attribute parameter, and so forth. The object instance selection operation may refer to a selection operation of at least one property parameter control corresponding to the target object instance.
As another alternative implementation, identifying whether the conversation message associates with the target object instance may be by determining whether the target object instance is involved in a history of the first conversation connection.
As yet another alternative implementation, it may be to identify descriptive keywords in the conversation message, and determine whether there is a target object instance whose attribute parameters match the descriptive keywords. For example, the description keyword in the dialogue message is a "light, thin and high-performance notebook", and the target object instance with the attribute parameter matched with the description keyword can be searched from multiple object instances of the target object according to the description keyword, for example, the target object is a notebook, and the searched target object instance matched with the "light, thin and high-performance notebook" is a notebook with "13 inches and 8GB memory". Thereby realizing personalized recommendation.
In some embodiments, generating the first response message corresponding to the dialogue message based on the instance information of the target object instance includes one or more of the following implementations:
As an alternative implementation manner, at least one question-answer knowledge pair corresponding to the target object instance can be searched for from the object knowledge base, a target question-answer knowledge pair matched with the dialogue message is identified from the at least one question-answer knowledge pair, and a first answer message corresponding to the dialogue message is generated based on answer data in the target question-answer knowledge pair.
The object knowledge base can correspondingly store the instance identifier of the object instance and at least one question-answer knowledge pair corresponding to the object instance, so that the at least one question-answer knowledge pair corresponding to the target object instance can be searched from the object knowledge base according to the instance identifier of the target object instance.
The instance identity of the target object instance upon which the query is based may be the instance identity carried in the service request described above,
The question-answer knowledge pair comprises answer data corresponding to the question data. And further, question data matched with the dialogue message can be determined from at least one question-answer knowledge pair, so that the question-answer knowledge pair to which the question data belongs is determined to be a target question-answer knowledge pair matched with the dialogue message, and a first answer message corresponding to the dialogue message is generated based on answer data in the target question-answer knowledge pair.
The method may determine the question data matched with the dialogue message from at least one question-answer knowledge pair by using a text matching manner, for example, the text similarity and/or semantic similarity between the question data in at least one question-answer knowledge pair and the dialogue message may be calculated, and the question data matched with the dialogue message may be determined. The application is not limited to the matching mode.
As another alternative implementation manner, object attribute information and instance attribute information corresponding to the target object instance may be searched for from the object information library, and the first answer message corresponding to the dialogue message is generated based on the object attribute information and the instance attribute information by using the question-answer processing model.
The object information base can store the object attribute information and the instance attribute information corresponding to the object instance, namely store the instance identifier of the object instance and the instance attribute information of the object instance, store the object identifier of the object to which the object instance belongs and the object attribute information, and store the instance identifier of the object instance and the object identifier of the object to which the object instance belongs in a correlated manner, so that the instance attribute information of the object instance and the object attribute information of the object to which the object instance belongs can be searched from the object attribute information base according to the instance identifier of the target object instance.
The object attribute information corresponding to the object instance may refer to object attribute information of an object to which the object instance belongs, where the object attribute information may include attribute information of an object dimension, and the like, and for example, the attribute information of the object dimension may include a category, a brand, and the like.
The instance attribute information corresponding to the object instance may include attribute information of an instance dimension of the object instance, and the attribute information of the instance dimension may include color, size, material, and the like.
Wherein instance attribute information for instance of the target object instance may include inventory quantity.
If the stock quantity of the target object examples is smaller than the preset quantity, at least one similar object example meeting the similarity requirement with the target object example can be inquired from the object information base, the question-answer processing model is utilized to generate recommendation prompt information based on the object attribute information and the example attribute information of the at least one similar object example, and the recommendation prompt information is used as a first response message. For example, object attribute information and instance attribute information of the target object instance may be calculated, and similarity with object attribute information and instance attribute information of other object instances may be calculated, and an object instance having a similarity greater than a similarity threshold may be used as at least one similar object instance. Under the condition of insufficient inventory of the target object instance, the object instance similar to the target object instance is recommended, inventory can be better managed, pre-sale shopping can be realized in a pre-sale scene, and the conversion rate and user experience of a user are improved.
As yet another alternative implementation manner, object attribute information and instance attribute information corresponding to the target object instance may be searched for from the object information library, whether attribute data matched with the dialogue message exists in the object attribute information and the instance attribute information is determined, and a first response message corresponding to the dialogue message is generated based on the attribute data.
In some embodiments, in order to perfect the object knowledge base, the method may further include generating a candidate question-answer knowledge pair corresponding to the target object instance based on the dialogue message and the first answer message, and storing the candidate question-answer knowledge pair corresponding to the instance identifier of the target object instance in the object knowledge base.
In addition, if the first answer message is a first answer message corresponding to the generated dialogue message based on the object information of the target object, a candidate question-answer knowledge pair corresponding to the target object may be generated based on the dialogue message and the first answer message, and the candidate question-answer knowledge pair and the object identifier of the target object are stored in the object knowledge base correspondingly.
According to the embodiment, the object knowledge base or the object information base can be queried to quickly search the related information of the target object instance, so that the efficiency of generating the first response message is improved.
In some embodiments, the method can further comprise responding to a service conversion request sent by the user side, sending a dialogue message and a first response message to the service providing side based on the second session connection, providing search prompt information to the service providing side, searching target information matched with the search keyword from the object information base and/or the object knowledge base based on the search keyword sent by the service providing side, and sending the target information to the service providing side.
The service providing end can face the manual service, and the service providing end can respond to the search keywords triggered by the manual service aiming at the search prompt information to send a search request to the service end.
The searching of the target information matched with the search keyword from the object information base and/or the object knowledge base by the service end based on the search keyword sent by the service providing end may be searching of the target information matched with the search keyword corresponding to the target object or the target object instance from the object information base and/or the object knowledge base according to the identified object identifier of the target object or the instance identifier of the target object instance and the search keyword sent by the service providing end.
Alternatively, the attribute data matching the search keyword may be searched for as the target information from the object attribute information and the instance attribute information of the target object or the target object instance of the object information base according to the object identification of the target object or the instance identification of the target object instance.
Alternatively, according to the object identification of the target object or the instance identification of the target object instance, the target question-answer knowledge pair matched with the search keyword can be searched from at least one question-answer knowledge pair corresponding to the target object or the target object instance in the object knowledge base, and response data in the target question-answer knowledge pair is used as target information.
Alternatively, information extraction such as removing redundant information in the two data may be performed based on attribute data of the search keyword matching and response data in the target question-answer knowledge pair, with the extracted information as target information.
The manual service may determine a second response message to the dialogue message according to the target information, for example, the service provider may determine the target information to be directly used as the second response message, or send the second response message to the server in response to the manual service determining that the updated target information is the second response message in response to the update operation of the target information.
The embodiment is beneficial to the user to transfer the manual service when the communication with the intelligent service is not smooth, and the coherent and effective communication experience is obtained. The service providing end can acquire the dialogue message and the first response message corresponding to the first dialogue connection, is favorable for the manual service to accurately and comprehensively grasp the user requirement, and the search prompt information is favorable for prompting the manual service to select the search keyword, so that the target information matched with the search keyword can be searched from the object information base and/or the object knowledge base, the manual service can be favorable for determining the second response message according to the target information, the user problem is accurately solved, the response efficiency of the manual service is improved, the communication efficiency of the manual service and the user is improved, and the user experience is improved.
In some embodiments, the method further comprises the steps of obtaining a second response message for the dialogue message sent by the service providing end based on the second session connection, generating a candidate question-answer knowledge pair corresponding to the target object instance based on the dialogue message and the second response message, and storing the candidate question-answer knowledge pair corresponding to the instance identification of the target object instance into the object knowledge base.
Candidate question-answer knowledge pairs formed by dialogue messages and second response messages of manual service responses can be saved to the object knowledge base.
In some embodiments, storing the candidate question-answer knowledge pairs in the object knowledge base in correspondence with the instance identifications of the target object instances may include sending the candidate question-answer knowledge pairs to a configurator, updating the candidate question-answer knowledge pairs in response to an update request triggered by the configurator, and storing the updated candidate question-answer knowledge pairs in the object knowledge base in correspondence with the instance identifications of the target object instances.
The candidate question-answer knowledge pair may be formed by a dialogue message and a first answer message, or may be formed by a dialogue message and a second answer message. The configurator can update dialogue messages, first response messages, second response messages and the like aiming at candidate question-answer knowledge pairs, for example, supplement the first response messages or the second response messages with imperfect information, modify the first response messages or the second response messages with error information and the like, so that accuracy of question-answer knowledge pairs stored in an object knowledge base is improved, and comprehensiveness and richness of the object knowledge base can be improved by adding new question-answer knowledge pairs into the object knowledge base.
It should be noted that, the technical solution of the embodiment of the present application is applicable to a network virtual environment, where the described user is generally referred to as a "virtual user", and a real user may register a user account in a server through a registration manner to obtain a user identity in the network environment. The same user account can log in to the server through different types of user terminals, so that the server can identify the same user.
The interaction operation between the server and the user can be realized based on the user account, and the corresponding data received or sent by the server to the user is realized based on the user account, so that the corresponding data is actually received or sent by the user corresponding to the user account to the server. In addition, communication and the like can be realized among users through user accounts. The user may refer to an individual, or may refer to an organization, such as an enterprise, and the present application is not particularly limited thereto.
For ease of understanding, fig. 3 shows a schematic view of scene interaction in a practical application according to an embodiment of the present application. As shown in fig. 3, the user terminal 301 and the service providing terminal 302 may respectively establish a connection with the service terminal 303 through a network.
The client 301 and the service provider 302 may be a browser, an APP (Application), or a web Application such as an H5 (HyperText Markup Language, 5 th edition of hypertext markup language) Application, or a light Application (also called an applet, a lightweight Application) or a cloud Application, etc., and the client 301 and the service provider 302 may be deployed in an electronic device, and need to run depending on the device or some APPs in the device. The electronic device may have a display screen and support information browsing, for example, may be a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc., and for ease of understanding, the user side 301 and the service provider side 302 are mainly shown in fig. 3 in a device image. Various other types of applications are also commonly deployed in electronic devices, such as human-machine conversation type applications, model training type applications, text processing type applications, web browser applications, shopping type applications, search type applications, instant messaging tools, mailbox clients, social platform software, and the like. The electronic device may be a device used by a user and having functions of calculation, internet surfing, communication and the like required by the user, for example, may be a mobile phone, a tablet computer, a personal computer, a wearable device and the like. An electronic device may generally include at least one processing component and at least one storage component. The electronic device may also include basic configurations such as a network card chip, an IO bus, an audio/video component, and the like, which is not limited in this aspect of the present application. Optionally, depending on the electronic device implementation, some peripheral devices may be included, such as a keyboard, mouse, stylus, printer, etc., as the application is not limited in this regard.
The server 303 may include a server that provides various services, such as a server that provides support for model training, a server that processes information sent by the client, and so on. It should be noted that, the server 303 may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. The server may also be a server of a distributed system or a server that incorporates a blockchain. The server may also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.
The server 303 may obtain a dialogue message sent by the client 301 based on the first session connection, identify a target object or a target object instance associated with the dialogue message, search object information of the target object or instance information of the target object from the object knowledge base 304 and/or the object information base 305, generate a first response message corresponding to the dialogue message, and send the first response message to the client 301 based on the first session connection.
The server 303 may send the dialogue message and the first response message to the service provider 302 based on the second session connection in response to the service conversion request sent by the client 301, obtain the second response message for the service request message sent by the service provider 302 based on the second session connection, and send the second response message to the client 301 based on the first session connection.
Referring specifically to the service providing flow diagram shown in fig. 4, the server 303 may perform step 401 of acquiring a session message sent by the user based on the first session connection, and perform step 402 of identifying whether the session message is associated with the target object.
After executing step 402, if the dialogue message does not associate with the target object, executing step 403 to determine at least one object according to the historical interaction data corresponding to the user side, further executing step 404 to provide second selection prompt information for at least one object to the user side, further executing step 405 to determine the selected target object in response to the second selection request triggered by the second selection prompt information, and further executing step 406 to determine whether the acquisition requirement of the target object instance exists based on the object information of the target object and the dialogue message.
After step 402 is performed, if the dialogue message is associated with the target object, step 406 is performed directly.
After execution of step 406, if there is a need for acquisition of the target object instance, execution of step 407 identifies whether the dialog message is associated with the target object instance.
After executing step 407, if the dialogue message does not associate with the target object instance, executing step 408, determining a plurality of object instances of the target object, further executing step 409, providing first selection prompt information for the plurality of object instances to the user side, further executing step 410, determining the selected target object instance in response to a first selection request triggered by the first selection prompt information, further executing step 411, obtaining instance information corresponding to the target object instance, further executing step 412, generating a first response message corresponding to the dialogue message based on the instance information corresponding to the target object instance, and sending the first response message to the user side based on the first session connection.
After step 407, if the dialog message is associated with the target object instance, step 411 is directly performed.
After executing step 406, if there is no acquisition requirement of the target object instance, executing step 413 to acquire object information of the target object, and executing step 414 to generate a first response message corresponding to the dialogue message based on the object information of the target object, and sending the first response message to the user terminal based on the first dialogue connection.
In addition, after step 414 is performed and after step 412 is performed, step 415 may be performed of generating a candidate question-answer knowledge pair corresponding to the target object instance based on the dialogue message and the first answer message, and saving the candidate question-answer knowledge pair corresponding to the instance identification of the target object instance to the object knowledge base.
In addition, after performing step 414 and after performing step 412, the server 303 may respond to the service conversion request sent by the client 301, and may further perform step 416 of sending a session message and a first response message to the service provider 302 based on the second session connection.
According to the embodiment, the server side can provide a selection function of the object instance for the user under the condition that the identification dialogue message is not related to the target object or the target object instance through multiple identification judgment, so that the user can accurately select the target object instance, and further the server side can generate a targeted and accurate response message based on the instance information of the target object instance, thereby providing more accurate intelligent service, improving communication efficiency and guaranteeing user experience. In the pre-sales service scene, the interaction desire of the user can be improved, and the object conversion rate is improved.
Fig. 5 is a flowchart of an embodiment of an information configuration method provided in the present application, where the method may include the following steps:
501, acquiring a question-answer knowledge pair provided by a configurator.
Wherein, alternatively, the question-answer knowledge pairs provided by the configurator may be updated by the candidate question-answer knowledge pairs in the embodiment of fig. 1. Alternatively, the configurator may also directly provide the question-answer knowledge pairs.
At 502, at least one object and/or at least one object instance set by a configurator for a question-answer knowledge pair is determined.
Wherein the same question-answer knowledge pair may be applicable to a plurality of objects and/or object instances, and thus may be the corresponding at least one object and/or at least one object instance of the question-answer knowledge pair setting.
And 503, storing the object identification of at least one object corresponding to the question-answer knowledge pair and/or the instance identification of at least one object instance to the object knowledge base.
The method comprises the steps of determining at least one question-answer knowledge pair corresponding to a target object or a target object instance associated with a dialogue message in an object knowledge base, determining a target question-answer pair matched with the dialogue message by the at least one question-answer knowledge pair, and generating a response message corresponding to the dialogue message by response data in the target question-answer pair.
The object knowledge base may be used to find at least one question-answer knowledge pair for a target object based on the object identification or for a target object instance based on the instance identification.
The specific explanation of the target object or the target object instance and the generation manner of the response message can be described in detail in the embodiment shown in fig. 1.
In this embodiment, the question-answer knowledge pair provided by the configurator and at least one object and/or at least one object instance set for the question-answer knowledge pair may be saved to the object knowledge base, so as to perfect the object knowledge base, so that when a dialogue message is obtained, a response message is generated by quickly searching for matched response data based on the object knowledge base, and communication efficiency is improved.
In some embodiments, obtaining a question and answer knowledge pair provided by a configurator, determining at least one object and/or at least one object instance set by the configurator for the question and answer knowledge pair may include providing a configuration interface, determining the question and answer knowledge pair provided by the configurator in response to a configuration request, and at least one object and/or at least one object instance set for the question and answer knowledge pair.
For ease of understanding, fig. 6 shows a schematic display of a configuration interface in one practical application, in which a question data configuration prompt 601, an object/object instance configuration prompt 602, and a response data configuration prompt 603 may be displayed in the configuration interface 600. The question data configuration prompt information 601 includes a question data input box, a configurator can input question data to be configured in the question input box, the object/object instance configuration prompt information 602 includes an identification input box, a configurator can input an identification of an object/object instance in the identification input box, and the like, the response data configuration prompt information 603 includes an editing area, and the configurator can input response data in the editing area.
Fig. 7 is a flowchart of an embodiment of an information display method provided by the present application, where the technical solution of the present embodiment may be executed by a service provider, and the method may include the following steps:
701 providing a service session interface in a user interface.
The service session interface is determined based on the second session connection corresponding to the service providing end.
702, Based on the second session connection, acquiring a dialogue message and a first response message corresponding to the first session connection;
703 displaying the dialogue message and the first response message in the service session interface.
And 704, displaying search prompt information in a user interface.
And 705, sending a search request to the service end based on the search keyword triggered by the search prompt information so that the service end can search target information matched with the search keyword from an object information base and/or an object knowledge base based on the search keyword sent by the service providing end and a target object or a target object instance related to the dialogue message, wherein the object knowledge base is used for storing at least one question-answer knowledge pair respectively corresponding to the object and/or the object instance, and the object information base is used for storing object attribute information and instance attribute information respectively corresponding to the object and/or the object instance.
The specific search process may be described in detail in the embodiment shown in fig. 1.
706, Displaying the target information in the user interface.
A schematic display of a user interface in one practical application is shown in fig. 8 for ease of understanding.
For example, the user interface 800 may include search prompt information 801, such as "origin introduction component material capacity specification version type", to prompt the manual service to select a search keyword, for example, the service provider may send a search request to the service provider in response to a trigger operation of the manual service for "origin introduction", and the service provider may search the object information base and/or the object knowledge base for target information, such as "origin XX", matching the "origin introduction" based on the search keyword "origin introduction", and send the target information to the service provider for the service provider to display the target information 802 in the user interface.
According to the embodiment, the acquired first session is connected with the corresponding dialogue message and the first response message, so that the user demand can be accurately and comprehensively mastered by the manual service, the search prompt information is displayed, the manual service is prompted to select the search keyword, the server side searches the target information matched with the search keyword from the object information base and/or the object knowledge base and displays the target information, the manual service is helped to determine the second response message according to the target information, the response efficiency of the manual service is improved, the communication efficiency of the manual service and the user is improved, and the user experience can be improved.
The detailed implementation and the beneficial effects of each step in the method of this embodiment have been described in the foregoing embodiments, and will not be described in detail herein.
It should be noted that, in some of the above embodiments and the flows described in the drawings, a plurality of operations appearing in a specific order are included, but it should be clearly understood that the operations may be performed out of the order in which they appear herein or performed in parallel, the sequence numbers of the operations such as 701, 702, etc. are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any execution sequence. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
Fig. 9 is a schematic structural diagram of an embodiment of a service providing apparatus according to an embodiment of the present application, where the apparatus includes:
A first obtaining module 901, configured to obtain a session message sent by a user terminal based on a first session connection, where the first session connection is established based on a service request sent by the user terminal;
An identification module 902 for identifying a target object associated with the dialogue message and determining a plurality of object instances of the target object;
A first providing module 903, configured to provide first selection prompt information for a plurality of object instances to a user;
a first determining module 904 that determines the selected target object instance in response to a first selection request triggered for the first selection hint information;
The generating module 905 generates a first response message corresponding to the dialogue message based on the instance information corresponding to the target object instance;
the first sending module 906 sends the first response message to the user terminal based on the first session connection.
In some embodiments, the identification module identifies a target object associated with the dialogue message and determines a plurality of object instances of the target object may include identifying whether the dialogue message is associated with the target object, if so, determining a plurality of object instances of the target object, if not, determining at least one object according to historical interaction data corresponding to the user terminal, providing second selection prompt information for the at least one object to the user terminal, and determining the selected target object in response to a second selection request triggered by the second selection prompt information.
In some embodiments, there are a number of implementations for identifying whether a conversation message is associated with a target object:
As an optional implementation manner, whether the service request carries the object identifier or not may be judged, if yes, a target object corresponding to the object identifier is determined. Wherein the service request may be generated in response to a triggering operation for the service hint information in the target object detail page. Thus, the service request may carry the object identification of the target object.
As another alternative implementation, it may be determined whether the target object is involved in the history of the first session connection.
In some embodiments, the identifying module determines a plurality of object instances of the target object may include determining whether an acquisition requirement of the target object instance exists based on object information of the target object and a dialogue message, if so, determining the plurality of object instances of the target object, and if not, generating a first response message corresponding to the dialogue message based on the object information of the target object.
In some embodiments, the generating module generates the first response message corresponding to the dialogue message based on the object information of the target object, where the generating module includes one or more of the following implementations:
As an alternative implementation manner, at least one question-answer knowledge pair corresponding to the target object can be searched for from the object knowledge base, the target question-answer knowledge pair matched with the dialogue message is identified from the at least one question-answer knowledge pair, and a first answer message corresponding to the dialogue message is generated based on answer data in the target question-answer knowledge pair;
As another alternative implementation manner, object attribute information and instance attribute information corresponding to the target object may be searched from the object information library, and the first answer message corresponding to the dialogue message is generated based on the object attribute information and the instance attribute information by using the question-answer processing model.
As yet another alternative implementation manner, the object attribute information and the instance attribute information corresponding to the target object may be searched from the object information base, whether attribute data matched with the dialogue message exists in the object attribute information and the instance attribute information is determined, and the first response message corresponding to the dialogue message is generated based on the attribute data.
In some embodiments, the identifying module determines whether the plurality of object instances of the target object may include identifying whether the dialogue message is associated with the target object instance, if so, performing an operation of generating a first response message corresponding to the dialogue message based on instance information corresponding to the target object instance, and if not, determining the plurality of object instances of the target object.
In some embodiments, there are a number of implementations for identifying whether a conversation message is associated with a target object instance:
as an alternative implementation manner, whether the dialogue message is associated with the target object instance can be identified by judging whether the service request carries an instance identifier, if so, determining the target object instance corresponding to the instance identifier.
As another alternative implementation, identifying whether the conversation message associates with the target object instance may be by determining whether the target object instance is involved in a history of the first conversation connection.
As yet another alternative implementation, it may be to identify descriptive keywords in the conversation message and determine whether there is a target object whose attribute parameters match the descriptive keywords.
In some embodiments, the generating module generates the first response message corresponding to the dialogue message based on the instance information of the target object instance, including one or more of the following implementations:
As an alternative implementation manner, at least one question-answer knowledge pair corresponding to the target object instance can be searched for from the object knowledge base, a target question-answer knowledge pair matched with the dialogue message is identified from the at least one question-answer knowledge pair, and a first answer message corresponding to the dialogue message is generated based on answer data in the target question-answer knowledge pair.
As another alternative implementation manner, object attribute information and instance attribute information corresponding to the target object instance may be searched for from the object information library, and the first answer message corresponding to the dialogue message is generated based on the object attribute information and the instance attribute information by using the question-answer processing model.
As yet another alternative implementation manner, object attribute information and instance attribute information corresponding to the target object instance may be searched for from the object information library, whether attribute data matched with the dialogue message exists in the object attribute information and the instance attribute information is determined, and a first response message corresponding to the dialogue message is generated based on the attribute data.
In some embodiments, to refine the object knowledge base, the apparatus may further include:
the first storage module is used for generating a candidate question-answer knowledge pair corresponding to the target object instance based on the dialogue message and the first response message, and storing the candidate question-answer knowledge pair corresponding to the instance identification of the target object instance into the object knowledge base.
In some embodiments, the apparatus may further comprise:
The service conversion module is used for responding to a service conversion request sent by the user terminal, sending the dialogue message and the first response message to the service providing terminal based on the second session connection, providing search prompt information for the service providing terminal, searching target information matched with the search keyword from the object information base and/or the object knowledge base based on the search keyword sent by the service providing terminal, and sending the target information to the service providing terminal.
In some embodiments, the first storage module may be further configured to obtain a second response message for the dialogue message sent by the service provider based on the second session connection, generate a candidate question-answer knowledge pair corresponding to the target object instance based on the dialogue message and the second response message, and store the candidate question-answer knowledge pair and the instance identifier of the target object instance in the object knowledge base.
In some embodiments, storing the candidate question-answer knowledge pairs in the object knowledge base in correspondence with the instance identifications of the target object instances may include sending the candidate question-answer knowledge pairs to a configurator, updating the candidate question-answer knowledge pairs in response to an update request triggered by the configurator, and storing the updated candidate question-answer knowledge pairs in the object knowledge base in correspondence with the instance identifications of the target object instances.
The service providing apparatus shown in fig. 9 may perform the service providing method described in the embodiment shown in fig. 1, and its implementation principle and technical effects are not repeated. The specific manner in which the respective modules and units of the service providing apparatus in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail herein.
Fig. 10 is a schematic structural diagram of an embodiment of an information configuration apparatus according to an embodiment of the present application, where the apparatus includes:
a second obtaining module 1001, configured to obtain a question-answer knowledge pair provided by a configurator;
A second determining module 1002, configured to determine at least one object and/or at least one object instance set by a configurator for a question-answer knowledge pair;
A second saving module 1002, configured to save the object identifier of at least one object and/or the instance identifier of at least one object instance corresponding to the question-answer knowledge pair to the object knowledge base.
The method comprises the steps of determining at least one question-answer knowledge pair corresponding to a target object or a target object instance associated with a dialogue message in an object knowledge base, determining a target question-answer pair matched with the dialogue message by the at least one question-answer knowledge pair, and generating a response message corresponding to the dialogue message by response data in the target question-answer pair.
In some embodiments, obtaining a question and answer knowledge pair provided by a configurator, determining at least one object and/or at least one object instance set by the configurator for the question and answer knowledge pair may include providing a configuration interface, determining the question and answer knowledge pair provided by the configurator in response to a configuration request, and at least one object and/or at least one object instance set for the question and answer knowledge pair.
The information configuration apparatus shown in fig. 10 may perform the information configuration method described in the embodiment shown in fig. 5, and its implementation principle and technical effects are not repeated. The specific manner in which the respective modules, units, and operations of the information configuration apparatus in the above embodiments are performed has been described in detail in the embodiments related to the method, and will not be described in detail here.
Fig. 11 is a schematic structural diagram of an embodiment of an information display device according to an embodiment of the present application, where the device includes:
a second providing module 701 for providing a service session interface in a user interface;
The service session interface is determined based on the second session connection corresponding to the service providing end;
A third obtaining module 1102, configured to obtain, based on the second session connection, a dialogue message and a first response message corresponding to the first session connection;
A first display module 1103, configured to display a dialogue message and a first response message in a service session interface;
A second display module 1104 for displaying search prompt information in the user interface;
The second sending module 1105 is configured to send a search request to the server based on a search keyword triggered by the search prompt information, so that the server searches for target information matched with the search keyword from an object information base and/or an object knowledge base based on the search keyword sent by the service provider and a target object or a target object instance associated with the dialogue message, where the object knowledge base is configured to store at least one question-answer knowledge pair corresponding to the object and/or the object instance, respectively;
A third display module 1106 for displaying the target information in the user interface.
The information display device shown in fig. 11 may perform the information display method described in the embodiment shown in fig. 7, and its implementation principle and technical effects are not repeated. The specific manner in which the respective modules, units, and operations of the information display apparatus in the above embodiments are performed has been described in detail in the embodiments related to the method, and will not be described in detail here.
FIG. 12 is a schematic diagram illustrating one embodiment of a computing device. As shown in FIG. 12, in practice, the computing device may include a storage component 1201 and a processing component 1202.
A storage component 1201 is used to store a computer program and may be configured to store various other data to support operations on a computing device. Examples of such data include instructions, data structures, contact data, phonebook data, messages, pictures, videos, etc. for any application or method operating on the computing device.
A processing unit 1202 coupled to the storage unit 1201 for executing a computer program in the storage unit 1201 for implementing the service providing method as described in the embodiment shown in fig. 1 or the information configuring method as described in the embodiment shown in fig. 5.
Further, as shown in FIG. 12, the computing device may also include other components such as a communication component 1203, a display component 1204, a power supply component 1205, an audio component 1206, and so forth. Only some of the components are schematically shown in fig. 12, which does not mean that the computing device only includes the components shown in fig. 12. In addition, the components within the dashed box in FIG. 12 are optional components, not necessarily components, depending on the product form of the particular computing device. The computing device of the embodiment may be implemented as a terminal device such as a desktop computer, a notebook computer, a smart phone, or an IOT (internet of things) device, or may be a server device such as a conventional server, a cloud server, or a server array. If the computing device of the embodiment is implemented as a terminal device such as a desktop computer, a notebook computer, or a smart phone, the computing device may include the components in the dashed-line box in fig. 12, and if the computing device of the embodiment is implemented as a server device such as a conventional server, a cloud server, or a server array, the computing device of the embodiment may not include the components in the dashed-line box in fig. 12.
The processing assembly includes one or more processors executing computer instructions to perform all or part of the steps of the methods described above. Of course, the processing component may also be implemented as one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for executing the methods described above.
The Memory components described above may be implemented by any type or combination of volatile or non-volatile Memory devices, such as Static Random-Access Memory (SRAM), electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY, EEPROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The communication component is configured to facilitate wired or wireless communication between the device in which the communication component is located and other devices. The device in which the communication component is located may access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In one exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.
The display assembly may include a screen, which may include a Liquid crystal display (Liquid CRYSTALDISPLAY, LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or sliding action, but also the duration and pressure associated with the touch or sliding operation.
The power supply component provides power for various components of equipment where the power supply component is located. The power components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the devices in which the power components are located.
The audio component described above may be configured to output and/or input an audio signal. For example, the audio component includes a Microphone (MIC) configured to receive external audio signals when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may be further stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals.
Accordingly, embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to implement the steps of the method embodiments described above. Wherein the computer-readable storage medium includes volatile or nonvolatile or a combination thereof implementations, which may be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change Memory (Phase-change Random Access Memory, PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (Dynamic Random Access Memory, DRAM), other types of Random Access Memory (RAM), read-only Memory (ROM), electrically erasable programmable read-only Memory (EEPROM), erasable programmable read-only Memory (EPROM), programmable read-only Memory (PROM), flash Memory or other Memory technology, compact disc read-only Memory (CD-ROM), digital versatile disc (DigitalVideo Disc, DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission media
Accordingly, embodiments of the present application also provide a computer program product comprising a computer program or instructions which, when executed by a processor, cause the processor to carry out the steps of the above-described method embodiments. It should be understood that each of the above-described method flows or a combination of flows may be implemented by a computer program or instructions. In addition, these computer programs or instructions may be applied to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus, such that the processor of the general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus is implemented as a device that performs the corresponding functions in the above described method embodiments.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
Finally, it should be noted that the above is only an example of the application and is not intended to limit the application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.